Re: Broadcom WiFi SDIO performance regression after commit "mmc: sdhci: Remove finish_tasklet"

[Dmitry Osipenko]

27.08.2020 09:45, Adrian Hunter пишет:
> On 27/08/20 9:07 am, Dmitry Osipenko wrote:
>> Hello!
>>
>> I was debugging WiFi performance problems on Acer A500 tablet device
>> that has BCM4329 WiFi chip which is connected to NVIDIA Terga20 SoC via
>> SDIO and found that the following commit causes a solid 5-10 Mbit/s of
>> WiFi throughput regression after 5.2 kernel:
> 
> What is that in percentage terms?

That is about 20%.

>> commit c07a48c2651965e84d35cf193dfc0e5f7892d612
>> Author: Adrian Hunter <adrian.hunter@xxxxxxxxx>
>> Date:   Fri Apr 5 15:40:20 2019 +0300
>>
>>     mmc: sdhci: Remove finish_tasklet
>>
>>     Remove finish_tasklet. Requests that require DMA-unmapping or
>> sdhci_reset
>>     are completed either in the IRQ thread or a workqueue if the
>> completion is
>>     not initiated by the IRQ.
>>
>> Reverting the offending commit on top of recent linux-next resolves the
>> problem.
>>
>> Ulf / Adrian, do you have any ideas what could be done in regards to
>> restoring the SDIO performance? Should we just revert the offending commit?
>>
> 
> Unfortunately I think we are past the point of returning to the tasklet.
> 
> sdhci can complete requests in the irq handler but only if ->pre_req() and
> ->post_req() are used, which is not supported by SDIO at present.  pre_req
> and post_req were introduced to reduce latency for the block driver, so it
> seems reasonable perhaps to look at using them in SDIO as well.
> 

I'll try to take a look at pre/post_req(), but I'm not very familiar
with the MMC code, so it may take quite some time. Will be great if you
could help with making a patch that I could test!