drm/tegra: Reuse IOVA mapping where possible

This partially reverts the DMA API support that was recently merged
because it was causing performance regressions on older Tegra devices.
Unfortunately, the cache maintenance performed by dma_map_sg() and
dma_unmap_sg() causes performance to drop by a factor of 10.

The right solution for this would be to cache mappings for buffers per
consumer device, but that's a bit involved. Instead, we simply revert to
the old behaviour of sharing IOVA mappings when we know that devices can
do so (i.e. they share the same IOMMU domain).

Cc: <stable@vger.kernel.org> # v5.5
Reported-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Dmitry Osipenko <digetx@gmail.com>

1 files changed, 25 insertions, 19 deletions

diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c
index cadcdd9ea427..9ccfb56e9b01 100644
--- a/drivers/gpu/drm/tegra/plane.c
+++ b/drivers/gpu/drm/tegra/plane.c
@@ -3,6 +3,8 @@
  * Copyright (C) 2017 NVIDIA CORPORATION.  All rights reserved.
  */
 
+#include <linux/iommu.h>
+
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fourcc.h>
@@ -107,21 +109,27 @@ const struct drm_plane_funcs tegra_plane_funcs = {
 
 static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 {
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dc->dev);
 	unsigned int i;
 	int err;
 
 	for (i = 0; i < state->base.fb->format->num_planes; i++) {
 		struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i);
+		dma_addr_t phys_addr, *phys;
+		struct sg_table *sgt;
 
-		if (!dc->client.group) {
-			struct sg_table *sgt;
+		if (!domain || dc->client.group)
+			phys = &phys_addr;
+		else
+			phys = NULL;
 
-			sgt = host1x_bo_pin(dc->dev, &bo->base, NULL);
-			if (IS_ERR(sgt)) {
-				err = PTR_ERR(sgt);
-				goto unpin;
-			}
+		sgt = host1x_bo_pin(dc->dev, &bo->base, phys);
+		if (IS_ERR(sgt)) {
+			err = PTR_ERR(sgt);
+			goto unpin;
+		}
 
+		if (sgt) {
 			err = dma_map_sg(dc->dev, sgt->sgl, sgt->nents,
 					 DMA_TO_DEVICE);
 			if (err == 0) {
@@ -143,7 +151,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 			state->iova[i] = sg_dma_address(sgt->sgl);
 			state->sgt[i] = sgt;
 		} else {
-			state->iova[i] = bo->iova;
+			state->iova[i] = phys_addr;
 		}
 	}
 
@@ -156,9 +164,11 @@ unpin:
 		struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i);
 		struct sg_table *sgt = state->sgt[i];
 
-		dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents, DMA_TO_DEVICE);
-		host1x_bo_unpin(dc->dev, &bo->base, sgt);
+		if (sgt)
+			dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents,
+				     DMA_TO_DEVICE);
 
+		host1x_bo_unpin(dc->dev, &bo->base, sgt);
 		state->iova[i] = DMA_MAPPING_ERROR;
 		state->sgt[i] = NULL;
 	}
@@ -172,17 +182,13 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state)
 
 	for (i = 0; i < state->base.fb->format->num_planes; i++) {
 		struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i);
+		struct sg_table *sgt = state->sgt[i];
 
-		if (!dc->client.group) {
-			struct sg_table *sgt = state->sgt[i];
-
-			if (sgt) {
-				dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents,
-					     DMA_TO_DEVICE);
-				host1x_bo_unpin(dc->dev, &bo->base, sgt);
-			}
-		}
+		if (sgt)
+			dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents,
+				     DMA_TO_DEVICE);
 
+		host1x_bo_unpin(dc->dev, &bo->base, sgt);
 		state->iova[i] = DMA_MAPPING_ERROR;
 		state->sgt[i] = NULL;
 	}