[0/7] drm/msm/gem: drm_exec conversion

  From: Rob Clark <robdclark@chromium.org>

Simplify the exec path (removing a legacy optimization) and convert to
drm_exec.  One drm_exec patch to allow passing in the expected # of GEM
objects to avoid re-allocation.

I'd be a bit happier if I could avoid the extra objects table allocation
in drm_exec in the first place, but wasn't really happy with any of the
things I tried to get rid of that.

Rob Clark (7):
  drm/msm/gem: Remove "valid" tracking
  drm/msm/gem: Remove submit_unlock_unpin_bo()
  drm/msm/gem: Don't queue job to sched in error cases
  drm/msm/gem: Split out submit_unpin_objects() helper
  drm/msm/gem: Cleanup submit_cleanup_bo()
  drm/exec: Pass in initial # of objects
  drm/msm/gem: Convert to drm_exec

 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c |   4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c |   4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c |   4 +-
 drivers/gpu/drm/drm_exec.c              |  15 +-
 drivers/gpu/drm/msm/Kconfig             |   1 +
 drivers/gpu/drm/msm/msm_gem.h           |  13 +-
 drivers/gpu/drm/msm/msm_gem_submit.c    | 197 ++++++------------------
 drivers/gpu/drm/msm/msm_ringbuffer.c    |   3 +-
 drivers/gpu/drm/nouveau/nouveau_exec.c  |   2 +-
 drivers/gpu/drm/nouveau/nouveau_uvmm.c  |   2 +-
 include/drm/drm_exec.h                  |   2 +-
 12 files changed, 79 insertions(+), 170 deletions(-)
  

Am 27.10.23 um 18:58 schrieb Rob Clark:
> From: Rob Clark <robdclark@chromium.org>
>
> In cases where the # is known ahead of time, it is silly to do the table
> resize dance.

Ah, yes that was my initial implementation as well, but I ditched that 
because nobody actually used it.

One comment below.

>
> Signed-off-by: Rob Clark <robdclark@chromium.org>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  |  2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c |  4 ++--
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c |  4 ++--
>   drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c |  4 ++--
>   drivers/gpu/drm/drm_exec.c              | 15 ++++++++++++---
>   drivers/gpu/drm/nouveau/nouveau_exec.c  |  2 +-
>   drivers/gpu/drm/nouveau/nouveau_uvmm.c  |  2 +-
>   include/drm/drm_exec.h                  |  2 +-
>   8 files changed, 22 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index efdb1c48f431..d27ca8f61929 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -65,7 +65,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
>   	}
>   
>   	amdgpu_sync_create(&p->sync);
> -	drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
> +	drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
>   	return 0;
>   }
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
> index 720011019741..796fa6f1420b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
> @@ -70,7 +70,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>   	struct drm_exec exec;
>   	int r;
>   
> -	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
> +	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		r = amdgpu_vm_lock_pd(vm, &exec, 0);
>   		if (likely(!r))
> @@ -110,7 +110,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>   	struct drm_exec exec;
>   	int r;
>   
> -	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
> +	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		r = amdgpu_vm_lock_pd(vm, &exec, 0);
>   		if (likely(!r))
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index ca4d2d430e28..16f1715148ad 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -203,7 +203,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
>   	struct drm_exec exec;
>   	long r;
>   
> -	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES);
> +	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1);
>   		drm_exec_retry_on_contention(&exec);
> @@ -739,7 +739,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
>   	}
>   
>   	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
> -		      DRM_EXEC_IGNORE_DUPLICATES);
> +		      DRM_EXEC_IGNORE_DUPLICATES, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		if (gobj) {
>   			r = drm_exec_lock_obj(&exec, gobj);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> index b6015157763a..3c351941701e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> @@ -1105,7 +1105,7 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
>   
>   	amdgpu_sync_create(&sync);
>   
> -	drm_exec_init(&exec, 0);
> +	drm_exec_init(&exec, 0, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		r = drm_exec_lock_obj(&exec,
>   				      &ctx_data->meta_data_obj->tbo.base);
> @@ -1176,7 +1176,7 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev,
>   	struct drm_exec exec;
>   	long r;
>   
> -	drm_exec_init(&exec, 0);
> +	drm_exec_init(&exec, 0, 0);
>   	drm_exec_until_all_locked(&exec) {
>   		r = drm_exec_lock_obj(&exec,
>   				      &ctx_data->meta_data_obj->tbo.base);
> diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c
> index 5d2809de4517..27d11c20d148 100644
> --- a/drivers/gpu/drm/drm_exec.c
> +++ b/drivers/gpu/drm/drm_exec.c
> @@ -69,16 +69,25 @@ static void drm_exec_unlock_all(struct drm_exec *exec)
>    * drm_exec_init - initialize a drm_exec object
>    * @exec: the drm_exec object to initialize
>    * @flags: controls locking behavior, see DRM_EXEC_* defines
> + * @nr: the initial # of objects
>    *
>    * Initialize the object and make sure that we can track locked objects.
> + *
> + * If nr is non-zero then it is used as the initial objects table size.
> + * In either case, the table will grow (be re-allocated) on demand.
>    */
> -void drm_exec_init(struct drm_exec *exec, uint32_t flags)
> +void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr)
>   {
> +	size_t sz = PAGE_SIZE;
> +
> +	if (nr)
> +		sz = (size_t)nr * sizeof(void *);
> +
>   	exec->flags = flags;
> -	exec->objects = kmalloc(PAGE_SIZE, GFP_KERNEL);
> +	exec->objects = kmalloc(sz, GFP_KERNEL);

Please use k*v*malloc() here since we can't predict how large that will be.

With that fixed the patch is Reviewed-by: Christian König 
<christian.koenig@amd.com>.

Regards,
Christian.

>   
>   	/* If allocation here fails, just delay that till the first use */
> -	exec->max_objects = exec->objects ? PAGE_SIZE / sizeof(void *) : 0;
> +	exec->max_objects = exec->objects ? sz / sizeof(void *) : 0;
>   	exec->num_objects = 0;
>   	exec->contended = DRM_EXEC_DUMMY;
>   	exec->prelocked = NULL;
> diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
> index 19024ce21fbb..f5930cc0b3fb 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_exec.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
> @@ -103,7 +103,7 @@ nouveau_exec_job_submit(struct nouveau_job *job)
>   
>   	nouveau_uvmm_lock(uvmm);
>   	drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
> -			    DRM_EXEC_IGNORE_DUPLICATES);
> +			    DRM_EXEC_IGNORE_DUPLICATES, 0);
>   	drm_exec_until_all_locked(exec) {
>   		struct drm_gpuva *va;
>   
> diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> index aae780e4a4aa..3a9331a1c830 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> @@ -1288,7 +1288,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
>   	}
>   
>   	drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
> -			    DRM_EXEC_IGNORE_DUPLICATES);
> +			    DRM_EXEC_IGNORE_DUPLICATES, 0);
>   	drm_exec_until_all_locked(exec) {
>   		list_for_each_op(op, &bind_job->ops) {
>   			struct drm_gpuva_op *va_op;
> diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h
> index b5bf0b6da791..f1a66c048721 100644
> --- a/include/drm/drm_exec.h
> +++ b/include/drm/drm_exec.h
> @@ -135,7 +135,7 @@ static inline bool drm_exec_is_contended(struct drm_exec *exec)
>   	return !!exec->contended;
>   }
>   
> -void drm_exec_init(struct drm_exec *exec, uint32_t flags);
> +void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr);
>   void drm_exec_fini(struct drm_exec *exec);
>   bool drm_exec_cleanup(struct drm_exec *exec);
>   int drm_exec_lock_obj(struct drm_exec *exec, struct drm_gem_object *obj);