On Thu, Sep 9, 2021 at 1:54 PM Rob Clark <robdclark@xxxxxxxxx> wrote:
>
> On Thu, Sep 9, 2021 at 12:50 PM Akhil P Oommen <akhilpo@xxxxxxxxxxxxxx> wrote:
> >
> > On 9/9/2021 9:42 PM, Amit Pundir wrote:
> > > On Thu, 9 Sept 2021 at 17:47, Amit Pundir <amit.pundir@xxxxxxxxxx> wrote:
> > >>
> > >> On Wed, 8 Sept 2021 at 07:50, Bjorn Andersson
> > >> <bjorn.andersson@xxxxxxxxxx> wrote:
> > >>>
> > >>> On Mon 09 Aug 10:26 PDT 2021, Akhil P Oommen wrote:
> > >>>
> > >>>> On 8/9/2021 9:48 PM, Caleb Connolly wrote:
> > >>>>>
> > >>>>>
> > >>>>> On 09/08/2021 17:12, Rob Clark wrote:
> > >>>>>> On Mon, Aug 9, 2021 at 7:52 AM Akhil P Oommen
> > >>>>>> <akhilpo@xxxxxxxxxxxxxx> wrote:
> > >>> [..]
> > >>>>>>> I am a bit confused. We don't define a power domain for gpu in dt,
> > >>>>>>> correct? Then what exactly set_opp do here? Do you think this usleep is
> > >>>>>>> what is helping here somehow to mask the issue?
> > >>>>> The power domains (for cx and gx) are defined in the GMU DT, the OPPs in
> > >>>>> the GPU DT. For the sake of simplicity I'll refer to the lowest
> > >>>>> frequency (257000000) and OPP level (RPMH_REGULATOR_LEVEL_LOW_SVS) as
> > >>>>> the "min" state, and the highest frequency (710000000) and OPP level
> > >>>>> (RPMH_REGULATOR_LEVEL_TURBO_L1) as the "max" state. These are defined in
> > >>>>> sdm845.dtsi under the gpu node.
> > >>>>>
> > >>>>> The new devfreq behaviour unmasks what I think is a driver bug, it
> > >>>>> inadvertently puts much more strain on the GPU regulators than they
> > >>>>> usually get. With the new behaviour the GPU jumps from it's min state to
> > >>>>> the max state and back again extremely rapidly under workloads as small
> > >>>>> as refreshing UI. Where previously the GPU would rarely if ever go above
> > >>>>> 342MHz when interacting with the device, it now jumps between min and
> > >>>>> max many times per second.
> > >>>>>
> > >>>>> If my understanding is correct, the current implementation of the GMU
> > >>>>> set freq is the following:
> > >>>>> - Get OPP for frequency to set
> > >>>>> - Push the frequency to the GMU - immediately updating the core clock
> > >>>>> - Call dev_pm_opp_set_opp() which triggers a notify chain, this winds
> > >>>>> up somewhere in power management code and causes the gx regulator level
> > >>>>> to be updated
> > >>>>
> > >>>> Nope. dev_pm_opp_set_opp() sets the bandwidth for gpu and nothing else. We
> > >>>> were using a different api earlier which got deprecated -
> > >>>> dev_pm_opp_set_bw().
> > >>>>
> > >>>
> > >>> On the Lenovo Yoga C630 this is reproduced by starting alacritty and if
> > >>> I'm lucky I managed to hit a few keys before it crashes, so I spent a
> > >>> few hours looking into this as well...
> > >>>
> > >>> As you say, the dev_pm_opp_set_opp() will only cast a interconnect vote.
> > >>> The opp-level is just there for show and isn't used by anything, at
> > >>> least not on 845.
> > >>>
> > >>> Further more, I'm missing something in my tree, so the interconnect
> > >>> doesn't hit sync_state, and as such we're not actually scaling the
> > >>> buses. So the problem is not that Linux doesn't turn on the buses in
> > >>> time.
> > >>>
> > >>> So I suspect that the "AHB bus error" isn't saying that we turned off
> > >>> the bus, but rather that the GPU becomes unstable or something of that
> > >>> sort.
> > >>>
> > >>>
> > >>> Lastly, I reverted 9bc95570175a ("drm/msm: Devfreq tuning") and ran
> > >>> Aquarium for 20 minutes without a problem. I then switched the gpu
> > >>> devfreq governor to "userspace" and ran the following:
> > >>>
> > >>> while true; do
> > >>> echo 257000000 > /sys/class/devfreq/5000000.gpu/userspace/set_freq
> > >>> echo 710000000 > /sys/class/devfreq/5000000.gpu/userspace/set_freq
> > >>> done
> > >>>
> > >>> It took 19 iterations of this loop to crash the GPU.
> > >>
> > >> Ack. With your above script, I can reproduce a crash too on db845c
> > >> (A630) running v5.14. I didn't get any crash log though and device
> > >> just rebooted to USB crash mode.
> > >>
> > >> And same crash on RB5 (A650) too https://hastebin.com/raw/ejutetuwun
> >
> > Are we sure this is the same issue? It could be, but I thought we were
> > seeing a bunch of random gpu errors (which may eventually hit device crash).
>
> In the sense that async-serror often seems to be a clk issue, it
> *could* be related.. but this would have to be triggered by CPU
> access. The symptom does seem very different.
>
The more I think about it, the more I think this is a different
issue.. a650 is somewhat different wrt gmu (ie. hfi vs legacy code
paths).
Amit, could you try the same experiment (with 9bc95570175a ("drm/msm:
Devfreq tuning") revert) while running something like webgl aquarium
to prevent the GPU from suspending? I'm kinda suspecting the issue
you hit is more likely some suspend/resume issue.
BR,
-R
