From: Rob Herring <robh@kernel.org>
To: Georgi Djakov <quic_c_gdjako@quicinc.com>
Cc: krzysztof.kozlowski+dt@linaro.org, devicetree@vger.kernel.org,
joro@8bytes.org, will@kernel.org, robin.murphy@arm.com,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
djakov@kernel.org
Subject: Re: [RFC v2 1/2] dt-bindings: iommu: Document iova-best-fit property for IOMMU masters
Date: Tue, 13 Dec 2022 10:35:06 -0600 [thread overview]
Message-ID: <20221213163506.GA2011062-robh@kernel.org> (raw)
In-Reply-To: <20221212215138.17897-1-quic_c_gdjako@quicinc.com>
On Mon, Dec 12, 2022 at 01:51:37PM -0800, Georgi Djakov wrote:
> Document the "iova-best-fit" device-tree property, which is used to
> describe that the iommu master is constrained on memory and the system
> must put more effort when allocating IOVAs to avoid holes/gaps in
> memory. This improves the memory utilization and helps with memory
> fragmentation issues in some cases, but it could take longer to allocate
> an IOVA compared with the default "first-fit" algorithm.
>
> Signed-off-by: Georgi Djakov <quic_c_gdjako@quicinc.com>
> ---
> Documentation/devicetree/bindings/iommu/iommu.txt | 4 ++++
> 1 file changed, 4 insertions(+)
No new properties in common .txt files. Schemas only.
However, this looks like kernel policy which doesn't belong in DT.
> diff --git a/Documentation/devicetree/bindings/iommu/iommu.txt b/Documentation/devicetree/bindings/iommu/iommu.txt
> index 26ba9e530f13..ca1b4813c5bf 100644
> --- a/Documentation/devicetree/bindings/iommu/iommu.txt
> +++ b/Documentation/devicetree/bindings/iommu/iommu.txt
> @@ -88,6 +88,10 @@ prevent any driver from properly setting up the translations.
>
> Optional properties:
> --------------------
> +- iova-best-fit: When present, the best-fit algorithm will be used, instead
> + of first-fit. This reduces memory fragmentation when allocating IOVAs in
> + some cases, but may also increase the time it takes to allocate an IOVA.
> +
> - pasid-num-bits: Some masters support multiple address spaces for DMA, by
> tagging DMA transactions with an address space identifier. By default,
> this is 0, which means that the device only has one address space.
>
prev parent reply other threads:[~2022-12-13 16:35 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-12 21:51 [RFC v2 1/2] dt-bindings: iommu: Document iova-best-fit property for IOMMU masters Georgi Djakov
2022-12-12 21:51 ` [RFC v2 2/2] iommu/iova: Add support for best-fit algorithm Georgi Djakov
2022-12-13 16:35 ` Rob Herring [this message]
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=20221213163506.GA2011062-robh@kernel.org \
--to=robh@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=djakov@kernel.org \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=krzysztof.kozlowski+dt@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=quic_c_gdjako@quicinc.com \
--cc=robin.murphy@arm.com \
--cc=will@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;
as well as URLs for NNTP newsgroup(s).