Date: Fri, 26 Jan 2024 19:13:05 +0000
From: Robin Murphy <robin.murphy@....com>
To: Petr Tesařík <petr@...arici.cz>
Cc: Alexander Lobakin <aleksander.lobakin@...el.com>,
 "David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
 Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
 Christoph Hellwig <hch@....de>, Marek Szyprowski <m.szyprowski@...sung.com>,
 Joerg Roedel <joro@...tes.org>, Will Deacon <will@...nel.org>,
 Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
 "Rafael J. Wysocki" <rafael@...nel.org>,
 Magnus Karlsson <magnus.karlsson@...el.com>,
 Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
 Alexander Duyck <alexanderduyck@...com>, bpf@...r.kernel.org,
 netdev@...r.kernel.org, iommu@...ts.linux.dev, linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next 2/7] dma: avoid expensive redundant calls for
 sync operations

On 26/01/2024 6:48 pm, Petr Tesařík wrote:
> On Fri, 26 Jan 2024 17:21:24 +0000
> Robin Murphy <robin.murphy@....com> wrote:
> 
>> On 26/01/2024 4:45 pm, Alexander Lobakin wrote:
>>> From: Robin Murphy <robin.murphy@....com>
>>> Date: Fri, 26 Jan 2024 15:48:54 +0000
>>>    
>>>> On 26/01/2024 1:54 pm, Alexander Lobakin wrote:
>>>>> From: Eric Dumazet <edumazet@...gle.com>
>>>>>
>>>>> Quite often, NIC devices do not need dma_sync operations on x86_64
>>>>> at least.
>>>>> Indeed, when dev_is_dma_coherent(dev) is true and
>>>>> dev_use_swiotlb(dev) is false, iommu_dma_sync_single_for_cpu()
>>>>> and friends do nothing.
>>>>>
>>>>> However, indirectly calling them when CONFIG_RETPOLINE=y consumes about
>>>>> 10% of cycles on a cpu receiving packets from softirq at ~100Gbit rate.
>>>>> Even if/when CONFIG_RETPOLINE is not set, there is a cost of about 3%.
>>>>>
>>>>> Add dev->skip_dma_sync boolean which is set during the device
>>>>> initialization depending on the setup: dev_is_dma_coherent() for direct
>>>>> DMA, !(sync_single_for_device || sync_single_for_cpu) or positive result
>>>>> from the new callback, dma_map_ops::can_skip_sync for non-NULL DMA ops.
>>>>> Then later, if/when swiotlb is used for the first time, the flag
>>>>> is turned off, from swiotlb_tbl_map_single().
>>>>
>>>> I think you could probably just promote the dma_uses_io_tlb flag from
>>>> SWIOTLB_DYNAMIC to a general SWIOTLB thing to serve this purpose now.
>>>
>>> Nice catch!
>>>    
>>>>
>>>> Similarly I don't think a new op is necessary now that we have
>>>> dma_map_ops.flags. A simple static flag to indicate that sync may be> skipped under the same conditions as implied for dma-direct - i.e.
>>>> dev_is_dma_coherent(dev) && !dev->dma_use_io_tlb - seems like it ought
>>>> to suffice.
>>>
>>> In my initial implementation, I used a new dma_map_ops flag, but then I
>>> realized different DMA ops may require or not require syncing under
>>> different conditions, not only dev_is_dma_coherent().
>>> Or am I wrong and they would always be the same?
>>
>> I think it's safe to assume that, as with P2P support, this will only
>> matter for dma-direct and iommu-dma for the foreseeable future, and
>> those do currently share the same conditions as above. Thus we may as
>> well keep things simple for now, and if anything ever does have cause to
>> change, it can be the future's problem to keep this mechanism working as
>> intended.
> 
> Can we have a comment that states this assumption along with the flag?
> Because when it breaks, it will keep someone cursing for days why DMA
> sometimes fails on their device before they find out it's not synced.
> And then wondering why the code makes such silly assumptions...

Indeed, apologies if it wasn't totally clear, but I really was implying 
a literal "may skip sync if coherent and not using SWIOTLB (which 
matches dma-direct)" flag, documented as such, and not trying to dress 
it up as anything more generic. I just can't suggest a suitably concise 
name for that of the top of my head... :)

Thanks,
Robin.

Powered by blists - more mailing lists