drm/nouveau: implement new VM_BIND UAPI

This commit provides the implementation for the new uapi motivated by the
Vulkan API. It allows user mode drivers (UMDs) to:

1) Initialize a GPU virtual address (VA) space via the new
   DRM_IOCTL_NOUVEAU_VM_INIT ioctl for UMDs to specify the portion of VA
   space managed by the kernel and userspace, respectively.

2) Allocate and free a VA space region as well as bind and unbind memory
   to the GPUs VA space via the new DRM_IOCTL_NOUVEAU_VM_BIND ioctl.
   UMDs can request the named operations to be processed either
   synchronously or asynchronously. It supports DRM syncobjs
   (incl. timelines) as synchronization mechanism. The management of the
   GPU VA mappings is implemented with the DRM GPU VA manager.

3) Execute push buffers with the new DRM_IOCTL_NOUVEAU_EXEC ioctl. The
   execution happens asynchronously. It supports DRM syncobj (incl.
   timelines) as synchronization mechanism. DRM GEM object locking is
   handled with drm_exec.

Both, DRM_IOCTL_NOUVEAU_VM_BIND and DRM_IOCTL_NOUVEAU_EXEC, use the DRM
GPU scheduler for the asynchronous paths.

Signed-off-by: Danilo Krummrich <dakr@redhat.com>

Documentation/gpu/driver-uapi.rst

@@ -13,4 +13,7 @@ drm/nouveau uAPI
 VM_BIND / EXEC uAPI
 -------------------
 
+.. kernel-doc:: drivers/gpu/drm/nouveau/nouveau_exec.c
+    :doc: Overview
+
 .. kernel-doc:: include/uapi/drm/nouveau_drm.h

drivers/gpu/drm/nouveau/Kbuild

@@ -47,6 +47,8 @@ nouveau-y += nouveau_prime.o
 nouveau-y += nouveau_sgdma.o
 nouveau-y += nouveau_ttm.o
 nouveau-y += nouveau_vmm.o
+nouveau-y += nouveau_exec.o
+nouveau-y += nouveau_sched.o
 nouveau-y += nouveau_uvmm.o
 
 # DRM - modesetting

drivers/gpu/drm/nouveau/Kconfig

@@ -10,6 +10,8 @@ config DRM_NOUVEAU
 	select DRM_KMS_HELPER
 	select DRM_TTM
 	select DRM_TTM_HELPER
+	select DRM_EXEC
+	select DRM_SCHED
 	select I2C
 	select I2C_ALGOBIT
 	select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT

drivers/gpu/drm/nouveau/nouveau_abi16.c

@@ -35,6 +35,7 @@
 #include "nouveau_chan.h"
 #include "nouveau_abi16.h"
 #include "nouveau_vmm.h"
+#include "nouveau_sched.h"
 
 static struct nouveau_abi16 *
 nouveau_abi16(struct drm_file *file_priv)
@@ -125,6 +126,17 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 {
 	struct nouveau_abi16_ntfy *ntfy, *temp;
 
+	/* When a client exits without waiting for it's queued up jobs to
+	 * finish it might happen that we fault the channel. This is due to
+	 * drm_file_free() calling drm_gem_release() before the postclose()
+	 * callback. Hence, we can't tear down this scheduler entity before
+	 * uvmm mappings are unmapped. Currently, we can't detect this case.
+	 *
+	 * However, this should be rare and harmless, since the channel isn't
+	 * needed anymore.
+	 */
+	nouveau_sched_entity_fini(&chan->sched_entity);
+
 	/* wait for all activity to stop before cleaning up */
 	if (chan->chan)
 		nouveau_channel_idle(chan->chan);
@@ -311,6 +323,10 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	if (ret)
 		goto done;
 
+	ret = nouveau_sched_entity_init(&chan->sched_entity, &drm->sched);
+	if (ret)
+		goto done;
+
 	init->channel = chan->chan->chid;
 
 	if (device->info.family >= NV_DEVICE_INFO_V0_TESLA)

drivers/gpu/drm/nouveau/nouveau_abi16.h

@@ -26,6 +26,7 @@ struct nouveau_abi16_chan {
 	struct nouveau_bo *ntfy;
 	struct nouveau_vma *ntfy_vma;
 	struct nvkm_mm  heap;
+	struct nouveau_sched_entity sched_entity;
 };
 
 struct nouveau_abi16 {

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -71,6 +71,7 @@
 #include "nouveau_svm.h"
 #include "nouveau_dmem.h"
 #include "nouveau_uvmm.h"
+#include "nouveau_sched.h"
 
 DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0,
 			"DRM_UT_CORE",
@@ -192,6 +193,7 @@ nouveau_cli_fini(struct nouveau_cli *cli)
 	flush_work(&cli->work);
 	WARN_ON(!list_empty(&cli->worker));
 
+	nouveau_sched_entity_fini(&cli->sched_entity);
 	usif_client_fini(cli);
 	nouveau_uvmm_fini(&cli->uvmm);
 	nouveau_vmm_fini(&cli->svm);
@@ -299,6 +301,11 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	}
 
 	cli->mem = &mems[ret];
+
+	ret = nouveau_sched_entity_init(&cli->sched_entity, &drm->sched);
+	if (ret)
+		goto done;
+
 	return 0;
 done:
 	if (ret)
@@ -611,8 +618,13 @@ nouveau_drm_device_init(struct drm_device *dev)
 		pm_runtime_put(dev->dev);
 	}
 
-	return 0;
+	ret = nouveau_sched_init(&drm->sched, drm);
+	if (ret)
+		goto fail_sched_init;
 
+	return 0;
+fail_sched_init:
+	nouveau_display_fini(dev, false, false);
 fail_dispinit:
 	nouveau_display_destroy(dev);
 fail_dispctor:
@@ -637,6 +649,8 @@ nouveau_drm_device_fini(struct drm_device *dev)
 	struct nouveau_cli *cli, *temp_cli;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	nouveau_sched_fini(&drm->sched);
+
 	if (nouveau_pmops_runtime()) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
@@ -1177,6 +1191,9 @@ nouveau_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_VM_INIT, nouveau_ioctl_vm_init, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_VM_BIND, nouveau_ioctl_vm_bind, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_EXEC, nouveau_ioctl_exec, DRM_RENDER_ALLOW),
 };
 
 long
@@ -1224,7 +1241,9 @@ nouveau_driver_fops = {
 static struct drm_driver
 driver_stub = {
 	.driver_features =
-		DRIVER_GEM | DRIVER_MODESET | DRIVER_RENDER
+		DRIVER_GEM | DRIVER_MODESET | DRIVER_RENDER |
+		DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE |
+		DRIVER_GEM_GPUVA
 #if defined(CONFIG_NOUVEAU_LEGACY_CTX_SUPPORT)
 		| DRIVER_KMS_LEGACY_CONTEXT
 #endif

drivers/gpu/drm/nouveau/nouveau_drv.h

@@ -10,8 +10,8 @@
 #define DRIVER_DATE		"20120801"
 
 #define DRIVER_MAJOR		1
-#define DRIVER_MINOR		3
-#define DRIVER_PATCHLEVEL	1
+#define DRIVER_MINOR		4
+#define DRIVER_PATCHLEVEL	0
 
 /*
  * 1.1.1:
@@ -63,6 +63,7 @@ struct platform_device;
 
 #include "nouveau_fence.h"
 #include "nouveau_bios.h"
+#include "nouveau_sched.h"
 #include "nouveau_vmm.h"
 #include "nouveau_uvmm.h"
 
@@ -94,6 +95,8 @@ struct nouveau_cli {
 	struct nouveau_vmm svm;
 	struct nouveau_uvmm uvmm;
 
+	struct nouveau_sched_entity sched_entity;
+
 	const struct nvif_mclass *mem;
 
 	struct list_head head;
@@ -305,6 +308,8 @@ struct nouveau_drm {
 		struct mutex lock;
 		bool component_registered;
 	} audio;
+
+	struct drm_gpu_scheduler sched;
 };
 
 static inline struct nouveau_drm *