Skip to contentSkip to conversation

vfio: remove VFIO_GROUP_NOTIFY_SET_KVM

PATCH Superseded Matthew Rosato 5 participants 8 messages May 18, 2022 – May 19, 2022

Subsystems (8)
DRM drivers KVM Intel i915 s390 +4 more subsystems

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

v2 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 Jason's group locking series:
https://github.com/jgunthorpe/linux/commits/vfio_group_locking

And tested with s390x-pci (zdev-kvm series) and vfio-ap (GVT changes are compile-tested only)

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     | 38 ++++---------
 drivers/s390/crypto/vfio_ap_private.h |  3 -
 drivers/vfio/vfio.c                   | 75 ++++++++----------------
 include/linux/vfio.h                  |  5 +-
 7 files changed, 56 insertions(+), 154 deletions(-)
Signature · 1 line
2.27.0
#1 lore raw

PATCH v2 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     | 38 ++++---------
 drivers/s390/crypto/vfio_ap_private.h |  3 -
 drivers/vfio/vfio.c                   | 75 ++++++++----------------
 include/linux/vfio.h                  |  5 +-
 7 files changed, 56 insertions(+), 154 deletions(-)
drivers/gpu/drm/i915/gvt/gtt.c +2 -2
index 9c5cc2800975..b4f69364f9a1 100644
@@ -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
index 2af4c83e733c..aee1a45da74b 100644
@@ -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 +10 -28
index e8914024f5b1..17a56bb4cf25 100644
@@ -1196,6 +1196,8 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 {
 	struct ap_matrix_mdev *m;
 
+	kvm_get_kvm(kvm);
+
 	if (kvm->arch.crypto.crycbd) {
 		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
 		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
@@ -1282,25 +1284,9 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 		mutex_unlock(&kvm->lock);
 		mutex_unlock(&matrix_dev->lock);
 	}
-}
 
-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;
+	if (kvm)
+		kvm_put_kvm(kvm);
 }
 
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
@@ -1402,11 +1388,10 @@ 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 -EPERM;
 
-	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 +1400,11 @@ 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 +1415,6 @@ 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
index 648fcaf8104a..a26efd804d0d 100644
@@ -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 +25 -50

157 lines not on this page · raw message

include/linux/vfio.h +1 -4
index 45b287826ce6..5f691453e3fb 100644
@@ -36,6 +36,7 @@ struct vfio_device {
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
 	unsigned int migration_flags;
+	struct kvm *kvm;
 
 	/* Members below here are private, not for driver use */
 	refcount_t refcount;
@@ -155,15 +156,11 @@ 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
Reviewed-by on v2 1/1
#2 lore raw
Quoted 9 lines

From: Matthew Rosato
Sent: Thursday, May 19, 2022 5:26 AM

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.

No changelog.

Quoted 3 lines

Not sure whether Christoph wants a s-o-b here when he wrote the snippet to remove the release work of gvt...

Quoted 10 lines
drivers/vfio/vfio.c +4 -0
@@ -1083,11 +1083,22 @@ static struct file *vfio_device_open(struct
 vfio_device *device)
 
 	mutex_lock(&device->dev_set->lock);
 	device->open_count++;
+	down_read(&device->group->group_rwsem);
+	if (device->open_count == 1 && device->group->kvm) {
+		/*
+		 * Here we pass the KVM pointer with the group under the

read

drivers/vfio/vfio.c static struct file *vfio_device_open(struct vfio_device *device) · line 1096

Quoted 7 lines
drivers/vfio/vfio.c +6 -0
+		 * lock.  If the device driver will use it, it must obtain a
+		 * reference and release it during close_device.
+		 */
+		device->kvm = device->group->kvm;
+	}
+
 	if (device->open_count == 1 && device->ops->open_device) {

Merge the two branches so both are under if (device->open_count == 1) {} (and group_rwsem can be also moved inside)

drivers/vfio/vfio.c static int vfio_device_fops_release(struct inode · line 1339

Quoted 11 lines
drivers/vfio/vfio.c +3 -0
@@ -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);
 	device->open_count--;
+	if (device->open_count == 0 && device->kvm)
+		device->kvm = NULL;

This can be moved out of group_rwsem as there is no reference to vfio_group.

Review static int vfio_device_fops_release(struct inode · line 1340

Quoted 1 line
(quoted diff) +1 -0
+	up_read(&device->group->group_rwsem);

otherwise,

Thanks
Kevin

Reviewed-by Christoph Hellwig
#3 lore raw
Quoted 3 lines · Kevin
Quoted 1 line

This fixes a user-triggerable oops in GVT.

No changelog.

??

the cover latter clearly states what has changed since v1, and this patch has a good commit log. This is exactly how it is supposed to be done.

Quoted 7 lines
Quoted 4 lines

Not sure whether Christoph wants a s-o-b here when he wrote the snippet to remove the release work of gvt...

That's just tivial code removal, so no.

Quoted 13 lines
Quoted 13 lines
drivers/vfio/vfio.c +4 -0
@@ -1083,11 +1083,22 @@ static struct file *vfio_device_open(struct
 vfio_device *device)
 
 	mutex_lock(&device->dev_set->lock);
 	device->open_count++;
+	down_read(&device->group->group_rwsem);
+	if (device->open_count == 1 && device->group->kvm) {
+		/*
+		 * Here we pass the KVM pointer with the group under the

read

drivers/vfio/vfio.c +2 -0
+		 * lock.  If the device driver will use it, it must obtain a
+		 * reference and release it during close_device.
Quoted 8 lines

drivers/vfio/vfio.c static struct file *vfio_device_open(struct vfio_device *device) · line 1096

Quoted 5 lines
drivers/vfio/vfio.c +4 -0
+		 */
+		device->kvm = device->group->kvm;
+	}
+
 	if (device->open_count == 1 && device->ops->open_device) {

Merge the two branches so both are under if (device->open_count == 1) {} (and group_rwsem can be also moved inside)

Yeah. And we don't really need the device->group->kvm check, as it would otherwise assign NULL which is perfectly fine.

But otherwise this also looks good to me:

#4 lore raw
Quoted 6 lines

From: [email protected] <[email protected]>
Sent: Thursday, May 19, 2022 2:48 PM

Quoted 2 lines · Kevin
Quoted 1 line

This fixes a user-triggerable oops in GVT.

Quoted 7 lines
Quoted 1 line

No changelog.

??

the cover latter clearly states what has changed since v1, and this patch has a good commit log. This is exactly how it is supposed to be done.

sigh... don't know why I missed the coverletter.

#5 lore raw
In reply to Matthew Rosato
Quoted 9 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.

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     | 38 ++++---------
 drivers/s390/crypto/vfio_ap_private.h |  3 -
 drivers/vfio/vfio.c                   | 75 ++++++++----------------
 include/linux/vfio.h                  |  5 +-
 7 files changed, 56 insertions(+), 154 deletions(-)

I'm fine with this, thanks for finishing it

Quoted 10 lines
drivers/s390/crypto/vfio_ap_ops.c +2 -0
index e8914024f5b1..17a56bb4cf25 100644
@@ -1196,6 +1196,8 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 {
        struct ap_matrix_mdev *m;
 
+       kvm_get_kvm(kvm);
+

[..]

drivers/s390/crypto/vfio_ap_ops.c static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) · line 1290

Quoted 3 lines
drivers/s390/crypto/vfio_ap_ops.c +2 -0
+       if (kvm)
+               kvm_put_kvm(kvm);
 }

This extra ref traffic is not necessary, the kvm will have a valid ref because we are under the group_rwsem here and then the function will obtain a ref when it stores it in matrix_mdev->kvm.

Quoted 7 lines
drivers/vfio/vfio.c +0 -0
index cfcff7764403..272acb62facd 100644
@@ -1083,11 +1083,22 @@ static struct file *vfio_device_open(struct vfio_device *device)
 
 	mutex_lock(&device->dev_set->lock);

drivers/vfio/vfio.c static struct file *vfio_device_open(struct vfio_device *device) · line 1094

Quoted 10 lines
drivers/vfio/vfio.c +9 -0
 	device->open_count++;
+	down_read(&device->group->group_rwsem);
+	if (device->open_count == 1 && device->group->kvm) {
+		/*
+		 * 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.
+		 */
+		device->kvm = device->group->kvm;
+	}

But it is a bit ugly to keep the device->kvm in the struct device without holding a reference count.

It is probably worth adding a comment to the definition in the struct as well that the device driver must reference it or never touch it.

Jason

maintainer Reviewed-by on v2 1/1
#6 lore raw
In reply to Matthew Rosato

I made a few comments, but other than that this looks good to me:

Quoted 250 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.

---
  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     | 38 ++++---------
  drivers/s390/crypto/vfio_ap_private.h |  3 -
  drivers/vfio/vfio.c                   | 75 ++++++++----------------
  include/linux/vfio.h                  |  5 +-
  7 files changed, 56 insertions(+), 154 deletions(-)
drivers/gpu/drm/i915/gvt/gtt.c +2 -2
index 9c5cc2800975..b4f69364f9a1 100644
@@ -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
index 2af4c83e733c..aee1a45da74b 100644
@@ -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
index 7655ffa97d51..e2f6c56ab342 100644
@@ -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 +0 -0
index e8914024f5b1..17a56bb4cf25 100644

drivers/s390/crypto/vfio_ap_ops.c static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, · line 1200

Quoted 5 lines
drivers/s390/crypto/vfio_ap_ops.c +2 -0
@@ -1196,6 +1196,8 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
  {
  	struct ap_matrix_mdev *m;
 
+	kvm_get_kvm(kvm);
+

I'm not sure what version of the code on which the patch was rebased, but in the latest master branch from our repository the kvm_get_kvm(kvm) function is called inside of the if block below. I'm fine with moving outside of the block, but I don't see a corresponding removal of it from inside the block.

Quoted 16 lines
drivers/s390/crypto/vfio_ap_ops.c +0 -8
  	if (kvm->arch.crypto.crycbd) {
  		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
  		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
@@ -1282,25 +1284,9 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
  		mutex_unlock(&kvm->lock);
  		mutex_unlock(&matrix_dev->lock);
  	}
-}
 
-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)

drivers/s390/crypto/vfio_ap_ops.c static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) · line 1303

Quoted 10 lines
drivers/s390/crypto/vfio_ap_ops.c +0 -10
-		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;

Similarly, there is a call to kvm_put_kvm(kvm) inside the if block. Again, I'm okay with moving this outside of the if block, but I would think the call inside the if block ought to be removed.

drivers/s390/crypto/vfio_ap_ops.c static int vfio_ap_mdev_open_device(struct vfio_device *vdev) · line 1392

Quoted 13 lines
drivers/s390/crypto/vfio_ap_ops.c +4 -2
+	if (kvm)
+		kvm_put_kvm(kvm);
  }
 
  static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
@@ -1402,11 +1388,10 @@ 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 -EPERM;

Perhaps -EINVAL or -EFAULT?

Quoted 24 lines
drivers/s390/crypto/vfio_ap_ops.c +4 -6
-	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 +1400,11 @@ 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;
  }
 

drivers/s390/crypto/vfio_ap_ops.c static void vfio_ap_mdev_close_device(struct vfio_device *vdev) · line 1418

Quoted 6 lines
drivers/s390/crypto/vfio_ap_ops.c +0 -2
@@ -1431,8 +1415,6 @@ 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);

I'm not sure if this matters, but the vfio_ap_mdev_unset_kvm(matrix_mdev) function uses the KVM pointer stored in matrix_mdev->kvm. I can't imagine the KVM pointer stored in vdev->kvm being different than matrix_mdev->kvm, but thought I should point it out. Previously, this function was called by the notifier handler which did not have access to the KVM pointer which is why it was retrieved from matrix_mdev->kvm. Even if the vdev->kvm and matrix_mdev->kvm did not match, we should probably go ahead and call the unset function anyway to remove access to AP resources for the guest and reset the queues.

Quoted 223 lines
drivers/s390/crypto/vfio_ap_ops.c +0 -0
  }
 
drivers/s390/crypto/vfio_ap_private.h +0 -3
index 648fcaf8104a..a26efd804d0d 100644
@@ -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 +25 -50
index cfcff7764403..272acb62facd 100644
@@ -1083,11 +1083,22 @@ static struct file *vfio_device_open(struct vfio_device *device)
 
  	mutex_lock(&device->dev_set->lock);
  	device->open_count++;
+	down_read(&device->group->group_rwsem);
+	if (device->open_count == 1 && device->group->kvm) {
+		/*
+		 * 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.
+		 */
+		device->kvm = device->group->kvm;
+	}
+
  	if (device->open_count == 1 && 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);
  	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);
@@ -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 +1 -4
index 45b287826ce6..5f691453e3fb 100644
@@ -36,6 +36,7 @@ struct vfio_device {
  	struct vfio_device_set *dev_set;
  	struct list_head dev_set_list;
  	unsigned int migration_flags;
+	struct kvm *kvm;
 
  	/* Members below here are private, not for driver use */
  	refcount_t refcount;
@@ -155,15 +156,11 @@ 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,
#7 lore raw
Quoted 5 lines · Tony Krowiak

I made a few comments, but other than that this looks good to me:

...

Quoted 1 line

I'm not sure what version of the code on which the patch was rebased,

Was on top of Jason's vfio_group_locking series, but now would apply on vfio-next since Alex pulled that series in to vfio-next.

Quoted 4 lines

but in the
latest master branch from our repository the kvm_get_kvm(kvm) function is called inside of the if block below. I'm fine with moving outside of the block, but I don't see a corresponding removal of it from inside the block.

Yeah, I didn't notice those there. v3 will simply remove my get/put additions and leave yours as-is.

...

Quoted 7 lines
Quoted 4 lines

vfio_ap_mdev_group_notifier;
-    events = VFIO_GROUP_NOTIFY_SET_KVM;
+    if (!vdev->kvm)
+        return -EPERM;

Perhaps -EINVAL or -EFAULT?

Whichever you'd prefer? If I don't hear back I'll just use -EINVAL in v3.

Quoted 23 lines
Quoted 23 lines

-    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;

drivers/s390/crypto/vfio_ap_ops.c +3 -4
@@ -1415,12 +1400,11 @@ 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 +1415,6 @@ static void vfio_ap_mdev_close_device(struct 
 vfio_device *vdev)
       vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
Quoted 8 lines

drivers/s390/crypto/vfio_ap_ops.c static void vfio_ap_mdev_close_device(struct vfio_device *vdev) · line 1418

Quoted 4 lines
drivers/s390/crypto/vfio_ap_ops.c +0 -2
                    &matrix_mdev->iommu_notifier);
-    vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY,
-                 &matrix_mdev->group_notifier);
       vfio_ap_mdev_unset_kvm(matrix_mdev);

I'm not sure if this matters, but the vfio_ap_mdev_unset_kvm(matrix_mdev) function uses the KVM pointer stored in matrix_mdev->kvm. I can't imagine the KVM pointer stored in vdev->kvm being different than matrix_mdev->kvm,

With this patch matrix_mdev->kvm is set from the value in vdev->kvm during vfio_ap_mdev_set_kvm (basically, doing the work that the notifier was doing but instead of getting it from notifier data get it from the vfio_device)

Quoted 7 lines

but thought I should point it out. Previously, this function was called by the notifier handler which did not have access to the KVM pointer which is why it was retrieved from matrix_mdev->kvm. Even if the vdev->kvm and matrix_mdev->kvm did not match, we should probably go ahead and call the unset function anyway to remove access to AP resources for the guest and reset the queues.