Commit 421cfe65 authored by Matthew Rosato's avatar Matthew Rosato Committed by Alex Williamson
Browse files

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.

Reviewed-by: default avatarTony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: default avatarKevin Tian <kevin.tian@intel.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Signed-off-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Signed-off-by: default avatarMatthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Acked-by: default avatarZhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20220519183311.582380-2-mjrosato@linux.ibm.com


Signed-off-by: default avatarAlex Williamson <alex.williamson@redhat.com>
parent c490513c
Loading
Loading
Loading
Loading
+2 −2
Original line number Diff line number Diff line
@@ -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));
+0 −3
Original line number Diff line number Diff line
@@ -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;
+18 −64
Original line number Diff line number Diff line
@@ -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;

+6 −29
Original line number Diff line number Diff line
@@ -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);
}

+0 −3
Original line number Diff line number Diff line
@@ -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;
Loading