Re: [PATCH v2] net/af_xdp: fix umem map size for zero copy

[Ferruh Yigit <ferruh.yigit@amd.com>]

On 5/22/2024 12:03 PM, Morten Brørup wrote:
>> From: Ferruh Yigit [mailto:ferruh.yigit@amd.com]
>> Sent: Wednesday, 22 May 2024 12.01
>>
>> On 5/22/2024 2:25 AM, Du, Frank wrote:
>>>> From: Ferruh Yigit <ferruh.yigit@amd.com>
>>>> Sent: Wednesday, May 22, 2024 1:58 AM
>>>>
>>>> Isn't there a mempool flag that can help us figure out mempool is not IOVA
>>>> contiguous? Isn't it sufficient on its own?
>>>
>>> Indeed, what we need to ascertain is whether it's contiguous in CPU virtual
>> space, not IOVA. I haven't come across a flag specifically for CPU virtual
>> contiguity. The major limitation in XDP is XSK UMEM only supports registering
>> a single contiguous virtual memory area.
>>>
>>
>> 'RTE_MEMPOOL_F_NO_IOVA_CONTIG' is the flag I was looking for. This flag
>> being *cleared* implies IOVA contiguous but not sure if it is
>> guaranteed, need to check.
> 
> Wrong.
> RTE_MEMPOOL_F_NO_IOVA_CONTIG only relates to individual objects in the pool. This flag being cleared only means that each individual object in the mempool is IOVA contiguous.
> It does not imply that the entire pool of objects is IOVA contiguous.
> 

Ah, thanks for clarification.