Merge tag 'drm/tegra/for-5.6-rc1-fixes' of git://anongit.freedesktop.org/tegra/linux into drm-next

drm/tegra: Fixes for v5.6-rc1

These are a couple of quick fixes for regressions that were found during
the first two weeks of the merge window.
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thierry Reding <thierry.reding@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200206172753.2185390-1-thierry.reding@gmail.com

drivers/gpu/drm/tegra/drm.c

@@ -1037,23 +1037,9 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt,
 	free_pages((unsigned long)virt, get_order(size));
 }
 
-static int host1x_drm_probe(struct host1x_device *dev)
+static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 {
-	struct drm_driver *driver = &tegra_drm_driver;
 	struct iommu_domain *domain;
-	struct tegra_drm *tegra;
-	struct drm_device *drm;
-	int err;
-
-	drm = drm_dev_alloc(driver, &dev->dev);
-	if (IS_ERR(drm))
-		return PTR_ERR(drm);
-
-	tegra = kzalloc(sizeof(*tegra), GFP_KERNEL);
-	if (!tegra) {
-		err = -ENOMEM;
-		goto put;
-	}
 
 	/*
 	 * If the Tegra DRM clients are backed by an IOMMU, push buffers are
@@ -1082,9 +1068,38 @@ static int host1x_drm_probe(struct host1x_device *dev)
 	 * up the device tree appropriately. This is considered an problem
 	 * of integration, so care must be taken for the DT to be consistent.
 	 */
-	domain = iommu_get_domain_for_dev(drm->dev->parent);
+	domain = iommu_get_domain_for_dev(dev->dev.parent);
+
+	/*
+	 * Tegra20 and Tegra30 don't support addressing memory beyond the
+	 * 32-bit boundary, so the regular GATHER opcodes will always be
+	 * sufficient and whether or not the host1x is attached to an IOMMU
+	 * doesn't matter.
+	 */
+	if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32))
+		return true;
+
+	return domain != NULL;
+}
+
+static int host1x_drm_probe(struct host1x_device *dev)
+{
+	struct drm_driver *driver = &tegra_drm_driver;
+	struct tegra_drm *tegra;
+	struct drm_device *drm;
+	int err;
+
+	drm = drm_dev_alloc(driver, &dev->dev);
+	if (IS_ERR(drm))
+		return PTR_ERR(drm);
+
+	tegra = kzalloc(sizeof(*tegra), GFP_KERNEL);
+	if (!tegra) {
+		err = -ENOMEM;
+		goto put;
+	}
 
-	if (domain && iommu_present(&platform_bus_type)) {
+	if (host1x_drm_wants_iommu(dev) && iommu_present(&platform_bus_type)) {
 		tegra->domain = iommu_domain_alloc(&platform_bus_type);
 		if (!tegra->domain) {
 			err = -ENOMEM;

drivers/gpu/drm/tegra/gem.c

@@ -60,8 +60,16 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo,
 	/*
 	 * If we've manually mapped the buffer object through the IOMMU, make
 	 * sure to return the IOVA address of our mapping.
+	 *
+	 * Similarly, for buffers that have been allocated by the DMA API the
+	 * physical address can be used for devices that are not attached to
+	 * an IOMMU. For these devices, callers must pass a valid pointer via
+	 * the @phys argument.
+	 *
+	 * Imported buffers were also already mapped at import time, so the
+	 * existing mapping can be reused.
 	 */
-	if (phys && obj->mm) {
+	if (phys) {
 		*phys = obj->iova;
 		return NULL;
 	}

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 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 		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;
 	}

drivers/gpu/drm/tegra/sor.c

@@ -3915,6 +3915,17 @@ static int tegra_sor_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, sor);
 	pm_runtime_enable(&pdev->dev);
 
+	INIT_LIST_HEAD(&sor->client.list);
+	sor->client.ops = &sor_client_ops;
+	sor->client.dev = &pdev->dev;
+
+	err = host1x_client_register(&sor->client);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
+			err);
+		goto rpm_disable;
+	}
+
 	/*
 	 * On Tegra210 and earlier, provide our own implementation for the
 	 * pad output clock.
@@ -3922,16 +3933,17 @@ static int tegra_sor_probe(struct platform_device *pdev)
 	if (!sor->clk_pad) {
 		char *name;
 
+		name = devm_kasprintf(sor->dev, GFP_KERNEL, "sor%u_pad_clkout",
+				      sor->index);
+		if (!name) {
+			err = -ENOMEM;
+			goto unregister;
+		}
+
 		err = host1x_client_resume(&sor->client);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to resume: %d\n", err);
-			goto remove;
-		}
-
-		name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "sor%u_pad_clkout", sor->index);
-		if (!name) {
-			err = -ENOMEM;
-			goto remove;
+			goto unregister;
 		}
 
 		sor->clk_pad = tegra_clk_sor_pad_register(sor, name);
@@ -3940,24 +3952,17 @@ static int tegra_sor_probe(struct platform_device *pdev)
 
 	if (IS_ERR(sor->clk_pad)) {
 		err = PTR_ERR(sor->clk_pad);
-		dev_err(&pdev->dev, "failed to register SOR pad clock: %d\n",
-			err);
-		goto remove;
-	}
-
-	INIT_LIST_HEAD(&sor->client.list);
-	sor->client.ops = &sor_client_ops;
-	sor->client.dev = &pdev->dev;
-
-	err = host1x_client_register(&sor->client);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
+		dev_err(sor->dev, "failed to register SOR pad clock: %d\n",
 			err);
-		goto remove;
+		goto unregister;
 	}
 
 	return 0;
 
+unregister:
+	host1x_client_unregister(&sor->client);
+rpm_disable:
+	pm_runtime_disable(&pdev->dev);
 remove:
 	if (sor->ops && sor->ops->remove)
 		sor->ops->remove(sor);
@@ -3971,8 +3976,6 @@ static int tegra_sor_remove(struct platform_device *pdev)
 	struct tegra_sor *sor = platform_get_drvdata(pdev);
 	int err;
 
-	pm_runtime_disable(&pdev->dev);
-
 	err = host1x_client_unregister(&sor->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
@@ -3980,6 +3983,8 @@ static int tegra_sor_remove(struct platform_device *pdev)
 		return err;
 	}
 
+	pm_runtime_disable(&pdev->dev);
+
 	if (sor->ops && sor->ops->remove) {
 		err = sor->ops->remove(sor);
 		if (err < 0)

drivers/gpu/host1x/job.c

@@ -8,6 +8,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/host1x.h>
+#include <linux/iommu.h>
 #include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
@@ -101,9 +102,11 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 {
 	struct host1x_client *client = job->client;
 	struct device *dev = client->dev;
+	struct iommu_domain *domain;
 	unsigned int i;
 	int err;
 
+	domain = iommu_get_domain_for_dev(dev);
 	job->num_unpins = 0;
 
 	for (i = 0; i < job->num_relocs; i++) {
@@ -117,7 +120,19 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 			goto unpin;
 		}
 
-		if (client->group)
+		/*
+		 * If the client device is not attached to an IOMMU, the
+		 * physical address of the buffer object can be used.
+		 *
+		 * Similarly, when an IOMMU domain is shared between all
+		 * host1x clients, the IOVA is already available, so no
+		 * need to map the buffer object again.
+		 *
+		 * XXX Note that this isn't always safe to do because it
+		 * relies on an assumption that no cache maintenance is
+		 * needed on the buffer objects.
+		 */
+		if (!domain || client->group)
 			phys = &phys_addr;
 		else
 			phys = NULL;
@@ -176,6 +191,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 		dma_addr_t phys_addr;
 		unsigned long shift;
 		struct iova *alloc;
+		dma_addr_t *phys;
 		unsigned int j;
 
 		g->bo = host1x_bo_get(g->bo);
@@ -184,7 +200,17 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 			goto unpin;
 		}
 
-		sgt = host1x_bo_pin(host->dev, g->bo, NULL);
+		/**
+		 * If the host1x is not attached to an IOMMU, there is no need
+		 * to map the buffer object for the host1x, since the physical
+		 * address can simply be used.
+		 */
+		if (!iommu_get_domain_for_dev(host->dev))
+			phys = &phys_addr;
+		else
+			phys = NULL;
+
+		sgt = host1x_bo_pin(host->dev, g->bo, phys);
 		if (IS_ERR(sgt)) {
 			err = PTR_ERR(sgt);
 			goto unpin;
@@ -214,7 +240,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 
 			job->unpins[job->num_unpins].size = gather_size;
 			phys_addr = iova_dma_addr(&host->iova, alloc);
-		} else {
+		} else if (sgt) {
 			err = dma_map_sg(host->dev, sgt->sgl, sgt->nents,
 					 DMA_TO_DEVICE);
 			if (!err) {
@@ -222,6 +248,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 				goto unpin;
 			}
 
+			job->unpins[job->num_unpins].dir = DMA_TO_DEVICE;
 			job->unpins[job->num_unpins].dev = host->dev;
 			phys_addr = sg_dma_address(sgt->sgl);
 		}
@@ -229,7 +256,6 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 		job->addr_phys[job->num_unpins] = phys_addr;
 		job->gather_addr_phys[i] = phys_addr;
 
-		job->unpins[job->num_unpins].dir = DMA_TO_DEVICE;
 		job->unpins[job->num_unpins].bo = g->bo;
 		job->unpins[job->num_unpins].sgt = sgt;
 		job->num_unpins++;