1 files changed, 24 insertions, 60 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 352b30409060..e73d152659a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -181,7 +181,7 @@ static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
 
 	if (level == adev->vm_manager.root_level)
 		/* For the root directory */
-		return round_up(adev->vm_manager.max_pfn, 1 << shift) >> shift;
+		return round_up(adev->vm_manager.max_pfn, 1ULL << shift) >> shift;
 	else if (level != AMDGPU_VM_PTB)
 		/* Everything in between */
 		return 512;
@@ -617,7 +617,8 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 {
 	entry->priority = 0;
 	entry->tv.bo = &vm->root.base.bo->tbo;
-	entry->tv.shared = true;
+	/* One for the VM updates, one for TTM and one for the CS job */
+	entry->tv.num_shared = 3;
 	entry->user_pages = NULL;
 	list_add(&entry->tv.head, validated);
 }
@@ -773,10 +774,6 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 
 	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
-	r = reservation_object_reserve_shared(bo->tbo.resv);
-	if (r)
-		return r;
-
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (r)
 		goto error;
@@ -1632,13 +1629,6 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			continue;
 		}
 
-		/* First check if the entry is already handled */
-		if (cursor.pfn < frag_start) {
-			cursor.entry->huge = true;
-			amdgpu_vm_pt_next(adev, &cursor);
-			continue;
-		}
-
 		/* If it isn't already handled it can't be a huge page */
 		if (cursor.entry->huge) {
 			/* Add the entry to the relocated list to update it. */
@@ -1663,9 +1653,11 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			if (!amdgpu_vm_pt_descendant(adev, &cursor))
 				return -ENOENT;
 			continue;
-		} else if (frag >= parent_shift) {
+		} else if (frag >= parent_shift &&
+			   cursor.level - 1 != adev->vm_manager.root_level) {
 			/* If the fragment size is even larger than the parent
-			 * shift we should go up one level and check it again.
+			 * shift we should go up one level and check it again
+			 * unless one level up is the root level.
 			 */
 			if (!amdgpu_vm_pt_ancestor(&cursor))
 				return -ENOENT;
@@ -1673,10 +1665,10 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 		}
 
 		/* Looks good so far, calculate parameters for the update */
-		incr = AMDGPU_GPU_PAGE_SIZE << shift;
+		incr = (uint64_t)AMDGPU_GPU_PAGE_SIZE << shift;
 		mask = amdgpu_vm_entries_mask(adev, cursor.level);
 		pe_start = ((cursor.pfn >> shift) & mask) * 8;
-		entry_end = (mask + 1) << shift;
+		entry_end = (uint64_t)(mask + 1) << shift;
 		entry_end += cursor.pfn & ~(entry_end - 1);
 		entry_end = min(entry_end, end);
 
@@ -1689,7 +1681,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 					      flags | AMDGPU_PTE_FRAG(frag));
 
 			pe_start += nptes * 8;
-			dst += nptes * AMDGPU_GPU_PAGE_SIZE << shift;
+			dst += (uint64_t)nptes * AMDGPU_GPU_PAGE_SIZE << shift;
 
 			frag_start = upd_end;
 			if (frag_start >= frag_end) {
@@ -1701,8 +1693,17 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			}
 		} while (frag_start < entry_end);
 
-		if (frag >= shift)
+		if (amdgpu_vm_pt_descendant(adev, &cursor)) {
+			/* Mark all child entries as huge */
+			while (cursor.pfn < frag_start) {
+				cursor.entry->huge = true;
+				amdgpu_vm_pt_next(adev, &cursor);
+			}
+
+		} else if (frag >= shift) {
+			/* or just move on to the next on the same level. */
 			amdgpu_vm_pt_next(adev, &cursor);
+		}
 	}
 
 	return 0;
@@ -1840,10 +1841,6 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
-	if (r)
-		goto error_free;
-
 	r = amdgpu_vm_update_ptes(&params, start, last + 1, addr, flags);
 	if (r)
 		goto error_free;
@@ -3024,6 +3021,10 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		goto error_free_root;
 
+	r = reservation_object_reserve_shared(root->tbo.resv, 1);
+	if (r)
+		goto error_unreserve;
+
 	r = amdgpu_vm_clear_bo(adev, vm, root,
 			       adev->vm_manager.root_level,
 			       vm->pte_support_ats);
@@ -3053,7 +3054,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	INIT_KFIFO(vm->faults);
-	vm->fault_credit = 16;
 
 	return 0;
 
@@ -3266,42 +3266,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 }
 
 /**
- * amdgpu_vm_pasid_fault_credit - Check fault credit for given PASID
- *
- * @adev: amdgpu_device pointer
- * @pasid: PASID do identify the VM
- *
- * This function is expected to be called in interrupt context.
- *
- * Returns:
- * True if there was fault credit, false otherwise
- */
-bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
-				  unsigned int pasid)
-{
-	struct amdgpu_vm *vm;
-
-	spin_lock(&adev->vm_manager.pasid_lock);
-	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
-	if (!vm) {
-		/* VM not found, can't track fault credit */
-		spin_unlock(&adev->vm_manager.pasid_lock);
-		return true;
-	}
-
-	/* No lock needed. only accessed by IRQ handler */
-	if (!vm->fault_credit) {
-		/* Too many faults in this VM */
-		spin_unlock(&adev->vm_manager.pasid_lock);
-		return false;
-	}
-
-	vm->fault_credit--;
-	spin_unlock(&adev->vm_manager.pasid_lock);
-	return true;
-}
-
-/**
  * amdgpu_vm_manager_init - init the VM manager
  *
  * @adev: amdgpu_device pointer