A8xx GPUs split GMEM evenly between their slices, and parts can have
slices fused off: a8xx_gpu_get_slice_info() reads the active slice mask
and folds the slice count into the chip ID. The GMEM size reported to
userspace (MSM_PARAM_GMEM_SIZE) is still the catalog value for all
slices, so on a part with fused-off slices userspace would size its
tiles and place its CCU caches past the end of the GMEM that exists.
Qualcomm's downstream driver reports GMEM for the active slices:
gen8_get_gmem_size() in KGSL divides the GMEM size by the number of
physical slices and multiplies it by the number of active ones. Do the
same when reading the slice mask. The GMEM protection and UCHE setup
still cover the full range, as in KGSL.
Fixes: 288a93200892 ("drm/msm/adreno: Introduce A8x GPU Support")
Signed-off-by: Rahul Pon <[email protected]>
---
Changes in v2:
- Reword the commit message without the device it was found on
- Parenthesize the GMEM expression and keep it on one line
- Link to v1:
https://lore.kernel.org/r/[email protected]
drivers/gpu/drm/msm/adreno/a8xx_gpu.c | 3 +++
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 3 ++-
drivers/gpu/drm/msm/adreno/adreno_gpu.h | 2 ++
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
index add93c1fa0..2f6f36fb8b 100644
--- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
@@ -112,6 +112,9 @@ void a8xx_gpu_get_slice_info(struct msm_gpu *gpu)
/* Chip ID depends on the number of slices available. So update it */
adreno_gpu->chip_id |= FIELD_PREP(GENMASK(7, 4), hweight32(slice_mask));
+ /* GMEM is split evenly between slices: report the active share */
+ adreno_gpu->gmem = (adreno_gpu->info->gmem / info->max_slices) *
hweight32(slice_mask);
+
/* Update the gpu-name to reflect the slice config: */
const char *name = devm_kasprintf(dev, GFP_KERNEL,
"%"ADRENO_CHIPID_FMT,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 5832dc25d6..dadfe4c694 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -379,7 +379,7 @@ int adreno_get_param(struct msm_gpu *gpu, struct
msm_context *ctx,
*value = adreno_gpu->info->revn;
return 0;
case MSM_PARAM_GMEM_SIZE:
- *value = adreno_gpu->info->gmem;
+ *value = adreno_gpu->gmem;
return 0;
case MSM_PARAM_GMEM_BASE:
if (adreno_gpu->info->family >= ADRENO_6XX_GEN3)
@@ -1205,6 +1205,7 @@ int adreno_gpu_init(struct drm_device *drm, struct
platform_device *pdev,
adreno_gpu->funcs = funcs;
adreno_gpu->info = config->info;
adreno_gpu->chip_id = config->chip_id;
+ adreno_gpu->gmem = config->info->gmem;
gpu->allow_relocs = config->info->family < ADRENO_6XX_GEN1;
gpu->pdev = pdev;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 114a40f79e..8e6a881036 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -204,6 +204,8 @@ struct adreno_gpu {
struct msm_gpu base;
const struct adreno_info *info;
uint32_t chip_id;
+ /* GMEM size available to userspace, see a8xx_gpu_get_slice_info(): */
+ uint32_t gmem;
uint16_t speedbin;
const struct adreno_gpu_funcs *funcs;
base-commit: d33622598496c8994c35ba0a8a913de064dfc1a4
--
2.53.0
