[PATCH v2 2/8] drm/ttm: Remap all page faults to per process dummy page.

[Andrey Grodzovsky]

On 6/22/20 5:41 AM, Daniel Vetter wrote:
> On Sun, Jun 21, 2020 at 02:03:02AM -0400, Andrey Grodzovsky wrote:
>> On device removal reroute all CPU mappings to dummy page per drm_file
>> instance or imported GEM object.
>>
>> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
>> ---
>>   drivers/gpu/drm/ttm/ttm_bo_vm.c | 65 ++++++++++++++++++++++++++++++++++++-----
>>   1 file changed, 57 insertions(+), 8 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> index 389128b..2f8bf5e 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> @@ -35,6 +35,8 @@
>>   #include <drm/ttm/ttm_bo_driver.h>
>>   #include <drm/ttm/ttm_placement.h>
>>   #include <drm/drm_vma_manager.h>
>> +#include <drm/drm_drv.h>
>> +#include <drm/drm_file.h>
>>   #include <linux/mm.h>
>>   #include <linux/pfn_t.h>
>>   #include <linux/rbtree.h>
>> @@ -328,19 +330,66 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
> Hm I think diff and code flow look a bit bad now. What about renaming the
> current function to __ttm_bo_vm_fault and then having something like the
> below:
>
> ttm_bo_vm_fault(args) {
>
> 	if (drm_dev_enter()) {
> 		__ttm_bo_vm_fault(args);
> 		drm_dev_exit();
> 	} else  {
> 		drm_gem_insert_dummy_pfn();
> 	}
> }
>
> I think drm_gem_insert_dummy_pfn(); should be portable across drivers, so
> another nice point to try to unifiy drivers as much as possible.
> -Daniel
>
>>   	pgprot_t prot;
>>   	struct ttm_buffer_object *bo = vma->vm_private_data;
>>   	vm_fault_t ret;
>> +	int idx;
>> +	struct drm_device *ddev = bo->base.dev;
>>   
>> -	ret = ttm_bo_vm_reserve(bo, vmf);
>> -	if (ret)
>> -		return ret;
>> +	if (drm_dev_enter(ddev, &idx)) {
>> +		ret = ttm_bo_vm_reserve(bo, vmf);
>> +		if (ret)
>> +			goto exit;
>> +
>> +		prot = vma->vm_page_prot;
>>   
>> -	prot = vma->vm_page_prot;
>> -	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
>> -	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
>> +		ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
>> +		if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
>> +			goto exit;
>> +
>> +		dma_resv_unlock(bo->base.resv);
>> +
>> +exit:
>> +		drm_dev_exit(idx);
>>   		return ret;
>> +	} else {
>>   
>> -	dma_resv_unlock(bo->base.resv);
>> +		struct drm_file *file = NULL;
>> +		struct page *dummy_page = NULL;
>> +		int handle;
>>   
>> -	return ret;
>> +		/* We are faulting on imported BO from dma_buf */
>> +		if (bo->base.dma_buf && bo->base.import_attach) {
>> +			dummy_page = bo->base.dummy_page;
>> +		/* We are faulting on non imported BO, find drm_file owning the BO*/
> Uh, we can't fish that out of the vma->vm_file pointer somehow? Or is that
> one all wrong? Doing this kind of list walk looks pretty horrible.
>
> If the vma doesn't have the right pointer I guess next option is that we
> store the drm_file page in gem_bo->dummy_page, and replace it on first
> export. But that's going to be tricky to track ...


For this one I hope to make all of this obsolete if Christian's suggestion from 
path 1/8 about mapping
global RO dummy page for read and COW on write will be possible to implement 
(testing
that indeed no memory usage explodes)

Andrey


>
>> +		} else {
>> +			struct drm_gem_object *gobj;
>> +
>> +			mutex_lock(&ddev->filelist_mutex);
>> +			list_for_each_entry(file, &ddev->filelist, lhead) {
>> +				spin_lock(&file->table_lock);
>> +				idr_for_each_entry(&file->object_idr, gobj, handle) {
>> +					if (gobj == &bo->base) {
>> +						dummy_page = file->dummy_page;
>> +						break;
>> +					}
>> +				}
>> +				spin_unlock(&file->table_lock);
>> +			}
>> +			mutex_unlock(&ddev->filelist_mutex);
>> +		}
>> +
>> +		if (dummy_page) {
>> +			/*
>> +			 * Let do_fault complete the PTE install e.t.c using vmf->page
>> +			 *
>> +			 * TODO - should i call free_page somewhere ?
> Nah, instead don't call get_page. The page will be around as long as
> there's a reference for the drm_file or gem_bo, which is longer than any
> mmap. Otherwise yes this would like really badly.
>
>> +			 */
>> +			get_page(dummy_page);
>> +			vmf->page = dummy_page;
>> +			return 0;
>> +		} else {
>> +			return VM_FAULT_SIGSEGV;
> Hm that would be a kernel bug, wouldn't it? WARN_ON() required here imo.
> -Daniel
>
>> +		}
>> +	}
>>   }
>>   EXPORT_SYMBOL(ttm_bo_vm_fault);
>>   
>> -- 
>> 2.7.4
>>