drm/xe/vm: move xe_svm_init() earlier

In xe_vm_close_and_put() we need to be able to call xe_svm_fini(),
however during vm creation we can call this on the error path, before
having actually initialised the svm state, leading to various splats
followed by a fatal NPD.

Fixes: 6fd979c2f331 ("drm/xe: Add SVM init / close / fini to faulting VMs")
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4967
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250514152424.149591-4-matthew.auld@intel.com
(cherry picked from commit 4f296d77cf49fcb5f90b4674123ad7f3a0676165)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a68fd99..8615777 100644 (file)
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1683,10 +1683,16 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
                xe_pm_runtime_get_noresume(xe);
        }
 
+       if (flags & XE_VM_FLAG_FAULT_MODE) {
+               err = xe_svm_init(vm);
+               if (err)
+                       goto err_no_resv;
+       }
+
        vm_resv_obj = drm_gpuvm_resv_object_alloc(&xe->drm);
        if (!vm_resv_obj) {
                err = -ENOMEM;
-               goto err_no_resv;
+               goto err_svm_fini;
        }
 
        drm_gpuvm_init(&vm->gpuvm, "Xe VM", DRM_GPUVM_RESV_PROTECTED, &xe->drm,
@@ -1757,12 +1763,6 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
                }
        }
 
-       if (flags & XE_VM_FLAG_FAULT_MODE) {
-               err = xe_svm_init(vm);
-               if (err)
-                       goto err_close;
-       }
-
        if (number_tiles > 1)
                vm->composite_fence_ctx = dma_fence_context_alloc(1);
 
@@ -1776,6 +1776,11 @@ err_close:
        xe_vm_close_and_put(vm);
        return ERR_PTR(err);
 
+err_svm_fini:
+       if (flags & XE_VM_FLAG_FAULT_MODE) {
+               vm->size = 0; /* close the vm */
+               xe_svm_fini(vm);
+       }
 err_no_resv:
        mutex_destroy(&vm->snap_mutex);
        for_each_tile(tile, xe, id)