From: Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
To: Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>
Cc: ard.biesheuvel-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org,
Jonathan.Cameron-hv44wF8Li93QT0dZR+AlfA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
ray.jui-dY08KVG/lbpWk0Htik3J/w@public.gmane.org,
thunder.leizhen-hv44wF8Li93QT0dZR+AlfA@public.gmane.org,
dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
Subject: Re: [PATCH v2 0/4] Optimise 64-bit IOVA allocations
Date: Wed, 26 Jul 2017 13:08:07 +0200 [thread overview]
Message-ID: <20170726110807.GN15833@8bytes.org> (raw)
In-Reply-To: <cover.1500636791.git.robin.murphy-5wv7dgnIgG8@public.gmane.org>
Hi Robin.
On Fri, Jul 21, 2017 at 12:41:57PM +0100, Robin Murphy wrote:
> Hi all,
>
> In the wake of the ARM SMMU optimisation efforts, it seems that certain
> workloads (e.g. storage I/O with large scatterlists) probably remain quite
> heavily influenced by IOVA allocation performance. Separately, Ard also
> reported massive performance drops for a graphical desktop on AMD Seattle
> when enabling SMMUs via IORT, which we traced to dma_32bit_pfn in the DMA
> ops domain getting initialised differently for ACPI vs. DT, and exposing
> the overhead of the rbtree slow path. Whilst we could go around trying to
> close up all the little gaps that lead to hitting the slowest case, it
> seems a much better idea to simply make said slowest case a lot less slow.
Do you have some numbers here? How big was the impact before these
patches and how is it with the patches?
Joerg
WARNING: multiple messages have this Message-ID (diff)
From: joro@8bytes.org (Joerg Roedel)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 0/4] Optimise 64-bit IOVA allocations
Date: Wed, 26 Jul 2017 13:08:07 +0200 [thread overview]
Message-ID: <20170726110807.GN15833@8bytes.org> (raw)
In-Reply-To: <cover.1500636791.git.robin.murphy@arm.com>
Hi Robin.
On Fri, Jul 21, 2017 at 12:41:57PM +0100, Robin Murphy wrote:
> Hi all,
>
> In the wake of the ARM SMMU optimisation efforts, it seems that certain
> workloads (e.g. storage I/O with large scatterlists) probably remain quite
> heavily influenced by IOVA allocation performance. Separately, Ard also
> reported massive performance drops for a graphical desktop on AMD Seattle
> when enabling SMMUs via IORT, which we traced to dma_32bit_pfn in the DMA
> ops domain getting initialised differently for ACPI vs. DT, and exposing
> the overhead of the rbtree slow path. Whilst we could go around trying to
> close up all the little gaps that lead to hitting the slowest case, it
> seems a much better idea to simply make said slowest case a lot less slow.
Do you have some numbers here? How big was the impact before these
patches and how is it with the patches?
Joerg
WARNING: multiple messages have this Message-ID (diff)
From: Joerg Roedel <joro@8bytes.org>
To: Robin Murphy <robin.murphy@arm.com>
Cc: iommu@lists.linux-foundation.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, dwmw2@infradead.org,
thunder.leizhen@huawei.com, lorenzo.pieralisi@arm.com,
ard.biesheuvel@linaro.org, Jonathan.Cameron@huawei.com,
nwatters@codeaurora.org, ray.jui@broadcom.com
Subject: Re: [PATCH v2 0/4] Optimise 64-bit IOVA allocations
Date: Wed, 26 Jul 2017 13:08:07 +0200 [thread overview]
Message-ID: <20170726110807.GN15833@8bytes.org> (raw)
In-Reply-To: <cover.1500636791.git.robin.murphy@arm.com>
Hi Robin.
On Fri, Jul 21, 2017 at 12:41:57PM +0100, Robin Murphy wrote:
> Hi all,
>
> In the wake of the ARM SMMU optimisation efforts, it seems that certain
> workloads (e.g. storage I/O with large scatterlists) probably remain quite
> heavily influenced by IOVA allocation performance. Separately, Ard also
> reported massive performance drops for a graphical desktop on AMD Seattle
> when enabling SMMUs via IORT, which we traced to dma_32bit_pfn in the DMA
> ops domain getting initialised differently for ACPI vs. DT, and exposing
> the overhead of the rbtree slow path. Whilst we could go around trying to
> close up all the little gaps that lead to hitting the slowest case, it
> seems a much better idea to simply make said slowest case a lot less slow.
Do you have some numbers here? How big was the impact before these
patches and how is it with the patches?
Joerg
next prev parent reply other threads:[~2017-07-26 11:08 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-21 11:41 [PATCH v2 0/4] Optimise 64-bit IOVA allocations Robin Murphy
2017-07-21 11:41 ` Robin Murphy
2017-07-21 11:42 ` [PATCH v2 4/4] iommu/iova: Make dma_32bit_pfn implicit Robin Murphy
2017-07-21 11:42 ` Robin Murphy
[not found] ` <cover.1500636791.git.robin.murphy-5wv7dgnIgG8@public.gmane.org>
2017-07-21 11:41 ` [PATCH v2 1/4] iommu/iova: Optimise rbtree searching Robin Murphy
2017-07-21 11:41 ` Robin Murphy
2017-07-21 11:41 ` Robin Murphy
2017-07-21 11:41 ` [PATCH v2 2/4] iommu/iova: Optimise the padding calculation Robin Murphy
2017-07-21 11:41 ` Robin Murphy
2017-07-21 11:41 ` Robin Murphy
2017-07-21 11:42 ` [PATCH v2 3/4] iommu/iova: Extend rbtree node caching Robin Murphy
2017-07-21 11:42 ` Robin Murphy
2017-07-21 11:42 ` Robin Murphy
2017-07-29 3:57 ` Nate Watterson
2017-07-29 3:57 ` Nate Watterson
[not found] ` <23972edc-e59e-3a43-59a9-d776e64af4d7-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-07-31 11:42 ` Robin Murphy
2017-07-31 11:42 ` Robin Murphy
2017-07-31 11:42 ` Robin Murphy
2017-08-03 19:41 ` Nate Watterson
2017-08-03 19:41 ` Nate Watterson
[not found] ` <a7eb678f-ff78-5c85-6fb0-cba1f82dc502-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
2017-08-31 9:46 ` Leizhen (ThunderTown)
2017-08-31 9:46 ` Leizhen (ThunderTown)
2017-08-31 9:46 ` Leizhen (ThunderTown)
[not found] ` <e5d4524e-bfe9-acf1-66c1-ea1d9d319855-5wv7dgnIgG8@public.gmane.org>
2017-09-19 9:42 ` Leizhen (ThunderTown)
2017-09-19 9:42 ` Leizhen (ThunderTown)
2017-09-19 9:42 ` Leizhen (ThunderTown)
[not found] ` <59C0E694.6080508-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-09-19 10:07 ` Robin Murphy
2017-09-19 10:07 ` Robin Murphy
2017-09-19 10:07 ` Robin Murphy
2017-07-26 11:08 ` Joerg Roedel [this message]
2017-07-26 11:08 ` [PATCH v2 0/4] Optimise 64-bit IOVA allocations Joerg Roedel
2017-07-26 11:08 ` Joerg Roedel
[not found] ` <20170726110807.GN15833-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-07-26 11:17 ` Leizhen (ThunderTown)
2017-07-26 11:17 ` Leizhen (ThunderTown)
2017-07-26 11:17 ` Leizhen (ThunderTown)
2017-08-08 12:03 ` Ganapatrao Kulkarni
2017-08-08 12:03 ` Ganapatrao Kulkarni
2017-08-09 1:42 ` Leizhen (ThunderTown)
2017-08-09 1:42 ` Leizhen (ThunderTown)
2017-08-09 1:42 ` Leizhen (ThunderTown)
[not found] ` <598A6877.4050307-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-08-09 3:24 ` Ganapatrao Kulkarni
2017-08-09 3:24 ` Ganapatrao Kulkarni
2017-08-09 3:24 ` Ganapatrao Kulkarni
2017-08-09 4:09 ` Leizhen (ThunderTown)
2017-08-09 4:09 ` Leizhen (ThunderTown)
2017-08-09 4:09 ` Leizhen (ThunderTown)
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=20170726110807.GN15833@8bytes.org \
--to=joro-zlv9swrftaidnm+yrofe0a@public.gmane.org \
--cc=Jonathan.Cameron-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
--cc=ard.biesheuvel-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org \
--cc=dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=ray.jui-dY08KVG/lbpWk0Htik3J/w@public.gmane.org \
--cc=robin.murphy-5wv7dgnIgG8@public.gmane.org \
--cc=thunder.leizhen-hv44wF8Li93QT0dZR+AlfA@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.