Re: [dpdk-dev] rte_vfio_container_dma_map/unmap functions

["Burakov, Anatoly" <anatoly.burakov@intel.com>]

On 20-Apr-20 6:39 PM, Thomas Monjalon wrote:
> 20/04/2020 16:07, Burakov, Anatoly:
>> On 19-Apr-20 2:10 PM, Thomas Monjalon wrote:
>>> 19/04/2020 15:09, Thomas Monjalon:
>>>> 17/04/2020 16:09, Burakov, Anatoly:
>>>>> On 17-Apr-20 3:05 PM, Burakov, Anatoly wrote:
>>>>>> On 22-Mar-20 5:20 PM, Tal Shnaiderman wrote:
>>>>>>> Hi Anatoly,
>>>>>>>
>>>>>>> I’m working on the implementation of bus/pci driver for Windows,
>>>>>>> pci_common.c uses the titled functions however they are relevant only
>>>>>>> for Linux OS.
>>>>>>>
>>>>>>> I’m wondering if the implementation of those functions should be moved
>>>>>>> to a Linux specific area since FreeBSD (and now Windows) are forced to
>>>>>>> implemented those in the current state.
>>>>>
>>>>> Unfortunately, we don't have a generic API for these, but since we
>>>>> export a single API on all platforms, either all platforms have to
>>>>> implement these functions, or none of them do. There's simply no way to
>>>>> avoid implementing stubs for these functions, short of coming up with a
>>>>> generic API that would replace these. Given that this API is heavily
>>>>> Linux specific, i don't see that happening.
>>>>
>>>> Because it is Linux specific, we should not force FreeBSD and Windows
>>>> having stubs. Can we move VFIO calls in Linux-specific files?
>>>>
>>>> I think rte_vfio.h should be moved in lib/librte_eal/linux/include.
>>>
>>> +Cc Bruce and David
>>
>> ...and have a Linux-specific ABI?
> 
> Yes, the ABI is different depending on arch and OS.
> That's a fact, and I don't see any problem with it.
> 

OK, no objections then :)

-- 
Thanks,
Anatoly