@@ -251,8 +251,8 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
gpu_write(gpu, REG_A4XX_UCHE_CACHE_WAYS_VFD, 0x07);
/* Disable L2 bypass to avoid UCHE out of bounds errors */
- gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, 0xffff0000);
- gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, 0xffff0000);
+ gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base));
+ gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base));
gpu_write(gpu, REG_A4XX_CP_DEBUG, (1 << 25) |
(adreno_is_a420(adreno_gpu) ? (1 << 29) : 0));
@@ -693,6 +693,8 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
if (ret)
goto fail;
+ adreno_gpu->uche_trap_base = 0xffff0000ffff0000ull;
+
if (!gpu->aspace) {
/* TODO we think it is possible to configure the GPU to
* restrict access to VRAM carveout. But the required
@@ -750,10 +750,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
gpu_write(gpu, REG_A5XX_UCHE_CACHE_WAYS, 0x02);
/* Disable L2 bypass in the UCHE */
- gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, 0xFFFF0000);
- gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, 0x0001FFFF);
- gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, 0xFFFF0000);
- gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, 0x0001FFFF);
+ gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base));
+ gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base));
+ gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base));
+ gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base));
/* Set the GMEM VA range (0 to gpu->gmem) */
gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000);
@@ -1805,5 +1805,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
adreno_gpu->ubwc_config.macrotile_mode = 0;
adreno_gpu->ubwc_config.ubwc_swizzle = 0x7;
+ adreno_gpu->uche_trap_base = 0x0001ffffffff0000ull;
+
return gpu;
}
@@ -1123,12 +1123,12 @@ static int hw_init(struct msm_gpu *gpu)
/* Disable L2 bypass in the UCHE */
if (adreno_is_a7xx(adreno_gpu)) {
- gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu);
- gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu);
+ gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base);
+ gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base);
} else {
- gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, 0x0001ffffffffffc0llu);
- gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu);
- gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu);
+ gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, adreno_gpu->uche_trap_base + 0xfc0);
+ gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base);
+ gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base);
}
if (!(adreno_is_a650_family(adreno_gpu) ||
@@ -2533,6 +2533,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
}
}
+ adreno_gpu->uche_trap_base = 0x1fffffffff000ull;
+
if (gpu->aspace)
msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu,
a6xx_fault_handler);
@@ -386,6 +386,11 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
case MSM_PARAM_MACROTILE_MODE:
*value = adreno_gpu->ubwc_config.macrotile_mode;
return 0;
+ case MSM_PARAM_UCHE_TRAP_BASE:
+ if (adreno_gpu->uche_trap_base == 0)
+ return UERR(EINVAL, drm, "no uche trap base");
+ *value = adreno_gpu->uche_trap_base;
+ return 0;
default:
return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param);
}
@@ -253,6 +253,8 @@ struct adreno_gpu {
bool gmu_is_wrapper;
bool has_ray_tracing;
+
+ u64 uche_trap_base;
};
#define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
@@ -90,6 +90,7 @@ struct drm_msm_timespec {
#define MSM_PARAM_RAYTRACING 0x11 /* RO */
#define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */
#define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */
+#define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */
/* For backwards compat. The original support for preemption was based on
* a single ring per priority level so # of priority levels equals the #
On at least a6xx+, shader could read 64b ALWAYSON counter from UCHE_TRAP_BASE+0 address. In Mesa it will be used to implement VK_KHR_shader_clock and GL_ARB_shader_clock. These extensions provide shader functions to query a real-time or monotonically incrementing counter at the subgroup level or across the device level. On a4xx and a5xx it was not tested what is at UCHE_TRAP_BASE address, there uche trap base is exposed just for completeness. Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com> --- Changes in v2: - Rebased on top of https://patchwork.freedesktop.org/series/141667/ in order to return error via UERR when there is no uche trap base. - Updated commit message to explain why we need to expose the value. --- drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 6 ++++-- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 10 ++++++---- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 12 +++++++----- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 5 +++++ drivers/gpu/drm/msm/adreno/adreno_gpu.h | 2 ++ include/uapi/drm/msm_drm.h | 1 + 6 files changed, 25 insertions(+), 11 deletions(-)