Merge tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Regular fixes for the week to end the merge window, i915 and xe have a
  few each, amdgpu makes up most of it with a bunch of SR-IOV related
  fixes amongst others.

  i915:
   - Fix BMG support to UHBR13.5
   - Two PSR fixes
   - Fix colorimetry detection for DP

  xe:
   - Fix macro for checking minimum GuC version
   - Fix CCS offset calculation for some BMG SKUs
   - Fix locking on memory usage reporting via fdinfo and BO destroy
   - Fix GPU page fault handler on a closed VM
   - Fix overflow in oa batch buffer

  amdgpu:
   - MES 12 fix
   - KFD fence sync fix
   - SR-IOV fixes
   - VCN 4.0.6 fix
   - SDMA 7.x fix
   - Bump driver version to note cleared VRAM support
   - SWSMU fix
   - CU occupancy logic fix
   - SDMA queue fix"

* tag 'drm-next-2024-09-28' of https://gitlab.freedesktop.org/drm/kernel: (79 commits)
  drm/amd/pm: update workload mask after the setting
  drm/amdgpu: bump driver version for cleared VRAM
  drm/amdgpu: fix vbios fetching for SR-IOV
  drm/amdgpu: fix PTE copy corruption for sdma 7
  drm/amdkfd: Add SDMA queue quantum support for GFX12
  drm/amdgpu/vcn: enable AV1 on both instances
  drm/amdkfd: Fix CU occupancy for GFX 9.4.3
  drm/amdkfd: Update logic for CU occupancy calculations
  drm/amdgpu: skip coredump after job timeout in SRIOV
  drm/amdgpu: sync to KFD fences before clearing PTEs
  drm/amdgpu/mes12: set enable_level_process_quantum_check
  drm/i915/dp: Fix colorimetry detection
  drm/amdgpu/mes12: reduce timeout
  drm/amdgpu/mes11: reduce timeout
  drm/amdgpu: use GEM references instead of TTMs v2
  drm/amd/display: Allow backlight to go below `AMDGPU_DM_DEFAULT_MIN_BACKLIGHT`
  drm/amd/display: Fix kdoc entry for 'tps' in 'dc_process_dmub_dpia_set_tps_notification'
  drm/amdgpu: update golden regs for gfx12
  drm/amdgpu: clean up vbios fetching code
  drm/amd/display: handle nulled pipe context in DCE110's set_drr()
  ...

1 files changed, 6 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 2452dfa6314f..6005280f5f38 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -465,7 +465,6 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 {
 	uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
 	struct amdgpu_vm_bo_base *bo_base;
-	struct amdgpu_bo *shadow;
 	struct amdgpu_bo *bo;
 	int r;
 
@@ -486,16 +485,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		spin_unlock(&vm->status_lock);
 
 		bo = bo_base->bo;
-		shadow = amdgpu_bo_shadowed(bo);
 
 		r = validate(param, bo);
 		if (r)
 			return r;
-		if (shadow) {
-			r = validate(param, shadow);
-			if (r)
-				return r;
-		}
 
 		if (bo->tbo.type != ttm_bo_type_kernel) {
 			amdgpu_vm_bo_moved(bo_base);
@@ -1176,6 +1169,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 				     AMDGPU_SYNC_EQ_OWNER, vm);
 		if (r)
 			goto error_free;
+		if (bo) {
+			r = amdgpu_sync_kfd(&sync, bo->tbo.base.resv);
+			if (r)
+				goto error_free;
+		}
+
 	} else {
 		struct drm_gem_object *obj = &bo->tbo.base;
 
@@ -2149,10 +2148,6 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 {
 	struct amdgpu_vm_bo_base *bo_base;
 
-	/* shadow bo doesn't have bo base, its validation needs its parent */
-	if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo))
-		bo = bo->parent;
-
 	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
 
@@ -2482,7 +2477,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	root_bo = amdgpu_bo_ref(&root->bo);
 	r = amdgpu_bo_reserve(root_bo, true);
 	if (r) {
-		amdgpu_bo_unref(&root->shadow);
 		amdgpu_bo_unref(&root_bo);
 		goto error_free_delayed;
 	}
@@ -2575,11 +2569,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->last_update = dma_fence_get_stub();
 	vm->is_compute_context = true;
 
-	/* Free the shadow bo for compute VM */
-	amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow);
-
-	goto unreserve_bo;
-
 unreserve_bo:
 	amdgpu_bo_unreserve(vm->root.bo);
 	return r;