Re: Problem with atomic accesses in pstore on some ARM CPUs

From: Guenter Roeck
Date: Tue Aug 16 2016 - 09:17:38 EST


On Tue, Aug 16, 2016 at 3:32 AM, Robin Murphy <robin.murphy@xxxxxxx> wrote:
> Hi Guenter,
>
> On 16/08/16 00:19, Guenter Roeck wrote:
>> Hi,
>>
>> we are having a problem with atomic accesses in pstore on some ARM
>> CPUs (specifically rk3288 and rk3399). With those chips, atomic
>> accesses fail with both pgprot_noncached and pgprot_writecombine
>> memory. Atomic accesses do work when selecting PAGE_KERNEL protection.
>
> What's the pstore backed by? I'm guessing it's not normal DRAM.
>

it is normal DRAM.

>> Debugging on rk3399 shows the following crash.
>>
>> [ 0.912669] Bad mode in Error handler detected, code 0xbf000002 -- SError
>> [ 0.920140] CPU: 4 PID: 1 Comm: swapper/0 Not tainted 4.4.14 #389
>> [ 0.926838] Hardware name: Google Kevin (DT)
>> [ 0.931533] task: ffffffc0edfe0000 ti: ffffffc0edf7c000 task.ti:
>> ffffffc0edf 7c000
>> [ 0.939780] PC is at __ll_sc___cmpxchg_case_mb_4+0x2c/0x5c
>> [ 0.945811] LR is at 0x1
>>
>> The "solution" for this problem in various Chrome OS releases is to
>> disable atomic accesses in pstore entirely, which seems to be a bit
>> brute-force. Question is what a proper upstream-acceptable solution
>
> From that, it sounds like the endpoint doesn't support exclusive
> accesses. I imagine you get away with it through a PAGE_KERNEL mapping
> by virtue of being write-back cacheable, such that the exclusives end up
> being handled by the local monitor at L1 and don't go out to memory, but
> I'm not sure even that's necessarily reliable.
>
> In general terms, not doing atomic accesses is probably the only 100%
> safe solution.
>
Not sure I understand. Atomics work for the rest of the DRAM. Can't I
just use the same access protection ?

Thanks,
Guenter

> Robin.
>
>> might be. Introduce another memory type to select PAGE_KERNEL ? Is
>> there some means to determine if atomic operations are supported with
>> a given protection mask, maybe ? Anything else ?
>>
>> Thanks,
>> Guenter
>>
>> _______________________________________________
>> linux-arm-kernel mailing list
>> linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
>>
>