@@ -401,6 +401,33 @@ static struct msm_gpu_state *a2xx_gpu_state_get(struct msm_gpu *gpu)
return state;
}
+static struct msm_gem_address_space *
+a2xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+ struct msm_gem_address_space *aspace;
+ struct msm_mmu *mmu = msm_gpummu_new(&pdev->dev, gpu);
+ int ret;
+
+ if (IS_ERR(mmu))
+ return ERR_CAST(mmu);
+
+ ret = mmu->funcs->attach(mmu, NULL, 0);
+ if (ret) {
+ mmu->funcs->destroy(mmu);
+ return ERR_PTR(ret);
+ }
+
+ aspace = msm_gem_address_space_create(mmu, "gpu",
+ SZ_16M, SZ_16M + 0xfff * SZ_64K);
+
+ if (IS_ERR(aspace)) {
+ mmu->funcs->detach(mmu, NULL, 0);
+ 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),
@@ -429,6 +456,7 @@ static const struct adreno_gpu_funcs funcs = {
#endif
.gpu_state_get = a2xx_gpu_state_get,
.gpu_state_put = adreno_gpu_state_put,
+ .create_address_space = a2xx_create_address_space,
},
};
@@ -448,6 +448,7 @@ static const struct adreno_gpu_funcs funcs = {
#endif
.gpu_state_get = a3xx_gpu_state_get,
.gpu_state_put = adreno_gpu_state_put,
+ .create_address_space = adreno_gpu_create_address_space,
},
};
@@ -538,6 +538,7 @@ static const struct adreno_gpu_funcs funcs = {
#endif
.gpu_state_get = a4xx_gpu_state_get,
.gpu_state_put = adreno_gpu_state_put,
+ .create_address_space = adreno_gpu_create_address_space,
},
.get_timestamp = a4xx_get_timestamp,
};
@@ -1385,6 +1385,7 @@ static const struct adreno_gpu_funcs funcs = {
.gpu_busy = a5xx_gpu_busy,
.gpu_state_get = a5xx_gpu_state_get,
.gpu_state_put = a5xx_gpu_state_put,
+ .create_address_space = adreno_gpu_create_address_space,
},
.get_timestamp = a5xx_get_timestamp,
};
@@ -810,6 +810,61 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
return (unsigned long)busy_time;
}
+static struct msm_gem_address_space *
+a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+ struct msm_gem_address_space *aspace;
+ struct iommu_domain *iommu;
+ struct msm_mmu *mmu;
+ int ret, val = 0;
+ u64 start, end;
+
+ iommu = iommu_domain_alloc(&platform_bus_type);
+ if (!iommu)
+ return NULL;
+
+ mmu = msm_iommu_new(&pdev->dev, iommu);
+ if (IS_ERR(mmu)) {
+ iommu_domain_free(iommu);
+ return ERR_CAST(mmu);
+ }
+
+ ret = mmu->funcs->attach(mmu, NULL, 0);
+ if (ret) {
+ mmu->funcs->destroy(mmu);
+ return ERR_PTR(ret);
+ }
+
+ iommu_domain_get_attr(iommu, DOMAIN_ATTR_SPLIT_TABLES, &val);
+
+ /*
+ * If split pagetables are enabled our virtual address range will start
+ * at 0xfff0000000000000 and we don't need to worry about a hole for the
+ * GMEM.
+ */
+ if (val)
+ start = iommu->geometry.aperture_start;
+ else
+ start = SZ_16M;
+
+ /*
+ * Regardless of the start, always take advantage of the entire
+ * available space
+ */
+ end = iommu->geometry.aperture_end;
+
+ DRM_DEV_INFO(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
+
+ aspace = msm_gem_address_space_create(mmu, "gpu", start, end);
+ if (IS_ERR(aspace)) {
+ mmu->funcs->detach(mmu, NULL, 0);
+ mmu->funcs->destroy(mmu);
+ }
+
+ return aspace;
+}
+
+
static const struct adreno_gpu_funcs funcs = {
.base = {
.get_param = adreno_get_param,
@@ -832,6 +887,7 @@ static const struct adreno_gpu_funcs funcs = {
.gpu_state_get = a6xx_gpu_state_get,
.gpu_state_put = a6xx_gpu_state_put,
#endif
+ .create_address_space = a6xx_create_address_space,
},
.get_timestamp = a6xx_get_timestamp,
};
@@ -18,6 +18,43 @@
#include "msm_gem.h"
#include "msm_mmu.h"
+/* Helper function for GPU targets that use arm-smmu but not split pagetables */
+struct msm_gem_address_space *
+adreno_gpu_create_address_space(struct msm_gpu *gpu,
+ struct platform_device *pdev)
+{
+ struct msm_gem_address_space *aspace;
+ struct iommu_domain *iommu;
+ struct msm_mmu *mmu;
+ int ret;
+
+ iommu = iommu_domain_alloc(&platform_bus_type);
+ if (!iommu)
+ return NULL;
+
+ mmu = msm_iommu_new(&pdev->dev, iommu);
+ if (IS_ERR(mmu)) {
+ iommu_domain_free(iommu);
+ return ERR_CAST(mmu);
+ }
+
+ ret = mmu->funcs->attach(mmu, NULL, 0);
+ if (ret) {
+ mmu->funcs->destroy(mmu);
+ return ERR_PTR(ret);
+ }
+
+ DRM_DEV_INFO(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
+
+ aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M, 0xffffffff);
+ if (IS_ERR(aspace)) {
+ mmu->funcs->detach(mmu, NULL, 0);
+ mmu->funcs->destroy(mmu);
+ }
+
+ return aspace;
+}
+
static bool zap_available = true;
static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
@@ -908,12 +945,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
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;
adreno_get_pwrlevels(&pdev->dev, gpu);
@@ -247,6 +247,11 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state);
int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
int adreno_gpu_state_put(struct msm_gpu_state *state);
+
+struct msm_gem_address_space *
+adreno_gpu_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
@@ -9,7 +9,6 @@
#include "msm_mmu.h"
#include "msm_fence.h"
#include "msm_gpu_trace.h"
-#include "adreno/adreno_gpu.h"
#include <generated/utsrelease.h>
#include <linux/string_helpers.h>
@@ -801,56 +800,6 @@ static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu)
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;
- struct msm_mmu *mmu;
- int ret;
-
- /*
- * 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;
-
- mmu = msm_iommu_new(&pdev->dev, iommu);
- if (IS_ERR(mmu)) {
- iommu_domain_free(iommu);
- return ERR_CAST(mmu);
- }
-
- DRM_DEV_INFO(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
-
- } else {
- mmu = msm_gpummu_new(&pdev->dev, gpu);
- if (IS_ERR(mmu))
- return ERR_CAST(mmu);
- }
-
- aspace = msm_gem_address_space_create(mmu, "gpu", va_start, va_end);
- if (IS_ERR(aspace)) {
- mmu->funcs->destroy(mmu);
-
- DRM_DEV_ERROR(gpu->dev->dev, "failed to init mmu: %ld\n",
- PTR_ERR(aspace));
- return ERR_CAST(aspace);
- }
-
- ret = aspace->mmu->funcs->attach(aspace->mmu, NULL, 0);
- if (ret) {
- msm_gem_address_space_put(aspace);
- return ERR_PTR(ret);
- }
-
- 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)
@@ -923,12 +872,13 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
msm_devfreq_init(gpu);
- gpu->aspace = msm_gpu_create_address_space(gpu, pdev,
- config->va_start, config->va_end);
+ gpu->aspace = funcs->create_address_space(gpu, pdev);
if (gpu->aspace == NULL)
DRM_DEV_INFO(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);
else if (IS_ERR(gpu->aspace)) {
+ DRM_DEV_ERROR(gpu->dev->dev, "failed to init mmu: %ld\n",
+ PTR_ERR(gpu->aspace));
ret = PTR_ERR(gpu->aspace);
goto fail;
}
@@ -21,8 +21,6 @@ struct msm_gpu_state;
struct msm_gpu_config {
const char *ioname;
- uint64_t va_start;
- uint64_t va_end;
unsigned int nr_rings;
};
@@ -64,6 +62,8 @@ struct msm_gpu_funcs {
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 {
Use a per-target function to set up the default address space for each GPU. This allows a6xx targets to set up the correct address range if split pagetables are enabled by the IOMMU device. This also gets rid of a misplaced bit of a2xx code in msm_gpu and returns it to where it belongs. Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org> --- drivers/gpu/drm/msm/adreno/a2xx_gpu.c | 28 +++++++++++++++++ drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 1 + drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 1 + drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 1 + drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 56 +++++++++++++++++++++++++++++++++ drivers/gpu/drm/msm/adreno/adreno_gpu.c | 43 +++++++++++++++++++++---- drivers/gpu/drm/msm/adreno/adreno_gpu.h | 5 +++ drivers/gpu/drm/msm/msm_gpu.c | 56 ++------------------------------- drivers/gpu/drm/msm/msm_gpu.h | 4 +-- 9 files changed, 134 insertions(+), 61 deletions(-)