drm/xe: Add unbind to SVM garbage collector

Add unbind to SVM garbage collector. To facilitate add unbind support
function to VM layer which unbinds a SVM range. Also teach PT layer to
understand unbinds of SVM ranges.

v3:
 - s/INVALID_VMA/XE_INVALID_VMA (Thomas)
 - Kernel doc (Thomas)
 - New GPU SVM range structure (Thomas)
 - s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
v4:
 - Use xe_vma_op_unmap_range (Himal)
v5:
 - s/PY/PT (Thomas)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-17-matthew.brost@intel.com

Author: mbrost05

drivers/gpu/drm/xe/xe_pt.c

@@ -964,10 +964,16 @@ static void xe_pt_cancel_bind(struct xe_vma *vma,
 	}
 }
 
+#define XE_INVALID_VMA	((struct xe_vma *)(0xdeaddeadull))
+
 static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
 {
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_vm *vm;
 
+	if (vma == XE_INVALID_VMA)
+		return;
+
+	vm = xe_vma_vm(vma);
 	lockdep_assert_held(&vm->lock);
 
 	if (!xe_vma_has_no_bo(vma))
@@ -978,8 +984,12 @@ static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
 
 static void xe_pt_commit_locks_assert(struct xe_vma *vma)
 {
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_vm *vm;
 
+	if (vma == XE_INVALID_VMA)
+		return;
+
+	vm = xe_vma_vm(vma);
 	xe_pt_commit_prepare_locks_assert(vma);
 
 	if (xe_vma_is_userptr(vma))
@@ -1007,7 +1017,8 @@ static void xe_pt_commit(struct xe_vma *vma,
 			int j_ = j + entries[i].ofs;
 
 			pt_dir->children[j_] = pt_dir->staging[j_];
-			xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred);
+			xe_pt_destroy(oldpte, (vma == XE_INVALID_VMA) ? 0 :
+				      xe_vma_vm(vma)->flags, deferred);
 		}
 	}
 }
@@ -1420,6 +1431,9 @@ static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
 	list_for_each_entry(op, &vops->list, link) {
 		struct xe_svm_range *range = op->map_range.range;
 
+		if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE)
+			continue;
+
 		xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma));
 		xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE);
 
@@ -1617,7 +1631,9 @@ static const struct xe_pt_walk_ops xe_pt_stage_unbind_ops = {
  * xe_pt_stage_unbind() - Build page-table update structures for an unbind
  * operation
  * @tile: The tile we're unbinding for.
+ * @vm: The vm
  * @vma: The vma we're unbinding.
+ * @range: The range we're unbinding.
  * @entries: Caller-provided storage for the update structures.
  *
  * Builds page-table update structures for an unbind operation. The function
@@ -1627,9 +1643,14 @@ static const struct xe_pt_walk_ops xe_pt_stage_unbind_ops = {
  *
  * Return: The number of entries used.
  */
-static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
+static unsigned int xe_pt_stage_unbind(struct xe_tile *tile,
+				       struct xe_vm *vm,
+				       struct xe_vma *vma,
+				       struct xe_svm_range *range,
 				       struct xe_vm_pgtable_update *entries)
 {
+	u64 start = range ? range->base.itree.start : xe_vma_start(vma);
+	u64 end = range ? range->base.itree.last + 1 : xe_vma_end(vma);
 	struct xe_pt_stage_unbind_walk xe_walk = {
 		.base = {
 			.ops = &xe_pt_stage_unbind_ops,
@@ -1638,14 +1659,14 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
 			.staging = true,
 		},
 		.tile = tile,
-		.modified_start = xe_vma_start(vma),
-		.modified_end = xe_vma_end(vma),
+		.modified_start = start,
+		.modified_end = end,
 		.wupd.entries = entries,
 	};
-	struct xe_pt *pt = xe_vma_vm(vma)->pt_root[tile->id];
+	struct xe_pt *pt = vm->pt_root[tile->id];
 
-	(void)xe_pt_walk_shared(&pt->base, pt->level, xe_vma_start(vma),
-				xe_vma_end(vma), &xe_walk.base);
+	(void)xe_pt_walk_shared(&pt->base, pt->level, start, end,
+				&xe_walk.base);
 
 	return xe_walk.wupd.num_used_entries;
 }
@@ -1887,13 +1908,6 @@ static int unbind_op_prepare(struct xe_tile *tile,
 	       "Preparing unbind, with range [%llx...%llx)\n",
 	       xe_vma_start(vma), xe_vma_end(vma) - 1);
 
-	/*
-	 * Wait for invalidation to complete. Can corrupt internal page table
-	 * state if an invalidation is running while preparing an unbind.
-	 */
-	if (xe_vma_is_userptr(vma) && xe_vm_in_fault_mode(xe_vma_vm(vma)))
-		mmu_interval_read_begin(&to_userptr_vma(vma)->userptr.notifier);
-
 	pt_op->vma = vma;
 	pt_op->bind = false;
 	pt_op->rebind = false;
@@ -1902,7 +1916,8 @@ static int unbind_op_prepare(struct xe_tile *tile,
 	if (err)
 		return err;
 
-	pt_op->num_entries = xe_pt_stage_unbind(tile, vma, pt_op->entries);
+	pt_op->num_entries = xe_pt_stage_unbind(tile, xe_vma_vm(vma),
+						vma, NULL, pt_op->entries);
 
 	xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries,
 				pt_op->num_entries, false);
@@ -1917,6 +1932,42 @@ static int unbind_op_prepare(struct xe_tile *tile,
 	return 0;
 }
 
+static int unbind_range_prepare(struct xe_vm *vm,
+				struct xe_tile *tile,
+				struct xe_vm_pgtable_update_ops *pt_update_ops,
+				struct xe_svm_range *range)
+{
+	u32 current_op = pt_update_ops->current_op;
+	struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op];
+
+	if (!(range->tile_present & BIT(tile->id)))
+		return 0;
+
+	vm_dbg(&vm->xe->drm,
+	       "Preparing unbind, with range [%lx...%lx)\n",
+	       range->base.itree.start, range->base.itree.last);
+
+	pt_op->vma = XE_INVALID_VMA;
+	pt_op->bind = false;
+	pt_op->rebind = false;
+
+	pt_op->num_entries = xe_pt_stage_unbind(tile, vm, NULL, range,
+						pt_op->entries);
+
+	xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries,
+				pt_op->num_entries, false);
+	xe_pt_update_ops_rfence_interval(pt_update_ops, range->base.itree.start,
+					 range->base.itree.last + 1);
+	++pt_update_ops->current_op;
+	pt_update_ops->needs_svm_lock = true;
+	pt_update_ops->needs_invalidation = true;
+
+	xe_pt_commit_prepare_unbind(XE_INVALID_VMA, pt_op->entries,
+				    pt_op->num_entries);
+
+	return 0;
+}
+
 static int op_prepare(struct xe_vm *vm,
 		      struct xe_tile *tile,
 		      struct xe_vm_pgtable_update_ops *pt_update_ops,
@@ -1984,6 +2035,9 @@ static int op_prepare(struct xe_vm *vm,
 			err = bind_range_prepare(vm, tile, pt_update_ops,
 						 op->map_range.vma,
 						 op->map_range.range);
+		} else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) {
+			err = unbind_range_prepare(vm, tile, pt_update_ops,
+						   op->unmap_range.range);
 		}
 		break;
 	default:
@@ -2173,6 +2227,8 @@ static void op_commit(struct xe_vm *vm,
 		if (op->subop == XE_VMA_SUBOP_MAP_RANGE) {
 			op->map_range.range->tile_present |= BIT(tile->id);
 			op->map_range.range->tile_invalidated &= ~BIT(tile->id);
+		} else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) {
+			op->unmap_range.range->tile_present &= ~BIT(tile->id);
 		}
 		break;
 	}

drivers/gpu/drm/xe/xe_svm.c

@@ -222,7 +222,14 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
 static int __xe_svm_garbage_collector(struct xe_vm *vm,
 				      struct xe_svm_range *range)
 {
-	/* TODO: Do unbind */
+	struct dma_fence *fence;
+
+	xe_vm_lock(vm, false);
+	fence = xe_vm_range_unbind(vm, range);
+	xe_vm_unlock(vm);
+	if (IS_ERR(fence))
+		return PTR_ERR(fence);
+	dma_fence_put(fence);
 
 	drm_gpusvm_range_remove(&vm->svm.gpusvm, &range->base);
 

drivers/gpu/drm/xe/xe_vm.c

@@ -1040,6 +1040,89 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
 	return fence;
 }
 
+static void xe_vm_populate_range_unbind(struct xe_vma_op *op,
+					struct xe_svm_range *range)
+{
+	INIT_LIST_HEAD(&op->link);
+	op->tile_mask = range->tile_present;
+	op->base.op = DRM_GPUVA_OP_DRIVER;
+	op->subop = XE_VMA_SUBOP_UNMAP_RANGE;
+	op->unmap_range.range = range;
+}
+
+static int
+xe_vm_ops_add_range_unbind(struct xe_vma_ops *vops,
+			   struct xe_svm_range *range)
+{
+	struct xe_vma_op *op;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	xe_vm_populate_range_unbind(op, range);
+	list_add_tail(&op->link, &vops->list);
+	xe_vma_ops_incr_pt_update_ops(vops, range->tile_present);
+
+	return 0;
+}
+
+/**
+ * xe_vm_range_unbind() - VM range unbind
+ * @vm: The VM which the range belongs to.
+ * @range: SVM range to rebind.
+ *
+ * Unbind SVM range removing the GPU page tables for the range.
+ *
+ * Return: dma fence for unbind to signal completion on succees, ERR_PTR on
+ * failure
+ */
+struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
+				     struct xe_svm_range *range)
+{
+	struct dma_fence *fence = NULL;
+	struct xe_vma_ops vops;
+	struct xe_vma_op *op, *next_op;
+	struct xe_tile *tile;
+	u8 id;
+	int err;
+
+	lockdep_assert_held(&vm->lock);
+	xe_vm_assert_held(vm);
+	xe_assert(vm->xe, xe_vm_in_fault_mode(vm));
+
+	if (!range->tile_present)
+		return dma_fence_get_stub();
+
+	xe_vma_ops_init(&vops, vm, NULL, NULL, 0);
+	for_each_tile(tile, vm->xe, id) {
+		vops.pt_update_ops[id].wait_vm_bookkeep = true;
+		vops.pt_update_ops[tile->id].q =
+			xe_tile_migrate_exec_queue(tile);
+	}
+
+	err = xe_vm_ops_add_range_unbind(&vops, range);
+	if (err)
+		return ERR_PTR(err);
+
+	err = xe_vma_ops_alloc(&vops, false);
+	if (err) {
+		fence = ERR_PTR(err);
+		goto free_ops;
+	}
+
+	fence = ops_execute(vm, &vops);
+
+free_ops:
+	list_for_each_entry_safe(op, next_op, &vops.list, link) {
+		list_del(&op->link);
+		kfree(op);
+	}
+	xe_vma_ops_fini(&vops);
+
+	return fence;
+}
+
 static void xe_vma_free(struct xe_vma *vma)
 {
 	if (xe_vma_is_userptr(vma))

drivers/gpu/drm/xe/xe_vm.h

@@ -223,6 +223,8 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
 				     struct xe_vma *vma,
 				     struct xe_svm_range *range,
 				     u8 tile_mask);
+struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
+				     struct xe_svm_range *range);
 
 int xe_vm_invalidate_vma(struct xe_vma *vma);
 

drivers/gpu/drm/xe/xe_vm_types.h

@@ -366,6 +366,12 @@ struct xe_vma_op_map_range {
 	struct xe_svm_range *range;
 };
 
+/** struct xe_vma_op_unmap_range - VMA unmap range operation */
+struct xe_vma_op_unmap_range {
+	/** @range: SVM range to unmap */
+	struct xe_svm_range *range;
+};
+
 /** enum xe_vma_op_flags - flags for VMA operation */
 enum xe_vma_op_flags {
 	/** @XE_VMA_OP_COMMITTED: VMA operation committed */
@@ -380,6 +386,8 @@ enum xe_vma_op_flags {
 enum xe_vma_subop {
 	/** @XE_VMA_SUBOP_MAP_RANGE: Map range */
 	XE_VMA_SUBOP_MAP_RANGE,
+	/** @XE_VMA_SUBOP_UNMAP_RANGE: Unmap range */
+	XE_VMA_SUBOP_UNMAP_RANGE,
 };
 
 /** struct xe_vma_op - VMA operation */
@@ -404,6 +412,8 @@ struct xe_vma_op {
 		struct xe_vma_op_prefetch prefetch;
 		/** @map_range: VMA map range operation specific data */
 		struct xe_vma_op_map_range map_range;
+		/** @unmap_range: VMA unmap range operation specific data */
+		struct xe_vma_op_unmap_range unmap_range;
 	};
 };