linux-kernel - Re: [PATCH] iommu/io-pgtable-arm: Optimize partial walk flush for large scatter-gather list

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 16 Jun 2021 14:33:04 +0530
From:   Sai Prakash Ranjan <saiprakash.ranjan@...eaurora.org>
To:     Robin Murphy <robin.murphy@....com>
Cc:     Krishna Reddy <vdumpa@...dia.com>, linux-arm-msm@...r.kernel.org,
        linux-kernel@...r.kernel.org, iommu@...ts.linux-foundation.org,
        Will Deacon <will@...nel.org>,
        linux-arm-kernel@...ts.infradead.org,
        Thierry Reding <treding@...dia.com>
Subject: Re: [PATCH] iommu/io-pgtable-arm: Optimize partial walk flush for
 large scatter-gather list

On 2021-06-16 12:28, Sai Prakash Ranjan wrote:
> Hi Robin,
> 
> On 2021-06-15 19:23, Robin Murphy wrote:
>> On 2021-06-15 12:51, Sai Prakash Ranjan wrote:
> 
> <snip>...
> 
>>> Hi @Robin, from these discussions it seems they are not ok with the 
>>> change
>>> for all SoC vendor implementations and do not have any data on such 
>>> impact.
>>> As I mentioned above, on QCOM platforms we do have several 
>>> optimizations in HW
>>> for TLBIs and would like to make use of it and reduce the unmap 
>>> latency.
>>> What do you think, should this be made implementation specific?
>> 
>> Yes, it sounds like there's enough uncertainty for now that this needs
>> to be an opt-in feature. However, I still think that non-strict mode
>> could use it generically, since that's all about over-invalidating to
>> save time on individual unmaps - and relatively non-deterministic -
>> already.
>> 
>> So maybe we have a second set of iommu_flush_ops, or just a flag
>> somewhere to control the tlb_flush_walk functions internally, and the
>> choice can be made in the iommu_get_dma_strict() test, but also forced
>> on all the time by your init_context hook. What do you reckon?
>> 
> 
> Sounds good to me. Since you mentioned non-strict mode using it 
> generically,
> can't we just set tlb_flush_all() in io_pgtable_tlb_flush_walk() like 
> below
> based on quirk so that we don't need to add any check in 
> iommu_get_dma_strict()
> and just force the new flush_ops in init_context hook?
> 
> if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
>         iop->cfg.tlb->tlb_flush_all(iop->cookie);
>         return;
> }
> 

Instead of flush_ops in init_context hook, perhaps a io_pgtable quirk 
since this
is related to tlb, probably a bad name but IO_PGTABLE_QUIRK_TLB_INV 
which will be
set in init_context impl hook and the prev condition in 
io_pgtable_tlb_flush_walk()
becomes something like below. Seems very minimal and neat instead of 
poking into
tlb_flush_walk functions or touching dma strict with some flag?

if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT ||
     iop->cfg.quirks & IO_PGTABLE_QUIRK_TLB_INV) {
         iop->cfg.tlb->tlb_flush_all(iop->cookie);
         return;
}

Thanks,
Sai

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a 
member
of Code Aurora Forum, hosted by The Linux Foundation