Re: [PATCH] soc: qcom: cmd-db: map shared memory as WT, not WB

[Nikita Travkin]

On Thu, Mar 28, 2024 at 04:12:11PM +0500, Nikita Travkin wrote:
> On Wed, Mar 27, 2024 at 08:09:34PM +0000, Volodymyr Babchuk wrote:
> > It appears that hardware does not like cacheable accesses to this
> > region. Trying to access this shared memory region as Normal Memory
> > leads to secure interrupt which causes an endless loop somewhere in
> > Trust Zone.
> > 
> > The only reason it is working right now is because Qualcomm Hypervisor
> > maps the same region as Non-Cacheable memory in Stage 2 translation
> > tables. The issue manifests if we want to use another hypervisor (like
> > Xen or KVM), which does not know anything about those specific
> > mappings. This patch fixes the issue by mapping the shared memory as
> > Write-Through. This removes dependency on correct mappings in Stage 2
> > tables.
> > 
> > I tested this on SA8155P with Xen.
> > 
> 
> Hi!
> 
> I observe a similar issue while trying to boot Linux in EL2 after taking
> over qcom's hyp on a sc7180 WoA device:
> 
> [    0.337736] CPU: All CPU(s) started at EL2
> (...)
> [    0.475135] Serial: AMBA PL011 UART driver
> [    0.479649] Internal error: synchronous external abort: 0000000096000410 [#1] PREEMPT SMP
> [    0.488053] Modules linked in:
> [    0.491213] CPU: 6 PID: 1 Comm: swapper/0 Not tainted 6.7.0 #41
> [    0.497310] Hardware name: Acer Aspire 1 (DT)
> [    0.501800] pstate: 00400009 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> [    0.508964] pc : cmd_db_dev_probe+0x38/0xc4
> [    0.513290] lr : cmd_db_dev_probe+0x2c/0xc4
> [    0.517606] sp : ffff8000817ebab0
> [    0.521019] x29: ffff8000817ebab0 x28: 0000000000000000 x27: ffff800081346050
>                      <uart cuts out>
> 
> Unfortunately this patch doesn't help in this case (I beileve I even
> tried same/similar change a while back when trying to debug this)
> 

I'm sorry, it looks like I made a mistake in my tooling while testing
this patch, which I only realized after trying Maulik's suggestion...

Both _WT and _WC fix the issue I see on sc7180 WoA, so whether you keep
the patch as is or change it to _WC as suggested:

Tested-By: Nikita Travkin <nikita@xxxxxxx> # sc7180 WoA in EL2

Thanks for looking into this!
Nikita

> Currently I can work around this by just reocationg the cmd-db while
> still under the qcom's hyp [1] but it would be nice to find a generic
> solution that doesn't need pre-boot hacks...
> 
> AFAIK this is not observed on at least sc8280xp WoA devices and I'd
> assume cros is not affected because they don't use qcom's TZ and instead
> use TF-A (which is overall more friendly, though still uses qcom's
> proprietary qtiseclib under the hood)
> 
> Nikita
> 
> [1] https://github.com/TravMurav/slbounce/blob/main/src/dtbhack_main.c#L17
> 
> > Signed-off-by: Volodymyr Babchuk <volodymyr_babchuk@xxxxxxxx>
> > ---
> >  drivers/soc/qcom/cmd-db.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c
> > index a5fd68411bed5..dd5ababdb476c 100644
> > --- a/drivers/soc/qcom/cmd-db.c
> > +++ b/drivers/soc/qcom/cmd-db.c
> > @@ -324,7 +324,7 @@ static int cmd_db_dev_probe(struct platform_device *pdev)
> >  		return -EINVAL;
> >  	}
> >  
> > -	cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WB);
> > +	cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WT);
> >  	if (!cmd_db_header) {
> >  		ret = -ENOMEM;
> >  		cmd_db_header = NULL;
> > -- 
> > 2.43.0