drm/xe/xe_vm: Implement xe_vm_get_property_ioctl

Add support for userspace to request a list of observed faults
from a specified VM.

v2:
- Only allow querying of failed pagefaults (Matt Brost)

v3:
- Remove unnecessary size parameter from helper function, as it
  is a property of the arguments. (jcavitt)
- Remove unnecessary copy_from_user (Jainxun)
- Set address_precision to 1 (Jainxun)
- Report max size instead of dynamic size for memory allocation
  purposes.  Total memory usage is reported separately.

v4:
- Return int from xe_vm_get_property_size (Shuicheng)
- Fix memory leak (Shuicheng)
- Remove unnecessary size variable (jcavitt)

v5:
- Rename ioctl to xe_vm_get_faults_ioctl (jcavitt)
- Update fill_property_pfs to eliminate need for kzalloc (Jianxun)

v6:
- Repair and move fill_faults break condition (Dan Carpenter)
- Free vm after use (jcavitt)
- Combine assertions (jcavitt)
- Expand size check in xe_vm_get_faults_ioctl (jcavitt)
- Remove return mask from fill_faults, as return is already -EFAULT or 0
  (jcavitt)

v7:
- Revert back to using xe_vm_get_property_ioctl
- Apply better copy_to_user logic (jcavitt)

v8:
- Fix and clean up error value handling in ioctl (jcavitt)
- Reapply return mask for fill_faults (jcavitt)

v9:
- Future-proof size logic for zero-size properties (jcavitt)
- Add access and fault types (Jianxun)
- Remove address type (Jianxun)

v10:
- Remove unnecessary switch case logic (Raag)
- Compress size get, size validation, and property fill functions into a
  single helper function (jcavitt)
- Assert valid size (jcavitt)

v11:
- Remove unnecessary else condition
- Correct backwards helper function size logic (jcavitt)

v12:
- Use size_t instead of int (Raag)

v13:
- Remove engine class and instance (Ivan)

v14:
- Map access type, fault type, and fault level to user macros (Matt
  Brost, Ivan)

v15:
- Remove unnecessary size assertion (jcavitt)

v16:
- Nit fixes (Matt Brost)

v17:
- Rebase and refactor (jcavitt)

v18:
- Do not copy_to_user in critical section (Matt Brost)
- Assert args->size is multiple of sizeof(struct xe_vm_fault) (Matt
  Brost)

v19:
- Remove unnecessary memset (Matt Brost)

v20:
- Report canonicalized address (Jose)
- Mask out prefetch data from access type (Jose, jcavitt)

v21:
- s/uAPI/Link in the commit log links
- Align debug parameters

Link: intel/compute-runtime#878
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Michal Mrozek <michal.mrozek@intel.com>
Cc: Jainxun Zhang <jianxun.zhang@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Cc: Raag Jadav <raag.jadav@intel.com>
Cc: Ivan Briano <ivan.briano@intel.com>
Cc: Jose Souza <jose.souza@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260324152935.72444-10-jonathan.cavitt@intel.com

Author: Jonathan-Cavitt

drivers/gpu/drm/xe/xe_device.c

@@ -211,6 +211,8 @@ static const struct drm_ioctl_desc xe_ioctls[] = {
 			  DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(XE_EXEC_QUEUE_SET_PROPERTY, xe_exec_queue_set_property_ioctl,
 			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(XE_VM_GET_PROPERTY, xe_vm_get_property_ioctl,
+			  DRM_RENDER_ALLOW),
 };
 
 static long xe_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)

drivers/gpu/drm/xe/xe_vm.c

@@ -3974,6 +3974,123 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	return err;
 }
 
+/*
+ * Map access type, fault type, and fault level from current bspec
+ * specification to user spec abstraction.  The current mapping is
+ * approximately 1-to-1, with access type being the only notable
+ * exception as it carries additional data with respect to prefetch
+ * status that needs to be masked out.
+ */
+static u8 xe_to_user_access_type(u8 access_type)
+{
+	return access_type & XE_PAGEFAULT_ACCESS_TYPE_MASK;
+}
+
+static u8 xe_to_user_fault_type(u8 fault_type)
+{
+	return fault_type;
+}
+
+static u8 xe_to_user_fault_level(u8 fault_level)
+{
+	return fault_level;
+}
+
+static int fill_faults(struct xe_vm *vm,
+		       struct drm_xe_vm_get_property *args)
+{
+	struct xe_vm_fault __user *usr_ptr = u64_to_user_ptr(args->data);
+	struct xe_vm_fault *fault_list, fault_entry = { 0 };
+	struct xe_vm_fault_entry *entry;
+	int ret = 0, i = 0, count, entry_size;
+
+	entry_size = sizeof(struct xe_vm_fault);
+	count = args->size / entry_size;
+
+	fault_list = kcalloc(count, sizeof(struct xe_vm_fault), GFP_KERNEL);
+	if (!fault_list)
+		return -ENOMEM;
+
+	spin_lock(&vm->faults.lock);
+	list_for_each_entry(entry, &vm->faults.list, list) {
+		if (i == count)
+			break;
+
+		fault_entry.address = xe_device_canonicalize_addr(vm->xe, entry->address);
+		fault_entry.address_precision = entry->address_precision;
+
+		fault_entry.access_type = xe_to_user_access_type(entry->access_type);
+		fault_entry.fault_type = xe_to_user_fault_type(entry->fault_type);
+		fault_entry.fault_level = xe_to_user_fault_level(entry->fault_level);
+
+		memcpy(&fault_list[i], &fault_entry, entry_size);
+
+		i++;
+	}
+	spin_unlock(&vm->faults.lock);
+
+	ret = copy_to_user(usr_ptr, fault_list, args->size);
+
+	kfree(fault_list);
+	return ret ? -EFAULT : 0;
+}
+
+static int xe_vm_get_property_helper(struct xe_vm *vm,
+				     struct drm_xe_vm_get_property *args)
+{
+	size_t size;
+
+	switch (args->property) {
+	case DRM_XE_VM_GET_PROPERTY_FAULTS:
+		spin_lock(&vm->faults.lock);
+		size = size_mul(sizeof(struct xe_vm_fault), vm->faults.len);
+		spin_unlock(&vm->faults.lock);
+
+		if (!args->size) {
+			args->size = size;
+			return 0;
+		}
+
+		/*
+		 * Number of faults may increase between calls to
+		 * xe_vm_get_property_ioctl, so just report the number of
+		 * faults the user requests if it's less than or equal to
+		 * the number of faults in the VM fault array.
+		 *
+		 * We should also at least assert that the args->size value
+		 * is a multiple of the xe_vm_fault struct size.
+		 */
+		if (args->size > size || args->size % sizeof(struct xe_vm_fault))
+			return -EINVAL;
+
+		return fill_faults(vm, args);
+	}
+	return -EINVAL;
+}
+
+int xe_vm_get_property_ioctl(struct drm_device *drm, void *data,
+			     struct drm_file *file)
+{
+	struct xe_device *xe = to_xe_device(drm);
+	struct xe_file *xef = to_xe_file(file);
+	struct drm_xe_vm_get_property *args = data;
+	struct xe_vm *vm;
+	int ret = 0;
+
+	if (XE_IOCTL_DBG(xe, (args->reserved[0] || args->reserved[1] ||
+			      args->reserved[2])))
+		return -EINVAL;
+
+	vm = xe_vm_lookup(xef, args->vm_id);
+	if (XE_IOCTL_DBG(xe, !vm))
+		return -ENOENT;
+
+	ret = xe_vm_get_property_helper(vm, args);
+
+	xe_vm_put(vm);
+	return ret;
+}
+
 /**
  * xe_vm_bind_kernel_bo - bind a kernel BO to a VM
  * @vm: VM to bind the BO to

drivers/gpu/drm/xe/xe_vm.h

@@ -210,6 +210,9 @@ int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
 int xe_vm_bind_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *file);
 int xe_vm_query_vmas_attrs_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
+int xe_vm_get_property_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file);
+
 void xe_vm_close_and_put(struct xe_vm *vm);
 
 static inline bool xe_vm_in_fault_mode(struct xe_vm *vm)