From: Robin Murphy <robin.murphy@arm.com>
To: Andi Kleen <ak@linux.intel.com>, Christoph Hellwig <hch@infradead.org>
Cc: parri.andrea@gmail.com, thomas.lendacky@amd.com,
wei.liu@kernel.org, Tianyu Lan <Tianyu.Lan@microsoft.com>,
konrad.wilk@oracle.com, linux-hyperv@vger.kernel.org,
Tianyu Lan <ltykernel@gmail.com>,
linux-kernel@vger.kernel.org, michael.h.kelley@microsoft.com,
iommu@lists.linux-foundation.org, andi.kleen@intel.com,
brijesh.singh@amd.com, vkuznets@redhat.com, kys@microsoft.com,
kirill.shutemov@intel.com, hch@lst.de
Subject: Re: [RFC PATCH 1/2] swiotlb: Split up single swiotlb lock
Date: Thu, 28 Apr 2022 17:59:11 +0100 [thread overview]
Message-ID: <3686314d-4226-b360-a72d-267af52c8918@arm.com> (raw)
In-Reply-To: <b3059196-a28b-a509-fc0e-75d2dbebdbae@linux.intel.com>
On 2022-04-28 17:02, Andi Kleen wrote:
>
> On 4/28/2022 8:07 AM, Robin Murphy wrote:
>> On 2022-04-28 15:55, Andi Kleen wrote:
>>>
>>> On 4/28/2022 7:45 AM, Christoph Hellwig wrote:
>>>> On Thu, Apr 28, 2022 at 03:44:36PM +0100, Robin Murphy wrote:
>>>>> Rather than introduce this extra level of allocator complexity, how
>>>>> about
>>>>> just dividing up the initial SWIOTLB allocation into multiple
>>>>> io_tlb_mem
>>>>> instances?
>>>> Yeah. We're almost done removing all knowledge of swiotlb from
>>>> drivers,
>>>> so the very last thing I want is an interface that allows a driver to
>>>> allocate a per-device buffer.
>>>
>>> At least for TDX need parallelism with a single device for performance.
>>>
>>> So if you split up the io tlb mems for a device then you would need a
>>> new mechanism to load balance the requests for single device over
>>> those. I doubt it would be any simpler.
>>
>> Eh, I think it would be, since the round-robin retry loop can then
>> just sit around the existing io_tlb_mem-based allocator, vs. the churn
>> of inserting it in the middle, plus it's then really easy to
>> statically distribute different starting points across different
>> devices via dev->dma_io_tlb_mem if we wanted to.
>>
>> Admittedly the overall patch probably ends up about the same size,
>> since it likely pushes a bit more complexity into swiotlb_init to
>> compensate, but that's still a trade-off I like.
>
> Unless you completely break the external API this will require a new
> mechanism to search a list of io_tlb_mems for the right area to free into.
>
> If the memory area not contiguous (like in the original patch) this will
> be a O(n) operation on the number of io_tlb_mems, so it would get more
> and more expensive on larger systems. Or you merge them all together (so
> that the simple address arithmetic to look up the area works again),
> which will require even more changes in the setup. Or you add hashing or
> similar which will be even more complicated.
>
> In the end doing it with a single io_tlb_mem is significantly simpler
> and also more natural.
Sorry if "dividing up the initial SWIOTLB allocation" somehow sounded
like "making multiple separate SWIOTLB allocations all over the place"?
I don't see there being any *functional* difference in whether a slice
of the overall SWIOTLB memory is represented by
"io_tlb_default_mem->areas[i]->blah" or "io_tlb_default_mem[i]->blah",
I'm simply advocating for not churning the already-complex allocator
internals by pushing the new complexity out to the margins instead.
Thanks,
Robin.
next prev parent reply other threads:[~2022-04-28 16:59 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-28 14:14 [RFC PATCH 0/2] swiotlb: Introduce swiotlb device allocation function Tianyu Lan
2022-04-28 14:14 ` [RFC PATCH 1/2] swiotlb: Split up single swiotlb lock Tianyu Lan
2022-04-28 14:44 ` Robin Murphy
2022-04-28 14:45 ` Christoph Hellwig
2022-04-28 14:55 ` Andi Kleen
2022-04-28 15:05 ` Christoph Hellwig
2022-04-28 15:16 ` Andi Kleen
2022-04-28 15:07 ` Robin Murphy
2022-04-28 16:02 ` Andi Kleen
2022-04-28 16:59 ` Robin Murphy [this message]
2022-04-28 14:56 ` Robin Murphy
2022-04-28 15:54 ` Tianyu Lan
2022-04-29 14:21 ` [RFC PATCH] swiotlb: Add Child IO TLB mem support Tianyu Lan
2022-04-29 14:25 ` Tianyu Lan
2022-04-28 14:14 ` [RFC PATCH 2/2] Swiotlb: Add device bounce buffer allocation interface Tianyu Lan
2022-04-28 15:50 ` Tianyu Lan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3686314d-4226-b360-a72d-267af52c8918@arm.com \
--to=robin.murphy@arm.com \
--cc=Tianyu.Lan@microsoft.com \
--cc=ak@linux.intel.com \
--cc=andi.kleen@intel.com \
--cc=brijesh.singh@amd.com \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=iommu@lists.linux-foundation.org \
--cc=kirill.shutemov@intel.com \
--cc=konrad.wilk@oracle.com \
--cc=kys@microsoft.com \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ltykernel@gmail.com \
--cc=michael.h.kelley@microsoft.com \
--cc=parri.andrea@gmail.com \
--cc=thomas.lendacky@amd.com \
--cc=vkuznets@redhat.com \
--cc=wei.liu@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®