From: Bobby Eshleman bobbyeshleman@meta.com

Add a net pointer to the vsock skb and helpers for getting/setting it. This is in preparation for adding vsock NS support.

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

--- Changes in v5: - some diff context change due to rebase to current net-next --- include/linux/virtio_vsock.h | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 0c67543a45c8..c547cda7196b 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -13,6 +13,7 @@ struct virtio_vsock_skb_cb { bool reply; bool tap_delivered; u32 offset; + struct net *net; };

#define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb)) @@ -130,6 +131,16 @@ static inline size_t virtio_vsock_skb_len(struct sk_buff *skb) return (size_t)(skb_end_pointer(skb) - skb->head); }

+static inline struct net *virtio_vsock_skb_net(struct sk_buff *skb) +{ + return VIRTIO_VSOCK_SKB_CB(skb)->net; +} + +static inline void virtio_vsock_skb_set_net(struct sk_buff *skb, struct net *net) +{ + VIRTIO_VSOCK_SKB_CB(skb)->net = net; +} + /* 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

From: Bobby Eshleman bobbyeshleman@meta.com

Add NS support to vsock loopback. Sockets in a global mode netns communicate with each other, regardless of namespace. Sockets in a local mode netns may only communicate with other sockets within the same namespace.

Add callbacks for transport to hook into the initialization and exit of net namespaces.

The transport's init hook will be called once per netns init. Likewise for exit.

When a set of init/exit callbacks is registered, the init callback is called on each already existing namespace.

Only one callback registration is supported for now. Currently vsock_loopback is the only user.

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

--- Changes in v5: - add callbacks code to avoid reverse dependency - add logic for handling vsock_loopback setup for already existing namespaces --- include/net/af_vsock.h | 34 +++++++++++++ include/net/netns/vsock.h | 5 ++ net/vmw_vsock/af_vsock.c | 110 +++++++++++++++++++++++++++++++++++++++++ net/vmw_vsock/vsock_loopback.c | 72 ++++++++++++++++++++++++--- 4 files changed, 213 insertions(+), 8 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 83f873174ba3..9333a98b9a1e 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -305,4 +305,38 @@ static inline bool vsock_net_check_mode(struct net *n1, struct net *n2) (vsock_net_mode(n1) == VSOCK_NET_MODE_GLOBAL && vsock_net_mode(n2) == VSOCK_NET_MODE_GLOBAL); } + +struct vsock_net_callbacks { + int (*init)(struct net *net); + void (*exit)(struct net *net); + struct module *owner; +}; + +#if IS_ENABLED(CONFIG_VSOCKETS_LOOPBACK) + +#define vsock_register_net_callbacks(__init, __exit) \ + __vsock_register_net_callbacks((__init), (__exit), THIS_MODULE) + +int __vsock_register_net_callbacks(int (*init)(struct net *net), + void (*exit)(struct net *net), + struct module *owner); +void vsock_unregister_net_callbacks(void); + +#else + +#define vsock_register_net_callbacks(__init, __exit) do { } while (0) + +static inline int __vsock_register_net_callbacks(int (*init)(struct net *net), + void (*exit)(struct net *net), + struct module *owner) +{ + return 0; +} + +static inline void vsock_unregister_net_callbacks(void) {} +static inline int vsock_net_call_init(struct net *net) { return 0; } +static inline void vsock_net_call_exit(struct net *net) {} + +#endif /* CONFIG_VSOCKETS_LOOPBACK */ + #endif /* __AF_VSOCK_H__ */ diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h index d4593c0b8dc4..08d9a933c540 100644 --- a/include/net/netns/vsock.h +++ b/include/net/netns/vsock.h @@ -9,6 +9,8 @@ enum vsock_net_mode { VSOCK_NET_MODE_LOCAL, };

+struct vsock_loopback; + struct netns_vsock { struct ctl_table_header *vsock_hdr; spinlock_t lock; @@ -16,5 +18,8 @@ struct netns_vsock { /* protected by lock */ enum vsock_net_mode mode; bool written; +#if IS_ENABLED(CONFIG_VSOCKETS_LOOPBACK) + struct vsock_loopback *loopback; +#endif }; #endif /* __NET_NET_NAMESPACE_VSOCK_H */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 68a8875c8106..5a73d9e1a96f 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -134,6 +134,9 @@ #include <uapi/linux/vm_sockets.h> #include <uapi/asm-generic/ioctls.h>

+static struct vsock_net_callbacks vsock_net_callbacks; +static DEFINE_MUTEX(vsock_net_callbacks_lock); + 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); @@ -2781,6 +2784,49 @@ static void vsock_net_init(struct net *net) net->vsock.mode = VSOCK_NET_MODE_GLOBAL; }

+#if IS_ENABLED(CONFIG_VSOCKETS_LOOPBACK) +static int vsock_net_call_init(struct net *net) +{ + struct vsock_net_callbacks *cbs; + int ret; + + mutex_lock(&vsock_net_callbacks_lock); + cbs = &vsock_net_callbacks; + + ret = 0; + if (!cbs->owner) + goto out; + + if (try_module_get(cbs->owner)) { + ret = cbs->init(net); + module_put(cbs->owner); + } + +out: + mutex_unlock(&vsock_net_callbacks_lock); + return ret; +} + +static void vsock_net_call_exit(struct net *net) +{ + struct vsock_net_callbacks *cbs; + + mutex_lock(&vsock_net_callbacks_lock); + cbs = &vsock_net_callbacks; + + if (!cbs->owner) + goto out; + + if (try_module_get(cbs->owner)) { + cbs->exit(net); + module_put(cbs->owner); + } + +out: + mutex_unlock(&vsock_net_callbacks_lock); +} +#endif /* CONFIG_VSOCKETS_LOOPBACK */ + static __net_init int vsock_sysctl_init_net(struct net *net) { vsock_net_init(net); @@ -2788,12 +2834,20 @@ static __net_init int vsock_sysctl_init_net(struct net *net) if (vsock_sysctl_register(net)) return -ENOMEM;

+ if (vsock_net_call_init(net) < 0) + goto err_sysctl; + return 0; + +err_sysctl: + vsock_sysctl_unregister(net); + return -ENOMEM; }

static __net_exit void vsock_sysctl_exit_net(struct net *net) { vsock_sysctl_unregister(net); + vsock_net_call_exit(net); }

static struct pernet_operations vsock_sysctl_ops __net_initdata = { @@ -2938,6 +2992,62 @@ void vsock_core_unregister(const struct vsock_transport *t) } EXPORT_SYMBOL_GPL(vsock_core_unregister);

+#if IS_ENABLED(CONFIG_VSOCKETS_LOOPBACK) +int __vsock_register_net_callbacks(int (*init)(struct net *net), + void (*exit)(struct net *net), + struct module *owner) +{ + struct vsock_net_callbacks *cbs; + struct net *net; + int ret = 0; + + mutex_lock(&vsock_net_callbacks_lock); + + cbs = &vsock_net_callbacks; + cbs->init = init; + cbs->exit = exit; + cbs->owner = owner; + + /* call callbacks on any net previously created */ + down_read(&net_rwsem); + + if (try_module_get(cbs->owner)) { + for_each_net(net) { + ret = cbs->init(net); + if (ret < 0) + break; + } + + if (ret < 0) + for_each_net(net) + cbs->exit(net); + + module_put(cbs->owner); + } + + up_read(&net_rwsem); + mutex_unlock(&vsock_net_callbacks_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(__vsock_register_net_callbacks); + +void vsock_unregister_net_callbacks(void) +{ + struct vsock_net_callbacks *cbs; + + mutex_lock(&vsock_net_callbacks_lock); + + cbs = &vsock_net_callbacks; + cbs->init = NULL; + cbs->exit = NULL; + cbs->owner = NULL; + + mutex_unlock(&vsock_net_callbacks_lock); +} +EXPORT_SYMBOL_GPL(vsock_unregister_net_callbacks); +#endif /* CONFIG_VSOCKETS_LOOPBACK */ + module_init(vsock_init); module_exit(vsock_exit);

diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 1b2fab73e0d0..f16d21711cb0 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -28,8 +28,19 @@ static u32 vsock_loopback_get_local_cid(void)

static int vsock_loopback_send_pkt(struct sk_buff *skb) { - struct vsock_loopback *vsock = &the_vsock_loopback; + struct vsock_loopback *vsock; int len = skb->len; + struct net *net; + + if (skb->sk) + net = sock_net(skb->sk); + else + net = NULL; + + if (net && net->vsock.mode == VSOCK_NET_MODE_LOCAL) + vsock = net->vsock.loopback; + else + vsock = &the_vsock_loopback;

virtio_vsock_skb_queue_tail(&vsock->pkt_queue, skb); queue_work(vsock->workqueue, &vsock->pkt_work); @@ -134,27 +145,72 @@ static void vsock_loopback_work(struct work_struct *work) } }

-static int __init vsock_loopback_init(void) +static int vsock_loopback_init_vsock(struct vsock_loopback *vsock) { - struct vsock_loopback *vsock = &the_vsock_loopback; - int ret; - vsock->workqueue = alloc_workqueue("vsock-loopback", 0, 0); if (!vsock->workqueue) return -ENOMEM;

skb_queue_head_init(&vsock->pkt_queue); INIT_WORK(&vsock->pkt_work, vsock_loopback_work); + return 0; +} + +static void vsock_loopback_deinit_vsock(struct vsock_loopback *vsock) +{ + if (vsock->workqueue) + destroy_workqueue(vsock->workqueue); +} + +/* called with vsock_net_callbacks lock held */ +static int vsock_loopback_init_net(struct net *net) +{ + if (WARN_ON_ONCE(net->vsock.loopback)) + return 0; + + net->vsock.loopback = kmalloc(sizeof(*net->vsock.loopback), GFP_KERNEL); + if (!net->vsock.loopback) + return -ENOMEM; + + return vsock_loopback_init_vsock(net->vsock.loopback); +} + +/* called with vsock_net_callbacks lock held */ +static void vsock_loopback_exit_net(struct net *net) +{ + if (net->vsock.loopback) { + vsock_loopback_deinit_vsock(net->vsock.loopback); + kfree(net->vsock.loopback); + } +} + +static int __init vsock_loopback_init(void) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + int ret; + + ret = vsock_loopback_init_vsock(vsock); + if (ret < 0) + return ret; + + ret = vsock_register_net_callbacks(vsock_loopback_init_net, + vsock_loopback_exit_net); + if (ret < 0) + goto out_deinit_vsock;

ret = vsock_core_register(&loopback_transport.transport, VSOCK_TRANSPORT_F_LOCAL); if (ret) - goto out_wq; + goto out_unregister_net; +

return 0;

-out_wq: - destroy_workqueue(vsock->workqueue); +out_unregister_net: + vsock_unregister_net_callbacks(); + +out_deinit_vsock: + vsock_loopback_deinit_vsock(vsock); return ret; }

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 | 14 ++++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c547cda7196b..ce6d15eede9c 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -184,6 +184,7 @@ 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 9b3aa4f0395d..7b566c8f8082 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -314,6 +314,8 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info * info->flags, zcopy);

+ virtio_vsock_skb_set_net(skb, info->net); + return skb; out: kfree_skb(skb); @@ -525,6 +527,7 @@ 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); @@ -1065,6 +1068,7 @@ 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); @@ -1080,6 +1084,7 @@ 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); @@ -1106,6 +1111,7 @@ 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); @@ -1143,6 +1149,7 @@ 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 */ @@ -1163,6 +1170,7 @@ 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;

@@ -1463,6 +1471,7 @@ 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); @@ -1577,6 +1586,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, struct sk_buff *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; @@ -1604,9 +1614,9 @@ 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); if (!sk) { - sk = vsock_find_bound_socket(&dst, vsock_global_dummy_net()); + sk = vsock_find_bound_socket(&dst, net); 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 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 | 913 ++++++++++++++++++++++++++++---- 1 file changed, 808 insertions(+), 105 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 5e36d1068f6f..9d830eb7e829 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 +34,125 @@ 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 MODES=("local" "global")

readonly LOG_LEVEL_DEBUG=0 readonly LOG_LEVEL_INFO=1 @@ -58,6 +161,12 @@ 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 +186,7 @@ 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 +198,87 @@ 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 +308,7 @@ 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}" @@ -170,6 +345,20 @@ 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 +383,14 @@ 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 +400,37 @@ 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 +438,8 @@ 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=$(( i + 1 )) @@ -269,6 +474,7 @@ wait_for_listener() grep -q "${pattern}"; then break fi + sleep "${interval}" done

@@ -278,17 +484,29 @@ 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 +645,506 @@ 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 }

-run_test() { + +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_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 +1156,93 @@ 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=$KSFT_FAIL - fi + host_oops_cnt_before=$(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=$KSFT_FAIL + fi + + host_warn_cnt_after=$(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

- 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=$KSFT_FAIL + check_result "${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

- return "${rc}" + add_namespaces + if init_netns_test "${arg}"; then + init_namespaces + fi + + 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 +1267,13 @@ 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}"