qemu/hw/virtio/virtio-bus.c

372 lines
10 KiB
C
Raw Normal View History

/*
* VirtioBus
*
* Copyright (C) 2012 : GreenSocs Ltd
* http://www.greensocs.com/ , email: info@greensocs.com
*
* Developed by :
* Frederic Konrad <fred.konrad@greensocs.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, see <http://www.gnu.org/licenses/>.
*
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
#include "qapi/error.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio.h"
#include "exec/address-spaces.h"
/* #define DEBUG_VIRTIO_BUS */
#ifdef DEBUG_VIRTIO_BUS
#define DPRINTF(fmt, ...) \
do { printf("virtio_bus: " fmt , ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) do { } while (0)
#endif
/* A VirtIODevice is being plugged */
void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
{
DeviceState *qdev = DEVICE(vdev);
BusState *qbus = BUS(qdev_get_parent_bus(qdev));
VirtioBusState *bus = VIRTIO_BUS(qbus);
VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
bool has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
virtio: fix the condition for iommu_platform not supported The commit 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") claims to fail the device hotplug when iommu_platform is requested, but not supported by the (vhost) device. On the first glance the condition for detecting that situation looks perfect, but because a certain peculiarity of virtio_platform it ain't. In fact the aforementioned commit introduces a regression. It breaks virtio-fs support for Secure Execution, and most likely also for AMD SEV or any other confidential guest scenario that relies encrypted guest memory. The same also applies to any other vhost device that does not support _F_ACCESS_PLATFORM. The peculiarity is that iommu_platform and _F_ACCESS_PLATFORM collates "device can not access all of the guest RAM" and "iova != gpa, thus device needs to translate iova". Confidential guest technologies currently rely on the device/hypervisor offering _F_ACCESS_PLATFORM, so that, after the feature has been negotiated, the guest grants access to the portions of memory the device needs to see. So in for confidential guests, generally, _F_ACCESS_PLATFORM is about the restricted access to memory, but not about the addresses used being something else than guest physical addresses. This is the very reason for which commit f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM") fences _F_ACCESS_PLATFORM from the vhost device that does not need it, because on the vhost interface it only means "I/O address translation is needed". This patch takes inspiration from f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM"), and uses the same condition for detecting the situation when _F_ACCESS_PLATFORM is requested, but no I/O translation by the device, and thus no device capability is needed. In this situation claiming that the device does not support iommu_plattform=on is counter-productive. So let us stop doing that! Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Reported-by: Jakob Naucke <Jakob.Naucke@ibm.com> Fixes: 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") Acked-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com> Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: qemu-stable@nongnu.org Message-Id: <20220207112857.607829-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com>
2022-02-07 14:28:57 +03:00
bool vdev_has_iommu;
Error *local_err = NULL;
DPRINTF("%s: plug device.\n", qbus->name);
if (klass->pre_plugged != NULL) {
klass->pre_plugged(qbus->parent, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
/* Get the features of the plugged device. */
assert(vdc->get_features != NULL);
vdev->host_features = vdc->get_features(vdev, vdev->host_features,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
if (klass->device_plugged != NULL) {
klass->device_plugged(qbus->parent, &local_err);
}
if (local_err) {
error_propagate(errp, local_err);
return;
}
virtio: fix feature negotiation for ACCESS_PLATFORM Unlike most virtio features ACCESS_PLATFORM is considered mandatory by QEMU, i.e. the driver must accept it if offered by the device. The virtio specification says that the driver SHOULD accept the ACCESS_PLATFORM feature if offered, and that the device MAY fail to operate if ACCESS_PLATFORM was offered but not negotiated. While a SHOULD ain't exactly a MUST, we are certainly allowed to fail the device when the driver fences ACCESS_PLATFORM. With commit 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") we already made the decision to do so whenever the get_dma_as() callback is implemented (by the bus), which in practice means for the entirety of virtio-pci. That means, if the device needs to translate I/O addresses, then ACCESS_PLATFORM is mandatory. The aforementioned commit tells us in the commit message that this is for security reasons. More precisely if we were to allow a less then trusted driver (e.g. an user-space driver, or a nested guest) to make the device bypass the IOMMU by not negotiating ACCESS_PLATFORM, then the guest kernel would have no ability to control/police (by programming the IOMMU) what pieces of guest memory the driver may manipulate using the device. Which would break security assumptions within the guest. If ACCESS_PLATFORM is offered not because we want the device to utilize an IOMMU and do address translation, but because the device does not have access to the entire guest RAM, and needs the driver to grant access to the bits it needs access to (e.g. confidential guest support), we still require the guest to have the corresponding logic and to accept ACCESS_PLATFORM. If the driver does not accept ACCESS_PLATFORM, then things are bound to go wrong, and we may see failures much less graceful than failing the device because the driver didn't negotiate ACCESS_PLATFORM. So let us make ACCESS_PLATFORM mandatory for the driver regardless of whether the get_dma_as() callback is implemented or not. Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Fixes: 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") Message-Id: <20220307112939.2780117-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com>
2022-03-07 14:29:39 +03:00
vdev->dma_as = &address_space_memory;
if (has_iommu) {
vdev_has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
/*
* Present IOMMU_PLATFORM to the driver iff iommu_plattform=on and
* device operational. If the driver does not accept IOMMU_PLATFORM
* we fail the device.
*/
virtio_add_feature(&vdev->host_features, VIRTIO_F_IOMMU_PLATFORM);
virtio: fix feature negotiation for ACCESS_PLATFORM Unlike most virtio features ACCESS_PLATFORM is considered mandatory by QEMU, i.e. the driver must accept it if offered by the device. The virtio specification says that the driver SHOULD accept the ACCESS_PLATFORM feature if offered, and that the device MAY fail to operate if ACCESS_PLATFORM was offered but not negotiated. While a SHOULD ain't exactly a MUST, we are certainly allowed to fail the device when the driver fences ACCESS_PLATFORM. With commit 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") we already made the decision to do so whenever the get_dma_as() callback is implemented (by the bus), which in practice means for the entirety of virtio-pci. That means, if the device needs to translate I/O addresses, then ACCESS_PLATFORM is mandatory. The aforementioned commit tells us in the commit message that this is for security reasons. More precisely if we were to allow a less then trusted driver (e.g. an user-space driver, or a nested guest) to make the device bypass the IOMMU by not negotiating ACCESS_PLATFORM, then the guest kernel would have no ability to control/police (by programming the IOMMU) what pieces of guest memory the driver may manipulate using the device. Which would break security assumptions within the guest. If ACCESS_PLATFORM is offered not because we want the device to utilize an IOMMU and do address translation, but because the device does not have access to the entire guest RAM, and needs the driver to grant access to the bits it needs access to (e.g. confidential guest support), we still require the guest to have the corresponding logic and to accept ACCESS_PLATFORM. If the driver does not accept ACCESS_PLATFORM, then things are bound to go wrong, and we may see failures much less graceful than failing the device because the driver didn't negotiate ACCESS_PLATFORM. So let us make ACCESS_PLATFORM mandatory for the driver regardless of whether the get_dma_as() callback is implemented or not. Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Fixes: 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") Message-Id: <20220307112939.2780117-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com>
2022-03-07 14:29:39 +03:00
if (klass->get_dma_as) {
vdev->dma_as = klass->get_dma_as(qbus->parent);
if (!vdev_has_iommu && vdev->dma_as != &address_space_memory) {
error_setg(errp,
virtio: fix the condition for iommu_platform not supported The commit 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") claims to fail the device hotplug when iommu_platform is requested, but not supported by the (vhost) device. On the first glance the condition for detecting that situation looks perfect, but because a certain peculiarity of virtio_platform it ain't. In fact the aforementioned commit introduces a regression. It breaks virtio-fs support for Secure Execution, and most likely also for AMD SEV or any other confidential guest scenario that relies encrypted guest memory. The same also applies to any other vhost device that does not support _F_ACCESS_PLATFORM. The peculiarity is that iommu_platform and _F_ACCESS_PLATFORM collates "device can not access all of the guest RAM" and "iova != gpa, thus device needs to translate iova". Confidential guest technologies currently rely on the device/hypervisor offering _F_ACCESS_PLATFORM, so that, after the feature has been negotiated, the guest grants access to the portions of memory the device needs to see. So in for confidential guests, generally, _F_ACCESS_PLATFORM is about the restricted access to memory, but not about the addresses used being something else than guest physical addresses. This is the very reason for which commit f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM") fences _F_ACCESS_PLATFORM from the vhost device that does not need it, because on the vhost interface it only means "I/O address translation is needed". This patch takes inspiration from f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM"), and uses the same condition for detecting the situation when _F_ACCESS_PLATFORM is requested, but no I/O translation by the device, and thus no device capability is needed. In this situation claiming that the device does not support iommu_plattform=on is counter-productive. So let us stop doing that! Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Reported-by: Jakob Naucke <Jakob.Naucke@ibm.com> Fixes: 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") Acked-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com> Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: qemu-stable@nongnu.org Message-Id: <20220207112857.607829-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com>
2022-02-07 14:28:57 +03:00
"iommu_platform=true is not supported by the device");
virtio: fix feature negotiation for ACCESS_PLATFORM Unlike most virtio features ACCESS_PLATFORM is considered mandatory by QEMU, i.e. the driver must accept it if offered by the device. The virtio specification says that the driver SHOULD accept the ACCESS_PLATFORM feature if offered, and that the device MAY fail to operate if ACCESS_PLATFORM was offered but not negotiated. While a SHOULD ain't exactly a MUST, we are certainly allowed to fail the device when the driver fences ACCESS_PLATFORM. With commit 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") we already made the decision to do so whenever the get_dma_as() callback is implemented (by the bus), which in practice means for the entirety of virtio-pci. That means, if the device needs to translate I/O addresses, then ACCESS_PLATFORM is mandatory. The aforementioned commit tells us in the commit message that this is for security reasons. More precisely if we were to allow a less then trusted driver (e.g. an user-space driver, or a nested guest) to make the device bypass the IOMMU by not negotiating ACCESS_PLATFORM, then the guest kernel would have no ability to control/police (by programming the IOMMU) what pieces of guest memory the driver may manipulate using the device. Which would break security assumptions within the guest. If ACCESS_PLATFORM is offered not because we want the device to utilize an IOMMU and do address translation, but because the device does not have access to the entire guest RAM, and needs the driver to grant access to the bits it needs access to (e.g. confidential guest support), we still require the guest to have the corresponding logic and to accept ACCESS_PLATFORM. If the driver does not accept ACCESS_PLATFORM, then things are bound to go wrong, and we may see failures much less graceful than failing the device because the driver didn't negotiate ACCESS_PLATFORM. So let us make ACCESS_PLATFORM mandatory for the driver regardless of whether the get_dma_as() callback is implemented or not. Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Fixes: 2943b53f68 ("virtio: force VIRTIO_F_IOMMU_PLATFORM") Message-Id: <20220307112939.2780117-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com>
2022-03-07 14:29:39 +03:00
return;
}
virtio: fix the condition for iommu_platform not supported The commit 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") claims to fail the device hotplug when iommu_platform is requested, but not supported by the (vhost) device. On the first glance the condition for detecting that situation looks perfect, but because a certain peculiarity of virtio_platform it ain't. In fact the aforementioned commit introduces a regression. It breaks virtio-fs support for Secure Execution, and most likely also for AMD SEV or any other confidential guest scenario that relies encrypted guest memory. The same also applies to any other vhost device that does not support _F_ACCESS_PLATFORM. The peculiarity is that iommu_platform and _F_ACCESS_PLATFORM collates "device can not access all of the guest RAM" and "iova != gpa, thus device needs to translate iova". Confidential guest technologies currently rely on the device/hypervisor offering _F_ACCESS_PLATFORM, so that, after the feature has been negotiated, the guest grants access to the portions of memory the device needs to see. So in for confidential guests, generally, _F_ACCESS_PLATFORM is about the restricted access to memory, but not about the addresses used being something else than guest physical addresses. This is the very reason for which commit f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM") fences _F_ACCESS_PLATFORM from the vhost device that does not need it, because on the vhost interface it only means "I/O address translation is needed". This patch takes inspiration from f7ef7e6e3b ("vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM"), and uses the same condition for detecting the situation when _F_ACCESS_PLATFORM is requested, but no I/O translation by the device, and thus no device capability is needed. In this situation claiming that the device does not support iommu_plattform=on is counter-productive. So let us stop doing that! Signed-off-by: Halil Pasic <pasic@linux.ibm.com> Reported-by: Jakob Naucke <Jakob.Naucke@ibm.com> Fixes: 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but unsupported") Acked-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com> Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: qemu-stable@nongnu.org Message-Id: <20220207112857.607829-1-pasic@linux.ibm.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com>
2022-02-07 14:28:57 +03:00
}
}
}
/* Reset the virtio_bus */
void virtio_bus_reset(VirtioBusState *bus)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
DPRINTF("%s: reset device.\n", BUS(bus)->name);
if (vdev != NULL) {
virtio_reset(vdev);
}
}
/* A VirtIODevice is being unplugged */
void virtio_bus_device_unplugged(VirtIODevice *vdev)
{
DeviceState *qdev = DEVICE(vdev);
BusState *qbus = BUS(qdev_get_parent_bus(qdev));
VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(qbus);
DPRINTF("%s: remove device.\n", qbus->name);
if (vdev != NULL) {
if (klass->device_unplugged != NULL) {
klass->device_unplugged(qbus->parent);
}
}
}
/* Get the device id of the plugged device. */
uint16_t virtio_bus_get_vdev_id(VirtioBusState *bus)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
assert(vdev != NULL);
return vdev->device_id;
}
/* Get the config_len field of the plugged device. */
size_t virtio_bus_get_vdev_config_len(VirtioBusState *bus)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
assert(vdev != NULL);
return vdev->config_len;
}
/* Get bad features of the plugged device. */
uint32_t virtio_bus_get_vdev_bad_features(VirtioBusState *bus)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioDeviceClass *k;
assert(vdev != NULL);
k = VIRTIO_DEVICE_GET_CLASS(vdev);
if (k->bad_features != NULL) {
return k->bad_features(vdev);
} else {
return 0;
}
}
/* Get config of the plugged device. */
void virtio_bus_get_vdev_config(VirtioBusState *bus, uint8_t *config)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioDeviceClass *k;
assert(vdev != NULL);
k = VIRTIO_DEVICE_GET_CLASS(vdev);
if (k->get_config != NULL) {
k->get_config(vdev, config);
}
}
/* Set config of the plugged device. */
void virtio_bus_set_vdev_config(VirtioBusState *bus, uint8_t *config)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioDeviceClass *k;
assert(vdev != NULL);
k = VIRTIO_DEVICE_GET_CLASS(vdev);
if (k->set_config != NULL) {
k->set_config(vdev, config);
}
}
virtio: introduce grab/release_ioeventfd to fix vhost Following the recent refactoring of virtio notifiers [1], more specifically the patch ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") that uses virtio_bus_set_host_notifier [2] by default, core virtio code requires 'ioeventfd_started' to be set to true/false when the host notifiers are configured. When vhost is stopped and started, however, there is a stop followed by another start. Since ioeventfd_started was never set to true, the 'stop' operation triggered by virtio_bus_set_host_notifier() will not result in a call to virtio_pci_ioeventfd_assign(assign=false). This leaves the memory regions with stale notifiers and results on the next start triggering the following assertion: kvm_mem_ioeventfd_add: error adding ioeventfd: File exists Aborted This patch reintroduces (hopefully in a cleaner way) the concept that was present with ioeventfd_disabled before the refactoring. When ioeventfd_grabbed>0, ioeventfd_started tracks whether ioeventfd should be enabled or not, but ioeventfd is actually not started at all until vhost releases the host notifiers. [1] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07748.html [2] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07760.html Reported-by: Felipe Franciosi <felipe@nutanix.com> Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Reported-by: Alex Williamson <alex.williamson@redhat.com> Fixes: ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Tested-by: Farhan Ali <alifm@linux.vnet.ibm.com> Tested-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2016-11-18 18:07:00 +03:00
/* On success, ioeventfd ownership belongs to the caller. */
int virtio_bus_grab_ioeventfd(VirtioBusState *bus)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
/* vhost can be used even if ioeventfd=off in the proxy device,
* so do not check k->ioeventfd_enabled.
*/
if (!k->ioeventfd_assign) {
return -ENOSYS;
}
if (bus->ioeventfd_grabbed == 0 && bus->ioeventfd_started) {
virtio_bus_stop_ioeventfd(bus);
/* Remember that we need to restart ioeventfd
* when ioeventfd_grabbed becomes zero.
*/
bus->ioeventfd_started = true;
}
bus->ioeventfd_grabbed++;
return 0;
}
void virtio_bus_release_ioeventfd(VirtioBusState *bus)
{
assert(bus->ioeventfd_grabbed != 0);
if (--bus->ioeventfd_grabbed == 0 && bus->ioeventfd_started) {
/* Force virtio_bus_start_ioeventfd to act. */
bus->ioeventfd_started = false;
virtio_bus_start_ioeventfd(bus);
}
}
int virtio_bus_start_ioeventfd(VirtioBusState *bus)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
int r;
if (!k->ioeventfd_assign || !k->ioeventfd_enabled(proxy)) {
return -ENOSYS;
}
if (bus->ioeventfd_started) {
return 0;
}
virtio: introduce grab/release_ioeventfd to fix vhost Following the recent refactoring of virtio notifiers [1], more specifically the patch ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") that uses virtio_bus_set_host_notifier [2] by default, core virtio code requires 'ioeventfd_started' to be set to true/false when the host notifiers are configured. When vhost is stopped and started, however, there is a stop followed by another start. Since ioeventfd_started was never set to true, the 'stop' operation triggered by virtio_bus_set_host_notifier() will not result in a call to virtio_pci_ioeventfd_assign(assign=false). This leaves the memory regions with stale notifiers and results on the next start triggering the following assertion: kvm_mem_ioeventfd_add: error adding ioeventfd: File exists Aborted This patch reintroduces (hopefully in a cleaner way) the concept that was present with ioeventfd_disabled before the refactoring. When ioeventfd_grabbed>0, ioeventfd_started tracks whether ioeventfd should be enabled or not, but ioeventfd is actually not started at all until vhost releases the host notifiers. [1] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07748.html [2] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07760.html Reported-by: Felipe Franciosi <felipe@nutanix.com> Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Reported-by: Alex Williamson <alex.williamson@redhat.com> Fixes: ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Tested-by: Farhan Ali <alifm@linux.vnet.ibm.com> Tested-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2016-11-18 18:07:00 +03:00
/* Only set our notifier if we have ownership. */
if (!bus->ioeventfd_grabbed) {
r = vdc->start_ioeventfd(vdev);
if (r < 0) {
error_report("%s: failed. Fallback to userspace (slower).", __func__);
return r;
}
}
bus->ioeventfd_started = true;
return 0;
}
void virtio_bus_stop_ioeventfd(VirtioBusState *bus)
{
VirtIODevice *vdev;
VirtioDeviceClass *vdc;
if (!bus->ioeventfd_started) {
return;
}
virtio: introduce grab/release_ioeventfd to fix vhost Following the recent refactoring of virtio notifiers [1], more specifically the patch ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") that uses virtio_bus_set_host_notifier [2] by default, core virtio code requires 'ioeventfd_started' to be set to true/false when the host notifiers are configured. When vhost is stopped and started, however, there is a stop followed by another start. Since ioeventfd_started was never set to true, the 'stop' operation triggered by virtio_bus_set_host_notifier() will not result in a call to virtio_pci_ioeventfd_assign(assign=false). This leaves the memory regions with stale notifiers and results on the next start triggering the following assertion: kvm_mem_ioeventfd_add: error adding ioeventfd: File exists Aborted This patch reintroduces (hopefully in a cleaner way) the concept that was present with ioeventfd_disabled before the refactoring. When ioeventfd_grabbed>0, ioeventfd_started tracks whether ioeventfd should be enabled or not, but ioeventfd is actually not started at all until vhost releases the host notifiers. [1] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07748.html [2] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07760.html Reported-by: Felipe Franciosi <felipe@nutanix.com> Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Reported-by: Alex Williamson <alex.williamson@redhat.com> Fixes: ed08a2a0b ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd") Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Tested-by: Farhan Ali <alifm@linux.vnet.ibm.com> Tested-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2016-11-18 18:07:00 +03:00
/* Only remove our notifier if we have ownership. */
if (!bus->ioeventfd_grabbed) {
vdev = virtio_bus_get_device(bus);
vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
vdc->stop_ioeventfd(vdev);
}
bus->ioeventfd_started = false;
}
bool virtio_bus_ioeventfd_enabled(VirtioBusState *bus)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
return k->ioeventfd_assign && k->ioeventfd_enabled(proxy);
}
/*
* This function switches ioeventfd on/off in the device.
* The caller must set or clear the handlers for the EventNotifier.
*/
int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
int r = 0;
if (!k->ioeventfd_assign) {
return -ENOSYS;
}
if (assign) {
r = event_notifier_init(notifier, 1);
if (r < 0) {
error_report("%s: unable to init event notifier: %s (%d)",
__func__, strerror(-r), r);
return r;
}
r = k->ioeventfd_assign(proxy, notifier, n, true);
if (r < 0) {
error_report("%s: unable to assign ioeventfd: %d", __func__, r);
virtio_bus_cleanup_host_notifier(bus, n);
}
} else {
k->ioeventfd_assign(proxy, notifier, n, false);
}
virtio: notify virtqueue via host notifier when available Host notifiers are used in several cases: 1. Traditional ioeventfd where virtqueue notifications are handled in the main loop thread. 2. IOThreads (aio_handle_output) where virtqueue notifications are handled in an IOThread AioContext. 3. vhost where virtqueue notifications are handled by kernel vhost or a vhost-user device backend. Most virtqueue notifications from the guest use the ioeventfd mechanism, but there are corner cases where QEMU code calls virtio_queue_notify(). This currently honors the host notifier for the IOThreads aio_handle_output case, but not for the vhost case. The result is that vhost does not receive virtqueue notifications from QEMU when virtio_queue_notify() is called. This patch extends virtio_queue_notify() to set the host notifier whenever it is enabled instead of calling the vq->(aio_)handle_output() function directly. We track the host notifier state for each virtqueue separately since some devices may use it only for certain virtqueues. This fixes the vhost case although it does add a trip through the eventfd for the traditional ioeventfd case. I don't think it's worth adding a fast path for the traditional ioeventfd case because calling virtio_queue_notify() is rare when ioeventfd is enabled. Reported-by: Felipe Franciosi <felipe@nutanix.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20191105140946.165584-1-stefanha@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2019-11-05 17:09:46 +03:00
if (r == 0) {
virtio_queue_set_host_notifier_enabled(vq, assign);
}
return r;
}
void virtio_bus_cleanup_host_notifier(VirtioBusState *bus, int n)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
/* Test and clear notifier after disabling event,
* in case poll callback didn't have time to run.
*/
virtio_queue_host_notifier_read(notifier);
event_notifier_cleanup(notifier);
}
static char *virtio_bus_get_dev_path(DeviceState *dev)
{
BusState *bus = qdev_get_parent_bus(dev);
DeviceState *proxy = DEVICE(bus->parent);
return qdev_get_dev_path(proxy);
}
static char *virtio_bus_get_fw_dev_path(DeviceState *dev)
{
return NULL;
}
bool virtio_bus_device_iommu_enabled(VirtIODevice *vdev)
{
DeviceState *qdev = DEVICE(vdev);
BusState *qbus = BUS(qdev_get_parent_bus(qdev));
VirtioBusState *bus = VIRTIO_BUS(qbus);
VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
if (!klass->iommu_enabled) {
return false;
}
return klass->iommu_enabled(qbus->parent);
}
static void virtio_bus_class_init(ObjectClass *klass, void *data)
{
BusClass *bus_class = BUS_CLASS(klass);
bus_class->get_dev_path = virtio_bus_get_dev_path;
bus_class->get_fw_dev_path = virtio_bus_get_fw_dev_path;
}
static const TypeInfo virtio_bus_info = {
.name = TYPE_VIRTIO_BUS,
.parent = TYPE_BUS,
.instance_size = sizeof(VirtioBusState),
.abstract = true,
.class_size = sizeof(VirtioBusClass),
.class_init = virtio_bus_class_init
};
static void virtio_register_types(void)
{
type_register_static(&virtio_bus_info);
}
type_init(virtio_register_types)