From: Daan De Meyer <daan.j.demeyer@gmail.com>
This allows passing the KVM device node to use as a file
descriptor via /dev/fdset/XX. Passing the device node to
use as a file descriptor allows running qemu unprivileged
even when the user running qemu is not in the kvm group
on distributions where access to /dev/kvm is gated behind
membership of the kvm group (as long as the process invoking
qemu is able to open /dev/kvm and passes the file descriptor
to qemu).
Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Message-ID: <20231021134015.1119597-1-daan.j.demeyer@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
include/sysemu/kvm_int.h | 1 +
accel/kvm/kvm-all.c | 25 ++++++++++++++++++++++++-
qemu-options.hx | 8 +++++++-
3 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index fd846394be1..882e37e12c5 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -120,6 +120,7 @@ struct KVMState
uint32_t xen_caps;
uint16_t xen_gnttab_max_frames;
uint16_t xen_evtchn_max_pirq;
+ char *device;
};
void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index bbc60146d15..49e755ec4ad 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2349,7 +2349,7 @@ static int kvm_init(MachineState *ms)
QTAILQ_INIT(&s->kvm_sw_breakpoints);
#endif
QLIST_INIT(&s->kvm_parked_vcpus);
- s->fd = qemu_open_old("/dev/kvm", O_RDWR);
+ s->fd = qemu_open_old(s->device ?: "/dev/kvm", O_RDWR);
if (s->fd == -1) {
fprintf(stderr, "Could not access KVM kernel module: %m\n");
ret = -errno;
@@ -3585,6 +3585,24 @@ static void kvm_set_dirty_ring_size(Object *obj, Visitor *v,
s->kvm_dirty_ring_size = value;
}
+static char *kvm_get_device(Object *obj,
+ Error **errp G_GNUC_UNUSED)
+{
+ KVMState *s = KVM_STATE(obj);
+
+ return g_strdup(s->device);
+}
+
+static void kvm_set_device(Object *obj,
+ const char *value,
+ Error **errp G_GNUC_UNUSED)
+{
+ KVMState *s = KVM_STATE(obj);
+
+ g_free(s->device);
+ s->device = g_strdup(value);
+}
+
static void kvm_accel_instance_init(Object *obj)
{
KVMState *s = KVM_STATE(obj);
@@ -3603,6 +3621,7 @@ static void kvm_accel_instance_init(Object *obj)
s->xen_version = 0;
s->xen_gnttab_max_frames = 64;
s->xen_evtchn_max_pirq = 256;
+ s->device = NULL;
}
/**
@@ -3643,6 +3662,10 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data)
object_class_property_set_description(oc, "dirty-ring-size",
"Size of KVM dirty page ring buffer (default: 0, i.e. use bitmap)");
+ object_class_property_add_str(oc, "device", kvm_get_device, kvm_set_device);
+ object_class_property_set_description(oc, "device",
+ "Path to the device node to use (default: /dev/kvm)");
+
kvm_arch_accel_class_init(oc);
}
diff --git a/qemu-options.hx b/qemu-options.hx
index b66570ae006..2ae51005c12 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -188,7 +188,8 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel,
" dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n"
" eager-split-size=n (KVM Eager Page Split chunk size, default 0, disabled. ARM only)\n"
" notify-vmexit=run|internal-error|disable,notify-window=n (enable notify VM exit and set notify window, x86 only)\n"
- " thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL)
+ " thread=single|multi (enable multi-threaded TCG)\n"
+ " device=path (KVM device path, default /dev/kvm)\n", QEMU_ARCH_ALL)
SRST
``-accel name[,prop=value[,...]]``
This is used to enable an accelerator. Depending on the target
@@ -269,6 +270,11 @@ SRST
open up for a specified of time (i.e. notify-window).
Default: notify-vmexit=run,notify-window=0.
+ ``device=path``
+ Sets the path to the KVM device node. Defaults to ``/dev/kvm``. This
+ option can be used to pass the KVM device to use via a file descriptor
+ by setting the value to ``/dev/fdset/NN``.
+
ERST
DEF("smp", HAS_ARG, QEMU_OPTION_smp,
--
2.43.0