[PATCH v9 02/12] drm/xe: Allow prefetch-only VM bind IOCTLs to use VM read lock

Prefetch-only VM bind IOCTLs do not modify VMAs or use userptr pages.
Downgrade vm->lock to read mode once setup is complete.

Lays the groundwork for prefetch IOCTLs to use threaded migration.

Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Francois Dugast <[email protected]>
---
 drivers/gpu/drm/xe/xe_vm.c       | 36 +++++++++++++++++++++++++++-----
 drivers/gpu/drm/xe/xe_vm_types.h |  2 ++
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a39854fbd3a2..25736c952304 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2451,10 +2451,12 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 			.map.gem.offset = bo_offset_or_userptr,
 		};
 
+		vops->flags |= XE_VMA_OPS_FLAG_MODIFIES_GPUVA;
 		ops = drm_gpuvm_sm_map_ops_create(&vm->gpuvm, &map_req);
 		break;
 	}
 	case DRM_XE_VM_BIND_OP_UNMAP:
+		vops->flags |= XE_VMA_OPS_FLAG_MODIFIES_GPUVA;
 		ops = drm_gpuvm_sm_unmap_ops_create(&vm->gpuvm, addr, range);
 		break;
 	case DRM_XE_VM_BIND_OP_PREFETCH:
@@ -2463,6 +2465,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 	case DRM_XE_VM_BIND_OP_UNMAP_ALL:
 		xe_assert(vm->xe, bo);
 
+		vops->flags |= XE_VMA_OPS_FLAG_MODIFIES_GPUVA;
 		err = xe_bo_lock(bo, true);
 		if (err)
 			return ERR_PTR(err);
@@ -2524,6 +2527,9 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 			u32 i;
 			bool need_put;
 
+			if (xe_vma_is_userptr(vma))
+				vops->flags |= XE_VMA_OPS_FLAG_MODIFIES_GPUVA;
+
 			if (!xe_vma_is_cpu_addr_mirror(vma)) {
 				op->prefetch.region = prefetch_region;
 				continue;
@@ -2715,10 +2721,12 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 {
 	int err = 0;
 
-	xe_vm_assert_write_mode_or_garbage_collector(vm);
+	lockdep_assert_held(&vm->lock);
 
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		err |= xe_vm_insert_vma(vm, op->map.vma);
 		if (!err)
 			op->flags |= XE_VMA_OP_COMMITTED;
@@ -2728,6 +2736,8 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 		u8 tile_present =
 			gpuva_to_vma(op->base.remap.unmap->va)->tile_present;
 
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		prep_vma_destroy(vm, gpuva_to_vma(op->base.remap.unmap->va),
 				 true);
 		op->flags |= XE_VMA_OP_COMMITTED;
@@ -2762,6 +2772,8 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 		break;
 	}
 	case DRM_GPUVA_OP_UNMAP:
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		prep_vma_destroy(vm, gpuva_to_vma(op->base.unmap.va), true);
 		op->flags |= XE_VMA_OP_COMMITTED;
 		break;
@@ -2986,10 +2998,12 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op,
 			     bool post_commit, bool prev_post_commit,
 			     bool next_post_commit)
 {
-	xe_vm_assert_write_mode_or_garbage_collector(vm);
+	lockdep_assert_held(&vm->lock);
 
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		if (op->map.vma) {
 			prep_vma_destroy(vm, op->map.vma, post_commit);
 			xe_vma_destroy_unlocked(op->map.vma);
@@ -2999,6 +3013,8 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op,
 	{
 		struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va);
 
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		if (vma) {
 			xe_svm_notifier_lock(vm);
 			vma->gpuva.flags &= ~XE_VMA_DESTROYED;
@@ -3012,6 +3028,8 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op,
 	{
 		struct xe_vma *vma = gpuva_to_vma(op->base.remap.unmap->va);
 
+		xe_vm_assert_write_mode_or_garbage_collector(vm);
+
 		if (op->remap.prev) {
 			prep_vma_destroy(vm, op->remap.prev, prev_post_commit);
 			xe_vma_destroy_unlocked(op->remap.prev);
@@ -3596,7 +3614,7 @@ static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	struct dma_fence *fence;
 	int err = 0;
 
-	lockdep_assert_held_write(&vm->lock);
+	lockdep_assert_held(&vm->lock);
 
 	xe_validation_guard(&ctx, &vm->xe->val, &exec,
 			    ((struct xe_val_flags) {
@@ -3919,7 +3937,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
 	struct drm_xe_vm_bind_op *bind_ops = NULL;
-	struct xe_vma_ops vops;
+	struct xe_vma_ops vops = { .flags = 0, };
 	struct dma_fence *fence;
 	int err;
 	int i;
@@ -4094,6 +4112,11 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto unwind_ops;
 	}
 
+	if (!(vops.flags & XE_VMA_OPS_FLAG_MODIFIES_GPUVA)) {
+		vops.flags |= XE_VMA_OPS_FLAG_DOWNGRADE_LOCK;
+		downgrade_write(&vm->lock);
+	}
+
 	err = xe_vma_ops_alloc(&vops, args->num_binds > 1);
 	if (err)
 		goto unwind_ops;
@@ -4130,7 +4153,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 free_bos:
 	kvfree(bos);
 release_vm_lock:
-	up_write(&vm->lock);
+	if (vops.flags & XE_VMA_OPS_FLAG_DOWNGRADE_LOCK)
+		up_read(&vm->lock);
+	else
+		up_write(&vm->lock);
 put_exec_queue:
 	if (q)
 		xe_exec_queue_put(q);
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index b94eb018d532..2f5f74fed9d2 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -561,6 +561,8 @@ struct xe_vma_ops {
 #define XE_VMA_OPS_ARRAY_OF_BINDS	 BIT(2)
 #define XE_VMA_OPS_FLAG_SKIP_TLB_WAIT	 BIT(3)
 #define XE_VMA_OPS_FLAG_ALLOW_SVM_UNMAP  BIT(4)
+#define XE_VMA_OPS_FLAG_MODIFIES_GPUVA	 BIT(5)
+#define XE_VMA_OPS_FLAG_DOWNGRADE_LOCK	 BIT(6)
 	u32 flags;
 #ifdef TEST_VM_OPS_ERROR
 	/** @inject_error: inject error to test error handling */
-- 
2.34.1