[Intel-gfx] [PATCH v7 06/15] drm/ttm: Add a generic TTM memcpy move for page-based iomem

Thomas Hellström thomas.hellstrom at linux.intel.com
Mon May 31 13:08:09 UTC 2021


On 5/31/21 2:36 PM, Christian König wrote:
> Am 31.05.21 um 14:19 schrieb Thomas Hellström:
>> The internal ttm_bo_util memcpy uses ioremap functionality, and while it
>> probably might be possible to use it for copying in- and out of
>> sglist represented io memory, using io_mem_reserve() / io_mem_free()
>> callbacks, that would cause problems with fault().
>> Instead, implement a method mapping page-by-page using kmap_local()
>> semantics. As an additional benefit we then avoid the occasional global
>> TLB flushes of ioremap() and consuming ioremap space, elimination of a
>> critical point of failure and with a slight change of semantics we could
>> also push the memcpy out async for testing and async driver development
>> purposes.
>>
>> A special linear iomem iterator is introduced internally to mimic the
>> old ioremap behaviour for code-paths that can't immediately be ported
>> over. This adds to the code size and should be considered a temporary
>> solution.
>>
>> Looking at the code we have a lot of checks for iomap tagged pointers.
>> Ideally we should extend the core memremap functions to also accept
>> uncached memory and kmap_local functionality. Then we could strip a
>> lot of code.
>>
>> Cc: Christian König <christian.koenig at amd.com>
>> Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
>> ---
>> v3:
>> - Split up in various TTM files and addressed review comments by
>>    Christian König. Tested and fixed legacy iomap memcpy path on i915.
>> v4:
>> - Fix an uninitialized variable
>>    Reported by: kernel test robot <lkp at intel.com>
>>    Reported by: Dan Carpenter <dan.carpenter at oracle.com>
>> - Minor change to the ttm_move_memcpy() interface.
>> - Gracefully handle lack of memremap() support on memcpy
>>    (Reported by Matthew Auld)
>> - Minor style fix (Reported by Matthew Auld)
>> ---
>>   drivers/gpu/drm/ttm/ttm_bo_util.c  | 280 ++++++++++-------------------
>>   drivers/gpu/drm/ttm/ttm_module.c   |  35 ++++
>>   drivers/gpu/drm/ttm/ttm_resource.c | 193 ++++++++++++++++++++
>>   drivers/gpu/drm/ttm/ttm_tt.c       |  42 +++++
>>   include/drm/ttm/ttm_bo_driver.h    |  28 +++
>>   include/drm/ttm/ttm_caching.h      |   2 +
>>   include/drm/ttm/ttm_kmap_iter.h    |  61 +++++++
>>   include/drm/ttm/ttm_resource.h     |  61 +++++++
>>   include/drm/ttm/ttm_tt.h           |  16 ++
>>   9 files changed, 536 insertions(+), 182 deletions(-)
>>   create mode 100644 include/drm/ttm/ttm_kmap_iter.h
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c 
>> b/drivers/gpu/drm/ttm/ttm_bo_util.c
>> index ae8b61460724..6ac7744a1a5c 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
>> @@ -72,190 +72,126 @@ void ttm_mem_io_free(struct ttm_device *bdev,
>>       mem->bus.addr = NULL;
>>   }
>>   -static int ttm_resource_ioremap(struct ttm_device *bdev,
>> -                   struct ttm_resource *mem,
>> -                   void **virtual)
>> +/**
>> + * ttm_move_memcpy - Helper to perform a memcpy ttm move operation.
>> + * @bo: The struct ttm_buffer_object.
>> + * @new_mem: The struct ttm_resource we're moving to (copy 
>> destination).
>> + * @new_iter: A struct ttm_kmap_iter representing the destination 
>> resource.
>> + * @src_iter: A struct ttm_kmap_iter representing the source resource.
>> + *
>> + * This function is intended to be able to move out async under a
>> + * dma-fence if desired.
>> + */
>> +void ttm_move_memcpy(struct ttm_buffer_object *bo,
>> +             pgoff_t num_pages,
>
> Can we switch to uint32_t for num_pages for TTM in general?
>
> That allows to copy 16TiB when you have 4KiB pages which should be 
> enough for quite a while and I had some really bad bugs because people 
> tend to do << PAGE_SHIFT and forget that it is only 32bit sometimes.

I can do that, although IIRC we've had some discussions internally that 
16TiB isn't enough for our bos in general, so at some point a request 
from us might to be to see what we can do to bump that across TTM for 
64-bit?

Matthew, you looked at this a couple of weeks ago?


>
> Apart from that feel free to stick my rb on the patch.

Thanks!

/Thomas


>
> Christian.
>


More information about the Intel-gfx mailing list