On 6/5/2025 4:44 PM, Johan Hovold wrote:
> On Thu, Jun 05, 2025 at 04:37:13PM +0800, Baochen Qiang wrote:
>> On 6/4/2025 10:45 PM, Johan Hovold wrote:
>>> As a follow up to commit:
>>>
>>> b67d2cf14ea ("wifi: ath12k: fix ring-buffer corruption")
>>>
>>> add the remaining missing memory barriers to make sure that destination
>>> ring descriptors are read after the head pointers to avoid using stale
>>> data on weakly ordered architectures like aarch64.
>>>
>>> Also switch back to plain accesses for the descriptor fields which is
>>> sufficient after the memory barrier.
>>>
>>> New in v2 are two patches that add the missing barriers also for source
>>> rings and when updating the tail pointer for destination rings.
>>>
>>> To avoid leaking ring details from the "hal" (lmac or non-lmac), the
>>> barriers are added to the ath12k_hal_srng_access_end() helper. For
>>
>> Could you elaborate? what do you mean by "leaking ring details from the 'hal'"?
>
> The type of barrier needed depends on the type of the ring. If we add
> the barrier directly in the caller, the caller would need to know what
> kind of ring (lmac or non-lmac) it is operating on, something which is
> currently abstracted away in the hal helpers.
>
Thanks, I get your point. I can see the difference in patch [3/4]
>>> symmetry I therefore moved also the dest ring barriers into
>>> ath12k_hal_srng_access_begin() and made the barrier conditional.
>
> Johan
