linux-kernel - Re: [PATCH V2 0/1] Optimise IOVA allocations for PCI devices

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]

Message-ID: <604a93b9-1af4-a961-6c78-cb755d0caa1e@caviumnetworks.com>
Date:   Thu, 12 Oct 2017 11:41:20 +0200
From:   Tomasz Nowicki <tnowicki@...iumnetworks.com>
To:     Tomasz Nowicki <tomasz.nowicki@...iumnetworks.com>,
        joro@...tes.org, robin.murphy@....com
Cc:     will.deacon@....com, Jayachandran.Nair@...ium.com,
        ard.biesheuvel@...aro.org, linux-kernel@...r.kernel.org,
        iommu@...ts.linux-foundation.org,
        linux-arm-kernel@...ts.infradead.org,
        Ganapatrao.Kulkarni@...ium.com
Subject: Re: [PATCH V2 0/1] Optimise IOVA allocations for PCI devices

Hi Joerg,

Can you please have a look and see if you are fine with this patch?

Thanks in advance,
Tomasz

On 20.09.2017 10:52, Tomasz Nowicki wrote:
> Here is my test setup where I have stareted performance measurements.
> 
>   ------------  PCIe  -------------   TX   -------------  PCIe  -----
> | ThunderX2  |------| Intel XL710 | ---> | Intel XL710 |------| X86 |
> | (128 cpus) |      |   40GbE     |      |    40GbE    |       -----
>   ------------        -------------        -------------
> 
> As the reference lets take v4.13 host, SMMUv3 off and 1-thread iperf
> taskset to one CPU. The performance results I got:
> 
> SMMU off -> 100%
> SMMU on -> 0,02%
> 
> I followed down the DMA mapping path and found out IOVA 32-bit space
> full so that kernel was flushing rcaches for all CPUs in (1).
> For 128 CPUs, this kills the performance. Furthermore, for my case, rcaches
> contained PFNs > 32-bit mostly so the second round of IOVA allocation failed
> as well. As the consequence IOVA had to be allocated outside of 32-bit (2)
> from scratch since all rcaches have been flushed in (1).
> 
>      if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
> (1)-->  iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
> 
>      if (!iova)
> (2)-->  iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
> 
> My fix simply introduces parameter for alloc_iova_fast() to decide whether
> rcache flush has to be done or not. All users follow mentioned scenario
> so they should let flush as the last chance to avoid time costly iteration
> over all CPUs.
> 
> This bring my iperf performance back to 100% with SMMU on.
> 
> My bad feelings regarding this solution is that machines with relatively
> small numbers of CPUs may get DAC addresses more frequently for PCI
> devices. Please let me know your thoughts.
> 
> Changelog:
> 
> v1 --> v2
> - add missing documentation
> - fix typo
> 
> Tomasz Nowicki (1):
>    iommu/iova: Make rcache flush optional on IOVA allocation failure
> 
>   drivers/iommu/amd_iommu.c   |  5 +++--
>   drivers/iommu/dma-iommu.c   |  6 ++++--
>   drivers/iommu/intel-iommu.c |  5 +++--
>   drivers/iommu/iova.c        | 11 ++++++-----
>   include/linux/iova.h        |  5 +++--
>   5 files changed, 19 insertions(+), 13 deletions(-)
>