diff options
| author | Rob Clark <robdclark@chromium.org> | 2023-08-03 00:21:52 +0200 |
|---|---|---|
| committer | Rob Clark <robdclark@chromium.org> | 2023-08-10 22:08:03 +0200 |
| commit | 7391c282ba0f0e82ac131658e2faf712215ed6a2 (patch) | |
| tree | a1de12c463d9ed0fb65da9b768b9dc0c1ce033ea /drivers/gpu/drm/msm/msm_ringbuffer.c | |
| parent | drm/msm: Take lru lock once per submit_pin_objects() (diff) | |
| download | linux-7391c282ba0f0e82ac131658e2faf712215ed6a2.tar.xz linux-7391c282ba0f0e82ac131658e2faf712215ed6a2.zip | |
drm/msm: Remove vma use tracking
This was not strictly necessary, as page unpinning (ie. shrinker) only
cares about the resv. It did give us some extra sanity checking for
userspace controlled iova, and was useful to catch issues on kernel and
userspace side when enabling userspace iova. But if userspace screws
this up, it just corrupts it's own gpu buffers and/or gets iova faults.
So we can just let userspace shoot it's own foot and drop the extra per-
buffer SUBMIT overhead.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Patchwork: https://patchwork.freedesktop.org/patch/551023/
Diffstat (limited to 'drivers/gpu/drm/msm/msm_ringbuffer.c')
| -rw-r--r-- | drivers/gpu/drm/msm/msm_ringbuffer.c | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 6fa427d2992e..7f5e0a961bba 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -26,9 +26,8 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; - msm_gem_vma_unpin_fenced(submit->bos[i].vma, fctx); msm_gem_unpin_active(obj); - submit->bos[i].flags &= ~(BO_VMA_PINNED | BO_OBJ_PINNED); + submit->bos[i].flags &= ~BO_PINNED; } mutex_unlock(&priv->lru.lock); |