* [PATCH net-next v10 02/11] vsock: add netns to vsock core
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add netns logic to vsock core. Additionally, modify transport hook
prototypes to be used by later transport-specific patches (e.g.,
*_seqpacket_allow()).
Namespaces are supported primarily by changing socket lookup functions
(e.g., vsock_find_connected_socket()) to take into account the socket
namespace and the namespace mode before considering a candidate socket a
"match".
This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode that
accepts the "global" or "local" mode strings.
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 v10:
- add file-level comment about what happens to sockets/devices
when the namespace mode changes (Stefano)
- change the 'if (write)' boolean in vsock_net_mode_string() to
if (!write), this simplifies a later patch which adds "goto"
for mutex unlocking on function exit.
Changes in v9:
- remove virtio_vsock_alloc_rx_skb() (Stefano)
- remove vsock_global_dummy_net, not needed as net=NULL +
net_mode=VSOCK_NET_MODE_GLOBAL achieves identical result
Changes in v7:
- hv_sock: fix hyperv build error
- explain why vhost does not use the dummy
- explain usage of __vsock_global_dummy_net
- explain why VSOCK_NET_MODE_STR_MAX is 8 characters
- use switch-case in vsock_net_mode_string()
- avoid changing transports as much as possible
- add vsock_find_{bound,connected}_socket_net()
- rename `vsock_hdr` to `sysctl_hdr`
- add virtio_vsock_alloc_linear_skb() wrapper for setting dummy net and
global mode for virtio-vsock, move skb->cb zero-ing into wrapper
- explain seqpacket_allow() change
- move net setting to __vsock_create() instead of vsock_create() so
that child sockets also have their net assigned upon accept()
Changes in v6:
- unregister sysctl ops in vsock_exit()
- af_vsock: clarify description of CID behavior
- af_vsock: fix buf vs buffer naming, and length checking
- af_vsock: fix length checking w/ correct ctl_table->maxlen
Changes in v5:
- vsock_global_net() -> vsock_global_dummy_net()
- update comments for new uAPI
- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
- add prototype changes so patch remains compilable
---
drivers/vhost/vsock.c | 6 +-
include/net/af_vsock.h | 9 +-
net/vmw_vsock/af_vsock.c | 258 ++++++++++++++++++++++++++++++++++++---
net/vmw_vsock/virtio_transport.c | 6 +-
net/vmw_vsock/vsock_loopback.c | 6 +-
5 files changed, 261 insertions(+), 24 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ae01457ea2cd..2c937a2df83b 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -404,7 +404,8 @@ static bool vhost_transport_msgzerocopy_allow(void)
return true;
}
-static bool vhost_transport_seqpacket_allow(u32 remote_cid);
+static bool
+vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
static struct virtio_transport vhost_transport = {
.transport = {
@@ -460,7 +461,8 @@ static struct virtio_transport vhost_transport = {
.send_pkt = vhost_transport_send_pkt,
};
-static bool vhost_transport_seqpacket_allow(u32 remote_cid)
+static bool
+vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
struct vhost_vsock *vsock;
bool seqpacket_allow = false;
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9b5bdd083b6f..59d97a143204 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -145,7 +145,7 @@ struct vsock_transport {
int flags);
int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg,
size_t len);
- bool (*seqpacket_allow)(u32 remote_cid);
+ bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid);
u32 (*seqpacket_has_data)(struct vsock_sock *vsk);
/* Notification. */
@@ -218,6 +218,13 @@ void vsock_remove_connected(struct vsock_sock *vsk);
struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr);
struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
struct sockaddr_vm *dst);
+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode);
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode);
void vsock_remove_sock(struct vsock_sock *vsk);
void vsock_for_each_connected_socket(struct vsock_transport *transport,
void (*fn)(struct sock *sk));
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 72bb6b7ed386..54373ae101c3 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -83,6 +83,38 @@
* TCP_ESTABLISHED - connected
* TCP_CLOSING - disconnecting
* TCP_LISTEN - listening
+ *
+ * - Namespaces in vsock support two different modes configured
+ * through /proc/sys/net/vsock/ns_mode. The modes are "local" and "global".
+ * Each mode defines how the namespace interacts with CIDs.
+ * /proc/sys/net/vsock/ns_mode is write-once, so that it may be configured
+ * and locked down by a namespace manager. The default is "global". The mode
+ * is set per-namespace.
+ *
+ * The modes affect the allocation and accessibility of CIDs as follows:
+ *
+ * - global - access and allocation are all system-wide
+ * - all CID allocation from global namespaces draw from the same
+ * system-wide pool.
+ * - if one global namespace has already allocated some CID, another
+ * global namespace will not be able to allocate the same CID.
+ * - global mode AF_VSOCK sockets can reach any VM or socket in any global
+ * namespace, they are not contained to only their own namespace.
+ * - AF_VSOCK sockets in a global mode namespace cannot reach VMs or
+ * sockets in any local mode namespace.
+ * - local - access and allocation are contained within the namespace
+ * - CID allocation draws only from a private pool local only to the
+ * namespace, and does not affect the CIDs available for allocation in any
+ * other namespace (global or local).
+ * - VMs in a local namespace do not collide with CIDs in any other local
+ * namespace or any global namespace. For example, if a VM in a local mode
+ * namespace is given CID 10, then CID 10 is still available for
+ * allocation in any other namespace, but not in the same namespace.
+ * - AF_VSOCK sockets in a local mode namespace can connect only to VMs or
+ * other sockets within their own namespace.
+ * - when a socket or device is initialized in a namespace with mode
+ * global, it will stay in global mode even if the namespace later
+ * changes to local.
*/
#include <linux/compat.h>
@@ -100,6 +132,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/net.h>
+#include <linux/proc_fs.h>
#include <linux/poll.h>
#include <linux/random.h>
#include <linux/skbuff.h>
@@ -111,9 +144,18 @@
#include <linux/workqueue.h>
#include <net/sock.h>
#include <net/af_vsock.h>
+#include <net/netns/vsock.h>
#include <uapi/linux/vm_sockets.h>
#include <uapi/asm-generic/ioctls.h>
+#define VSOCK_NET_MODE_STR_GLOBAL "global"
+#define VSOCK_NET_MODE_STR_LOCAL "local"
+
+/* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'.
+ * The newline is added by proc_dostring() for read operations.
+ */
+#define VSOCK_NET_MODE_STR_MAX 8
+
static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
static void vsock_sk_destruct(struct sock *sk);
static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
@@ -235,33 +277,47 @@ static void __vsock_remove_connected(struct vsock_sock *vsk)
sock_put(&vsk->sk);
}
-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_sock *vsk;
list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
- if (vsock_addr_equals_addr(addr, &vsk->local_addr))
- return sk_vsock(vsk);
+ struct sock *sk = sk_vsock(vsk);
+
+ if (vsock_addr_equals_addr(addr, &vsk->local_addr) &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
+ net_mode))
+ return sk;
if (addr->svm_port == vsk->local_addr.svm_port &&
(vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
- addr->svm_cid == VMADDR_CID_ANY))
- return sk_vsock(vsk);
+ addr->svm_cid == VMADDR_CID_ANY) &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
+ net_mode))
+ return sk;
}
return NULL;
}
-static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
- struct sockaddr_vm *dst)
+static struct sock *
+__vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_sock *vsk;
list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
connected_table) {
+ struct sock *sk = sk_vsock(vsk);
+
if (vsock_addr_equals_addr(src, &vsk->remote_addr) &&
- dst->svm_port == vsk->local_addr.svm_port) {
- return sk_vsock(vsk);
+ dst->svm_port == vsk->local_addr.svm_port &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
+ net_mode)) {
+ return sk;
}
}
@@ -304,12 +360,14 @@ void vsock_remove_connected(struct vsock_sock *vsk)
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);
-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct sock *sk;
spin_lock_bh(&vsock_table_lock);
- sk = __vsock_find_bound_socket(addr);
+ sk = __vsock_find_bound_socket_net(addr, net, net_mode);
if (sk)
sock_hold(sk);
@@ -317,15 +375,23 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net);
+
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+{
+ return vsock_find_bound_socket_net(addr, NULL, VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_bound_socket);
-struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
- struct sockaddr_vm *dst)
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct sock *sk;
spin_lock_bh(&vsock_table_lock);
- sk = __vsock_find_connected_socket(src, dst);
+ sk = __vsock_find_connected_socket_net(src, dst, net, net_mode);
if (sk)
sock_hold(sk);
@@ -333,6 +399,14 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net);
+
+struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst)
+{
+ return vsock_find_connected_socket_net(src, dst,
+ NULL, VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
@@ -528,7 +602,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
- !new_transport->seqpacket_allow(remote_cid)) {
+ !new_transport->seqpacket_allow(vsk, remote_cid)) {
module_put(new_transport->module);
return -ESOCKTNOSUPPORT;
}
@@ -676,6 +750,7 @@ static void vsock_pending_work(struct work_struct *work)
static int __vsock_bind_connectible(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
+ struct net *net = sock_net(sk_vsock(vsk));
static u32 port;
struct sockaddr_vm new_addr;
@@ -695,7 +770,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
new_addr.svm_port = port++;
- if (!__vsock_find_bound_socket(&new_addr)) {
+ if (!__vsock_find_bound_socket_net(&new_addr, net,
+ vsk->net_mode)) {
found = true;
break;
}
@@ -712,7 +788,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
return -EACCES;
}
- if (__vsock_find_bound_socket(&new_addr))
+ if (__vsock_find_bound_socket_net(&new_addr, net,
+ vsk->net_mode))
return -EADDRINUSE;
}
@@ -836,6 +913,8 @@ static struct sock *__vsock_create(struct net *net,
vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE;
}
+ vsk->net_mode = vsock_net_mode(net);
+
return sk;
}
@@ -2636,6 +2715,142 @@ static struct miscdevice vsock_device = {
.fops = &vsock_device_ops,
};
+static int vsock_net_mode_string(const struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ char data[VSOCK_NET_MODE_STR_MAX] = {0};
+ enum vsock_net_mode mode;
+ struct ctl_table tmp;
+ struct net *net;
+ int ret;
+
+ if (!table->data || !table->maxlen || !*lenp) {
+ *lenp = 0;
+ return 0;
+ }
+
+ net = current->nsproxy->net_ns;
+ tmp = *table;
+ tmp.data = data;
+
+ if (!write) {
+ const char *p;
+
+ mode = vsock_net_mode(net);
+
+ switch (mode) {
+ case VSOCK_NET_MODE_GLOBAL:
+ p = VSOCK_NET_MODE_STR_GLOBAL;
+ break;
+ case VSOCK_NET_MODE_LOCAL:
+ p = VSOCK_NET_MODE_STR_LOCAL;
+ break;
+ default:
+ WARN_ONCE(true, "netns has invalid vsock mode");
+ *lenp = 0;
+ return 0;
+ }
+
+ strscpy(data, p, sizeof(data));
+ tmp.maxlen = strlen(p);
+ }
+
+ ret = proc_dostring(&tmp, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+
+ if (!write)
+ return 0;
+
+ if (*lenp >= sizeof(data))
+ return -EINVAL;
+
+ if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_GLOBAL;
+ else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_LOCAL;
+ else
+ return -EINVAL;
+
+ if (!vsock_net_write_mode(net, mode))
+ return -EPERM;
+
+ return 0;
+}
+
+static struct ctl_table vsock_table[] = {
+ {
+ .procname = "ns_mode",
+ .data = &init_net.vsock.mode,
+ .maxlen = VSOCK_NET_MODE_STR_MAX,
+ .mode = 0644,
+ .proc_handler = vsock_net_mode_string
+ },
+};
+
+static int __net_init vsock_sysctl_register(struct net *net)
+{
+ struct ctl_table *table;
+
+ if (net_eq(net, &init_net)) {
+ table = vsock_table;
+ } else {
+ table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL);
+ if (!table)
+ goto err_alloc;
+
+ table[0].data = &net->vsock.mode;
+ }
+
+ net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table,
+ ARRAY_SIZE(vsock_table));
+ if (!net->vsock.sysctl_hdr)
+ goto err_reg;
+
+ return 0;
+
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void vsock_sysctl_unregister(struct net *net)
+{
+ const struct ctl_table *table;
+
+ table = net->vsock.sysctl_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->vsock.sysctl_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static void vsock_net_init(struct net *net)
+{
+ net->vsock.mode = VSOCK_NET_MODE_GLOBAL;
+}
+
+static __net_init int vsock_sysctl_init_net(struct net *net)
+{
+ vsock_net_init(net);
+
+ if (vsock_sysctl_register(net))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static __net_exit void vsock_sysctl_exit_net(struct net *net)
+{
+ vsock_sysctl_unregister(net);
+}
+
+static struct pernet_operations vsock_sysctl_ops __net_initdata = {
+ .init = vsock_sysctl_init_net,
+ .exit = vsock_sysctl_exit_net,
+};
+
static int __init vsock_init(void)
{
int err = 0;
@@ -2663,10 +2878,18 @@ static int __init vsock_init(void)
goto err_unregister_proto;
}
+ if (register_pernet_subsys(&vsock_sysctl_ops)) {
+ err = -ENOMEM;
+ goto err_unregister_sock;
+ }
+
+ vsock_net_init(&init_net);
vsock_bpf_build_proto();
return 0;
+err_unregister_sock:
+ sock_unregister(AF_VSOCK);
err_unregister_proto:
proto_unregister(&vsock_proto);
err_deregister_misc:
@@ -2680,6 +2903,7 @@ static void __exit vsock_exit(void)
misc_deregister(&vsock_device);
sock_unregister(AF_VSOCK);
proto_unregister(&vsock_proto);
+ unregister_pernet_subsys(&vsock_sysctl_ops);
}
const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk)
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8c867023a2e5..5d379ccf3770 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -536,7 +536,8 @@ static bool virtio_transport_msgzerocopy_allow(void)
return true;
}
-static bool virtio_transport_seqpacket_allow(u32 remote_cid);
+static bool
+virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
static struct virtio_transport virtio_transport = {
.transport = {
@@ -593,7 +594,8 @@ static struct virtio_transport virtio_transport = {
.can_msgzerocopy = virtio_transport_can_msgzerocopy,
};
-static bool virtio_transport_seqpacket_allow(u32 remote_cid)
+static bool
+virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
struct virtio_vsock *vsock;
bool seqpacket_allow;
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index bc2ff918b315..8722337a4f80 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -46,7 +46,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
return 0;
}
-static bool vsock_loopback_seqpacket_allow(u32 remote_cid);
+static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk,
+ u32 remote_cid);
static bool vsock_loopback_msgzerocopy_allow(void)
{
return true;
@@ -106,7 +107,8 @@ static struct virtio_transport loopback_transport = {
.send_pkt = vsock_loopback_send_pkt,
};
-static bool vsock_loopback_seqpacket_allow(u32 remote_cid)
+static bool
+vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
return true;
}
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 03/11] vsock: reject bad VSOCK_NET_MODE_LOCAL configuration for G2H
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Reject setting VSOCK_NET_MODE_LOCAL with -EOPNOTSUPP if a G2H transport
is operational. Additionally, reject G2H transport registration if there
already exists a namespace in local mode.
G2H sockets break in local mode because the G2H transports don't support
namespacing yet. The current approach is to coerce packets coming out of
G2H transports into VSOCK_NET_MODE_GLOBAL mode, but it is not possible
to coerce sockets in the same way because it cannot be deduced which
transport will be used by the socket. Specifically, when bound to
VMADDR_CID_ANY in a nested VM (both G2H and H2G available), it is not
until a packet is received and matched to the bound socket that we
assign the transport. This presents a chicken-and-egg problem, because
we need the namespace to lookup the socket and resolve the transport,
but we need the transport to know how to use the namespace during
lookup.
For that reason, this patch prevents VSOCK_NET_MODE_LOCAL from being
used on systems that support G2H, even nested systems that also have H2G
transports.
Local mode is blocked based on detecting the presence of G2H devices
(when possible, as hyperv is special). This means that a host kernel
with G2H support compiled in (or has the module loaded), will still
support local mode if there is no G2H (e.g., virtio-vsock) device
detected. This enables using the same kernel in the host and in the
guest, as we do in kselftest.
Systems with only namespace-aware transports (vhost-vsock, loopback) can
still use both VSOCK_NET_MODE_GLOBAL and VSOCK_NET_MODE_LOCAL modes as
intended.
Add supports_local_mode() transport callback to indicate
transport-specific local mode support.
These restrictions can be lifted in a future patch series when G2H
transports gain namespace support.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v10:
- move this patch before any transports bring online namespacing (Stefano)
- move vsock_net_mode_string into critical section (Stefano)
- add ->supports_local_mode() callback to transports (Stefano)
---
drivers/vhost/vsock.c | 6 +++++
include/net/af_vsock.h | 5 ++++
net/vmw_vsock/af_vsock.c | 50 ++++++++++++++++++++++++++++++++++------
net/vmw_vsock/hyperv_transport.c | 6 +++++
net/vmw_vsock/virtio_transport.c | 13 +++++++++++
net/vmw_vsock/vmci_transport.c | 7 ++++++
net/vmw_vsock/vsock_loopback.c | 6 +++++
7 files changed, 86 insertions(+), 7 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 2c937a2df83b..c8319cd1c232 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -64,6 +64,11 @@ static u32 vhost_transport_get_local_cid(void)
return VHOST_VSOCK_DEFAULT_HOST_CID;
}
+static bool vhost_transport_supports_local_mode(void)
+{
+ return true;
+}
+
/* Callers that dereference the return value must hold vhost_vsock_mutex or the
* RCU read lock.
*/
@@ -412,6 +417,7 @@ static struct virtio_transport vhost_transport = {
.module = THIS_MODULE,
.get_local_cid = vhost_transport_get_local_cid,
+ .supports_local_mode = vhost_transport_supports_local_mode,
.init = virtio_transport_do_socket_init,
.destruct = virtio_transport_destruct,
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 59d97a143204..824d89657d41 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -180,6 +180,11 @@ struct vsock_transport {
/* Addressing. */
u32 (*get_local_cid)(void);
+ /* Return true if this transport supports VSOCK_NET_MODE_LOCAL.
+ * Otherwise, return false.
+ */
+ bool (*supports_local_mode)(void);
+
/* Read a single skb */
int (*read_skb)(struct vsock_sock *, skb_read_actor_t);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 54373ae101c3..7a235bb94437 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -91,6 +91,12 @@
* and locked down by a namespace manager. The default is "global". The mode
* is set per-namespace.
*
+ * Note: LOCAL mode is only supported when using namespace-aware transports
+ * (vhost-vsock, loopback). If a guest-to-host transport (virtio-vsock,
+ * hyperv-vsock, vmci-vsock) is loaded, attempts to set LOCAL mode will fail
+ * with EOPNOTSUPP, as these transports do not support per-namespace
+ * isolation.
+ *
* The modes affect the allocation and accessibility of CIDs as follows:
*
* - global - access and allocation are all system-wide
@@ -2765,17 +2771,30 @@ static int vsock_net_mode_string(const struct ctl_table *table, int write,
if (*lenp >= sizeof(data))
return -EINVAL;
- if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
+ ret = 0;
+ mutex_lock(&vsock_register_mutex);
+ 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)))
+ } else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data))) {
+ if (transport_g2h && transport_g2h->supports_local_mode &&
+ !transport_g2h->supports_local_mode()) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
mode = VSOCK_NET_MODE_LOCAL;
- else
- return -EINVAL;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
- if (!vsock_net_write_mode(net, mode))
- return -EPERM;
+ if (!vsock_net_write_mode(net, mode)) {
+ ret = -EPERM;
+ goto out;
+ }
- return 0;
+out:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
static struct ctl_table vsock_table[] = {
@@ -2916,6 +2935,7 @@ int vsock_core_register(const struct vsock_transport *t, int features)
{
const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local;
int err = mutex_lock_interruptible(&vsock_register_mutex);
+ struct net *net;
if (err)
return err;
@@ -2938,6 +2958,22 @@ int vsock_core_register(const struct vsock_transport *t, int features)
err = -EBUSY;
goto err_busy;
}
+
+ /* G2H sockets break in LOCAL mode namespaces because G2H
+ * transports don't support them yet. Block registering new G2H
+ * transports if we already have local mode namespaces on the
+ * system.
+ */
+ rcu_read_lock();
+ for_each_net_rcu(net) {
+ if (vsock_net_mode(net) == VSOCK_NET_MODE_LOCAL) {
+ rcu_read_unlock();
+ err = -EOPNOTSUPP;
+ goto err_busy;
+ }
+ }
+ rcu_read_unlock();
+
t_g2h = t;
}
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 432fcbbd14d4..279f04fcd81a 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -833,10 +833,16 @@ int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
return -EOPNOTSUPP;
}
+static bool hvs_supports_local_mode(void)
+{
+ return false;
+}
+
static struct vsock_transport hvs_transport = {
.module = THIS_MODULE,
.get_local_cid = hvs_get_local_cid,
+ .supports_local_mode = hvs_supports_local_mode,
.init = hvs_sock_init,
.destruct = hvs_destruct,
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 5d379ccf3770..e585cb66c6f5 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -94,6 +94,18 @@ static u32 virtio_transport_get_local_cid(void)
return ret;
}
+static bool virtio_transport_supports_local_mode(void)
+{
+ struct virtio_vsock *vsock;
+
+ rcu_read_lock();
+ vsock = rcu_dereference(the_virtio_vsock);
+ rcu_read_unlock();
+
+ /* Local mode is supported only when no G2H device is present. */
+ return vsock ? false : true;
+}
+
/* Caller need to hold vsock->tx_lock on vq */
static int virtio_transport_send_skb(struct sk_buff *skb, struct virtqueue *vq,
struct virtio_vsock *vsock, gfp_t gfp)
@@ -544,6 +556,7 @@ static struct virtio_transport virtio_transport = {
.module = THIS_MODULE,
.get_local_cid = virtio_transport_get_local_cid,
+ .supports_local_mode = virtio_transport_supports_local_mode,
.init = virtio_transport_do_socket_init,
.destruct = virtio_transport_destruct,
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 7eccd6708d66..da7c52ad7b2a 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -2033,6 +2033,12 @@ static u32 vmci_transport_get_local_cid(void)
return vmci_get_context_id();
}
+static bool vmci_transport_supports_local_mode(void)
+{
+ /* Local mode is supported only when no device is present. */
+ return vmci_transport_get_local_cid() == VMCI_INVALID_ID;
+}
+
static struct vsock_transport vmci_transport = {
.module = THIS_MODULE,
.init = vmci_transport_socket_init,
@@ -2062,6 +2068,7 @@ static struct vsock_transport vmci_transport = {
.notify_send_post_enqueue = vmci_transport_notify_send_post_enqueue,
.shutdown = vmci_transport_shutdown,
.get_local_cid = vmci_transport_get_local_cid,
+ .supports_local_mode = vmci_transport_supports_local_mode,
};
static bool vmci_check_transport(struct vsock_sock *vsk)
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 8722337a4f80..1e25c1a6b43f 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -26,6 +26,11 @@ static u32 vsock_loopback_get_local_cid(void)
return VMADDR_CID_LOCAL;
}
+static bool vsock_loopback_supports_local_mode(void)
+{
+ return true;
+}
+
static int vsock_loopback_send_pkt(struct sk_buff *skb)
{
struct vsock_loopback *vsock = &the_vsock_loopback;
@@ -58,6 +63,7 @@ static struct virtio_transport loopback_transport = {
.module = THIS_MODULE,
.get_local_cid = vsock_loopback_get_local_cid,
+ .supports_local_mode = vsock_loopback_supports_local_mode,
.init = virtio_transport_do_socket_init,
.destruct = virtio_transport_destruct,
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 04/11] vsock: add netns support to virtio transports
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add netns support to loopback and vhost. Keep netns disabled for
virtio-vsock, but add necessary changes to comply with common API
updates.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v10:
- Splitting patches complicates the series with meaningless placeholder values that eventually get replaced anyway,
so to avoid that this patch combines into one. Links
to previous patches here:
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-3-852787a37bed@meta.com/
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-6-852787a37bed@meta.com/
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-7-852787a37bed@meta.com/
- remove placeholder values (Stefano)
- update comment describe net/net_mode for
virtio_transport_reset_no_sock()
---
drivers/vhost/vsock.c | 45 +++++++++++++++++------
include/linux/virtio_vsock.h | 8 +++--
net/vmw_vsock/virtio_transport.c | 10 ++++--
net/vmw_vsock/virtio_transport_common.c | 63 ++++++++++++++++++++++++---------
net/vmw_vsock/vsock_loopback.c | 8 +++--
5 files changed, 102 insertions(+), 32 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index c8319cd1c232..2846076d484f 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -46,6 +46,11 @@ static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8);
struct vhost_vsock {
struct vhost_dev dev;
struct vhost_virtqueue vqs[2];
+ struct net *net;
+ netns_tracker ns_tracker;
+
+ /* The ns mode at the time vhost_vsock was created */
+ enum vsock_net_mode net_mode;
/* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */
struct hlist_node hash;
@@ -72,7 +77,8 @@ static bool vhost_transport_supports_local_mode(void)
/* Callers that dereference the return value must hold vhost_vsock_mutex or the
* RCU read lock.
*/
-static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
+static struct vhost_vsock *vhost_vsock_get(u32 guest_cid, struct net *net,
+ enum vsock_net_mode mode)
{
struct vhost_vsock *vsock;
@@ -83,9 +89,10 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
if (other_cid == 0)
continue;
- if (other_cid == guest_cid)
+ if (other_cid == guest_cid &&
+ vsock_net_check_mode(net, mode, vsock->net,
+ vsock->net_mode))
return vsock;
-
}
return NULL;
@@ -274,7 +281,8 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work)
}
static int
-vhost_transport_send_pkt(struct sk_buff *skb)
+vhost_transport_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct vhost_vsock *vsock;
@@ -283,7 +291,7 @@ vhost_transport_send_pkt(struct sk_buff *skb)
rcu_read_lock();
/* Find the vhost_vsock according to guest context id */
- vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid));
+ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid), net, net_mode);
if (!vsock) {
rcu_read_unlock();
kfree_skb(skb);
@@ -310,7 +318,8 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
rcu_read_lock();
/* Find the vhost_vsock according to guest context id */
- vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
+ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid,
+ sock_net(sk_vsock(vsk)), vsk->net_mode);
if (!vsock)
goto out;
@@ -470,11 +479,12 @@ static struct virtio_transport vhost_transport = {
static bool
vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
+ struct net *net = sock_net(sk_vsock(vsk));
struct vhost_vsock *vsock;
bool seqpacket_allow = false;
rcu_read_lock();
- vsock = vhost_vsock_get(remote_cid);
+ vsock = vhost_vsock_get(remote_cid, net, vsk->net_mode);
if (vsock)
seqpacket_allow = vsock->seqpacket_allow;
@@ -545,7 +555,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid &&
le64_to_cpu(hdr->dst_cid) ==
vhost_transport_get_local_cid())
- virtio_transport_recv_pkt(&vhost_transport, skb);
+ virtio_transport_recv_pkt(&vhost_transport, skb,
+ vsock->net, vsock->net_mode);
else
kfree_skb(skb);
@@ -662,6 +673,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
{
struct vhost_virtqueue **vqs;
struct vhost_vsock *vsock;
+ struct net *net;
int ret;
/* This struct is large and allocation could fail, fall back to vmalloc
@@ -677,6 +689,17 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
goto out;
}
+ net = current->nsproxy->net_ns;
+ vsock->net = get_net_track(net, &vsock->ns_tracker, GFP_KERNEL);
+
+ /* Store the mode of the namespace at the time of creation. If this
+ * namespace later changes from "global" to "local", we want this vsock
+ * to continue operating normally and not suddenly break. For that
+ * reason, we save the mode here and later use it when performing
+ * socket lookups with vsock_net_check_mode() (see vhost_vsock_get()).
+ */
+ vsock->net_mode = vsock_net_mode(net);
+
vsock->guest_cid = 0; /* no CID assigned yet */
vsock->seqpacket_allow = false;
@@ -716,7 +739,8 @@ static void vhost_vsock_reset_orphans(struct sock *sk)
*/
/* If the peer is still valid, no need to reset connection */
- if (vhost_vsock_get(vsk->remote_addr.svm_cid))
+ if (vhost_vsock_get(vsk->remote_addr.svm_cid, sock_net(sk),
+ vsk->net_mode))
return;
/* If the close timeout is pending, let it expire. This avoids races
@@ -761,6 +785,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
vhost_dev_cleanup(&vsock->dev);
+ put_net_track(vsock->net, &vsock->ns_tracker);
kfree(vsock->dev.vqs);
vhost_vsock_free(vsock);
return 0;
@@ -787,7 +812,7 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
/* Refuse if CID is already in use */
mutex_lock(&vhost_vsock_mutex);
- other = vhost_vsock_get(guest_cid);
+ other = vhost_vsock_get(guest_cid, vsock->net, vsock->net_mode);
if (other && other != vsock) {
mutex_unlock(&vhost_vsock_mutex);
return -EADDRINUSE;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 0c67543a45c8..5ed6136a4ed4 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -173,6 +173,8 @@ struct virtio_vsock_pkt_info {
u32 remote_cid, remote_port;
struct vsock_sock *vsk;
struct msghdr *msg;
+ struct net *net;
+ enum vsock_net_mode net_mode;
u32 pkt_len;
u16 type;
u16 op;
@@ -185,7 +187,8 @@ struct virtio_transport {
struct vsock_transport transport;
/* Takes ownership of the packet */
- int (*send_pkt)(struct sk_buff *skb);
+ int (*send_pkt)(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode);
/* Used in MSG_ZEROCOPY mode. Checks, that provided data
* (number of buffers) could be transmitted with zerocopy
@@ -280,7 +283,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
void virtio_transport_destruct(struct vsock_sock *vsk);
void virtio_transport_recv_pkt(struct virtio_transport *t,
- struct sk_buff *skb);
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode);
void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb);
u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index e585cb66c6f5..bc266bdb7faa 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -243,7 +243,8 @@ static int virtio_transport_send_skb_fast_path(struct virtio_vsock *vsock, struc
}
static int
-virtio_transport_send_pkt(struct sk_buff *skb)
+virtio_transport_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr;
struct virtio_vsock *vsock;
@@ -675,7 +676,12 @@ static void virtio_transport_rx_work(struct work_struct *work)
virtio_vsock_skb_put(skb, payload_len);
virtio_transport_deliver_tap_pkt(skb);
- virtio_transport_recv_pkt(&virtio_transport, skb);
+
+ /* Force virtio-transport into global mode since it
+ * does not yet support local-mode namespacing.
+ */
+ virtio_transport_recv_pkt(&virtio_transport, skb,
+ NULL, VSOCK_NET_MODE_GLOBAL);
}
} while (!virtqueue_enable_cb(vq));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index dcc8a1d5851e..168e7517a3f0 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -413,7 +413,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
virtio_transport_inc_tx_pkt(vvs, skb);
- ret = t_ops->send_pkt(skb);
+ ret = t_ops->send_pkt(skb, info->net, info->net_mode);
if (ret < 0)
break;
@@ -527,6 +527,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1067,6 +1069,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1082,6 +1086,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1108,6 +1114,8 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1145,6 +1153,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
.op = VIRTIO_VSOCK_OP_RST,
.reply = !!skb,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
+ .net_mode = vsk->net_mode,
};
/* Send RST only if the original pkt is not a RST pkt */
@@ -1156,15 +1166,27 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
/* Normally packets are associated with a socket. There may be no socket if an
* attempt was made to connect to a socket that does not exist.
+ *
+ * net and net_mode refer to the namespace of whoever sent the invalid message.
+ * For loopback, this is the namespace of the socket. For vhost, this is the
+ * namespace of the VM (i.e., vhost_vsock).
*/
static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(hdr->type),
.reply = true,
+
+ /* net or net_mode are not defined here because we pass
+ * net and net_mode directly to t->send_pkt(), instead of
+ * relying on virtio_transport_send_pkt_info() to pass them to
+ * t->send_pkt(). They are not needed by
+ * virtio_transport_alloc_skb().
+ */
};
struct sk_buff *reply;
@@ -1183,7 +1205,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
if (!reply)
return -ENOMEM;
- return t->send_pkt(reply);
+ return t->send_pkt(reply, net, net_mode);
}
/* This function should be called with sk_lock held and SOCK_DONE set */
@@ -1465,6 +1487,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1507,12 +1531,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
int ret;
if (le16_to_cpu(hdr->op) != VIRTIO_VSOCK_OP_REQUEST) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ENOMEM;
}
@@ -1520,13 +1546,15 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
* Subsequent enqueues would lead to a memory leak.
*/
if (sk->sk_shutdown == SHUTDOWN_MASK) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ESHUTDOWN;
}
child = vsock_create_connected(sk);
if (!child) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ENOMEM;
}
@@ -1548,7 +1576,8 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
*/
if (ret || vchild->transport != &t->transport) {
release_sock(child);
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
sock_put(child);
return ret;
}
@@ -1576,7 +1605,8 @@ static bool virtio_transport_valid_type(u16 type)
* lock.
*/
void virtio_transport_recv_pkt(struct virtio_transport *t,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct sockaddr_vm src, dst;
@@ -1599,24 +1629,25 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
le32_to_cpu(hdr->fwd_cnt));
if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
goto free_pkt;
}
/* 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);
+ (void)virtio_transport_reset_no_sock(t, skb, net,
+ net_mode);
goto free_pkt;
}
}
if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
sock_put(sk);
goto free_pkt;
}
@@ -1635,7 +1666,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
*/
if (sock_flag(sk, SOCK_DONE) ||
(sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
release_sock(sk);
sock_put(sk);
goto free_pkt;
@@ -1667,7 +1698,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
kfree_skb(skb);
break;
default:
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
kfree_skb(skb);
break;
}
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 1e25c1a6b43f..a730fa74d2d9 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -31,7 +31,8 @@ static bool vsock_loopback_supports_local_mode(void)
return true;
}
-static int vsock_loopback_send_pkt(struct sk_buff *skb)
+static int vsock_loopback_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_loopback *vsock = &the_vsock_loopback;
int len = skb->len;
@@ -138,7 +139,10 @@ static void vsock_loopback_work(struct work_struct *work)
*/
virtio_transport_consume_skb_sent(skb, false);
virtio_transport_deliver_tap_pkt(skb);
- virtio_transport_recv_pkt(&loopback_transport, skb);
+
+ virtio_transport_recv_pkt(&loopback_transport, skb,
+ sock_net(skb->sk),
+ vsock_sk(skb->sk)->net_mode);
}
}
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 05/11] virtio: set skb owner of virtio_transport_reset_no_sock() reply
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Associate reply packets with the sending socket. When vsock must reply
with an RST packet and there exists a sending socket (e.g., for
loopback), setting the skb owner to the socket correctly handles
reference counting between the skb and sk (i.e., the sk stays alive
until the skb is freed).
This allows the net namespace to be used for socket lookups for the
duration of the reply skb's lifetime, preventing race conditions between
the namespace lifecycle and vsock socket search using the namespace
pointer.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v10:
- break this out into its own patch for easy revert (Stefano)
---
net/vmw_vsock/virtio_transport_common.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 168e7517a3f0..5bb498caa19e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1181,6 +1181,12 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
.type = le16_to_cpu(hdr->type),
.reply = true,
+ /* Set sk owner to socket we are replying to (may be NULL for
+ * non-loopback). This keeps a reference to the sock and
+ * sock_net(sk) until the reply skb is freed.
+ */
+ .vsk = vsock_sk(skb->sk),
+
/* net or net_mode are not defined here because we pass
* net and net_mode directly to t->send_pkt(), instead of
* relying on virtio_transport_send_pkt_info() to pass them to
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 06/11] selftests/vsock: add namespace helpers to vmtest.sh
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
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 | 41 +++++++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index c7b270dd77a9..f78cc574c274 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -49,6 +49,7 @@ readonly TEST_DESCS=(
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
+readonly NS_MODES=("local" "global")
VERBOSE=0
@@ -103,6 +104,45 @@ check_result() {
fi
}
+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 $?
@@ -110,6 +150,7 @@ vm_ssh() {
cleanup() {
terminate_pidfiles "${!PIDFILES[@]}"
+ del_namespaces
}
check_args() {
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 07/11] selftests/vsock: prepare vm management helpers for namespaces
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add namespace support to vm management, ssh helpers, and vsock_test
wrapper functions. This enables running VMs and test helpers in specific
namespaces, which is required for upcoming namespace isolation tests.
The functions still work correctly within the init ns, though the caller
must now pass "init_ns" explicitly.
No functional changes for existing tests. All have been updated to pass
"init_ns" explicitly.
Affected functions (such as vm_start() and vm_ssh()) now wrap their
commands with 'ip netns exec' when executing commands in non-init
namespaces.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 102 +++++++++++++++++++++-----------
1 file changed, 69 insertions(+), 33 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index f78cc574c274..1a7c810f282f 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -144,7 +144,18 @@ ns_set_mode() {
}
vm_ssh() {
- ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@"
+ local ns_exec
+
+ if [[ "${1}" == init_ns ]]; then
+ ns_exec=""
+ else
+ ns_exec="ip netns exec ${1}"
+ fi
+
+ shift
+
+ ${ns_exec} ssh -q -o UserKnownHostsFile=/dev/null -p "${SSH_HOST_PORT}" localhost "$@"
+
return $?
}
@@ -267,10 +278,12 @@ terminate_pidfiles() {
vm_start() {
local pidfile=$1
+ local ns=$2
local logfile=/dev/null
local verbose_opt=""
local kernel_opt=""
local qemu_opts=""
+ local ns_exec=""
local qemu
qemu=$(command -v "${QEMU}")
@@ -291,7 +304,11 @@ vm_start() {
kernel_opt="${KERNEL_CHECKOUT}"
fi
- vng \
+ if [[ "${ns}" != "init_ns" ]]; then
+ ns_exec="ip netns exec ${ns}"
+ fi
+
+ ${ns_exec} vng \
--run \
${kernel_opt} \
${verbose_opt} \
@@ -306,6 +323,7 @@ vm_start() {
}
vm_wait_for_ssh() {
+ local ns=$1
local i
i=0
@@ -313,7 +331,8 @@ 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 ))
@@ -347,30 +366,40 @@ wait_for_listener()
}
vm_wait_for_listener() {
- local port=$1
+ local ns=$1
+ local port=$2
- vm_ssh <<EOF
+ vm_ssh "${ns}" <<EOF
$(declare -f wait_for_listener)
wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
EOF
}
host_wait_for_listener() {
- local port=$1
+ local ns=$1
+ local port=$2
- wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ if [[ "${ns}" == "init_ns" ]]; then
+ wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ else
+ ip netns exec "${ns}" bash <<-EOF
+ $(declare -f wait_for_listener)
+ wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
+ EOF
+ fi
}
vm_vsock_test() {
- local host=$1
- local cid=$2
- local port=$3
+ local ns=$1
+ local host=$2
+ local cid=$3
+ local port=$4
local rc
# log output and use pipefail to respect vsock_test errors
set -o pipefail
if [[ "${host}" != server ]]; then
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=client \
--control-host="${host}" \
--peer-cid="${cid}" \
@@ -378,7 +407,7 @@ vm_vsock_test() {
2>&1 | log_guest
rc=$?
else
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=server \
--peer-cid="${cid}" \
--control-port="${port}" \
@@ -390,7 +419,7 @@ vm_vsock_test() {
return $rc
fi
- vm_wait_for_listener "${port}"
+ vm_wait_for_listener "${ns}" "${port}"
rc=$?
fi
set +o pipefail
@@ -399,22 +428,28 @@ vm_vsock_test() {
}
host_vsock_test() {
- local host=$1
- local cid=$2
- local port=$3
+ local ns=$1
+ local host=$2
+ local cid=$3
+ local port=$4
local rc
+ local cmd="${VSOCK_TEST}"
+ if [[ "${ns}" != "init_ns" ]]; then
+ cmd="ip netns exec ${ns} ${cmd}"
+ fi
+
# log output and use pipefail to respect vsock_test errors
set -o pipefail
if [[ "${host}" != server ]]; then
- ${VSOCK_TEST} \
+ ${cmd} \
--mode=client \
--peer-cid="${cid}" \
--control-host="${host}" \
--control-port="${port}" 2>&1 | log_host
rc=$?
else
- ${VSOCK_TEST} \
+ ${cmd} \
--mode=server \
--peer-cid="${cid}" \
--control-port="${port}" 2>&1 | log_host &
@@ -425,7 +460,7 @@ host_vsock_test() {
return $rc
fi
- host_wait_for_listener "${port}"
+ host_wait_for_listener "${ns}" "${port}"
rc=$?
fi
set +o pipefail
@@ -469,11 +504,11 @@ log_guest() {
}
test_vm_server_host_client() {
- if ! vm_vsock_test "server" 2 "${TEST_GUEST_PORT}"; then
+ if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then
return "${KSFT_FAIL}"
fi
- if ! host_vsock_test "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then
+ if ! host_vsock_test "init_ns" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then
return "${KSFT_FAIL}"
fi
@@ -481,11 +516,11 @@ test_vm_server_host_client() {
}
test_vm_client_host_server() {
- if ! host_vsock_test "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then
+ if ! host_vsock_test "init_ns" "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then
return "${KSFT_FAIL}"
fi
- if ! vm_vsock_test "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then
+ if ! vm_vsock_test "init_ns" "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then
return "${KSFT_FAIL}"
fi
@@ -495,13 +530,14 @@ test_vm_client_host_server() {
test_vm_loopback() {
local port=60000 # non-forwarded local port
- vm_ssh -- modprobe vsock_loopback &> /dev/null || :
+ vm_ssh "init_ns" -- modprobe vsock_loopback &> /dev/null || :
- if ! vm_vsock_test "server" 1 "${port}"; then
+ if ! vm_vsock_test "init_ns" "server" 1 "${port}"; then
return "${KSFT_FAIL}"
fi
- if ! vm_vsock_test "127.0.0.1" 1 "${port}"; then
+
+ if ! vm_vsock_test "init_ns" "127.0.0.1" 1 "${port}"; then
return "${KSFT_FAIL}"
fi
@@ -559,8 +595,8 @@ run_shared_vm_test() {
host_oops_cnt_before=$(dmesg | grep -c -i 'Oops')
host_warn_cnt_before=$(dmesg --level=warn | grep -c -i 'vsock')
- vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops')
- vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock')
+ vm_oops_cnt_before=$(vm_ssh "init_ns" -- dmesg | grep -c -i 'Oops')
+ vm_warn_cnt_before=$(vm_ssh "init_ns" -- dmesg --level=warn | grep -c -i 'vsock')
name=$(echo "${1}" | awk '{ print $1 }')
eval test_"${name}"
@@ -577,14 +613,14 @@ run_shared_vm_test() {
echo "FAIL: kernel warning detected on host" | log_host
rc=$KSFT_FAIL
fi
-
- vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l)
+ vm_oops_cnt_after=$(vm_ssh "init_ns" -- dmesg | grep -c -i 'Oops')
+ vm_oops_cnt_after=$(vm_ssh "init_ns" -- dmesg | grep -i 'Oops' | wc -l)
if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then
echo "FAIL: kernel oops detected on vm" | log_host
rc=$KSFT_FAIL
fi
- vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock')
+ vm_warn_cnt_after=$(vm_ssh "init_ns" -- dmesg --level=warn | grep -c -i 'vsock')
if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then
echo "FAIL: kernel warning detected on vm" | log_host
rc=$KSFT_FAIL
@@ -630,8 +666,8 @@ cnt_total=0
if shared_vm_tests_requested "${ARGS[@]}"; then
log_host "Booting up VM"
pidfile="$(create_pidfile)"
- vm_start "${pidfile}"
- vm_wait_for_ssh
+ vm_start "${pidfile}" "init_ns"
+ vm_wait_for_ssh "init_ns"
log_host "VM booted up"
run_shared_vm_tests "${ARGS[@]}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 08/11] selftests/vsock: add tests for proc sys vsock ns_mode
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
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.
Add a test to verify that guest VMs with an active G2H transport
(virtio-vsock) cannot set namespace mode to 'local'. This validates
the mutual exclusion between G2H transports and LOCAL mode.
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>
---
Changes in v10:
- Remove extraneous add_namespaces/del_namespaces calls.
- Rename run_tests() to run_ns_tests() since it is designed to only
run ns tests.
Changes in v9:
- add test ns_vm_local_mode_rejected to check that guests cannot use
local mode
---
tools/testing/selftests/vsock/vmtest.sh | 140 +++++++++++++++++++++++++++++++-
1 file changed, 138 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 1a7c810f282f..86483249f490 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -41,14 +41,40 @@ 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
+ ns_vm_local_mode_rejected
+)
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."
+
+ # ns_vm_local_mode_rejected
+ "Test that guest VM with G2H transport cannot set namespace mode to 'local'"
)
-readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
+readonly USE_SHARED_VM=(
+ vm_server_host_client
+ vm_client_host_server
+ vm_loopback
+ ns_vm_local_mode_rejected
+)
readonly NS_MODES=("local" "global")
VERBOSE=0
@@ -205,6 +231,20 @@ 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 ${tname}"
+ return 1
+ fi
+
+ return 0
+}
+
check_vng() {
local tested_versions
local version
@@ -503,6 +543,32 @@ log_guest() {
LOG_PREFIX=guest log "$@"
}
+test_ns_host_vsock_ns_mode_ok() {
+ for mode in "${NS_MODES[@]}"; do
+ if ! ns_set_mode "${mode}0" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_host_vsock_ns_mode_write_once_ok() {
+ for mode in "${NS_MODES[@]}"; do
+ local ns="${mode}0"
+ if ! ns_set_mode "${ns}" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ # try writing again and expect failure
+ if ns_set_mode "${ns}" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ return "${KSFT_PASS}"
+}
+
test_vm_server_host_client() {
if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then
return "${KSFT_FAIL}"
@@ -544,6 +610,26 @@ test_vm_loopback() {
return "${KSFT_PASS}"
}
+test_ns_vm_local_mode_rejected() {
+ # Guest VMs have a G2H transport (virtio-vsock) active, so they
+ # should not be able to set namespace mode to 'local'.
+ # This test verifies that the sysctl write fails as expected.
+
+ # Try to set local mode in the guest's init_ns
+ if vm_ssh init_ns "echo local | tee /proc/sys/net/vsock/ns_mode &>/dev/null"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ # Verify mode is still 'global'
+ local mode
+ mode=$(vm_ssh init_ns "cat /proc/sys/net/vsock/ns_mode")
+ if [[ "${mode}" != "global" ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
shared_vm_test() {
local tname
@@ -576,6 +662,11 @@ run_shared_vm_tests() {
continue
fi
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}" "${arg}"
+ continue
+ fi
+
run_shared_vm_test "${arg}"
check_result "$?" "${arg}"
done
@@ -629,6 +720,49 @@ run_shared_vm_test() {
return "${rc}"
}
+run_ns_tests() {
+ for arg in "${ARGS[@]}"; do
+ if shared_vm_test "${arg}"; then
+ continue
+ fi
+
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}" "${arg}"
+ continue
+ fi
+
+ add_namespaces
+
+ name=$(echo "${arg}" | awk '{ print $1 }')
+ log_host "Executing test_${name}"
+
+ host_oops_before=$(dmesg 2>/dev/null | grep -c -i 'Oops')
+ host_warn_before=$(dmesg --level=warn 2>/dev/null | grep -c -i 'vsock')
+ eval test_"${name}"
+ rc=$?
+
+ host_oops_after=$(dmesg 2>/dev/null | grep -c -i 'Oops')
+ if [[ "${host_oops_after}" -gt "${host_oops_before}" ]]; then
+ echo "FAIL: kernel oops detected on host" | log_host
+ check_result "${KSFT_FAIL}" "${name}"
+ del_namespaces
+ continue
+ fi
+
+ host_warn_after=$(dmesg --level=warn 2>/dev/null | grep -c -i 'vsock')
+ if [[ "${host_warn_after}" -gt "${host_warn_before}" ]]; then
+ echo "FAIL: kernel warning detected on host" | log_host
+ check_result "${KSFT_FAIL}" "${name}"
+ del_namespaces
+ continue
+ fi
+
+ check_result "${rc}" "${name}"
+
+ del_namespaces
+ done
+}
+
BUILD=0
QEMU="qemu-system-$(uname -m)"
@@ -674,6 +808,8 @@ if shared_vm_tests_requested "${ARGS[@]}"; then
terminate_pidfiles "${pidfile}"
fi
+run_ns_tests "${ARGS[@]}"
+
echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}"
echo "Log: ${LOG}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 09/11] selftests/vsock: add namespace tests for CID collisions
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests to verify CID collision rules across different vsock namespace
modes.
1. Two VMs with the same CID cannot start in different global namespaces
(ns_global_same_cid_fails)
2. Two VMs with the same CID can start in different local namespaces
(ns_local_same_cid_ok)
3. VMs with the same CID can coexist when one is in a global namespace
and another is in a local namespace (ns_global_local_same_cid_ok and
ns_local_global_same_cid_ok)
The tests ns_global_local_same_cid_ok and ns_local_global_same_cid_ok
make sure that ordering does not matter.
The tests use a shared helper function namespaces_can_boot_same_cid()
that attempts to start two VMs with identical CIDs in the specified
namespaces and verifies whether VM initialization failed or succeeded.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 73 +++++++++++++++++++++++++++++++++
1 file changed, 73 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 86483249f490..a8bf78a5075d 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -48,6 +48,10 @@ readonly TEST_NAMES=(
ns_host_vsock_ns_mode_ok
ns_host_vsock_ns_mode_write_once_ok
ns_vm_local_mode_rejected
+ ns_global_same_cid_fails
+ ns_local_same_cid_ok
+ ns_global_local_same_cid_ok
+ ns_local_global_same_cid_ok
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -67,6 +71,17 @@ readonly TEST_DESCS=(
# ns_vm_local_mode_rejected
"Test that guest VM with G2H transport cannot set namespace mode to 'local'"
+ # ns_global_same_cid_fails
+ "Check QEMU fails to start two VMs with same CID in two different global namespaces."
+
+ # ns_local_same_cid_ok
+ "Check QEMU successfully starts two VMs with same CID in two different local namespaces."
+
+ # ns_global_local_same_cid_ok
+ "Check QEMU successfully starts one VM in a global ns and then another VM in a local ns with the same CID."
+
+ # ns_local_global_same_cid_ok
+ "Check QEMU successfully starts one VM in a local ns and then another VM in a global ns with the same CID."
)
readonly USE_SHARED_VM=(
@@ -553,6 +568,64 @@ test_ns_host_vsock_ns_mode_ok() {
return "${KSFT_PASS}"
}
+namespaces_can_boot_same_cid() {
+ local ns0=$1
+ local ns1=$2
+ local pidfile1 pidfile2
+ local rc
+
+ pidfile1="$(create_pidfile)"
+ vm_start "${pidfile1}" "${ns0}"
+
+ pidfile2="$(create_pidfile)"
+ vm_start "${pidfile2}" "${ns1}"
+
+ rc=$?
+ terminate_pidfiles "${pidfile1}" "${pidfile2}"
+
+ return "${rc}"
+}
+
+test_ns_global_same_cid_fails() {
+ init_namespaces
+
+ if namespaces_can_boot_same_cid "global0" "global1"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_local_global_same_cid_ok() {
+ init_namespaces
+
+ if namespaces_can_boot_same_cid "local0" "global0"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_global_local_same_cid_ok() {
+ init_namespaces
+
+ if namespaces_can_boot_same_cid "global0" "local0"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_local_same_cid_ok() {
+ init_namespaces
+
+ if namespaces_can_boot_same_cid "local0" "local0"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
test_ns_host_vsock_ns_mode_write_once_ok() {
for mode in "${NS_MODES[@]}"; do
local ns="${mode}0"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 10/11] selftests/vsock: add tests for host <-> vm connectivity with namespaces
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
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.
Add vm_dmesg_start() and vm_dmesg_check() to encapsulate checking dmesg
for oops and warnings.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v10:
- add vm_dmesg_start() and vm_dmesg_check()
Changes in v9:
- consistent variable quoting
---
tools/testing/selftests/vsock/vmtest.sh | 558 +++++++++++++++++++++++++++++++-
1 file changed, 556 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index a8bf78a5075d..9c12c1bd1edc 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
#
# shellcheck disable=SC2317,SC2119
@@ -52,6 +53,19 @@ 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
@@ -82,6 +96,45 @@ 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=(
@@ -113,7 +166,7 @@ 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
@@ -232,7 +285,7 @@ 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}"
@@ -283,6 +336,20 @@ 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
@@ -331,6 +398,14 @@ 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
@@ -444,6 +519,40 @@ host_wait_for_listener() {
fi
}
+vm_dmesg_oops_count() {
+ local ns=$1
+
+ vm_ssh "${ns}" -- dmesg 2>/dev/null | grep -c -i 'Oops'
+}
+
+vm_dmesg_warn_count() {
+ local ns=$1
+
+ vm_ssh "${ns}" -- dmesg --level=warn 2>/dev/null | grep -c -i 'vsock'
+}
+
+vm_dmesg_check() {
+ local pidfile=$1
+ local ns=$2
+ local oops_before=$3
+ local warn_before=$4
+ local oops_after warn_after
+
+ oops_after=$(vm_ssh "${ns}" -- dmesg 2>/dev/null | grep -c -i 'Oops')
+ if [[ "${oops_after}" -gt "${oops_before}" ]]; then
+ echo "FAIL: kernel oops detected on vm in ns ${ns}" | log_host
+ return 1
+ fi
+
+ warn_after=$(vm_ssh "${ns}" -- dmesg --level=warn 2>/dev/null | grep -c -i 'vsock')
+ if [[ "${warn_after}" -gt "${warn_before}" ]]; then
+ echo "FAIL: kernel warning detected on vm in ns ${ns}" | log_host
+ return 1
+ fi
+
+ return 0
+}
+
vm_vsock_test() {
local ns=$1
local host=$2
@@ -568,6 +677,450 @@ test_ns_host_vsock_ns_mode_ok() {
return "${KSFT_PASS}"
}
+test_ns_diff_global_host_connect_to_global_vm_ok() {
+ local oops_before warn_before
+ local pids pid pidfile
+ local ns0 ns1 port
+ declare -a pids
+ local unixfile
+ ns0="global0"
+ ns1="global1"
+ port=1234
+ local rc
+
+ init_namespaces
+
+ pidfile="$(create_pidfile)"
+
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns0}"
+ oops_before=$(vm_dmesg_oops_count "${ns0}")
+ warn_before=$(vm_dmesg_warn_count "${ns0}")
+
+ unixfile=$(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}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ vm_dmesg_check "${pidfile}" "${ns0}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pids "${pids[@]}"
+ terminate_pidfiles "${pidfile}"
+
+ if [[ "${rc}" -ne 0 ]] || [[ "${dmesg_rc}" -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_diff_global_host_connect_to_local_vm_fails() {
+ local oops_before warn_before
+ local ns0="global0"
+ local ns1="local0"
+ local port=12345
+ local dmesg_rc
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ outfile=$(mktemp)
+
+ pidfile="$(create_pidfile)"
+ if ! vm_start "${pidfile}" "${ns1}"; then
+ log_host "failed to start vm (cid=${VSOCK_CID}, ns=${ns0})"
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns1}"
+ oops_before=$(vm_dmesg_oops_count "${ns1}")
+ warn_before=$(vm_dmesg_warn_count "${ns1}")
+
+ vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" &
+ echo TEST | ip netns exec "${ns0}" \
+ socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null
+
+ vm_dmesg_check "${pidfile}" "${ns1}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" == "TEST" ]] || [[ "${dmesg_rc}" -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_diff_global_vm_connect_to_global_host_ok() {
+ local oops_before warn_before
+ local ns0="global0"
+ local ns1="global1"
+ local port=12345
+ local unixfile
+ local dmesg_rc
+ local pidfile
+ local pids
+ local rc
+
+ 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="$(create_pidfile)"
+ if ! vm_start "${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 "${ns0}"
+
+ oops_before=$(vm_dmesg_oops_count "${ns0}")
+ warn_before=$(vm_dmesg_warn_count "${ns0}")
+
+ vm_vsock_test "${ns0}" "10.0.2.2" 2 "${port}"
+ rc=$?
+
+ vm_dmesg_check "${pidfile}" "${ns0}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pids[@]}"
+ rm -f "${unixfile}"
+
+ if [[ "${rc}" -ne 0 ]] || [[ "${dmesg_rc}" -ne 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 oops_before warn_before
+ local dmesg_rc
+ 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="$(create_pidfile)"
+ if ! vm_start "${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 "${ns0}"
+
+ oops_before=$(vm_dmesg_oops_count "${ns0}")
+ warn_before=$(vm_dmesg_warn_count "${ns0}")
+
+ vm_ssh "${ns0}" -- \
+ bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest
+
+ vm_dmesg_check "${pidfile}" "${ns0}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pid}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]] && [[ "${dmesg_rc}" -eq 0 ]]; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_local_host_connect_to_local_vm_fails() {
+ local ns0="local0"
+ local ns1="local1"
+ local port=12345
+ local oops_before warn_before
+ local dmesg_rc
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ outfile=$(mktemp)
+
+ pidfile="$(create_pidfile)"
+ if ! vm_start "${pidfile}" "${ns1}"; then
+ log_host "failed to start vm (cid=${cid}, ns=${ns0})"
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns1}"
+ oops_before=$(vm_dmesg_oops_count "${ns1}")
+ warn_before=$(vm_dmesg_warn_count "${ns1}")
+
+ vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" &
+ echo TEST | ip netns exec "${ns0}" \
+ socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null
+
+ vm_dmesg_check "${pidfile}" "${ns1}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]] && [[ "${dmesg_rc}" -eq 0 ]]; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_local_vm_connect_to_local_host_fails() {
+ local oops_before warn_before
+ local ns0="local0"
+ local ns1="local1"
+ local port=12345
+ local dmesg_rc
+ 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="$(create_pidfile)"
+ if ! vm_start "${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}"
+ oops_before=$(vm_dmesg_oops_count "${ns0}")
+ warn_before=$(vm_dmesg_warn_count "${ns0}")
+
+ vm_ssh "${ns0}" -- \
+ bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest
+
+ vm_dmesg_check "${pidfile}" "${ns0}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pid}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]] && [[ "${dmesg_rc}" -eq 0 ]]; 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 oops_before warn_before
+ local ns="local0"
+ local port=1234
+ local dmesg_rc
+ local pidfile
+ local rc
+
+ init_namespaces
+
+ pidfile="$(create_pidfile)"
+
+ if ! vm_start "${pidfile}" "${ns}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns}"
+ oops_before=$(vm_dmesg_oops_count "${ns}")
+ warn_before=$(vm_dmesg_warn_count "${ns}")
+
+ vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}"
+ host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ vm_dmesg_check "${pidfile}" "${ns}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+
+ if [[ "${rc}" -ne 0 ]] || [[ "${dmesg_rc}" -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_same_local_vm_connect_to_local_host_ok() {
+ local oops_before warn_before
+ local ns="local0"
+ local port=1234
+ local dmesg_rc
+ local pidfile
+ local rc
+
+ init_namespaces
+
+ pidfile="$(create_pidfile)"
+
+ if ! vm_start "${pidfile}" "${ns}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns}"
+ oops_before=$(vm_dmesg_oops_count "${ns}")
+ warn_before=$(vm_dmesg_warn_count "${ns}")
+
+ vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}"
+ host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ vm_dmesg_check "${pidfile}" "${ns}" "${oops_before}" "${warn_before}"
+ dmesg_rc=$?
+
+ terminate_pidfiles "${pidfile}"
+
+ if [[ "${rc}" -ne 0 ]] || [[ "${dmesg_rc}" -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
namespaces_can_boot_same_cid() {
local ns0=$1
local ns1=$2
@@ -861,6 +1414,7 @@ fi
check_args "${ARGS[@]}"
check_deps
check_vng
+check_socat
handle_build
echo "1..${#ARGS[@]}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v10 11/11] selftests/vsock: add tests for namespace deletion and mode changes
From: Bobby Eshleman @ 2025-11-18 2:00 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, Sargun Dhillon, Bobby Eshleman, berrange,
Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests that validate vsock sockets are resilient to deleting
namespaces or changing namespace modes from global to local. The vsock
sockets should still function normally.
The function check_ns_changes_dont_break_connection() is added to re-use
the step-by-step logic of 1) setup connections, 2) do something that
would maybe break the connections, 3) check that the connections are
still ok.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v9:
- more consistent shell style
- clarify -u usage comment for pipefile
---
tools/testing/selftests/vsock/vmtest.sh | 123 ++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 9c12c1bd1edc..2b6e94aafc19 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -66,6 +66,12 @@ readonly TEST_NAMES=(
ns_same_local_loopback_ok
ns_same_local_host_connect_to_local_vm_ok
ns_same_local_vm_connect_to_local_host_ok
+ ns_mode_change_connection_continue_vm_ok
+ ns_mode_change_connection_continue_host_ok
+ ns_mode_change_connection_continue_both_ok
+ ns_delete_vm_ok
+ ns_delete_host_ok
+ ns_delete_both_ok
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -135,6 +141,24 @@ readonly TEST_DESCS=(
# ns_same_local_vm_connect_to_local_host_ok
"Run vsock_test client in VM in a local ns with server in same ns."
+
+ # ns_mode_change_connection_continue_vm_ok
+ "Check that changing NS mode of VM namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_host_ok
+ "Check that changing NS mode of host namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_both_ok
+ "Check that changing NS mode of host and VM namespaces from global to local after a connection is established doesn't break the connection"
+
+ # ns_delete_vm_ok
+ "Check that deleting the VM's namespace does not break the socket connection"
+
+ # ns_delete_host_ok
+ "Check that deleting the host's namespace does not break the socket connection"
+
+ # ns_delete_both_ok
+ "Check that deleting the VM and host's namespaces does not break the socket connection"
)
readonly USE_SHARED_VM=(
@@ -1256,6 +1280,105 @@ test_ns_vm_local_mode_rejected() {
return "${KSFT_PASS}"
}
+check_ns_changes_dont_break_connection() {
+ local pipefile pidfile outfile
+ local ns0="global0"
+ local ns1="global1"
+ local port=12345
+ local pids=()
+ local rc=0
+
+ init_namespaces
+
+ pidfile="$(create_pidfile)"
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ return "${KSFT_FAIL}"
+ fi
+ vm_wait_for_ssh "${ns0}"
+
+ outfile=$(mktemp)
+ vm_ssh "${ns0}" -- \
+ socat VSOCK-LISTEN:"${port}",fork STDOUT > "${outfile}" 2>/dev/null &
+ pids+=($!)
+
+ # wait_for_listener() does not work for vsock because vsock does not
+ # export socket state to /proc/net/. Instead, we have no choice but to
+ # sleep for some hardcoded time.
+ sleep "${WAIT_PERIOD}"
+
+ # We use a pipe here so that we can echo into the pipe instead of using
+ # socat and a unix socket file. We just need a name for the pipe (not a
+ # regular file) so use -u.
+ pipefile=$(mktemp -u /tmp/vmtest_pipe_XXXX)
+ ip netns exec "${ns1}" \
+ socat PIPE:"${pipefile}" VSOCK-CONNECT:"${VSOCK_CID}":"${port}" &
+ pids+=($!)
+
+ timeout "${WAIT_PERIOD}" \
+ bash -c 'while [[ ! -e '"${pipefile}"' ]]; do sleep 1; done; exit 0'
+
+ if [[ $2 == "delete" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ip netns del "${ns0}"
+ elif [[ "$1" == "host" ]]; then
+ ip netns del "${ns1}"
+ elif [[ "$1" == "both" ]]; then
+ ip netns del "${ns0}"
+ ip netns del "${ns1}"
+ fi
+ elif [[ $2 == "change_mode" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ns_set_mode "${ns0}" "local"
+ elif [[ "$1" == "host" ]]; then
+ ns_set_mode "${ns1}" "local"
+ elif [[ "$1" == "both" ]]; then
+ ns_set_mode "${ns0}" "local"
+ ns_set_mode "${ns1}" "local"
+ fi
+ fi
+
+ echo "TEST" > "${pipefile}"
+
+ timeout "${WAIT_PERIOD}" \
+ bash -c 'while [[ ! -s '"${outfile}"' ]]; do sleep 1; done; exit 0'
+
+ if grep -q "TEST" "${outfile}"; then
+ rc="${KSFT_PASS}"
+ else
+ rc="${KSFT_FAIL}"
+ fi
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pids[@]}"
+ rm -f "${outfile}"
+
+ return "${rc}"
+}
+
+test_ns_mode_change_connection_continue_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_host_ok() {
+ check_ns_changes_dont_break_connection "host" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_both_ok() {
+ check_ns_changes_dont_break_connection "both" "change_mode"
+}
+
+test_ns_delete_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "delete"
+}
+
+test_ns_delete_host_ok() {
+ check_ns_changes_dont_break_connection "host" "delete"
+}
+
+test_ns_delete_both_ok() {
+ check_ns_changes_dont_break_connection "both" "delete"
+}
+
shared_vm_test() {
local tname
--
2.47.3
^ permalink raw reply related
* Re: [PATCH net-next v5 1/2] net: mana: Handle SKB if TX SGEs exceed hardware limit
From: Jakub Kicinski @ 2025-11-18 3:46 UTC (permalink / raw)
To: Aditya Garg
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
pabeni, longli, kotaranov, horms, shradhagupta, ssengar, ernis,
dipayanroy, shirazsaleem, leon, mlevitsk, yury.norov, sbhatta,
linux-hyperv, netdev, linux-kernel, linux-rdma, gargaditya
In-Reply-To: <1763155003-21503-2-git-send-email-gargaditya@linux.microsoft.com>
On Fri, 14 Nov 2025 13:16:42 -0800 Aditya Garg wrote:
> The MANA hardware supports a maximum of 30 scatter-gather entries (SGEs)
> per TX WQE. Exceeding this limit can cause TX failures.
> Add ndo_features_check() callback to validate SKB layout before
> transmission. For GSO SKBs that would exceed the hardware SGE limit, clear
> NETIF_F_GSO_MASK to enforce software segmentation in the stack.
> Add a fallback in mana_start_xmit() to linearize non-GSO SKBs that still
> exceed the SGE limit.
> + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES);
> +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
> + if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
nit: please try to avoid the use of ifdef if you can. This helps to
avoid build breakage sneaking in as this code will be compiled out
on default config on all platforms.
Instead you should be able to simply add the static condition to the
if statement:
if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES &&
skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
and let the compiler (rather than preprocessor) eliminate this if ()
block.
> + /* GSO skb with Hardware SGE limit exceeded is not expected here
> + * as they are handled in mana_features_check() callback
> + */
> + if (skb_linearize(skb)) {
> + netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n",
> + skb_shinfo(skb)->nr_frags,
> + skb_is_gso(skb));
> + goto tx_drop_count;
> + }
> + apc->eth_stats.linear_pkt_tx_cnt++;
> + }
> +#endif
--
pw-bot: cr
^ permalink raw reply
* Re: [PATCH net-next v3 0/2] net: mana: Refactor GF stats handling and add rx_missed_errors counter
From: patchwork-bot+netdevbpf @ 2025-11-18 4:00 UTC (permalink / raw)
To: Erni Sri Satya Vennela
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, longli, kotaranov, horms, shradhagupta, ssengar,
dipayanroy, shirazsaleem, sbhatta, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1763120599-6331-1-git-send-email-ernis@linux.microsoft.com>
Hello:
This series was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:
On Fri, 14 Nov 2025 03:43:17 -0800 you wrote:
> Restructure mana_query_gf_stats() to operate on the per-VF mana_context,
> instead of per-port statistics. Introduce mana_ethtool_hc_stats to
> isolate hardware counter statistics and update the
> "ethtool -S <interface>" output to expose all relevant counters while
> preserving backward compatibility.
>
> Add support for the standard rx_missed_errors counter by mapping it to
> the hardware's hc_rx_discards_no_wqe metric. Introduce a
> global workqueue that refreshes statistics every 2 seconds, ensuring
> timely and consistent updates of hardware counters.
>
> [...]
Here is the summary with links:
- [net-next,v3,1/2] net: mana: Move hardware counter stats from per-port to per-VF context
https://git.kernel.org/netdev/net-next/c/e275d9091c01
- [net-next,v3,2/2] net: mana: Add standard counter rx_missed_errors
https://git.kernel.org/netdev/net-next/c/be4f1d67ec56
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* Re: [PATCH v7 0/9] x86/hyperv/hv_vtl: Use a wakeup mailbox to boot secondary CPUs
From: Ricardo Neri @ 2025-11-18 5:13 UTC (permalink / raw)
To: x86, Krzysztof Kozlowski, Conor Dooley, Rob Herring,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Michael Kelley, Rafael J. Wysocki
Cc: Saurabh Sengar, Chris Oo, Kirill A. Shutemov, linux-hyperv,
devicetree, linux-acpi, linux-kernel, Ricardo Neri,
Rafael J. Wysocki (Intel), Yunhong Jiang, Thomas Gleixner
In-Reply-To: <20251117-rneri-wakeup-mailbox-v7-0-4a8b82ab7c2c@linux.intel.com>
On Mon, Nov 17, 2025 at 09:02:46AM -0800, Ricardo Neri wrote:
> Hi,
>
> Many thanks to Boris, Rafael, Rob, and Dexuan for their valuable feedback!
> The main change in this version is the removal of the patch that moved the
> ACPI mailbox code from the x86 ACPI subsystem to a generic location. Users
> with DeviceTree-based firmware who wish use the ACPI wakeup mailbox need to
> select CONFIG_ACPI=y.
Also, this patchset uncovered, IMHO, missing definitions in arch/x86/asm/
topology.h. I posted a patch for that effect here:
https://lore.kernel.org/all/20251117-rneri-topology-cpuinfo-bug-v1-1-a905bb5f91e2@linux.intel.com/
I can repost this patchset along with the patch above if it makes things
easier.
BR,
Ricardo
^ permalink raw reply
* Re: [PATCH net-next v5 1/2] net: mana: Handle SKB if TX SGEs exceed hardware limit
From: Aditya Garg @ 2025-11-18 11:08 UTC (permalink / raw)
To: Jakub Kicinski
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
pabeni, longli, kotaranov, horms, shradhagupta, ssengar, ernis,
dipayanroy, shirazsaleem, leon, mlevitsk, yury.norov, sbhatta,
linux-hyperv, netdev, linux-kernel, linux-rdma, gargaditya
In-Reply-To: <20251117194618.33af8e98@kernel.org>
On 18-11-2025 09:16, Jakub Kicinski wrote:
> On Fri, 14 Nov 2025 13:16:42 -0800 Aditya Garg wrote:
>> The MANA hardware supports a maximum of 30 scatter-gather entries (SGEs)
>> per TX WQE. Exceeding this limit can cause TX failures.
>> Add ndo_features_check() callback to validate SKB layout before
>> transmission. For GSO SKBs that would exceed the hardware SGE limit, clear
>> NETIF_F_GSO_MASK to enforce software segmentation in the stack.
>> Add a fallback in mana_start_xmit() to linearize non-GSO SKBs that still
>> exceed the SGE limit.
>
>> + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES);
>> +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
>> + if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
>
> nit: please try to avoid the use of ifdef if you can. This helps to
> avoid build breakage sneaking in as this code will be compiled out
> on default config on all platforms.
>
> Instead you should be able to simply add the static condition to the
> if statement:
>
> if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES &&
> skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
>
> and let the compiler (rather than preprocessor) eliminate this if ()
> block.
>
Thanks for review and explanation Jakub, I will incorporate this change
in next revision.
Regards,
Aditya
^ permalink raw reply
* [PATCH net-next v6 0/2] net: mana: Enforce TX SGE limit and fix error cleanup
From: Aditya Garg @ 2025-11-18 11:11 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, longli, kotaranov, horms, shradhagupta, ssengar,
ernis, dipayanroy, shirazsaleem, leon, mlevitsk, yury.norov,
sbhatta, linux-hyperv, netdev, linux-kernel, linux-rdma,
gargaditya
Cc: Aditya Garg
Add pre-transmission checks to block SKBs that exceed the hardware's SGE
limit. Force software segmentation for GSO traffic and linearize non-GSO
packets as needed.
Update TX error handling to drop failed SKBs and unmap resources
immediately.
---
Changes in v6:
* Replace #if logic with constant expression in if().
Changes in v5:
* Drop skb_is_gso() check for disabling GSO in mana_features_check().
* Register .ndo_features_check conditionally to avoid unnecessary call.
Changes in v4:
* Fix warning during build reported by kernel test robot
---
Aditya Garg (2):
net: mana: Handle SKB if TX SGEs exceed hardware limit
net: mana: Drop TX skb on post_work_request failure and unmap
resources
.../net/ethernet/microsoft/mana/gdma_main.c | 6 +--
drivers/net/ethernet/microsoft/mana/mana_en.c | 47 ++++++++++++++++---
.../ethernet/microsoft/mana/mana_ethtool.c | 2 +
include/net/mana/gdma.h | 8 +++-
include/net/mana/mana.h | 2 +
5 files changed, 53 insertions(+), 12 deletions(-)
--
2.43.0
^ permalink raw reply
* [PATCH net-next v6 1/2] net: mana: Handle SKB if TX SGEs exceed hardware limit
From: Aditya Garg @ 2025-11-18 11:11 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, longli, kotaranov, horms, shradhagupta, ssengar,
ernis, dipayanroy, shirazsaleem, leon, mlevitsk, yury.norov,
sbhatta, linux-hyperv, netdev, linux-kernel, linux-rdma,
gargaditya
Cc: Aditya Garg
In-Reply-To: <1763464269-10431-1-git-send-email-gargaditya@linux.microsoft.com>
The MANA hardware supports a maximum of 30 scatter-gather entries (SGEs)
per TX WQE. Exceeding this limit can cause TX failures.
Add ndo_features_check() callback to validate SKB layout before
transmission. For GSO SKBs that would exceed the hardware SGE limit, clear
NETIF_F_GSO_MASK to enforce software segmentation in the stack.
Add a fallback in mana_start_xmit() to linearize non-GSO SKBs that still
exceed the SGE limit.
Also, Add ethtool counter for SKBs linearized
Co-developed-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
---
Changes in v6:
* Replace #if logic with constant expression in if().
Changes in v5:
* Drop skb_is_gso() check for disabling GSO in mana_features_check().
* Register .ndo_features_check conditionally to avoid unnecessary call.
Changes in v4:
* No change.
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 40 ++++++++++++++++++-
.../ethernet/microsoft/mana/mana_ethtool.c | 2 +
include/net/mana/gdma.h | 8 +++-
include/net/mana/mana.h | 1 +
4 files changed, 48 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 13f47be7aca6..7b49ab005e2d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
#include <linux/mm.h>
#include <linux/pci.h>
#include <linux/export.h>
+#include <linux/skbuff.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
@@ -329,6 +330,21 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
cq = &apc->tx_qp[txq_idx].tx_cq;
tx_stats = &txq->stats;
+ BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES);
+ if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES &&
+ skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+ /* GSO skb with Hardware SGE limit exceeded is not expected here
+ * as they are handled in mana_features_check() callback
+ */
+ if (skb_linearize(skb)) {
+ netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n",
+ skb_shinfo(skb)->nr_frags,
+ skb_is_gso(skb));
+ goto tx_drop_count;
+ }
+ apc->eth_stats.tx_linear_pkt_cnt++;
+ }
+
pkg.tx_oob.s_oob.vcq_num = cq->gdma_id;
pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame;
@@ -442,8 +458,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
}
}
- WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES);
-
if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) {
pkg.wqe_req.sgl = pkg.sgl_array;
} else {
@@ -518,6 +532,25 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
return NETDEV_TX_OK;
}
+#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
+static netdev_features_t mana_features_check(struct sk_buff *skb,
+ struct net_device *ndev,
+ netdev_features_t features)
+{
+ if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+ /* Exceeds HW SGE limit.
+ * GSO case:
+ * Disable GSO so the stack will software-segment the skb
+ * into smaller skbs that fit the SGE budget.
+ * Non-GSO case:
+ * The xmit path will attempt skb_linearize() as a fallback.
+ */
+ features &= ~NETIF_F_GSO_MASK;
+ }
+ return features;
+}
+#endif
+
static void mana_get_stats64(struct net_device *ndev,
struct rtnl_link_stats64 *st)
{
@@ -883,6 +916,9 @@ static const struct net_device_ops mana_devops = {
.ndo_open = mana_open,
.ndo_stop = mana_close,
.ndo_select_queue = mana_select_queue,
+#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
+ .ndo_features_check = mana_features_check,
+#endif
.ndo_start_xmit = mana_start_xmit,
.ndo_validate_addr = eth_validate_addr,
.ndo_get_stats64 = mana_get_stats64,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 99e811208683..0e2f4343ac67 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -18,6 +18,8 @@ static const struct mana_stats_desc mana_eth_stats[] = {
{"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)},
{"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
tx_cqe_unknown_type)},
+ {"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats,
+ tx_linear_pkt_cnt)},
{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
rx_coalesced_err)},
{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 2e4f2f3175e5..a4cf307859f8 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -486,6 +486,8 @@ struct gdma_wqe {
#define INLINE_OOB_SMALL_SIZE 8
#define INLINE_OOB_LARGE_SIZE 24
+#define MANA_MAX_TX_WQE_SGL_ENTRIES 30
+
#define MAX_TX_WQE_SIZE 512
#define MAX_RX_WQE_SIZE 256
@@ -592,6 +594,9 @@ enum {
#define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17)
#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
+/* Driver supports linearizing the skb when num_sge exceeds hardware limit */
+#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20)
+
/* Driver can send HWC periodically to query stats */
#define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21)
@@ -605,7 +610,8 @@ enum {
GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \
- GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY)
+ GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \
+ GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE)
#define GDMA_DRV_CAP_FLAGS2 0
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index d37f4cea0ac3..fb28b3cac067 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -377,6 +377,7 @@ struct mana_ethtool_stats {
u64 wake_queue;
u64 tx_cqe_err;
u64 tx_cqe_unknown_type;
+ u64 tx_linear_pkt_cnt;
u64 rx_coalesced_err;
u64 rx_cqe_unknown_type;
};
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v6 2/2] net: mana: Drop TX skb on post_work_request failure and unmap resources
From: Aditya Garg @ 2025-11-18 11:11 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, longli, kotaranov, horms, shradhagupta, ssengar,
ernis, dipayanroy, shirazsaleem, leon, mlevitsk, yury.norov,
sbhatta, linux-hyperv, netdev, linux-kernel, linux-rdma,
gargaditya
Cc: Aditya Garg
In-Reply-To: <1763464269-10431-1-git-send-email-gargaditya@linux.microsoft.com>
Drop TX packets when posting the work request fails and ensure DMA
mappings are always cleaned up.
Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
---
Changes in v6:
* No change.
Changes in v5:
* No change.
Changes in v4:
* Fix warning during build reported by kernel test robot
---
drivers/net/ethernet/microsoft/mana/gdma_main.c | 6 +-----
drivers/net/ethernet/microsoft/mana/mana_en.c | 7 +++----
include/net/mana/mana.h | 1 +
3 files changed, 5 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index effe0a2f207a..8fd70b34807a 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1300,7 +1300,6 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
struct gdma_posted_wqe_info *wqe_info)
{
u32 client_oob_size = wqe_req->inline_oob_size;
- struct gdma_context *gc;
u32 sgl_data_size;
u32 max_wqe_size;
u32 wqe_size;
@@ -1330,11 +1329,8 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
if (wqe_size > max_wqe_size)
return -EINVAL;
- if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq)) {
- gc = wq->gdma_dev->gdma_context;
- dev_err(gc->dev, "unsuccessful flow control!\n");
+ if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq))
return -ENOSPC;
- }
if (wqe_info)
wqe_info->wqe_size_in_bu = wqe_size / GDMA_WQE_BU_SIZE;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 7b49ab005e2d..1ad154f9db1a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -492,9 +492,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
if (err) {
(void)skb_dequeue_tail(&txq->pending_skbs);
+ mana_unmap_skb(skb, apc);
netdev_warn(ndev, "Failed to post TX OOB: %d\n", err);
- err = NETDEV_TX_BUSY;
- goto tx_busy;
+ goto free_sgl_ptr;
}
err = NETDEV_TX_OK;
@@ -514,7 +514,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
tx_stats->bytes += len + ((num_gso_seg - 1) * gso_hs);
u64_stats_update_end(&tx_stats->syncp);
-tx_busy:
if (netif_tx_queue_stopped(net_txq) && mana_can_tx(gdma_sq)) {
netif_tx_wake_queue(net_txq);
apc->eth_stats.wake_queue++;
@@ -1687,7 +1686,7 @@ static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units)
return 0;
}
-static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
{
struct mana_skb_head *ash = (struct mana_skb_head *)skb->head;
struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index fb28b3cac067..d7e089c6b694 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -593,6 +593,7 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
void mana_query_phy_stats(struct mana_port_context *apc);
int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc);
extern const struct ethtool_ops mana_ethtool_ops;
extern struct dentry *mana_debugfs_root;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
From: kernel test robot @ 2025-11-18 13:38 UTC (permalink / raw)
To: Praveen K Paladugu, kys, haiyangz, wei.liu, decui, tglx, mingo,
linux-hyperv, linux-kernel, bp, dave.hansen, x86, hpa, arnd
Cc: oe-kbuild-all, anbelski, prapal, easwar.hariharan, nunodasneves,
skinsburskii
In-Reply-To: <20251117210855.108126-3-prapal@linux.microsoft.com>
Hi Praveen,
kernel test robot noticed the following build errors:
[auto build test ERROR on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base: next-20251117
patch link: https://lore.kernel.org/r/20251117210855.108126-3-prapal%40linux.microsoft.com
patch subject: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
config: i386-randconfig-141-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182134.X8qi5PeT-lkp@intel.com/config)
compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182134.X8qi5PeT-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182134.X8qi5PeT-lkp@intel.com/
All errors (new ones prefixed by >>):
>> drivers/hv/mshv_common.c:210:6: error: redefinition of 'hv_sleep_notifiers_register'
210 | void hv_sleep_notifiers_register(void)
| ^
arch/x86/include/asm/mshyperv.h:188:20: note: previous definition is here
188 | static inline void hv_sleep_notifiers_register(void) {};
| ^
1 error generated.
vim +/hv_sleep_notifiers_register +210 drivers/hv/mshv_common.c
209
> 210 void hv_sleep_notifiers_register(void)
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
^ permalink raw reply
* Re: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
From: kernel test robot @ 2025-11-18 13:59 UTC (permalink / raw)
To: Praveen K Paladugu, kys, haiyangz, wei.liu, decui, tglx, mingo,
linux-hyperv, linux-kernel, bp, dave.hansen, x86, hpa, arnd
Cc: llvm, oe-kbuild-all, anbelski, prapal, easwar.hariharan,
nunodasneves, skinsburskii
In-Reply-To: <20251117210855.108126-3-prapal@linux.microsoft.com>
Hi Praveen,
kernel test robot noticed the following build warnings:
[auto build test WARNING on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base: next-20251117
patch link: https://lore.kernel.org/r/20251117210855.108126-3-prapal%40linux.microsoft.com
patch subject: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
config: arm64-randconfig-003-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182118.ZOxiv0Fn-lkp@intel.com/config)
compiler: clang version 19.1.7 (https://github.com/llvm/llvm-project cd708029e0b2869e80abe31ddb175f7c35361f90)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182118.ZOxiv0Fn-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182118.ZOxiv0Fn-lkp@intel.com/
All warnings (new ones prefixed by >>):
>> drivers/hv/mshv_common.c:210:6: warning: no previous prototype for function 'hv_sleep_notifiers_register' [-Wmissing-prototypes]
210 | void hv_sleep_notifiers_register(void)
| ^
drivers/hv/mshv_common.c:210:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
210 | void hv_sleep_notifiers_register(void)
| ^
| static
1 warning generated.
vim +/hv_sleep_notifiers_register +210 drivers/hv/mshv_common.c
209
> 210 void hv_sleep_notifiers_register(void)
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
^ permalink raw reply
* Re: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV
From: kernel test robot @ 2025-11-18 15:53 UTC (permalink / raw)
To: Praveen K Paladugu, kys, haiyangz, wei.liu, decui, tglx, mingo,
linux-hyperv, linux-kernel, bp, dave.hansen, x86, hpa, arnd
Cc: llvm, oe-kbuild-all, anbelski, prapal, easwar.hariharan,
nunodasneves, skinsburskii
In-Reply-To: <20251117210855.108126-4-prapal@linux.microsoft.com>
Hi Praveen,
kernel test robot noticed the following build warnings:
[auto build test WARNING on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base: next-20251117
patch link: https://lore.kernel.org/r/20251117210855.108126-4-prapal%40linux.microsoft.com
patch subject: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV
config: arm64-randconfig-003-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182353.5FvVmUhR-lkp@intel.com/config)
compiler: clang version 19.1.7 (https://github.com/llvm/llvm-project cd708029e0b2869e80abe31ddb175f7c35361f90)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182353.5FvVmUhR-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182353.5FvVmUhR-lkp@intel.com/
All warnings (new ones prefixed by >>):
drivers/hv/mshv_common.c:210:6: warning: no previous prototype for function 'hv_sleep_notifiers_register' [-Wmissing-prototypes]
210 | void hv_sleep_notifiers_register(void)
| ^
drivers/hv/mshv_common.c:210:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
210 | void hv_sleep_notifiers_register(void)
| ^
| static
>> drivers/hv/mshv_common.c:224:6: warning: no previous prototype for function 'hv_machine_power_off' [-Wmissing-prototypes]
224 | void hv_machine_power_off(void)
| ^
drivers/hv/mshv_common.c:224:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
224 | void hv_machine_power_off(void)
| ^
| static
2 warnings generated.
vim +/hv_machine_power_off +224 drivers/hv/mshv_common.c
219
220 /*
221 * Power off the machine by entering S5 sleep state via Hyper-V hypercall.
222 * This call does not return if successful.
223 */
> 224 void hv_machine_power_off(void)
225 {
226 unsigned long flags;
227 struct hv_input_enter_sleep_state *in;
228
229 local_irq_save(flags);
230 in = *this_cpu_ptr(hyperv_pcpu_input_arg);
231 in->sleep_state = HV_SLEEP_STATE_S5;
232
233 (void)hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
234 local_irq_restore(flags);
235
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
^ permalink raw reply
* RE: [PATCH v6 3/5] Drivers: hv: Batch GPA unmap operations to improve large region performance
From: Michael Kelley @ 2025-11-18 16:28 UTC (permalink / raw)
To: Stanislav Kinsburskii, kys@microsoft.com, haiyangz@microsoft.com,
wei.liu@kernel.org, decui@microsoft.com
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <176339836892.27330.9465609709535892557.stgit@skinsburskii-cloud-desktop.internal.cloudapp.net>
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com> Sent: Monday, November 17, 2025 8:53 AM
>
> Reduce overhead when unmapping large memory regions by batching GPA unmap
> operations in 2MB-aligned chunks.
>
> Use a dedicated constant for batch size to improve code clarity and
> maintainability.
>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> Reviewed-by: Michael Kelley <mhklinux@outlook.com>
> Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> ---
> drivers/hv/mshv_root.h | 2 ++
> drivers/hv/mshv_root_hv_call.c | 2 +-
> drivers/hv/mshv_root_main.c | 36 ++++++++++++++++++++++++++++++------
> 3 files changed, 33 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/hv/mshv_root.h b/drivers/hv/mshv_root.h
> index 3eb815011b46..5eece7077f8b 100644
> --- a/drivers/hv/mshv_root.h
> +++ b/drivers/hv/mshv_root.h
> @@ -32,6 +32,8 @@ static_assert(HV_HYP_PAGE_SIZE == MSHV_HV_PAGE_SIZE);
>
> #define MSHV_PIN_PAGES_BATCH_SIZE (0x10000000ULL / HV_HYP_PAGE_SIZE)
>
> +#define MSHV_MAX_UNMAP_GPA_PAGES 512
> +
> struct mshv_vp {
> u32 vp_index;
> struct mshv_partition *vp_partition;
> diff --git a/drivers/hv/mshv_root_hv_call.c b/drivers/hv/mshv_root_hv_call.c
> index caf02cfa49c9..8fa983f1109b 100644
> --- a/drivers/hv/mshv_root_hv_call.c
> +++ b/drivers/hv/mshv_root_hv_call.c
> @@ -17,7 +17,7 @@
> /* Determined empirically */
> #define HV_INIT_PARTITION_DEPOSIT_PAGES 208
> #define HV_MAP_GPA_DEPOSIT_PAGES 256
> -#define HV_UMAP_GPA_PAGES 512
> +#define HV_UMAP_GPA_PAGES MSHV_MAX_UNMAP_GPA_PAGES
>
> #define HV_PAGE_COUNT_2M_ALIGNED(pg_count) (!((pg_count) & (0x200 - 1)))
>
> diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
> index a85872b72b1a..ef36d8115d8a 100644
> --- a/drivers/hv/mshv_root_main.c
> +++ b/drivers/hv/mshv_root_main.c
> @@ -1365,7 +1365,7 @@ mshv_map_user_memory(struct mshv_partition *partition,
> static void mshv_partition_destroy_region(struct mshv_mem_region *region)
> {
> struct mshv_partition *partition = region->partition;
> - u32 unmap_flags = 0;
> + u64 gfn, gfn_count, start_gfn, end_gfn;
> int ret;
>
> hlist_del(®ion->hnode);
> @@ -1380,12 +1380,36 @@ static void mshv_partition_destroy_region(struct mshv_mem_region *region)
> }
> }
>
> - if (region->flags.large_pages)
> - unmap_flags |= HV_UNMAP_GPA_LARGE_PAGE;
> + start_gfn = region->start_gfn;
> + end_gfn = region->start_gfn + region->nr_pages;
> +
> + for (gfn = start_gfn; gfn < end_gfn; gfn += gfn_count) {
> + u32 unmap_flags = 0;
> +
> + if (gfn % MSHV_MAX_UNMAP_GPA_PAGES)
> + gfn_count = ALIGN(gfn, MSHV_MAX_UNMAP_GPA_PAGES) - gfn;
> + else
> + gfn_count = MSHV_MAX_UNMAP_GPA_PAGES;
> +
> + if (gfn + gfn_count > end_gfn)
> + gfn_count = end_gfn - gfn;
>
> - /* ignore unmap failures and continue as process may be exiting */
> - hv_call_unmap_gpa_pages(partition->pt_id, region->start_gfn,
> - region->nr_pages, unmap_flags);
> + /* Skip all pages in this range if none are mapped */
> + if (!memchr_inv(region->pages + (gfn - start_gfn), 0,
> + gfn_count * sizeof(struct page *)))
> + continue;
> +
> + if (region->flags.large_pages &&
> + VALUE_PMD_ALIGNED(gfn) && VALUE_PMD_ALIGNED(gfn_count))
VALUE_PMD_ALIGNED isn't defined until Patch 4 of this series.
The idea of a page count being PMD aligned occurs a few other places in
Linux kernel code, and it is usually written as IS_ALIGNED(count, PTRS_PER_PMD),
though there's one occurrence of !(count % PTRS_PER_PMD).
Also mshv_root_hv_call.c has HV_PAGE_COUNT_2M_ALIGNED() that does
the same thing. Some macro consolidation is appropriate, or just open code
as IS_ALIGNED(<cnt>, PTRS_PER_PMD) and eliminate the macros.
> + unmap_flags |= HV_UNMAP_GPA_LARGE_PAGE;
> +
> + ret = hv_call_unmap_gpa_pages(partition->pt_id, gfn,
> + gfn_count, unmap_flags);
> + if (ret)
> + pt_err(partition,
> + "Failed to unmap GPA pages %#llx-%#llx: %d\n",
> + gfn, gfn + gfn_count - 1, ret);
> + }
>
> mshv_region_invalidate(region);
>
>
>
^ permalink raw reply
* RE: [PATCH v6 5/5] Drivers: hv: Add support for movable memory regions
From: Michael Kelley @ 2025-11-18 16:29 UTC (permalink / raw)
To: Stanislav Kinsburskii, kys@microsoft.com, haiyangz@microsoft.com,
wei.liu@kernel.org, decui@microsoft.com
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <176339837995.27330.14240947043073674139.stgit@skinsburskii-cloud-desktop.internal.cloudapp.net>
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com> Sent: Monday, November 17, 2025 8:53 AM
>
> Introduce support for movable memory regions in the Hyper-V root partition
> driver, thus improving memory management flexibility and preparing the
> driver for advanced use cases such as dynamic memory remapping.
>
> Integrate mmu_interval_notifier for movable regions, implement functions to
> handle HMM faults and memory invalidation, and update memory region mapping
> logic to support movable regions.
>
> While MMU notifiers are commonly used in virtualization drivers, this
> implementation leverages HMM (Heterogeneous Memory Management) for its
> tailored functionality. HMM provides a ready-made framework for mirroring,
> invalidation, and fault handling, avoiding the need to reimplement these
> mechanisms for a single callback. Although MMU notifiers are more generic,
> using HMM reduces boilerplate and ensures maintainability by utilizing a
> mechanism specifically designed for such use cases.
I wasn't previously familiar with HMM when reviewing this code, so I had to
work through the details, and mentally build a high-level view of how this
case use maps to concepts in the Linux kernel documentation for HMM.
Here's my take:
In this use case, the goal is what HMM calls "address space mirroring"
between Linux in the root partition and a guest VM. Linux in the root
partition is the primary owner of the memory. Each guest VM is a
"device" from the HMM standpoint, and the device page tables are the
hypervisor's SLAT entries that are managed using hypercalls to map and
unmap memory. When a guest VM is using unpinned memory, the guest
VM faults and generates a VP intercept when it first touches a page in its
GFN space. MSHV is the device driver for the "device", and it handles the
VP intercept by calling hmm_range_fault() to populate the pages, and then
making hypercalls to set up the "device" page tables (i.e., the SLAT entries).
Linux in the root partition can reclaim ownership of a memory range via
the HMM "invalidate" callback, which MSHV handles by making hypercalls
to clear the SLAT entries. After such a invalidate, the guest VM will fault
again if it touches the memory range.
Is this a correct understanding? If so, including such a summary in the
commit message or as a code comment would be helpful to people
in the future who are looking at the code.
>
> Signed-off-by: Anirudh Rayabharam <anrayabh@linux.microsoft.com>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> ---
> drivers/hv/Kconfig | 1
> drivers/hv/mshv_root.h | 8 +
> drivers/hv/mshv_root_main.c | 328
> ++++++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 327 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
> index 0b8c391a0342..5f1637cbb6e3 100644
> --- a/drivers/hv/Kconfig
> +++ b/drivers/hv/Kconfig
> @@ -75,6 +75,7 @@ config MSHV_ROOT
> depends on PAGE_SIZE_4KB
> select EVENTFD
> select VIRT_XFER_TO_GUEST_WORK
> + select HMM_MIRROR
Couldn't you also do "select MMU_NOTIFIER" to avoid the #ifdef's
and stubs for when it isn't selected? There are other Linux kernel
drivers that select it. Or is the intent to allow building an image that
doesn't support unpinned memory, and the #ifdef's save space?
> default n
> help
> Select this option to enable support for booting and running as root
> diff --git a/drivers/hv/mshv_root.h b/drivers/hv/mshv_root.h
> index 5eece7077f8b..117399dea780 100644
> --- a/drivers/hv/mshv_root.h
> +++ b/drivers/hv/mshv_root.h
> @@ -15,6 +15,7 @@
> #include <linux/hashtable.h>
> #include <linux/dev_printk.h>
> #include <linux/build_bug.h>
> +#include <linux/mmu_notifier.h>
> #include <uapi/linux/mshv.h>
>
> /*
> @@ -81,9 +82,14 @@ struct mshv_mem_region {
> struct {
> u64 large_pages: 1; /* 2MiB */
> u64 range_pinned: 1;
> - u64 reserved: 62;
> + u64 is_ram : 1; /* mem region can be ram or mmio */
The combination of "range_pinned" and "is_ram" effectively define three
MSHV region types:
1) MMIO
2) Pinned RAM
3) Unpinned RAM
Would it make sense to have an enum instead of 2 booleans? It seems
like that would simplify the code a bit in a couple places. For example,
mshv_handle_gpa_intercept() could just do one WARN_ON() instead of two.
Also you would not need mshv_partition_destroy_region() testing "is_ram",
and then mshv_region_movable_fini() testing "range_pinned". A single test
could cover both.
Just a suggestion. Ignore my comment if you prefer the 2 booleans.
> + u64 reserved: 61;
> } flags;
> struct mshv_partition *partition;
> +#if defined(CONFIG_MMU_NOTIFIER)
> + struct mmu_interval_notifier mni;
> + struct mutex mutex; /* protects region pages remapping */
> +#endif
> struct page *pages[];
> };
>
> diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
> index 73aaa149c14c..fe0c5eaa1248 100644
> --- a/drivers/hv/mshv_root_main.c
> +++ b/drivers/hv/mshv_root_main.c
> @@ -29,6 +29,7 @@
> #include <linux/crash_dump.h>
> #include <linux/panic_notifier.h>
> #include <linux/vmalloc.h>
> +#include <linux/hmm.h>
>
> #include "mshv_eventfd.h"
> #include "mshv.h"
> @@ -36,6 +37,8 @@
>
> #define VALUE_PMD_ALIGNED(c) (!((c) & (PTRS_PER_PMD - 1)))
>
> +#define MSHV_MAP_FAULT_IN_PAGES HPAGE_PMD_NR
> +
> MODULE_AUTHOR("Microsoft");
> MODULE_LICENSE("GPL");
> MODULE_DESCRIPTION("Microsoft Hyper-V root partition VMM interface /dev/mshv");
> @@ -76,6 +79,11 @@ static int mshv_vp_mmap(struct file *file, struct vm_area_struct *vma);
> static vm_fault_t mshv_vp_fault(struct vm_fault *vmf);
> static int mshv_init_async_handler(struct mshv_partition *partition);
> static void mshv_async_hvcall_handler(void *data, u64 *status);
> +static struct mshv_mem_region
> + *mshv_partition_region_by_gfn(struct mshv_partition *pt, u64 gfn);
> +static int mshv_region_remap_pages(struct mshv_mem_region *region,
> + u32 map_flags, u64 page_offset,
> + u64 page_count);
>
> static const union hv_input_vtl input_vtl_zero;
> static const union hv_input_vtl input_vtl_normal = {
> @@ -602,14 +610,197 @@ static long mshv_run_vp_with_root_scheduler(struct mshv_vp *vp)
> static_assert(sizeof(struct hv_message) <= MSHV_RUN_VP_BUF_SZ,
> "sizeof(struct hv_message) must not exceed MSHV_RUN_VP_BUF_SZ");
>
> +#ifdef CONFIG_X86_64
> +
> +#if defined(CONFIG_MMU_NOTIFIER)
> +/**
> + * mshv_region_hmm_fault_and_lock - Handle HMM faults and lock the memory region
> + * @region: Pointer to the memory region structure
> + * @range: Pointer to the HMM range structure
> + *
> + * This function performs the following steps:
> + * 1. Reads the notifier sequence for the HMM range.
> + * 2. Acquires a read lock on the memory map.
> + * 3. Handles HMM faults for the specified range.
> + * 4. Releases the read lock on the memory map.
> + * 5. If successful, locks the memory region mutex.
> + * 6. Verifies if the notifier sequence has changed during the operation.
> + * If it has, releases the mutex and returns -EBUSY to match with
> + * hmm_range_fault() return code for repeating.
> + *
> + * Return: 0 on success, a negative error code otherwise.
> + */
> +static int mshv_region_hmm_fault_and_lock(struct mshv_mem_region *region,
> + struct hmm_range *range)
> +{
> + int ret;
> +
> + range->notifier_seq = mmu_interval_read_begin(range->notifier);
> + mmap_read_lock(region->mni.mm);
> + ret = hmm_range_fault(range);
> + mmap_read_unlock(region->mni.mm);
> + if (ret)
> + return ret;
> +
> + mutex_lock(®ion->mutex);
> +
> + if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
> + mutex_unlock(®ion->mutex);
> + cond_resched();
> + return -EBUSY;
> + }
> +
> + return 0;
> +}
> +
> +/**
> + * mshv_region_range_fault - Handle memory range faults for a given region.
> + * @region: Pointer to the memory region structure.
> + * @page_offset: Offset of the page within the region.
> + * @page_count: Number of pages to handle.
> + *
> + * This function resolves memory faults for a specified range of pages
> + * within a memory region. It uses HMM (Heterogeneous Memory Management)
> + * to fault in the required pages and updates the region's page array.
> + *
> + * Return: 0 on success, negative error code on failure.
> + */
> +static int mshv_region_range_fault(struct mshv_mem_region *region,
> + u64 page_offset, u64 page_count)
> +{
> + struct hmm_range range = {
> + .notifier = ®ion->mni,
> + .default_flags = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE,
> + };
> + unsigned long *pfns;
> + int ret;
> + u64 i;
> +
> + pfns = kmalloc_array(page_count, sizeof(unsigned long), GFP_KERNEL);
> + if (!pfns)
> + return -ENOMEM;
> +
> + range.hmm_pfns = pfns;
> + range.start = region->start_uaddr + page_offset * HV_HYP_PAGE_SIZE;
> + range.end = range.start + page_count * HV_HYP_PAGE_SIZE;
> +
> + do {
> + ret = mshv_region_hmm_fault_and_lock(region, &range);
> + } while (ret == -EBUSY);
I expected the looping on -EBUSY to be in mshv_region_hmm_fault_and_lock(),
but I guess it really doesn't matter.
> +
> + if (ret)
> + goto out;
> +
> + for (i = 0; i < page_count; i++)
> + region->pages[page_offset + i] = hmm_pfn_to_page(pfns[i]);
The comment with hmm_pfn_to_page() says that the caller is assumed to
have tested the pfn for HMM_PFN_VALID, which I don't see done anywhere.
Is there a reason it's not necessary to test?
> +
> + if (PageHuge(region->pages[page_offset]))
> + region->flags.large_pages = true;
See comment below in mshv_region_handle_gfn_fault().
> +
> + ret = mshv_region_remap_pages(region, region->hv_map_flags,
> + page_offset, page_count);
> +
> + mutex_unlock(®ion->mutex);
> +out:
> + kfree(pfns);
> + return ret;
> +}
> +#else /* CONFIG_MMU_NOTIFIER */
> +static int mshv_region_range_fault(struct mshv_mem_region *region,
> + u64 page_offset, u64 page_count)
> +{
> + return -ENODEV;
> +}
> +#endif /* CONFIG_MMU_NOTIFIER */
> +
> +static bool mshv_region_handle_gfn_fault(struct mshv_mem_region *region, u64 gfn)
> +{
> + u64 page_offset, page_count;
> + int ret;
> +
> + if (WARN_ON_ONCE(region->flags.range_pinned))
> + return false;
> +
> + /* Align the page offset to the nearest MSHV_MAP_FAULT_IN_PAGES. */
> + page_offset = ALIGN_DOWN(gfn - region->start_gfn,
> + MSHV_MAP_FAULT_IN_PAGES);
> +
> + /* Map more pages than requested to reduce the number of faults. */
> + page_count = min(region->nr_pages - page_offset,
> + MSHV_MAP_FAULT_IN_PAGES);
These computations make the range defined by page_offset and page_count
start on a 512 page boundary relative to start_gfn, and have a size that is a
multiple of 512 pages. But they don't ensure that the range aligns to a large page
boundary within gfn space since region->start_gfn may not be a multiple of
512. Then mshv_region_range_fault() tests the first page of the range for
being a large page, and if so, sets region->large_pages. This doesn't make
sense to me if the range doesn't align to a large page boundary.
Does this code need to make sure that the range is aligned to a large
page boundary in gfn space? Or am I misunderstanding what the
region->large_pages flag means? Given the fixes in this v6 of the
patch set, I was thinking that region->large_pages means that every
large page aligned area within the region is a large page. If region->
start_gfn and region->nr_pages aren't multiples of 512, then there
may be an initial range and a final range that aren't large pages,
but everything in between is. If that's not a correct understanding,
could you clarify the exact meaning of the region->large_pages
flag?
> +
> + ret = mshv_region_range_fault(region, page_offset, page_count);
> +
> + WARN_ONCE(ret,
> + "p%llu: GPA intercept failed: region %#llx-%#llx, gfn %#llx, page_offset %llu, page_count %llu\n",
> + region->partition->pt_id, region->start_uaddr,
> + region->start_uaddr + (region->nr_pages << HV_HYP_PAGE_SHIFT),
> + gfn, page_offset, page_count);
> +
> + return !ret;
> +}
> +
> +/**
> + * mshv_handle_gpa_intercept - Handle GPA (Guest Physical Address) intercepts.
> + * @vp: Pointer to the virtual processor structure.
> + *
> + * This function processes GPA intercepts by identifying the memory region
> + * corresponding to the intercepted GPA, aligning the page offset, and
> + * mapping the required pages. It ensures that the region is valid and
> + * handles faults efficiently by mapping multiple pages at once.
> + *
> + * Return: true if the intercept was handled successfully, false otherwise.
> + */
> +static bool mshv_handle_gpa_intercept(struct mshv_vp *vp)
> +{
> + struct mshv_partition *p = vp->vp_partition;
> + struct mshv_mem_region *region;
> + struct hv_x64_memory_intercept_message *msg;
> + u64 gfn;
> +
> + msg = (struct hv_x64_memory_intercept_message *)
> + vp->vp_intercept_msg_page->u.payload;
> +
> + gfn = HVPFN_DOWN(msg->guest_physical_address);
> +
> + region = mshv_partition_region_by_gfn(p, gfn);
> + if (!region)
> + return false;
Does it ever happen that the gfn is legitimately not found in any
region, perhaps due to a race? I think the vp_mutex is held here,
so maybe that protects the region layout for the VP and "not found"
should never occur. If so, should there be a WARN_ON here?
If "gfn not found" can be legitimate, perhaps a comment to
explain the circumstances would be helpful.
> +
> + if (WARN_ON_ONCE(!region->flags.is_ram))
> + return false;
> +
> + if (WARN_ON_ONCE(region->flags.range_pinned))
> + return false;
> +
> + return mshv_region_handle_gfn_fault(region, gfn);
> +}
> +
> +#else /* CONFIG_X86_64 */
> +
> +static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) { return false; }
> +
> +#endif /* CONFIG_X86_64 */
> +
> +static bool mshv_vp_handle_intercept(struct mshv_vp *vp)
> +{
> + switch (vp->vp_intercept_msg_page->header.message_type) {
> + case HVMSG_GPA_INTERCEPT:
> + return mshv_handle_gpa_intercept(vp);
> + }
> + return false;
> +}
> +
> static long mshv_vp_ioctl_run_vp(struct mshv_vp *vp, void __user *ret_msg)
> {
> long rc;
>
> - if (hv_scheduler_type == HV_SCHEDULER_TYPE_ROOT)
> - rc = mshv_run_vp_with_root_scheduler(vp);
> - else
> - rc = mshv_run_vp_with_hyp_scheduler(vp);
> + do {
> + if (hv_scheduler_type == HV_SCHEDULER_TYPE_ROOT)
> + rc = mshv_run_vp_with_root_scheduler(vp);
> + else
> + rc = mshv_run_vp_with_hyp_scheduler(vp);
> + } while (rc == 0 && mshv_vp_handle_intercept(vp));
>
> if (rc)
> return rc;
> @@ -1194,6 +1385,110 @@ mshv_partition_region_by_gfn(struct mshv_partition *partition, u64 gfn)
> return NULL;
> }
>
> +#if defined(CONFIG_MMU_NOTIFIER)
> +static void mshv_region_movable_fini(struct mshv_mem_region *region)
> +{
> + if (region->flags.range_pinned)
> + return;
> +
> + mmu_interval_notifier_remove(®ion->mni);
> +}
> +
> +/**
> + * mshv_region_interval_invalidate - Invalidate a range of memory region
> + * @mni: Pointer to the mmu_interval_notifier structure
> + * @range: Pointer to the mmu_notifier_range structure
> + * @cur_seq: Current sequence number for the interval notifier
> + *
> + * This function invalidates a memory region by remapping its pages with
> + * no access permissions. It locks the region's mutex to ensure thread safety
> + * and updates the sequence number for the interval notifier. If the range
> + * is blockable, it uses a blocking lock; otherwise, it attempts a non-blocking
> + * lock and returns false if unsuccessful.
> + *
> + * NOTE: Failure to invalidate a region is a serious error, as the pages will
> + * be considered freed while they are still mapped by the hypervisor.
> + * Any attempt to access such pages will likely crash the system.
> + *
> + * Return: true if the region was successfully invalidated, false otherwise.
> + */
> +static bool
> +mshv_region_interval_invalidate(struct mmu_interval_notifier *mni,
> + const struct mmu_notifier_range *range,
> + unsigned long cur_seq)
> +{
> + struct mshv_mem_region *region = container_of(mni,
> + struct mshv_mem_region,
> + mni);
> + u64 page_offset, page_count;
> + unsigned long mstart, mend;
> + int ret = -EPERM;
> +
> + if (mmu_notifier_range_blockable(range))
> + mutex_lock(®ion->mutex);
> + else if (!mutex_trylock(®ion->mutex))
> + goto out_fail;
> +
> + mmu_interval_set_seq(mni, cur_seq);
> +
> + mstart = max(range->start, region->start_uaddr);
> + mend = min(range->end, region->start_uaddr +
> + (region->nr_pages << HV_HYP_PAGE_SHIFT));
I'm pretty sure region->start_uaddr is always page aligned. But what
about range->start and range->end? The code here and below assumes
they are page aligned. It also assumes that range->end is greater than
range->start so the computation of page_count doesn't wrap and so
page_count is >= 1. I don't know whether checks for these assumptions
are appropriate.
> +
> + page_offset = HVPFN_DOWN(mstart - region->start_uaddr);
> + page_count = HVPFN_DOWN(mend - mstart);
> +
> + ret = mshv_region_remap_pages(region, HV_MAP_GPA_NO_ACCESS,
> + page_offset, page_count);
> + if (ret)
> + goto out_fail;
> +
> + mshv_region_invalidate_pages(region, page_offset, page_count);
> +
> + mutex_unlock(®ion->mutex);
> +
> + return true;
> +
> +out_fail:
> + WARN_ONCE(ret,
> + "Failed to invalidate region %#llx-%#llx (range %#lx-%#lx, event: %u, pages %#llx-%#llx, mm: %#llx): %d\n",
> + region->start_uaddr,
> + region->start_uaddr + (region->nr_pages << HV_HYP_PAGE_SHIFT),
> + range->start, range->end, range->event,
> + page_offset, page_offset + page_count - 1, (u64)range->mm, ret);
> + return false;
> +}
> +
> +static const struct mmu_interval_notifier_ops mshv_region_mni_ops = {
> + .invalidate = mshv_region_interval_invalidate,
> +};
> +
> +static bool mshv_region_movable_init(struct mshv_mem_region *region)
> +{
> + int ret;
> +
> + ret = mmu_interval_notifier_insert(®ion->mni, current->mm,
> + region->start_uaddr,
> + region->nr_pages << HV_HYP_PAGE_SHIFT,
> + &mshv_region_mni_ops);
> + if (ret)
> + return false;
> +
> + mutex_init(®ion->mutex);
> +
> + return true;
> +}
> +#else
> +static inline void mshv_region_movable_fini(struct mshv_mem_region *region)
> +{
> +}
> +
> +static inline bool mshv_region_movable_init(struct mshv_mem_region *region)
> +{
> + return false;
> +}
> +#endif
> +
> /*
> * NB: caller checks and makes sure mem->size is page aligned
> * Returns: 0 with regionpp updated on success, or -errno
> @@ -1228,9 +1523,14 @@ static int mshv_partition_create_region(struct mshv_partition *partition,
> if (mem->flags & BIT(MSHV_SET_MEM_BIT_EXECUTABLE))
> region->hv_map_flags |= HV_MAP_GPA_EXECUTABLE;
>
> - /* Note: large_pages flag populated when we pin the pages */
> - if (!is_mmio)
> - region->flags.range_pinned = true;
> + /* Note: large_pages flag populated when pages are allocated. */
> + if (!is_mmio) {
> + region->flags.is_ram = true;
> +
> + if (mshv_partition_encrypted(partition) ||
> + !mshv_region_movable_init(region))
> + region->flags.range_pinned = true;
> + }
>
> region->partition = partition;
>
> @@ -1350,9 +1650,16 @@ mshv_map_user_memory(struct mshv_partition *partition,
> if (is_mmio)
> ret = hv_call_map_mmio_pages(partition->pt_id, mem.guest_pfn,
> mmio_pfn, HVPFN_DOWN(mem.size));
> - else
> + else if (region->flags.range_pinned)
> ret = mshv_prepare_pinned_region(region);
> -
> + else
> + /*
> + * For non-pinned regions, remap with no access to let the
> + * hypervisor track dirty pages, enabling pre-copy live
> + * migration.
> + */
> + ret = mshv_region_remap_pages(region, HV_MAP_GPA_NO_ACCESS,
> + 0, region->nr_pages);
> if (ret)
> goto errout;
>
> @@ -1374,6 +1681,9 @@ static void mshv_partition_destroy_region(struct mshv_mem_region *region)
>
> hlist_del(®ion->hnode);
>
> + if (region->flags.is_ram)
> + mshv_region_movable_fini(region);
> +
> if (mshv_partition_encrypted(partition)) {
> ret = mshv_partition_region_share(region);
> if (ret) {
>
>
^ permalink raw reply
* Re: [PATCH net-next v10 01/11] vsock: a per-net vsock NS mode state
From: Stefano Garzarella @ 2025-11-18 18:03 UTC (permalink / raw)
To: Bobby Eshleman
Cc: David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin, Jason Wang,
Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan, linux-kernel,
virtualization, netdev, kvm, linux-hyperv, linux-kselftest,
Sargun Dhillon, berrange, Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-1-df08f165bf3e@meta.com>
On Mon, Nov 17, 2025 at 06:00:24PM -0800, Bobby Eshleman wrote:
>From: Bobby Eshleman <bobbyeshleman@meta.com>
>
>Add the per-net vsock NS mode state. This only adds the structure for
>holding the mode and some of the functions for setting/getting and
>checking the mode, but does not integrate the functionality yet.
>
>A "net_mode" field is added to vsock_sock to store the mode of the
>namespace when the vsock_sock was created. In order to evaluate
>namespace mode rules we need to know both a) which namespace the
>endpoints are in, and b) what mode that namespace had when the endpoints
>were created. This allows us to handle the changing of modes from global
>to local *after* a socket has been created by remembering that the mode
>was global when the socket was created. If we were to use the current
>net's mode instead, then the lookup would fail and the socket would
>break.
>
>Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
>---
>Changes in v10:
>- change mode_locked to int (Stefano)
>
>Changes in v9:
>- use xchg(), WRITE_ONCE(), READ_ONCE() for mode and mode_locked (Stefano)
>- clarify mode0/mode1 meaning in vsock_net_check_mode() comment
>- remove spin lock in net->vsock (not used anymore)
>- change mode from u8 to enum vsock_net_mode in vsock_net_write_mode()
>
>Changes in v7:
>- clarify vsock_net_check_mode() comments
>- change to `orig_net_mode == VSOCK_NET_MODE_GLOBAL && orig_net_mode == vsk->orig_net_mode`
>- remove extraneous explanation of `orig_net_mode`
>- rename `written` to `mode_locked`
>- rename `vsock_hdr` to `sysctl_hdr`
>- change `orig_net_mode` to `net_mode`
>- make vsock_net_check_mode() more generic by taking just net pointers
> and modes, instead of a vsock_sock ptr, for reuse by transports
> (e.g., vhost_vsock)
>
>Changes in v6:
>- add orig_net_mode to store mode at creation time which will be used to
> avoid breakage when namespace changes mode during socket/VM lifespan
>
>Changes in v5:
>- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
>- change from net->vsock.ns_mode to net->vsock.mode
>- change vsock_net_set_mode() to vsock_net_write_mode()
>- vsock_net_write_mode() returns bool for write success to avoid
> need to use vsock_net_mode_can_set()
>- remove vsock_net_mode_can_set()
>---
> MAINTAINERS | 1 +
> include/net/af_vsock.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
> include/net/net_namespace.h | 4 ++++
> include/net/netns/vsock.h | 17 +++++++++++++++++
> 4 files changed, 66 insertions(+)
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Thanks,
Stefano
>
>diff --git a/MAINTAINERS b/MAINTAINERS
>index 37f4278db851..e1e0e2092d0c 100644
>--- a/MAINTAINERS
>+++ b/MAINTAINERS
>@@ -27101,6 +27101,7 @@ L: netdev@vger.kernel.org
> S: Maintained
> F: drivers/vhost/vsock.c
> F: include/linux/virtio_vsock.h
>+F: include/net/netns/vsock.h
> F: include/uapi/linux/virtio_vsock.h
> F: net/vmw_vsock/virtio_transport.c
> F: net/vmw_vsock/virtio_transport_common.c
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index d40e978126e3..9b5bdd083b6f 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -10,6 +10,7 @@
>
> #include <linux/kernel.h>
> #include <linux/workqueue.h>
>+#include <net/netns/vsock.h>
> #include <net/sock.h>
> #include <uapi/linux/vm_sockets.h>
>
>@@ -65,6 +66,7 @@ struct vsock_sock {
> u32 peer_shutdown;
> bool sent_request;
> bool ignore_connecting_rst;
>+ enum vsock_net_mode net_mode;
>
> /* Protected by lock_sock(sk) */
> u64 buffer_size;
>@@ -256,4 +258,46 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
> {
> return t->msgzerocopy_allow && t->msgzerocopy_allow();
> }
>+
>+static inline enum vsock_net_mode vsock_net_mode(struct net *net)
>+{
>+ return READ_ONCE(net->vsock.mode);
>+}
>+
>+static inline bool vsock_net_write_mode(struct net *net,
>+ enum vsock_net_mode mode)
>+{
>+ if (xchg(&net->vsock.mode_locked, 1))
>+ return false;
>+
>+ WRITE_ONCE(net->vsock.mode, mode);
>+ return true;
>+}
>+
>+/* Return true if two namespaces and modes pass the mode rules. Otherwise,
>+ * return false.
>+ *
>+ * - ns0 and ns1 are the namespaces being checked.
>+ * - mode0 and mode1 are the vsock namespace modes of ns0 and ns1 at the time
>+ * the vsock objects were created.
>+ *
>+ * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c.
>+ */
>+static inline bool vsock_net_check_mode(struct net *ns0,
>+ enum vsock_net_mode mode0,
>+ struct net *ns1,
>+ enum vsock_net_mode mode1)
>+{
>+ /* Any vsocks within the same network namespace are always reachable,
>+ * regardless of the mode.
>+ */
>+ if (net_eq(ns0, ns1))
>+ return true;
>+
>+ /*
>+ * If the network namespaces differ, vsocks are only reachable if both
>+ * were created in VSOCK_NET_MODE_GLOBAL mode.
>+ */
>+ return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1;
>+}
> #endif /* __AF_VSOCK_H__ */
>diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
>index cb664f6e3558..66d3de1d935f 100644
>--- a/include/net/net_namespace.h
>+++ b/include/net/net_namespace.h
>@@ -37,6 +37,7 @@
> #include <net/netns/smc.h>
> #include <net/netns/bpf.h>
> #include <net/netns/mctp.h>
>+#include <net/netns/vsock.h>
> #include <net/net_trackers.h>
> #include <linux/ns_common.h>
> #include <linux/idr.h>
>@@ -196,6 +197,9 @@ struct net {
> /* Move to a better place when the config guard is removed. */
> struct mutex rtnl_mutex;
> #endif
>+#if IS_ENABLED(CONFIG_VSOCKETS)
>+ struct netns_vsock vsock;
>+#endif
> } __randomize_layout;
>
> #include <linux/seq_file_net.h>
>diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
>new file mode 100644
>index 000000000000..c1a5e805949d
>--- /dev/null
>+++ b/include/net/netns/vsock.h
>@@ -0,0 +1,17 @@
>+/* SPDX-License-Identifier: GPL-2.0 */
>+#ifndef __NET_NET_NAMESPACE_VSOCK_H
>+#define __NET_NET_NAMESPACE_VSOCK_H
>+
>+#include <linux/types.h>
>+
>+enum vsock_net_mode {
>+ VSOCK_NET_MODE_GLOBAL,
>+ VSOCK_NET_MODE_LOCAL,
>+};
>+
>+struct netns_vsock {
>+ struct ctl_table_header *sysctl_hdr;
>+ enum vsock_net_mode mode;
>+ int mode_locked;
>+};
>+#endif /* __NET_NET_NAMESPACE_VSOCK_H */
>
>--
>2.47.3
>
^ permalink raw reply
* Re: [PATCH net-next v10 02/11] vsock: add netns to vsock core
From: Stefano Garzarella @ 2025-11-18 18:09 UTC (permalink / raw)
To: Bobby Eshleman
Cc: David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin, Jason Wang,
Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan, linux-kernel,
virtualization, netdev, kvm, linux-hyperv, linux-kselftest,
Sargun Dhillon, berrange, Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-2-df08f165bf3e@meta.com>
On Mon, Nov 17, 2025 at 06:00:25PM -0800, Bobby Eshleman wrote:
>From: Bobby Eshleman <bobbyeshleman@meta.com>
>
>Add netns logic to vsock core. Additionally, modify transport hook
>prototypes to be used by later transport-specific patches (e.g.,
>*_seqpacket_allow()).
>
>Namespaces are supported primarily by changing socket lookup functions
>(e.g., vsock_find_connected_socket()) to take into account the socket
>namespace and the namespace mode before considering a candidate socket a
>"match".
>
>This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode that
>accepts the "global" or "local" mode strings.
>
>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 v10:
>- add file-level comment about what happens to sockets/devices
> when the namespace mode changes (Stefano)
>- change the 'if (write)' boolean in vsock_net_mode_string() to
> if (!write), this simplifies a later patch which adds "goto"
> for mutex unlocking on function exit.
>
>Changes in v9:
>- remove virtio_vsock_alloc_rx_skb() (Stefano)
>- remove vsock_global_dummy_net, not needed as net=NULL +
> net_mode=VSOCK_NET_MODE_GLOBAL achieves identical result
>
>Changes in v7:
>- hv_sock: fix hyperv build error
>- explain why vhost does not use the dummy
>- explain usage of __vsock_global_dummy_net
>- explain why VSOCK_NET_MODE_STR_MAX is 8 characters
>- use switch-case in vsock_net_mode_string()
>- avoid changing transports as much as possible
>- add vsock_find_{bound,connected}_socket_net()
>- rename `vsock_hdr` to `sysctl_hdr`
>- add virtio_vsock_alloc_linear_skb() wrapper for setting dummy net and
> global mode for virtio-vsock, move skb->cb zero-ing into wrapper
>- explain seqpacket_allow() change
>- move net setting to __vsock_create() instead of vsock_create() so
> that child sockets also have their net assigned upon accept()
>
>Changes in v6:
>- unregister sysctl ops in vsock_exit()
>- af_vsock: clarify description of CID behavior
>- af_vsock: fix buf vs buffer naming, and length checking
>- af_vsock: fix length checking w/ correct ctl_table->maxlen
>
>Changes in v5:
>- vsock_global_net() -> vsock_global_dummy_net()
>- update comments for new uAPI
>- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
>- add prototype changes so patch remains compilable
>---
> drivers/vhost/vsock.c | 6 +-
> include/net/af_vsock.h | 9 +-
> net/vmw_vsock/af_vsock.c | 258 ++++++++++++++++++++++++++++++++++++---
> net/vmw_vsock/virtio_transport.c | 6 +-
> net/vmw_vsock/vsock_loopback.c | 6 +-
> 5 files changed, 261 insertions(+), 24 deletions(-)
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Thanks,
Stefano
>
>diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
>index ae01457ea2cd..2c937a2df83b 100644
>--- a/drivers/vhost/vsock.c
>+++ b/drivers/vhost/vsock.c
>@@ -404,7 +404,8 @@ static bool vhost_transport_msgzerocopy_allow(void)
> return true;
> }
>
>-static bool vhost_transport_seqpacket_allow(u32 remote_cid);
>+static bool
>+vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
>
> static struct virtio_transport vhost_transport = {
> .transport = {
>@@ -460,7 +461,8 @@ static struct virtio_transport vhost_transport = {
> .send_pkt = vhost_transport_send_pkt,
> };
>
>-static bool vhost_transport_seqpacket_allow(u32 remote_cid)
>+static bool
>+vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
> {
> struct vhost_vsock *vsock;
> bool seqpacket_allow = false;
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index 9b5bdd083b6f..59d97a143204 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -145,7 +145,7 @@ struct vsock_transport {
> int flags);
> int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg,
> size_t len);
>- bool (*seqpacket_allow)(u32 remote_cid);
>+ bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid);
> u32 (*seqpacket_has_data)(struct vsock_sock *vsk);
>
> /* Notification. */
>@@ -218,6 +218,13 @@ void vsock_remove_connected(struct vsock_sock *vsk);
> struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr);
> struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
> struct sockaddr_vm *dst);
>+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
>+ struct net *net,
>+ enum vsock_net_mode net_mode);
>+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
>+ struct sockaddr_vm *dst,
>+ struct net *net,
>+ enum vsock_net_mode net_mode);
> void vsock_remove_sock(struct vsock_sock *vsk);
> void vsock_for_each_connected_socket(struct vsock_transport *transport,
> void (*fn)(struct sock *sk));
>diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>index 72bb6b7ed386..54373ae101c3 100644
>--- a/net/vmw_vsock/af_vsock.c
>+++ b/net/vmw_vsock/af_vsock.c
>@@ -83,6 +83,38 @@
> * TCP_ESTABLISHED - connected
> * TCP_CLOSING - disconnecting
> * TCP_LISTEN - listening
>+ *
>+ * - Namespaces in vsock support two different modes configured
>+ * through /proc/sys/net/vsock/ns_mode. The modes are "local" and "global".
>+ * Each mode defines how the namespace interacts with CIDs.
>+ * /proc/sys/net/vsock/ns_mode is write-once, so that it may be configured
>+ * and locked down by a namespace manager. The default is "global". The mode
>+ * is set per-namespace.
>+ *
>+ * The modes affect the allocation and accessibility of CIDs as follows:
>+ *
>+ * - global - access and allocation are all system-wide
>+ * - all CID allocation from global namespaces draw from the same
>+ * system-wide pool.
>+ * - if one global namespace has already allocated some CID, another
>+ * global namespace will not be able to allocate the same CID.
>+ * - global mode AF_VSOCK sockets can reach any VM or socket in any global
>+ * namespace, they are not contained to only their own namespace.
>+ * - AF_VSOCK sockets in a global mode namespace cannot reach VMs or
>+ * sockets in any local mode namespace.
>+ * - local - access and allocation are contained within the namespace
>+ * - CID allocation draws only from a private pool local only to the
>+ * namespace, and does not affect the CIDs available for allocation in any
>+ * other namespace (global or local).
>+ * - VMs in a local namespace do not collide with CIDs in any other local
>+ * namespace or any global namespace. For example, if a VM in a local mode
>+ * namespace is given CID 10, then CID 10 is still available for
>+ * allocation in any other namespace, but not in the same namespace.
>+ * - AF_VSOCK sockets in a local mode namespace can connect only to VMs or
>+ * other sockets within their own namespace.
>+ * - when a socket or device is initialized in a namespace with mode
>+ * global, it will stay in global mode even if the namespace later
>+ * changes to local.
> */
>
> #include <linux/compat.h>
>@@ -100,6 +132,7 @@
> #include <linux/module.h>
> #include <linux/mutex.h>
> #include <linux/net.h>
>+#include <linux/proc_fs.h>
> #include <linux/poll.h>
> #include <linux/random.h>
> #include <linux/skbuff.h>
>@@ -111,9 +144,18 @@
> #include <linux/workqueue.h>
> #include <net/sock.h>
> #include <net/af_vsock.h>
>+#include <net/netns/vsock.h>
> #include <uapi/linux/vm_sockets.h>
> #include <uapi/asm-generic/ioctls.h>
>
>+#define VSOCK_NET_MODE_STR_GLOBAL "global"
>+#define VSOCK_NET_MODE_STR_LOCAL "local"
>+
>+/* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'.
>+ * The newline is added by proc_dostring() for read operations.
>+ */
>+#define VSOCK_NET_MODE_STR_MAX 8
>+
> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
> static void vsock_sk_destruct(struct sock *sk);
> static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
>@@ -235,33 +277,47 @@ static void __vsock_remove_connected(struct vsock_sock *vsk)
> sock_put(&vsk->sk);
> }
>
>-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
>+static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr,
>+ struct net *net,
>+ enum vsock_net_mode net_mode)
> {
> struct vsock_sock *vsk;
>
> list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
>- if (vsock_addr_equals_addr(addr, &vsk->local_addr))
>- return sk_vsock(vsk);
>+ struct sock *sk = sk_vsock(vsk);
>+
>+ if (vsock_addr_equals_addr(addr, &vsk->local_addr) &&
>+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
>+ net_mode))
>+ return sk;
>
> if (addr->svm_port == vsk->local_addr.svm_port &&
> (vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
>- addr->svm_cid == VMADDR_CID_ANY))
>- return sk_vsock(vsk);
>+ addr->svm_cid == VMADDR_CID_ANY) &&
>+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
>+ net_mode))
>+ return sk;
> }
>
> return NULL;
> }
>
>-static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
>- struct sockaddr_vm *dst)
>+static struct sock *
>+__vsock_find_connected_socket_net(struct sockaddr_vm *src,
>+ struct sockaddr_vm *dst, struct net *net,
>+ enum vsock_net_mode net_mode)
> {
> struct vsock_sock *vsk;
>
> list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
> connected_table) {
>+ struct sock *sk = sk_vsock(vsk);
>+
> if (vsock_addr_equals_addr(src, &vsk->remote_addr) &&
>- dst->svm_port == vsk->local_addr.svm_port) {
>- return sk_vsock(vsk);
>+ dst->svm_port == vsk->local_addr.svm_port &&
>+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net,
>+ net_mode)) {
>+ return sk;
> }
> }
>
>@@ -304,12 +360,14 @@ void vsock_remove_connected(struct vsock_sock *vsk)
> }
> EXPORT_SYMBOL_GPL(vsock_remove_connected);
>
>-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
>+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
>+ struct net *net,
>+ enum vsock_net_mode net_mode)
> {
> struct sock *sk;
>
> spin_lock_bh(&vsock_table_lock);
>- sk = __vsock_find_bound_socket(addr);
>+ sk = __vsock_find_bound_socket_net(addr, net, net_mode);
> if (sk)
> sock_hold(sk);
>
>@@ -317,15 +375,23 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
>
> return sk;
> }
>+EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net);
>+
>+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
>+{
>+ return vsock_find_bound_socket_net(addr, NULL, VSOCK_NET_MODE_GLOBAL);
>+}
> EXPORT_SYMBOL_GPL(vsock_find_bound_socket);
>
>-struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
>- struct sockaddr_vm *dst)
>+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
>+ struct sockaddr_vm *dst,
>+ struct net *net,
>+ enum vsock_net_mode net_mode)
> {
> struct sock *sk;
>
> spin_lock_bh(&vsock_table_lock);
>- sk = __vsock_find_connected_socket(src, dst);
>+ sk = __vsock_find_connected_socket_net(src, dst, net, net_mode);
> if (sk)
> sock_hold(sk);
>
>@@ -333,6 +399,14 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
>
> return sk;
> }
>+EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net);
>+
>+struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
>+ struct sockaddr_vm *dst)
>+{
>+ return vsock_find_connected_socket_net(src, dst,
>+ NULL, VSOCK_NET_MODE_GLOBAL);
>+}
> EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
>
> void vsock_remove_sock(struct vsock_sock *vsk)
>@@ -528,7 +602,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
>
> if (sk->sk_type == SOCK_SEQPACKET) {
> if (!new_transport->seqpacket_allow ||
>- !new_transport->seqpacket_allow(remote_cid)) {
>+ !new_transport->seqpacket_allow(vsk, remote_cid)) {
> module_put(new_transport->module);
> return -ESOCKTNOSUPPORT;
> }
>@@ -676,6 +750,7 @@ static void vsock_pending_work(struct work_struct *work)
> static int __vsock_bind_connectible(struct vsock_sock *vsk,
> struct sockaddr_vm *addr)
> {
>+ struct net *net = sock_net(sk_vsock(vsk));
> static u32 port;
> struct sockaddr_vm new_addr;
>
>@@ -695,7 +770,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
>
> new_addr.svm_port = port++;
>
>- if (!__vsock_find_bound_socket(&new_addr)) {
>+ if (!__vsock_find_bound_socket_net(&new_addr, net,
>+ vsk->net_mode)) {
> found = true;
> break;
> }
>@@ -712,7 +788,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
> return -EACCES;
> }
>
>- if (__vsock_find_bound_socket(&new_addr))
>+ if (__vsock_find_bound_socket_net(&new_addr, net,
>+ vsk->net_mode))
> return -EADDRINUSE;
> }
>
>@@ -836,6 +913,8 @@ static struct sock *__vsock_create(struct net *net,
> vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE;
> }
>
>+ vsk->net_mode = vsock_net_mode(net);
>+
> return sk;
> }
>
>@@ -2636,6 +2715,142 @@ static struct miscdevice vsock_device = {
> .fops = &vsock_device_ops,
> };
>
>+static int vsock_net_mode_string(const struct ctl_table *table, int write,
>+ void *buffer, size_t *lenp, loff_t *ppos)
>+{
>+ char data[VSOCK_NET_MODE_STR_MAX] = {0};
>+ enum vsock_net_mode mode;
>+ struct ctl_table tmp;
>+ struct net *net;
>+ int ret;
>+
>+ if (!table->data || !table->maxlen || !*lenp) {
>+ *lenp = 0;
>+ return 0;
>+ }
>+
>+ net = current->nsproxy->net_ns;
>+ tmp = *table;
>+ tmp.data = data;
>+
>+ if (!write) {
>+ const char *p;
>+
>+ mode = vsock_net_mode(net);
>+
>+ switch (mode) {
>+ case VSOCK_NET_MODE_GLOBAL:
>+ p = VSOCK_NET_MODE_STR_GLOBAL;
>+ break;
>+ case VSOCK_NET_MODE_LOCAL:
>+ p = VSOCK_NET_MODE_STR_LOCAL;
>+ break;
>+ default:
>+ WARN_ONCE(true, "netns has invalid vsock mode");
>+ *lenp = 0;
>+ return 0;
>+ }
>+
>+ strscpy(data, p, sizeof(data));
>+ tmp.maxlen = strlen(p);
>+ }
>+
>+ ret = proc_dostring(&tmp, write, buffer, lenp, ppos);
>+ if (ret)
>+ return ret;
>+
>+ if (!write)
>+ return 0;
>+
>+ if (*lenp >= sizeof(data))
>+ return -EINVAL;
>+
>+ if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
>+ mode = VSOCK_NET_MODE_GLOBAL;
>+ else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data)))
>+ mode = VSOCK_NET_MODE_LOCAL;
>+ else
>+ return -EINVAL;
>+
>+ if (!vsock_net_write_mode(net, mode))
>+ return -EPERM;
>+
>+ return 0;
>+}
>+
>+static struct ctl_table vsock_table[] = {
>+ {
>+ .procname = "ns_mode",
>+ .data = &init_net.vsock.mode,
>+ .maxlen = VSOCK_NET_MODE_STR_MAX,
>+ .mode = 0644,
>+ .proc_handler = vsock_net_mode_string
>+ },
>+};
>+
>+static int __net_init vsock_sysctl_register(struct net *net)
>+{
>+ struct ctl_table *table;
>+
>+ if (net_eq(net, &init_net)) {
>+ table = vsock_table;
>+ } else {
>+ table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL);
>+ if (!table)
>+ goto err_alloc;
>+
>+ table[0].data = &net->vsock.mode;
>+ }
>+
>+ net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table,
>+ ARRAY_SIZE(vsock_table));
>+ if (!net->vsock.sysctl_hdr)
>+ goto err_reg;
>+
>+ return 0;
>+
>+err_reg:
>+ if (!net_eq(net, &init_net))
>+ kfree(table);
>+err_alloc:
>+ return -ENOMEM;
>+}
>+
>+static void vsock_sysctl_unregister(struct net *net)
>+{
>+ const struct ctl_table *table;
>+
>+ table = net->vsock.sysctl_hdr->ctl_table_arg;
>+ unregister_net_sysctl_table(net->vsock.sysctl_hdr);
>+ if (!net_eq(net, &init_net))
>+ kfree(table);
>+}
>+
>+static void vsock_net_init(struct net *net)
>+{
>+ net->vsock.mode = VSOCK_NET_MODE_GLOBAL;
>+}
>+
>+static __net_init int vsock_sysctl_init_net(struct net *net)
>+{
>+ vsock_net_init(net);
>+
>+ if (vsock_sysctl_register(net))
>+ return -ENOMEM;
>+
>+ return 0;
>+}
>+
>+static __net_exit void vsock_sysctl_exit_net(struct net *net)
>+{
>+ vsock_sysctl_unregister(net);
>+}
>+
>+static struct pernet_operations vsock_sysctl_ops __net_initdata = {
>+ .init = vsock_sysctl_init_net,
>+ .exit = vsock_sysctl_exit_net,
>+};
>+
> static int __init vsock_init(void)
> {
> int err = 0;
>@@ -2663,10 +2878,18 @@ static int __init vsock_init(void)
> goto err_unregister_proto;
> }
>
>+ if (register_pernet_subsys(&vsock_sysctl_ops)) {
>+ err = -ENOMEM;
>+ goto err_unregister_sock;
>+ }
>+
>+ vsock_net_init(&init_net);
> vsock_bpf_build_proto();
>
> return 0;
>
>+err_unregister_sock:
>+ sock_unregister(AF_VSOCK);
> err_unregister_proto:
> proto_unregister(&vsock_proto);
> err_deregister_misc:
>@@ -2680,6 +2903,7 @@ static void __exit vsock_exit(void)
> misc_deregister(&vsock_device);
> sock_unregister(AF_VSOCK);
> proto_unregister(&vsock_proto);
>+ unregister_pernet_subsys(&vsock_sysctl_ops);
> }
>
> const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk)
>diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>index 8c867023a2e5..5d379ccf3770 100644
>--- a/net/vmw_vsock/virtio_transport.c
>+++ b/net/vmw_vsock/virtio_transport.c
>@@ -536,7 +536,8 @@ static bool virtio_transport_msgzerocopy_allow(void)
> return true;
> }
>
>-static bool virtio_transport_seqpacket_allow(u32 remote_cid);
>+static bool
>+virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
>
> static struct virtio_transport virtio_transport = {
> .transport = {
>@@ -593,7 +594,8 @@ static struct virtio_transport virtio_transport = {
> .can_msgzerocopy = virtio_transport_can_msgzerocopy,
> };
>
>-static bool virtio_transport_seqpacket_allow(u32 remote_cid)
>+static bool
>+virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
> {
> struct virtio_vsock *vsock;
> bool seqpacket_allow;
>diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
>index bc2ff918b315..8722337a4f80 100644
>--- a/net/vmw_vsock/vsock_loopback.c
>+++ b/net/vmw_vsock/vsock_loopback.c
>@@ -46,7 +46,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
> return 0;
> }
>
>-static bool vsock_loopback_seqpacket_allow(u32 remote_cid);
>+static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk,
>+ u32 remote_cid);
> static bool vsock_loopback_msgzerocopy_allow(void)
> {
> return true;
>@@ -106,7 +107,8 @@ static struct virtio_transport loopback_transport = {
> .send_pkt = vsock_loopback_send_pkt,
> };
>
>-static bool vsock_loopback_seqpacket_allow(u32 remote_cid)
>+static bool
>+vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
> {
> return true;
> }
>
>--
>2.47.3
>
^ permalink raw reply
* Re: [PATCH net-next v10 03/11] vsock: reject bad VSOCK_NET_MODE_LOCAL configuration for G2H
From: Stefano Garzarella @ 2025-11-18 18:10 UTC (permalink / raw)
To: Bobby Eshleman
Cc: David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin, Jason Wang,
Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan, linux-kernel,
virtualization, netdev, kvm, linux-hyperv, linux-kselftest,
Sargun Dhillon, berrange, Bobby Eshleman
In-Reply-To: <20251117-vsock-vmtest-v10-3-df08f165bf3e@meta.com>
On Mon, Nov 17, 2025 at 06:00:26PM -0800, Bobby Eshleman wrote:
>From: Bobby Eshleman <bobbyeshleman@meta.com>
>
>Reject setting VSOCK_NET_MODE_LOCAL with -EOPNOTSUPP if a G2H transport
>is operational. Additionally, reject G2H transport registration if there
>already exists a namespace in local mode.
>
>G2H sockets break in local mode because the G2H transports don't support
>namespacing yet. The current approach is to coerce packets coming out of
>G2H transports into VSOCK_NET_MODE_GLOBAL mode, but it is not possible
>to coerce sockets in the same way because it cannot be deduced which
>transport will be used by the socket. Specifically, when bound to
>VMADDR_CID_ANY in a nested VM (both G2H and H2G available), it is not
>until a packet is received and matched to the bound socket that we
>assign the transport. This presents a chicken-and-egg problem, because
>we need the namespace to lookup the socket and resolve the transport,
>but we need the transport to know how to use the namespace during
>lookup.
>
>For that reason, this patch prevents VSOCK_NET_MODE_LOCAL from being
>used on systems that support G2H, even nested systems that also have H2G
>transports.
>
>Local mode is blocked based on detecting the presence of G2H devices
>(when possible, as hyperv is special). This means that a host kernel
>with G2H support compiled in (or has the module loaded), will still
>support local mode if there is no G2H (e.g., virtio-vsock) device
>detected. This enables using the same kernel in the host and in the
>guest, as we do in kselftest.
>
>Systems with only namespace-aware transports (vhost-vsock, loopback) can
>still use both VSOCK_NET_MODE_GLOBAL and VSOCK_NET_MODE_LOCAL modes as
>intended.
>
>Add supports_local_mode() transport callback to indicate
>transport-specific local mode support.
>
>These restrictions can be lifted in a future patch series when G2H
>transports gain namespace support.
>
>Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
>---
>Changes in v10:
>- move this patch before any transports bring online namespacing (Stefano)
>- move vsock_net_mode_string into critical section (Stefano)
>- add ->supports_local_mode() callback to transports (Stefano)
>---
> drivers/vhost/vsock.c | 6 +++++
> include/net/af_vsock.h | 5 ++++
> net/vmw_vsock/af_vsock.c | 50 ++++++++++++++++++++++++++++++++++------
> net/vmw_vsock/hyperv_transport.c | 6 +++++
> net/vmw_vsock/virtio_transport.c | 13 +++++++++++
> net/vmw_vsock/vmci_transport.c | 7 ++++++
> net/vmw_vsock/vsock_loopback.c | 6 +++++
> 7 files changed, 86 insertions(+), 7 deletions(-)
>
>diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
>index 2c937a2df83b..c8319cd1c232 100644
>--- a/drivers/vhost/vsock.c
>+++ b/drivers/vhost/vsock.c
>@@ -64,6 +64,11 @@ static u32 vhost_transport_get_local_cid(void)
> return VHOST_VSOCK_DEFAULT_HOST_CID;
> }
>
>+static bool vhost_transport_supports_local_mode(void)
>+{
>+ return true;
Should we enable this later, when we really add support, or it doesn't
affect anything if vhost-vsock is not really supporting it in this PR
(thinking about bisection issues).
>+}
>+
> /* Callers that dereference the return value must hold vhost_vsock_mutex or the
> * RCU read lock.
> */
>@@ -412,6 +417,7 @@ static struct virtio_transport vhost_transport = {
> .module = THIS_MODULE,
>
> .get_local_cid = vhost_transport_get_local_cid,
>+ .supports_local_mode = vhost_transport_supports_local_mode,
>
> .init = virtio_transport_do_socket_init,
> .destruct = virtio_transport_destruct,
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index 59d97a143204..824d89657d41 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -180,6 +180,11 @@ struct vsock_transport {
> /* Addressing. */
> u32 (*get_local_cid)(void);
>
>+ /* Return true if this transport supports VSOCK_NET_MODE_LOCAL.
nit: Here I would make it clearer that rather than supporting
MODE_LOCAL, the transport is not compatible with it, etc.
A summary of the excellent description we have in the commit.
>+ * Otherwise, return false.
>+ */
>+ bool (*supports_local_mode)(void);
>+
> /* Read a single skb */
> int (*read_skb)(struct vsock_sock *, skb_read_actor_t);
>
>diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>index 54373ae101c3..7a235bb94437 100644
>--- a/net/vmw_vsock/af_vsock.c
>+++ b/net/vmw_vsock/af_vsock.c
>@@ -91,6 +91,12 @@
> * and locked down by a namespace manager. The default is "global". The mode
> * is set per-namespace.
> *
>+ * Note: LOCAL mode is only supported when using namespace-aware transports
>+ * (vhost-vsock, loopback). If a guest-to-host transport (virtio-vsock,
>+ * hyperv-vsock, vmci-vsock) is loaded, attempts to set LOCAL mode will fail
>+ * with EOPNOTSUPP, as these transports do not support per-namespace
>+ * isolation.
Okay, maybe this is fine, so if you don't need to resend, feel free to
ignore the previous comment.
>+ *
> * The modes affect the allocation and accessibility of CIDs as follows:
> *
> * - global - access and allocation are all system-wide
>@@ -2765,17 +2771,30 @@ static int vsock_net_mode_string(const struct ctl_table *table, int write,
> if (*lenp >= sizeof(data))
> return -EINVAL;
>
>- if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
>+ ret = 0;
IIUC `ret` should already be 0 at this point, no?
>+ mutex_lock(&vsock_register_mutex);
I honestly don't like to mix the parsing, with this new check, so what
about leaving the parsing as before this patch (also without the mutex),
then just (untested):
mutex_lock(&vsock_register_mutex);
if (mode == VSOCK_NET_MODE_LOCAL && transport_g2h &&
transport_g2h->supports_local_mode &&
!transport_g2h->supports_local_mode()) {
ret = -EOPNOTSUPP;
goto out;
}
if (!vsock_net_write_mode(net, mode)) {
ret = -EPERM;
}
out:
mutex_unlock(&vsock_register_mutex);
return ret;
}
>+ 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)))
>+ } else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data))) {
>+ if (transport_g2h && transport_g2h->supports_local_mode &&
>+ !transport_g2h->supports_local_mode()) {
>+ ret = -EOPNOTSUPP;
>+ goto out;
>+ }
> mode = VSOCK_NET_MODE_LOCAL;
>- else
>- return -EINVAL;
>+ } else {
>+ ret = -EINVAL;
>+ goto out;
>+ }
>
>- if (!vsock_net_write_mode(net, mode))
>- return -EPERM;
>+ if (!vsock_net_write_mode(net, mode)) {
>+ ret = -EPERM;
>+ goto out;
>+ }
>
>- return 0;
>+out:
>+ mutex_unlock(&vsock_register_mutex);
>+ return ret;
> }
>
> static struct ctl_table vsock_table[] = {
>@@ -2916,6 +2935,7 @@ int vsock_core_register(const struct vsock_transport *t, int features)
> {
> const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local;
> int err = mutex_lock_interruptible(&vsock_register_mutex);
>+ struct net *net;
>
> if (err)
> return err;
>@@ -2938,6 +2958,22 @@ int vsock_core_register(const struct vsock_transport *t, int features)
> err = -EBUSY;
> goto err_busy;
> }
>+
>+ /* G2H sockets break in LOCAL mode namespaces because G2H
>+ * transports don't support them yet. Block registering new G2H
>+ * transports if we already have local mode namespaces on the
>+ * system.
>+ */
>+ rcu_read_lock();
>+ for_each_net_rcu(net) {
>+ if (vsock_net_mode(net) == VSOCK_NET_MODE_LOCAL) {
>+ rcu_read_unlock();
>+ err = -EOPNOTSUPP;
>+ goto err_busy;
>+ }
>+ }
>+ rcu_read_unlock();
>+
> t_g2h = t;
> }
>
>diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>index 432fcbbd14d4..279f04fcd81a 100644
>--- a/net/vmw_vsock/hyperv_transport.c
>+++ b/net/vmw_vsock/hyperv_transport.c
>@@ -833,10 +833,16 @@ int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
> return -EOPNOTSUPP;
> }
>
>+static bool hvs_supports_local_mode(void)
>+{
>+ return false;
>+}
>+
> static struct vsock_transport hvs_transport = {
> .module = THIS_MODULE,
>
> .get_local_cid = hvs_get_local_cid,
>+ .supports_local_mode = hvs_supports_local_mode,
>
> .init = hvs_sock_init,
> .destruct = hvs_destruct,
>diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>index 5d379ccf3770..e585cb66c6f5 100644
>--- a/net/vmw_vsock/virtio_transport.c
>+++ b/net/vmw_vsock/virtio_transport.c
>@@ -94,6 +94,18 @@ static u32 virtio_transport_get_local_cid(void)
> return ret;
> }
>
>+static bool virtio_transport_supports_local_mode(void)
>+{
>+ struct virtio_vsock *vsock;
>+
>+ rcu_read_lock();
>+ vsock = rcu_dereference(the_virtio_vsock);
>+ rcu_read_unlock();
>+
>+ /* Local mode is supported only when no G2H device is present. */
>+ return vsock ? false : true;
>+}
>+
> /* Caller need to hold vsock->tx_lock on vq */
> static int virtio_transport_send_skb(struct sk_buff *skb, struct virtqueue *vq,
> struct virtio_vsock *vsock, gfp_t gfp)
>@@ -544,6 +556,7 @@ static struct virtio_transport virtio_transport = {
> .module = THIS_MODULE,
>
> .get_local_cid = virtio_transport_get_local_cid,
>+ .supports_local_mode = virtio_transport_supports_local_mode,
>
> .init = virtio_transport_do_socket_init,
> .destruct = virtio_transport_destruct,
>diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
>index 7eccd6708d66..da7c52ad7b2a 100644
>--- a/net/vmw_vsock/vmci_transport.c
>+++ b/net/vmw_vsock/vmci_transport.c
>@@ -2033,6 +2033,12 @@ static u32 vmci_transport_get_local_cid(void)
> return vmci_get_context_id();
> }
>
>+static bool vmci_transport_supports_local_mode(void)
>+{
>+ /* Local mode is supported only when no device is present. */
>+ return vmci_transport_get_local_cid() == VMCI_INVALID_ID;
IIRC vmci can be registered both as H2G and G2H, so should we filter out
the H2G case?
Also, IMO is better to use VMADDR_CID_ANY with get_local_cid().
>+}
>+
> static struct vsock_transport vmci_transport = {
> .module = THIS_MODULE,
> .init = vmci_transport_socket_init,
>@@ -2062,6 +2068,7 @@ static struct vsock_transport vmci_transport = {
> .notify_send_post_enqueue = vmci_transport_notify_send_post_enqueue,
> .shutdown = vmci_transport_shutdown,
> .get_local_cid = vmci_transport_get_local_cid,
>+ .supports_local_mode = vmci_transport_supports_local_mode,
> };
>
> static bool vmci_check_transport(struct vsock_sock *vsk)
>diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
>index 8722337a4f80..1e25c1a6b43f 100644
>--- a/net/vmw_vsock/vsock_loopback.c
>+++ b/net/vmw_vsock/vsock_loopback.c
>@@ -26,6 +26,11 @@ static u32 vsock_loopback_get_local_cid(void)
> return VMADDR_CID_LOCAL;
> }
>
>+static bool vsock_loopback_supports_local_mode(void)
>+{
>+ return true;
>+}
>+
> static int vsock_loopback_send_pkt(struct sk_buff *skb)
> {
> struct vsock_loopback *vsock = &the_vsock_loopback;
>@@ -58,6 +63,7 @@ static struct virtio_transport loopback_transport = {
> .module = THIS_MODULE,
>
> .get_local_cid = vsock_loopback_get_local_cid,
>+ .supports_local_mode = vsock_loopback_supports_local_mode,
>
> .init = virtio_transport_do_socket_init,
> .destruct = virtio_transport_destruct,
>
>--
>2.47.3
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox