| Message ID | 20190306225519.4538-1-digetx@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v1] drm/tegra: gem: Fix CPU-cache maintenance for BO's allocated using get_pages() | expand |
07.03.2019 1:55, Dmitry Osipenko пишет: > The allocated pages need to be invalidated in CPU caches. On ARM32 the > DMA_BIDIRECTIONAL flag only ensures that data is written-back to DRAM and > the data stays in CPU cache lines. While the DMA_FROM_DEVICE flag ensures > that the corresponding CPU cache lines are getting invalidated and nothing > more, that's exactly what is needed for a newly allocated pages. > > This fixes randomly failing rendercheck tests on Tegra30 using the > Opentegra driver for tests that use small-sized pixmaps (10x10 and less, > i.e. 1-2 memory pages) because apparently CPU reads out stale data from > caches and/or that data is getting evicted to DRAM at the time of HW job > execution. > > Cc: stable <stable@vger.kernel.org> > Signed-off-by: Dmitry Osipenko <digetx@gmail.com> Thierry, please don't forget about this patch.
On Thu, Mar 07, 2019 at 01:55:19AM +0300, Dmitry Osipenko wrote: > The allocated pages need to be invalidated in CPU caches. On ARM32 the > DMA_BIDIRECTIONAL flag only ensures that data is written-back to DRAM and > the data stays in CPU cache lines. While the DMA_FROM_DEVICE flag ensures > that the corresponding CPU cache lines are getting invalidated and nothing > more, that's exactly what is needed for a newly allocated pages. > > This fixes randomly failing rendercheck tests on Tegra30 using the > Opentegra driver for tests that use small-sized pixmaps (10x10 and less, > i.e. 1-2 memory pages) because apparently CPU reads out stale data from > caches and/or that data is getting evicted to DRAM at the time of HW job > execution. > > Cc: stable <stable@vger.kernel.org> > Signed-off-by: Dmitry Osipenko <digetx@gmail.com> > --- > drivers/gpu/drm/tegra/gem.c | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) Applied, thanks. Thierry
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 4f80100ff5f3..4cce11fd8836 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -204,7 +204,7 @@ static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo) { if (bo->pages) { dma_unmap_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); drm_gem_put_pages(&bo->gem, bo->pages, true, true); sg_free_table(bo->sgt); kfree(bo->sgt); @@ -230,7 +230,7 @@ static int tegra_bo_get_pages(struct drm_device *drm, struct tegra_bo *bo) } err = dma_map_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); if (err == 0) { err = -EFAULT; goto free_sgt;
The allocated pages need to be invalidated in CPU caches. On ARM32 the DMA_BIDIRECTIONAL flag only ensures that data is written-back to DRAM and the data stays in CPU cache lines. While the DMA_FROM_DEVICE flag ensures that the corresponding CPU cache lines are getting invalidated and nothing more, that's exactly what is needed for a newly allocated pages. This fixes randomly failing rendercheck tests on Tegra30 using the Opentegra driver for tests that use small-sized pixmaps (10x10 and less, i.e. 1-2 memory pages) because apparently CPU reads out stale data from caches and/or that data is getting evicted to DRAM at the time of HW job execution. Cc: stable <stable@vger.kernel.org> Signed-off-by: Dmitry Osipenko <digetx@gmail.com> --- drivers/gpu/drm/tegra/gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)