High CPU load produced by USB (DW2)

[Minas Harutyunyan]

On 2/8/2018 5:07 PM, Mirza Krak wrote:
> On 8 February 2018 at 12:02, Minas Harutyunyan
> <Minas.Harutyunyan at synopsys.com> wrote:
>> Hi Mirza,
>>
>> On 2/7/2018 1:49 PM, Mirza Krak wrote:
> 
> < snip >
> 
>>
>> Could you please provide additional info:
>> 1. Does your core support descriptor DMA mode? (bits 31 and 30 of GHWCFG4).
>> 2. Version of core (GSNPSID)?
> 
> It does seem to support descriptor DMA mode, and content of both
> GHWCFG4 and GSNPSID are posted below.
> 
> root at esp5-d1:~# dmesg | grep -E "GHWCFG4|GSNPSID"
> [    1.109298] dwc2 ff540000.usb: GSNPSID @0xF0940040 : 0x4F54310A
> [    1.109344] dwc2 ff540000.usb: GHWCFG4 @0xF0940050 : 0xC8004030
> [    1.489016] dwc2 ff580000.usb: GSNPSID @0xF09C0040 : 0x4F54310A
> [    1.489063] dwc2 ff580000.usb: GHWCFG4 @0xF09C0050 : 0xDBF04030
> 
> Full register dump at boot (no devices connected) can be found at [1].
> 
>> 3. Do you connect any HS HUB between dwc core port and keyboard? Is it
>> available connection scenarios when Split traffic generated?
> 
> There is actually an HS HUB (FE1_QFP48) between dwc core and keyboard,
> I was not aware of it but it is mounted on the board.
> 
> 
> [1]. https://urldefense.proofpoint.com/v2/url?u=https-3A__gist.github.com_mirzak_a6245dddd4670f3b908a9783f9db8b0d&d=DwIFaQ&c=DPL6_X_6JkXFx7AXWqB0tg&r=6z9Al9FrHR_ZqbbtSAsD16pvOL2S3XHxQnSzq8kusyI&m=FuRmhDEOJlbUvuyApaxG_YmB514C3IOGSzs6Mq_fzC0&s=ELF0UP4IluOiL35JlnFjiltWZx-BcTIsTaPjaWb0RFk&e=
> 
Actually your core supported DDMA mode, moreover core allow SW to 
dynamically switch between BDMA and DDMA after core reset.
If dwc2 core work in DDMA mode then core can track (u)frames internally 
and unmasking SOF's not required, but Host in DDMA doesn't support Split 
transfers. This is why, in your case (FS/LS keyboard connected to HS 
HUB), core switched to BDMA and unmasking SOF interrupt to track (u)frames.

Thanks,
Minas