* [PULL 01/28] vfio/container: ram discard disable helper
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 02/28] vfio/container: reform vfio_container_connect cleanup Cédric Le Goater
` (27 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, Steve Sistare, Cedric Le Goater
From: Steve Sistare <steven.sistare@oracle.com>
Define a helper to set ram discard disable, generate error messages,
and cleanup on failure. The second vfio_ram_block_discard_disable
call site now performs VFIO_GROUP_UNSET_CONTAINER immediately on failure,
instead of relying on the close of the container fd to do so in the kernel,
but this is equivalent.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cedric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1746195760-101443-2-git-send-email-steven.sistare@oracle.com
[ clg: vfio_attach_discard_disable() -> vfio_container_attach_discard_disable() ]
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/container.c | 48 +++++++++++++++++++++++++--------------------
1 file changed, 27 insertions(+), 21 deletions(-)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 77ff56b43f0a906167a3c7c8d8ae6376552762f7..2ea137fb024fedd2b8d578f2fb5a7eea2b11e4fa 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -511,16 +511,10 @@ static bool vfio_legacy_setup(VFIOContainerBase *bcontainer, Error **errp)
return true;
}
-static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
- Error **errp)
+static bool vfio_container_attach_discard_disable(VFIOContainer *container,
+ VFIOGroup *group, Error **errp)
{
- VFIOContainer *container;
- VFIOContainerBase *bcontainer;
- int ret, fd;
- VFIOAddressSpace *space;
- VFIOIOMMUClass *vioc;
-
- space = vfio_address_space_get(as);
+ int ret;
/*
* VFIO is currently incompatible with discarding of RAM insofar as the
@@ -553,18 +547,32 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
* details once we know which type of IOMMU we are using.
*/
+ ret = vfio_ram_block_discard_disable(container, true);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
+ if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) {
+ error_report("vfio: error disconnecting group %d from"
+ " container", group->groupid);
+ }
+ }
+ return !ret;
+}
+
+static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
+ Error **errp)
+{
+ VFIOContainer *container;
+ VFIOContainerBase *bcontainer;
+ int ret, fd;
+ VFIOAddressSpace *space;
+ VFIOIOMMUClass *vioc;
+
+ space = vfio_address_space_get(as);
+
QLIST_FOREACH(bcontainer, &space->containers, next) {
container = container_of(bcontainer, VFIOContainer, bcontainer);
if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
- ret = vfio_ram_block_discard_disable(container, true);
- if (ret) {
- error_setg_errno(errp, -ret,
- "Cannot set discarding of RAM broken");
- if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER,
- &container->fd)) {
- error_report("vfio: error disconnecting group %d from"
- " container", group->groupid);
- }
+ if (!vfio_container_attach_discard_disable(container, group, errp)) {
return false;
}
group->container = container;
@@ -596,9 +604,7 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
goto free_container_exit;
}
- ret = vfio_ram_block_discard_disable(container, true);
- if (ret) {
- error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
+ if (!vfio_container_attach_discard_disable(container, group, errp)) {
goto unregister_container_exit;
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 02/28] vfio/container: reform vfio_container_connect cleanup
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
2025-05-09 13:12 ` [PULL 01/28] vfio/container: ram discard disable helper Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 03/28] vfio/container: vfio_container_group_add Cédric Le Goater
` (26 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, Steve Sistare, Cedric Le Goater
From: Steve Sistare <steven.sistare@oracle.com>
Replace the proliferation of exit labels in vfio_container_connect with
conditionals for cleaning each piece of state. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cedric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1746195760-101443-3-git-send-email-steven.sistare@oracle.com
[ clg: vfio_attach_discard_disable() -> vfio_container_attach_discard_disable() ]
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/container.c | 60 +++++++++++++++++++++++++--------------------
1 file changed, 33 insertions(+), 27 deletions(-)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 2ea137fb024fedd2b8d578f2fb5a7eea2b11e4fa..4b2864cfa85d815fb67f2465b7544eb9de1664d3 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -563,9 +563,12 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
{
VFIOContainer *container;
VFIOContainerBase *bcontainer;
- int ret, fd;
+ int ret, fd = -1;
VFIOAddressSpace *space;
- VFIOIOMMUClass *vioc;
+ VFIOIOMMUClass *vioc = NULL;
+ bool new_container = false;
+ bool group_was_added = false;
+ bool discard_disabled = false;
space = vfio_address_space_get(as);
@@ -584,35 +587,37 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
fd = qemu_open("/dev/vfio/vfio", O_RDWR, errp);
if (fd < 0) {
- goto put_space_exit;
+ goto fail;
}
ret = ioctl(fd, VFIO_GET_API_VERSION);
if (ret != VFIO_API_VERSION) {
error_setg(errp, "supported vfio version: %d, "
"reported version: %d", VFIO_API_VERSION, ret);
- goto close_fd_exit;
+ goto fail;
}
container = vfio_create_container(fd, group, errp);
if (!container) {
- goto close_fd_exit;
+ goto fail;
}
+ new_container = true;
bcontainer = &container->bcontainer;
if (!vfio_cpr_register_container(bcontainer, errp)) {
- goto free_container_exit;
+ goto fail;
}
if (!vfio_container_attach_discard_disable(container, group, errp)) {
- goto unregister_container_exit;
+ goto fail;
}
+ discard_disabled = true;
vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
assert(vioc->setup);
if (!vioc->setup(bcontainer, errp)) {
- goto enable_discards_exit;
+ goto fail;
}
vfio_group_add_kvm_device(group);
@@ -621,35 +626,36 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
group->container = container;
QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+ group_was_added = true;
if (!vfio_listener_register(bcontainer, errp)) {
- goto listener_release_exit;
+ goto fail;
}
bcontainer->initialized = true;
return true;
-listener_release_exit:
- QLIST_REMOVE(group, container_next);
- vfio_group_del_kvm_device(group);
+
+fail:
vfio_listener_unregister(bcontainer);
- if (vioc->release) {
+
+ if (group_was_added) {
+ QLIST_REMOVE(group, container_next);
+ vfio_group_del_kvm_device(group);
+ }
+ if (vioc && vioc->release) {
vioc->release(bcontainer);
}
-
-enable_discards_exit:
- vfio_ram_block_discard_disable(container, false);
-
-unregister_container_exit:
- vfio_cpr_unregister_container(bcontainer);
-
-free_container_exit:
- object_unref(container);
-
-close_fd_exit:
- close(fd);
-
-put_space_exit:
+ if (discard_disabled) {
+ vfio_ram_block_discard_disable(container, false);
+ }
+ if (new_container) {
+ vfio_cpr_unregister_container(bcontainer);
+ object_unref(container);
+ }
+ if (fd >= 0) {
+ close(fd);
+ }
vfio_address_space_put(space);
return false;
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 03/28] vfio/container: vfio_container_group_add
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
2025-05-09 13:12 ` [PULL 01/28] vfio/container: ram discard disable helper Cédric Le Goater
2025-05-09 13:12 ` [PULL 02/28] vfio/container: reform vfio_container_connect cleanup Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 04/28] vfio/igd: Restrict legacy mode to Gen6-9 devices Cédric Le Goater
` (25 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, Steve Sistare, Cedric Le Goater
From: Steve Sistare <steven.sistare@oracle.com>
Add vfio_container_group_add to de-dup some code. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cedric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1746195760-101443-4-git-send-email-steven.sistare@oracle.com
[ clg: vfio_attach_discard_disable() -> vfio_container_attach_discard_disable() ]
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/container.c | 47 ++++++++++++++++++++++++---------------------
1 file changed, 25 insertions(+), 22 deletions(-)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 4b2864cfa85d815fb67f2465b7544eb9de1664d3..a761f0958b71de39093d8849b49c55e3662e096f 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -558,6 +558,26 @@ static bool vfio_container_attach_discard_disable(VFIOContainer *container,
return !ret;
}
+static bool vfio_container_group_add(VFIOContainer *container, VFIOGroup *group,
+ Error **errp)
+{
+ if (!vfio_container_attach_discard_disable(container, group, errp)) {
+ return false;
+ }
+ group->container = container;
+ QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+ vfio_group_add_kvm_device(group);
+ return true;
+}
+
+static void vfio_container_group_del(VFIOContainer *container, VFIOGroup *group)
+{
+ QLIST_REMOVE(group, container_next);
+ group->container = NULL;
+ vfio_group_del_kvm_device(group);
+ vfio_ram_block_discard_disable(container, false);
+}
+
static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
Error **errp)
{
@@ -568,20 +588,13 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
VFIOIOMMUClass *vioc = NULL;
bool new_container = false;
bool group_was_added = false;
- bool discard_disabled = false;
space = vfio_address_space_get(as);
QLIST_FOREACH(bcontainer, &space->containers, next) {
container = container_of(bcontainer, VFIOContainer, bcontainer);
if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
- if (!vfio_container_attach_discard_disable(container, group, errp)) {
- return false;
- }
- group->container = container;
- QLIST_INSERT_HEAD(&container->group_list, group, container_next);
- vfio_group_add_kvm_device(group);
- return true;
+ return vfio_container_group_add(container, group, errp);
}
}
@@ -608,11 +621,6 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
goto fail;
}
- if (!vfio_container_attach_discard_disable(container, group, errp)) {
- goto fail;
- }
- discard_disabled = true;
-
vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
assert(vioc->setup);
@@ -620,12 +628,11 @@ static bool vfio_container_connect(VFIOGroup *group, AddressSpace *as,
goto fail;
}
- vfio_group_add_kvm_device(group);
-
vfio_address_space_insert(space, bcontainer);
- group->container = container;
- QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+ if (!vfio_container_group_add(container, group, errp)) {
+ goto fail;
+ }
group_was_added = true;
if (!vfio_listener_register(bcontainer, errp)) {
@@ -640,15 +647,11 @@ fail:
vfio_listener_unregister(bcontainer);
if (group_was_added) {
- QLIST_REMOVE(group, container_next);
- vfio_group_del_kvm_device(group);
+ vfio_container_group_del(container, group);
}
if (vioc && vioc->release) {
vioc->release(bcontainer);
}
- if (discard_disabled) {
- vfio_ram_block_discard_disable(container, false);
- }
if (new_container) {
vfio_cpr_unregister_container(bcontainer);
object_unref(container);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 04/28] vfio/igd: Restrict legacy mode to Gen6-9 devices
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (2 preceding siblings ...)
2025-05-09 13:12 ` [PULL 03/28] vfio/container: vfio_container_group_add Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 05/28] vfio/igd: Always emulate ASLS (OpRegion) register Cédric Le Goater
` (24 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
Intel only provides legacy VBIOS for IGD up to Gen9, and there is no
CSM support on later devices. Additionally, Seabios can only handle
32-bit BDSM register used until Gen9. Since legacy mode requires VGA
capability, restrict it to Gen6 through Gen9 devices.
Link: https://lore.kernel.org/qemu-devel/20250325172239.27926-1-tomitamoeko@gmail.com/T/
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-2-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
docs/igd-assign.txt | 1 +
hw/vfio/igd.c | 6 +++++-
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/docs/igd-assign.txt b/docs/igd-assign.txt
index 3aed7956d5d4fbc763d52c0f6ae0288c9a423679..95beb7681279ca97fc2b4b390045847dcd59eabd 100644
--- a/docs/igd-assign.txt
+++ b/docs/igd-assign.txt
@@ -47,6 +47,7 @@ Intel document [1] shows how to dump VBIOS to file. For UEFI Option ROM, see
QEMU also provides a "Legacy" mode that implicitly enables full functionality
on IGD, it is automatically enabled when
+* IGD generation is 6 to 9 (Sandy Bridge to Comet Lake)
* Machine type is i440fx
* IGD is assigned to guest BDF 00:02.0
* ROM BAR or romfile is present
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index d7e4728fdc84a0d91086f224c889f24120e1ce14..e06484c9112f104b87c18bb7b2d0a2cd2de1992e 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -517,11 +517,13 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
/*
* For backward compatibility, enable legacy mode when
+ * - Device geneation is 6 to 9 (including both)
* - Machine type is i440fx (pc_piix)
* - IGD device is at guest BDF 00:02.0
* - Not manually disabled by x-igd-legacy-mode=off
*/
if ((vdev->igd_legacy_mode != ON_OFF_AUTO_OFF) &&
+ (gen >= 6 && gen <= 9) &&
!strcmp(MACHINE_GET_CLASS(qdev_get_machine())->family, "pc_piix") &&
(&vdev->pdev == pci_find_device(pci_device_root_bus(&vdev->pdev),
0, PCI_DEVFN(0x2, 0)))) {
@@ -566,7 +568,9 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
vdev->features |= VFIO_FEATURE_ENABLE_IGD_LPC;
} else if (vdev->igd_legacy_mode == ON_OFF_AUTO_ON) {
error_setg(&err,
- "Machine is not i440fx or assigned BDF is not 00:02.0");
+ "Machine is not i440fx, assigned BDF is not 00:02.0, "
+ "or device %04x (gen %d) doesn't support legacy mode",
+ vdev->device_id, gen);
goto error;
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 05/28] vfio/igd: Always emulate ASLS (OpRegion) register
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (3 preceding siblings ...)
2025-05-09 13:12 ` [PULL 04/28] vfio/igd: Restrict legacy mode to Gen6-9 devices Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 06/28] vfio/igd: Detect IGD device by OpRegion Cédric Le Goater
` (23 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
ASLS register represents the base address of OpRegion, and it is
programmed with HPA. In IGD passthrough scenario, it needs to be
reprogrammed with GPA by guest firmware. To prevent guest accessing
wrong memory range, ASLS should always be emulated and cleared.
In GVT-g scenario, emulating ASLS is unnecessary as access is handled
by kvmgt backend [1].
[1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/gpu/drm/i915/gvt/cfg_space.c?h=v6.14#n295
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-3-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index e06484c9112f104b87c18bb7b2d0a2cd2de1992e..b1fce76f7250c2b2185cc259ac673d0d595832e8 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -182,10 +182,6 @@ static bool vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
trace_vfio_pci_igd_opregion_enabled(vdev->vbasedev.name);
- pci_set_long(vdev->pdev.config + IGD_ASLS, 0);
- pci_set_long(vdev->pdev.wmask + IGD_ASLS, ~0);
- pci_set_long(vdev->emulated_config_bits + IGD_ASLS, ~0);
-
return true;
}
@@ -584,7 +580,15 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
if ((vdev->features & VFIO_FEATURE_ENABLE_IGD_LPC) &&
!vfio_pci_igd_setup_lpc_bridge(vdev, errp)) {
goto error;
- }
+ }
+
+ /*
+ * ASLS (OpRegion address) is read-only, emulated
+ * It contains HPA, guest firmware need to reprogram it with GPA.
+ */
+ pci_set_long(vdev->pdev.config + IGD_ASLS, 0);
+ pci_set_long(vdev->pdev.wmask + IGD_ASLS, ~0);
+ pci_set_long(vdev->emulated_config_bits + IGD_ASLS, ~0);
/*
* Allow user to override dsm size using x-igd-gms option, in multiples of
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 06/28] vfio/igd: Detect IGD device by OpRegion
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (4 preceding siblings ...)
2025-05-09 13:12 ` [PULL 05/28] vfio/igd: Always emulate ASLS (OpRegion) register Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 07/28] vfio/igd: Check vendor and device ID on GVT-g mdev Cédric Le Goater
` (22 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
There is currently no straightforward way to distinguish if a Intel
graphics device is IGD or discrete GPU. However, only IGD devices have
OpRegion. Use the presence of VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION
to identify IGD devices. Still, OpRegion on hotplugged IGD device is
not supported.
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-4-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index b1fce76f7250c2b2185cc259ac673d0d595832e8..347253d08ce594d46cafb674ebbd9ca8878200e0 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -185,9 +185,10 @@ static bool vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
return true;
}
-static bool vfio_pci_igd_setup_opregion(VFIOPCIDevice *vdev, Error **errp)
+static bool vfio_pci_igd_opregion_detect(VFIOPCIDevice *vdev,
+ struct vfio_region_info **opregion,
+ Error **errp)
{
- g_autofree struct vfio_region_info *opregion = NULL;
int ret;
/* Hotplugging is not supported for opregion access */
@@ -198,17 +199,13 @@ static bool vfio_pci_igd_setup_opregion(VFIOPCIDevice *vdev, Error **errp)
ret = vfio_device_get_region_info_type(&vdev->vbasedev,
VFIO_REGION_TYPE_PCI_VENDOR_TYPE | PCI_VENDOR_ID_INTEL,
- VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, &opregion);
+ VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, opregion);
if (ret) {
error_setg_errno(errp, -ret,
"Device does not supports IGD OpRegion feature");
return false;
}
- if (!vfio_pci_igd_opregion_init(vdev, opregion, errp)) {
- return false;
- }
-
return true;
}
@@ -480,6 +477,7 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
+ g_autofree struct vfio_region_info *opregion = NULL;
int ret, gen;
uint64_t gms_size;
uint64_t *bdsm_size;
@@ -487,16 +485,17 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
bool legacy_mode_enabled = false;
Error *err = NULL;
- /*
- * This must be an Intel VGA device at address 00:02.0 for us to even
- * consider enabling legacy mode. The vBIOS has dependencies on the
- * PCI bus address.
- */
if (!vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, PCI_ANY_ID) ||
!vfio_is_vga(vdev)) {
return true;
}
+ /* IGD device always comes with OpRegion */
+ if (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp)) {
+ return true;
+ }
+ info_report("OpRegion detected on Intel display %x.", vdev->device_id);
+
/*
* IGD is not a standard, they like to change their specs often. We
* only attempt to support back to SandBridge and we hope that newer
@@ -572,7 +571,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
/* Setup OpRegion access */
if ((vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) &&
- !vfio_pci_igd_setup_opregion(vdev, errp)) {
+ !vfio_pci_igd_opregion_init(vdev, opregion, errp)) {
goto error;
}
@@ -672,8 +671,11 @@ error:
*/
static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
+ g_autofree struct vfio_region_info *opregion = NULL;
+
if ((vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) &&
- !vfio_pci_igd_setup_opregion(vdev, errp)) {
+ (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp) ||
+ !vfio_pci_igd_opregion_init(vdev, opregion, errp))) {
return false;
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 07/28] vfio/igd: Check vendor and device ID on GVT-g mdev
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (5 preceding siblings ...)
2025-05-09 13:12 ` [PULL 06/28] vfio/igd: Detect IGD device by OpRegion Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 08/28] vfio/igd: Check OpRegion support " Cédric Le Goater
` (21 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
Check the vendor and device ID on GVT-g mdev to ensure it is a supported
device [1]. This extra check is required for automatically enabling
OpRegion access later.
Note that Cherryview and Gemini Lake are marked as supported here since
current code cannot distinguish them with other Gen8 and Gen9 devices.
Since mdev cannot be created on these devices, this has no functional
impact.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/gpu/drm/i915/intel_gvt.c?h=v6.14#n52
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-5-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index 347253d08ce594d46cafb674ebbd9ca8878200e0..f5dd4750282920a71c52ca59f9ca42899d895c1e 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -672,6 +672,18 @@ error:
static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
g_autofree struct vfio_region_info *opregion = NULL;
+ int gen;
+
+ if (!vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, PCI_ANY_ID) ||
+ !vfio_is_vga(vdev)) {
+ return true;
+ }
+
+ /* FIXME: Cherryview is Gen8, but don't support GVT-g */
+ gen = igd_gen(vdev);
+ if (gen != 8 && gen != 9) {
+ return true;
+ }
if ((vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) &&
(!vfio_pci_igd_opregion_detect(vdev, &opregion, errp) ||
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 08/28] vfio/igd: Check OpRegion support on GVT-g mdev
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (6 preceding siblings ...)
2025-05-09 13:12 ` [PULL 07/28] vfio/igd: Check vendor and device ID on GVT-g mdev Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 09/28] vfio/igd: Enable OpRegion by default Cédric Le Goater
` (20 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
The Intel GVT-g backend `kvmgt` always emulates OpRegion for vGPU,
make sure the OpRegion is present for enabling access to it
automatically later.
Also, hotplugging GVT-g vGPU is now always disallowed regardless of
OpRegion to prevent potential issues. Intel has never claimed support
for GVT-g hotplugging.
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-6-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index f5dd4750282920a71c52ca59f9ca42899d895c1e..9dec32818c91f2021f6dc0c4bbe1fc0682df1a55 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -685,9 +685,13 @@ static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp)
return true;
}
+ if (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp)) {
+ /* Should never reach here, KVMGT always emulates OpRegion */
+ return false;
+ }
+
if ((vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) &&
- (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp) ||
- !vfio_pci_igd_opregion_init(vdev, opregion, errp))) {
+ !vfio_pci_igd_opregion_init(vdev, opregion, errp)) {
return false;
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 09/28] vfio/igd: Enable OpRegion by default
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (7 preceding siblings ...)
2025-05-09 13:12 ` [PULL 08/28] vfio/igd: Check OpRegion support " Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:12 ` [PULL 10/28] vfio/igd: Allow overriding GMS with 0xf0 to 0xfe on Gen9+ Cédric Le Goater
` (19 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
As the presence of OpRegion is used to detect IGD device now, and
guest driver usually depends on OpRegion to work. Enable OpRegion
on IGD devices by default for out-of-the-box passthrough experience
(except pre-boot display output), especially for libvirt users.
Example of IGD passthrough with libvirt:
<hostdev mode="subsystem" type="pci" managed="yes">
<source>
<address domain="0x0000" bus="0x00" slot="0x02" function="0x0"/>
</source>
<rom file="/path/to/igd/rom"/>
<address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x0"/>
</hostdev>
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-7-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
docs/igd-assign.txt | 4 ++--
hw/vfio/pci.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/docs/igd-assign.txt b/docs/igd-assign.txt
index 95beb7681279ca97fc2b4b390045847dcd59eabd..fc444503ff310a317d5d6724b4656c29c4a7dc87 100644
--- a/docs/igd-assign.txt
+++ b/docs/igd-assign.txt
@@ -102,7 +102,7 @@ digital formats work well.
Options
=======
-* x-igd-opregion=[on|*off*]
+* x-igd-opregion=[*on*|off]
Copy host IGD OpRegion and expose it to guest with fw_cfg
* x-igd-lpc=[on|*off*]
@@ -124,7 +124,7 @@ Examples
* Adding IGD with OpRegion and LPC ID hack, but without VGA ranges
(For UEFI guests)
- -device vfio-pci,host=00:02.0,id=hostdev0,addr=2.0,x-igd-legacy-mode=off,x-igd-opregion=on,x-igd-lpc=on,romfile=efi_oprom.rom
+ -device vfio-pci,host=00:02.0,id=hostdev0,addr=2.0,x-igd-legacy-mode=off,x-igd-lpc=on,romfile=efi_oprom.rom
Guest firmware
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 6908bcc0d3145c98d2999841d00451bdc51b6a3e..e1fab21b47adb4df9b011b3efb6d7c15c84bc8c2 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3385,7 +3385,7 @@ static const Property vfio_pci_dev_properties[] = {
DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
VFIO_FEATURE_ENABLE_REQ_BIT, true),
DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
- VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
+ VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, true),
DEFINE_PROP_BIT("x-igd-lpc", VFIOPCIDevice, features,
VFIO_FEATURE_ENABLE_IGD_LPC_BIT, false),
DEFINE_PROP_ON_OFF_AUTO("x-igd-legacy-mode", VFIOPCIDevice,
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 10/28] vfio/igd: Allow overriding GMS with 0xf0 to 0xfe on Gen9+
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (8 preceding siblings ...)
2025-05-09 13:12 ` [PULL 09/28] vfio/igd: Enable OpRegion by default Cédric Le Goater
@ 2025-05-09 13:12 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 11/28] vfio/igd: Only emulate GGC register when x-igd-gms is set Cédric Le Goater
` (18 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:12 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
On Gen9 and later IGD devices, GMS 0xf0 to 0xfe represents 4MB to 60MB
pre-allocated memory size in 4MB increments. Allow users overriding
GMS with these values.
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-8-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 59 +++++++++++++++++++++++++++++++++++----------------
1 file changed, 41 insertions(+), 18 deletions(-)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index 9dec32818c91f2021f6dc0c4bbe1fc0682df1a55..8ad9d723e29cd4d63e12346b6e40604ac020e747 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -412,6 +412,44 @@ static bool vfio_pci_igd_setup_lpc_bridge(VFIOPCIDevice *vdev, Error **errp)
return true;
}
+static bool vfio_pci_igd_override_gms(int gen, uint32_t gms, uint32_t *gmch)
+{
+ bool ret = false;
+
+ if (gen == -1) {
+ error_report("x-igd-gms is not supported on this device");
+ } else if (gen < 8) {
+ if (gms <= 0x10) {
+ *gmch &= ~(IGD_GMCH_GEN6_GMS_MASK << IGD_GMCH_GEN6_GMS_SHIFT);
+ *gmch |= gms << IGD_GMCH_GEN6_GMS_SHIFT;
+ ret = true;
+ } else {
+ error_report(QERR_INVALID_PARAMETER_VALUE, "x-igd-gms", "0~0x10");
+ }
+ } else if (gen == 8) {
+ if (gms <= 0x40) {
+ *gmch &= ~(IGD_GMCH_GEN8_GMS_MASK << IGD_GMCH_GEN8_GMS_SHIFT);
+ *gmch |= gms << IGD_GMCH_GEN8_GMS_SHIFT;
+ ret = true;
+ } else {
+ error_report(QERR_INVALID_PARAMETER_VALUE, "x-igd-gms", "0~0x40");
+ }
+ } else {
+ /* 0x0 to 0x40: 32MB increments starting at 0MB */
+ /* 0xf0 to 0xfe: 4MB increments starting at 4MB */
+ if ((gms <= 0x40) || (gms >= 0xf0 && gms <= 0xfe)) {
+ *gmch &= ~(IGD_GMCH_GEN8_GMS_MASK << IGD_GMCH_GEN8_GMS_SHIFT);
+ *gmch |= gms << IGD_GMCH_GEN8_GMS_SHIFT;
+ ret = true;
+ } else {
+ error_report(QERR_INVALID_PARAMETER_VALUE,
+ "x-igd-gms", "0~0x40 or 0xf0~0xfe");
+ }
+ }
+
+ return ret;
+}
+
#define IGD_GGC_MMIO_OFFSET 0x108040
#define IGD_BDSM_MMIO_OFFSET 0x1080C0
@@ -594,24 +632,9 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
* 32MiB. This option should only be used when the desired size cannot be
* set from DVMT Pre-Allocated option in host BIOS.
*/
- if (vdev->igd_gms) {
- if (gen < 8) {
- if (vdev->igd_gms <= 0x10) {
- gmch &= ~(IGD_GMCH_GEN6_GMS_MASK << IGD_GMCH_GEN6_GMS_SHIFT);
- gmch |= vdev->igd_gms << IGD_GMCH_GEN6_GMS_SHIFT;
- } else {
- error_report(QERR_INVALID_PARAMETER_VALUE,
- "x-igd-gms", "0~0x10");
- }
- } else {
- if (vdev->igd_gms <= 0x40) {
- gmch &= ~(IGD_GMCH_GEN8_GMS_MASK << IGD_GMCH_GEN8_GMS_SHIFT);
- gmch |= vdev->igd_gms << IGD_GMCH_GEN8_GMS_SHIFT;
- } else {
- error_report(QERR_INVALID_PARAMETER_VALUE,
- "x-igd-gms", "0~0x40");
- }
- }
+ if (vdev->igd_gms &&
+ !vfio_pci_igd_override_gms(gen, vdev->igd_gms, &gmch)) {
+ return false;
}
gms_size = igd_stolen_memory_size(gen, gmch);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 11/28] vfio/igd: Only emulate GGC register when x-igd-gms is set
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (9 preceding siblings ...)
2025-05-09 13:12 ` [PULL 10/28] vfio/igd: Allow overriding GMS with 0xf0 to 0xfe on Gen9+ Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 12/28] vfio/igd: Remove generation limitation for IGD passthrough Cédric Le Goater
` (17 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
x-igd-gms is used for overriding DSM region size in GGC register in
both config space and MMIO BAR0, by default host value is used.
There is no need to emulate it in default case.
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-9-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/igd.c | 49 ++++++++++++++++++++++++++-----------------------
1 file changed, 26 insertions(+), 23 deletions(-)
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index 8ad9d723e29cd4d63e12346b6e40604ac020e747..886d44f017f415d5f82c892e630ae2de1637677c 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -478,22 +478,24 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
return;
}
- ggc_quirk = vfio_quirk_alloc(1);
- ggc_mirror = ggc_quirk->data = g_malloc0(sizeof(*ggc_mirror));
- ggc_mirror->mem = ggc_quirk->mem;
- ggc_mirror->vdev = vdev;
- ggc_mirror->bar = nr;
- ggc_mirror->offset = IGD_GGC_MMIO_OFFSET;
- ggc_mirror->config_offset = IGD_GMCH;
-
- memory_region_init_io(ggc_mirror->mem, OBJECT(vdev),
- &vfio_generic_mirror_quirk, ggc_mirror,
- "vfio-igd-ggc-quirk", 2);
- memory_region_add_subregion_overlap(vdev->bars[nr].region.mem,
- ggc_mirror->offset, ggc_mirror->mem,
- 1);
+ if (vdev->igd_gms) {
+ ggc_quirk = vfio_quirk_alloc(1);
+ ggc_mirror = ggc_quirk->data = g_malloc0(sizeof(*ggc_mirror));
+ ggc_mirror->mem = ggc_quirk->mem;
+ ggc_mirror->vdev = vdev;
+ ggc_mirror->bar = nr;
+ ggc_mirror->offset = IGD_GGC_MMIO_OFFSET;
+ ggc_mirror->config_offset = IGD_GMCH;
- QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, ggc_quirk, next);
+ memory_region_init_io(ggc_mirror->mem, OBJECT(vdev),
+ &vfio_generic_mirror_quirk, ggc_mirror,
+ "vfio-igd-ggc-quirk", 2);
+ memory_region_add_subregion_overlap(vdev->bars[nr].region.mem,
+ ggc_mirror->offset, ggc_mirror->mem,
+ 1);
+
+ QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, ggc_quirk, next);
+ }
bdsm_quirk = vfio_quirk_alloc(1);
bdsm_mirror = bdsm_quirk->data = g_malloc0(sizeof(*bdsm_mirror));
@@ -632,9 +634,15 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
* 32MiB. This option should only be used when the desired size cannot be
* set from DVMT Pre-Allocated option in host BIOS.
*/
- if (vdev->igd_gms &&
- !vfio_pci_igd_override_gms(gen, vdev->igd_gms, &gmch)) {
- return false;
+ if (vdev->igd_gms) {
+ if (!vfio_pci_igd_override_gms(gen, vdev->igd_gms, &gmch)) {
+ return false;
+ }
+
+ /* GMCH is read-only, emulated */
+ pci_set_long(vdev->pdev.config + IGD_GMCH, gmch);
+ pci_set_long(vdev->pdev.wmask + IGD_GMCH, 0);
+ pci_set_long(vdev->emulated_config_bits + IGD_GMCH, ~0);
}
gms_size = igd_stolen_memory_size(gen, gmch);
@@ -652,11 +660,6 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
fw_cfg_add_file(fw_cfg_find(), "etc/igd-bdsm-size",
bdsm_size, sizeof(*bdsm_size));
- /* GMCH is read-only, emulated */
- pci_set_long(vdev->pdev.config + IGD_GMCH, gmch);
- pci_set_long(vdev->pdev.wmask + IGD_GMCH, 0);
- pci_set_long(vdev->emulated_config_bits + IGD_GMCH, ~0);
-
/* BDSM is read-write, emulated. The BIOS needs to be able to write it */
if (gen < 11) {
pci_set_long(vdev->pdev.config + IGD_BDSM, 0);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 12/28] vfio/igd: Remove generation limitation for IGD passthrough
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (10 preceding siblings ...)
2025-05-09 13:13 ` [PULL 11/28] vfio/igd: Only emulate GGC register when x-igd-gms is set Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 13/28] linux-header: update-linux-header script changes Cédric Le Goater
` (16 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, Tomita Moeko, Corvin Köhne,
Cédric Le Goater
From: Tomita Moeko <tomitamoeko@gmail.com>
Starting from Intel Core Ultra Series (Meteor Lake), Data Stolen Memory
has became a part of LMEMBAR (MMIO BAR2) [1][2], meaning that BDSM and
GGC register quirks are no longer needed on these platforms.
To support Meteor/Arrow/Lunar Lake and future IGD devices, remove the
generation limitation in IGD passthrough, and apply BDSM and GGC quirks
only to known Gen6-12 devices.
[1] https://edc.intel.com/content/www/us/en/design/publications/14th-generation-core-processors-cfg-and-mem-registers/d2-f0-processor-graphics-registers/
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/gpu/drm/i915/gem/i915_gem_stolen.c?h=v6.14#n142
Signed-off-by: Tomita Moeko <tomitamoeko@gmail.com>
Reviewed-by: Corvin Köhne <c.koehne@beckhoff.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250505170305.23622-10-tomitamoeko@gmail.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
docs/igd-assign.txt | 6 +++++
hw/vfio/igd.c | 58 ++++++++++++++++-----------------------------
2 files changed, 27 insertions(+), 37 deletions(-)
diff --git a/docs/igd-assign.txt b/docs/igd-assign.txt
index fc444503ff310a317d5d6724b4656c29c4a7dc87..af4e8391fc25898906b0b8bf123e1ec44e45efc0 100644
--- a/docs/igd-assign.txt
+++ b/docs/igd-assign.txt
@@ -157,6 +157,12 @@ fw_cfg requirements on the VM firmware:
it's expected that this fw_cfg file is only relevant to a single PCI
class VGA device with Intel vendor ID, appearing at PCI bus address 00:02.0.
+ Starting from Meteor Lake, IGD devices access stolen memory via its MMIO
+ BAR2 (LMEMBAR) and removed the BDSM register in config space. There is
+ no need for guest firmware to allocate data stolen memory in guest address
+ space and write it to BDSM register. Value of this fw_cfg file is 0 in
+ such case.
+
Upstream Seabios has OpRegion and BDSM (pre-Gen11 device only) support.
However, the support is not accepted by upstream EDK2/OVMF. A recommended
solution is to create a virtual OpRom with following DXE drivers:
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index 886d44f017f415d5f82c892e630ae2de1637677c..3ee1a73b57c57563f661a246e6dd7e505231be91 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -103,6 +103,7 @@ static int igd_gen(VFIOPCIDevice *vdev)
/*
* Unfortunately, Intel changes it's specification quite often. This makes
* it impossible to use a suitable default value for unknown devices.
+ * Return -1 for not applying any generation-specific quirks.
*/
return -1;
}
@@ -459,20 +460,12 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
VFIOConfigMirrorQuirk *ggc_mirror, *bdsm_mirror;
int gen;
- /*
- * This must be an Intel VGA device at address 00:02.0 for us to even
- * consider enabling legacy mode. Some driver have dependencies on the PCI
- * bus address.
- */
if (!vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, PCI_ANY_ID) ||
!vfio_is_vga(vdev) || nr != 0) {
return;
}
- /*
- * Only on IGD devices of gen 11 and above, the BDSM register is mirrored
- * into MMIO space and read from MMIO space by the Windows driver.
- */
+ /* Only on IGD Gen6-12 device needs quirks in BAR 0 */
gen = igd_gen(vdev);
if (gen < 6) {
return;
@@ -519,7 +512,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
g_autofree struct vfio_region_info *opregion = NULL;
int ret, gen;
- uint64_t gms_size;
+ uint64_t gms_size = 0;
uint64_t *bdsm_size;
uint32_t gmch;
bool legacy_mode_enabled = false;
@@ -536,18 +529,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
}
info_report("OpRegion detected on Intel display %x.", vdev->device_id);
- /*
- * IGD is not a standard, they like to change their specs often. We
- * only attempt to support back to SandBridge and we hope that newer
- * devices maintain compatibility with generation 8.
- */
gen = igd_gen(vdev);
- if (gen == -1) {
- error_report("IGD device %s is unsupported in legacy mode, "
- "try SandyBridge or newer", vdev->vbasedev.name);
- return true;
- }
-
gmch = vfio_pci_read_config(&vdev->pdev, IGD_GMCH, 4);
/*
@@ -645,32 +627,34 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
pci_set_long(vdev->emulated_config_bits + IGD_GMCH, ~0);
}
- gms_size = igd_stolen_memory_size(gen, gmch);
+ if (gen > 0) {
+ gms_size = igd_stolen_memory_size(gen, gmch);
+
+ /* BDSM is read-write, emulated. BIOS needs to be able to write it */
+ if (gen < 11) {
+ pci_set_long(vdev->pdev.config + IGD_BDSM, 0);
+ pci_set_long(vdev->pdev.wmask + IGD_BDSM, ~0);
+ pci_set_long(vdev->emulated_config_bits + IGD_BDSM, ~0);
+ } else {
+ pci_set_quad(vdev->pdev.config + IGD_BDSM_GEN11, 0);
+ pci_set_quad(vdev->pdev.wmask + IGD_BDSM_GEN11, ~0);
+ pci_set_quad(vdev->emulated_config_bits + IGD_BDSM_GEN11, ~0);
+ }
+ }
/*
* Request reserved memory for stolen memory via fw_cfg. VM firmware
* must allocate a 1MB aligned reserved memory region below 4GB with
- * the requested size (in bytes) for use by the Intel PCI class VGA
- * device at VM address 00:02.0. The base address of this reserved
- * memory region must be written to the device BDSM register at PCI
- * config offset 0x5C.
+ * the requested size (in bytes) for use by the IGD device. The base
+ * address of this reserved memory region must be written to the
+ * device BDSM register.
+ * For newer device without BDSM register, this fw_cfg item is 0.
*/
bdsm_size = g_malloc(sizeof(*bdsm_size));
*bdsm_size = cpu_to_le64(gms_size);
fw_cfg_add_file(fw_cfg_find(), "etc/igd-bdsm-size",
bdsm_size, sizeof(*bdsm_size));
- /* BDSM is read-write, emulated. The BIOS needs to be able to write it */
- if (gen < 11) {
- pci_set_long(vdev->pdev.config + IGD_BDSM, 0);
- pci_set_long(vdev->pdev.wmask + IGD_BDSM, ~0);
- pci_set_long(vdev->emulated_config_bits + IGD_BDSM, ~0);
- } else {
- pci_set_quad(vdev->pdev.config + IGD_BDSM_GEN11, 0);
- pci_set_quad(vdev->pdev.wmask + IGD_BDSM_GEN11, ~0);
- pci_set_quad(vdev->emulated_config_bits + IGD_BDSM_GEN11, ~0);
- }
-
trace_vfio_pci_igd_bdsm_enabled(vdev->vbasedev.name, (gms_size / MiB));
return true;
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 13/28] linux-header: update-linux-header script changes
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (11 preceding siblings ...)
2025-05-09 13:13 ` [PULL 12/28] vfio/igd: Remove generation limitation for IGD passthrough Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 14/28] linux-headers: Update to Linux v6.15-rc3 Cédric Le Goater
` (15 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, Rorie Reyes, Cédric Le Goater
From: Rorie Reyes <rreyes@linux.ibm.com>
Kernel commit 8a141be3233a changed from using
ASSEMBLY to ASSEMBLER
Updated the update-linux-header script to match
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250425052401.8287-2-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
| 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh
index 8913e4fb99b7d6589dd90143cec407b0f0cf6301..b43b8ef75a6321588475ec2bdf7f04e4b1ca5090 100755
--- a/scripts/update-linux-headers.sh
+++ b/scripts/update-linux-headers.sh
@@ -177,7 +177,7 @@ EOF
# Remove everything except the macros from bootparam.h avoiding the
# unnecessary import of several video/ist/etc headers
- sed -e '/__ASSEMBLY__/,/__ASSEMBLY__/d' \
+ sed -e '/__ASSEMBLER__/,/__ASSEMBLER__/d' \
"$hdrdir/include/asm/bootparam.h" > "$hdrdir/bootparam.h"
cp_portable "$hdrdir/bootparam.h" \
"$output/include/standard-headers/asm-$arch"
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 14/28] linux-headers: Update to Linux v6.15-rc3
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (12 preceding siblings ...)
2025-05-09 13:13 ` [PULL 13/28] linux-header: update-linux-header script changes Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 15/28] vfio: add vfio_device_prepare() Cédric Le Goater
` (14 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, Rorie Reyes, Cédric Le Goater
From: Rorie Reyes <rreyes@linux.ibm.com>
Update headers to retrieve uapi information for vfio-ap
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250425052401.8287-3-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/standard-headers/asm-x86/setup_data.h | 4 +-
include/standard-headers/drm/drm_fourcc.h | 41 ++++++
include/standard-headers/linux/const.h | 2 +-
include/standard-headers/linux/ethtool.h | 22 +++
include/standard-headers/linux/fuse.h | 12 +-
include/standard-headers/linux/pci_regs.h | 13 +-
include/standard-headers/linux/virtio_net.h | 13 ++
include/standard-headers/linux/virtio_snd.h | 2 +-
| 11 ++
| 1 +
| 1 +
| 4 +-
| 1 +
| 1 +
| 1 +
| 1 +
| 1 +
| 1 +
| 2 +
| 1 +
| 1 +
| 1 +
| 1 +
| 3 +
| 1 +
| 1 +
| 1 +
| 8 +-
| 2 +-
| 129 +++++++++++++++++-
| 1 +
| 21 ++-
| 2 +
| 30 ++--
34 files changed, 301 insertions(+), 36 deletions(-)
diff --git a/include/standard-headers/asm-x86/setup_data.h b/include/standard-headers/asm-x86/setup_data.h
index 09355f54c55ff41a27d8669aa7768d0198a7c035..a483d72f42863b6b841eb21ffa916c3b6b97bf5b 100644
--- a/include/standard-headers/asm-x86/setup_data.h
+++ b/include/standard-headers/asm-x86/setup_data.h
@@ -18,7 +18,7 @@
#define SETUP_INDIRECT (1<<31)
#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include "standard-headers/linux/types.h"
@@ -78,6 +78,6 @@ struct ima_setup_data {
uint64_t size;
} QEMU_PACKED;
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif /* _ASM_X86_SETUP_DATA_H */
diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h
index 708647776f9a1d48ef4a81597b1eb96315c6cfe8..a8b759dcbc8b00e871f5ee22f8eb77d3041e25bd 100644
--- a/include/standard-headers/drm/drm_fourcc.h
+++ b/include/standard-headers/drm/drm_fourcc.h
@@ -420,6 +420,7 @@ extern "C" {
#define DRM_FORMAT_MOD_VENDOR_ARM 0x08
#define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09
#define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a
+#define DRM_FORMAT_MOD_VENDOR_MTK 0x0b
/* add more to the end as needed */
@@ -1452,6 +1453,46 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier)
*/
#define AMLOGIC_FBC_OPTION_MEM_SAVING (1ULL << 0)
+/* MediaTek modifiers
+ * Bits Parameter Notes
+ * ----- ------------------------ ---------------------------------------------
+ * 7: 0 TILE LAYOUT Values are MTK_FMT_MOD_TILE_*
+ * 15: 8 COMPRESSION Values are MTK_FMT_MOD_COMPRESS_*
+ * 23:16 10 BIT LAYOUT Values are MTK_FMT_MOD_10BIT_LAYOUT_*
+ *
+ */
+
+#define DRM_FORMAT_MOD_MTK(__flags) fourcc_mod_code(MTK, __flags)
+
+/*
+ * MediaTek Tiled Modifier
+ * The lowest 8 bits of the modifier is used to specify the tiling
+ * layout. Only the 16L_32S tiling is used for now, but we define an
+ * "untiled" version and leave room for future expansion.
+ */
+#define MTK_FMT_MOD_TILE_MASK 0xf
+#define MTK_FMT_MOD_TILE_NONE 0x0
+#define MTK_FMT_MOD_TILE_16L32S 0x1
+
+/*
+ * Bits 8-15 specify compression options
+ */
+#define MTK_FMT_MOD_COMPRESS_MASK (0xf << 8)
+#define MTK_FMT_MOD_COMPRESS_NONE (0x0 << 8)
+#define MTK_FMT_MOD_COMPRESS_V1 (0x1 << 8)
+
+/*
+ * Bits 16-23 specify how the bits of 10 bit formats are
+ * stored out in memory
+ */
+#define MTK_FMT_MOD_10BIT_LAYOUT_MASK (0xf << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_PACKED (0x0 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBTILED (0x1 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBRASTER (0x2 << 16)
+
+/* alias for the most common tiling format */
+#define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S)
+
/*
* AMD modifiers
*
diff --git a/include/standard-headers/linux/const.h b/include/standard-headers/linux/const.h
index 2122610de7f97a8f0129bbd3e6d6f72e4b405414..95ede2334204048d49b228284e9fbc1561337a16 100644
--- a/include/standard-headers/linux/const.h
+++ b/include/standard-headers/linux/const.h
@@ -33,7 +33,7 @@
* Missing __asm__ support
*
* __BIT128() would not work in the __asm__ code, as it shifts an
- * 'unsigned __init128' data type as direct representation of
+ * 'unsigned __int128' data type as direct representation of
* 128 bit constants is not supported in the gcc compiler, as
* they get silently truncated.
*
diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h
index e83382531cd1c6e909bf2f3fc852aabeff1d861d..5d1ad5fdeab66979d7f996b272b84493043a1ee9 100644
--- a/include/standard-headers/linux/ethtool.h
+++ b/include/standard-headers/linux/ethtool.h
@@ -2059,6 +2059,24 @@ enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100,
ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101,
ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT = 102,
+ ETHTOOL_LINK_MODE_200000baseCR_Full_BIT = 103,
+ ETHTOOL_LINK_MODE_200000baseKR_Full_BIT = 104,
+ ETHTOOL_LINK_MODE_200000baseDR_Full_BIT = 105,
+ ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT = 106,
+ ETHTOOL_LINK_MODE_200000baseSR_Full_BIT = 107,
+ ETHTOOL_LINK_MODE_200000baseVR_Full_BIT = 108,
+ ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT = 109,
+ ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT = 110,
+ ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT = 111,
+ ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT = 112,
+ ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT = 113,
+ ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT = 114,
+ ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT = 115,
+ ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT = 116,
+ ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT = 117,
+ ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118,
+ ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119,
+ ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120,
/* must be last entry */
__ETHTOOL_LINK_MODE_MASK_NBITS
@@ -2271,6 +2289,10 @@ static inline int ethtool_validate_duplex(uint8_t duplex)
* be exploited to reduce the RSS queue spread.
*/
#define RXH_XFRM_SYM_XOR (1 << 0)
+/* Similar to SYM_XOR, except that one copy of the XOR'ed fields is replaced by
+ * an OR of the same fields
+ */
+#define RXH_XFRM_SYM_OR_XOR (1 << 1)
#define RXH_XFRM_NO_CHANGE 0xff
/* L2-L4 network traffic flow types */
diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h
index d303effb2a0d232a344051997dadbddbb3273a8d..a2b5815d890871d83a1e6d5f2b56437b6efbaba7 100644
--- a/include/standard-headers/linux/fuse.h
+++ b/include/standard-headers/linux/fuse.h
@@ -229,6 +229,9 @@
* - FUSE_URING_IN_OUT_HEADER_SZ
* - FUSE_URING_OP_IN_OUT_SZ
* - enum fuse_uring_cmd
+ *
+ * 7.43
+ * - add FUSE_REQUEST_TIMEOUT
*/
#ifndef _LINUX_FUSE_H
@@ -260,7 +263,7 @@
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 42
+#define FUSE_KERNEL_MINOR_VERSION 43
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
@@ -431,6 +434,8 @@ struct fuse_file_lock {
* of the request ID indicates resend requests
* FUSE_ALLOW_IDMAP: allow creation of idmapped mounts
* FUSE_OVER_IO_URING: Indicate that client supports io-uring
+ * FUSE_REQUEST_TIMEOUT: kernel supports timing out requests.
+ * init_out.request_timeout contains the timeout (in secs)
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
@@ -473,11 +478,11 @@ struct fuse_file_lock {
#define FUSE_PASSTHROUGH (1ULL << 37)
#define FUSE_NO_EXPORT_SUPPORT (1ULL << 38)
#define FUSE_HAS_RESEND (1ULL << 39)
-
/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP
#define FUSE_ALLOW_IDMAP (1ULL << 40)
#define FUSE_OVER_IO_URING (1ULL << 41)
+#define FUSE_REQUEST_TIMEOUT (1ULL << 42)
/**
* CUSE INIT request/reply flags
@@ -905,7 +910,8 @@ struct fuse_init_out {
uint16_t map_alignment;
uint32_t flags2;
uint32_t max_stack_depth;
- uint32_t unused[6];
+ uint16_t request_timeout;
+ uint16_t unused[11];
};
#define CUSE_INIT_INFO_MAX 4096
diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
index 3445c4970e4d8e72f426071032adf82799aedbf7..ba326710f9c8b626645a77a7fecd31f1b481f3d4 100644
--- a/include/standard-headers/linux/pci_regs.h
+++ b/include/standard-headers/linux/pci_regs.h
@@ -486,6 +486,7 @@
#define PCI_EXP_TYPE_RC_EC 0xa /* Root Complex Event Collector */
#define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */
#define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */
+#define PCI_EXP_FLAGS_FLIT 0x8000 /* Flit Mode Supported */
#define PCI_EXP_DEVCAP 0x04 /* Device capabilities */
#define PCI_EXP_DEVCAP_PAYLOAD 0x00000007 /* Max_Payload_Size */
#define PCI_EXP_DEVCAP_PHANTOM 0x00000018 /* Phantom functions */
@@ -795,6 +796,8 @@
#define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */
#define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */
#define PCI_ERR_CAP_PREFIX_LOG_PRESENT 0x00000800 /* TLP Prefix Log Present */
+#define PCI_ERR_CAP_TLP_LOG_FLIT 0x00040000 /* TLP was logged in Flit Mode */
+#define PCI_ERR_CAP_TLP_LOG_SIZE 0x00f80000 /* Logged TLP Size (only in Flit mode) */
#define PCI_ERR_HEADER_LOG 0x1c /* Header Log Register (16 bytes) */
#define PCI_ERR_ROOT_COMMAND 0x2c /* Root Error Command */
#define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 /* Correctable Err Reporting Enable */
@@ -1013,7 +1016,7 @@
/* Resizable BARs */
#define PCI_REBAR_CAP 4 /* capability register */
-#define PCI_REBAR_CAP_SIZES 0x00FFFFF0 /* supported BAR sizes */
+#define PCI_REBAR_CAP_SIZES 0xFFFFFFF0 /* supported BAR sizes */
#define PCI_REBAR_CTRL 8 /* control register */
#define PCI_REBAR_CTRL_BAR_IDX 0x00000007 /* BAR index */
#define PCI_REBAR_CTRL_NBAR_MASK 0x000000E0 /* # of resizable BARs */
@@ -1061,8 +1064,9 @@
#define PCI_EXP_DPC_CAP_RP_EXT 0x0020 /* Root Port Extensions */
#define PCI_EXP_DPC_CAP_POISONED_TLP 0x0040 /* Poisoned TLP Egress Blocking Supported */
#define PCI_EXP_DPC_CAP_SW_TRIGGER 0x0080 /* Software Triggering Supported */
-#define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0x0F00 /* RP PIO Log Size */
+#define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0x0F00 /* RP PIO Log Size [3:0] */
#define PCI_EXP_DPC_CAP_DL_ACTIVE 0x1000 /* ERR_COR signal on DL_Active supported */
+#define PCI_EXP_DPC_RP_PIO_LOG_SIZE4 0x2000 /* RP PIO Log Size [4] */
#define PCI_EXP_DPC_CTL 0x06 /* DPC control */
#define PCI_EXP_DPC_CTL_EN_FATAL 0x0001 /* Enable trigger on ERR_FATAL message */
@@ -1205,9 +1209,12 @@
#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff
#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER 0x0000ff00
#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff
-#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000
+#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE 0x00ff0000
#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000
+/* Deprecated old name, replaced with PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE */
+#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE
+
/* Compute Express Link (CXL r3.1, sec 8.1.5) */
#define PCI_DVSEC_CXL_PORT 3
#define PCI_DVSEC_CXL_PORT_CTL 0x0c
diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h
index fc594fe5fcbe3a750d835aa9003d966da26d53a0..982e854f14e49e3a7d2637f151c0c622aa84dcaa 100644
--- a/include/standard-headers/linux/virtio_net.h
+++ b/include/standard-headers/linux/virtio_net.h
@@ -327,6 +327,19 @@ struct virtio_net_rss_config {
uint8_t hash_key_data[/* hash_key_length */];
};
+struct virtio_net_rss_config_hdr {
+ uint32_t hash_types;
+ uint16_t indirection_table_mask;
+ uint16_t unclassified_queue;
+ uint16_t indirection_table[/* 1 + indirection_table_mask */];
+};
+
+struct virtio_net_rss_config_trailer {
+ uint16_t max_tx_vq;
+ uint8_t hash_key_length;
+ uint8_t hash_key_data[/* hash_key_length */];
+};
+
#define VIRTIO_NET_CTRL_MQ_RSS_CONFIG 1
/*
diff --git a/include/standard-headers/linux/virtio_snd.h b/include/standard-headers/linux/virtio_snd.h
index 860f12e0a4e196b6469fc7f4ee44545c4130b380..160d57899f83550a6d2ee20cf65723366b9d7fb0 100644
--- a/include/standard-headers/linux/virtio_snd.h
+++ b/include/standard-headers/linux/virtio_snd.h
@@ -25,7 +25,7 @@ struct virtio_snd_config {
uint32_t streams;
/* # of available channel maps */
uint32_t chmaps;
- /* # of available control elements */
+ /* # of available control elements (if VIRTIO_SND_F_CTLS) */
uint32_t controls;
};
--git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
index ec1e82bdc8882da5be677d91e91713e123c1ccb4..4e6aff08df8b05d04483b2e18844de3eabb362ea 100644
--- a/linux-headers/asm-arm64/kvm.h
+++ b/linux-headers/asm-arm64/kvm.h
@@ -105,6 +105,7 @@ struct kvm_regs {
#define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */
#define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */
#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */
+#define KVM_ARM_VCPU_HAS_EL2_E2H0 8 /* Limit NV support to E2H RES0 */
struct kvm_vcpu_init {
__u32 target;
@@ -365,6 +366,7 @@ enum {
KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0,
};
+/* Vendor hyper call function numbers 0-63 */
#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2)
enum {
@@ -372,6 +374,14 @@ enum {
KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1,
};
+/* Vendor hyper call function numbers 64-127 */
+#define KVM_REG_ARM_VENDOR_HYP_BMAP_2 KVM_REG_ARM_FW_FEAT_BMAP_REG(3)
+
+enum {
+ KVM_REG_ARM_VENDOR_HYP_BIT_DISCOVER_IMPL_VER = 0,
+ KVM_REG_ARM_VENDOR_HYP_BIT_DISCOVER_IMPL_CPUS = 1,
+};
+
/* Device Control API on vm fd */
#define KVM_ARM_VM_SMCCC_CTRL 0
#define KVM_ARM_VM_SMCCC_FILTER 0
@@ -394,6 +404,7 @@ enum {
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ 9
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
--git a/linux-headers/asm-arm64/unistd_64.h b/linux-headers/asm-arm64/unistd_64.h
index d4e90fff76057b7944c9b0d41306380238dcf4f0..ee9aaebdf325243c588834674d1b963ebb3070b5 100644
--- a/linux-headers/asm-arm64/unistd_64.h
+++ b/linux-headers/asm-arm64/unistd_64.h
@@ -323,6 +323,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_64_H */
--git a/linux-headers/asm-generic/mman-common.h b/linux-headers/asm-generic/mman-common.h
index 1ea2c4c33b86a2638b03335ad5bfcfd1691cef3e..ef1c27fa3c570fa4ff06fc6f742914925f8b02c8 100644
--- a/linux-headers/asm-generic/mman-common.h
+++ b/linux-headers/asm-generic/mman-common.h
@@ -85,6 +85,7 @@
/* compatibility flags */
#define MAP_FILE 0
+#define PKEY_UNRESTRICTED 0x0
#define PKEY_DISABLE_ACCESS 0x1
#define PKEY_DISABLE_WRITE 0x2
#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\
--git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h
index 88dc393c2bca38c0fa1b3fae579f7cfe4931223c..2892a45023af6d3eb941623d4fed04841ab07e02 100644
--- a/linux-headers/asm-generic/unistd.h
+++ b/linux-headers/asm-generic/unistd.h
@@ -849,9 +849,11 @@ __SYSCALL(__NR_getxattrat, sys_getxattrat)
__SYSCALL(__NR_listxattrat, sys_listxattrat)
#define __NR_removexattrat 466
__SYSCALL(__NR_removexattrat, sys_removexattrat)
+#define __NR_open_tree_attr 467
+__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
#undef __NR_syscalls
-#define __NR_syscalls 467
+#define __NR_syscalls 468
/*
* 32 bit systems traditionally used different
--git a/linux-headers/asm-loongarch/unistd_64.h b/linux-headers/asm-loongarch/unistd_64.h
index 23fb96a8a77f011e59d0b0789b6df2509155df07..50d22df8f7ce85b01f991ef5fd81724866aaa8ac 100644
--- a/linux-headers/asm-loongarch/unistd_64.h
+++ b/linux-headers/asm-loongarch/unistd_64.h
@@ -319,6 +319,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_64_H */
--git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h
index 9a757196448c5706236635186fc5811d0dd75a08..bdcc2f460babac1da7ad95aa1804883bd7fbfc0f 100644
--- a/linux-headers/asm-mips/unistd_n32.h
+++ b/linux-headers/asm-mips/unistd_n32.h
@@ -395,5 +395,6 @@
#define __NR_getxattrat (__NR_Linux + 464)
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
+#define __NR_open_tree_attr (__NR_Linux + 467)
#endif /* _ASM_UNISTD_N32_H */
--git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h
index 7086783b0cf2199f7e4b3831e1380240132f7b61..3b6b0193b69055194f7d025044616cc41fc40ef4 100644
--- a/linux-headers/asm-mips/unistd_n64.h
+++ b/linux-headers/asm-mips/unistd_n64.h
@@ -371,5 +371,6 @@
#define __NR_getxattrat (__NR_Linux + 464)
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
+#define __NR_open_tree_attr (__NR_Linux + 467)
#endif /* _ASM_UNISTD_N64_H */
--git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h
index b3825823e486240ecaa4f42077015fd23843cdb8..4609a4b4d38b425647b8c740975a0856e344af45 100644
--- a/linux-headers/asm-mips/unistd_o32.h
+++ b/linux-headers/asm-mips/unistd_o32.h
@@ -441,5 +441,6 @@
#define __NR_getxattrat (__NR_Linux + 464)
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
+#define __NR_open_tree_attr (__NR_Linux + 467)
#endif /* _ASM_UNISTD_O32_H */
--git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h
index 38ee4dc35d757ce0474cf51acd75c53ec34c3c8c..5d38a427e0af76192f8ec6a9b8542a2fb81262c0 100644
--- a/linux-headers/asm-powerpc/unistd_32.h
+++ b/linux-headers/asm-powerpc/unistd_32.h
@@ -448,6 +448,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_32_H */
--git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h
index 5e5f156834698e79e61d42d04b35cbc717a48aac..860a488e4d1a17bb553ab68a97439995be0c9488 100644
--- a/linux-headers/asm-powerpc/unistd_64.h
+++ b/linux-headers/asm-powerpc/unistd_64.h
@@ -420,6 +420,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_64_H */
--git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h
index f06bc5efcd79a24fcfa656c49b0ee2526f455cd1..5f59fd226cc57af811706c4705fee12eafcc7d08 100644
--- a/linux-headers/asm-riscv/kvm.h
+++ b/linux-headers/asm-riscv/kvm.h
@@ -182,6 +182,8 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_SVVPTC,
KVM_RISCV_ISA_EXT_ZABHA,
KVM_RISCV_ISA_EXT_ZICCRSE,
+ KVM_RISCV_ISA_EXT_ZAAMO,
+ KVM_RISCV_ISA_EXT_ZALRSC,
KVM_RISCV_ISA_EXT_MAX,
};
--git a/linux-headers/asm-riscv/unistd_32.h b/linux-headers/asm-riscv/unistd_32.h
index 74f6127aedaa5e5fbd521d1f1f6a078ba6f3e9c4..a5e769f1d996721840ea40ea949529b69e4ad282 100644
--- a/linux-headers/asm-riscv/unistd_32.h
+++ b/linux-headers/asm-riscv/unistd_32.h
@@ -314,6 +314,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_32_H */
--git a/linux-headers/asm-riscv/unistd_64.h b/linux-headers/asm-riscv/unistd_64.h
index bb6a15a2ec407509862123bd806b07d9d556159b..8df4d64841c2ab8ad73af78305348e89f32d62d2 100644
--- a/linux-headers/asm-riscv/unistd_64.h
+++ b/linux-headers/asm-riscv/unistd_64.h
@@ -324,6 +324,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_64_H */
--git a/linux-headers/asm-s390/unistd_32.h b/linux-headers/asm-s390/unistd_32.h
index 620201cb36534b06b7e884bb8dcdb57b774724d0..85eedbd18e31feba19d3741a9e89694fa7bc3dde 100644
--- a/linux-headers/asm-s390/unistd_32.h
+++ b/linux-headers/asm-s390/unistd_32.h
@@ -439,5 +439,6 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_S390_UNISTD_32_H */
--git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h
index e7e4a10aaf0b3f8ae25da665fbe5e6f0a332ad74..c03b1b9701024db8cef8ee34ce3359cc39bcbf8d 100644
--- a/linux-headers/asm-s390/unistd_64.h
+++ b/linux-headers/asm-s390/unistd_64.h
@@ -387,5 +387,6 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_S390_UNISTD_64_H */
--git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
index 86f2c34e7afa27e3271eec0f6fd2585e98e97522..dc591fb17e59d40c9a36ec0f74c2c519dfb968be 100644
--- a/linux-headers/asm-x86/kvm.h
+++ b/linux-headers/asm-x86/kvm.h
@@ -557,6 +557,9 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8)
+#define KVM_XEN_MSR_MIN_INDEX 0x40000000u
+#define KVM_XEN_MSR_MAX_INDEX 0x4fffffffu
+
struct kvm_xen_hvm_config {
__u32 flags;
__u32 msr;
--git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h
index a2eb492a75ec0246a0195ab4eef9aaf55a8b006b..491d6b4eb68eefafd78a902f468407dce8333fdc 100644
--- a/linux-headers/asm-x86/unistd_32.h
+++ b/linux-headers/asm-x86/unistd_32.h
@@ -457,6 +457,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_32_H */
--git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h
index 2f5fc400f5922a6ac3e1faef89a5f9689c82ffd0..7cf88bf9bdac6a6381063376f6673faaf29b393c 100644
--- a/linux-headers/asm-x86/unistd_64.h
+++ b/linux-headers/asm-x86/unistd_64.h
@@ -380,6 +380,7 @@
#define __NR_getxattrat 464
#define __NR_listxattrat 465
#define __NR_removexattrat 466
+#define __NR_open_tree_attr 467
#endif /* _ASM_UNISTD_64_H */
--git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h
index fecd832e7fcc806507a9f965178456a784980cda..82959111e6a5e8cad2e8fb28b8e5431c19b313d5 100644
--- a/linux-headers/asm-x86/unistd_x32.h
+++ b/linux-headers/asm-x86/unistd_x32.h
@@ -333,6 +333,7 @@
#define __NR_getxattrat (__X32_SYSCALL_BIT + 464)
#define __NR_listxattrat (__X32_SYSCALL_BIT + 465)
#define __NR_removexattrat (__X32_SYSCALL_BIT + 466)
+#define __NR_open_tree_attr (__X32_SYSCALL_BIT + 467)
#define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512)
#define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513)
#define __NR_ioctl (__X32_SYSCALL_BIT + 514)
--git a/linux-headers/linux/bits.h b/linux-headers/linux/bits.h
index c0d00c0a9868beffb660d6070df70c5b6e3ad8a2..58596d18f43b4f6107f833b2636adbbc0cdf3ce4 100644
--- a/linux-headers/linux/bits.h
+++ b/linux-headers/linux/bits.h
@@ -4,13 +4,9 @@
#ifndef _LINUX_BITS_H
#define _LINUX_BITS_H
-#define __GENMASK(h, l) \
- (((~_UL(0)) - (_UL(1) << (l)) + 1) & \
- (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
-#define __GENMASK_ULL(h, l) \
- (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
- (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
#define __GENMASK_U128(h, l) \
((_BIT128((h)) << 1) - (_BIT128(l)))
--git a/linux-headers/linux/const.h b/linux-headers/linux/const.h
index 2122610de7f97a8f0129bbd3e6d6f72e4b405414..95ede2334204048d49b228284e9fbc1561337a16 100644
--- a/linux-headers/linux/const.h
+++ b/linux-headers/linux/const.h
@@ -33,7 +33,7 @@
* Missing __asm__ support
*
* __BIT128() would not work in the __asm__ code, as it shifts an
- * 'unsigned __init128' data type as direct representation of
+ * 'unsigned __int128' data type as direct representation of
* 128 bit constants is not supported in the gcc compiler, as
* they get silently truncated.
*
--git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h
index ccbdca5e1138d50d45ea3c33e4300345a86edc21..cb0f7d6b4dec916a4d74b743b1ae2cfb1291233c 100644
--- a/linux-headers/linux/iommufd.h
+++ b/linux-headers/linux/iommufd.h
@@ -55,6 +55,7 @@ enum {
IOMMUFD_CMD_VIOMMU_ALLOC = 0x90,
IOMMUFD_CMD_VDEVICE_ALLOC = 0x91,
IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92,
+ IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93,
};
/**
@@ -392,6 +393,9 @@ struct iommu_vfio_ioas {
* Any domain attached to the non-PASID part of the
* device must also be flagged, otherwise attaching a
* PASID will blocked.
+ * For the user that wants to attach PASID, ioas is
+ * not recommended for both the non-PASID part
+ * and PASID part of the device.
* If IOMMU does not support PASID it will return
* error (-EOPNOTSUPP).
*/
@@ -608,9 +612,17 @@ enum iommu_hw_info_type {
* IOMMU_HWPT_GET_DIRTY_BITMAP
* IOMMU_HWPT_SET_DIRTY_TRACKING
*
+ * @IOMMU_HW_CAP_PCI_PASID_EXEC: Execute Permission Supported, user ignores it
+ * when the struct
+ * iommu_hw_info::out_max_pasid_log2 is zero.
+ * @IOMMU_HW_CAP_PCI_PASID_PRIV: Privileged Mode Supported, user ignores it
+ * when the struct
+ * iommu_hw_info::out_max_pasid_log2 is zero.
*/
enum iommufd_hw_capabilities {
IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0,
+ IOMMU_HW_CAP_PCI_PASID_EXEC = 1 << 1,
+ IOMMU_HW_CAP_PCI_PASID_PRIV = 1 << 2,
};
/**
@@ -626,6 +638,9 @@ enum iommufd_hw_capabilities {
* iommu_hw_info_type.
* @out_capabilities: Output the generic iommu capability info type as defined
* in the enum iommu_hw_capabilities.
+ * @out_max_pasid_log2: Output the width of PASIDs. 0 means no PASID support.
+ * PCI devices turn to out_capabilities to check if the
+ * specific capabilities is supported or not.
* @__reserved: Must be 0
*
* Query an iommu type specific hardware information data from an iommu behind
@@ -649,7 +664,8 @@ struct iommu_hw_info {
__u32 data_len;
__aligned_u64 data_uptr;
__u32 out_data_type;
- __u32 __reserved;
+ __u8 out_max_pasid_log2;
+ __u8 __reserved[3];
__aligned_u64 out_capabilities;
};
#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
@@ -1014,4 +1030,115 @@ struct iommu_ioas_change_process {
#define IOMMU_IOAS_CHANGE_PROCESS \
_IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_CHANGE_PROCESS)
+/**
+ * enum iommu_veventq_flag - flag for struct iommufd_vevent_header
+ * @IOMMU_VEVENTQ_FLAG_LOST_EVENTS: vEVENTQ has lost vEVENTs
+ */
+enum iommu_veventq_flag {
+ IOMMU_VEVENTQ_FLAG_LOST_EVENTS = (1U << 0),
+};
+
+/**
+ * struct iommufd_vevent_header - Virtual Event Header for a vEVENTQ Status
+ * @flags: Combination of enum iommu_veventq_flag
+ * @sequence: The sequence index of a vEVENT in the vEVENTQ, with a range of
+ * [0, INT_MAX] where the following index of INT_MAX is 0
+ *
+ * Each iommufd_vevent_header reports a sequence index of the following vEVENT:
+ *
+ * +----------------------+-------+----------------------+-------+---+-------+
+ * | header0 {sequence=0} | data0 | header1 {sequence=1} | data1 |...| dataN |
+ * +----------------------+-------+----------------------+-------+---+-------+
+ *
+ * And this sequence index is expected to be monotonic to the sequence index of
+ * the previous vEVENT. If two adjacent sequence indexes has a delta larger than
+ * 1, it means that delta - 1 number of vEVENTs has lost, e.g. two lost vEVENTs:
+ *
+ * +-----+----------------------+-------+----------------------+-------+-----+
+ * | ... | header3 {sequence=3} | data3 | header6 {sequence=6} | data6 | ... |
+ * +-----+----------------------+-------+----------------------+-------+-----+
+ *
+ * If a vEVENT lost at the tail of the vEVENTQ and there is no following vEVENT
+ * providing the next sequence index, an IOMMU_VEVENTQ_FLAG_LOST_EVENTS header
+ * would be added to the tail, and no data would follow this header:
+ *
+ * +--+----------------------+-------+-----------------------------------------+
+ * |..| header3 {sequence=3} | data3 | header4 {flags=LOST_EVENTS, sequence=4} |
+ * +--+----------------------+-------+-----------------------------------------+
+ */
+struct iommufd_vevent_header {
+ __u32 flags;
+ __u32 sequence;
+};
+
+/**
+ * enum iommu_veventq_type - Virtual Event Queue Type
+ * @IOMMU_VEVENTQ_TYPE_DEFAULT: Reserved for future use
+ * @IOMMU_VEVENTQ_TYPE_ARM_SMMUV3: ARM SMMUv3 Virtual Event Queue
+ */
+enum iommu_veventq_type {
+ IOMMU_VEVENTQ_TYPE_DEFAULT = 0,
+ IOMMU_VEVENTQ_TYPE_ARM_SMMUV3 = 1,
+};
+
+/**
+ * struct iommu_vevent_arm_smmuv3 - ARM SMMUv3 Virtual Event
+ * (IOMMU_VEVENTQ_TYPE_ARM_SMMUV3)
+ * @evt: 256-bit ARM SMMUv3 Event record, little-endian.
+ * Reported event records: (Refer to "7.3 Event records" in SMMUv3 HW Spec)
+ * - 0x04 C_BAD_STE
+ * - 0x06 F_STREAM_DISABLED
+ * - 0x08 C_BAD_SUBSTREAMID
+ * - 0x0a C_BAD_CD
+ * - 0x10 F_TRANSLATION
+ * - 0x11 F_ADDR_SIZE
+ * - 0x12 F_ACCESS
+ * - 0x13 F_PERMISSION
+ *
+ * StreamID field reports a virtual device ID. To receive a virtual event for a
+ * device, a vDEVICE must be allocated via IOMMU_VDEVICE_ALLOC.
+ */
+struct iommu_vevent_arm_smmuv3 {
+ __aligned_le64 evt[4];
+};
+
+/**
+ * struct iommu_veventq_alloc - ioctl(IOMMU_VEVENTQ_ALLOC)
+ * @size: sizeof(struct iommu_veventq_alloc)
+ * @flags: Must be 0
+ * @viommu_id: virtual IOMMU ID to associate the vEVENTQ with
+ * @type: Type of the vEVENTQ. Must be defined in enum iommu_veventq_type
+ * @veventq_depth: Maximum number of events in the vEVENTQ
+ * @out_veventq_id: The ID of the new vEVENTQ
+ * @out_veventq_fd: The fd of the new vEVENTQ. User space must close the
+ * successfully returned fd after using it
+ * @__reserved: Must be 0
+ *
+ * Explicitly allocate a virtual event queue interface for a vIOMMU. A vIOMMU
+ * can have multiple FDs for different types, but is confined to one per @type.
+ * User space should open the @out_veventq_fd to read vEVENTs out of a vEVENTQ,
+ * if there are vEVENTs available. A vEVENTQ will lose events due to overflow,
+ * if the number of the vEVENTs hits @veventq_depth.
+ *
+ * Each vEVENT in a vEVENTQ encloses a struct iommufd_vevent_header followed by
+ * a type-specific data structure, in a normal case:
+ *
+ * +-+---------+-------+---------+-------+-----+---------+-------+-+
+ * | | header0 | data0 | header1 | data1 | ... | headerN | dataN | |
+ * +-+---------+-------+---------+-------+-----+---------+-------+-+
+ *
+ * unless a tailing IOMMU_VEVENTQ_FLAG_LOST_EVENTS header is logged (refer to
+ * struct iommufd_vevent_header).
+ */
+struct iommu_veventq_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 viommu_id;
+ __u32 type;
+ __u32 veventq_depth;
+ __u32 out_veventq_id;
+ __u32 out_veventq_fd;
+ __u32 __reserved;
+};
+#define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC)
#endif
--git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 27181b3dd8fb2aa81e859ff052a9d5df35c15938..e5f3e8b5a02a8e07dc3edb206d1873ed8cfb474b 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -921,6 +921,7 @@ struct kvm_enable_cap {
#define KVM_CAP_PRE_FAULT_MEMORY 236
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
+#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
struct kvm_irq_routing_irqchip {
__u32 irqchip;
--git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h
index 17bf19157329de9be248954d4279c557b586dcb6..113c4ceb78407ed46e8863ac2f3e108266eefd3c 100644
--- a/linux-headers/linux/psp-sev.h
+++ b/linux-headers/linux/psp-sev.h
@@ -73,13 +73,20 @@ typedef enum {
SEV_RET_INVALID_PARAM,
SEV_RET_RESOURCE_LIMIT,
SEV_RET_SECURE_DATA_INVALID,
- SEV_RET_INVALID_KEY = 0x27,
- SEV_RET_INVALID_PAGE_SIZE,
- SEV_RET_INVALID_PAGE_STATE,
- SEV_RET_INVALID_MDATA_ENTRY,
- SEV_RET_INVALID_PAGE_OWNER,
- SEV_RET_INVALID_PAGE_AEAD_OFLOW,
- SEV_RET_RMP_INIT_REQUIRED,
+ SEV_RET_INVALID_PAGE_SIZE = 0x0019,
+ SEV_RET_INVALID_PAGE_STATE = 0x001A,
+ SEV_RET_INVALID_MDATA_ENTRY = 0x001B,
+ SEV_RET_INVALID_PAGE_OWNER = 0x001C,
+ SEV_RET_AEAD_OFLOW = 0x001D,
+ SEV_RET_EXIT_RING_BUFFER = 0x001F,
+ SEV_RET_RMP_INIT_REQUIRED = 0x0020,
+ SEV_RET_BAD_SVN = 0x0021,
+ SEV_RET_BAD_VERSION = 0x0022,
+ SEV_RET_SHUTDOWN_REQUIRED = 0x0023,
+ SEV_RET_UPDATE_FAILED = 0x0024,
+ SEV_RET_RESTORE_REQUIRED = 0x0025,
+ SEV_RET_RMP_INITIALIZATION_FAILED = 0x0026,
+ SEV_RET_INVALID_KEY = 0x0027,
SEV_RET_MAX,
} sev_ret_code;
--git a/linux-headers/linux/stddef.h b/linux-headers/linux/stddef.h
index e1416f793738f56beb5b47447f1c422eb103da72..e1fcfcf3b33261939797d79f4e29a28fa1da6e10 100644
--- a/linux-headers/linux/stddef.h
+++ b/linux-headers/linux/stddef.h
@@ -70,4 +70,6 @@
#define __counted_by_be(m)
#endif
+#define __kernel_nonstring
+
#endif /* _LINUX_STDDEF_H */
--git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 1b5e254d6a7d77a6baff58c55bc3bf4f12387159..79bf8c0cc5e405bcbca1e92c82468ce39665ab5f 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -671,6 +671,7 @@ enum {
*/
enum {
VFIO_AP_REQ_IRQ_INDEX,
+ VFIO_AP_CFG_CHG_IRQ_INDEX,
VFIO_AP_NUM_IRQS
};
@@ -931,29 +932,34 @@ struct vfio_device_bind_iommufd {
* VFIO_DEVICE_ATTACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 19,
* struct vfio_device_attach_iommufd_pt)
* @argsz: User filled size of this data.
- * @flags: Must be 0.
+ * @flags: Flags for attach.
* @pt_id: Input the target id which can represent an ioas or a hwpt
* allocated via iommufd subsystem.
* Output the input ioas id or the attached hwpt id which could
* be the specified hwpt itself or a hwpt automatically created
* for the specified ioas by kernel during the attachment.
+ * @pasid: The pasid to be attached, only meaningful when
+ * VFIO_DEVICE_ATTACH_PASID is set in @flags
*
* Associate the device with an address space within the bound iommufd.
* Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close. This is only
* allowed on cdev fds.
*
- * If a vfio device is currently attached to a valid hw_pagetable, without doing
- * a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl
- * passing in another hw_pagetable (hwpt) id is allowed. This action, also known
- * as a hw_pagetable replacement, will replace the device's currently attached
- * hw_pagetable with a new hw_pagetable corresponding to the given pt_id.
+ * If a vfio device or a pasid of this device is currently attached to a valid
+ * hw_pagetable (hwpt), without doing a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second
+ * VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl passing in another hwpt id is allowed.
+ * This action, also known as a hw_pagetable replacement, will replace the
+ * currently attached hwpt of the device or the pasid of this device with a new
+ * hwpt corresponding to the given pt_id.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_attach_iommufd_pt {
__u32 argsz;
__u32 flags;
+#define VFIO_DEVICE_ATTACH_PASID (1 << 0)
__u32 pt_id;
+ __u32 pasid;
};
#define VFIO_DEVICE_ATTACH_IOMMUFD_PT _IO(VFIO_TYPE, VFIO_BASE + 19)
@@ -962,17 +968,21 @@ struct vfio_device_attach_iommufd_pt {
* VFIO_DEVICE_DETACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 20,
* struct vfio_device_detach_iommufd_pt)
* @argsz: User filled size of this data.
- * @flags: Must be 0.
+ * @flags: Flags for detach.
+ * @pasid: The pasid to be detached, only meaningful when
+ * VFIO_DEVICE_DETACH_PASID is set in @flags
*
- * Remove the association of the device and its current associated address
- * space. After it, the device should be in a blocking DMA state. This is only
- * allowed on cdev fds.
+ * Remove the association of the device or a pasid of the device and its current
+ * associated address space. After it, the device or the pasid should be in a
+ * blocking DMA state. This is only allowed on cdev fds.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_detach_iommufd_pt {
__u32 argsz;
__u32 flags;
+#define VFIO_DEVICE_DETACH_PASID (1 << 0)
+ __u32 pasid;
};
#define VFIO_DEVICE_DETACH_IOMMUFD_PT _IO(VFIO_TYPE, VFIO_BASE + 20)
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 15/28] vfio: add vfio_device_prepare()
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (13 preceding siblings ...)
2025-05-09 13:13 ` [PULL 14/28] linux-headers: Update to Linux v6.15-rc3 Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 16/28] vfio: add vfio_device_unprepare() Cédric Le Goater
` (13 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Commonize some initialization code shared by the legacy and iommufd vfio
implementations.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-2-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 3 +++
hw/vfio/container.c | 14 ++------------
hw/vfio/device.c | 14 ++++++++++++++
hw/vfio/iommufd.c | 9 +--------
4 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 81c95bb51eeead0e8c4d126c2d0561e235632946..081929ca4b9bc59217c633421fcbe84ea4171aa7 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -134,6 +134,9 @@ typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
extern VFIODeviceList vfio_device_list;
#ifdef CONFIG_LINUX
+void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
+ struct vfio_device_info *info);
+
int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info);
int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index a761f0958b71de39093d8849b49c55e3662e096f..d30c1a141d34d8b026876e4a289c08ba067ef8a7 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -826,18 +826,14 @@ static bool vfio_device_get(VFIOGroup *group, const char *name,
}
}
+ vfio_device_prepare(vbasedev, &group->container->bcontainer, info);
+
vbasedev->fd = fd;
vbasedev->group = group;
QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
- vbasedev->num_irqs = info->num_irqs;
- vbasedev->num_regions = info->num_regions;
- vbasedev->flags = info->flags;
-
trace_vfio_device_get(name, info->flags, info->num_regions, info->num_irqs);
- vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
-
return true;
}
@@ -890,7 +886,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
int groupid = vfio_device_get_groupid(vbasedev, errp);
VFIODevice *vbasedev_iter;
VFIOGroup *group;
- VFIOContainerBase *bcontainer;
if (groupid < 0) {
return false;
@@ -919,11 +914,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
goto device_put_exit;
}
- bcontainer = &group->container->bcontainer;
- vbasedev->bcontainer = bcontainer;
- QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
- QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
-
return true;
device_put_exit:
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index d625a7c4dbbf4ac222541283c4034e840da02b08..f3b9902d21cdb4443ffd603b1b3f8ad5950996fc 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -398,3 +398,17 @@ void vfio_device_detach(VFIODevice *vbasedev)
}
VFIO_IOMMU_GET_CLASS(vbasedev->bcontainer)->detach_device(vbasedev);
}
+
+void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
+ struct vfio_device_info *info)
+{
+ vbasedev->num_irqs = info->num_irqs;
+ vbasedev->num_regions = info->num_regions;
+ vbasedev->flags = info->flags;
+ vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
+
+ vbasedev->bcontainer = bcontainer;
+ QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
+
+ QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 232c06dd15ba922b9ac4adbb96ec04e2e56a4072..83033c352a7d8d868aea52b2bdfcdcbbb6914bff 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -588,14 +588,7 @@ found_container:
iommufd_cdev_ram_block_discard_disable(false);
}
- vbasedev->group = 0;
- vbasedev->num_irqs = dev_info.num_irqs;
- vbasedev->num_regions = dev_info.num_regions;
- vbasedev->flags = dev_info.flags;
- vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
- vbasedev->bcontainer = bcontainer;
- QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
- QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+ vfio_device_prepare(vbasedev, bcontainer, &dev_info);
trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
vbasedev->num_regions, vbasedev->flags);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 16/28] vfio: add vfio_device_unprepare()
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (14 preceding siblings ...)
2025-05-09 13:13 ` [PULL 15/28] vfio: add vfio_device_prepare() Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 17/28] vfio: add vfio_attach_device_by_iommu_type() Cédric Le Goater
` (12 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Add a helper that's the inverse of vfio_device_prepare().
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-3-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 2 ++
hw/vfio/container.c | 6 +++---
hw/vfio/device.c | 7 +++++++
hw/vfio/iommufd.c | 4 +---
4 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 081929ca4b9bc59217c633421fcbe84ea4171aa7..342c4ba3bfec8d143a297203dbfa0e6f6fae3535 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -137,6 +137,8 @@ extern VFIODeviceList vfio_device_list;
void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
struct vfio_device_info *info);
+void vfio_device_unprepare(VFIODevice *vbasedev);
+
int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info);
int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index d30c1a141d34d8b026876e4a289c08ba067ef8a7..cf23aa799f61da58da09411ca6213a753a7f4794 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -927,10 +927,10 @@ static void vfio_legacy_detach_device(VFIODevice *vbasedev)
{
VFIOGroup *group = vbasedev->group;
- QLIST_REMOVE(vbasedev, global_next);
- QLIST_REMOVE(vbasedev, container_next);
- vbasedev->bcontainer = NULL;
trace_vfio_device_detach(vbasedev->name, group->groupid);
+
+ vfio_device_unprepare(vbasedev);
+
object_unref(vbasedev->hiod);
vfio_device_put(vbasedev);
vfio_group_put(group);
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index f3b9902d21cdb4443ffd603b1b3f8ad5950996fc..31c441a3dfffdf459994407904ab78b1798bf979 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -412,3 +412,10 @@ void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
}
+
+void vfio_device_unprepare(VFIODevice *vbasedev)
+{
+ QLIST_REMOVE(vbasedev, container_next);
+ QLIST_REMOVE(vbasedev, global_next);
+ vbasedev->bcontainer = NULL;
+}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 83033c352a7d8d868aea52b2bdfcdcbbb6914bff..62ecb758f1ade0e39efaef2b4001dab91abaa001 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -615,9 +615,7 @@ static void iommufd_cdev_detach(VFIODevice *vbasedev)
VFIOIOMMUFDContainer *container = container_of(bcontainer,
VFIOIOMMUFDContainer,
bcontainer);
- QLIST_REMOVE(vbasedev, global_next);
- QLIST_REMOVE(vbasedev, container_next);
- vbasedev->bcontainer = NULL;
+ vfio_device_unprepare(vbasedev);
if (!vbasedev->ram_block_discard_allowed) {
iommufd_cdev_ram_block_discard_disable(false);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 17/28] vfio: add vfio_attach_device_by_iommu_type()
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (15 preceding siblings ...)
2025-05-09 13:13 ` [PULL 16/28] vfio: add vfio_device_unprepare() Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 18/28] vfio: add vfio_device_get_irq_info() helper Cédric Le Goater
` (11 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Allow attachment by explicitly passing a TYPE_VFIO_IOMMU_* string;
vfio-user will use this later.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-4-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 3 +++
hw/vfio/device.c | 22 +++++++++++++++-------
2 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 342c4ba3bfec8d143a297203dbfa0e6f6fae3535..8b1437ba6654d08f65740f42dc3a50775d7f5cc1 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -127,6 +127,9 @@ bool vfio_device_hiod_create_and_realize(VFIODevice *vbasedev,
const char *typename, Error **errp);
bool vfio_device_attach(char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
+bool vfio_device_attach_by_iommu_type(const char *iommu_type, char *name,
+ VFIODevice *vbasedev, AddressSpace *as,
+ Error **errp);
void vfio_device_detach(VFIODevice *vbasedev);
VFIODevice *vfio_get_vfio_device(Object *obj);
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 31c441a3dfffdf459994407904ab78b1798bf979..9673b0717ead435e117d8084720fde4ba3a13dd8 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -376,21 +376,29 @@ VFIODevice *vfio_get_vfio_device(Object *obj)
}
}
-bool vfio_device_attach(char *name, VFIODevice *vbasedev,
- AddressSpace *as, Error **errp)
+bool vfio_device_attach_by_iommu_type(const char *iommu_type, char *name,
+ VFIODevice *vbasedev, AddressSpace *as,
+ Error **errp)
{
const VFIOIOMMUClass *ops =
- VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_LEGACY));
-
- if (vbasedev->iommufd) {
- ops = VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
- }
+ VFIO_IOMMU_CLASS(object_class_by_name(iommu_type));
assert(ops);
return ops->attach_device(name, vbasedev, as, errp);
}
+bool vfio_device_attach(char *name, VFIODevice *vbasedev,
+ AddressSpace *as, Error **errp)
+{
+ const char *iommu_type = vbasedev->iommufd ?
+ TYPE_VFIO_IOMMU_IOMMUFD :
+ TYPE_VFIO_IOMMU_LEGACY;
+
+ return vfio_device_attach_by_iommu_type(iommu_type, name, vbasedev,
+ as, errp);
+}
+
void vfio_device_detach(VFIODevice *vbasedev)
{
if (!vbasedev->bcontainer) {
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 18/28] vfio: add vfio_device_get_irq_info() helper
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (16 preceding siblings ...)
2025-05-09 13:13 ` [PULL 17/28] vfio: add vfio_attach_device_by_iommu_type() Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 19/28] vfio: consistently handle return value for helpers Cédric Le Goater
` (10 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Add a helper similar to vfio_device_get_region_info() and use it
everywhere.
Replace a couple of needless allocations with stack variables.
As a side-effect, this fixes a minor error reporting issue in the call
from vfio_msix_early_setup().
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-5-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 3 +++
hw/vfio/ap.c | 19 ++++++++++---------
hw/vfio/ccw.c | 20 +++++++++++---------
hw/vfio/device.c | 15 +++++++++++++++
hw/vfio/pci.c | 23 +++++++++++------------
hw/vfio/platform.c | 6 +++---
6 files changed, 53 insertions(+), 33 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 8b1437ba6654d08f65740f42dc3a50775d7f5cc1..a7eaaa31e7e98a1ec73eefde0d935842ef9da401 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -147,6 +147,9 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
uint32_t subtype, struct vfio_region_info **info);
bool vfio_device_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type);
+
+int vfio_device_get_irq_info(VFIODevice *vbasedev, int index,
+ struct vfio_irq_info *info);
#endif
/* Returns 0 on success, or a negative errno. */
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index 1207c08d8d94dc6b9004725f8e266c2ec4d04105..785c0a019754a436c59357cf957c4dc6f81ba578 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -74,10 +74,10 @@ static bool vfio_ap_register_irq_notifier(VFIOAPDevice *vapdev,
unsigned int irq, Error **errp)
{
int fd;
- size_t argsz;
+ int ret;
IOHandler *fd_read;
EventNotifier *notifier;
- g_autofree struct vfio_irq_info *irq_info = NULL;
+ struct vfio_irq_info irq_info;
VFIODevice *vdev = &vapdev->vdev;
switch (irq) {
@@ -96,14 +96,15 @@ static bool vfio_ap_register_irq_notifier(VFIOAPDevice *vapdev,
return false;
}
- argsz = sizeof(*irq_info);
- irq_info = g_malloc0(argsz);
- irq_info->index = irq;
- irq_info->argsz = argsz;
+ ret = vfio_device_get_irq_info(vdev, irq, &irq_info);
+
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "vfio: Error getting irq info");
+ return false;
+ }
- if (ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO,
- irq_info) < 0 || irq_info->count < 1) {
- error_setg_errno(errp, errno, "vfio: Error getting irq info");
+ if (irq_info.count < 1) {
+ error_setg(errp, "vfio: Error getting irq info, count=0");
return false;
}
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index fde0c3fbef3ca2204381c8ee6d07b502d2160e63..ab3fabf991c35abb6c40d925f526c2a2d8955aef 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -376,8 +376,8 @@ static bool vfio_ccw_register_irq_notifier(VFIOCCWDevice *vcdev,
Error **errp)
{
VFIODevice *vdev = &vcdev->vdev;
- g_autofree struct vfio_irq_info *irq_info = NULL;
- size_t argsz;
+ struct vfio_irq_info irq_info;
+ int ret;
int fd;
EventNotifier *notifier;
IOHandler *fd_read;
@@ -406,13 +406,15 @@ static bool vfio_ccw_register_irq_notifier(VFIOCCWDevice *vcdev,
return false;
}
- argsz = sizeof(*irq_info);
- irq_info = g_malloc0(argsz);
- irq_info->index = irq;
- irq_info->argsz = argsz;
- if (ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO,
- irq_info) < 0 || irq_info->count < 1) {
- error_setg_errno(errp, errno, "vfio: Error getting irq info");
+ ret = vfio_device_get_irq_info(vdev, irq, &irq_info);
+
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "vfio: Error getting irq info");
+ return false;
+ }
+
+ if (irq_info.count < 1) {
+ error_setg(errp, "vfio: Error getting irq info, count=0");
return false;
}
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 9673b0717ead435e117d8084720fde4ba3a13dd8..5d837092cba2c35ad17d93dd5c3627d83defc818 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -185,6 +185,21 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
return false;
}
+int vfio_device_get_irq_info(VFIODevice *vbasedev, int index,
+ struct vfio_irq_info *info)
+{
+ int ret;
+
+ memset(info, 0, sizeof(*info));
+
+ info->argsz = sizeof(*info);
+ info->index = index;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
+
+ return ret < 0 ? -errno : ret;
+}
+
int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info)
{
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index e1fab21b47adb4df9b011b3efb6d7c15c84bc8c2..5ccfc67aef6e1653dcf47c88d53265072c7a95c6 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1555,8 +1555,7 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
uint16_t ctrl;
uint32_t table, pba;
int ret, fd = vdev->vbasedev.fd;
- struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
- .index = VFIO_PCI_MSIX_IRQ_INDEX };
+ struct vfio_irq_info irq_info;
VFIOMSIXInfo *msix;
pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
@@ -1593,7 +1592,8 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ ret = vfio_device_get_irq_info(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX,
+ &irq_info);
if (ret < 0) {
error_setg_errno(errp, -ret, "failed to get MSI-X irq info");
g_free(msix);
@@ -2736,7 +2736,7 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
g_autofree struct vfio_region_info *reg_info = NULL;
- struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
+ struct vfio_irq_info irq_info;
int i, ret = -1;
/* Sanity check device */
@@ -2797,12 +2797,10 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
}
}
- irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
-
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ ret = vfio_device_get_irq_info(vbasedev, VFIO_PCI_ERR_IRQ_INDEX, &irq_info);
if (ret) {
/* This can fail for an old kernel or legacy PCI dev */
- trace_vfio_populate_device_get_irq_info_failure(strerror(errno));
+ trace_vfio_populate_device_get_irq_info_failure(strerror(-ret));
} else if (irq_info.count == 1) {
vdev->pci_aer = true;
} else {
@@ -2911,17 +2909,18 @@ static void vfio_req_notifier_handler(void *opaque)
static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
{
- struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
- .index = VFIO_PCI_REQ_IRQ_INDEX };
+ struct vfio_irq_info irq_info;
Error *err = NULL;
int32_t fd;
+ int ret;
if (!(vdev->features & VFIO_FEATURE_ENABLE_REQ)) {
return;
}
- if (ioctl(vdev->vbasedev.fd,
- VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) {
+ ret = vfio_device_get_irq_info(&vdev->vbasedev, VFIO_PCI_REQ_IRQ_INDEX,
+ &irq_info);
+ if (ret < 0 || irq_info.count < 1) {
return;
}
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index ffb3681607e2816ff0c07e2b5cfd255b46500b10..9a21f2e50a2945a6658b9be4fdec1bc1c98d0f20 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -474,10 +474,10 @@ static bool vfio_populate_device(VFIODevice *vbasedev, Error **errp)
QSIMPLEQ_INIT(&vdev->pending_intp_queue);
for (i = 0; i < vbasedev->num_irqs; i++) {
- struct vfio_irq_info irq = { .argsz = sizeof(irq) };
+ struct vfio_irq_info irq;
+
+ ret = vfio_device_get_irq_info(vbasedev, i, &irq);
- irq.index = i;
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq);
if (ret) {
error_setg_errno(errp, -ret, "failed to get device irq info");
goto irq_err;
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 19/28] vfio: consistently handle return value for helpers
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (17 preceding siblings ...)
2025-05-09 13:13 ` [PULL 18/28] vfio: add vfio_device_get_irq_info() helper Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 20/28] vfio: add strread/writeerror() Cédric Le Goater
` (9 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Various bits of code that call vfio device APIs should consistently use
the "return -errno" approach for passing errors back, rather than
presuming errno is (still) set correctly.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-6-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/pci.c | 33 ++++++++++++++++++++-------------
1 file changed, 20 insertions(+), 13 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 5ccfc67aef6e1653dcf47c88d53265072c7a95c6..866cf58d04600cdd5394a52e0ebe9dd7bb41a1c6 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -398,7 +398,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
- return ret;
+ return ret < 0 ? -errno : ret;
}
static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
@@ -459,7 +459,7 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
g_free(irq_set);
- return ret;
+ return ret < 0 ? -errno : ret;
}
static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,
@@ -581,7 +581,8 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
vfio_device_irq_disable(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
ret = vfio_enable_vectors(vdev, true);
if (ret) {
- error_report("vfio: failed to enable vectors, %d", ret);
+ error_report("vfio: failed to enable vectors, %s",
+ strerror(-ret));
}
} else {
Error *err = NULL;
@@ -695,7 +696,8 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
if (vdev->nr_vectors) {
ret = vfio_enable_vectors(vdev, true);
if (ret) {
- error_report("vfio: failed to enable vectors, %d", ret);
+ error_report("vfio: failed to enable vectors, %s",
+ strerror(-ret));
}
} else {
/*
@@ -712,7 +714,8 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
*/
ret = vfio_enable_msix_no_vec(vdev);
if (ret) {
- error_report("vfio: failed to enable MSI-X, %d", ret);
+ error_report("vfio: failed to enable MSI-X, %s",
+ strerror(-ret));
}
}
@@ -765,7 +768,8 @@ retry:
ret = vfio_enable_vectors(vdev, false);
if (ret) {
if (ret < 0) {
- error_report("vfio: Error: Failed to setup MSI fds: %m");
+ error_report("vfio: Error: Failed to setup MSI fds: %s",
+ strerror(-ret));
} else {
error_report("vfio: Error: Failed to enable %d "
"MSI vectors, retry with %d", vdev->nr_vectors, ret);
@@ -882,17 +886,21 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
{
g_autofree struct vfio_region_info *reg_info = NULL;
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint64_t size;
off_t off = 0;
ssize_t bytes;
+ int ret;
+
+ ret = vfio_device_get_region_info(vbasedev, VFIO_PCI_ROM_REGION_INDEX,
+ ®_info);
- if (vfio_device_get_region_info(&vdev->vbasedev,
- VFIO_PCI_ROM_REGION_INDEX, ®_info)) {
- error_report("vfio: Error getting ROM info: %m");
+ if (ret != 0) {
+ error_report("vfio: Error getting ROM info: %s", strerror(-ret));
return;
}
- trace_vfio_pci_load_rom(vdev->vbasedev.name, (unsigned long)reg_info->size,
+ trace_vfio_pci_load_rom(vbasedev->name, (unsigned long)reg_info->size,
(unsigned long)reg_info->offset,
(unsigned long)reg_info->flags);
@@ -901,8 +909,7 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
if (!vdev->rom_size) {
vdev->rom_read_failed = true;
- error_report("vfio-pci: Cannot read device rom at "
- "%s", vdev->vbasedev.name);
+ error_report("vfio-pci: Cannot read device rom at %s", vbasedev->name);
error_printf("Device option ROM contents are probably invalid "
"(check dmesg).\nSkip option ROM probe with rombar=0, "
"or load from file with romfile=\n");
@@ -913,7 +920,7 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
memset(vdev->rom, 0xff, size);
while (size) {
- bytes = pread(vdev->vbasedev.fd, vdev->rom + off,
+ bytes = pread(vbasedev->fd, vdev->rom + off,
size, vdev->rom_offset + off);
if (bytes == 0) {
break;
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 20/28] vfio: add strread/writeerror()
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (18 preceding siblings ...)
2025-05-09 13:13 ` [PULL 19/28] vfio: consistently handle return value for helpers Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 21/28] vfio: add vfio_pci_config_space_read/write() Cédric Le Goater
` (8 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Add simple helpers to correctly report failures from read/write routines
using the return -errno style.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-7-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index a7eaaa31e7e98a1ec73eefde0d935842ef9da401..4a3220294309d718bb3230a5d3f4bab9e082f951 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -115,6 +115,20 @@ struct VFIODeviceOps {
int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
};
+/*
+ * Given a return value of either a short number of bytes read or -errno,
+ * construct a meaningful error message.
+ */
+#define strreaderror(ret) \
+ (ret < 0 ? strerror(-ret) : "short read")
+
+/*
+ * Given a return value of either a short number of bytes written or -errno,
+ * construct a meaningful error message.
+ */
+#define strwriteerror(ret) \
+ (ret < 0 ? strerror(-ret) : "short write")
+
void vfio_device_irq_disable(VFIODevice *vbasedev, int index);
void vfio_device_irq_unmask(VFIODevice *vbasedev, int index);
void vfio_device_irq_mask(VFIODevice *vbasedev, int index);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 21/28] vfio: add vfio_pci_config_space_read/write()
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (19 preceding siblings ...)
2025-05-09 13:13 ` [PULL 20/28] vfio: add strread/writeerror() Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 22/28] vfio: add unmap_all flag to DMA unmap callback Cédric Le Goater
` (7 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Add these helpers that access config space and return an -errno style
return.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-8-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/pci.c | 123 ++++++++++++++++++++++++++++++++------------------
1 file changed, 80 insertions(+), 43 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 866cf58d04600cdd5394a52e0ebe9dd7bb41a1c6..f65c9463ce0350e6a1962309da21e96d1aa6cfdd 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -967,6 +967,28 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
}
}
+/* "Raw" read of underlying config space. */
+static int vfio_pci_config_space_read(VFIOPCIDevice *vdev, off_t offset,
+ uint32_t size, void *data)
+{
+ ssize_t ret;
+
+ ret = pread(vdev->vbasedev.fd, data, size, vdev->config_offset + offset);
+
+ return ret < 0 ? -errno : (int)ret;
+}
+
+/* "Raw" write of underlying config space. */
+static int vfio_pci_config_space_write(VFIOPCIDevice *vdev, off_t offset,
+ uint32_t size, void *data)
+{
+ ssize_t ret;
+
+ ret = pwrite(vdev->vbasedev.fd, data, size, vdev->config_offset + offset);
+
+ return ret < 0 ? -errno : (int)ret;
+}
+
static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size)
{
VFIOPCIDevice *vdev = opaque;
@@ -1019,10 +1041,9 @@ static const MemoryRegionOps vfio_rom_ops = {
static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
- off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
char *name;
- int fd = vdev->vbasedev.fd;
if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
/* Since pci handles romfile, just print a message and return */
@@ -1039,11 +1060,12 @@ static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
* Use the same size ROM BAR as the physical device. The contents
* will get filled in later when the guest tries to read it.
*/
- if (pread(fd, &orig, 4, offset) != 4 ||
- pwrite(fd, &size, 4, offset) != 4 ||
- pread(fd, &size, 4, offset) != 4 ||
- pwrite(fd, &orig, 4, offset) != 4) {
- error_report("%s(%s) failed: %m", __func__, vdev->vbasedev.name);
+ if (vfio_pci_config_space_read(vdev, PCI_ROM_ADDRESS, 4, &orig) != 4 ||
+ vfio_pci_config_space_write(vdev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
+ vfio_pci_config_space_read(vdev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
+ vfio_pci_config_space_write(vdev, PCI_ROM_ADDRESS, 4, &orig) != 4) {
+
+ error_report("%s(%s) ROM access failed", __func__, vbasedev->name);
return;
}
@@ -1223,6 +1245,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
@@ -1235,12 +1258,12 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
if (~emu_bits & (0xffffffffU >> (32 - len * 8))) {
ssize_t ret;
- ret = pread(vdev->vbasedev.fd, &phys_val, len,
- vdev->config_offset + addr);
+ ret = vfio_pci_config_space_read(vdev, addr, len, &phys_val);
if (ret != len) {
- error_report("%s(%s, 0x%x, 0x%x) failed: %m",
- __func__, vdev->vbasedev.name, addr, len);
- return -errno;
+ error_report("%s(%s, 0x%x, 0x%x) failed: %s",
+ __func__, vbasedev->name, addr, len,
+ strreaderror(ret));
+ return -1;
}
phys_val = le32_to_cpu(phys_val);
}
@@ -1256,15 +1279,18 @@ void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t val_le = cpu_to_le32(val);
+ int ret;
trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
/* Write everything to VFIO, let it filter out what we can't write */
- if (pwrite(vdev->vbasedev.fd, &val_le, len, vdev->config_offset + addr)
- != len) {
- error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %m",
- __func__, vdev->vbasedev.name, addr, val, len);
+ ret = vfio_pci_config_space_write(vdev, addr, len, &val_le);
+ if (ret != len) {
+ error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %s",
+ __func__, vbasedev->name, addr, val, len,
+ strwriteerror(ret));
}
/* MSI/MSI-X Enabling/Disabling */
@@ -1352,9 +1378,11 @@ static bool vfio_msi_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
int ret, entries;
Error *err = NULL;
- if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl),
- vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
- error_setg_errno(errp, errno, "failed reading MSI PCI_CAP_FLAGS");
+ ret = vfio_pci_config_space_read(vdev, pos + PCI_CAP_FLAGS,
+ sizeof(ctrl), &ctrl);
+ if (ret != sizeof(ctrl)) {
+ error_setg(errp, "failed reading MSI PCI_CAP_FLAGS: %s",
+ strreaderror(ret));
return false;
}
ctrl = le16_to_cpu(ctrl);
@@ -1561,30 +1589,35 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
uint8_t pos;
uint16_t ctrl;
uint32_t table, pba;
- int ret, fd = vdev->vbasedev.fd;
struct vfio_irq_info irq_info;
VFIOMSIXInfo *msix;
+ int ret;
pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
if (!pos) {
return true;
}
- if (pread(fd, &ctrl, sizeof(ctrl),
- vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX FLAGS");
+ ret = vfio_pci_config_space_read(vdev, pos + PCI_MSIX_FLAGS,
+ sizeof(ctrl), &ctrl);
+ if (ret != sizeof(ctrl)) {
+ error_setg(errp, "failed to read PCI MSIX FLAGS: %s",
+ strreaderror(ret));
return false;
}
- if (pread(fd, &table, sizeof(table),
- vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX TABLE");
+ ret = vfio_pci_config_space_read(vdev, pos + PCI_MSIX_TABLE,
+ sizeof(table), &table);
+ if (ret != sizeof(table)) {
+ error_setg(errp, "failed to read PCI MSIX TABLE: %s",
+ strreaderror(ret));
return false;
}
- if (pread(fd, &pba, sizeof(pba),
- vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX PBA");
+ ret = vfio_pci_config_space_read(vdev, pos + PCI_MSIX_PBA,
+ sizeof(pba), &pba);
+ if (ret != sizeof(pba)) {
+ error_setg(errp, "failed to read PCI MSIX PBA: %s", strreaderror(ret));
return false;
}
@@ -1744,10 +1777,10 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
}
/* Determine what type of BAR this is for registration */
- ret = pread(vdev->vbasedev.fd, &pci_bar, sizeof(pci_bar),
- vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr));
+ ret = vfio_pci_config_space_read(vdev, PCI_BASE_ADDRESS_0 + (4 * nr),
+ sizeof(pci_bar), &pci_bar);
if (ret != sizeof(pci_bar)) {
- error_report("vfio: Failed to read BAR %d (%m)", nr);
+ error_report("vfio: Failed to read BAR %d: %s", nr, strreaderror(ret));
return;
}
@@ -2450,21 +2483,23 @@ void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
void vfio_pci_post_reset(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
Error *err = NULL;
- int nr;
+ int ret, nr;
if (!vfio_intx_enable(vdev, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) {
- off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr);
+ off_t addr = PCI_BASE_ADDRESS_0 + (4 * nr);
uint32_t val = 0;
uint32_t len = sizeof(val);
- if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) {
- error_report("%s(%s) reset bar %d failed: %m", __func__,
- vdev->vbasedev.name, nr);
+ ret = vfio_pci_config_space_write(vdev, addr, len, &val);
+ if (ret != len) {
+ error_report("%s(%s) reset bar %d failed: %s", __func__,
+ vbasedev->name, nr, strwriteerror(ret));
}
}
@@ -3101,6 +3136,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
int i, ret;
char uuid[UUID_STR_LEN];
g_autofree char *name = NULL;
+ uint32_t config_space_size;
if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
@@ -3155,13 +3191,14 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
goto error;
}
+ config_space_size = MIN(pci_config_size(&vdev->pdev), vdev->config_size);
+
/* Get a copy of config space */
- ret = pread(vbasedev->fd, vdev->pdev.config,
- MIN(pci_config_size(&vdev->pdev), vdev->config_size),
- vdev->config_offset);
- if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) {
- ret = ret < 0 ? -errno : -EFAULT;
- error_setg_errno(errp, -ret, "failed to read device config space");
+ ret = vfio_pci_config_space_read(vdev, 0, config_space_size,
+ vdev->pdev.config);
+ if (ret < (int)config_space_size) {
+ ret = ret < 0 ? -ret : EFAULT;
+ error_setg_errno(errp, ret, "failed to read device config space");
goto error;
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 22/28] vfio: add unmap_all flag to DMA unmap callback
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (20 preceding siblings ...)
2025-05-09 13:13 ` [PULL 21/28] vfio: add vfio_pci_config_space_read/write() Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 23/28] vfio: implement unmap all for DMA unmap callbacks Cédric Le Goater
` (6 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
We'll use this parameter shortly; this just adds the plumbing.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-9-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-container-base.h | 15 +++++++++++++--
hw/vfio/container-base.c | 4 ++--
hw/vfio/container.c | 8 ++++++--
hw/vfio/iommufd.c | 6 +++++-
hw/vfio/listener.c | 8 ++++----
5 files changed, 30 insertions(+), 11 deletions(-)
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 5527e027220ac05f82d2a9beaf8b921e26597271..59f07d26e8226916c9c58eac07cb494552097138 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -81,7 +81,7 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
void *vaddr, bool readonly);
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb);
+ IOMMUTLBEntry *iotlb, bool unmap_all);
bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
MemoryRegionSection *section,
Error **errp);
@@ -120,9 +120,20 @@ struct VFIOIOMMUClass {
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
void *vaddr, bool readonly);
+ /**
+ * @dma_unmap
+ *
+ * Unmap an address range from the container.
+ *
+ * @bcontainer: #VFIOContainerBase to use for unmap
+ * @iova: start address to unmap
+ * @size: size of the range to unmap
+ * @iotlb: The IOMMU TLB mapping entry (or NULL)
+ * @unmap_all: if set, unmap the entire address space
+ */
int (*dma_unmap)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb);
+ IOMMUTLBEntry *iotlb, bool unmap_all);
bool (*attach_device)(const char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
void (*detach_device)(VFIODevice *vbasedev);
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 09340fd97a074c9a3b56c686e7a750530bed619f..3ff473a45c2db779a54f3d8e77079d4a1601eb36 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -85,12 +85,12 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, bool unmap_all)
{
VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
g_assert(vioc->dma_unmap);
- return vioc->dma_unmap(bcontainer, iova, size, iotlb);
+ return vioc->dma_unmap(bcontainer, iova, size, iotlb, unmap_all);
}
bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index cf23aa799f61da58da09411ca6213a753a7f4794..d5f4e66f1c4146c2eb6a2ce209c74c4d391c27ce 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -124,7 +124,7 @@ unmap_exit:
*/
static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, bool unmap_all)
{
const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
bcontainer);
@@ -138,6 +138,10 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
int ret;
Error *local_err = NULL;
+ if (unmap_all) {
+ return -ENOTSUP;
+ }
+
if (iotlb && vfio_container_dirty_tracking_is_started(bcontainer)) {
if (!vfio_container_devices_dirty_tracking_is_supported(bcontainer) &&
bcontainer->dirty_pages_supported) {
@@ -205,7 +209,7 @@ static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
*/
if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
(errno == EBUSY &&
- vfio_legacy_dma_unmap(bcontainer, iova, size, NULL) == 0 &&
+ vfio_legacy_dma_unmap(bcontainer, iova, size, NULL, false) == 0 &&
ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
return 0;
}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 62ecb758f1ade0e39efaef2b4001dab91abaa001..6b2764c044135b95c199b5df2f864156817fb6fc 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -46,11 +46,15 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, bool unmap_all)
{
const VFIOIOMMUFDContainer *container =
container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+ if (unmap_all) {
+ return -ENOTSUP;
+ }
+
/* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
return iommufd_backend_unmap_dma(container->be,
container->ioas_id, iova, size);
diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
index 6f77e18a7a2f9437d50976eeb9847f99bfe4a739..c5183700dbd859c9a66083f2cb6f74a75a01cc66 100644
--- a/hw/vfio/listener.c
+++ b/hw/vfio/listener.c
@@ -172,7 +172,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
}
} else {
ret = vfio_container_dma_unmap(bcontainer, iova,
- iotlb->addr_mask + 1, iotlb);
+ iotlb->addr_mask + 1, iotlb, false);
if (ret) {
error_setg(&local_err,
"vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
@@ -201,7 +201,7 @@ static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
int ret;
/* Unmap with a single call. */
- ret = vfio_container_dma_unmap(bcontainer, iova, size , NULL);
+ ret = vfio_container_dma_unmap(bcontainer, iova, size , NULL, false);
if (ret) {
error_report("%s: vfio_container_dma_unmap() failed: %s", __func__,
strerror(-ret));
@@ -638,7 +638,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
/* The unmap ioctl doesn't accept a full 64-bit span. */
llsize = int128_rshift(llsize, 1);
ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL);
+ int128_get64(llsize), NULL, false);
if (ret) {
error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%s)",
@@ -648,7 +648,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
iova += int128_get64(llsize);
}
ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL);
+ int128_get64(llsize), NULL, false);
if (ret) {
error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%s)",
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 23/28] vfio: implement unmap all for DMA unmap callbacks
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (21 preceding siblings ...)
2025-05-09 13:13 ` [PULL 22/28] vfio: add unmap_all flag to DMA unmap callback Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 24/28] vfio: add device IO ops vector Cédric Le Goater
` (5 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Handle unmap_all in the DMA unmap handlers rather than in the caller.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-10-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/container.c | 41 +++++++++++++++++++++++++++++++----------
hw/vfio/iommufd.c | 15 ++++++++++++++-
hw/vfio/listener.c | 19 ++++++-------------
3 files changed, 51 insertions(+), 24 deletions(-)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index d5f4e66f1c4146c2eb6a2ce209c74c4d391c27ce..a9f0dbaec4c8d83450048d9bc53b34d859731ebb 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -119,12 +119,9 @@ unmap_exit:
return ret;
}
-/*
- * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
- */
-static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
- hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb, bool unmap_all)
+static int vfio_legacy_dma_unmap_one(const VFIOContainerBase *bcontainer,
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb)
{
const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
bcontainer);
@@ -138,10 +135,6 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
int ret;
Error *local_err = NULL;
- if (unmap_all) {
- return -ENOTSUP;
- }
-
if (iotlb && vfio_container_dirty_tracking_is_started(bcontainer)) {
if (!vfio_container_devices_dirty_tracking_is_supported(bcontainer) &&
bcontainer->dirty_pages_supported) {
@@ -185,6 +178,34 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
return 0;
}
+/*
+ * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
+ */
+static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb, bool unmap_all)
+{
+ int ret;
+
+ if (unmap_all) {
+ /* The unmap ioctl doesn't accept a full 64-bit span. */
+ Int128 llsize = int128_rshift(int128_2_64(), 1);
+
+ ret = vfio_legacy_dma_unmap_one(bcontainer, 0, int128_get64(llsize),
+ iotlb);
+
+ if (ret == 0) {
+ ret = vfio_legacy_dma_unmap_one(bcontainer, int128_get64(llsize),
+ int128_get64(llsize), iotlb);
+ }
+
+ } else {
+ ret = vfio_legacy_dma_unmap_one(bcontainer, iova, size, iotlb);
+ }
+
+ return ret;
+}
+
static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
ram_addr_t size, void *vaddr, bool readonly)
{
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 6b2764c044135b95c199b5df2f864156817fb6fc..af1c7ab10a090a2a4a2913231fc50903be9fb0f1 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -51,8 +51,21 @@ static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
const VFIOIOMMUFDContainer *container =
container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+ /* unmap in halves */
if (unmap_all) {
- return -ENOTSUP;
+ Int128 llsize = int128_rshift(int128_2_64(), 1);
+ int ret;
+
+ ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+ 0, int128_get64(llsize));
+
+ if (ret == 0) {
+ ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+ int128_get64(llsize),
+ int128_get64(llsize));
+ }
+
+ return ret;
}
/* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
index c5183700dbd859c9a66083f2cb6f74a75a01cc66..e7ade7d62ec81c9228e096ba4818a8dd09f54bd3 100644
--- a/hw/vfio/listener.c
+++ b/hw/vfio/listener.c
@@ -634,21 +634,14 @@ static void vfio_listener_region_del(MemoryListener *listener,
}
if (try_unmap) {
+ bool unmap_all = false;
+
if (int128_eq(llsize, int128_2_64())) {
- /* The unmap ioctl doesn't accept a full 64-bit span. */
- llsize = int128_rshift(llsize, 1);
- ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL, false);
- if (ret) {
- error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
- "0x%"HWADDR_PRIx") = %d (%s)",
- bcontainer, iova, int128_get64(llsize), ret,
- strerror(-ret));
- }
- iova += int128_get64(llsize);
+ unmap_all = true;
+ llsize = int128_zero();
}
- ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL, false);
+ ret = vfio_container_dma_unmap(bcontainer, iova, int128_get64(llsize),
+ NULL, unmap_all);
if (ret) {
error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%s)",
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 24/28] vfio: add device IO ops vector
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (22 preceding siblings ...)
2025-05-09 13:13 ` [PULL 23/28] vfio: implement unmap all for DMA unmap callbacks Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 25/28] vfio: add region info cache Cédric Le Goater
` (4 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, John Levon, John Johnson, Elena Ufimtseva,
Jagannathan Raman, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
For vfio-user, device operations such as IRQ handling and region
read/writes are implemented in userspace over the control socket, not
ioctl() to the vfio kernel driver; add an ops vector to generalize this,
and implement vfio_device_io_ops_ioctl for interacting with the kernel
vfio driver.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-11-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 38 ++++++++++++++++++
hw/vfio/container-base.c | 6 +--
hw/vfio/device.c | 74 +++++++++++++++++++++++++++++------
hw/vfio/listener.c | 13 +++---
hw/vfio/pci.c | 10 ++---
5 files changed, 114 insertions(+), 27 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 4a3220294309d718bb3230a5d3f4bab9e082f951..7e1e81e76bd2b484108282f7147ff7a0793360cf 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -41,6 +41,7 @@ enum {
};
typedef struct VFIODeviceOps VFIODeviceOps;
+typedef struct VFIODeviceIOOps VFIODeviceIOOps;
typedef struct VFIOMigration VFIOMigration;
typedef struct IOMMUFDBackend IOMMUFDBackend;
@@ -66,6 +67,7 @@ typedef struct VFIODevice {
OnOffAuto migration_multifd_transfer;
bool migration_events;
VFIODeviceOps *ops;
+ VFIODeviceIOOps *io_ops;
unsigned int num_irqs;
unsigned int num_regions;
unsigned int flags;
@@ -151,6 +153,42 @@ typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
extern VFIODeviceList vfio_device_list;
#ifdef CONFIG_LINUX
+/*
+ * How devices communicate with the server. The default option is through
+ * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote
+ * process.
+ */
+struct VFIODeviceIOOps {
+ /**
+ * @device_feature
+ *
+ * Fill in feature info for the given device.
+ */
+ int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
+
+ /**
+ * @get_region_info
+ *
+ * Fill in @info with information on the region given by @info->index.
+ */
+ int (*get_region_info)(VFIODevice *vdev,
+ struct vfio_region_info *info);
+
+ /**
+ * @get_irq_info
+ *
+ * Fill in @irq with information on the IRQ given by @info->index.
+ */
+ int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq);
+
+ /**
+ * @set_irqs
+ *
+ * Configure IRQs as defined by @irqs.
+ */
+ int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
+};
+
void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
struct vfio_device_info *info);
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 3ff473a45c2db779a54f3d8e77079d4a1601eb36..1c6ca94b6040813a63bb8fca07b25189a8d8cb76 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -198,11 +198,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
feature->flags = VFIO_DEVICE_FEATURE_GET |
VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
- return -errno;
- }
-
- return 0;
+ return vbasedev->io_ops->device_feature(vbasedev, feature);
}
static int vfio_container_iommu_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 5d837092cba2c35ad17d93dd5c3627d83defc818..40a196bfb9a86656610863d4f064db383c7072e0 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -82,7 +82,7 @@ void vfio_device_irq_disable(VFIODevice *vbasedev, int index)
.count = 0,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
}
void vfio_device_irq_unmask(VFIODevice *vbasedev, int index)
@@ -95,7 +95,7 @@ void vfio_device_irq_unmask(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
}
void vfio_device_irq_mask(VFIODevice *vbasedev, int index)
@@ -108,7 +108,7 @@ void vfio_device_irq_mask(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
}
static inline const char *action_to_str(int action)
@@ -167,7 +167,7 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
pfd = (int32_t *)&irq_set->data;
*pfd = fd;
- if (!ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
+ if (!vbasedev->io_ops->set_irqs(vbasedev, irq_set)) {
return true;
}
@@ -188,22 +188,19 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
int vfio_device_get_irq_info(VFIODevice *vbasedev, int index,
struct vfio_irq_info *info)
{
- int ret;
-
memset(info, 0, sizeof(*info));
info->argsz = sizeof(*info);
info->index = index;
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
-
- return ret < 0 ? -errno : ret;
+ return vbasedev->io_ops->get_irq_info(vbasedev, info);
}
int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info)
{
size_t argsz = sizeof(struct vfio_region_info);
+ int ret;
*info = g_malloc0(argsz);
@@ -211,10 +208,11 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
retry:
(*info)->argsz = argsz;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
+ ret = vbasedev->io_ops->get_region_info(vbasedev, *info);
+ if (ret != 0) {
g_free(*info);
*info = NULL;
- return -errno;
+ return ret;
}
if ((*info)->argsz > argsz) {
@@ -320,11 +318,14 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
vbasedev->fd = fd;
}
+static VFIODeviceIOOps vfio_device_io_ops_ioctl;
+
void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
DeviceState *dev, bool ram_discard)
{
vbasedev->type = type;
vbasedev->ops = ops;
+ vbasedev->io_ops = &vfio_device_io_ops_ioctl;
vbasedev->dev = dev;
vbasedev->fd = -1;
@@ -442,3 +443,54 @@ void vfio_device_unprepare(VFIODevice *vbasedev)
QLIST_REMOVE(vbasedev, global_next);
vbasedev->bcontainer = NULL;
}
+
+/*
+ * Traditional ioctl() based io
+ */
+
+static int vfio_device_io_device_feature(VFIODevice *vbasedev,
+ struct vfio_device_feature *feature)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_device_io_get_region_info(VFIODevice *vbasedev,
+ struct vfio_region_info *info)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_device_io_get_irq_info(VFIODevice *vbasedev,
+ struct vfio_irq_info *info)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_device_io_set_irqs(VFIODevice *vbasedev,
+ struct vfio_irq_set *irqs)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irqs);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static VFIODeviceIOOps vfio_device_io_ops_ioctl = {
+ .device_feature = vfio_device_io_device_feature,
+ .get_region_info = vfio_device_io_get_region_info,
+ .get_irq_info = vfio_device_io_get_irq_info,
+ .set_irqs = vfio_device_io_set_irqs,
+};
diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
index e7ade7d62ec81c9228e096ba4818a8dd09f54bd3..2b93ca55b6d47e4ef3e89bea681d6e345f8d3abe 100644
--- a/hw/vfio/listener.c
+++ b/hw/vfio/listener.c
@@ -794,13 +794,17 @@ static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP;
QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
+ int ret;
+
if (!vbasedev->dirty_tracking) {
continue;
}
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ ret = vbasedev->io_ops->device_feature(vbasedev, feature);
+
+ if (ret != 0) {
warn_report("%s: Failed to stop DMA logging, err %d (%s)",
- vbasedev->name, -errno, strerror(errno));
+ vbasedev->name, -ret, strerror(-ret));
}
vbasedev->dirty_tracking = false;
}
@@ -901,10 +905,9 @@ static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
continue;
}
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+ ret = vbasedev->io_ops->device_feature(vbasedev, feature);
if (ret) {
- ret = -errno;
- error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
+ error_setg_errno(errp, -ret, "%s: Failed to start DMA logging",
vbasedev->name);
goto out;
}
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index f65c9463ce0350e6a1962309da21e96d1aa6cfdd..da2ffc9bf36778fb61a7decf345391caee528b2a 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -381,7 +381,7 @@ static void vfio_msi_interrupt(void *opaque)
static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
{
g_autofree struct vfio_irq_set *irq_set = NULL;
- int ret = 0, argsz;
+ int argsz;
int32_t *fd;
argsz = sizeof(*irq_set) + sizeof(*fd);
@@ -396,9 +396,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
fd = (int32_t *)&irq_set->data;
*fd = -1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
-
- return ret < 0 ? -errno : ret;
+ return vdev->vbasedev.io_ops->set_irqs(&vdev->vbasedev, irq_set);
}
static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
@@ -455,11 +453,11 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
fds[i] = fd;
}
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+ ret = vdev->vbasedev.io_ops->set_irqs(&vdev->vbasedev, irq_set);
g_free(irq_set);
- return ret < 0 ? -errno : ret;
+ return ret;
}
static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 25/28] vfio: add region info cache
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (23 preceding siblings ...)
2025-05-09 13:13 ` [PULL 24/28] vfio: add device IO ops vector Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-10-14 13:16 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 26/28] vfio: add read/write to device IO ops vector Cédric Le Goater
` (3 subsequent siblings)
28 siblings, 1 reply; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, John Levon, John Johnson, Elena Ufimtseva,
Jagannathan Raman, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Instead of requesting region information on demand with
VFIO_DEVICE_GET_REGION_INFO, maintain a cache: this will become
necessary for performance for vfio-user, where this call becomes a
message over the control socket, so is of higher overhead than the
traditional path.
We will also need it to generalize region accesses, as that means we
can't use ->config_offset for configuration space accesses, but must
look up the region offset (if relevant) each time.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-12-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 1 +
hw/vfio/ccw.c | 5 -----
hw/vfio/device.c | 25 +++++++++++++++++++++----
hw/vfio/igd.c | 10 +++++-----
hw/vfio/pci.c | 6 +++---
hw/vfio/region.c | 2 +-
6 files changed, 31 insertions(+), 18 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 7e1e81e76bd2b484108282f7147ff7a0793360cf..4fff3dcee3b4a2a3c8a4bd6fa017cf822a16668e 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -83,6 +83,7 @@ typedef struct VFIODevice {
IOMMUFDBackend *iommufd;
VFIOIOASHwpt *hwpt;
QLIST_ENTRY(VFIODevice) hwpt_next;
+ struct vfio_region_info **reginfo;
} VFIODevice;
struct VFIODeviceOps {
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index ab3fabf991c35abb6c40d925f526c2a2d8955aef..cea9d6e00562c241832184cafe862005fcdc992b 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -504,7 +504,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
vcdev->io_region_offset = info->offset;
vcdev->io_region = g_malloc0(info->size);
- g_free(info);
/* check for the optional async command region */
ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
@@ -517,7 +516,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->async_cmd_region_offset = info->offset;
vcdev->async_cmd_region = g_malloc0(info->size);
- g_free(info);
}
ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
@@ -530,7 +528,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->schib_region_offset = info->offset;
vcdev->schib_region = g_malloc(info->size);
- g_free(info);
}
ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
@@ -544,7 +541,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->crw_region_offset = info->offset;
vcdev->crw_region = g_malloc(info->size);
- g_free(info);
}
return true;
@@ -554,7 +550,6 @@ out_err:
g_free(vcdev->schib_region);
g_free(vcdev->async_cmd_region);
g_free(vcdev->io_region);
- g_free(info);
return false;
}
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 40a196bfb9a86656610863d4f064db383c7072e0..77b0675abe7b4f4155ea79cf3fd0e3ab4b21f8ea 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -202,6 +202,12 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
size_t argsz = sizeof(struct vfio_region_info);
int ret;
+ /* check cache */
+ if (vbasedev->reginfo[index] != NULL) {
+ *info = vbasedev->reginfo[index];
+ return 0;
+ }
+
*info = g_malloc0(argsz);
(*info)->index = index;
@@ -222,6 +228,9 @@ retry:
goto retry;
}
+ /* fill cache */
+ vbasedev->reginfo[index] = *info;
+
return 0;
}
@@ -240,7 +249,6 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
if (!hdr) {
- g_free(*info);
continue;
}
@@ -252,8 +260,6 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
if (cap_type->type == type && cap_type->subtype == subtype) {
return 0;
}
-
- g_free(*info);
}
*info = NULL;
@@ -262,7 +268,7 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
bool vfio_device_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
{
- g_autofree struct vfio_region_info *info = NULL;
+ struct vfio_region_info *info = NULL;
bool ret = false;
if (!vfio_device_get_region_info(vbasedev, region, &info)) {
@@ -435,10 +441,21 @@ void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+
+ vbasedev->reginfo = g_new0(struct vfio_region_info *,
+ vbasedev->num_regions);
}
void vfio_device_unprepare(VFIODevice *vbasedev)
{
+ int i;
+
+ for (i = 0; i < vbasedev->num_regions; i++) {
+ g_free(vbasedev->reginfo[i]);
+ }
+ g_free(vbasedev->reginfo);
+ vbasedev->reginfo = NULL;
+
QLIST_REMOVE(vbasedev, container_next);
QLIST_REMOVE(vbasedev, global_next);
vbasedev->bcontainer = NULL;
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index 3ee1a73b57c57563f661a246e6dd7e505231be91..e7952d15a014f28fe302cab312ab8e60a414c679 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -349,8 +349,8 @@ static int vfio_pci_igd_lpc_init(VFIOPCIDevice *vdev,
static bool vfio_pci_igd_setup_lpc_bridge(VFIOPCIDevice *vdev, Error **errp)
{
- g_autofree struct vfio_region_info *host = NULL;
- g_autofree struct vfio_region_info *lpc = NULL;
+ struct vfio_region_info *host = NULL;
+ struct vfio_region_info *lpc = NULL;
PCIDevice *lpc_bridge;
int ret;
@@ -510,7 +510,7 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
- g_autofree struct vfio_region_info *opregion = NULL;
+ struct vfio_region_info *opregion = NULL;
int ret, gen;
uint64_t gms_size = 0;
uint64_t *bdsm_size;
@@ -551,7 +551,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
* - OpRegion
* - Same LPC bridge and Host bridge VID/DID/SVID/SSID as host
*/
- g_autofree struct vfio_region_info *rom = NULL;
+ struct vfio_region_info *rom = NULL;
legacy_mode_enabled = true;
info_report("IGD legacy mode enabled, "
@@ -681,7 +681,7 @@ error:
*/
static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp)
{
- g_autofree struct vfio_region_info *opregion = NULL;
+ struct vfio_region_info *opregion = NULL;
int gen;
if (!vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, PCI_ANY_ID) ||
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index da2ffc9bf36778fb61a7decf345391caee528b2a..9136cf52c82711939db01c09a8a1277327bc484f 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -883,8 +883,8 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
{
- g_autofree struct vfio_region_info *reg_info = NULL;
VFIODevice *vbasedev = &vdev->vbasedev;
+ struct vfio_region_info *reg_info = NULL;
uint64_t size;
off_t off = 0;
ssize_t bytes;
@@ -2710,7 +2710,7 @@ static VFIODeviceOps vfio_pci_ops = {
bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
- g_autofree struct vfio_region_info *reg_info = NULL;
+ struct vfio_region_info *reg_info = NULL;
int ret;
ret = vfio_device_get_region_info(vbasedev, VFIO_PCI_VGA_REGION_INDEX, ®_info);
@@ -2775,7 +2775,7 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
- g_autofree struct vfio_region_info *reg_info = NULL;
+ struct vfio_region_info *reg_info = NULL;
struct vfio_irq_info irq_info;
int i, ret = -1;
diff --git a/hw/vfio/region.c b/hw/vfio/region.c
index 04bf9eb0987c0ac460e0a1c3ba5abdf4a87f7499..ef2630cac3924fef200b2ece1be0dbad219dd67d 100644
--- a/hw/vfio/region.c
+++ b/hw/vfio/region.c
@@ -182,7 +182,7 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
int index, const char *name)
{
- g_autofree struct vfio_region_info *info = NULL;
+ struct vfio_region_info *info = NULL;
int ret;
ret = vfio_device_get_region_info(vbasedev, index, &info);
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* Re: [PULL 25/28] vfio: add region info cache
2025-05-09 13:13 ` [PULL 25/28] vfio: add region info cache Cédric Le Goater
@ 2025-10-14 13:16 ` Cédric Le Goater
2025-10-14 13:32 ` John Levon
0 siblings, 1 reply; 38+ messages in thread
From: Cédric Le Goater @ 2025-10-14 13:16 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, John Levon, John Johnson, Elena Ufimtseva,
Jagannathan Raman
Hello John,
On 5/9/25 15:13, Cédric Le Goater wrote:
> From: John Levon <john.levon@nutanix.com>
>
> Instead of requesting region information on demand with
> VFIO_DEVICE_GET_REGION_INFO, maintain a cache: this will become
> necessary for performance for vfio-user, where this call becomes a
> message over the control socket, so is of higher overhead than the
> traditional path.
>
> We will also need it to generalize region accesses, as that means we
> can't use ->config_offset for configuration space accesses, but must
> look up the region offset (if relevant) each time.
>
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> Reviewed-by: Cédric Le Goater <clg@redhat.com>
> Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-12-john.levon@nutanix.com
> Signed-off-by: Cédric Le Goater <clg@redhat.com>
> ---
> include/hw/vfio/vfio-device.h | 1 +
> hw/vfio/ccw.c | 5 -----
> hw/vfio/device.c | 25 +++++++++++++++++++++----
> hw/vfio/igd.c | 10 +++++-----
> hw/vfio/pci.c | 6 +++---
> hw/vfio/region.c | 2 +-
> 6 files changed, 31 insertions(+), 18 deletions(-)
>
> diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
> index 7e1e81e76bd2b484108282f7147ff7a0793360cf..4fff3dcee3b4a2a3c8a4bd6fa017cf822a16668e 100644
> --- a/include/hw/vfio/vfio-device.h
> +++ b/include/hw/vfio/vfio-device.h
> @@ -83,6 +83,7 @@ typedef struct VFIODevice {
> IOMMUFDBackend *iommufd;
> VFIOIOASHwpt *hwpt;
> QLIST_ENTRY(VFIODevice) hwpt_next;
> + struct vfio_region_info **reginfo;
> } VFIODevice;
>
> struct VFIODeviceOps {
> diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
> index ab3fabf991c35abb6c40d925f526c2a2d8955aef..cea9d6e00562c241832184cafe862005fcdc992b 100644
> --- a/hw/vfio/ccw.c
> +++ b/hw/vfio/ccw.c
> @@ -504,7 +504,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
>
> vcdev->io_region_offset = info->offset;
> vcdev->io_region = g_malloc0(info->size);
> - g_free(info);
>
> /* check for the optional async command region */
> ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
> @@ -517,7 +516,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->async_cmd_region_offset = info->offset;
> vcdev->async_cmd_region = g_malloc0(info->size);
> - g_free(info);
> }
>
> ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
> @@ -530,7 +528,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->schib_region_offset = info->offset;
> vcdev->schib_region = g_malloc(info->size);
> - g_free(info);
> }
>
> ret = vfio_device_get_region_info_type(vdev, VFIO_REGION_TYPE_CCW,
> @@ -544,7 +541,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->crw_region_offset = info->offset;
> vcdev->crw_region = g_malloc(info->size);
> - g_free(info);
> }
>
> return true;
> @@ -554,7 +550,6 @@ out_err:
> g_free(vcdev->schib_region);
> g_free(vcdev->async_cmd_region);
> g_free(vcdev->io_region);
> - g_free(info);
> return false;
> }
>
> diff --git a/hw/vfio/device.c b/hw/vfio/device.c
> index 40a196bfb9a86656610863d4f064db383c7072e0..77b0675abe7b4f4155ea79cf3fd0e3ab4b21f8ea 100644
> --- a/hw/vfio/device.c
> +++ b/hw/vfio/device.c
> @@ -202,6 +202,12 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
> size_t argsz = sizeof(struct vfio_region_info);
> int ret;
>
> + /* check cache */
It would be good to add an assert to check the index value. More important
we need to fix an ugly "index out-of-bounds" bug that can occur when booting
a VM with a vGPU :
-device vfio-pci-nohotplug,host=0000:27:00.4,display=on,ramfb=true ...
The interesting part is :
Thread 1 (Thread 0x7ffff6891ec0 (LWP 11372) "qemu-kvm"):
#0 0x000055555581b83d in vfio_region_setup (obj=0x5555588c0b70, vbasedev=0x5555588c1630, region=0x555558a9c040, index=9, name=0x555555de94ba <str.68.llvm> "display") at ../hw/vfio/region.c:199
#1 0x00005555558208a4 in vfio_display_region_update (opaque=<optimized out>) at ../hw/vfio/display.c:449
#2 0x00005555556bdd6c in graphic_hw_update (con=0x555558acf830) at ../ui/console.c:143
#3 vnc_refresh (dcl=0x7fffec048050) at ../ui/vnc.c:3262
#4 0x00005555556a15cb in dpy_refresh (s=0x555558acf980) at ../ui/console.c:880
#5 gui_update (opaque=0x555558acf980) at ../ui/console.c:90
(gdb) p vbasedev->num_regions
$9 = 9
Index 9 is beyond the maximum valid index of the reginfo array :/
We didn't take into account the ioctl VFIO_DEVICE_QUERY_GFX_PLANE
which can return region index 9 which is beyond the maximum valid
index of the reginfo array :/
I didn't expect that. Sometimes the best way to learn how something
works is to break it ... Ideas welcome.
Thanks,
C.
> + if (vbasedev->reginfo[index] != NULL) {
> + *info = vbasedev->reginfo[index];
> + return 0;
> + }
> +
> *info = g_malloc0(argsz);
>
> (*info)->index = index;
> @@ -222,6 +228,9 @@ retry:
> goto retry;
> }
>
> + /* fill cache */
> + vbasedev->reginfo[index] = *info;
> +
> return 0;
> }
>
> @@ -240,7 +249,6 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
>
> hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
> if (!hdr) {
> - g_free(*info);
> continue;
> }
>
> @@ -252,8 +260,6 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
> if (cap_type->type == type && cap_type->subtype == subtype) {
> return 0;
> }
> -
> - g_free(*info);
> }
>
> *info = NULL;
> @@ -262,7 +268,7 @@ int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
>
> bool vfio_device_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
> {
> - g_autofree struct vfio_region_info *info = NULL;
> + struct vfio_region_info *info = NULL;
> bool ret = false;
>
> if (!vfio_device_get_region_info(vbasedev, region, &info)) {
> @@ -435,10 +441,21 @@ void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
>
> QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> +
> + vbasedev->reginfo = g_new0(struct vfio_region_info *,
> + vbasedev->num_regions);
> }
>
> void vfio_device_unprepare(VFIODevice *vbasedev)
> {
> + int i;
> +
> + for (i = 0; i < vbasedev->num_regions; i++) {
> + g_free(vbasedev->reginfo[i]);
> + }
> + g_free(vbasedev->reginfo);
> + vbasedev->reginfo = NULL;
> +
> QLIST_REMOVE(vbasedev, container_next);
> QLIST_REMOVE(vbasedev, global_next);
> vbasedev->bcontainer = NULL;
> diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
> index 3ee1a73b57c57563f661a246e6dd7e505231be91..e7952d15a014f28fe302cab312ab8e60a414c679 100644
> --- a/hw/vfio/igd.c
> +++ b/hw/vfio/igd.c
> @@ -349,8 +349,8 @@ static int vfio_pci_igd_lpc_init(VFIOPCIDevice *vdev,
>
> static bool vfio_pci_igd_setup_lpc_bridge(VFIOPCIDevice *vdev, Error **errp)
> {
> - g_autofree struct vfio_region_info *host = NULL;
> - g_autofree struct vfio_region_info *lpc = NULL;
> + struct vfio_region_info *host = NULL;
> + struct vfio_region_info *lpc = NULL;
> PCIDevice *lpc_bridge;
> int ret;
>
> @@ -510,7 +510,7 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
>
> static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
> {
> - g_autofree struct vfio_region_info *opregion = NULL;
> + struct vfio_region_info *opregion = NULL;
> int ret, gen;
> uint64_t gms_size = 0;
> uint64_t *bdsm_size;
> @@ -551,7 +551,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp)
> * - OpRegion
> * - Same LPC bridge and Host bridge VID/DID/SVID/SSID as host
> */
> - g_autofree struct vfio_region_info *rom = NULL;
> + struct vfio_region_info *rom = NULL;
>
> legacy_mode_enabled = true;
> info_report("IGD legacy mode enabled, "
> @@ -681,7 +681,7 @@ error:
> */
> static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp)
> {
> - g_autofree struct vfio_region_info *opregion = NULL;
> + struct vfio_region_info *opregion = NULL;
> int gen;
>
> if (!vfio_pci_is(vdev, PCI_VENDOR_ID_INTEL, PCI_ANY_ID) ||
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index da2ffc9bf36778fb61a7decf345391caee528b2a..9136cf52c82711939db01c09a8a1277327bc484f 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -883,8 +883,8 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
>
> static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
> {
> - g_autofree struct vfio_region_info *reg_info = NULL;
> VFIODevice *vbasedev = &vdev->vbasedev;
> + struct vfio_region_info *reg_info = NULL;
> uint64_t size;
> off_t off = 0;
> ssize_t bytes;
> @@ -2710,7 +2710,7 @@ static VFIODeviceOps vfio_pci_ops = {
> bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
> {
> VFIODevice *vbasedev = &vdev->vbasedev;
> - g_autofree struct vfio_region_info *reg_info = NULL;
> + struct vfio_region_info *reg_info = NULL;
> int ret;
>
> ret = vfio_device_get_region_info(vbasedev, VFIO_PCI_VGA_REGION_INDEX, ®_info);
> @@ -2775,7 +2775,7 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
> static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
> {
> VFIODevice *vbasedev = &vdev->vbasedev;
> - g_autofree struct vfio_region_info *reg_info = NULL;
> + struct vfio_region_info *reg_info = NULL;
> struct vfio_irq_info irq_info;
> int i, ret = -1;
>
> diff --git a/hw/vfio/region.c b/hw/vfio/region.c
> index 04bf9eb0987c0ac460e0a1c3ba5abdf4a87f7499..ef2630cac3924fef200b2ece1be0dbad219dd67d 100644
> --- a/hw/vfio/region.c
> +++ b/hw/vfio/region.c
> @@ -182,7 +182,7 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
> int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
> int index, const char *name)
> {
> - g_autofree struct vfio_region_info *info = NULL;
> + struct vfio_region_info *info = NULL;
> int ret;
>
> ret = vfio_device_get_region_info(vbasedev, index, &info);
^ permalink raw reply [flat|nested] 38+ messages in thread* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 13:16 ` Cédric Le Goater
@ 2025-10-14 13:32 ` John Levon
2025-10-14 13:49 ` Alex Williamson
0 siblings, 1 reply; 38+ messages in thread
From: John Levon @ 2025-10-14 13:32 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Alex Williamson, John Johnson, Elena Ufimtseva,
Jagannathan Raman
On Tue, Oct 14, 2025 at 03:16:46PM +0200, Cédric Le Goater wrote:
> > + /* check cache */
>
> It would be good to add an assert to check the index value. More important
> we need to fix an ugly "index out-of-bounds" bug that can occur when booting
> a VM with a vGPU :
>
> -device vfio-pci-nohotplug,host=0000:27:00.4,display=on,ramfb=true ...
>
> The interesting part is :
>
> Thread 1 (Thread 0x7ffff6891ec0 (LWP 11372) "qemu-kvm"):
> #0 0x000055555581b83d in vfio_region_setup (obj=0x5555588c0b70, vbasedev=0x5555588c1630, region=0x555558a9c040, index=9, name=0x555555de94ba <str.68.llvm> "display") at ../hw/vfio/region.c:199
> #1 0x00005555558208a4 in vfio_display_region_update (opaque=<optimized out>) at ../hw/vfio/display.c:449
> #2 0x00005555556bdd6c in graphic_hw_update (con=0x555558acf830) at ../ui/console.c:143
> #3 vnc_refresh (dcl=0x7fffec048050) at ../ui/vnc.c:3262
> #4 0x00005555556a15cb in dpy_refresh (s=0x555558acf980) at ../ui/console.c:880
> #5 gui_update (opaque=0x555558acf980) at ../ui/console.c:90
> (gdb) p vbasedev->num_regions
> $9 = 9
>
> Index 9 is beyond the maximum valid index of the reginfo array :/
>
> We didn't take into account the ioctl VFIO_DEVICE_QUERY_GFX_PLANE
> which can return region index 9 which is beyond the maximum valid
> index of the reginfo array :/
My apologies - we hit the exact same issue internally, but with a much older
codebase, so I did not realise this could be an upstream problem as well!
We put this down to a bug in the nvidia driver - surely it shouldn't be
reporting fewer regions than are actually in use. So we applied what we thought
to be a gross hack of boundary checking, and not using the region cache in case
it's beyond num_regions.
To put it another way, the header file says:
217 __u32 num_regions; /* Max region index + 1 */
If it's not actually the max region index + 1, what are the expected semantics
of this field, or of region indices more generally? We could not find any clear
documentation on the topic other than this comment.
regards
john
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 13:32 ` John Levon
@ 2025-10-14 13:49 ` Alex Williamson
2025-10-14 13:58 ` Cédric Le Goater
2025-10-14 14:00 ` John Levon
0 siblings, 2 replies; 38+ messages in thread
From: Alex Williamson @ 2025-10-14 13:49 UTC (permalink / raw)
To: John Levon, Cédric Le Goater
Cc: qemu-devel, Alex Williamson, John Johnson, Elena Ufimtseva,
Jagannathan Raman
On Tue, Oct 14, 2025, at 7:32 AM, John Levon wrote:
> On Tue, Oct 14, 2025 at 03:16:46PM +0200, Cédric Le Goater wrote:
>
>> > + /* check cache */
>>
>> It would be good to add an assert to check the index value. More important
>> we need to fix an ugly "index out-of-bounds" bug that can occur when booting
>> a VM with a vGPU :
>>
>> -device vfio-pci-nohotplug,host=0000:27:00.4,display=on,ramfb=true ...
>>
>> The interesting part is :
>>
>> Thread 1 (Thread 0x7ffff6891ec0 (LWP 11372) "qemu-kvm"):
>> #0 0x000055555581b83d in vfio_region_setup (obj=0x5555588c0b70, vbasedev=0x5555588c1630, region=0x555558a9c040, index=9, name=0x555555de94ba <str.68.llvm> "display") at ../hw/vfio/region.c:199
>> #1 0x00005555558208a4 in vfio_display_region_update (opaque=<optimized out>) at ../hw/vfio/display.c:449
>> #2 0x00005555556bdd6c in graphic_hw_update (con=0x555558acf830) at ../ui/console.c:143
>> #3 vnc_refresh (dcl=0x7fffec048050) at ../ui/vnc.c:3262
>> #4 0x00005555556a15cb in dpy_refresh (s=0x555558acf980) at ../ui/console.c:880
>> #5 gui_update (opaque=0x555558acf980) at ../ui/console.c:90
>> (gdb) p vbasedev->num_regions
>> $9 = 9
>>
>> Index 9 is beyond the maximum valid index of the reginfo array :/
>>
>> We didn't take into account the ioctl VFIO_DEVICE_QUERY_GFX_PLANE
>> which can return region index 9 which is beyond the maximum valid
>> index of the reginfo array :/
>
> My apologies - we hit the exact same issue internally, but with a much older
> codebase, so I did not realise this could be an upstream problem as well!
>
> We put this down to a bug in the nvidia driver - surely it shouldn't be
> reporting fewer regions than are actually in use. So we applied what we thought
> to be a gross hack of boundary checking, and not using the region cache in case
> it's beyond num_regions.
>
> To put it another way, the header file says:
>
> 217 __u32 num_regions; /* Max region index + 1 */
>
> If it's not actually the max region index + 1, what are the expected semantics
> of this field, or of region indices more generally? We could not find any clear
> documentation on the topic other than this comment.
'9' only defines the end of the fixed, pre-defined region indexes for vfio-pci, ie. VFIO_PCI_NUM_REGIONS. Beyond that, we support device specific regions. The GFX region is one such device specific region.
We enumerate these regions based on vfio_device_info.num_regions and use the capabilities feature of the vfio_region_info to introspect the region type provided.
There is no fixed limit to the number of regions a device may expose, nor is vfio_device_info.num_regions necessarily a static value. We're currently discussing a uAPI for generating special mappings to a region that could dynamically increase the reported regions. Thanks,
Alex
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 13:49 ` Alex Williamson
@ 2025-10-14 13:58 ` Cédric Le Goater
2025-10-14 14:01 ` John Levon
2025-10-14 14:00 ` John Levon
1 sibling, 1 reply; 38+ messages in thread
From: Cédric Le Goater @ 2025-10-14 13:58 UTC (permalink / raw)
To: Alex Williamson, John Levon
Cc: qemu-devel, Alex Williamson, John Johnson, Elena Ufimtseva,
Jagannathan Raman
On 10/14/25 15:49, Alex Williamson wrote:
> On Tue, Oct 14, 2025, at 7:32 AM, John Levon wrote:
>> On Tue, Oct 14, 2025 at 03:16:46PM +0200, Cédric Le Goater wrote:
>>
>>>> + /* check cache */
>>>
>>> It would be good to add an assert to check the index value. More important
>>> we need to fix an ugly "index out-of-bounds" bug that can occur when booting
>>> a VM with a vGPU :
>>>
>>> -device vfio-pci-nohotplug,host=0000:27:00.4,display=on,ramfb=true ...
>>>
>>> The interesting part is :
>>>
>>> Thread 1 (Thread 0x7ffff6891ec0 (LWP 11372) "qemu-kvm"):
>>> #0 0x000055555581b83d in vfio_region_setup (obj=0x5555588c0b70, vbasedev=0x5555588c1630, region=0x555558a9c040, index=9, name=0x555555de94ba <str.68.llvm> "display") at ../hw/vfio/region.c:199
>>> #1 0x00005555558208a4 in vfio_display_region_update (opaque=<optimized out>) at ../hw/vfio/display.c:449
>>> #2 0x00005555556bdd6c in graphic_hw_update (con=0x555558acf830) at ../ui/console.c:143
>>> #3 vnc_refresh (dcl=0x7fffec048050) at ../ui/vnc.c:3262
>>> #4 0x00005555556a15cb in dpy_refresh (s=0x555558acf980) at ../ui/console.c:880
>>> #5 gui_update (opaque=0x555558acf980) at ../ui/console.c:90
>>> (gdb) p vbasedev->num_regions
>>> $9 = 9
>>>
>>> Index 9 is beyond the maximum valid index of the reginfo array :/
>>>
>>> We didn't take into account the ioctl VFIO_DEVICE_QUERY_GFX_PLANE
>>> which can return region index 9 which is beyond the maximum valid
>>> index of the reginfo array :/
>>
>> My apologies - we hit the exact same issue internally, but with a much older
>> codebase, so I did not realise this could be an upstream problem as well!
>>
>> We put this down to a bug in the nvidia driver - surely it shouldn't be
>> reporting fewer regions than are actually in use. So we applied what we thought
>> to be a gross hack of boundary checking, and not using the region cache in case
>> it's beyond num_regions.
>>
>> To put it another way, the header file says:
>>
>> 217 __u32 num_regions; /* Max region index + 1 */
>>
>> If it's not actually the max region index + 1, what are the expected semantics
>> of this field, or of region indices more generally? We could not find any clear
>> documentation on the topic other than this comment.
>
> '9' only defines the end of the fixed, pre-defined region indexes for vfio-pci, ie. VFIO_PCI_NUM_REGIONS. Beyond that, we support device specific regions. The GFX region is one such device specific region.
>
> We enumerate these regions based on vfio_device_info.num_regions and use the capabilities feature of the vfio_region_info to introspect the region type provided.
>
> There is no fixed limit to the number of regions a device may expose, nor is vfio_device_info.num_regions necessarily a static value. We're currently discussing a uAPI for generating special mappings to a region that could dynamically increase the reported regions. Thanks,
We should then improve the VFIO region cache handling by reallocating
the reginfo array on demand.
Thanks,
C.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 13:58 ` Cédric Le Goater
@ 2025-10-14 14:01 ` John Levon
0 siblings, 0 replies; 38+ messages in thread
From: John Levon @ 2025-10-14 14:01 UTC (permalink / raw)
To: Cédric Le Goater
Cc: Alex Williamson, qemu-devel, Alex Williamson, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On Tue, Oct 14, 2025 at 03:58:02PM +0200, Cédric Le Goater wrote:
> We should then improve the VFIO region cache handling by reallocating
> the reginfo array on demand.
That would render it more or less pointless as that'd be a round-trip socket
message every time for vfio-user.
regards
john
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 13:49 ` Alex Williamson
2025-10-14 13:58 ` Cédric Le Goater
@ 2025-10-14 14:00 ` John Levon
2025-10-14 14:29 ` Alex Williamson
1 sibling, 1 reply; 38+ messages in thread
From: John Levon @ 2025-10-14 14:00 UTC (permalink / raw)
To: Alex Williamson
Cc: Cédric Le Goater, qemu-devel, Alex Williamson, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On Tue, Oct 14, 2025 at 07:49:24AM -0600, Alex Williamson wrote:
> > My apologies - we hit the exact same issue internally, but with a much older
> > codebase, so I did not realise this could be an upstream problem as well!
> >
> > We put this down to a bug in the nvidia driver - surely it shouldn't be
> > reporting fewer regions than are actually in use. So we applied what we
> > thought to be a gross hack of boundary checking, and not using the region
> > cache in case it's beyond num_regions.
> >
> > To put it another way, the header file says:
> >
> > 217 __u32 num_regions; /* Max region index + 1 */
> >
> > If it's not actually the max region index + 1, what are the expected
> > semantics of this field, or of region indices more generally? We could not
> > find any clear documentation on the topic other than this comment.
>
> '9' only defines the end of the fixed, pre-defined region indexes for
> vfio-pci, ie. VFIO_PCI_NUM_REGIONS. Beyond that, we support device specific
> regions. The GFX region is one such device specific region.
To be clear, nowhere in the code are we hard-coding 9, we ask the underlying
vfio instance for the num_regions value.
In this case, it appears that the underlying instance is returning 9, and then
trying to use index 9.
> There is no fixed limit to the number of regions a device may expose
Sure.
>, nor is vfio_device_info.num_regions necessarily a static value.
Ah - is this documented somewhere? And do you have an example of where this
varies over the lifetime of a device currently?
IOW, are these devices actually changing the num_regions value they report
sometime after initialization (namely, can it change after
vfio_device_prepare()) ?
Or would querying num_regions still return the original value, and in fact the
semantics of the field are "it's not the max region index, but the max region
index during initialization" or similar ?
> We're currently discussing a uAPI for generating special mappings to a region
> that could dynamically increase the reported regions.
OK. Probably should rename the field to ->num_init_regions as well as fix up the
cache, depending on your replies to the above.
thanks
john
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 14:00 ` John Levon
@ 2025-10-14 14:29 ` Alex Williamson
2025-10-14 14:36 ` John Levon
0 siblings, 1 reply; 38+ messages in thread
From: Alex Williamson @ 2025-10-14 14:29 UTC (permalink / raw)
To: John Levon
Cc: Cédric Le Goater, qemu-devel, Alex Williamson, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On Tue, 14 Oct 2025 16:00:26 +0200
John Levon <john.levon@nutanix.com> wrote:
> On Tue, Oct 14, 2025 at 07:49:24AM -0600, Alex Williamson wrote:
>
> > > My apologies - we hit the exact same issue internally, but with a much older
> > > codebase, so I did not realise this could be an upstream problem as well!
> > >
> > > We put this down to a bug in the nvidia driver - surely it shouldn't be
> > > reporting fewer regions than are actually in use. So we applied what we
> > > thought to be a gross hack of boundary checking, and not using the region
> > > cache in case it's beyond num_regions.
> > >
> > > To put it another way, the header file says:
> > >
> > > 217 __u32 num_regions; /* Max region index + 1 */
> > >
> > > If it's not actually the max region index + 1, what are the expected
> > > semantics of this field, or of region indices more generally? We could not
> > > find any clear documentation on the topic other than this comment.
> >
> > '9' only defines the end of the fixed, pre-defined region indexes for
> > vfio-pci, ie. VFIO_PCI_NUM_REGIONS. Beyond that, we support device specific
> > regions. The GFX region is one such device specific region.
>
> To be clear, nowhere in the code are we hard-coding 9, we ask the underlying
> vfio instance for the num_regions value.
>
> In this case, it appears that the underlying instance is returning 9, and then
> trying to use index 9.
That sounds like a bug, in vfio_pci_ioctl_get_info() we return
num_regions as (VFIO_PCI_NUM_REGIONS + vdev->num_regions) where
vdev->num_regions is incremented via
vfio_pci_core_register_dev_region(). Any read, write, or mmap access
done through vfio-pci-core would need to increment vdev->num_regions to
support that access. I think we're dealing with NVIDIA vGPU here,
which afaik is the only driver that uses a region for the display, so
I'd suspect they have a bug and don't use the vfio-pci-core callbacks
here.
Does QEMU's caching model need to fall through to GET_REGION_INFO and
expand the cache for an out-of-bounds index to handle such a bug?
> > There is no fixed limit to the number of regions a device may expose
>
> Sure.
>
> >, nor is vfio_device_info.num_regions necessarily a static value.
>
> Ah - is this documented somewhere? And do you have an example of where this
> varies over the lifetime of a device currently?
It's more the case that it's not specifically defined as static over
the lifetime of the device. I don't think we want device spontaneously
creating new regions, we have no device-check notification mechanism to
userspace to reevaluate regions, but a user initiated action defined to
create a new region seems like a fair vector where num_regions could be
updated. Also the current working idea would be that regions are only
added, not modified or deleted.
> IOW, are these devices actually changing the num_regions value they report
> sometime after initialization (namely, can it change after
> vfio_device_prepare()) ?
In theory, yes.
> Or would querying num_regions still return the original value, and in fact the
> semantics of the field are "it's not the max region index, but the max region
> index during initialization" or similar ?
Ultimately it's just a marker that *should* indicate there are no
regions to query above (num_regions - 1). It should be valid at the
time it's queried. I don't think it would be valid that it could be
dynamic in any other way than a monotonically increasing value. Thanks,
Alex
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PULL 25/28] vfio: add region info cache
2025-10-14 14:29 ` Alex Williamson
@ 2025-10-14 14:36 ` John Levon
0 siblings, 0 replies; 38+ messages in thread
From: John Levon @ 2025-10-14 14:36 UTC (permalink / raw)
To: Alex Williamson
Cc: Cédric Le Goater, qemu-devel, Alex Williamson, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On Tue, Oct 14, 2025 at 08:29:49AM -0600, Alex Williamson wrote:
> > Ah - is this documented somewhere? And do you have an example of where this
> > varies over the lifetime of a device currently?
>
> It's more the case that it's not specifically defined as static over
> the lifetime of the device. I don't think we want device spontaneously
> creating new regions, we have no device-check notification mechanism to
> userspace to reevaluate regions, but a user initiated action defined to
> create a new region seems like a fair vector where num_regions could be
> updated. Also the current working idea would be that regions are only
> added, not modified or deleted.
>
> > IOW, are these devices actually changing the num_regions value they report
> > sometime after initialization (namely, can it change after
> > vfio_device_prepare()) ?
>
> In theory, yes.
OK, thanks. So the question over whether there's an nvidia bug or not here seems
to be moot, since anyway to support this kind of case, we need the region cache
guardrails.
This means that such "dynamic" regions are never cached, but that's not a
specific issue for vfio-user at least.
I will prepare a patch if you can help test it, Cédric.
regards
john
^ permalink raw reply [flat|nested] 38+ messages in thread
* [PULL 26/28] vfio: add read/write to device IO ops vector
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (24 preceding siblings ...)
2025-05-09 13:13 ` [PULL 25/28] vfio: add region info cache Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 27/28] vfio: add vfio-pci-base class Cédric Le Goater
` (2 subsequent siblings)
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Now we have the region info cache, add ->region_read/write device I/O
operations instead of explicit pread()/pwrite() system calls.
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-13-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-device.h | 18 ++++++++++++++++++
hw/vfio/device.c | 34 ++++++++++++++++++++++++++++++++++
hw/vfio/pci.c | 28 ++++++++++++++--------------
hw/vfio/region.c | 17 +++++++++++------
4 files changed, 77 insertions(+), 20 deletions(-)
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 4fff3dcee3b4a2a3c8a4bd6fa017cf822a16668e..8bcb3c19f62b5a47c835e10149c04a9bd7536520 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -188,6 +188,24 @@ struct VFIODeviceIOOps {
* Configure IRQs as defined by @irqs.
*/
int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
+
+ /**
+ * @region_read
+ *
+ * Read @size bytes from the region @nr at offset @off into the buffer
+ * @data.
+ */
+ int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
+ void *data);
+
+ /**
+ * @region_write
+ *
+ * Write @size bytes to the region @nr at offset @off from the buffer
+ * @data.
+ */
+ int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
+ void *data);
};
void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 77b0675abe7b4f4155ea79cf3fd0e3ab4b21f8ea..0b2cd90d64dc797bb2f20c60c57ff49706816aed 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -505,9 +505,43 @@ static int vfio_device_io_set_irqs(VFIODevice *vbasedev,
return ret < 0 ? -errno : ret;
}
+static int vfio_device_io_region_read(VFIODevice *vbasedev, uint8_t index,
+ off_t off, uint32_t size, void *data)
+{
+ struct vfio_region_info *info;
+ int ret;
+
+ ret = vfio_device_get_region_info(vbasedev, index, &info);
+ if (ret != 0) {
+ return ret;
+ }
+
+ ret = pread(vbasedev->fd, data, size, info->offset + off);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_device_io_region_write(VFIODevice *vbasedev, uint8_t index,
+ off_t off, uint32_t size, void *data)
+{
+ struct vfio_region_info *info;
+ int ret;
+
+ ret = vfio_device_get_region_info(vbasedev, index, &info);
+ if (ret != 0) {
+ return ret;
+ }
+
+ ret = pwrite(vbasedev->fd, data, size, info->offset + off);
+
+ return ret < 0 ? -errno : ret;
+}
+
static VFIODeviceIOOps vfio_device_io_ops_ioctl = {
.device_feature = vfio_device_io_device_feature,
.get_region_info = vfio_device_io_get_region_info,
.get_irq_info = vfio_device_io_get_irq_info,
.set_irqs = vfio_device_io_set_irqs,
+ .region_read = vfio_device_io_region_read,
+ .region_write = vfio_device_io_region_write,
};
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 9136cf52c82711939db01c09a8a1277327bc484f..1236de315d1a73aa408c108e2e650a37b037b93e 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -918,18 +918,22 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
memset(vdev->rom, 0xff, size);
while (size) {
- bytes = pread(vbasedev->fd, vdev->rom + off,
- size, vdev->rom_offset + off);
+ bytes = vbasedev->io_ops->region_read(vbasedev,
+ VFIO_PCI_ROM_REGION_INDEX,
+ off, size, vdev->rom + off);
+
if (bytes == 0) {
break;
} else if (bytes > 0) {
off += bytes;
size -= bytes;
} else {
- if (errno == EINTR || errno == EAGAIN) {
+ if (bytes == -EINTR || bytes == -EAGAIN) {
continue;
}
- error_report("vfio: Error reading device ROM: %m");
+ error_report("vfio: Error reading device ROM: %s",
+ strreaderror(bytes));
+
break;
}
}
@@ -969,22 +973,18 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
static int vfio_pci_config_space_read(VFIOPCIDevice *vdev, off_t offset,
uint32_t size, void *data)
{
- ssize_t ret;
-
- ret = pread(vdev->vbasedev.fd, data, size, vdev->config_offset + offset);
-
- return ret < 0 ? -errno : (int)ret;
+ return vdev->vbasedev.io_ops->region_read(&vdev->vbasedev,
+ VFIO_PCI_CONFIG_REGION_INDEX,
+ offset, size, data);
}
/* "Raw" write of underlying config space. */
static int vfio_pci_config_space_write(VFIOPCIDevice *vdev, off_t offset,
uint32_t size, void *data)
{
- ssize_t ret;
-
- ret = pwrite(vdev->vbasedev.fd, data, size, vdev->config_offset + offset);
-
- return ret < 0 ? -errno : (int)ret;
+ return vdev->vbasedev.io_ops->region_write(&vdev->vbasedev,
+ VFIO_PCI_CONFIG_REGION_INDEX,
+ offset, size, data);
}
static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size)
diff --git a/hw/vfio/region.c b/hw/vfio/region.c
index ef2630cac3924fef200b2ece1be0dbad219dd67d..34752c3f65c4b43fc961754657b18f5269c01ef1 100644
--- a/hw/vfio/region.c
+++ b/hw/vfio/region.c
@@ -45,6 +45,7 @@ void vfio_region_write(void *opaque, hwaddr addr,
uint32_t dword;
uint64_t qword;
} buf;
+ int ret;
switch (size) {
case 1:
@@ -64,11 +65,13 @@ void vfio_region_write(void *opaque, hwaddr addr,
break;
}
- if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
+ ret = vbasedev->io_ops->region_write(vbasedev, region->nr,
+ addr, size, &buf);
+ if (ret != size) {
error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
- ",%d) failed: %m",
+ ",%d) failed: %s",
__func__, vbasedev->name, region->nr,
- addr, data, size);
+ addr, data, size, strwriteerror(ret));
}
trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
@@ -96,11 +99,13 @@ uint64_t vfio_region_read(void *opaque,
uint64_t qword;
} buf;
uint64_t data = 0;
+ int ret;
- if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
- error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
+ ret = vbasedev->io_ops->region_read(vbasedev, region->nr, addr, size, &buf);
+ if (ret != size) {
+ error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s",
__func__, vbasedev->name, region->nr,
- addr, size);
+ addr, size, strreaderror(ret));
return (uint64_t)-1;
}
switch (size) {
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 27/28] vfio: add vfio-pci-base class
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (25 preceding siblings ...)
2025-05-09 13:13 ` [PULL 26/28] vfio: add read/write to device IO ops vector Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-09 13:13 ` [PULL 28/28] vfio/container: pass listener_begin/commit callbacks Cédric Le Goater
2025-05-10 18:36 ` [PULL 00/28] vfio queue Stefan Hajnoczi
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel
Cc: Alex Williamson, John Levon, John Johnson, Elena Ufimtseva,
Jagannathan Raman, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
Split out parts of TYPE_VFIO_PCI into a base TYPE_VFIO_PCI_BASE,
although we have not yet introduced another subclass, so all the
properties have remained in TYPE_VFIO_PCI.
Note that currently there is no need for additional data for
TYPE_VFIO_PCI, so it shares the same C struct type as
TYPE_VFIO_PCI_BASE, VFIOPCIDevice.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-14-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/pci.h | 10 +++++++-
hw/vfio/device.c | 2 +-
hw/vfio/pci.c | 62 +++++++++++++++++++++++++++++++-----------------
3 files changed, 50 insertions(+), 24 deletions(-)
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index f835b1dbc2b1e8aab820924900e1eb6c36613d16..5ce0fb916f3896a448b59fc0b99e892c11c3a9e1 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -118,8 +118,16 @@ typedef struct VFIOMSIXInfo {
bool noresize;
} VFIOMSIXInfo;
+/*
+ * TYPE_VFIO_PCI_BASE is an abstract type used to share code
+ * between VFIO implementations that use a kernel driver
+ * with those that use user sockets.
+ */
+#define TYPE_VFIO_PCI_BASE "vfio-pci-base"
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI_BASE)
+
#define TYPE_VFIO_PCI "vfio-pci"
-OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI)
+/* TYPE_VFIO_PCI shares struct VFIOPCIDevice. */
struct VFIOPCIDevice {
PCIDevice pdev;
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 0b2cd90d64dc797bb2f20c60c57ff49706816aed..9fba2c7272f207f2fe870fc97b46c342bd57dc0a 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -392,7 +392,7 @@ bool vfio_device_hiod_create_and_realize(VFIODevice *vbasedev,
VFIODevice *vfio_get_vfio_device(Object *obj)
{
if (object_dynamic_cast(obj, TYPE_VFIO_PCI)) {
- return &VFIO_PCI(obj)->vbasedev;
+ return &VFIO_PCI_BASE(obj)->vbasedev;
} else {
return NULL;
}
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 1236de315d1a73aa408c108e2e650a37b037b93e..a1bfdfe3751fdf171b0b96d78d0b51853d8e7838 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -241,7 +241,7 @@ static void vfio_intx_update(VFIOPCIDevice *vdev, PCIINTxRoute *route)
static void vfio_intx_routing_notifier(PCIDevice *pdev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
PCIINTxRoute route;
if (vdev->interrupt != VFIO_INT_INTx) {
@@ -514,7 +514,7 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg,
static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
MSIMessage *msg, IOHandler *handler)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIOMSIVector *vector;
int ret;
bool resizing = !!(vdev->nr_vectors < nr + 1);
@@ -620,7 +620,7 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIOMSIVector *vector = &vdev->msi_vectors[nr];
trace_vfio_msix_vector_release(vdev->vbasedev.name, nr);
@@ -1196,7 +1196,7 @@ static const MemoryRegionOps vfio_vga_ops = {
*/
static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIORegion *region = &vdev->bars[bar].region;
MemoryRegion *mmap_mr, *region_mr, *base_mr;
PCIIORegion *r;
@@ -1242,7 +1242,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
*/
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
@@ -1276,7 +1276,7 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t val_le = cpu_to_le32(val);
int ret;
@@ -3129,7 +3129,7 @@ static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
ERRP_GUARD();
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
int i, ret;
char uuid[UUID_STR_LEN];
@@ -3300,7 +3300,7 @@ error:
static void vfio_instance_finalize(Object *obj)
{
- VFIOPCIDevice *vdev = VFIO_PCI(obj);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
vfio_display_finalize(vdev);
vfio_bars_finalize(vdev);
@@ -3318,7 +3318,7 @@ static void vfio_instance_finalize(Object *obj)
static void vfio_exitfn(PCIDevice *pdev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
vfio_unregister_req_notifier(vdev);
@@ -3342,7 +3342,7 @@ static void vfio_exitfn(PCIDevice *pdev)
static void vfio_pci_reset(DeviceState *dev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(dev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(dev);
trace_vfio_pci_reset(vdev->vbasedev.name);
@@ -3382,7 +3382,7 @@ post_reset:
static void vfio_instance_init(Object *obj)
{
PCIDevice *pci_dev = PCI_DEVICE(obj);
- VFIOPCIDevice *vdev = VFIO_PCI(obj);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
device_add_bootindex_property(obj, &vdev->bootindex,
@@ -3403,6 +3403,31 @@ static void vfio_instance_init(Object *obj)
pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
}
+static void vfio_pci_base_dev_class_init(ObjectClass *klass, const void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
+
+ dc->desc = "VFIO PCI base device";
+ set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+ pdc->exit = vfio_exitfn;
+ pdc->config_read = vfio_pci_read_config;
+ pdc->config_write = vfio_pci_write_config;
+}
+
+static const TypeInfo vfio_pci_base_dev_info = {
+ .name = TYPE_VFIO_PCI_BASE,
+ .parent = TYPE_PCI_DEVICE,
+ .instance_size = 0,
+ .abstract = true,
+ .class_init = vfio_pci_base_dev_class_init,
+ .interfaces = (const InterfaceInfo[]) {
+ { INTERFACE_PCIE_DEVICE },
+ { INTERFACE_CONVENTIONAL_PCI_DEVICE },
+ { }
+ },
+};
+
static PropertyInfo vfio_pci_migration_multifd_transfer_prop;
static const Property vfio_pci_dev_properties[] = {
@@ -3473,7 +3498,8 @@ static const Property vfio_pci_dev_properties[] = {
#ifdef CONFIG_IOMMUFD
static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
{
- vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+ vfio_device_set_fd(&vdev->vbasedev, str, errp);
}
#endif
@@ -3488,11 +3514,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data)
object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
#endif
dc->desc = "VFIO-based PCI device assignment";
- set_bit(DEVICE_CATEGORY_MISC, dc->categories);
pdc->realize = vfio_realize;
- pdc->exit = vfio_exitfn;
- pdc->config_read = vfio_pci_read_config;
- pdc->config_write = vfio_pci_write_config;
object_class_property_set_description(klass, /* 1.3 */
"host",
@@ -3617,16 +3639,11 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data)
static const TypeInfo vfio_pci_dev_info = {
.name = TYPE_VFIO_PCI,
- .parent = TYPE_PCI_DEVICE,
+ .parent = TYPE_VFIO_PCI_BASE,
.instance_size = sizeof(VFIOPCIDevice),
.class_init = vfio_pci_dev_class_init,
.instance_init = vfio_instance_init,
.instance_finalize = vfio_instance_finalize,
- .interfaces = (const InterfaceInfo[]) {
- { INTERFACE_PCIE_DEVICE },
- { INTERFACE_CONVENTIONAL_PCI_DEVICE },
- { }
- },
};
static const Property vfio_pci_dev_nohotplug_properties[] = {
@@ -3673,6 +3690,7 @@ static void register_vfio_pci_dev_type(void)
vfio_pci_migration_multifd_transfer_prop = qdev_prop_on_off_auto;
vfio_pci_migration_multifd_transfer_prop.realized_set_allowed = true;
+ type_register_static(&vfio_pci_base_dev_info);
type_register_static(&vfio_pci_dev_info);
type_register_static(&vfio_pci_nohotplug_dev_info);
}
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* [PULL 28/28] vfio/container: pass listener_begin/commit callbacks
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (26 preceding siblings ...)
2025-05-09 13:13 ` [PULL 27/28] vfio: add vfio-pci-base class Cédric Le Goater
@ 2025-05-09 13:13 ` Cédric Le Goater
2025-05-10 18:36 ` [PULL 00/28] vfio queue Stefan Hajnoczi
28 siblings, 0 replies; 38+ messages in thread
From: Cédric Le Goater @ 2025-05-09 13:13 UTC (permalink / raw)
To: qemu-devel; +Cc: Alex Williamson, John Levon, Cédric Le Goater
From: John Levon <john.levon@nutanix.com>
The vfio-user container will later need to hook into these callbacks;
set up vfio to use them, and optionally pass them through to the
container.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250507152020.1254632-15-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
include/hw/vfio/vfio-container-base.h | 2 ++
hw/vfio/listener.c | 28 +++++++++++++++++++++++++++
2 files changed, 30 insertions(+)
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 59f07d26e8226916c9c58eac07cb494552097138..3d392b0fd8bca9de1480d75ccfac8f3625e82121 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -117,6 +117,8 @@ struct VFIOIOMMUClass {
/* basic feature */
bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
+ void (*listener_begin)(VFIOContainerBase *bcontainer);
+ void (*listener_commit)(VFIOContainerBase *bcontainer);
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
void *vaddr, bool readonly);
diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
index 2b93ca55b6d47e4ef3e89bea681d6e345f8d3abe..bfacb3d8d9cd5b7764a1678142eedf6d553cc07a 100644
--- a/hw/vfio/listener.c
+++ b/hw/vfio/listener.c
@@ -411,6 +411,32 @@ static bool vfio_get_section_iova_range(VFIOContainerBase *bcontainer,
return true;
}
+static void vfio_listener_begin(MemoryListener *listener)
+{
+ VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
+ listener);
+ void (*listener_begin)(VFIOContainerBase *bcontainer);
+
+ listener_begin = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
+
+ if (listener_begin) {
+ listener_begin(bcontainer);
+ }
+}
+
+static void vfio_listener_commit(MemoryListener *listener)
+{
+ VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
+ listener);
+ void (*listener_commit)(VFIOContainerBase *bcontainer);
+
+ listener_commit = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
+
+ if (listener_commit) {
+ listener_commit(bcontainer);
+ }
+}
+
static void vfio_device_error_append(VFIODevice *vbasedev, Error **errp)
{
/*
@@ -1161,6 +1187,8 @@ static void vfio_listener_log_sync(MemoryListener *listener,
static const MemoryListener vfio_memory_listener = {
.name = "vfio",
+ .begin = vfio_listener_begin,
+ .commit = vfio_listener_commit,
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
.log_global_start = vfio_listener_log_global_start,
--
2.49.0
^ permalink raw reply related [flat|nested] 38+ messages in thread* Re: [PULL 00/28] vfio queue
2025-05-09 13:12 [PULL 00/28] vfio queue Cédric Le Goater
` (27 preceding siblings ...)
2025-05-09 13:13 ` [PULL 28/28] vfio/container: pass listener_begin/commit callbacks Cédric Le Goater
@ 2025-05-10 18:36 ` Stefan Hajnoczi
28 siblings, 0 replies; 38+ messages in thread
From: Stefan Hajnoczi @ 2025-05-10 18:36 UTC (permalink / raw)
To: Cédric Le Goater; +Cc: qemu-devel, Alex Williamson, Cédric Le Goater
[-- Attachment #1: Type: text/plain, Size: 116 bytes --]
Applied, thanks.
Please update the changelog at https://wiki.qemu.org/ChangeLog/10.1 for any user-visible changes.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 38+ messages in thread