From: Bobby Eshleman bobbyeshleman@meta.com

Reduce holes in struct virtio_vsock_skb_cb. As this struct continues to grow, we want to keep it trimmed down so it doesn't exceed the size of skb->cb (currently 48 bytes). Eliminating the 2 byte hole provides an additional two bytes for new fields at the end of the structure. It does not shrink the total size, however.

Future work could include combining fields like reply and tap_delivered into a single bitfield, but currently doing so will not make the total struct size smaller (although, would extend the tail-end padding area by one byte).

Before this patch:

struct virtio_vsock_skb_cb { bool reply; /* 0 1 */ bool tap_delivered; /* 1 1 */

/* XXX 2 bytes hole, try to pack */

u32 offset; /* 4 4 */

/* size: 8, cachelines: 1, members: 3 */ /* sum members: 6, holes: 1, sum holes: 2 */ /* last cacheline: 8 bytes */ }; ;

After this patch:

struct virtio_vsock_skb_cb { u32 offset; /* 0 4 */ bool reply; /* 4 1 */ bool tap_delivered; /* 5 1 */

/* size: 8, cachelines: 1, members: 3 */ /* padding: 2 */ /* last cacheline: 8 bytes */ };

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- include/linux/virtio_vsock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 0c67543a45c8..87cf4dcac78a 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -10,9 +10,9 @@ #define VIRTIO_VSOCK_SKB_HEADROOM (sizeof(struct virtio_vsock_hdr))

struct virtio_vsock_skb_cb { + u32 offset; bool reply; bool tap_delivered; - u32 offset; };

#define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb))

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".

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, which makes them behave as if always in the global namespace. Vhost is an exception because it inherits its namespace from the process that opens the vhost device.

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.

seqpacket_allow() callbacks are modified to take a vsk so that transport implementations can inspect sock_net(sk) and vsk->net_mode when performing lookups (e.g., vhost does this in its future netns patch). Because the API change affects all transports, it seemed more appropriate to make this internal API change in the "vsock core" patch then in the "vhost" patch.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- 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 --- drivers/vhost/vsock.c | 4 +- include/linux/virtio_vsock.h | 21 ++++ include/net/af_vsock.h | 14 ++- net/vmw_vsock/af_vsock.c | 264 ++++++++++++++++++++++++++++++++++++--- net/vmw_vsock/virtio_transport.c | 7 +- net/vmw_vsock/vsock_loopback.c | 4 +- 6 files changed, 288 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/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 7f334a32133c..29290395054c 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -153,6 +153,27 @@ static inline void virtio_vsock_skb_set_net_mode(struct sk_buff *skb, VIRTIO_VSOCK_SKB_CB(skb)->net_mode = net_mode; }

+static inline struct sk_buff * +virtio_vsock_alloc_rx_skb(unsigned int size, gfp_t mask) +{ + struct sk_buff *skb; + + skb = virtio_vsock_alloc_linear_skb(size, mask); + if (!skb) + return NULL; + + memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM); + + /* virtio-vsock does not yet support namespaces, so on receive + * we force legacy namespace behavior using the global dummy net + * and global net mode. + */ + virtio_vsock_skb_set_net(skb, vsock_global_dummy_net()); + virtio_vsock_skb_set_net_mode(skb, VSOCK_NET_MODE_GLOBAL); + + return skb; +} + /* Dimension the RX SKB so that the entire thing fits exactly into * a single 4KiB page. This avoids wasting memory due to alloc_skb() * rounding up to the next page order and also means that we diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index bce5389ef742..69bb70c3c0fd 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -145,7 +145,7 @@ struct vsock_transport { int flags); int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len); - bool (*seqpacket_allow)(u32 remote_cid); + bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid); u32 (*seqpacket_has_data)(struct vsock_sock *vsk);

/* Notification. */ @@ -218,6 +218,12 @@ void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct net *net, + enum vsock_net_mode net_mode); +struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + struct net *net, + enum vsock_net_mode net_mode); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); @@ -259,6 +265,12 @@ 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 4c2db6cca557..656a78810c68 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 +141,18 @@ #include <linux/workqueue.h> #include <net/sock.h> #include <net/af_vsock.h> +#include <net/netns/vsock.h> #include <uapi/linux/vm_sockets.h> #include <uapi/asm-generic/ioctls.h>

+#define VSOCK_NET_MODE_STR_GLOBAL "global" +#define VSOCK_NET_MODE_STR_LOCAL "local" + +/* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'. + * The newline is added by proc_dostring() for read operations. + */ +#define VSOCK_NET_MODE_STR_MAX 8 + static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); @@ -149,6 +188,15 @@ static const struct vsock_transport *transport_dgram; static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex);

+/* This net is used only for transports that do support namespaces. It is never + * registered with the namespace subsystem and always has + * VSOCK_NET_MODE_GLOBAL. Pass this net to the net lookup functions (e.g., + * vsock_find_bound_socket_net()) when you want to force global-mode or the + * same behavior as before namespaces were supported. + */ +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 @@ -235,33 +283,44 @@ static void __vsock_remove_connected(struct vsock_sock *vsk) sock_put(&vsk->sk); }

-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) +static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net, + enum vsock_net_mode net_mode) { struct vsock_sock *vsk;

list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { - if (vsock_addr_equals_addr(addr, &vsk->local_addr)) - return sk_vsock(vsk); + struct sock *sk = sk_vsock(vsk); + + if (vsock_addr_equals_addr(addr, &vsk->local_addr) && + vsock_net_check_mode(sock_net(sk), vsk->net_mode, net, net_mode)) + return sk;

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

return NULL; }

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

list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { + struct sock *sk = sk_vsock(vsk); + if (vsock_addr_equals_addr(src, &vsk->remote_addr) && - dst->svm_port == vsk->local_addr.svm_port) { - return sk_vsock(vsk); + dst->svm_port == vsk->local_addr.svm_port && + vsock_net_check_mode(sock_net(sk), vsk->net_mode, net, net_mode)) { + return sk; } }

@@ -304,12 +363,14 @@ void vsock_remove_connected(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_remove_connected);

-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net, + enum vsock_net_mode net_mode) { struct sock *sk;

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

@@ -317,15 +378,24 @@ 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, vsock_global_dummy_net(), + VSOCK_NET_MODE_GLOBAL); +} EXPORT_SYMBOL_GPL(vsock_find_bound_socket);

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

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

@@ -333,6 +403,15 @@ 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, + vsock_global_dummy_net(), + VSOCK_NET_MODE_GLOBAL); +} EXPORT_SYMBOL_GPL(vsock_find_connected_socket);

void vsock_remove_sock(struct vsock_sock *vsk) @@ -528,7 +607,7 @@ 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 +755,7 @@ 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 +775,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,

new_addr.svm_port = port++;

- if (!__vsock_find_bound_socket(&new_addr)) { + if (!__vsock_find_bound_socket_net(&new_addr, net, + vsk->net_mode)) { found = true; break; } @@ -712,7 +793,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, return -EACCES; }

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

@@ -836,6 +918,8 @@ static struct sock *__vsock_create(struct net *net, vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; }

+ vsk->net_mode = vsock_net_mode(net); + return sk; }

@@ -2636,6 +2720,142 @@ static struct miscdevice vsock_device = { .fops = &vsock_device_ops, };

+static int vsock_net_mode_string(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + char data[VSOCK_NET_MODE_STR_MAX] = {0}; + enum vsock_net_mode mode; + struct ctl_table tmp; + struct net *net; + int ret; + + if (!table->data || !table->maxlen || !*lenp) { + *lenp = 0; + return 0; + } + + net = current->nsproxy->net_ns; + tmp = *table; + tmp.data = data; + + if (!write) { + const char *p; + + mode = vsock_net_mode(net); + + switch (mode) { + case VSOCK_NET_MODE_GLOBAL: + p = VSOCK_NET_MODE_STR_GLOBAL; + break; + case VSOCK_NET_MODE_LOCAL: + p = VSOCK_NET_MODE_STR_LOCAL; + break; + default: + WARN_ONCE(true, "netns has invalid vsock mode"); + *lenp = 0; + return 0; + } + + strscpy(data, p, sizeof(data)); + tmp.maxlen = strlen(p); + } + + ret = proc_dostring(&tmp, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (write) { + if (*lenp >= sizeof(data)) + return -EINVAL; + + if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data))) + mode = VSOCK_NET_MODE_GLOBAL; + else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data))) + mode = VSOCK_NET_MODE_LOCAL; + else + return -EINVAL; + + if (!vsock_net_write_mode(net, mode)) + return -EPERM; + } + + return 0; +} + +static struct ctl_table vsock_table[] = { + { + .procname = "ns_mode", + .data = &init_net.vsock.mode, + .maxlen = VSOCK_NET_MODE_STR_MAX, + .mode = 0644, + .proc_handler = vsock_net_mode_string + }, +}; + +static int __net_init vsock_sysctl_register(struct net *net) +{ + struct ctl_table *table; + + if (net_eq(net, &init_net)) { + table = vsock_table; + } else { + table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->vsock.mode; + } + + net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table, + ARRAY_SIZE(vsock_table)); + if (!net->vsock.sysctl_hdr) + goto err_reg; + + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void vsock_sysctl_unregister(struct net *net) +{ + const struct ctl_table *table; + + table = net->vsock.sysctl_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->vsock.sysctl_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static void vsock_net_init(struct net *net) +{ + 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 +2883,19 @@ 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 +2909,7 @@ static void __exit vsock_exit(void) misc_deregister(&vsock_device); sock_unregister(AF_VSOCK); proto_unregister(&vsock_proto); + unregister_pernet_subsys(&vsock_sysctl_ops); }

const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 8c867023a2e5..6abec6b9b5bc 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -316,11 +316,10 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) vq = vsock->vqs[VSOCK_VQ_RX];

do { - skb = virtio_vsock_alloc_linear_skb(total_len, GFP_KERNEL); + skb = virtio_vsock_alloc_rx_skb(total_len, GFP_KERNEL); if (!skb) break;

- memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM); sg_init_one(&pkt, virtio_vsock_hdr(skb), total_len); p = &pkt; ret = virtqueue_add_sgs(vq, &p, 0, 1, skb, GFP_KERNEL); @@ -536,7 +535,7 @@ 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 +592,7 @@ 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; diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index bc2ff918b315..a8f218f0c5a3 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

Enable network namespace support in the virtio-vsock common transport layer by declaring namespace pointers in the transmit and receive paths.

The changes include: 1. Add a 'net' field to virtio_vsock_pkt_info to carry the namespace pointer for outgoing packets. 2. Store the namespace and namespace mode in the skb control buffer when allocating packets (except for VIRTIO_VSOCK_OP_RST packets which do not have an associated socket). 3. Retrieve namespace information from skbs on the receive path for lookups using vsock_find_connected_socket_net() and vsock_find_bound_socket_net().

This allows users of virtio transport common code (vhost-vsock/virtio-vsock) to later enable namespace support.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v7: - add comment explaining the !vsk case in virtio_transport_alloc_skb() --- include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport_common.c | 21 +++++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 29290395054c..f90646f82993 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -217,6 +217,7 @@ 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 dcc8a1d5851e..b8e52c71920a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -316,6 +316,15 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info * info->flags, zcopy);

+ /* + * If there is no corresponding socket, then we don't have a + * corresponding namespace. This only happens For VIRTIO_VSOCK_OP_RST. + */ + if (vsk) { + virtio_vsock_skb_set_net(skb, info->net); + virtio_vsock_skb_set_net_mode(skb, vsk->net_mode); + } + return skb; out: kfree_skb(skb); @@ -527,6 +536,7 @@ 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 +1077,7 @@ 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 +1093,7 @@ 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 +1120,7 @@ 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 +1158,7 @@ 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 */ @@ -1465,6 +1479,7 @@ 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 +1593,9 @@ 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 net_mode = virtio_vsock_skb_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 +1623,9 @@ 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_net(&src, &dst, net, net_mode); if (!sk) { - sk = vsock_find_bound_socket(&dst); + sk = vsock_find_bound_socket_net(&dst, net, net_mode); if (!sk) { (void)virtio_transport_reset_no_sock(t, skb); goto free_pkt;

From: Bobby Eshleman bobbyeshleman@meta.com

Add functions for initializing namespaces with the different vsock NS modes. Callers can use add_namespaces() and del_namespaces() to create namespaces global0, global1, local0, and local1.

The init_namespaces() function initializes global0, local0, etc... with their respective vsock NS mode. This function is separate so that tests that depend on this initialization can use it, while other tests that want to test the initialization interface itself can start with a clean slate by omitting this call.

Remove namespaces upon exiting the program in cleanup(). This is unlikely to be needed for a healthy run, but it is useful for tests that are manually killed mid-test. In that case, this patch prevents the subsequent test run from finding stale namespaces with already-write-once-locked vsock ns modes.

This patch is in preparation for later namespace tests.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 45 +++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 62b4f5ede9f6..5f4bae952e13 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -46,6 +46,7 @@ readonly TEST_DESCS=( )

readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) +readonly NS_MODES=("local" "global")

VERBOSE=0

@@ -100,11 +101,55 @@ check_result() { cnt_total=$(( cnt_total + 1 )) }

+add_namespaces() { + # add namespaces local0, local1, global0, and global1 + for mode in "${NS_MODES[@]}"; do + ip netns add "${mode}0" 2>/dev/null + ip netns add "${mode}1" 2>/dev/null + done +} + +init_namespaces() { + for mode in "${NS_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 "${mode}1" ip link set dev lo up + done +} + +del_namespaces() { + for mode in "${NS_MODES[@]}"; do + ip netns del "${mode}0" &>/dev/null + ip netns del "${mode}1" &>/dev/null + log_host "removed ns ${mode}0" + log_host "removed ns ${mode}1" + done +} + +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 ${SSH_HOST_PORT} localhost "$@" return $? }

+cleanup() { + del_namespaces +} + +trap cleanup EXIT

check_args() { local found

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests for the /proc/sys/net/vsock/ns_mode interface. Namely, that it accepts "global" and "local" strings and enforces a write-once policy.

Start a convention of commenting the test name over the test description. Add test name comments over test descriptions that existed before this convention.

Add a check_netns() function that checks if the test requires namespaces and if the current kernel supports namespaces. Skip tests that require namespaces if the system does not have namespace support.

This patch is the first to add tests that do *not* re-use the same shared VM. For that reason, it adds a run_tests() function to run these tests and filter out the shared VM tests.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 99 ++++++++++++++++++++++++++++++++- 1 file changed, 98 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index d047f6d27df4..b775fb0cd4ed 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -38,11 +38,28 @@ readonly KERNEL_CMDLINE="\ 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 + ns_host_vsock_ns_mode_ok + ns_host_vsock_ns_mode_write_once_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." + + # ns_host_vsock_ns_mode_ok + "Check /proc/sys/net/vsock/ns_mode strings on the host." + + # ns_host_vsock_ns_mode_write_once_ok + "Check /proc/sys/net/vsock/ns_mode is write-once on the host." )

readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) @@ -203,6 +220,20 @@ check_deps() { fi }

+check_netns() { + local tname=$1 + + # If the test requires NS support, check if NS support exists + # using /proc/self/ns + if [[ "${tname}" =~ ^ns_ ]] && + [[ ! -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 @@ -502,6 +533,43 @@ log_guest() { LOG_PREFIX=guest log $@ }

+test_ns_host_vsock_ns_mode_ok() { + add_namespaces + + for mode in "${NS_MODES[@]}"; do + if ! ns_set_mode "${mode}0" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi + done + + del_namespaces + + return "${KSFT_PASS}" +} + +test_ns_host_vsock_ns_mode_write_once_ok() { + add_namespaces + + for mode in "${NS_MODES[@]}"; do + local ns="${mode}0" + if ! ns_set_mode "${ns}" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi + + # try writing again and expect failure + if ns_set_mode "${ns}" "${mode}"; then + del_namespaces + return "${KSFT_FAIL}" + fi + done + + del_namespaces + + return "${KSFT_PASS}" +} + test_vm_server_host_client() { if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then return "${KSFT_FAIL}" @@ -575,6 +643,11 @@ run_shared_vm_tests() { continue fi

+ if ! check_netns "${arg}"; then + check_result "${KSFT_SKIP}" + continue + fi + run_shared_vm_test "${arg}" check_result $? done @@ -628,6 +701,28 @@ run_shared_vm_test() { return "${rc}" }

+run_tests() { + for arg in "${ARGS[@]}"; do + if shared_vm_test "${arg}"; then + continue + fi + + if ! check_netns "${arg}"; then + check_result "${KSFT_SKIP}" + continue + fi + + add_namespaces + + 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)"

@@ -671,6 +766,8 @@ if shared_vm_tests_requested "${ARGS[@]}"; then terminate_pidfiles "${pidfile}" fi

+run_tests "${ARGS[@]}" + echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" echo "Log: ${LOG}"

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests to validate namespace correctness using vsock_test and socat. The vsock_test tool is used to validate expected success tests, but socat is used for expected failure tests. socat is used to ensure that connections are rejected outright instead of failing due to some other socket behavior (as tested in vsock_test). Additionally, socat is already required for tunneling TCP traffic from vsock_test. Using only one of the vsock_test tests like 'test_stream_client_close_client' would have yielded a similar result, but doing so wouldn't remove the socat dependency.

Additionally, check for the dependency socat. socat needs special handling beyond just checking if it is on the path because it must be compiled with support for both vsock and unix. The function check_socat() checks that this support exists.

Add more padding to test name printf strings because the tests added in this patch would otherwise overflow.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 463 +++++++++++++++++++++++++++++++- 1 file changed, 461 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index f2a99cde9fb4..60d349c80153 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}"/../../../../) @@ -48,6 +49,19 @@ readonly TEST_NAMES=( ns_local_same_cid_ok ns_global_local_same_cid_ok ns_local_global_same_cid_ok + ns_diff_global_host_connect_to_global_vm_ok + ns_diff_global_host_connect_to_local_vm_fails + ns_diff_global_vm_connect_to_global_host_ok + ns_diff_global_vm_connect_to_local_host_fails + ns_diff_local_host_connect_to_local_vm_fails + ns_diff_local_vm_connect_to_local_host_fails + ns_diff_global_to_local_loopback_local_fails + ns_diff_local_to_global_loopback_fails + ns_diff_local_to_local_loopback_fails + ns_diff_global_to_global_loopback_ok + ns_same_local_loopback_ok + ns_same_local_host_connect_to_local_vm_ok + ns_same_local_vm_connect_to_local_host_ok ) readonly TEST_DESCS=( # vm_server_host_client @@ -76,6 +90,45 @@ readonly TEST_DESCS=(

# 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." + + # ns_diff_global_host_connect_to_global_vm_ok + "Run vsock_test client in global ns with server in VM in another global ns." + + # ns_diff_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." + + # ns_diff_global_vm_connect_to_global_host_ok + "Run vsock_test client in VM in a global ns with server in another global ns." + + # ns_diff_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." + + # ns_diff_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." + + # ns_diff_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." + + # ns_diff_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." + + # ns_diff_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." + + # ns_diff_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." + + # ns_diff_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." + + # ns_same_local_loopback_ok + "Run socat to test a loopback vsock in a local ns successfully connects to a vsock in the same ns." + + # ns_same_local_host_connect_to_local_vm_ok + "Run vsock_test client in a local ns with server in VM in same ns." + + # ns_same_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) @@ -102,7 +155,7 @@ 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

@@ -222,7 +275,7 @@ 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}" @@ -273,6 +326,20 @@ 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 @@ -310,6 +377,14 @@ terminate_pidfiles() { done }

+terminate_pids() { + local pid + + for pid in "$@"; do + kill -SIGTERM "${pid}" &>/dev/null || : + done +} + vm_start() { local pidfile=$1 local ns=$2 @@ -564,6 +639,389 @@ test_ns_host_vsock_ns_mode_ok() { return "${KSFT_PASS}" }

+test_ns_diff_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 + + init_namespaces + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + + if ! vm_start "${pidfile}" "${ns0}"; then + return "${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}" "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 "${KSFT_PASS}" +} + +test_ns_diff_global_host_connect_to_local_vm_fails() { + local ns0="global0" + local ns1="local0" + local port=12345 + local pidfile + local result + local pid + + init_namespaces + + outfile=$(mktemp) + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + if ! vm_start "${pidfile}" "${ns1}"; then + log_host "failed to start vm (cid=${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_ns_diff_global_vm_connect_to_global_host_ok() { + local ns0="global0" + local ns1="global1" + local port=12345 + local unixfile + local pidfile + local pids + + init_namespaces + + 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 $PIDFILE_TEMPLATE) + if ! vm_start "${pidfile}" "${ns0}"; then + log_host "failed to start vm (cid=${cid}, ns=${ns0})" + terminate_pids "${pids[@]}" + rm -f "${unixfile}" + return $KSFT_FAIL + fi + + vm_wait_for_ssh "${ns0}" + vm_vsock_test "${ns0}" "10.0.2.2" 2 "${port}" + rc=$? + + terminate_pidfiles "${pidfile}" + terminate_pids "${pids[@]}" + rm -f "${unixfile}" + + if [[ ! $rc -eq 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" + +} + +test_ns_diff_global_vm_connect_to_local_host_fails() { + local ns0="global0" + local ns1="local0" + local port=12345 + local pidfile + local result + local pid + + init_namespaces + + log_host "Launching socat in ns ${ns1}" + outfile=$(mktemp) + ip netns exec "${ns1}" socat VSOCK-LISTEN:${port} STDOUT &> "${outfile}" & + pid=$! + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + if ! vm_start "${pidfile}" "${ns0}"; then + log_host "failed to start vm (cid=${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_ns_diff_local_host_connect_to_local_vm_fails() { + local ns0="local0" + local ns1="local1" + local port=12345 + local pidfile + local result + local pid + + init_namespaces + + outfile=$(mktemp) + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + if ! vm_start "${pidfile}" "${ns1}"; then + log_host "failed to start vm (cid=${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_ns_diff_local_vm_connect_to_local_host_fails() { + local ns0="local0" + local ns1="local1" + local port=12345 + local pidfile + local result + local pid + + init_namespaces + + log_host "Launching socat in ns ${ns1}" + outfile=$(mktemp) + ip netns exec "${ns1}" socat VSOCK-LISTEN:"${port}" STDOUT &> "${outfile}" & + pid=$! + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + if ! vm_start "${pidfile}" "${ns0}"; then + log_host "failed to start vm (cid=${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_ns_diff_global_to_local_loopback_local_fails() { + init_namespaces + + if ! __test_loopback_two_netns "global0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_diff_local_to_global_loopback_fails() { + init_namespaces + + if ! __test_loopback_two_netns "local0" "global0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_diff_local_to_local_loopback_fails() { + init_namespaces + + if ! __test_loopback_two_netns "local0" "local1"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_diff_global_to_global_loopback_ok() { + init_namespaces + + if __test_loopback_two_netns "global0" "global1"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_same_local_loopback_ok() { + init_namespaces + + if __test_loopback_two_netns "local0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_same_local_host_connect_to_local_vm_ok() { + local ns="local0" + local port=1234 + local pidfile + local rc + + init_namespaces + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + + if ! vm_start "${pidfile}" "${ns}"; then + return "${KSFT_FAIL}" + fi + + vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}" + host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}" + rc=$? + + terminate_pidfiles "${pidfile}" + + if [[ $rc -ne 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_ns_same_local_vm_connect_to_local_host_ok() { + local ns="local0" + local port=1234 + local pidfile + local rc + + init_namespaces + + pidfile=$(mktemp $PIDFILE_TEMPLATE) + + if ! vm_start "${pidfile}" "${ns}"; then + return "${KSFT_FAIL}" + fi + + vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}" + host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}" + rc=$? + + terminate_pidfiles "${pidfile}" + + if [[ $rc -ne 0 ]]; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + namespaces_can_boot_same_cid() { local ns0=$1 local ns1=$2 @@ -820,6 +1278,7 @@ fi check_args "${ARGS[@]}" check_deps check_vng +check_socat handle_build

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

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests to check that module loading order does not break vsock_loopback. Because vsock_loopback has some per-namespace data structure initialization that affects vsock namespace modes, lets make sure that namespace modes are respected and loopback sockets are functional even when the namespaces and modes are set prior to loading the vsock_loopback module.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 138 ++++++++++++++++++++++++++++++++ 1 file changed, 138 insertions(+)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 014cecd93858..9aa3200b160f 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -68,6 +68,8 @@ readonly TEST_NAMES=( ns_delete_vm_ok ns_delete_host_ok ns_delete_both_ok + ns_loopback_global_global_late_module_load_ok + ns_loopback_local_local_late_module_load_fails ) readonly TEST_DESCS=( # vm_server_host_client @@ -153,6 +155,12 @@ readonly TEST_DESCS=(

# ns_delete_both_ok "Check that deleting the VM and host's namespaces does not break the socket connection" + + # ns_loopback_global_global_late_module_load_ok + "Test that loopback still works in global namespaces initialized prior to loading the vsock_loopback kmod" + + # ns_loopback_local_local_late_module_load_fails + "Test that loopback connections still fail between local namespaces initialized prior to loading the vsock_loopback kmod" )

readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) @@ -914,6 +922,30 @@ test_ns_diff_local_vm_connect_to_local_host_fails() { return "${KSFT_FAIL}" }

+unload_module() { + local module=$1 + local retries=5 + readonly retries + local delay=1 + local i + + # Sometimes previously executed tests may result in a delayed release + # of the reference to the vsock_loopback module and result in the + # module being unremovable. For that reason, we use retries to allow + # some time for those references to be dropped. + for ((i = 0; i < ${retries}; i++)); do + modprobe -r "${module}" 2>/dev/null || : + + if [[ "$(lsmod | grep -c ${module})" -eq 0 ]]; then + return 0 + fi + + sleep ${delay} + done + + return 1 +} + __test_loopback_two_netns() { local ns0=$1 local ns1=$2 @@ -1266,6 +1298,112 @@ test_ns_delete_both_ok() { check_ns_changes_dont_break_connection "both" "delete" }

+test_ns_loopback_global_global_late_module_load_ok() { + declare -a pids + local unixfile + local ns0 ns1 + local pids + local port + + if ! unload_module vsock_loopback; then + log_host "Unable to unload vsock_loopback, skipping..." + return "${KSFT_SKIP}" + fi + + ns0=loopback_ns0 + ns1=loopback_ns1 + + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + ip netns add "${ns0}" + ip netns add "${ns1}" + ns_set_mode "${ns0}" global + ns_set_mode "${ns1}" global + ip netns exec "${ns0}" ip link set dev lo up + ip netns exec "${ns1}" ip link set dev lo up + + modprobe vsock_loopback &> /dev/null || : + + unixfile=$(mktemp -u /tmp/XXXX.sock) + port=321 + ip netns exec "${ns1}" \ + socat TCP-LISTEN:"${port}",fork \ + UNIX-CONNECT:"${unixfile}" & + pids+=($!) + + host_wait_for_listener "${ns1}" "${port}" + ip netns exec "${ns0}" socat UNIX-LISTEN:"${unixfile}",fork \ + TCP-CONNECT:localhost:"${port}" & + pids+=($!) + + if ! host_vsock_test "${ns0}" "server" 1 "${port}"; then + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + terminate_pids "${pids[@]}" + return "${KSFT_FAIL}" + fi + + if ! host_vsock_test "${ns1}" "127.0.0.1" 1 "${port}"; then + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + terminate_pids "${pids[@]}" + return "${KSFT_FAIL}" + fi + + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + terminate_pids "${pids[@]}" + + return "${KSFT_PASS}" +} + +test_ns_loopback_local_local_late_module_load_fails() { + declare -a pids + local ns0 ns1 + local outfile + local pids + local rc + + if ! unload_module vsock_loopback; then + log_host "Unable to unload vsock_loopback, skipping..." + return "${KSFT_SKIP}" + fi + + ns0=loopback_ns0 + ns1=loopback_ns1 + + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + ip netns add "${ns0}" + ip netns add "${ns1}" + ns_set_mode "${ns0}" local + ns_set_mode "${ns1}" local + + modprobe vsock_loopback &> /dev/null || : + + outfile=$(mktemp /tmp/XXXX.vmtest.out) + ip netns exec "${ns0}" socat VSOCK-LISTEN:${port} STDOUT \ + > "${outfile}" 2>/dev/null & + pids+=($!) + + echo TEST | \ + ip netns exec "${ns1}" socat STDIN VSOCK-CONNECT:1:${port} \ + 2>/dev/null + + if grep -q "TEST" "${outfile}" 2>/dev/null; then + rc="${KSFT_FAIL}" + else + rc="${KSFT_PASS}" + fi + + ip netns del "${ns0}" &>/dev/null || : + ip netns del "${ns1}" &>/dev/null || : + terminate_pids "${pids[@]}" + rm -f "${outfile}" + + return "${rc}" +} + shared_vm_test() { local tname