[PATCH] drm/amd/amdgpu: remove vram_page_split kernel option (v2)

[StDenis, Tom]

Ah ya I misread the original default as MiB instead of pages.


Tom

On 2019-06-06 6:35 a.m., Christian König wrote:
> Am 04.06.19 um 19:15 schrieb StDenis, Tom:
>> This option is no longer needed.  The default code paths
>> are now the only option.
>>
>> v2: Add HPAGE support and a default for non contiguous maps
>>
>> Signed-off-by: Tom St Denis <tom.stdenis at amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu.h          |  1 -
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c   |  7 -------
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c      |  8 --------
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 14 +++++++++-----
>>   4 files changed, 9 insertions(+), 21 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> index 19a00282e34c..e54f31865f60 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> @@ -142,7 +142,6 @@ extern uint amdgpu_sdma_phase_quantum;
>>   extern char *amdgpu_disable_cu;
>>   extern char *amdgpu_virtual_display;
>>   extern uint amdgpu_pp_feature_mask;
>> -extern int amdgpu_vram_page_split;
>>   extern int amdgpu_ngg;
>>   extern int amdgpu_prim_buf_per_se;
>>   extern int amdgpu_pos_buf_per_se;
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index d00fd5dd307a..ef7d99ebe92d 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -973,13 +973,6 @@ static int amdgpu_device_check_arguments(struct 
>> amdgpu_device *adev)
>>         amdgpu_device_check_block_size(adev);
>>   -    if (amdgpu_vram_page_split != -1 && (amdgpu_vram_page_split < 
>> 16 ||
>> -        !is_power_of_2(amdgpu_vram_page_split))) {
>> -        dev_warn(adev->dev, "invalid VRAM page split (%d)\n",
>> -             amdgpu_vram_page_split);
>> -        amdgpu_vram_page_split = 1024;
>> -    }
>> -
>>       ret = amdgpu_device_get_job_timeout_settings(adev);
>>       if (ret) {
>>           dev_err(adev->dev, "invalid lockup_timeout parameter 
>> syntax\n");
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
>> index 1f38d6fc1fe3..ef22a2a25448 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
>> @@ -108,7 +108,6 @@ int amdgpu_vm_fragment_size = -1;
>>   int amdgpu_vm_block_size = -1;
>>   int amdgpu_vm_fault_stop = 0;
>>   int amdgpu_vm_debug = 0;
>> -int amdgpu_vram_page_split = 512;
>>   int amdgpu_vm_update_mode = -1;
>>   int amdgpu_exp_hw_support = 0;
>>   int amdgpu_dc = -1;
>> @@ -342,13 +341,6 @@ module_param_named(vm_debug, amdgpu_vm_debug, 
>> int, 0644);
>>   MODULE_PARM_DESC(vm_update_mode, "VM update using CPU (0 = never 
>> (default except for large BAR(LB)), 1 = Graphics only, 2 = Compute 
>> only (default for LB), 3 = Both");
>>   module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
>>   -/**
>> - * DOC: vram_page_split (int)
>> - * Override the number of pages after we split VRAM allocations 
>> (default 512, -1 = disable). The default is 512.
>> - */
>> -MODULE_PARM_DESC(vram_page_split, "Number of pages after we split 
>> VRAM allocations (default 512, -1 = disable)");
>> -module_param_named(vram_page_split, amdgpu_vram_page_split, int, 0444);
>> -
>>   /**
>>    * DOC: exp_hw_support (int)
>>    * Enable experimental hw support (1 = enable). The default is 0 
>> (disabled).
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
>> index ec9ea3fdbb4a..0bc01e25a0b4 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
>> @@ -284,17 +284,21 @@ static int amdgpu_vram_mgr_new(struct 
>> ttm_mem_type_manager *man,
>>       if (!lpfn)
>>           lpfn = man->size;
>>   -    if (place->flags & TTM_PL_FLAG_CONTIGUOUS ||
>> -        amdgpu_vram_page_split == -1) {
>> +    if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
>>           pages_per_node = ~0ul;
>>           num_nodes = 1;
>>       } else {
>> -        pages_per_node = max((uint32_t)amdgpu_vram_page_split,
>> -                     mem->page_alignment);
>> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
>> +        pages_per_node = HPAGE_PMD_NR;
>> +#else
>> +        /* default to 512MB */
>> +        pages_per_node = (512UL << (20UL - PAGE_SHIFT));
>
> That is way to large, the fallback should be only 2MB (512 pages).
>
> Christian.
>
>> +#endif
>> +        pages_per_node = max((uint32_t)pages_per_node, 
>> mem->page_alignment);
>>           num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node);
>>       }
>>   -    nodes = kvmalloc_array(num_nodes, sizeof(*nodes),
>> +    nodes = kvmalloc_array((uint32_t)num_nodes, sizeof(*nodes),
>>                      GFP_KERNEL | __GFP_ZERO);
>>       if (!nodes)
>>           return -ENOMEM;
>