vfio: Replace the DMA unmapping notifier with a callback

Instead of having drivers register the notifier with explicit code just
have them provide a dma_unmap callback op in their driver ops and rely on
the core code to wire it up.

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v4-681e038e30fd+78-vfio_unmap_notif_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

Author: jgunthorpe

drivers/gpu/drm/i915/gvt/gvt.h

@@ -226,7 +226,6 @@ struct intel_vgpu {
 	unsigned long nr_cache_entries;
 	struct mutex cache_lock;
 
-	struct notifier_block iommu_notifier;
 	atomic_t released;
 
 	struct kvm_page_track_notifier_node track_node;

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -729,34 +729,25 @@ int intel_gvt_set_edid(struct intel_vgpu *vgpu, int port_num)
 	return ret;
 }
 
-static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void intel_vgpu_dma_unmap(struct vfio_device *vfio_dev, u64 iova,
+				 u64 length)
 {
-	struct intel_vgpu *vgpu =
-		container_of(nb, struct intel_vgpu, iommu_notifier);
-
-	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
-		struct vfio_iommu_type1_dma_unmap *unmap = data;
-		struct gvt_dma *entry;
-		unsigned long iov_pfn, end_iov_pfn;
+	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
+	struct gvt_dma *entry;
+	u64 iov_pfn = iova >> PAGE_SHIFT;
+	u64 end_iov_pfn = iov_pfn + length / PAGE_SIZE;
 
-		iov_pfn = unmap->iova >> PAGE_SHIFT;
-		end_iov_pfn = iov_pfn + unmap->size / PAGE_SIZE;
+	mutex_lock(&vgpu->cache_lock);
+	for (; iov_pfn < end_iov_pfn; iov_pfn++) {
+		entry = __gvt_cache_find_gfn(vgpu, iov_pfn);
+		if (!entry)
+			continue;
 
-		mutex_lock(&vgpu->cache_lock);
-		for (; iov_pfn < end_iov_pfn; iov_pfn++) {
-			entry = __gvt_cache_find_gfn(vgpu, iov_pfn);
-			if (!entry)
-				continue;
-
-			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr,
-					   entry->size);
-			__gvt_cache_remove_entry(vgpu, entry);
-		}
-		mutex_unlock(&vgpu->cache_lock);
+		gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr,
+				   entry->size);
+		__gvt_cache_remove_entry(vgpu, entry);
 	}
-
-	return NOTIFY_OK;
+	mutex_unlock(&vgpu->cache_lock);
 }
 
 static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
@@ -783,36 +774,20 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
 static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 {
 	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
-	unsigned long events;
-	int ret;
-
-	vgpu->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier;
 
-	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,
-				     &vgpu->iommu_notifier);
-	if (ret != 0) {
-		gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
-			ret);
-		goto out;
-	}
-
-	ret = -EEXIST;
 	if (vgpu->attached)
-		goto undo_iommu;
+		return -EEXIST;
 
-	ret = -ESRCH;
 	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_iommu;
+		return -ESRCH;
 	}
 
 	kvm_get_kvm(vgpu->vfio_device.kvm);
 
-	ret = -EEXIST;
 	if (__kvmgt_vgpu_exist(vgpu))
-		goto undo_iommu;
+		return -EEXIST;
 
 	vgpu->attached = true;
 
@@ -831,12 +806,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 
 	atomic_set(&vgpu->released, 0);
 	return 0;
-
-undo_iommu:
-	vfio_unregister_notifier(vfio_dev, VFIO_IOMMU_NOTIFY,
-				 &vgpu->iommu_notifier);
-out:
-	return ret;
 }
 
 static void intel_vgpu_release_msi_eventfd_ctx(struct intel_vgpu *vgpu)
@@ -853,8 +822,6 @@ static void intel_vgpu_release_msi_eventfd_ctx(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;
 
 	if (!vgpu->attached)
 		return;
@@ -864,11 +831,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
 
 	intel_gvt_release_vgpu(vgpu);
 
-	ret = vfio_unregister_notifier(&vgpu->vfio_device, VFIO_IOMMU_NOTIFY,
-				       &vgpu->iommu_notifier);
-	drm_WARN(&i915->drm, ret,
-		 "vfio_unregister_notifier for iommu failed: %d\n", ret);
-
 	debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
 
 	kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
@@ -1610,6 +1572,7 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = {
 	.write		= intel_vgpu_write,
 	.mmap		= intel_vgpu_mmap,
 	.ioctl		= intel_vgpu_ioctl,
+	.dma_unmap	= intel_vgpu_dma_unmap,
 };
 
 static int intel_vgpu_probe(struct mdev_device *mdev)

drivers/s390/cio/vfio_ccw_ops.c

@@ -33,30 +33,16 @@ static int vfio_ccw_mdev_reset(struct vfio_ccw_private *private)
 	return 0;
 }
 
-static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
-				  unsigned long action,
-				  void *data)
+static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
 {
 	struct vfio_ccw_private *private =
-		container_of(nb, struct vfio_ccw_private, nb);
-
-	/*
-	 * Vendor drivers MUST unpin pages in response to an
-	 * invalidation.
-	 */
-	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
-		struct vfio_iommu_type1_dma_unmap *unmap = data;
-
-		if (!cp_iova_pinned(&private->cp, unmap->iova))
-			return NOTIFY_OK;
-
-		if (vfio_ccw_mdev_reset(private))
-			return NOTIFY_BAD;
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
-		return NOTIFY_OK;
-	}
+	/* Drivers MUST unpin pages in response to an invalidation. */
+	if (!cp_iova_pinned(&private->cp, iova))
+		return;
 
-	return NOTIFY_DONE;
+	vfio_ccw_mdev_reset(private);
 }
 
 static ssize_t name_show(struct mdev_type *mtype,
@@ -154,23 +140,15 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
-	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
 	int ret;
 
 	/* Device cannot simply be opened again from this state */
 	if (private->state == VFIO_CCW_STATE_NOT_OPER)
 		return -EINVAL;
 
-	private->nb.notifier_call = vfio_ccw_mdev_notifier;
-
-	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY,
-				     &events, &private->nb);
-	if (ret)
-		return ret;
-
 	ret = vfio_ccw_register_async_dev_regions(private);
 	if (ret)
-		goto out_unregister;
+		return ret;
 
 	ret = vfio_ccw_register_schib_dev_regions(private);
 	if (ret)
@@ -190,7 +168,6 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 	return ret;
 }
 
@@ -201,7 +178,6 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
@@ -624,6 +600,7 @@ static const struct vfio_device_ops vfio_ccw_dev_ops = {
 	.write = vfio_ccw_mdev_write,
 	.ioctl = vfio_ccw_mdev_ioctl,
 	.request = vfio_ccw_mdev_request,
+	.dma_unmap = vfio_ccw_dma_unmap,
 };
 
 struct mdev_driver vfio_ccw_mdev_driver = {

drivers/s390/cio/vfio_ccw_private.h

@@ -73,7 +73,6 @@ struct vfio_ccw_crw {
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
  * @avail: available for creating a mediated device
- * @nb: notifier for vfio events
  * @io_region: MMIO region to input/output I/O arguments/results
  * @io_mutex: protect against concurrent update of I/O regions
  * @region: additional regions for other subchannel operations
@@ -96,7 +95,6 @@ struct vfio_ccw_private {
 	int			state;
 	struct completion	*completion;
 	atomic_t		avail;
-	struct notifier_block	nb;
 	struct ccw_io_region	*io_region;
 	struct mutex		io_mutex;
 	struct vfio_ccw_region *region;

drivers/s390/crypto/vfio_ap_ops.c

@@ -1226,34 +1226,14 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 	return 0;
 }
 
-/**
- * vfio_ap_mdev_iommu_notifier - IOMMU notifier callback
- *
- * @nb: The notifier block
- * @action: Action to be taken
- * @data: data associated with the request
- *
- * For an UNMAP request, unpin the guest IOVA (the NIB guest address we
- * pinned before). Other requests are ignored.
- *
- * Return: for an UNMAP request, NOFITY_OK; otherwise NOTIFY_DONE.
- */
-static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
-				       unsigned long action, void *data)
+static void vfio_ap_mdev_dma_unmap(struct vfio_device *vdev, u64 iova,
+				   u64 length)
 {
-	struct ap_matrix_mdev *matrix_mdev;
-
-	matrix_mdev = container_of(nb, struct ap_matrix_mdev, iommu_notifier);
-
-	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
-		struct vfio_iommu_type1_dma_unmap *unmap = data;
-		unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;
-
-		vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1);
-		return NOTIFY_OK;
-	}
+	struct ap_matrix_mdev *matrix_mdev =
+		container_of(vdev, struct ap_matrix_mdev, vdev);
+	unsigned long g_pfn = iova >> PAGE_SHIFT;
 
-	return NOTIFY_DONE;
+	vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1);
 }
 
 /**
@@ -1380,36 +1360,18 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 {
 	struct ap_matrix_mdev *matrix_mdev =
 		container_of(vdev, struct ap_matrix_mdev, vdev);
-	unsigned long events;
-	int ret;
 
 	if (!vdev->kvm)
 		return -EINVAL;
 
-	ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm);
-	if (ret)
-		return ret;
-
-	matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
-	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events,
-				     &matrix_mdev->iommu_notifier);
-	if (ret)
-		goto err_kvm;
-	return 0;
-
-err_kvm:
-	vfio_ap_mdev_unset_kvm(matrix_mdev);
-	return ret;
+	return vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm);
 }
 
 static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
 {
 	struct ap_matrix_mdev *matrix_mdev =
 		container_of(vdev, struct ap_matrix_mdev, vdev);
 
-	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
-				 &matrix_mdev->iommu_notifier);
 	vfio_ap_mdev_unset_kvm(matrix_mdev);
 }
 
@@ -1461,6 +1423,7 @@ static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
 	.open_device = vfio_ap_mdev_open_device,
 	.close_device = vfio_ap_mdev_close_device,
 	.ioctl = vfio_ap_mdev_ioctl,
+	.dma_unmap = vfio_ap_mdev_dma_unmap,
 };
 
 static struct mdev_driver vfio_ap_matrix_driver = {

drivers/s390/crypto/vfio_ap_private.h

@@ -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.
- * @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
  * @pqap_hook:	the function pointer to the interception handler for the
  *		PQAP(AQIC) instruction.
@@ -92,7 +90,6 @@ struct ap_matrix_mdev {
 	struct vfio_device vdev;
 	struct list_head node;
 	struct ap_matrix matrix;
-	struct notifier_block iommu_notifier;
 	struct kvm *kvm;
 	crypto_hook pqap_hook;
 	struct mdev_device *mdev;