vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
Subsystems (8)
v3 cover vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
As discussed in this thread:
https://lore.kernel.org/kvm/[email protected]/
Let's remove VFIO_GROUP_NOTIFY_SET_KVM and instead assume the association has already been established prior to device_open. For the types today that need a KVM (GVT, vfio-ap) these will fail if a KVM is not found. Looking ahead, vfio-pci-zdev will optionally want the KVM association (enable hardware assists) but it will not be a hard requirement (still want to allow other, non-KVM userspace usage).
This is built on top of vfio-next and tested with s390x-pci (zdev-kvm series) and vfio-ap (GVT changes are compile-tested only)
Changes for v3:
- merge branches under if (device->open_count == 1) (Kevin)
- move device->open_count-- out from group_rwsem (Kevin)
- drop null KVM check (Christoph)
- remove extra kvm_{get,put}_kvm from vfio_ap_ops, it was already getting a reference (Jason)
- Add comment about kvm reference in vfio.h (Jason)
- Return -EINVAL if !kvm for vfio-ap (Tony)
Changes for v2:
- gvt no longer needs release_work, get rid of it (Christoph)
- a few compile fixes for gvt
- update commit to mention fixes gvt oops (Jason)
- s/down_write/down_read/ in a few spots (Jason)
- avoid kvm build dependency by holding group read lock over device open/close and put the onus on the driver to obtain a reference if it will actually use the kvm pointer. Document the requirement, use lockdep_assert to ensure lock is held during register_notifer; today all callers are from driver open_device.
Matthew Rosato (1):
vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)
Signature · 1 line
2.27.0
PATCH v3 1/1 vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to device_open. The first time a device is opened associate the group KVM with the device.
This fixes a user-triggerable oops in GVT.
--- drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)
drivers/gpu/drm/i915/gvt/gtt.c +2 -2
@@ -51,7 +51,7 @@ static int preallocated_oos_pages = 8192;static bool intel_gvt_is_valid_gfn (struct intel_vgpu *vgpu,unsigned long gfn) { -struct kvm *kvm = vgpu->kvm; +struct kvm *kvm = vgpu->vfio_device.kvm;int idx;bool ret;
@@ -1185,7 +1185,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,if (!vgpu->attached)return -EINVAL ; - pfn =gfn_to_pfn (vgpu->kvm, ops->get_pfn (entry)); + pfn =gfn_to_pfn (vgpu->vfio_device.kvm, ops->get_pfn (entry));if (is_error_noslot_pfn (pfn))return -EINVAL ;return PageTransHuge (pfn_to_page (pfn));
drivers/gpu/drm/i915/gvt/gvt.h +0 -3
@@ -227,9 +227,6 @@ struct intel_vgpu {struct mutex cache_lock;struct notifier_block iommu_notifier; -struct notifier_block group_notifier; -struct kvm *kvm; -struct work_struct release_work;atomic_t released;struct kvm_page_track_notifier_node track_node;
drivers/gpu/drm/i915/gvt/kvmgt.c +18 -64
175 lines not on this page · raw message
drivers/s390/crypto/vfio_ap_ops.c +6 -29
@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -int notify_rc =NOTIFY_OK ; -struct ap_matrix_mdev *matrix_mdev; - -if (action !=VFIO_GROUP_NOTIFY_SET_KVM ) -return NOTIFY_OK ; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - -if (!data) -vfio_ap_mdev_unset_kvm (matrix_mdev); -else if (vfio_ap_mdev_set_kvm (matrix_mdev, data)) - notify_rc =NOTIFY_DONE ; - -return notify_rc; -} -static struct vfio_ap_queue *vfio_ap_find_queue (int apqn) {struct device *dev;
@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)unsigned long events;int ret; - matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events =VFIO_GROUP_NOTIFY_SET_KVM ; +if (!vdev->kvm) +return -EINVAL ; - ret =vfio_register_notifier (vdev,VFIO_GROUP_NOTIFY , &events, - &matrix_mdev->group_notifier); + ret =vfio_ap_mdev_set_kvm (matrix_mdev, vdev->kvm);if (ret)return ret;
@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret =vfio_register_notifier (vdev,VFIO_IOMMU_NOTIFY , &events, &matrix_mdev->iommu_notifier);if (ret) - goto out_unregister_group; + goto err_kvm;return 0 ; -out_unregister_group: -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier); +err_kvm: +vfio_ap_mdev_unset_kvm (matrix_mdev);return ret; }
@@ -1431,8 +1410,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)vfio_unregister_notifier (vdev,VFIO_IOMMU_NOTIFY , &matrix_mdev->iommu_notifier); -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier);vfio_ap_mdev_unset_kvm (matrix_mdev); }
drivers/s390/crypto/vfio_ap_private.h +0 -3
@@ -81,8 +81,6 @@ struct ap_matrix {* @node: allows the ap_matrix_mdev struct to be added to a list * @matrix: the adapters, usage domains and control domains assigned to the * mediated matrix device. -* @group_notifier: notifier block used for specifying callback function for -* handling the VFIO_GROUP_NOTIFY_SET_KVM event * @iommu_notifier: notifier block used for specifying callback function for * handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even * @kvm: the struct holding guest's state
@@ -94,7 +92,6 @@ struct ap_matrix_mdev {struct vfio_device vdev;struct list_head node;struct ap_matrix matrix; -struct notifier_block group_notifier;struct notifier_block iommu_notifier;struct kvm *kvm;crypto_hook pqap_hook;
drivers/vfio/vfio.c +29 -54
160 lines not on this page · raw message
include/linux/vfio.h +2 -4
@@ -36,6 +36,8 @@ struct vfio_device {struct vfio_device_set *dev_set;struct list_head dev_set_list;unsigned int migration_flags; +/* Driver must reference the kvm during open_device or never touch it */ +struct kvm *kvm;/* Members below here are private, not for driver use */ refcount_t refcount;
@@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,/* each type has independent events */ enum vfio_notify_type {VFIO_IOMMU_NOTIFY =0 , -VFIO_GROUP_NOTIFY =1 , };/* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events,
Signature · 1 line
2.27.0
Looks good:
Quoted 12 lines · Matthew Rosato
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>
Quoted 9 lines
--- drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)
Jason
Tony Krowiak
maintainerQuoted 58 lines · Matthew Rosato
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>--- drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)drivers/s390/crypto/vfio_ap_ops.c +0
-19@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -int notify_rc =NOTIFY_OK ; -struct ap_matrix_mdev *matrix_mdev; - -if (action !=VFIO_GROUP_NOTIFY_SET_KVM ) -return NOTIFY_OK ; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - -if (!data) -vfio_ap_mdev_unset_kvm (matrix_mdev); -else if (vfio_ap_mdev_set_kvm (matrix_mdev, data)) - notify_rc =NOTIFY_DONE ; - -return notify_rc; -} -static struct vfio_ap_queue *vfio_ap_find_queue (int apqn) {struct device *dev;@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)unsigned long events;int ret;
drivers/s390/crypto/vfio_ap_ops.c static int vfio_ap_mdev_open_device(struct vfio_device *vdev) · line 1391
Quoted 10 lines
drivers/s390/crypto/vfio_ap_ops.c +3
-4- matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events =VFIO_GROUP_NOTIFY_SET_KVM ; +if (!vdev->kvm) +return -EINVAL ; - ret =vfio_register_notifier (vdev,VFIO_GROUP_NOTIFY , &events, - &matrix_mdev->group_notifier); + ret =vfio_ap_mdev_set_kvm (matrix_mdev, vdev->kvm);if (ret)return ret;
I'm sorry I didn't see this with my last review, but maybe move the call to vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm) after the successful registration of the IOMMU notifier? This way you won't be plugging AP queues into the guest only to remove them if the registration fails.
Quoted 251 lines
drivers/s390/crypto/vfio_ap_ops.c +3
-6@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret =vfio_register_notifier (vdev,VFIO_IOMMU_NOTIFY , &events, &matrix_mdev->iommu_notifier);if (ret) - goto out_unregister_group; + goto err_kvm;return 0 ; -out_unregister_group: -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier); +err_kvm: +vfio_ap_mdev_unset_kvm (matrix_mdev);return ret; }@@ -1431,8 +1410,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)vfio_unregister_notifier (vdev,VFIO_IOMMU_NOTIFY , &matrix_mdev->iommu_notifier); -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier);vfio_ap_mdev_unset_kvm (matrix_mdev); }drivers/s390/crypto/vfio_ap_private.h +0
-3@@ -81,8 +81,6 @@ struct ap_matrix {* @node: allows the ap_matrix_mdev struct to be added to a list * @matrix: the adapters, usage domains and control domains assigned to the * mediated matrix device. -* @group_notifier: notifier block used for specifying callback function for -* handling the VFIO_GROUP_NOTIFY_SET_KVM event * @iommu_notifier: notifier block used for specifying callback function for * handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even * @kvm: the struct holding guest's state @@ -94,7 +92,6 @@ struct ap_matrix_mdev {struct vfio_device vdev;struct list_head node;struct ap_matrix matrix; -struct notifier_block group_notifier;struct notifier_block iommu_notifier;struct kvm *kvm;crypto_hook pqap_hook;drivers/vfio/vfio.c +29
-54@@ -1083,10 +1083,21 @@ static struct file *vfio_device_open(struct vfio_device *device)mutex_lock (&device->dev_set->lock); device->open_count++; -if (device->open_count ==1 && device->ops->open_device) { - ret = device->ops->open_device (device); -if (ret) - goto err_undo_count; +if (device->open_count ==1 ) { +/* +* Here we pass the KVM pointer with the group under the read +* lock. If the device driver will use it, it must obtain a +* reference and release it during close_device. +*/ +down_read (&device->group->group_rwsem); + device->kvm = device->group->kvm; + +if (device->ops->open_device) { + ret = device->ops->open_device (device); +if (ret) + goto err_undo_count; + } +up_read (&device->group->group_rwsem); }mutex_unlock (&device->dev_set->lock);@@ -1119,10 +1130,14 @@ static struct file *vfio_device_open(struct vfio_device *device) err_close_device:mutex_lock (&device->dev_set->lock); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); err_undo_count: device->open_count--; +if (device->open_count ==0 && device->kvm) + device->kvm =NULL ; +up_read (&device->group->group_rwsem);mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner); err_unassign_container:@@ -1315,9 +1330,13 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)mutex_lock (&device->dev_set->lock);vfio_assert_device_open (device); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); +up_read (&device->group->group_rwsem); device->open_count--; +if (device->open_count ==0 ) + device->kvm =NULL ;mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner);@@ -1726,8 +1745,8 @@ EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);* @file: VFIO group file * @kvm: KVM to link * -* The kvm pointer will be forwarded to all the vfio_device's attached to the -* VFIO file via the VFIO_GROUP_NOTIFY_SET_KVM notifier. +* When a VFIO device is first opened the KVM will be available in +* device->kvm if one was associated with the group. */ void vfio_file_set_kvm (struct file *file,struct kvm *kvm) {@@ -1738,8 +1757,6 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)down_write (&group->group_rwsem); group->kvm = kvm; -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , kvm);up_write (&group->group_rwsem); }EXPORT_SYMBOL_GPL (vfio_file_set_kvm);@@ -2006,7 +2023,8 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->register_notifier))@@ -2014,7 +2032,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group, events, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; }@@ -2026,7 +2043,8 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->unregister_notifier))@@ -2034,47 +2052,10 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; } -static int vfio_register_group_notifier (struct vfio_group *group, -unsigned long *events, -struct notifier_block *nb) -{ -int ret; -bool set_kvm = false; - -if (*events &VFIO_GROUP_NOTIFY_SET_KVM ) - set_kvm = true; - -/* clear known events */ - *events &= ~VFIO_GROUP_NOTIFY_SET_KVM ; - -/* refuse to continue if still events remaining */ -if (*events) -return -EINVAL ; - - ret =blocking_notifier_chain_register (&group->notifier, nb); -if (ret) -return ret; - -/* -* The attaching of kvm and vfio_group might already happen, so -* here we replay once upon registration. -*/ -if (set_kvm) { -down_read (&group->group_rwsem); -if (group->kvm) -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , - group->kvm); -up_read (&group->group_rwsem); - } -return 0 ; -} -int vfio_register_notifier (struct vfio_device *device,enum vfio_notify_type type,unsigned long *events,struct notifier_block *nb)@@ -2090,9 +2071,6 @@ int vfio_register_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_register_iommu_notifier (group, events, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =vfio_register_group_notifier (group, events, nb); -break ;default : ret = -EINVAL ; }@@ -2114,9 +2092,6 @@ int vfio_unregister_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_unregister_iommu_notifier (group, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =blocking_notifier_chain_unregister (&group->notifier, nb); -break ;default : ret = -EINVAL ; }include/linux/vfio.h +2
-4@@ -36,6 +36,8 @@ struct vfio_device {struct vfio_device_set *dev_set;struct list_head dev_set_list;unsigned int migration_flags; +/* Driver must reference the kvm during open_device or never touch it */ +struct kvm *kvm;/* Members below here are private, not for driver use */ refcount_t refcount;@@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,/* each type has independent events */ enum vfio_notify_type {VFIO_IOMMU_NOTIFY =0 , -VFIO_GROUP_NOTIFY =1 , };/* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events,
Quoted 68 lines · Tony Krowiak
Quoted 65 lines · Matthew Rosato
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to device_open. The first time a device is opened associate the group KVM with the device.
This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>---
drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++---------drivers/s390/crypto/vfio_ap_private.h| 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +-7 files changed, 57 insertions(+), 159 deletions(-)drivers/s390/crypto/vfio_ap_ops.c +0
-19@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, - unsigned long action, void *data) -{ - int notify_rc = NOTIFY_OK; - struct ap_matrix_mdev *matrix_mdev; - - if (action != VFIO_GROUP_NOTIFY_SET_KVM) - return NOTIFY_OK; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - - if (!data) - vfio_ap_mdev_unset_kvm(matrix_mdev); - else if (vfio_ap_mdev_set_kvm(matrix_mdev, data)) - notify_rc = NOTIFY_DONE; - - return notify_rc; -} - static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) {struct device *dev;
drivers/s390/crypto/vfio_ap_ops.c +2
-4@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) unsigned long events; int ret; - matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events = VFIO_GROUP_NOTIFY_SET_KVM; + if (!vdev->kvm) + return -EINVAL; - ret = vfio_register_notifier(vdev, VFIO_GROUP_NOTIFY, &events, - &matrix_mdev->group_notifier);
Quoted 8 lines
drivers/s390/crypto/vfio_ap_ops.c static int vfio_ap_mdev_open_device(struct vfio_device *vdev) · line 1391
Quoted 3 lines
drivers/s390/crypto/vfio_ap_ops.c +1
-0+ ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm); if (ret) return ret;I'm sorry I didn't see this with my last review, but maybe move the call to
vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm)after the successful registration of the IOMMU notifier? This way you won't be plugging AP queues into the guest only to remove them if the registration fails.
This is a pretty edge error case, and the vfio_ap_mdev_unset_kvm(matrix_mdev) call at err_kvm should do the proper cleanup, right? I guess I'm wondering if it's really any different than the prior code which would have registered the VFIO_GROUP_NOTIFY_SET_KVM first, which would have immediately triggered the notifier since the KVM was already registered to the group, meaning it would haved called vfio_ap_mdev_group_notifier->vfio_ap_mdev_set_kvm anyway (see vfio_register_group_notifier, the "The attaching of kvm and vfio_group might already happen..." comment)
Quoted 16 lines
Quoted 16 lines
drivers/s390/crypto/vfio_ap_ops.c +3
-4@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events, &matrix_mdev->iommu_notifier); if (ret) - goto out_unregister_group; + goto err_kvm; return 0; -out_unregister_group: - vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY, - &matrix_mdev->group_notifier); +err_kvm: + vfio_ap_mdev_unset_kvm(matrix_mdev); return ret; }
Tony Krowiak
maintainerQuoted 79 lines · Matthew Rosato
Quoted 69 lines · Tony Krowiak
Quoted 66 lines · Matthew Rosato
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to device_open. The first time a device is opened associate the group KVM with the device.
This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>---
drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++---------drivers/s390/crypto/vfio_ap_private.h| 3 - drivers/vfio/vfio.c | 83
++++++++++-----------------
include/linux/vfio.h | 6 +-7 files changed, 57 insertions(+), 159 deletions(-)drivers/s390/crypto/vfio_ap_ops.c +0
-19@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, - unsigned long action, void *data) -{ - int notify_rc = NOTIFY_OK; - struct ap_matrix_mdev *matrix_mdev; - - if (action != VFIO_GROUP_NOTIFY_SET_KVM) - return NOTIFY_OK; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - - if (!data) - vfio_ap_mdev_unset_kvm(matrix_mdev); - else if (vfio_ap_mdev_set_kvm(matrix_mdev, data)) - notify_rc = NOTIFY_DONE; - - return notify_rc; -} - static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) {struct device *dev;
drivers/s390/crypto/vfio_ap_ops.c +2
-4@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) unsigned long events; int ret; - matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events = VFIO_GROUP_NOTIFY_SET_KVM; + if (!vdev->kvm) + return -EINVAL; - ret = vfio_register_notifier(vdev, VFIO_GROUP_NOTIFY, &events, - &matrix_mdev->group_notifier);Quoted 8 lines
drivers/s390/crypto/vfio_ap_ops.c static int vfio_ap_mdev_open_device(struct vfio_device *vdev) · line 1391
Quoted 3 lines
drivers/s390/crypto/vfio_ap_ops.c +1
-0+ ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm); if (ret) return ret;I'm sorry I didn't see this with my last review, but maybe move the call to
vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm)after the successful registration of the IOMMU notifier? This way you won't be plugging AP queues into the guest only to remove them if the registration fails.
Quoted 1 line
This is a pretty edge error case, and the
vfio_ap_mdev_unset_kvm(matrix_mdev)call aterr_kvmshould do the proper cleanup, right? I guess I'm wondering if it's really any different than the prior code which would have registered theVFIO_GROUP_NOTIFY_SET_KVMfirst, which would have immediately triggered the notifier since the KVM was already registered to the group, meaning it would haved calledvfio_ap_mdev_group_notifier->vfio_ap_mdev_set_kvmanyway (seevfio_register_group_notifier, the "The attaching of kvm andvfio_groupmight already happen..." comment)
You are correct, the VFIO_GROUP_NOTIFY_SET_KVM notifier will get triggered when it is registered; however, you may have pointed out a flaw in the previous version of the code. I'm guessing this notifier is not triggered when it is unregistered, so unless the guest is terminated due to a non-zero return code from the open_device callback, it will have access to the AP queues. In hindsight, we probably should have registered the IOMMU notifier first.
You make a valid point about this being an edge case and I don't think it's critical, so feel free to keep it as-is.
My r-b still stands.
Quoted 18 lines
Quoted 17 lines
Quoted 17 lines
drivers/s390/crypto/vfio_ap_ops.c +3
-4@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events, &matrix_mdev->iommu_notifier); if (ret) - goto out_unregister_group; + goto err_kvm; return 0; -out_unregister_group: - vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY, - &matrix_mdev->group_notifier); +err_kvm: + vfio_ap_mdev_unset_kvm(matrix_mdev); return ret; }
Hi Zhi & Zhenyu,
Please review gvt changes below, I'd prefer to get your ack included. Thanks!
Alex
Quoted 543 lines · On Thu, 19 May 2022 14:33:11 -0400 Matthew Rosato <[email protected]>…
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>--- drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)drivers/gpu/drm/i915/gvt/gtt.c +2
-2@@ -51,7 +51,7 @@ static int preallocated_oos_pages = 8192;static bool intel_gvt_is_valid_gfn (struct intel_vgpu *vgpu,unsigned long gfn) { -struct kvm *kvm = vgpu->kvm; +struct kvm *kvm = vgpu->vfio_device.kvm;int idx;bool ret;@@ -1185,7 +1185,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,if (!vgpu->attached)return -EINVAL ; - pfn =gfn_to_pfn (vgpu->kvm, ops->get_pfn (entry)); + pfn =gfn_to_pfn (vgpu->vfio_device.kvm, ops->get_pfn (entry));if (is_error_noslot_pfn (pfn))return -EINVAL ;return PageTransHuge (pfn_to_page (pfn));drivers/gpu/drm/i915/gvt/gvt.h +0
-3@@ -227,9 +227,6 @@ struct intel_vgpu {struct mutex cache_lock;struct notifier_block iommu_notifier; -struct notifier_block group_notifier; -struct kvm *kvm; -struct work_struct release_work;atomic_t released;struct kvm_page_track_notifier_node track_node;drivers/gpu/drm/i915/gvt/kvmgt.c +18
-64@@ -228,8 +228,6 @@ static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt) } } -static void intel_vgpu_release_work (struct work_struct *work); -static void gvt_unpin_guest_page (struct intel_vgpu *vgpu,unsigned long gfn,unsigned long size) {@@ -761,23 +759,6 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,return NOTIFY_OK ; } -static int intel_vgpu_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -struct intel_vgpu *vgpu = - container_of(nb, struct intel_vgpu, group_notifier); - -/* the only action we care about */ -if (action ==VFIO_GROUP_NOTIFY_SET_KVM ) { - vgpu->kvm = data; - -if (!data) -schedule_work (&vgpu->release_work); - } - -return NOTIFY_OK ; -} -static bool __kvmgt_vgpu_exist (struct intel_vgpu *vgpu) {struct intel_vgpu *itr;@@ -789,7 +770,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)if (!itr->attached)continue ; -if (vgpu->kvm == itr->kvm) { +if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) { ret = true; goto out; }@@ -806,7 +787,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)int ret; vgpu->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier; - vgpu->group_notifier.notifier_call = intel_vgpu_group_notifier; events =VFIO_IOMMU_NOTIFY_DMA_UNMAP ; ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,@@ -817,38 +797,32 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) goto out; } - events =VFIO_GROUP_NOTIFY_SET_KVM ; - ret =vfio_register_notifier (vfio_dev,VFIO_GROUP_NOTIFY , &events, - &vgpu->group_notifier); -if (ret !=0 ) { -gvt_vgpu_err ("vfio_register_notifier for group failed: %d\n" , - ret); - goto undo_iommu; - } - ret = -EEXIST ;if (vgpu->attached) - goto undo_register; + goto undo_iommu; ret = -ESRCH ; -if (!vgpu->kvm || vgpu->kvm->mm != current->mm) { +if (!vgpu->vfio_device.kvm || + vgpu->vfio_device.kvm->mm != current->mm) {gvt_vgpu_err ("KVM is required to use Intel vGPU\n" ); - goto undo_register; + goto undo_iommu; } +kvm_get_kvm (vgpu->vfio_device.kvm); + ret = -EEXIST ;if (__kvmgt_vgpu_exist (vgpu)) - goto undo_register; + goto undo_iommu; vgpu->attached = true; -kvm_get_kvm (vgpu->kvm);kvmgt_protect_table_init (vgpu);gvt_cache_init (vgpu); vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; -kvm_page_track_register_notifier (vgpu->kvm, &vgpu->track_node); +kvm_page_track_register_notifier (vgpu->vfio_device.kvm, + &vgpu->track_node);debugfs_create_ulong (KVMGT_DEBUGFS_FILENAME ,0444 , vgpu->debugfs, &vgpu->nr_cache_entries);@@ -858,10 +832,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)atomic_set (&vgpu->released,0 );return 0 ; -undo_register: -vfio_unregister_notifier (vfio_dev,VFIO_GROUP_NOTIFY , - &vgpu->group_notifier); - undo_iommu:vfio_unregister_notifier (vfio_dev,VFIO_IOMMU_NOTIFY , &vgpu->iommu_notifier);@@ -880,8 +850,9 @@ static void intel_vgpu_release_msi_eventfd_ctx(struct intel_vgpu *vgpu) } } -static void __intel_vgpu_release (struct intel_vgpu *vgpu) +static void intel_vgpu_close_device (struct vfio_device *vfio_dev) { +struct intel_vgpu *vgpu =vfio_dev_to_vgpu (vfio_dev);struct drm_i915_private *i915 = vgpu->gvt->gt->i915;int ret;@@ -898,35 +869,19 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)drm_WARN (&i915->drm, ret,"vfio_unregister_notifier for iommu failed: %d\n" , ret); - ret =vfio_unregister_notifier (&vgpu->vfio_device,VFIO_GROUP_NOTIFY , - &vgpu->group_notifier); -drm_WARN (&i915->drm, ret, -"vfio_unregister_notifier for group failed: %d\n" , ret); -debugfs_remove (debugfs_lookup (KVMGT_DEBUGFS_FILENAME , vgpu->debugfs)); -kvm_page_track_unregister_notifier (vgpu->kvm, &vgpu->track_node); -kvm_put_kvm (vgpu->kvm); +kvm_page_track_unregister_notifier (vgpu->vfio_device.kvm, + &vgpu->track_node);kvmgt_protect_table_destroy (vgpu);gvt_cache_destroy (vgpu);intel_vgpu_release_msi_eventfd_ctx (vgpu); - vgpu->kvm =NULL ; vgpu->attached = false; -} - -static void intel_vgpu_close_device (struct vfio_device *vfio_dev) -{ -__intel_vgpu_release (vfio_dev_to_vgpu (vfio_dev)); -} - -static void intel_vgpu_release_work (struct work_struct *work) -{ -struct intel_vgpu *vgpu = - container_of(work, struct intel_vgpu, release_work); -__intel_vgpu_release (vgpu); +if (vgpu->vfio_device.kvm) +kvm_put_kvm (vgpu->vfio_device.kvm); }static u64 intel_vgpu_get_bar_addr (struct intel_vgpu *vgpu,int bar)@@ -1675,7 +1630,6 @@ static int intel_vgpu_probe(struct mdev_device *mdev)return PTR_ERR (vgpu); } -INIT_WORK (&vgpu->release_work, intel_vgpu_release_work);vfio_init_group_dev (&vgpu->vfio_device, &mdev->dev, &intel_vgpu_dev_ops);@@ -1713,7 +1667,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {int intel_gvt_page_track_add (struct intel_vgpu *info,u64 gfn) { -struct kvm *kvm = info->kvm; +struct kvm *kvm = info->vfio_device.kvm;struct kvm_memory_slot *slot;int idx;@@ -1743,7 +1697,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)int intel_gvt_page_track_remove (struct intel_vgpu *info,u64 gfn) { -struct kvm *kvm = info->kvm; +struct kvm *kvm = info->vfio_device.kvm;struct kvm_memory_slot *slot;int idx;drivers/s390/crypto/vfio_ap_ops.c +6
-29@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -int notify_rc =NOTIFY_OK ; -struct ap_matrix_mdev *matrix_mdev; - -if (action !=VFIO_GROUP_NOTIFY_SET_KVM ) -return NOTIFY_OK ; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - -if (!data) -vfio_ap_mdev_unset_kvm (matrix_mdev); -else if (vfio_ap_mdev_set_kvm (matrix_mdev, data)) - notify_rc =NOTIFY_DONE ; - -return notify_rc; -} -static struct vfio_ap_queue *vfio_ap_find_queue (int apqn) {struct device *dev;@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)unsigned long events;int ret; - matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events =VFIO_GROUP_NOTIFY_SET_KVM ; +if (!vdev->kvm) +return -EINVAL ; - ret =vfio_register_notifier (vdev,VFIO_GROUP_NOTIFY , &events, - &matrix_mdev->group_notifier); + ret =vfio_ap_mdev_set_kvm (matrix_mdev, vdev->kvm);if (ret)return ret;@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret =vfio_register_notifier (vdev,VFIO_IOMMU_NOTIFY , &events, &matrix_mdev->iommu_notifier);if (ret) - goto out_unregister_group; + goto err_kvm;return 0 ; -out_unregister_group: -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier); +err_kvm: +vfio_ap_mdev_unset_kvm (matrix_mdev);return ret; }@@ -1431,8 +1410,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)vfio_unregister_notifier (vdev,VFIO_IOMMU_NOTIFY , &matrix_mdev->iommu_notifier); -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier);vfio_ap_mdev_unset_kvm (matrix_mdev); }drivers/s390/crypto/vfio_ap_private.h +0
-3@@ -81,8 +81,6 @@ struct ap_matrix {* @node: allows the ap_matrix_mdev struct to be added to a list * @matrix: the adapters, usage domains and control domains assigned to the * mediated matrix device. -* @group_notifier: notifier block used for specifying callback function for -* handling the VFIO_GROUP_NOTIFY_SET_KVM event * @iommu_notifier: notifier block used for specifying callback function for * handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even * @kvm: the struct holding guest's state @@ -94,7 +92,6 @@ struct ap_matrix_mdev {struct vfio_device vdev;struct list_head node;struct ap_matrix matrix; -struct notifier_block group_notifier;struct notifier_block iommu_notifier;struct kvm *kvm;crypto_hook pqap_hook;drivers/vfio/vfio.c +29
-54@@ -1083,10 +1083,21 @@ static struct file *vfio_device_open(struct vfio_device *device)mutex_lock (&device->dev_set->lock); device->open_count++; -if (device->open_count ==1 && device->ops->open_device) { - ret = device->ops->open_device (device); -if (ret) - goto err_undo_count; +if (device->open_count ==1 ) { +/* +* Here we pass the KVM pointer with the group under the read +* lock. If the device driver will use it, it must obtain a +* reference and release it during close_device. +*/ +down_read (&device->group->group_rwsem); + device->kvm = device->group->kvm; + +if (device->ops->open_device) { + ret = device->ops->open_device (device); +if (ret) + goto err_undo_count; + } +up_read (&device->group->group_rwsem); }mutex_unlock (&device->dev_set->lock);@@ -1119,10 +1130,14 @@ static struct file *vfio_device_open(struct vfio_device *device) err_close_device:mutex_lock (&device->dev_set->lock); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); err_undo_count: device->open_count--; +if (device->open_count ==0 && device->kvm) + device->kvm =NULL ; +up_read (&device->group->group_rwsem);mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner); err_unassign_container:@@ -1315,9 +1330,13 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)mutex_lock (&device->dev_set->lock);vfio_assert_device_open (device); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); +up_read (&device->group->group_rwsem); device->open_count--; +if (device->open_count ==0 ) + device->kvm =NULL ;mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner);@@ -1726,8 +1745,8 @@ EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);* @file: VFIO group file * @kvm: KVM to link * -* The kvm pointer will be forwarded to all the vfio_device's attached to the -* VFIO file via the VFIO_GROUP_NOTIFY_SET_KVM notifier. +* When a VFIO device is first opened the KVM will be available in +* device->kvm if one was associated with the group. */ void vfio_file_set_kvm (struct file *file,struct kvm *kvm) {@@ -1738,8 +1757,6 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)down_write (&group->group_rwsem); group->kvm = kvm; -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , kvm);up_write (&group->group_rwsem); }EXPORT_SYMBOL_GPL (vfio_file_set_kvm);@@ -2006,7 +2023,8 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->register_notifier))@@ -2014,7 +2032,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group, events, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; }@@ -2026,7 +2043,8 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->unregister_notifier))@@ -2034,47 +2052,10 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; } -static int vfio_register_group_notifier (struct vfio_group *group, -unsigned long *events, -struct notifier_block *nb) -{ -int ret; -bool set_kvm = false; - -if (*events &VFIO_GROUP_NOTIFY_SET_KVM ) - set_kvm = true; - -/* clear known events */ - *events &= ~VFIO_GROUP_NOTIFY_SET_KVM ; - -/* refuse to continue if still events remaining */ -if (*events) -return -EINVAL ; - - ret =blocking_notifier_chain_register (&group->notifier, nb); -if (ret) -return ret; - -/* -* The attaching of kvm and vfio_group might already happen, so -* here we replay once upon registration. -*/ -if (set_kvm) { -down_read (&group->group_rwsem); -if (group->kvm) -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , - group->kvm); -up_read (&group->group_rwsem); - } -return 0 ; -} -int vfio_register_notifier (struct vfio_device *device,enum vfio_notify_type type,unsigned long *events,struct notifier_block *nb)@@ -2090,9 +2071,6 @@ int vfio_register_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_register_iommu_notifier (group, events, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =vfio_register_group_notifier (group, events, nb); -break ;default : ret = -EINVAL ; }@@ -2114,9 +2092,6 @@ int vfio_unregister_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_unregister_iommu_notifier (group, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =blocking_notifier_chain_unregister (&group->notifier, nb); -break ;default : ret = -EINVAL ; }include/linux/vfio.h +2
-4@@ -36,6 +36,8 @@ struct vfio_device {struct vfio_device_set *dev_set;struct list_head dev_set_list;unsigned int migration_flags; +/* Driver must reference the kvm during open_device or never touch it */ +struct kvm *kvm;/* Members below here are private, not for driver use */ refcount_t refcount;@@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,/* each type has independent events */ enum vfio_notify_type {VFIO_IOMMU_NOTIFY =0 , -VFIO_GROUP_NOTIFY =1 , };/* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events,
Wang, Zhi A
Acked-byQuoted 548 lines · Alex Williamson
Hi Zhi & Zhenyu,
Please review gvt changes below, I'd prefer to get your ack included. Thanks!
Alex
Quoted 537 lines · On Thu, 19 May 2022 14:33:11 -0400 Matthew Rosato <[email protected]>…
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.This fixes a user-triggerable oops in GVT.
Reviewed-by Tony Krowiak <[email protected]>Reviewed-by Kevin Tian <[email protected]>Reviewed-by Christoph Hellwig <[email protected]>Signed-off-by Jason Gunthorpe <[email protected]>Signed-off-by Matthew Rosato <[email protected]>--- drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)drivers/gpu/drm/i915/gvt/gtt.c +2
-2@@ -51,7 +51,7 @@ static int preallocated_oos_pages = 8192;static bool intel_gvt_is_valid_gfn (struct intel_vgpu *vgpu,unsigned long gfn) { -struct kvm *kvm = vgpu->kvm; +struct kvm *kvm = vgpu->vfio_device.kvm;int idx;bool ret;@@ -1185,7 +1185,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,if (!vgpu->attached)return -EINVAL ; - pfn =gfn_to_pfn (vgpu->kvm, ops->get_pfn (entry)); + pfn =gfn_to_pfn (vgpu->vfio_device.kvm, ops->get_pfn (entry));if (is_error_noslot_pfn (pfn))return -EINVAL ;return PageTransHuge (pfn_to_page (pfn));drivers/gpu/drm/i915/gvt/gvt.h +0
-3@@ -227,9 +227,6 @@ struct intel_vgpu {struct mutex cache_lock;struct notifier_block iommu_notifier; -struct notifier_block group_notifier; -struct kvm *kvm; -struct work_struct release_work;atomic_t released;struct kvm_page_track_notifier_node track_node;drivers/gpu/drm/i915/gvt/kvmgt.c +18
-64@@ -228,8 +228,6 @@ static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt) } } -static void intel_vgpu_release_work (struct work_struct *work); -static void gvt_unpin_guest_page (struct intel_vgpu *vgpu,unsigned long gfn,unsigned long size) {@@ -761,23 +759,6 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,return NOTIFY_OK ; } -static int intel_vgpu_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -struct intel_vgpu *vgpu = - container_of(nb, struct intel_vgpu, group_notifier); - -/* the only action we care about */ -if (action ==VFIO_GROUP_NOTIFY_SET_KVM ) { - vgpu->kvm = data; - -if (!data) -schedule_work (&vgpu->release_work); - } - -return NOTIFY_OK ; -} -static bool __kvmgt_vgpu_exist (struct intel_vgpu *vgpu) {struct intel_vgpu *itr;@@ -789,7 +770,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)if (!itr->attached)continue ; -if (vgpu->kvm == itr->kvm) { +if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) { ret = true; goto out; }@@ -806,7 +787,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)int ret; vgpu->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier; - vgpu->group_notifier.notifier_call = intel_vgpu_group_notifier; events =VFIO_IOMMU_NOTIFY_DMA_UNMAP ; ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,@@ -817,38 +797,32 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) goto out; } - events =VFIO_GROUP_NOTIFY_SET_KVM ; - ret =vfio_register_notifier (vfio_dev,VFIO_GROUP_NOTIFY , &events, - &vgpu->group_notifier); -if (ret !=0 ) { -gvt_vgpu_err ("vfio_register_notifier for group failed: %d\n" , - ret); - goto undo_iommu; - } - ret = -EEXIST ;if (vgpu->attached) - goto undo_register; + goto undo_iommu; ret = -ESRCH ; -if (!vgpu->kvm || vgpu->kvm->mm != current->mm) { +if (!vgpu->vfio_device.kvm || + vgpu->vfio_device.kvm->mm != current->mm) {gvt_vgpu_err ("KVM is required to use Intel vGPU\n" ); - goto undo_register; + goto undo_iommu; } +kvm_get_kvm (vgpu->vfio_device.kvm); + ret = -EEXIST ;if (__kvmgt_vgpu_exist (vgpu)) - goto undo_register; + goto undo_iommu; vgpu->attached = true; -kvm_get_kvm (vgpu->kvm);kvmgt_protect_table_init (vgpu);gvt_cache_init (vgpu); vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; -kvm_page_track_register_notifier (vgpu->kvm, &vgpu->track_node); +kvm_page_track_register_notifier (vgpu->vfio_device.kvm, + &vgpu->track_node);debugfs_create_ulong (KVMGT_DEBUGFS_FILENAME ,0444 , vgpu->debugfs, &vgpu->nr_cache_entries);@@ -858,10 +832,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)atomic_set (&vgpu->released,0 );return 0 ; -undo_register: -vfio_unregister_notifier (vfio_dev,VFIO_GROUP_NOTIFY , - &vgpu->group_notifier); - undo_iommu:vfio_unregister_notifier (vfio_dev,VFIO_IOMMU_NOTIFY , &vgpu->iommu_notifier);@@ -880,8 +850,9 @@ static void intel_vgpu_release_msi_eventfd_ctx(struct intel_vgpu *vgpu) } } -static void __intel_vgpu_release (struct intel_vgpu *vgpu) +static void intel_vgpu_close_device (struct vfio_device *vfio_dev) { +struct intel_vgpu *vgpu =vfio_dev_to_vgpu (vfio_dev);struct drm_i915_private *i915 = vgpu->gvt->gt->i915;int ret;@@ -898,35 +869,19 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)drm_WARN (&i915->drm, ret,"vfio_unregister_notifier for iommu failed: %d\n" , ret); - ret =vfio_unregister_notifier (&vgpu->vfio_device,VFIO_GROUP_NOTIFY , - &vgpu->group_notifier); -drm_WARN (&i915->drm, ret, -"vfio_unregister_notifier for group failed: %d\n" , ret); -debugfs_remove (debugfs_lookup (KVMGT_DEBUGFS_FILENAME , vgpu->debugfs)); -kvm_page_track_unregister_notifier (vgpu->kvm, &vgpu->track_node); -kvm_put_kvm (vgpu->kvm); +kvm_page_track_unregister_notifier (vgpu->vfio_device.kvm, + &vgpu->track_node);kvmgt_protect_table_destroy (vgpu);gvt_cache_destroy (vgpu);intel_vgpu_release_msi_eventfd_ctx (vgpu); - vgpu->kvm =NULL ; vgpu->attached = false; -} - -static void intel_vgpu_close_device (struct vfio_device *vfio_dev) -{ -__intel_vgpu_release (vfio_dev_to_vgpu (vfio_dev)); -} - -static void intel_vgpu_release_work (struct work_struct *work) -{ -struct intel_vgpu *vgpu = - container_of(work, struct intel_vgpu, release_work); -__intel_vgpu_release (vgpu); +if (vgpu->vfio_device.kvm) +kvm_put_kvm (vgpu->vfio_device.kvm); }static u64 intel_vgpu_get_bar_addr (struct intel_vgpu *vgpu,int bar)@@ -1675,7 +1630,6 @@ static int intel_vgpu_probe(struct mdev_device *mdev)return PTR_ERR (vgpu); } -INIT_WORK (&vgpu->release_work, intel_vgpu_release_work);vfio_init_group_dev (&vgpu->vfio_device, &mdev->dev, &intel_vgpu_dev_ops);@@ -1713,7 +1667,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {int intel_gvt_page_track_add (struct intel_vgpu *info,u64 gfn) { -struct kvm *kvm = info->kvm; +struct kvm *kvm = info->vfio_device.kvm;struct kvm_memory_slot *slot;int idx;@@ -1743,7 +1697,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)int intel_gvt_page_track_remove (struct intel_vgpu *info,u64 gfn) { -struct kvm *kvm = info->kvm; +struct kvm *kvm = info->vfio_device.kvm;struct kvm_memory_slot *slot;int idx;drivers/s390/crypto/vfio_ap_ops.c +6
-29@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) } } -static int vfio_ap_mdev_group_notifier (struct notifier_block *nb, -unsigned long action,void *data) -{ -int notify_rc =NOTIFY_OK ; -struct ap_matrix_mdev *matrix_mdev; - -if (action !=VFIO_GROUP_NOTIFY_SET_KVM ) -return NOTIFY_OK ; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); - -if (!data) -vfio_ap_mdev_unset_kvm (matrix_mdev); -else if (vfio_ap_mdev_set_kvm (matrix_mdev, data)) - notify_rc =NOTIFY_DONE ; - -return notify_rc; -} -static struct vfio_ap_queue *vfio_ap_find_queue (int apqn) {struct device *dev;@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)unsigned long events;int ret; - matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier; - events =VFIO_GROUP_NOTIFY_SET_KVM ; +if (!vdev->kvm) +return -EINVAL ; - ret =vfio_register_notifier (vdev,VFIO_GROUP_NOTIFY , &events, - &matrix_mdev->group_notifier); + ret =vfio_ap_mdev_set_kvm (matrix_mdev, vdev->kvm);if (ret)return ret;@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) ret =vfio_register_notifier (vdev,VFIO_IOMMU_NOTIFY , &events, &matrix_mdev->iommu_notifier);if (ret) - goto out_unregister_group; + goto err_kvm;return 0 ; -out_unregister_group: -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier); +err_kvm: +vfio_ap_mdev_unset_kvm (matrix_mdev);return ret; }@@ -1431,8 +1410,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)vfio_unregister_notifier (vdev,VFIO_IOMMU_NOTIFY , &matrix_mdev->iommu_notifier); -vfio_unregister_notifier (vdev,VFIO_GROUP_NOTIFY , - &matrix_mdev->group_notifier);vfio_ap_mdev_unset_kvm (matrix_mdev); }drivers/s390/crypto/vfio_ap_private.h +0
-3@@ -81,8 +81,6 @@ struct ap_matrix {* @node: allows the ap_matrix_mdev struct to be added to a list * @matrix: the adapters, usage domains and control domains assigned to the * mediated matrix device. -* @group_notifier: notifier block used for specifying callback function for -* handling the VFIO_GROUP_NOTIFY_SET_KVM event * @iommu_notifier: notifier block used for specifying callback function for * handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even * @kvm: the struct holding guest's state @@ -94,7 +92,6 @@ struct ap_matrix_mdev {struct vfio_device vdev;struct list_head node;struct ap_matrix matrix; -struct notifier_block group_notifier;struct notifier_block iommu_notifier;struct kvm *kvm;crypto_hook pqap_hook;drivers/vfio/vfio.c +29
-54@@ -1083,10 +1083,21 @@ static struct file *vfio_device_open(struct vfio_device *device)mutex_lock (&device->dev_set->lock); device->open_count++; -if (device->open_count ==1 && device->ops->open_device) { - ret = device->ops->open_device (device); -if (ret) - goto err_undo_count; +if (device->open_count ==1 ) { +/* +* Here we pass the KVM pointer with the group under the read +* lock. If the device driver will use it, it must obtain a +* reference and release it during close_device. +*/ +down_read (&device->group->group_rwsem); + device->kvm = device->group->kvm; + +if (device->ops->open_device) { + ret = device->ops->open_device (device); +if (ret) + goto err_undo_count; + } +up_read (&device->group->group_rwsem); }mutex_unlock (&device->dev_set->lock);@@ -1119,10 +1130,14 @@ static struct file *vfio_device_open(struct vfio_device *device) err_close_device:mutex_lock (&device->dev_set->lock); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); err_undo_count: device->open_count--; +if (device->open_count ==0 && device->kvm) + device->kvm =NULL ; +up_read (&device->group->group_rwsem);mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner); err_unassign_container:@@ -1315,9 +1330,13 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)mutex_lock (&device->dev_set->lock);vfio_assert_device_open (device); +down_read (&device->group->group_rwsem);if (device->open_count ==1 && device->ops->close_device) device->ops->close_device (device); +up_read (&device->group->group_rwsem); device->open_count--; +if (device->open_count ==0 ) + device->kvm =NULL ;mutex_unlock (&device->dev_set->lock);module_put (device->dev->driver->owner);@@ -1726,8 +1745,8 @@ EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);* @file: VFIO group file * @kvm: KVM to link * -* The kvm pointer will be forwarded to all the vfio_device's attached to the -* VFIO file via the VFIO_GROUP_NOTIFY_SET_KVM notifier. +* When a VFIO device is first opened the KVM will be available in +* device->kvm if one was associated with the group. */ void vfio_file_set_kvm (struct file *file,struct kvm *kvm) {@@ -1738,8 +1757,6 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)down_write (&group->group_rwsem); group->kvm = kvm; -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , kvm);up_write (&group->group_rwsem); }EXPORT_SYMBOL_GPL (vfio_file_set_kvm);@@ -2006,7 +2023,8 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->register_notifier))@@ -2014,7 +2032,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group, events, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; }@@ -2026,7 +2043,8 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,struct vfio_iommu_driver *driver;int ret; -down_read (&group->group_rwsem); +lockdep_assert_held_read (&group->group_rwsem); + container = group->container; driver = container->iommu_driver;if (likely (driver && driver->ops->unregister_notifier))@@ -2034,47 +2052,10 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group, nb); else ret = -ENOTTY ; -up_read (&group->group_rwsem);return ret; } -static int vfio_register_group_notifier (struct vfio_group *group, -unsigned long *events, -struct notifier_block *nb) -{ -int ret; -bool set_kvm = false; - -if (*events &VFIO_GROUP_NOTIFY_SET_KVM ) - set_kvm = true; - -/* clear known events */ - *events &= ~VFIO_GROUP_NOTIFY_SET_KVM ; - -/* refuse to continue if still events remaining */ -if (*events) -return -EINVAL ; - - ret =blocking_notifier_chain_register (&group->notifier, nb); -if (ret) -return ret; - -/* -* The attaching of kvm and vfio_group might already happen, so -* here we replay once upon registration. -*/ -if (set_kvm) { -down_read (&group->group_rwsem); -if (group->kvm) -blocking_notifier_call_chain (&group->notifier, -VFIO_GROUP_NOTIFY_SET_KVM , - group->kvm); -up_read (&group->group_rwsem); - } -return 0 ; -} -int vfio_register_notifier (struct vfio_device *device,enum vfio_notify_type type,unsigned long *events,struct notifier_block *nb)@@ -2090,9 +2071,6 @@ int vfio_register_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_register_iommu_notifier (group, events, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =vfio_register_group_notifier (group, events, nb); -break ;default : ret = -EINVAL ; }@@ -2114,9 +2092,6 @@ int vfio_unregister_notifier(struct vfio_device *device,case VFIO_IOMMU_NOTIFY : ret =vfio_unregister_iommu_notifier (group, nb);break ; -case VFIO_GROUP_NOTIFY : - ret =blocking_notifier_chain_unregister (&group->notifier, nb); -break ;default : ret = -EINVAL ; }include/linux/vfio.h +2
-1@@ -36,6 +36,8 @@ struct vfio_device {struct vfio_device_set *dev_set;struct list_head dev_set_list;unsigned int migration_flags; +/* Driver must reference the kvm during open_device or never touch it */ +struct kvm *kvm;/* Members below here are private, not for driver use */ refcount_t refcount;@@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,/* each type has independent events */ enum vfio_notify_type {VFIO_IOMMU_NOTIFY =0 , -VFIO_GROUP_NOTIFY =1 , };/* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0)
Quoted 7 lines
include/linux/vfio.h extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, · line 167
Quoted 6 lines
include/linux/vfio.h +0
-3-/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events,
Quoted 6 lines · On Thu, 19 May 2022 14:33:11 -0400 Matthew Rosato <[email protected]>…
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.This fixes a user-triggerable oops in GVT.
It seems this has traded an oops for a deadlock, which still exists today in both GVT-g and vfio-ap. These are the only vfio drivers that care about kvm, so they make use of kvm_{get,put}_kvm(), where the latter is called by their .close_device() callbacks.
.close_device() is called holding the group->group_lock, or at the time of this commit group->group_rwsem. The remaining call chain looks like this:
kvm_put_kvm
-> kvm_destroy_vm
-> kvm_destroy_devices
-> kvm_vfio_destroy
-> kvm_vfio_file_set_kvm
-> vfio_file_set_kvm
-> group->group_lock/group_rwsemAny suggestions for a fix? Thanks,
Alex
Quoted 8 lines · Alex Williamson
Quoted 5 lines · On Thu, 19 May 2022 14:33:11 -0400 Matthew Rosato <[email protected]>…
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.
Quoted 6 lines
Quoted 1 line
This fixes a user-triggerable oops in GVT.
It seems this has traded an oops for a deadlock, which still exists today in both GVT-g and vfio-ap. These are the only vfio drivers that care about kvm, so they make use of kvm_{get,put}_kvm(), where the latter is called by their .close_device() callbacks.
Bleck
It is pretty common to run the final part of 'put' from a workqueue specifically to avoid stuff like this, eg fput does it
Maybe that is the simplest?
Jason
Quoted 9 lines · Jason Gunthorpe
Quoted 8 lines · Alex Williamson
Quoted 5 lines · On Thu, 19 May 2022 14:33:11 -0400 Matthew Rosato <[email protected]>…
Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to
device_open. The first time a device is opened associate the group KVM with the device.
Quoted 5 lines
Quoted 5 lines
Quoted 1 line
This fixes a user-triggerable oops in GVT.
It seems this has traded an oops for a deadlock, which still exists today in both GVT-g and vfio-ap. These are the only vfio drivers that care about kvm, so they make use of kvm_{get,put}_kvm(), where the
vfio-pci-zdev also
Quoted 1 line
Quoted 1 line
latter is called by their .close_device() callbacks.
Huh, I've never seen this deadlock with vfio-pci-zdev or vfio-ap, but I see what you're saying... I guess it's not seen under typical circumstances with QEMU because kvm_vfio_group_del would have already been triggered via KVM_DEV_VFIO_GROUP_DEL by the time we close the device, such that the group would not be found during the kvm_vfio_destroy call? (I'm not at all suggesting that we should rely on userspace behaving in this order, just wondering why I never saw it while testing)
Quoted 7 lines
Bleck
It is pretty common to run the final part of 'put' from a workqueue specifically to avoid stuff like this, eg fput does it
Maybe that is the simplest?
Yeah, this is also what I was thinking, replace the direct kvm_put_kvm calls with, say, schedule_delayed_work in each driver, where the delayed task just does the kvm_put_kvm (along with a brief comment explaining why we handle the put asynchronously).
Other than that.. The goal of this patch originally was to get the kvm reference at first open_device and release it with the very last close_device, so the only other option I could think of would be to take the responsibility back from the vfio drivers and do the kvm_get_kvm and kvm_put_kvm directly in vfio_main after dropping the (but that would result in some ugly symbol linkage and would acquire kvm references that a driver maybe does not care about so I don't really like that idea)
Quoted 4 lines · Matthew Rosato
Yeah, this is also what I was thinking, replace the direct
kvm_put_kvmcalls with, say,schedule_delayed_workin each driver, where the delayed task just does thekvm_put_kvm(along with a brief comment explaining why we handle the put asynchronously).
Don't put that in every driver, do something like mmput_async() where the core code has all of this.
Quoted 8 lines
Other than that.. The goal of this patch originally was to get the kvm reference at first
open_deviceand release it with the very lastclose_device, so the only other option I could think of would be to take the responsibility back from the vfio drivers and do thekvm_get_kvmandkvm_put_kvmdirectly invfio_mainafter dropping the (but that would result in some ugly symbol linkage and would acquire kvm references that a driver maybe does not care about so I don't really like that idea)
And we still have the deadlock problem anyhow..
Jason
Quoted 10 lines · Jason Gunthorpe
Quoted 4 lines · Matthew Rosato
Yeah, this is also what I was thinking, replace the direct
kvm_put_kvmcalls with, say,schedule_delayed_workin each driver, where the delayed task just does thekvm_put_kvm(along with a brief comment explaining why we handle the put asynchronously).Don't put that in every driver, do something like
mmput_async()where the core code has all of this.
If the core vfio code were to add logic to invoke kvm_put_kvm and kvm_get_kvm, won't this introduce a vfio dependency on kvm? If I recall, we have the drivers handling the kvm reference today in order to avoid that..
Quoted 10 lines
Quoted 8 lines
Other than that.. The goal of this patch originally was to get the kvm reference at first
open_deviceand release it with the very lastclose_device, so the only other option I could think of would be to take the responsibility back from the vfio drivers and do thekvm_get_kvmandkvm_put_kvmdirectly invfio_mainafter dropping the (but that would result in some ugly symbol linkage and would acquire kvm references that a driver maybe does not care about so I don't really like that idea)And we still have the deadlock problem anyhow..
Looks like I never finished my sentence here -- I meant call kvm_put_kvm directly in vfio_main after dropping the group lock (e.g. when we set device->kvm = NULL;). But I think we'd still have the kvm dependency issue
Quoted 8 lines · Matthew Rosato
Quoted 7 lines · Jason Gunthorpe
Quoted 4 lines · Matthew Rosato
Yeah, this is also what I was thinking, replace the direct
kvm_put_kvmcalls with, say,schedule_delayed_workin each driver, where the delayed task just does thekvm_put_kvm(along with a brief comment explaining why we handle the put asynchronously).
Quoted 8 lines
Quoted 3 lines
Don't put that in every driver, do something like
mmput_async()where the core code has all of this.If the core vfio code were to add logic to invoke
kvm_put_kvmandkvm_get_kvm, won't this introduce a vfio dependency on kvm? If I recall, we have the drivers handling the kvm reference today in order to avoid that..
Not in vfio, put it in kvm 'kvm_put_async()'
Jason
Alex Williamson
AppliedQuoted 37 lines · On Thu, 19 May 2022 14:33:10 -0400 Matthew Rosato <[email protected]>…
As discussed in this thread:
https://lore.kernel.org/kvm/[email protected]/
Let's remove
VFIO_GROUP_NOTIFY_SET_KVMand instead assume the association has already been established prior todevice_open. For the types today that need a KVM (GVT, vfio-ap) these will fail if a KVM is not found. Looking ahead, vfio-pci-zdev will optionally want the KVM association (enable hardware assists) but it will not be a hard requirement (still want to allow other, non-KVM userspace usage).This is built on top of vfio-next and tested with s390x-pci (zdev-kvm series) and vfio-ap (GVT changes are compile-tested only)
Changes for v3:
- merge branches under if (device->open_count== 1) (Kevin)
- move device->open_count-- out fromgroup_rwsem(Kevin)
- drop null KVM check (Christoph)
- remove extra kvm_{get,put}_kvm fromvfio_ap_ops, it was already getting a reference (Jason)
- Add comment about kvm reference invfio.h(Jason)
- Return-EINVALif !kvm for vfio-ap (Tony)Changes for v2:
- gvt no longer needsrelease_work, get rid of it (Christoph)
- a few compile fixes for gvt
- update commit to mention fixes gvt oops (Jason)
- s/down_write/down_read/ in a few spots (Jason)
- avoid kvm build dependency by holding group read lock over device open/close and put the onus on the driver to obtain a reference if it will actually use the kvm pointer. Document the requirement, uselockdep_assertto ensure lock is held duringregister_notifer; today all callers are from driveropen_device.Matthew Rosato (1):
vfio: removeVFIO_GROUP_NOTIFY_SET_KVM
Quoted 8 lines
drivers/gpu/drm/i915/gvt/gtt.c | 4 +- drivers/gpu/drm/i915/gvt/gvt.h | 3 - drivers/gpu/drm/i915/gvt/kvmgt.c | 82 ++++++-------------------- drivers/s390/crypto/vfio_ap_ops.c | 35 ++--------- drivers/s390/crypto/vfio_ap_private.h | 3 - drivers/vfio/vfio.c | 83 ++++++++++----------------- include/linux/vfio.h | 6 +- 7 files changed, 57 insertions(+), 159 deletions(-)
Applied to vfio next branch for v5.19. Thanks,
Alex