drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR

Add the DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR flag, which is used to
create unpopulated virtual memory areas (VMAs) without memory backing or
GPU page tables. These VMAs are referred to as CPU address mirror VMAs.
The idea is that upon a page fault or prefetch, the memory backing and
GPU page tables will be populated.

CPU address mirror VMAs only update GPUVM state; they do not have an
internal page table (PT) state, nor do they have GPU mappings.

It is expected that CPU address mirror VMAs will be mixed with buffer
object (BO) VMAs within a single VM. In other words, system allocations
and runtime allocations can be mixed within a single user-mode driver
(UMD) program.

Expected usage:

- Bind the entire virtual address (VA) space upon program load using the
  DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR flag.
- If a buffer object (BO) requires GPU mapping (runtime allocation),
  allocate a CPU address using mmap(PROT_NONE), bind the BO to the
  mmapped address using existing bind IOCTLs. If a CPU map of the BO is
  needed, mmap it again to the same CPU address using mmap(MAP_FIXED)
- If a BO no longer requires GPU mapping, munmap it from the CPU address
  space and them bind the mapping address with the
  DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR flag.
- Any malloc'd or mmapped CPU address accessed by the GPU will be
  faulted in via the SVM implementation (system allocation).
- Upon freeing any mmapped or malloc'd data, the SVM implementation will
  remove GPU mappings.

Only supporting 1 to 1 mapping between user address space and GPU
address space at the moment as that is the expected use case. uAPI
defines interface for non 1 to 1 but enforces 1 to 1, this restriction
can be lifted if use cases arrise for non 1 to 1 mappings.

This patch essentially short-circuits the code in the existing VM bind
paths to avoid populating page tables when the
DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR flag is set.

v3:
 - Call vm_bind_ioctl_ops_fini on -ENODATA
 - Don't allow DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR on non-faulting VMs
 - s/DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATOR/DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR (Thomas)
 - Rework commit message for expected usage (Thomas)
 - Describe state of code after patch in commit message (Thomas)
v4:
 - Fix alignment (Checkpatch)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-9-matthew.brost@intel.com

1 files changed, 61 insertions, 15 deletions

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index dc24baa84092..651512023829 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1090,6 +1090,11 @@ static int op_add_deps(struct xe_vm *vm, struct xe_vma_op *op,
 {
 	int err = 0;
 
+	/*
+	 * No need to check for is_cpu_addr_mirror here as vma_add_deps is a
+	 * NOP if VMA is_cpu_addr_mirror
+	 */
+
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		if (!op->map.immediate && xe_vm_in_fault_mode(vm))
@@ -1648,6 +1653,7 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile,
 	struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op];
 	int err;
 
+	xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma));
 	xe_bo_assert_held(xe_vma_bo(vma));
 
 	vm_dbg(&xe_vma_vm(vma)->xe->drm,
@@ -1715,6 +1721,7 @@ static int unbind_op_prepare(struct xe_tile *tile,
 	if (!((vma->tile_present | vma->tile_staged) & BIT(tile->id)))
 		return 0;
 
+	xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma));
 	xe_bo_assert_held(xe_vma_bo(vma));
 
 	vm_dbg(&xe_vma_vm(vma)->xe->drm,
@@ -1761,15 +1768,21 @@ static int op_prepare(struct xe_vm *vm,
 
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
-		if (!op->map.immediate && xe_vm_in_fault_mode(vm))
+		if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) ||
+		    op->map.is_cpu_addr_mirror)
 			break;
 
 		err = bind_op_prepare(vm, tile, pt_update_ops, op->map.vma);
 		pt_update_ops->wait_vm_kernel = true;
 		break;
 	case DRM_GPUVA_OP_REMAP:
-		err = unbind_op_prepare(tile, pt_update_ops,
-					gpuva_to_vma(op->base.remap.unmap->va));
+	{
+		struct xe_vma *old = gpuva_to_vma(op->base.remap.unmap->va);
+
+		if (xe_vma_is_cpu_addr_mirror(old))
+			break;
+
+		err = unbind_op_prepare(tile, pt_update_ops, old);
 
 		if (!err && op->remap.prev) {
 			err = bind_op_prepare(vm, tile, pt_update_ops,
@@ -1782,15 +1795,28 @@ static int op_prepare(struct xe_vm *vm,
 			pt_update_ops->wait_vm_bookkeep = true;
 		}
 		break;
+	}
 	case DRM_GPUVA_OP_UNMAP:
-		err = unbind_op_prepare(tile, pt_update_ops,
-					gpuva_to_vma(op->base.unmap.va));
+	{
+		struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va);
+
+		if (xe_vma_is_cpu_addr_mirror(vma))
+			break;
+
+		err = unbind_op_prepare(tile, pt_update_ops, vma);
 		break;
+	}
 	case DRM_GPUVA_OP_PREFETCH:
-		err = bind_op_prepare(vm, tile, pt_update_ops,
-				      gpuva_to_vma(op->base.prefetch.va));
+	{
+		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
+
+		if (xe_vma_is_cpu_addr_mirror(vma))
+			break;
+
+		err = bind_op_prepare(vm, tile, pt_update_ops, vma);
 		pt_update_ops->wait_vm_kernel = true;
 		break;
+	}
 	default:
 		drm_warn(&vm->xe->drm, "NOT POSSIBLE");
 	}
@@ -1860,6 +1886,8 @@ static void bind_op_commit(struct xe_vm *vm, struct xe_tile *tile,
 			   struct xe_vma *vma, struct dma_fence *fence,
 			   struct dma_fence *fence2)
 {
+	xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma));
+
 	if (!xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) {
 		dma_resv_add_fence(xe_vma_bo(vma)->ttm.base.resv, fence,
 				   pt_update_ops->wait_vm_bookkeep ?
@@ -1893,6 +1921,8 @@ static void unbind_op_commit(struct xe_vm *vm, struct xe_tile *tile,
 			     struct xe_vma *vma, struct dma_fence *fence,
 			     struct dma_fence *fence2)
 {
+	xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma));
+
 	if (!xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) {
 		dma_resv_add_fence(xe_vma_bo(vma)->ttm.base.resv, fence,
 				   pt_update_ops->wait_vm_bookkeep ?
@@ -1927,16 +1957,21 @@ static void op_commit(struct xe_vm *vm,
 
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
-		if (!op->map.immediate && xe_vm_in_fault_mode(vm))
+		if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) ||
+		    op->map.is_cpu_addr_mirror)
 			break;
 
 		bind_op_commit(vm, tile, pt_update_ops, op->map.vma, fence,
 			       fence2);
 		break;
 	case DRM_GPUVA_OP_REMAP:
-		unbind_op_commit(vm, tile, pt_update_ops,
-				 gpuva_to_vma(op->base.remap.unmap->va), fence,
-				 fence2);
+	{
+		struct xe_vma *old = gpuva_to_vma(op->base.remap.unmap->va);
+
+		if (xe_vma_is_cpu_addr_mirror(old))
+			break;
+
+		unbind_op_commit(vm, tile, pt_update_ops, old, fence, fence2);
 
 		if (op->remap.prev)
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.prev,
@@ -1945,14 +1980,25 @@ static void op_commit(struct xe_vm *vm,
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.next,
 				       fence, fence2);
 		break;
+	}
 	case DRM_GPUVA_OP_UNMAP:
-		unbind_op_commit(vm, tile, pt_update_ops,
-				 gpuva_to_vma(op->base.unmap.va), fence, fence2);
+	{
+		struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va);
+
+		if (!xe_vma_is_cpu_addr_mirror(vma))
+			unbind_op_commit(vm, tile, pt_update_ops, vma, fence,
+					 fence2);
 		break;
+	}
 	case DRM_GPUVA_OP_PREFETCH:
-		bind_op_commit(vm, tile, pt_update_ops,
-			       gpuva_to_vma(op->base.prefetch.va), fence, fence2);
+	{
+		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
+
+		if (!xe_vma_is_cpu_addr_mirror(vma))
+			bind_op_commit(vm, tile, pt_update_ops, vma, fence,
+				       fence2);
 		break;
+	}
 	default:
 		drm_warn(&vm->xe->drm, "NOT POSSIBLE");
 	}