Commit 014f831a authored by Danilo Krummrich's avatar Danilo Krummrich
Browse files

drm/nouveau: use GPUVM common infrastructure 



GPUVM provides common infrastructure to track external and evicted GEM
objects as well as locking and validation helpers.

Especially external and evicted object tracking is a huge improvement
compared to the current brute force approach of iterating all mappings
in order to lock and validate the GPUVM's GEM objects. Hence, make us of
it.

Signed-off-by: default avatarDanilo Krummrich <dakr@redhat.com>
Reviewed-by: default avatarDave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113221202.7203-1-dakr@redhat.com
parent 6c18005d

drivers/gpu/drm/nouveau/nouveau_bo.c

+3 −1
Original line number Diff line number Diff line
@@ -1061,17 +1061,18 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, 
{

	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);

	struct nouveau_bo *nvbo = nouveau_bo(bo);

	struct drm_gem_object *obj = &bo->base;

	struct ttm_resource *old_reg = bo->resource;

	struct nouveau_drm_tile *new_tile = NULL;

	int ret = 0;





	if (new_reg->mem_type == TTM_PL_TT) {

		ret = nouveau_ttm_tt_bind(bo->bdev, bo->ttm, new_reg);

		if (ret)

			return ret;

	}



	drm_gpuvm_bo_gem_evict(obj, evict);

	nouveau_bo_move_ntfy(bo, new_reg);

	ret = ttm_bo_wait_ctx(bo, ctx);

	if (ret)
@@ -1136,6 +1137,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, 
out_ntfy:

	if (ret) {

		nouveau_bo_move_ntfy(bo, bo->resource);

		drm_gpuvm_bo_gem_evict(obj, !evict);

	}

	return ret;

}

drivers/gpu/drm/nouveau/nouveau_exec.c

+15 −42
Original line number Diff line number Diff line 
// SPDX-License-Identifier: MIT



#include <drm/drm_exec.h>



#include "nouveau_drv.h"

#include "nouveau_gem.h"

#include "nouveau_mem.h"
@@ -86,14 +84,12 @@ 
 */



static int

nouveau_exec_job_submit(struct nouveau_job *job)

nouveau_exec_job_submit(struct nouveau_job *job,

			struct drm_gpuvm_exec *vme)

{

	struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job);

	struct nouveau_cli *cli = job->cli;

	struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli);

	struct drm_exec *exec = &job->exec;

	struct drm_gem_object *obj;

	unsigned long index;

	int ret;



	/* Create a new fence, but do not emit yet. */
@@ -102,52 +98,29 @@ nouveau_exec_job_submit(struct nouveau_job *job) 
		return ret;



	nouveau_uvmm_lock(uvmm);

	drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT |

			    DRM_EXEC_IGNORE_DUPLICATES);

	drm_exec_until_all_locked(exec) {

		struct drm_gpuva *va;



		drm_gpuvm_for_each_va(va, &uvmm->base) {

			if (unlikely(va == &uvmm->base.kernel_alloc_node))

				continue;



			ret = drm_exec_prepare_obj(exec, va->gem.obj, 1);

			drm_exec_retry_on_contention(exec);

			if (ret)

				goto err_uvmm_unlock;

		}

	ret = drm_gpuvm_exec_lock(vme);

	if (ret) {

		nouveau_uvmm_unlock(uvmm);

		return ret;

	}

	nouveau_uvmm_unlock(uvmm);



	drm_exec_for_each_locked_object(exec, index, obj) {

		struct nouveau_bo *nvbo = nouveau_gem_object(obj);



		ret = nouveau_bo_validate(nvbo, true, false);

		if (ret)

			goto err_exec_fini;

	ret = drm_gpuvm_exec_validate(vme);

	if (ret) {

		drm_gpuvm_exec_unlock(vme);

		return ret;

	}



	return 0;



err_uvmm_unlock:

	nouveau_uvmm_unlock(uvmm);

err_exec_fini:

	drm_exec_fini(exec);

	return ret;



}



static void

nouveau_exec_job_armed_submit(struct nouveau_job *job)

nouveau_exec_job_armed_submit(struct nouveau_job *job,

			      struct drm_gpuvm_exec *vme)

{

	struct drm_exec *exec = &job->exec;

	struct drm_gem_object *obj;

	unsigned long index;



	drm_exec_for_each_locked_object(exec, index, obj)

		dma_resv_add_fence(obj->resv, job->done_fence, job->resv_usage);



	drm_exec_fini(exec);

	drm_gpuvm_exec_resv_add_fence(vme, job->done_fence,

				      job->resv_usage, job->resv_usage);

	drm_gpuvm_exec_unlock(vme);

}



static struct dma_fence *

drivers/gpu/drm/nouveau/nouveau_exec.h

+0 −4
Original line number Diff line number Diff line
@@ -3,16 +3,12 @@ 
#ifndef __NOUVEAU_EXEC_H__

#define __NOUVEAU_EXEC_H__



#include <drm/drm_exec.h>



#include "nouveau_drv.h"

#include "nouveau_sched.h"



struct nouveau_exec_job_args {

	struct drm_file *file_priv;

	struct nouveau_sched_entity *sched_entity;



	struct drm_exec exec;

	struct nouveau_channel *chan;



	struct {

drivers/gpu/drm/nouveau/nouveau_sched.c

+7 −2
Original line number Diff line number Diff line
@@ -263,6 +263,11 @@ nouveau_job_submit(struct nouveau_job *job) 
{

	struct nouveau_sched_entity *entity = to_nouveau_sched_entity(job->base.entity);

	struct dma_fence *done_fence = NULL;

	struct drm_gpuvm_exec vm_exec = {

		.vm = &nouveau_cli_uvmm(job->cli)->base,

		.flags = DRM_EXEC_IGNORE_DUPLICATES,

		.num_fences = 1,

	};

	int ret;



	ret = nouveau_job_add_deps(job);
@@ -282,7 +287,7 @@ nouveau_job_submit(struct nouveau_job *job) 
	 * successfully.

	 */

	if (job->ops->submit) {

		ret = job->ops->submit(job);

		ret = job->ops->submit(job, &vm_exec);

		if (ret)

			goto err_cleanup;

	}
@@ -315,7 +320,7 @@ nouveau_job_submit(struct nouveau_job *job) 
	set_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &job->done_fence->flags);



	if (job->ops->armed_submit)

		job->ops->armed_submit(job);

		job->ops->armed_submit(job, &vm_exec);



	nouveau_job_fence_attach(job);

drivers/gpu/drm/nouveau/nouveau_sched.h

+3 −4
Original line number Diff line number Diff line
@@ -5,7 +5,7 @@ 


#include <linux/types.h>



#include <drm/drm_exec.h>

#include <drm/drm_gpuvm.h>

#include <drm/gpu_scheduler.h>



#include "nouveau_drv.h"
@@ -54,7 +54,6 @@ struct nouveau_job { 
	struct drm_file *file_priv;

	struct nouveau_cli *cli;



	struct drm_exec exec;

	enum dma_resv_usage resv_usage;

	struct dma_fence *done_fence;
@@ -76,8 +75,8 @@ struct nouveau_job { 
		/* If .submit() returns without any error, it is guaranteed that

		 * armed_submit() is called.

		 */

		int (*submit)(struct nouveau_job *);

		void (*armed_submit)(struct nouveau_job *);

		int (*submit)(struct nouveau_job *, struct drm_gpuvm_exec *);

		void (*armed_submit)(struct nouveau_job *, struct drm_gpuvm_exec *);

		struct dma_fence *(*run)(struct nouveau_job *);

		void (*free)(struct nouveau_job *);

		enum drm_gpu_sched_stat (*timeout)(struct nouveau_job *);