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.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com

--- 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 | 55 +++++++++++++++++++++++++++++++++++++++++++++ include/net/net_namespace.h | 4 ++++ include/net/netns/vsock.h | 20 +++++++++++++++++ 4 files changed, 80 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS index 47bc35743f22..bc53c67e0926 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -26634,6 +26634,7 @@ 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..2857e97699de 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 orig_net_mode;

/* Protected by lock_sock(sk) */ u64 buffer_size; @@ -256,4 +258,57 @@ 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.written) { + ret = false; + goto skip; + } + + net->vsock.mode = mode; + net->vsock.written = true; + ret = true; + +skip: + spin_unlock_bh(&net->vsock.lock); + return ret; +} + +/* Return true if vsock_sock passes the mode rules for a given net and + * orig_net_mode. Otherwise, return false. + * + * net is the current net namespace of the object being checked. orig_net_mode + * is the mode of net when the object was created. + * + * orig_net_mode is the mode of arg 'net' at the time of creation for the + * object being checked. For example, if searching for a vsock_sock then + * orig_net_mode is arg net's mode at the time the vsock_sock was created. + * + * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c. + */ +static inline bool vsock_net_check_mode(struct vsock_sock *vsk, struct net *net, + enum vsock_net_mode orig_net_mode) +{ + struct net *vsk_net = sock_net(sk_vsock(vsk)); + + if (net_eq(vsk_net, net)) + return true; + + return orig_net_mode == VSOCK_NET_MODE_GLOBAL && vsk->orig_net_mode == VSOCK_NET_MODE_GLOBAL; +} #endif /* __AF_VSOCK_H__ */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 025a7574b275..005c0da4fb62 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..d4593c0b8dc4 --- /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 *vsock_hdr; + spinlock_t lock; + + /* protected by lock */ + enum vsock_net_mode mode; + bool written; +}; +#endif /* __NET_NET_NAMESPACE_VSOCK_H */

From: Bobby Eshleman bobbyeshleman@meta.com

Add netns to 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".

Introduce a dummy namespace struct, __vsock_global_dummy_net, to be used by transports that do not support namespacing. This dummy always has mode "global" to preserve previous CID behavior.

This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode that accepts the "global" or "local" mode strings.

The transports (besides vhost) are modified to use the global dummy.

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.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com

--- 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 --- drivers/vhost/vsock.c | 4 +- include/net/af_vsock.h | 15 ++- net/vmw_vsock/af_vsock.c | 219 ++++++++++++++++++++++++++++++-- net/vmw_vsock/hyperv_transport.c | 2 +- net/vmw_vsock/virtio_transport.c | 6 +- net/vmw_vsock/virtio_transport_common.c | 4 +- net/vmw_vsock/vmci_transport.c | 6 +- net/vmw_vsock/vsock_loopback.c | 4 +- 8 files changed, 234 insertions(+), 26 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index ae01457ea2cd..34adf0cf9124 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -404,7 +404,7 @@ 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 +460,7 @@ 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 2857e97699de..628e35ae9d00 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. */ @@ -215,9 +215,12 @@ void vsock_enqueue_accept(struct sock *listener, struct sock *connected); void vsock_insert_connected(struct vsock_sock *vsk); void vsock_remove_bound(struct vsock_sock *vsk); void vsock_remove_connected(struct vsock_sock *vsk); -struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); +struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr, struct net *net, + enum vsock_net_mode orig_net_mode); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst); + struct sockaddr_vm *dst, + struct net *net, + enum vsock_net_mode orig_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)); @@ -259,6 +262,12 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t) return t->msgzerocopy_allow && t->msgzerocopy_allow(); }

+extern struct net __vsock_global_dummy_net; +static inline struct net *vsock_global_dummy_net(void) +{ + return &__vsock_global_dummy_net; +} + static inline enum vsock_net_mode vsock_net_mode(struct net *net) { enum vsock_net_mode ret; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 0538948d5fd9..c78aba9cd20e 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -83,6 +83,35 @@ * 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. */

#include <linux/compat.h> @@ -100,6 +129,7 @@ #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 +141,14 @@ #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" +#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); @@ -149,6 +184,9 @@ static const struct vsock_transport *transport_dgram; static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex);

+struct net __vsock_global_dummy_net; +EXPORT_SYMBOL_GPL(__vsock_global_dummy_net); + /**** UTILS ****/

/* Each bound VSocket is stored in the bind hash table and each connected @@ -235,17 +273,21 @@ 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(struct sockaddr_vm *addr, + struct net *net, + enum vsock_net_mode orig_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)) + if (vsock_addr_equals_addr(addr, &vsk->local_addr) && + vsock_net_check_mode(vsk, net, orig_net_mode)) return sk_vsock(vsk);

if (addr->svm_port == vsk->local_addr.svm_port && (vsk->local_addr.svm_cid == VMADDR_CID_ANY || - addr->svm_cid == VMADDR_CID_ANY)) + addr->svm_cid == VMADDR_CID_ANY) && + vsock_net_check_mode(vsk, net, orig_net_mode)) return sk_vsock(vsk); }

@@ -253,14 +295,17 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) }

static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst) + struct sockaddr_vm *dst, + struct net *net, + enum vsock_net_mode orig_net_mode) { struct vsock_sock *vsk;

list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { if (vsock_addr_equals_addr(src, &vsk->remote_addr) && - dst->svm_port == vsk->local_addr.svm_port) { + dst->svm_port == vsk->local_addr.svm_port && + vsock_net_check_mode(vsk, net, orig_net_mode)) { return sk_vsock(vsk); } } @@ -304,12 +349,13 @@ 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(struct sockaddr_vm *addr, struct net *net, + enum vsock_net_mode orig_net_mode) { struct sock *sk;

spin_lock_bh(&vsock_table_lock); - sk = __vsock_find_bound_socket(addr); + sk = __vsock_find_bound_socket(addr, net, orig_net_mode); if (sk) sock_hold(sk);

@@ -320,12 +366,14 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) EXPORT_SYMBOL_GPL(vsock_find_bound_socket);

struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst) + struct sockaddr_vm *dst, + struct net *net, + enum vsock_net_mode orig_net_mode) { struct sock *sk;

spin_lock_bh(&vsock_table_lock); - sk = __vsock_find_connected_socket(src, dst); + sk = __vsock_find_connected_socket(src, dst, net, orig_net_mode); if (sk) sock_hold(sk);

@@ -528,7 +576,7 @@ 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 +724,7 @@ 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 +744,8 @@ 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(&new_addr, net, + vsk->orig_net_mode)) { found = true; break; } @@ -712,7 +762,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, return -EACCES; }

- if (__vsock_find_bound_socket(&new_addr)) + if (__vsock_find_bound_socket(&new_addr, net, + vsk->orig_net_mode)) return -EADDRINUSE; }

@@ -2552,6 +2603,7 @@ static int vsock_create(struct net *net, struct socket *sock, return -ENOMEM;

vsk = vsock_sk(sk); + vsk->orig_net_mode = vsock_net_mode(net);

if (sock->type == SOCK_DGRAM) { ret = vsock_assign_transport(vsk, NULL); @@ -2636,6 +2688,139 @@ 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); + + if (mode == VSOCK_NET_MODE_GLOBAL) { + p = VSOCK_NET_MODE_STR_GLOBAL; + } else if (mode == VSOCK_NET_MODE_LOCAL) { + p = VSOCK_NET_MODE_STR_LOCAL; + } else { + 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) { + 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.vsock_hdr = register_net_sysctl_sz(net, "net/vsock", table, + ARRAY_SIZE(vsock_table)); + if (!net->vsock.vsock_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.vsock_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->vsock.vsock_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static void vsock_net_init(struct net *net) +{ + spin_lock_init(&net->vsock.lock); + 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 +2848,19 @@ 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_net_init(vsock_global_dummy_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 +2874,7 @@ 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..79bc55eeecb3 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -313,7 +313,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) return;

hvs_addr_init(&addr, conn_from_host ? if_type : if_instance); - sk = vsock_find_bound_socket(&addr); + sk = vsock_find_bound_socket(&addr, vsock_global_dummy_net()); if (!sk) return;

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index b6569b0ca2bb..4626ba0428ef 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -536,7 +536,7 @@ 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 +593,7 @@ 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; @@ -659,6 +659,8 @@ static void virtio_transport_rx_work(struct work_struct *work) if (payload_len) virtio_vsock_skb_put(skb, payload_len);

+ virtio_vsock_skb_set_net(skb, vsock_global_dummy_net()); + virtio_vsock_skb_set_orig_net_mode(skb, VSOCK_NET_MODE_GLOBAL); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&virtio_transport, skb); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index dcc8a1d5851e..1a9129e33d51 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1606,9 +1606,9 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, /* The socket must be in connected or bound table * otherwise send reset back */ - sk = vsock_find_connected_socket(&src, &dst); + sk = vsock_find_connected_socket(&src, &dst, vsock_global_dummy_net()); if (!sk) { - sk = vsock_find_bound_socket(&dst); + sk = vsock_find_bound_socket(&dst, vsock_global_dummy_net()); if (!sk) { (void)virtio_transport_reset_no_sock(t, skb); goto free_pkt; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 7eccd6708d66..aa0cd2efe561 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -703,9 +703,11 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port);

- sk = vsock_find_connected_socket(&src, &dst); + sk = vsock_find_connected_socket(&src, &dst, vsock_global_dummy_net(), + VSOCK_NET_MODE_GLOBAL); if (!sk) { - sk = vsock_find_bound_socket(&dst); + sk = vsock_find_bound_socket(&dst, vsock_global_dummy_net(), + VSOCK_NET_MODE_GLOBAL); if (!sk) { /* We could not find a socket for this specified * address. If this packet is a RST, we just drop it. diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 6e78927a598e..1b2fab73e0d0 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -46,7 +46,7 @@ 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 +106,7 @@ 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; }

From: Bobby Eshleman bobbyeshleman@meta.com

Add support to the virtio-vsock common code for passing around net namespace pointers (tx and rx). The series still requires vhost/virtio transport support to be added by future patches.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport_common.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index ea955892488a..165157580cb8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -196,6 +196,7 @@ struct virtio_vsock_pkt_info { u32 remote_cid, remote_port; struct vsock_sock *vsk; struct msghdr *msg; + struct net *net; u32 pkt_len; u16 type; u16 op; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 1a9129e33d51..8a08a5103e7c 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -316,6 +316,11 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info * info->flags, zcopy);

+ virtio_vsock_skb_set_net(skb, info->net); + + if (vsk) + virtio_vsock_skb_set_orig_net_mode(skb, vsk->orig_net_mode); + return skb; out: kfree_skb(skb); @@ -527,6 +532,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

return virtio_transport_send_pkt_info(vsk, &info); @@ -1067,6 +1073,7 @@ int virtio_transport_connect(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

return virtio_transport_send_pkt_info(vsk, &info); @@ -1082,6 +1089,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) (mode & SEND_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_SEND : 0), .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

return virtio_transport_send_pkt_info(vsk, &info); @@ -1108,6 +1116,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, .msg = msg, .pkt_len = len, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

return virtio_transport_send_pkt_info(vsk, &info); @@ -1145,6 +1154,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk, .op = VIRTIO_VSOCK_OP_RST, .reply = !!skb, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

/* Send RST only if the original pkt is not a RST pkt */ @@ -1165,6 +1175,7 @@ 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, + .net = virtio_vsock_skb_net(skb), }; struct sk_buff *reply;

@@ -1465,6 +1476,7 @@ virtio_transport_send_response(struct vsock_sock *vsk, .remote_port = le32_to_cpu(hdr->src_port), .reply = true, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), };

return virtio_transport_send_pkt_info(vsk, &info); @@ -1578,7 +1590,9 @@ static bool virtio_transport_valid_type(u16 type) void virtio_transport_recv_pkt(struct virtio_transport *t, struct sk_buff *skb) { + enum vsock_net_mode orig_net_mode = virtio_vsock_skb_orig_net_mode(skb); struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); + struct net *net = virtio_vsock_skb_net(skb); struct sockaddr_vm src, dst; struct vsock_sock *vsk; struct sock *sk; @@ -1606,9 +1620,9 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, /* The socket must be in connected or bound table * otherwise send reset back */ - sk = vsock_find_connected_socket(&src, &dst, vsock_global_dummy_net()); + sk = vsock_find_connected_socket(&src, &dst, net, orig_net_mode); if (!sk) { - sk = vsock_find_bound_socket(&dst, vsock_global_dummy_net()); + sk = vsock_find_bound_socket(&dst, net, orig_net_mode); if (!sk) { (void)virtio_transport_reset_no_sock(t, skb); goto free_pkt;

From: Bobby Eshleman bobbyeshleman@meta.com

Improve logging by adding configurable log levels. Additionally, improve usability of logging functions. Remove the test name prefix from logging functions so that logging calls can be made deeper into the call stack without passing down the test name or setting some global. Teach log function to accept a LOG_PREFIX variable to avoid unnecessary argument shifting.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 75 ++++++++++++++++----------------- 1 file changed, 37 insertions(+), 38 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index edacebfc1632..183647a86c8a 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -51,7 +51,12 @@ readonly TEST_DESCS=( "Run vsock_test using the loopback transport in the VM." )

-VERBOSE=0 +readonly LOG_LEVEL_DEBUG=0 +readonly LOG_LEVEL_INFO=1 +readonly LOG_LEVEL_WARN=2 +readonly LOG_LEVEL_ERROR=3 + +VERBOSE="${LOG_LEVEL_WARN}"

usage() { local name @@ -196,7 +201,7 @@ vm_start() {

qemu=$(command -v "${QEMU}")

- if [[ "${VERBOSE}" -eq 1 ]]; then + if [[ ${VERBOSE} -le ${LOG_LEVEL_DEBUG} ]]; then verbose_opt="--verbose" logfile=/dev/stdout fi @@ -271,60 +276,56 @@ EOF

host_wait_for_listener() { wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" -} - -__log_stdin() { - cat | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' -}

-__log_args() { - echo "$*" | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' }

log() { - local prefix="$1" + local redirect + local prefix

- shift - local redirect= - if [[ ${VERBOSE} -eq 0 ]]; then + if [[ ${VERBOSE} -gt ${LOG_LEVEL_INFO} ]]; then redirect=/dev/null else redirect=/dev/stdout fi

+ prefix="${LOG_PREFIX:-}" + if [[ "$#" -eq 0 ]]; then - __log_stdin | tee -a "${LOG}" > ${redirect} + if [[ -n "${prefix}" ]]; then + cat | awk -v prefix="${prefix}" '{printf "%s: %s\n", prefix, $0}' + else + cat + fi else - __log_args "$@" | tee -a "${LOG}" > ${redirect} - fi + if [[ -n "${prefix}" ]]; then + echo "${prefix}: " "$@" + else + echo "$@" + fi + fi | tee -a "${LOG}" > ${redirect} }

-log_setup() { - log "setup" "$@" +log_host() { + LOG_PREFIX=host log $@ }

-log_host() { - local testname=$1 +log_guest() { + LOG_PREFIX=guest log $@ +}

- shift - log "test:${testname}:host" "$@" }

-log_guest() { - local testname=$1

- shift - log "test:${testname}:guest" "$@" }

test_vm_server_host_client() { - local testname="${FUNCNAME[0]#test_}"

vm_ssh -- "${VSOCK_TEST}" \ --mode=server \ --control-port="${TEST_GUEST_PORT}" \ --peer-cid=2 \ - 2>&1 | log_guest "${testname}" & + 2>&1 | log_guest &

vm_wait_for_listener "${TEST_GUEST_PORT}"

@@ -332,18 +333,17 @@ test_vm_server_host_client() { --mode=client \ --control-host=127.0.0.1 \ --peer-cid="${VSOCK_CID}" \ - --control-port="${TEST_HOST_PORT}" 2>&1 | log_host "${testname}" + --control-port="${TEST_HOST_PORT}" 2>&1 | log_host

return $? }

test_vm_client_host_server() { - local testname="${FUNCNAME[0]#test_}"

${VSOCK_TEST} \ --mode "server" \ --control-port "${TEST_HOST_PORT_LISTENER}" \ - --peer-cid "${VSOCK_CID}" 2>&1 | log_host "${testname}" & + --peer-cid "${VSOCK_CID}" 2>&1 | log_host &

host_wait_for_listener

@@ -351,19 +351,18 @@ test_vm_client_host_server() { --mode=client \ --control-host=10.0.2.2 \ --peer-cid=2 \ - --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest "${testname}" + --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest

return $? }

test_vm_loopback() { - local testname="${FUNCNAME[0]#test_}" local port=60000 # non-forwarded local port

vm_ssh -- "${VSOCK_TEST}" \ --mode=server \ --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" & + --peer-cid=1 2>&1 | log_guest &

vm_wait_for_listener "${port}"

@@ -371,7 +370,7 @@ test_vm_loopback() { --mode=client \ --control-host="127.0.0.1" \ --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" + --peer-cid=1 2>&1 | log_guest

return $? } @@ -429,7 +428,7 @@ QEMU="qemu-system-$(uname -m)" while getopts :hvsq:b o do case $o in - v) VERBOSE=1;; + v) VERBOSE=$(( VERBOSE - 1 ));; b) BUILD=1;; q) QEMU=$OPTARG;; h|*) usage;; @@ -452,10 +451,10 @@ handle_build

echo "1..${#ARGS[@]}"

-log_setup "Booting up VM" +log_host "Booting up VM" vm_start vm_wait_for_ssh -log_setup "VM booted up" +log_host "VM booted up"

cnt_pass=0 cnt_fail=0

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests for namespace support in vsock. Use socat for basic connection failure tests and vsock_test for full functionality tests when communication is expected to succeed. vsock_test is not used for failure cases because in theory vsock_test could allow connection and some traffic flow but fail on some other case (e.g., fail on MSG_ZEROCOPY).

Tests cover all cases of clients and servers being in all variants of local ns, global ns, host process, and VM process.

Legacy tests are retained and executed in the init ns.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com

--- Changes in v6: - check for namespace support in vmtest.sh

Changes in v5: - use /proc/sys/net/vsock/ns_mode - clarify logic of tests that reuse the same VM and tests that require netns setup - fix unassigned BUILD bug --- tools/testing/selftests/vsock/vmtest.sh | 954 ++++++++++++++++++++++++++++---- 1 file changed, 849 insertions(+), 105 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 5e36d1068f6f..59621b32cf1a 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -7,6 +7,7 @@ # * virtme-ng # * busybox-static (used by virtme-ng) # * qemu (used by virtme-ng) +# * socat

readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) @@ -23,7 +24,7 @@ readonly VSOCK_CID=1234 readonly WAIT_PERIOD=3 readonly WAIT_PERIOD_MAX=60 readonly WAIT_TOTAL=$(( WAIT_PERIOD * WAIT_PERIOD_MAX )) -readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) +readonly WAIT_QEMU=5

# virtme-ng offers a netdev for ssh when using "--ssh", but we also need a # control port forwarded for vsock_test. Because virtme-ng doesn't support @@ -33,23 +34,146 @@ readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) # add the kernel cmdline options that virtme-init uses to setup the interface. readonly QEMU_TEST_PORT_FWD="hostfwd=tcp::${TEST_HOST_PORT}-:${TEST_GUEST_PORT}" readonly QEMU_SSH_PORT_FWD="hostfwd=tcp::${SSH_HOST_PORT}-:${SSH_GUEST_PORT}" -readonly QEMU_OPTS="\ - -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ - -device virtio-net-pci,netdev=n0 \ - -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ - --pidfile ${QEMU_PIDFILE} \ -" readonly KERNEL_CMDLINE="\ virtme.dhcp net.ifnames=0 biosdevname=0 \ virtme.ssh virtme_ssh_channel=tcp virtme_ssh_user=$USER \ " readonly LOG=$(mktemp /tmp/vsock_vmtest_XXXX.log) -readonly TEST_NAMES=(vm_server_host_client vm_client_host_server vm_loopback) +readonly TEST_NAMES=( + vm_server_host_client + vm_client_host_server + vm_loopback + host_vsock_ns_mode_ok + host_vsock_ns_mode_write_once_ok + global_same_cid_fails + local_same_cid_ok + global_local_same_cid_ok + local_global_same_cid_ok + diff_ns_global_host_connect_to_global_vm_ok + diff_ns_global_host_connect_to_local_vm_fails + diff_ns_global_vm_connect_to_global_host_ok + diff_ns_global_vm_connect_to_local_host_fails + diff_ns_local_host_connect_to_local_vm_fails + diff_ns_local_vm_connect_to_local_host_fails + diff_ns_global_to_local_loopback_local_fails + diff_ns_local_to_global_loopback_fails + diff_ns_local_to_local_loopback_fails + diff_ns_global_to_global_loopback_ok + same_ns_local_loopback_ok + same_ns_local_host_connect_to_local_vm_ok + same_ns_local_vm_connect_to_local_host_ok +) + readonly TEST_DESCS=( + # vm_server_host_client "Run vsock_test in server mode on the VM and in client mode on the host." + + # vm_client_host_server "Run vsock_test in client mode on the VM and in server mode on the host." + + # vm_loopback "Run vsock_test using the loopback transport in the VM." + + # host_vsock_ns_mode_ok + "Check /proc/sys/net/vsock/ns_mode strings on the host." + + # host_vsock_ns_mode_write_once_ok + "Check /proc/sys/net/vsock/ns_mode is write-once on the host." + + # global_same_cid_fails + "Check QEMU fails to start two VMs with same CID in two different global namespaces." + + # local_same_cid_ok + "Check QEMU successfully starts two VMs with same CID in two different local namespaces." + + # 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." + + # 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." + + # diff_ns_global_host_connect_to_global_vm_ok + "Run vsock_test client in global ns with server in VM in another global ns." + + # diff_ns_global_host_connect_to_local_vm_fails + "Run socat to test a process in a global ns fails to connect to a VM in a local ns." + + # diff_ns_global_vm_connect_to_global_host_ok + "Run vsock_test client in VM in a global ns with server in another global ns." + + # diff_ns_global_vm_connect_to_local_host_fails + "Run socat to test a VM in a global ns fails to connect to a host process in a local ns." + + # diff_ns_local_host_connect_to_local_vm_fails + "Run socat to test a host process in a local ns fails to connect to a VM in another local ns." + + # diff_ns_local_vm_connect_to_local_host_fails + "Run socat to test a VM in a local ns fails to connect to a host process in another local ns." + + # diff_ns_global_to_local_loopback_local_fails + "Run socat to test a loopback vsock in a global ns fails to connect to a vsock in a local ns." + + # diff_ns_local_to_global_loopback_fails + "Run socat to test a loopback vsock in a local ns fails to connect to a vsock in a global ns." + + # diff_ns_local_to_local_loopback_fails + "Run socat to test a loopback vsock in a local ns fails to connect to a vsock in another local ns." + + # diff_ns_global_to_global_loopback_ok + "Run socat to test a loopback vsock in a global ns successfully connects to a vsock in another global ns." + + # same_ns_local_loopback_ok + "Run socat to test a loopback vsock in a local ns successfully connects to a vsock in the same ns." + + # same_ns_local_host_connect_to_local_vm_ok + "Run vsock_test client in a local ns with server in VM in same ns." + + # same_ns_local_vm_connect_to_local_host_ok + "Run vsock_test client in VM in a local ns with server in same ns." +) + +readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) +readonly USE_INIT_NETNS=( + global_same_cid_fails + local_same_cid_ok + global_local_same_cid_ok + local_global_same_cid_ok + diff_ns_global_host_connect_to_global_vm_ok + diff_ns_global_host_connect_to_local_vm_fails + diff_ns_global_vm_connect_to_global_host_ok + diff_ns_global_vm_connect_to_local_host_fails + diff_ns_local_host_connect_to_local_vm_fails + diff_ns_local_vm_connect_to_local_host_fails + diff_ns_global_to_local_loopback_local_fails + diff_ns_local_to_global_loopback_fails + diff_ns_local_to_local_loopback_fails + diff_ns_global_to_global_loopback_ok + same_ns_local_loopback_ok + same_ns_local_host_connect_to_local_vm_ok + same_ns_local_vm_connect_to_local_host_ok +) +readonly REQUIRES_NETNS=( + host_vsock_ns_mode_ok + host_vsock_ns_mode_write_once_ok + global_same_cid_fails + local_same_cid_ok + global_local_same_cid_ok + local_global_same_cid_ok + diff_ns_global_host_connect_to_global_vm_ok + diff_ns_global_host_connect_to_local_vm_fails + diff_ns_global_vm_connect_to_global_host_ok + diff_ns_global_vm_connect_to_local_host_fails + diff_ns_local_host_connect_to_local_vm_fails + diff_ns_local_vm_connect_to_local_host_fails + diff_ns_global_to_local_loopback_local_fails + diff_ns_local_to_global_loopback_fails + diff_ns_local_to_local_loopback_fails + diff_ns_global_to_global_loopback_ok + same_ns_local_loopback_ok + same_ns_local_host_connect_to_local_vm_ok + same_ns_local_vm_connect_to_local_host_ok ) +readonly MODES=("local" "global")

readonly LOG_LEVEL_DEBUG=0 readonly LOG_LEVEL_INFO=1 @@ -58,6 +182,12 @@ readonly LOG_LEVEL_ERROR=3

VERBOSE="${LOG_LEVEL_WARN}"

+# Test pass/fail counters +cnt_pass=0 +cnt_fail=0 +cnt_skip=0 +cnt_total=0 + usage() { local name local desc @@ -77,7 +207,7 @@ usage() { for ((i = 0; i < ${#TEST_NAMES[@]}; i++)); do name=${TEST_NAMES[${i}]} desc=${TEST_DESCS[${i}]} - printf "\t%-35s%-35s\n" "${name}" "${desc}" + printf "\t%-55s%-35s\n" "${name}" "${desc}" done echo

@@ -89,21 +219,87 @@ die() { exit "${KSFT_FAIL}" }

+add_namespaces() { + # add namespaces local0, local1, global0, and global1 + for mode in "${MODES[@]}"; do + ip netns add "${mode}0" 2>/dev/null + ip netns add "${mode}1" 2>/dev/null + done +} + +init_namespaces() { + for mode in "${MODES[@]}"; do + ns_set_mode "${mode}0" "${mode}" + ns_set_mode "${mode}1" "${mode}" + + log_host "set ns ${mode}0 to mode ${mode}" + log_host "set ns ${mode}1 to mode ${mode}" + + # we need lo for qemu port forwarding + ip netns exec "${mode}0" ip link set dev lo up + ip netns exec "${mode}1" ip link set dev lo up + done +} + +del_namespaces() { + for mode in "${MODES[@]}"; do + ip netns del "${mode}0" + ip netns del "${mode}1" + log_host "removed ns ${mode}0" + log_host "removed ns ${mode}1" + done &>/dev/null +} + +ns_set_mode() { + local ns=$1 + local mode=$2 + + echo "${mode}" | ip netns exec "${ns}" \ + tee /proc/sys/net/vsock/ns_mode &>/dev/null +} + vm_ssh() { - ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@" + local ns_exec + + if [[ "${1}" == none ]]; then + local ns_exec="" + else + local ns_exec="ip netns exec ${1}" + fi + + shift + + ${ns_exec} ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost $* + return $? }

cleanup() { - if [[ -s "${QEMU_PIDFILE}" ]]; then - pkill -SIGTERM -F "${QEMU_PIDFILE}" > /dev/null 2>&1 - fi + del_namespaces +}

- # If failure occurred during or before qemu start up, then we need - # to clean this up ourselves. - if [[ -e "${QEMU_PIDFILE}" ]]; then - rm "${QEMU_PIDFILE}" - fi +terminate_pidfiles() { + local pidfile + + for pidfile in "$@"; do + if [[ -s "${pidfile}" ]]; then + pkill -SIGTERM -F "${pidfile}" 2>&1 > /dev/null + fi + + # If failure occurred during or before qemu start up, then we need + # to clean this up ourselves. + if [[ -e "${pidfile}" ]]; then + rm -f "${pidfile}" + fi + done +} + +terminate_pids() { + local pid + + for pid in "$@"; do + kill -SIGTERM "${pid}" &>/dev/null || : + done }

check_args() { @@ -133,7 +329,7 @@ check_args() { }

check_deps() { - for dep in vng ${QEMU} busybox pkill ssh; do + for dep in vng ${QEMU} busybox pkill ssh socat; do if [[ ! -x $(command -v "${dep}") ]]; then echo -e "skip: dependency ${dep} not found!\n" exit "${KSFT_SKIP}" @@ -147,6 +343,20 @@ check_deps() { fi }

+check_test_deps() { + local tname=$1 + + # If the test requires NS support, check if NS support exists + # using /proc/self/ns + if [[ "${tname}" =~ "${REQUIRES_NETNS[@]}" ]] && + [[ ! -e /proc/self/ns ]]; then + log_host "No NS support detected for test ${tname}" + return 1 + fi + + return 0 +} + check_vng() { local tested_versions local version @@ -170,6 +380,20 @@ check_vng() { fi }

+check_socat() { + local support_string + + support_string="$(socat -V)" + + if [[ "${support_string}" != *"WITH_VSOCK 1"* ]]; then + die "err: socat is missing vsock support" + fi + + if [[ "${support_string}" != *"WITH_UNIX 1"* ]]; then + die "err: socat is missing unix support" + fi +} + handle_build() { if [[ ! "${BUILD}" -eq 1 ]]; then return @@ -194,9 +418,14 @@ handle_build() { }

vm_start() { + local cid=$1 + local ns=$2 + local pidfile=$3 local logfile=/dev/null local verbose_opt="" + local qemu_opts="" local kernel_opt="" + local ns_exec="" local qemu

qemu=$(command -v "${QEMU}") @@ -206,27 +435,37 @@ vm_start() { logfile=/dev/stdout fi

+ qemu_opts="\ + -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ + -device virtio-net-pci,netdev=n0 \ + ${QEMU_OPTS} -device vhost-vsock-pci,guest-cid=${cid} \ + --pidfile ${pidfile} + " + if [[ "${BUILD}" -eq 1 ]]; then kernel_opt="${KERNEL_CHECKOUT}" fi

- vng \ + if [[ "${ns}" != "none" ]]; then + ns_exec="ip netns exec ${ns}" + fi + + ${ns_exec} vng \ --run \ ${kernel_opt} \ ${verbose_opt} \ - --qemu-opts="${QEMU_OPTS}" \ + --qemu-opts="${qemu_opts}" \ --qemu="${qemu}" \ --user root \ --append "${KERNEL_CMDLINE}" \ --rw &> ${logfile} &

- if ! timeout ${WAIT_TOTAL} \ - bash -c 'while [[ ! -s '"${QEMU_PIDFILE}"' ]]; do sleep 1; done; exit 0'; then - die "failed to boot VM" - fi + timeout "${WAIT_QEMU}" \ + bash -c 'while [[ ! -s '"${pidfile}"' ]]; do sleep 1; done; exit 0' }

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

i=0 @@ -234,7 +473,8 @@ 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=$(( i + 1 )) @@ -269,6 +509,7 @@ wait_for_listener() grep -q "${pattern}"; then break fi + sleep "${interval}" done

@@ -278,17 +519,29 @@ wait_for_listener() }

vm_wait_for_listener() { - local port=$1 + local ns=$1 + local port=$2 + + log "Waiting for listener on port ${port} on vm"

- 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() { - wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + local ns=$1 + local port=$2

+ if [[ "${ns}" == none ]]; then + wait_for_listener "${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 }

log() { @@ -427,51 +680,506 @@ test_vm_client_host_server() { }

test_vm_loopback() { + vm_ssh "none" modprobe vsock_loopback || : vm_vsock_test "none" "server" 1 "${TEST_HOST_PORT_LISTENER}" vm_vsock_test "none" "client" "127.0.0.1" 1 "${TEST_HOST_PORT_LISTENER}" }

+test_host_vsock_ns_mode_ok() { + add_namespaces

+ for mode in "${MODES[@]}"; do + if ! ns_set_mode "${mode}0" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi + done + + del_namespaces }

-test_vm_client_host_server() { +test_host_vsock_ns_mode_write_once_ok() { + add_namespaces

- ${VSOCK_TEST} \ - --mode "server" \ - --control-port "${TEST_HOST_PORT_LISTENER}" \ - --peer-cid "${VSOCK_CID}" 2>&1 | log_host & + for mode in "${MODES[@]}"; do + local ns="${mode}0" + if ! ns_set_mode "${ns}" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi

- host_wait_for_listener + # try writing again and expect failure + if ns_set_mode "${ns}" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi + done

- vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host=10.0.2.2 \ - --peer-cid=2 \ - --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest + del_namespaces

- return $? + return "${KSFT_PASS}" }

-test_vm_loopback() { - local port=60000 # non-forwarded local port +namespaces_can_boot_same_cid() { + local ns0=$1 + local ns1=$2 + local pidfile1 pidfile2 + local cid=20 + readonly cid + local rc

- vm_ssh -- "${VSOCK_TEST}" \ - --mode=server \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest & + pidfile1=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + vm_start "${cid}" "${ns0}" "${pidfile1}"

- vm_wait_for_listener "${port}" + pidfile2=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + vm_start "${cid}" "${ns1}" "${pidfile2}"

- vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host="127.0.0.1" \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest + rc=$? + terminate_pidfiles "${pidfile1}" "${pidfile2}"

- return $? + return $rc +} + +test_global_same_cid_fails() { + if namespaces_can_boot_same_cid "global0" "global1"; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_local_global_same_cid_ok() { + if namespaces_can_boot_same_cid "local0" "global0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_global_local_same_cid_ok() { + if namespaces_can_boot_same_cid "global0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_local_same_cid_ok() { + if namespaces_can_boot_same_cid "local0" "local0"; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_diff_ns_global_host_connect_to_global_vm_ok() { + local pids pid pidfile + local ns0 ns1 port + declare -a pids + local unixfile + ns0="global0" + ns1="global1" + port=1234 + local rc + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + + if ! vm_start "${VSOCK_CID}" "${ns0}" "${pidfile}"; then + return "${KSFT_FAIL}" + fi + + unixfile=$(mktemp -u /tmp/XXXX.sock) + ip netns exec "${ns1}" \ + socat TCP-LISTEN:"${TEST_HOST_PORT}",fork \ + UNIX-CONNECT:"${unixfile}" & + pids+=($!) + host_wait_for_listener "${ns1}" "${TEST_HOST_PORT}" + + ip netns exec "${ns0}" socat UNIX-LISTEN:"${unixfile}",fork \ + TCP-CONNECT:localhost:"${TEST_HOST_PORT}" & + pids+=($!) + + vm_vsock_test "${ns0}" "server" 2 "${TEST_GUEST_PORT}" + vm_wait_for_listener "${ns0}" "${TEST_GUEST_PORT}" + host_vsock_test "${ns1}" "client" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}" + rc=$? + + for pid in "${pids[@]}"; do + if [[ "$(jobs -p)" = *"${pid}"* ]]; then + kill -SIGTERM "${pid}" &>/dev/null + fi + done + + terminate_pidfiles "${pidfile}" + + if [[ $rc -ne 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_diff_ns_global_host_connect_to_local_vm_fails() { + local ns0="global0" + local ns1="local0" + local port=12345 + local pidfile + local result + local pid + + outfile=$(mktemp) + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + if ! vm_start "${VSOCK_CID}" "${ns1}" "${pidfile}"; then + log_host "failed to start vm (cid=${VSOCK_CID}, ns=${ns0})" + return $KSFT_FAIL + fi + + vm_wait_for_ssh "${ns1}" + vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" & + echo TEST | ip netns exec "${ns0}" \ + socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null + + terminate_pidfiles "${pidfile}" + + result=$(cat "${outfile}") + rm -f "${outfile}" + + if [[ "${result}" != TEST ]]; then + return $KSFT_PASS + fi + + return $KSFT_FAIL +} + +test_diff_ns_global_vm_connect_to_global_host_ok() { + local ns0="global0" + local ns1="global1" + local port=12345 + local unixfile + local pidfile + local pids + + declare -a pids + + log_host "Setup socat bridge from ns ${ns0} to ns ${ns1} over port ${port}" + + unixfile=$(mktemp -u /tmp/XXXX.sock) + + ip netns exec "${ns0}" \ + socat TCP-LISTEN:"${port}" UNIX-CONNECT:"${unixfile}" & + pids+=($!) + + ip netns exec "${ns1}" \ + socat UNIX-LISTEN:"${unixfile}" TCP-CONNECT:127.0.0.1:"${port}" & + pids+=($!) + + log_host "Launching ${VSOCK_TEST} in ns ${ns1}" + host_vsock_test "${ns1}" "server" "${VSOCK_CID}" "${port}" + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + if ! vm_start "${VSOCK_CID}" "${ns0}" "${pidfile}"; then + log_host "failed to start vm (cid=${cid}, ns=${ns0})" + terminate_pids "${pids[@]}" + rm -f "${unixfile}" + return $KSFT_FAIL + fi + + vm_wait_for_ssh "${ns0}" + vm_vsock_test "${ns0}" "client" "10.0.2.2" 2 "${port}" + rc=$? + + terminate_pidfiles "${pidfile}" + terminate_pids "${pids[@]}" + rm -f "${unixfile}" + + if [[ ! $rc -eq 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" + +} + +test_diff_ns_global_vm_connect_to_local_host_fails() { + local ns0="global0" + local ns1="local0" + local port=12345 + local pidfile + local result + local pid + + log_host "Launching socat in ns ${ns1}" + outfile=$(mktemp) + ip netns exec "${ns1}" socat VSOCK-LISTEN:${port} STDOUT &> "${outfile}" & + pid=$! + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + if ! vm_start "${VSOCK_CID}" "${ns0}" "${pidfile}"; then + log_host "failed to start vm (cid=${cid}, ns=${ns0})" + terminate_pids "${pid}" + rm -f "${outfile}" + return $KSFT_FAIL + fi + + vm_wait_for_ssh "${ns0}" + + vm_ssh "${ns0}" -- \ + bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest + + terminate_pidfiles "${pidfile}" + terminate_pids "${pid}" + + result=$(cat "${outfile}") + rm -f "${outfile}" + + if [[ "${result}" != TEST ]]; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_diff_ns_local_host_connect_to_local_vm_fails() { + local ns0="local0" + local ns1="local1" + local port=12345 + local pidfile + local result + local pid + + outfile=$(mktemp) + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + if ! vm_start "${VSOCK_CID}" "${ns1}" "${pidfile}"; then + log_host "failed to start vm (cid=${cid}, ns=${ns0})" + return $KSFT_FAIL + fi + + vm_wait_for_ssh "${ns1}" + vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" & + echo TEST | ip netns exec "${ns0}" \ + socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null + + terminate_pidfiles "${pidfile}" + + result=$(cat "${outfile}") + rm -f "${outfile}" + + if [[ "${result}" != TEST ]]; then + return $KSFT_PASS + fi + + return $KSFT_FAIL +} + +test_diff_ns_local_vm_connect_to_local_host_fails() { + local ns0="local0" + local ns1="local1" + local port=12345 + local pidfile + local result + local pid + + log_host "Launching socat in ns ${ns1}" + outfile=$(mktemp) + ip netns exec "${ns1}" socat VSOCK-LISTEN:"${port}" STDOUT &> "${outfile}" & + pid=$! + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + if ! vm_start "${VSOCK_CID}" "${ns0}" "${pidfile}"; then + log_host "failed to start vm (cid=${cid}, ns=${ns0})" + rm -f "${outfile}" + return "${KSFT_FAIL}" + fi + + vm_wait_for_ssh "${ns0}" + + vm_ssh "${ns0}" -- \ + bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest + + terminate_pidfiles "${pidfile}" + terminate_pids "${pid}" + + result=$(cat "${outfile}") + rm -f "${outfile}" + + if [[ "${result}" != TEST ]]; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +__test_loopback_two_netns() { + local ns0=$1 + local ns1=$2 + local port=12345 + local result + local pid + + modprobe vsock_loopback &> /dev/null || : + + log_host "Launching socat in ns ${ns1}" + outfile=$(mktemp) + ip netns exec "${ns1}" socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" 2>/dev/null & + pid=$! + + log_host "Launching socat in ns ${ns0}" + echo TEST | ip netns exec "${ns0}" socat STDIN VSOCK-CONNECT:1:"${port}" 2>/dev/null + terminate_pids "${pid}" + + result=$(cat "${outfile}") + rm -f "${outfile}" + + if [[ "${result}" == TEST ]]; then + return 0 + fi + + return 1 +} + +test_diff_ns_global_to_local_loopback_local_fails() { + if ! __test_loopback_two_netns "global0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_diff_ns_local_to_global_loopback_fails() { + if ! __test_loopback_two_netns "local0" "global0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_diff_ns_local_to_local_loopback_fails() { + if ! __test_loopback_two_netns "local0" "local1"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_diff_ns_global_to_global_loopback_ok() { + if __test_loopback_two_netns "global0" "global1"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_same_ns_local_loopback_ok() { + if __test_loopback_two_netns "local0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_same_ns_local_host_connect_to_local_vm_ok() { + local ns="local0" + local port=1234 + local pidfile + local rc + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + + if ! vm_start "${VSOCK_CID}" "${ns}" "${pidfile}"; then + return "${KSFT_FAIL}" + fi + + vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}" + host_vsock_test "${ns}" "client" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}" + rc=$? + + terminate_pidfiles "${pidfile}" + + if [[ $rc -ne 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_same_ns_local_vm_connect_to_local_host_ok() { + local ns="local0" + local port=1234 + local pidfile + local rc + + pidfile=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + + if ! vm_start "${VSOCK_CID}" "${ns}" "${pidfile}"; then + return "${KSFT_FAIL}" + fi + + vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}" + host_vsock_test "${ns}" "client" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}" + rc=$? + + terminate_pidfiles "${pidfile}" + + if [[ $rc -ne 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +shared_vm_test() { + local tname + + tname="${1}" + + for testname in "${USE_SHARED_VM[@]}"; do + if [[ "${tname}" == "${testname}" ]]; then + return 0 + fi + done + + return 1 +} + + +init_netns_test() { + local tname + + tname="${1}" + + for testname in "${USE_INIT_NETNS[@]}"; do + if [[ "${tname}" == "${testname}" ]]; then + return 0 + fi + done + + return 1 +} + +check_result() { + local rc num + + rc=$1 + num=$(( cnt_total + 1 )) + + if [[ ${rc} -eq $KSFT_PASS ]]; then + cnt_pass=$(( cnt_pass + 1 )) + echo "ok ${num} ${arg}" + elif [[ ${rc} -eq $KSFT_SKIP ]]; then + cnt_skip=$(( cnt_skip + 1 )) + echo "ok ${num} ${arg} # SKIP" + elif [[ ${rc} -eq $KSFT_FAIL ]]; then + cnt_fail=$(( cnt_fail + 1 )) + echo "not ok ${num} ${arg} # exit=$rc" + fi + + cnt_total=$(( cnt_total + 1 )) }

-run_test() { +run_shared_vm_tests() { + local start_shared_vm pidfile local host_oops_cnt_before local host_warn_cnt_before local vm_oops_cnt_before @@ -483,42 +1191,99 @@ run_test() { local name local rc

- host_oops_cnt_before=$(dmesg | grep -c -i 'Oops') - host_warn_cnt_before=$(dmesg --level=warn | wc -l) - vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops') - vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | wc -l) + start_shared_vm=0

- name=$(echo "${1}" | awk '{ print $1 }') - eval test_"${name}" - rc=$? + for arg in "${ARGS[@]}"; do + if shared_vm_test "${arg}"; then + start_shared_vm=1 + break + fi + done

- host_oops_cnt_after=$(dmesg | grep -i 'Oops' | wc -l) - if [[ ${host_oops_cnt_after} -gt ${host_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on host" | log_host "${name}" - rc=$KSFT_FAIL + pidfile="" + if [[ "${start_shared_vm}" == 1 ]]; then + pidfile=$(mktemp $PIDFILE_TEMPLATE) + log_host "Booting up VM" + vm_start "${VSOCK_CID}" "none" "${pidfile}" + vm_wait_for_ssh "none" + log_host "VM booted up" fi

- host_warn_cnt_after=$(dmesg --level=warn | wc -l) - if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on host" | log_host "${name}" - rc=$KSFT_FAIL - fi + for arg in "${ARGS[@]}"; do + if ! shared_vm_test "${arg}"; then + continue + fi

- vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l) - if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on vm" | log_host "${name}" - rc=$KSFT_FAIL - fi + if ! check_test_deps "${arg}"; then + log_host "Skipping ${arg}" + check_result "${KSFT_SKIP}" + continue + fi + + host_oops_cnt_before=$(dmesg | grep -c -i 'Oops') + host_warn_cnt_before=$(dmesg --level=warn | wc -l) + vm_oops_cnt_before=$(vm_ssh none -- dmesg | grep -c -i 'Oops') + vm_warn_cnt_before=$(vm_ssh none -- dmesg --level=warn | wc -l) + + name=$(echo "${arg}" | awk '{ print $1 }') + log_host "Executing test_${name}" + eval test_"${name}" + rc=$? + + host_oops_cnt_after=$(dmesg | grep -i 'Oops' | wc -l) + if [[ ${host_oops_cnt_after} -gt ${host_oops_cnt_before} ]]; then + echo "FAIL: kernel oops detected on host" | log_host "${name}" + rc=$KSFT_FAIL + fi

- vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | wc -l) - if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on vm" | log_host "${name}" - rc=$KSFT_FAIL + host_warn_cnt_after=$(dmesg --level=warn | wc -l) + if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then + echo "FAIL: kernel warning detected on host" | log_host "${name}" + rc=$KSFT_FAIL + fi + + vm_oops_cnt_after=$(vm_ssh none -- dmesg | grep -i 'Oops' | wc -l) + if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then + echo "FAIL: kernel oops detected on vm" | log_host "${name}" + rc=$KSFT_FAIL + fi + + vm_warn_cnt_after=$(vm_ssh none -- dmesg --level=warn | wc -l) + if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then + echo "FAIL: kernel warning detected on vm" | log_host "${name}" + rc=$KSFT_FAIL + fi + + check_result "${rc}" + done + + if [[ -n "${pidfile}" ]]; then + log_host "VM terminate" + terminate_pidfiles "${pidfile}" fi +} + +run_isolated_vm_tests() { + for arg in "${ARGS[@]}"; do + if shared_vm_test "${arg}"; then + continue + fi + + add_namespaces + if init_netns_test "${arg}"; then + init_namespaces + fi

- return "${rc}" + name=$(echo "${arg}" | awk '{ print $1 }') + log_host "Executing test_${name}" + eval test_"${name}" + check_result $? + + del_namespaces + done }

+BUILD=0 QEMU="qemu-system-$(uname -m)"

while getopts :hvsq:b o @@ -543,34 +1308,13 @@ fi check_args "${ARGS[@]}" check_deps check_vng +check_socat handle_build

echo "1..${#ARGS[@]}"

-log_host "Booting up VM" -vm_start -vm_wait_for_ssh -log_host "VM booted up" - -cnt_pass=0 -cnt_fail=0 -cnt_skip=0 -cnt_total=0 -for arg in "${ARGS[@]}"; do - run_test "${arg}" - rc=$? - if [[ ${rc} -eq $KSFT_PASS ]]; then - cnt_pass=$(( cnt_pass + 1 )) - echo "ok ${cnt_total} ${arg}" - elif [[ ${rc} -eq $KSFT_SKIP ]]; then - cnt_skip=$(( cnt_skip + 1 )) - echo "ok ${cnt_total} ${arg} # SKIP" - elif [[ ${rc} -eq $KSFT_FAIL ]]; then - cnt_fail=$(( cnt_fail + 1 )) - echo "not ok ${cnt_total} ${arg} # exit=$rc" - fi - cnt_total=$(( cnt_total + 1 )) -done +run_shared_vm_tests +run_isolated_vm_tests

echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" echo "Log: ${LOG}"