drm/msm: Refactor address space initialization

Refactor how address space initialization works. Instead of having the
address space function create the MMU object (and thus require separate but
equal functions for gpummu and iommu) use a single function and pass the
MMU struct in. Make the generic code cleaner by using target specific
functions to create the address space so a2xx can do its own thing in its
own space. For all the other targets use a generic helper to initialize
IOMMU but leave the door open for newer targets to use customization
if they need it.

Reviewed-by: Rob Clark <[e-mail]>
Signed-off-by: Jordan Crouse <[e-mail]>
Tested-by: Shawn Guo <[e-mail]>
[squash in rebase fixups]
Signed-off-by: Rob Clark <[e-mail]>

drivers/gpu/drm/msm/adreno/a2xx_gpu.c

···
 	return state;
 }
 
+static struct msm_gem_address_space *
+a2xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+	struct msm_mmu *mmu = msm_gpummu_new(&pdev->dev, gpu);
+	struct msm_gem_address_space *aspace;
+
+	aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M,
+		SZ_16M + 0xfff * SZ_64K);
+
+	if (IS_ERR(aspace) && !IS_ERR(mmu))
+		mmu->funcs->destroy(mmu);
+
+	return aspace;
+}
+
 /* Register offset defines for A2XX - copy of A3XX */
 static const unsigned int a2xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
···
 #endif
 		.gpu_state_get = a2xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
+		.create_address_space = a2xx_create_address_space,
 	},
 };
 

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

···
 #endif
 		.gpu_state_get = a3xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
+		.create_address_space = adreno_iommu_create_address_space,
 	},
 };
 

drivers/gpu/drm/msm/adreno/a4xx_gpu.c

···
 #endif
 		.gpu_state_get = a4xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
+		.create_address_space = adreno_iommu_create_address_space,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

···
 		.gpu_busy = a5xx_gpu_busy,
 		.gpu_state_get = a5xx_gpu_state_get,
 		.gpu_state_put = a5xx_gpu_state_put,
+		.create_address_space = adreno_iommu_create_address_space,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

···
 static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
 {
 	struct iommu_domain *domain;
+	struct msm_mmu *mmu;
 
 	domain = iommu_domain_alloc(&platform_bus_type);
 	if (!domain)
 		return -ENODEV;
 
-	domain->geometry.aperture_start = 0x00000000;
-	domain->geometry.aperture_end = 0x7fffffff;
-
-	gmu->aspace = msm_gem_address_space_create(gmu->dev, domain, "gmu");
+	mmu = msm_iommu_new(gmu->dev, domain);
+	gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x7fffffff);
 	if (IS_ERR(gmu->aspace)) {
 		iommu_domain_free(domain);
 		return PTR_ERR(gmu->aspace);

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

···
 #if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,
+		.create_address_space = adreno_iommu_create_address_space,
 #endif
 	},
 	.get_timestamp = a6xx_get_timestamp,

drivers/gpu/drm/msm/adreno/adreno_gpu.c

···
 	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
 }
 
+struct msm_gem_address_space *
+adreno_iommu_create_address_space(struct msm_gpu *gpu,
+		struct platform_device *pdev)
+{
+	struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type);
+	struct msm_mmu *mmu = msm_iommu_new(&pdev->dev, iommu);
+	struct msm_gem_address_space *aspace;
+
+	aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M,
+		0xfffffff);
+
+	if (IS_ERR(aspace) && !IS_ERR(mmu))
+		mmu->funcs->destroy(mmu);
+
+	return aspace;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
···
 	adreno_gpu->rev = config->rev;
 
 	adreno_gpu_config.ioname = "kgsl_3d0_reg_memory";
-
-	adreno_gpu_config.va_start = SZ_16M;
-	adreno_gpu_config.va_end = 0xffffffff;
-	/* maximum range of a2xx mmu */
-	if (adreno_is_a2xx(adreno_gpu))
-		adreno_gpu_config.va_end = SZ_16M + 0xfff * SZ_64K;
 
 	adreno_gpu_config.nr_rings = nr_rings;
 

drivers/gpu/drm/msm/adreno/adreno_gpu.h

···
 int adreno_gpu_state_put(struct msm_gpu_state *state);
 
 /*
+ * Common helper function to initialize the default address space for arm-smmu
+ * attached targets
+ */
+struct msm_gem_address_space *
+adreno_iommu_create_address_space(struct msm_gpu *gpu,
+		struct platform_device *pdev);
+
+/*
  * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
  * out of secure mode
  */

drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c

···
 {
 	struct iommu_domain *domain;
 	struct msm_gem_address_space *aspace;
+	struct msm_mmu *mmu;
 
 	domain = iommu_domain_alloc(&platform_bus_type);
 	if (!domain)
 		return 0;
 
-	domain->geometry.aperture_start = 0x1000;
-	domain->geometry.aperture_end = 0xffffffff;
+	mmu = msm_iommu_new(dpu_kms->dev->dev, domain);
+	aspace = msm_gem_address_space_create(mmu, "dpu1",
+		0x1000, 0xfffffff);
 
-	aspace = msm_gem_address_space_create(dpu_kms->dev->dev,
-			domain, "dpu1");
 	if (IS_ERR(aspace)) {
-		iommu_domain_free(domain);
+		mmu->funcs->destroy(mmu);
 		return PTR_ERR(aspace);
 	}
 

drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c

···
 	mdelay(16);
 
 	if (config->iommu) {
-		aspace = msm_gem_address_space_create(&pdev->dev,
-				config->iommu, "mdp4");
+		struct msm_mmu *mmu = msm_iommu_new(&pdev->dev,
+			config->iommu);
+
+		aspace  = msm_gem_address_space_create(mmu,
+			"mdp4", 0x1000, 0xffffffff);
+
 		if (IS_ERR(aspace)) {
+			if (!IS_ERR(mmu))
+				mmu->funcs->destroy(mmu);
 			ret = PTR_ERR(aspace);
 			goto fail;
 		}
···
 	/* TODO: Chips that aren't apq8064 have a 200 Mhz max_clk */
 	config.max_clk = 266667000;
 	config.iommu = iommu_domain_alloc(&platform_bus_type);
-	if (config.iommu) {
-		config.iommu->geometry.aperture_start = 0x1000;
-		config.iommu->geometry.aperture_end = 0xffffffff;
-	}
 
 	return &config;
 }

drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c

···
 	static struct mdp5_cfg_platform config = {};
 
 	config.iommu = iommu_domain_alloc(&platform_bus_type);
-	if (config.iommu) {
-		config.iommu->geometry.aperture_start = 0x1000;
-		config.iommu->geometry.aperture_end = 0xffffffff;
-	}
 
 	return &config;
 }

drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c

···
 	mdelay(16);
 
 	if (config->platform.iommu) {
+		struct msm_mmu *mmu;
+
 		iommu_dev = &pdev->dev;
 		if (!dev_iommu_fwspec_get(iommu_dev))
 			iommu_dev = iommu_dev->parent;
 
-		aspace = msm_gem_address_space_create(iommu_dev,
-				config->platform.iommu, "mdp5");
+		mmu = msm_iommu_new(iommu_dev, config->platform.iommu);
+
+		aspace = msm_gem_address_space_create(mmu, "mdp5",
+			0x1000, 0xffffffff);
+
 		if (IS_ERR(aspace)) {
+			if (!IS_ERR(mmu))
+				mmu->funcs->destroy(mmu);
 			ret = PTR_ERR(aspace);
 			goto fail;
 		}

drivers/gpu/drm/msm/msm_drv.h

···
 void msm_gem_address_space_put(struct msm_gem_address_space *aspace);
 
 struct msm_gem_address_space *
-msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
-		const char *name);
-
-struct msm_gem_address_space *
-msm_gem_address_space_create_a2xx(struct device *dev, struct msm_gpu *gpu,
-		const char *name, uint64_t va_start, uint64_t va_end);
+msm_gem_address_space_create(struct msm_mmu *mmu, const char *name,
+		u64 va_start, u64 size);
 
 int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu);

drivers/gpu/drm/msm/msm_gem_vma.c

···
 	return 0;
 }
 
-
 struct msm_gem_address_space *
-msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
-		const char *name)
+msm_gem_address_space_create(struct msm_mmu *mmu, const char *name,
+		u64 va_start, u64 size)
 {
 	struct msm_gem_address_space *aspace;
-	u64 start = domain->geometry.aperture_start;
-	u64 size = domain->geometry.aperture_end - start;
+
+	if (IS_ERR(mmu))
+		return ERR_CAST(mmu);
 
 	aspace = kzalloc(sizeof(*aspace), GFP_KERNEL);
 	if (!aspace)
···
 
 	spin_lock_init(&aspace->lock);
 	aspace->name = name;
-	aspace->mmu = msm_iommu_new(dev, domain);
-	if (IS_ERR(aspace->mmu)) {
-		int ret = PTR_ERR(aspace->mmu);
+	aspace->mmu = mmu;
 
-		kfree(aspace);
-		return ERR_PTR(ret);
-	}
-
-	/*
-	 * Attaching the IOMMU device changes the aperture values so use the
-	 * cached values instead
-	 */
-	drm_mm_init(&aspace->mm, start >> PAGE_SHIFT, size >> PAGE_SHIFT);
-
-	kref_init(&aspace->kref);
-
-	return aspace;
-}
-
-struct msm_gem_address_space *
-msm_gem_address_space_create_a2xx(struct device *dev, struct msm_gpu *gpu,
-		const char *name, uint64_t va_start, uint64_t va_end)
-{
-	struct msm_gem_address_space *aspace;
-	u64 size = va_end - va_start;
-
-	aspace = kzalloc(sizeof(*aspace), GFP_KERNEL);
-	if (!aspace)
-		return ERR_PTR(-ENOMEM);
-
-	spin_lock_init(&aspace->lock);
-	aspace->name = name;
-	aspace->mmu = msm_gpummu_new(dev, gpu);
-	if (IS_ERR(aspace->mmu)) {
-		int ret = PTR_ERR(aspace->mmu);
-
-		kfree(aspace);
-		return ERR_PTR(ret);
-	}
-
-	drm_mm_init(&aspace->mm, (va_start >> PAGE_SHIFT),
-		size >> PAGE_SHIFT);
+	drm_mm_init(&aspace->mm, va_start >> PAGE_SHIFT, size >> PAGE_SHIFT);
 
 	kref_init(&aspace->kref);
 

drivers/gpu/drm/msm/msm_gpu.c

···
 	return 0;
 }
 
-static struct msm_gem_address_space *
-msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
-		uint64_t va_start, uint64_t va_end)
-{
-	struct msm_gem_address_space *aspace;
-
-	/*
-	 * Setup IOMMU.. eventually we will (I think) do this once per context
-	 * and have separate page tables per context.  For now, to keep things
-	 * simple and to get something working, just use a single address space:
-	 */
-	if (!adreno_is_a2xx(to_adreno_gpu(gpu))) {
-		struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type);
-		if (!iommu)
-			return NULL;
-
-		iommu->geometry.aperture_start = va_start;
-		iommu->geometry.aperture_end = va_end;
-
-		DRM_DEV_INFO(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
-
-		aspace = msm_gem_address_space_create(&pdev->dev, iommu, "gpu");
-		if (IS_ERR(aspace))
-			iommu_domain_free(iommu);
-	} else {
-		aspace = msm_gem_address_space_create_a2xx(&pdev->dev, gpu, "gpu",
-			va_start, va_end);
-	}
-
-	if (IS_ERR(aspace))
-		DRM_DEV_ERROR(gpu->dev->dev, "failed to init mmu: %ld\n",
-			PTR_ERR(aspace));
-
-	return aspace;
-}
-
 int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
 		const char *name, struct msm_gpu_config *config)
···
 
 	msm_devfreq_init(gpu);
 
-	gpu->aspace = msm_gpu_create_address_space(gpu, pdev,
-		config->va_start, config->va_end);
+
+	gpu->aspace = gpu->funcs->create_address_space(gpu, pdev);
 
 	if (gpu->aspace == NULL)
 		DRM_DEV_INFO(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);

drivers/gpu/drm/msm/msm_gpu.h

···
 
 struct msm_gpu_config {
 	const char *ioname;
-	uint64_t va_start;
-	uint64_t va_end;
 	unsigned int nr_rings;
 };
 
···
 	int (*gpu_state_put)(struct msm_gpu_state *state);
 	unsigned long (*gpu_get_freq)(struct msm_gpu *gpu);
 	void (*gpu_set_freq)(struct msm_gpu *gpu, unsigned long freq);
+	struct msm_gem_address_space *(*create_address_space)
+		(struct msm_gpu *gpu, struct platform_device *pdev);
 };
 
 struct msm_gpu {

drivers/gpu/drm/msm/msm_iommu.c

···
 	struct msm_iommu *iommu;
 	int ret;
 
+	if (!domain)
+		return ERR_PTR(-ENODEV);
+
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
 		return ERR_PTR(-ENOMEM);