Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1425344

Re: [PATCH 6/6] arm64: trap userspace "dc cvau" cache operation on errata-affected core

From Suzuki K Poulose <Suzuki.Poulose@arm.com>
Newsgroups linux.kernel
Subject Re: [PATCH 6/6] arm64: trap userspace "dc cvau" cache operation on errata-affected core
Date 2016-06-17 19:30 +0200
Message-ID <rL5KF-Zn-15@gated-at.bofh.it> (permalink)
References <rwWxA-11Z-19@gated-at.bofh.it> <rwWxA-11Z-17@gated-at.bofh.it> <rJZeh-7cH-5@gated-at.bofh.it> <rL5KF-Zn-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 17/06/16 18:20, Andre Przywara wrote:
> Hi Suzuki,
>
> thanks for having a look!
>
> On 14/06/16 17:16, Suzuki K Poulose wrote:
>> On 09/05/16 17:49, Andre Przywara wrote:
>>> The ARM errata 819472, 826319, 827319 and 824069 for affected
>>> Cortex-A53 cores demand to promote "dc cvau" instructions to
>>> "dc civac". Since we allow userspace to also emit those instructions,
>>> we should make sure that "dc cvau" gets promoted there too.
>>> So lets grasp the nettle here and actually trap every userland cache
>>> maintenance instruction once we detect at least one affected core in
>>> the system.
            __user_cache_maint("dc civac", address, ret);
>>> +            break;
>>> +        case 10:        /* DC CVAC, gets promoted */
>>> +            __user_cache_maint("dc civac", address, ret);
>>> +            break;
>>> +        case 14:        /* DC CIVAC */
>>> +            __user_cache_maint("dc civac", address, ret);
>>> +            break;
>>> +        case 5:            /* IC IVAU */
>>> +            __user_cache_maint("ic ivau", address, ret);
>>> +            break;
>>> +        default:
>>> +            force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
>>> +            return;
>>> +        }
>>> +    } else {
>>> +        force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
>>> +        return;
>>
>> Correct me if I am wrong, I think we should handle DC ZVA and emulate
>> the same ?
>> Thats the only EL0 accessible instruction we don't handle above.
>
> Mmmh, but why should we care?
> 1) DC ZVA is not trapped by setting SCTLR.UCI - instead it has its own
> bit (SCTLR.DZE).

You are right. I was thinking that UCI traps all DC operations. It only
traps  DC CVAU, DC CIVAC, DC CVAC, and IC IVAU.






Cheers
Suzuki

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

Re: [PATCH 6/6] arm64: trap userspace "dc cvau" cache operation on  errata-affected core Suzuki K Poulose <Suzuki.Poulose@arm.com> - 2016-06-14 18:20 +0200
  Re: [PATCH 6/6] arm64: trap userspace "dc cvau" cache operation on  errata-affected core Andre Przywara <andre.przywara@arm.com> - 2016-06-17 19:30 +0200
    Re: [PATCH 6/6] arm64: trap userspace "dc cvau" cache operation on  errata-affected core Suzuki K Poulose <Suzuki.Poulose@arm.com> - 2016-06-17 19:30 +0200

csiph-web