Abort driver load when num_mem_partitions is zero since operation is unreliable without valid memory partition info. Skip absent resources in soc_v1_0_get_xcp_res_info() to avoid divide-by-zero on firmware- reported zero instance counts.
v2: Remove redundant checks (Lijo) v3: Return error instead when num_mem_partitions is zero (Lijo) Signed-off-by: Asad Kamal <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 9 +++++++-- drivers/gpu/drm/amd/amdgpu/soc_v1_0.c | 4 +++- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 2b557c9096df..8bc347b75de0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -1762,10 +1762,15 @@ int amdgpu_gmc_init_mem_ranges(struct amdgpu_device *adev) valid = true; else valid = amdgpu_gmc_validate_partition_info(adev); - if (!valid) { - /* TODO: handle invalid case */ + if (!valid) dev_warn(adev->dev, "Mem ranges not matching with hardware config\n"); + + if (!adev->gmc.num_mem_partitions) { + dev_err(adev->dev, "num_mem_partitions is zero\n"); + kfree(adev->gmc.mem_partitions); + adev->gmc.mem_partitions = NULL; + return -EINVAL; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/soc_v1_0.c b/drivers/gpu/drm/amd/amdgpu/soc_v1_0.c index 5f05c8e68297..f3f3fac435d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/soc_v1_0.c @@ -600,8 +600,10 @@ static int soc_v1_0_get_xcp_res_info(struct amdgpu_xcp_mgr *xcp_mgr, xcp_cfg->num_res = ARRAY_SIZE(max_res); for (i = 0; i < xcp_cfg->num_res; i++) { - res_lt_xcp = max_res[i] < num_xcp; xcp_cfg->xcp_res[i].id = i; + if (!max_res[i]) + continue; + res_lt_xcp = max_res[i] < num_xcp; xcp_cfg->xcp_res[i].num_inst = res_lt_xcp ? 1 : max_res[i] / num_xcp; xcp_cfg->xcp_res[i].num_inst = -- 2.46.0
