From: Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>
To: joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org,
hch-jcswGhMUV9g@public.gmane.org
Cc: guohanjun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org,
catalin.marinas-5wv7dgnIgG8@public.gmane.org,
will.deacon-5wv7dgnIgG8@public.gmane.org,
linuxarm-hv44wF8Li93QT0dZR+AlfA@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
Subject: [PATCH v2 0/3] iommu: Avoid DMA ops domain refcount contention
Date: Wed, 12 Sep 2018 16:24:11 +0100 [thread overview]
Message-ID: <cover.1536764440.git.robin.murphy@arm.com> (raw)
John raised the issue[1] that we have some unnecessary refcount contention
in the DMA ops path which shows scalability problems now that we have more
real high-performance hardware using iommu-dma. The x86 IOMMU drivers are
sidestepping this by stashing domain references in archdata, but since
that's not very nice for architecture-agnostic code, I think it's time to
look at a generic API-level solution.
These are a couple of quick patches based on the idea I had back when
first implementing iommu-dma, but didn't have any way to justify at the
time. However, the reports of 10-25% better networking performance on v1
suggest that it's very worthwhile (and far more significant than I ever
would have guessed).
As far as merging goes, I don't mind at all whether this goes via IOMMU,
or via dma-mapping provided Joerg's happy to ack it.
Robin.
[1] https://lists.linuxfoundation.org/pipermail/iommu/2018-August/029303.html
Robin Murphy (3):
iommu: Add fast hook for getting DMA domains
iommu/dma: Use fast DMA domain lookup
arm64/dma-mapping: Mildly optimise non-coherent IOMMU ops
arch/arm64/mm/dma-mapping.c | 10 +++++-----
drivers/iommu/dma-iommu.c | 23 ++++++++++++-----------
drivers/iommu/iommu.c | 9 +++++++++
include/linux/iommu.h | 1 +
4 files changed, 27 insertions(+), 16 deletions(-)
--
2.19.0.dirty
WARNING: multiple messages have this Message-ID (diff)
From: robin.murphy@arm.com (Robin Murphy)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 0/3] iommu: Avoid DMA ops domain refcount contention
Date: Wed, 12 Sep 2018 16:24:11 +0100 [thread overview]
Message-ID: <cover.1536764440.git.robin.murphy@arm.com> (raw)
John raised the issue[1] that we have some unnecessary refcount contention
in the DMA ops path which shows scalability problems now that we have more
real high-performance hardware using iommu-dma. The x86 IOMMU drivers are
sidestepping this by stashing domain references in archdata, but since
that's not very nice for architecture-agnostic code, I think it's time to
look at a generic API-level solution.
These are a couple of quick patches based on the idea I had back when
first implementing iommu-dma, but didn't have any way to justify at the
time. However, the reports of 10-25% better networking performance on v1
suggest that it's very worthwhile (and far more significant than I ever
would have guessed).
As far as merging goes, I don't mind at all whether this goes via IOMMU,
or via dma-mapping provided Joerg's happy to ack it.
Robin.
[1] https://lists.linuxfoundation.org/pipermail/iommu/2018-August/029303.html
Robin Murphy (3):
iommu: Add fast hook for getting DMA domains
iommu/dma: Use fast DMA domain lookup
arm64/dma-mapping: Mildly optimise non-coherent IOMMU ops
arch/arm64/mm/dma-mapping.c | 10 +++++-----
drivers/iommu/dma-iommu.c | 23 ++++++++++++-----------
drivers/iommu/iommu.c | 9 +++++++++
include/linux/iommu.h | 1 +
4 files changed, 27 insertions(+), 16 deletions(-)
--
2.19.0.dirty
next reply other threads:[~2018-09-12 15:24 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-12 15:24 Robin Murphy [this message]
2018-09-12 15:24 ` [PATCH v2 0/3] iommu: Avoid DMA ops domain refcount contention Robin Murphy
[not found] ` <cover.1536764440.git.robin.murphy-5wv7dgnIgG8@public.gmane.org>
2018-09-12 15:24 ` [PATCH v2 1/3] iommu: Add fast hook for getting DMA domains Robin Murphy
2018-09-12 15:24 ` Robin Murphy
2018-09-12 15:24 ` [PATCH v2 2/3] iommu/dma: Use fast DMA domain lookup Robin Murphy
2018-09-12 15:24 ` Robin Murphy
[not found] ` <e42771992a73620f23128c0479b2ae91b3e177bf.1536764440.git.robin.murphy-5wv7dgnIgG8@public.gmane.org>
2018-09-28 13:26 ` Marek Szyprowski
2018-09-28 13:26 ` Marek Szyprowski
[not found] ` <20180928132605eucas1p1d39fedc3be3e4e2c16035c01a40cfab6~Ykz2Rax6e0538205382eucas1p17-MHMrYXj8g+pqW5MlFJXMulaTQe2KTcn/@public.gmane.org>
2018-09-28 13:52 ` Robin Murphy
2018-09-28 13:52 ` Robin Murphy
[not found] ` <78a5b373-d569-4461-e258-3104286ba322-5wv7dgnIgG8@public.gmane.org>
2018-09-28 14:21 ` Marek Szyprowski
2018-09-28 14:21 ` Marek Szyprowski
[not found] ` <20180928142148eucas1p17d6ecbd5c98b3fe1bf008dbcf0626c76~YlkfonoPN1120711207eucas1p1u-MHMrYXj8g+pqW5MlFJXMulaTQe2KTcn/@public.gmane.org>
2018-09-28 15:31 ` Robin Murphy
2018-09-28 15:31 ` Robin Murphy
[not found] ` <a9eb4b79-1fb8-eec7-0566-966f84022d7b-5wv7dgnIgG8@public.gmane.org>
2018-09-28 15:33 ` Christoph Hellwig
2018-09-28 15:33 ` Christoph Hellwig
[not found] ` <20180928153334.GA9462-jcswGhMUV9g@public.gmane.org>
2018-09-28 15:46 ` Robin Murphy
2018-09-28 15:46 ` Robin Murphy
2018-09-28 16:18 ` Marek Szyprowski
2018-09-28 16:18 ` Marek Szyprowski
2018-10-01 10:55 ` Inki Dae
2018-10-01 10:55 ` Inki Dae
2018-09-28 16:09 ` [PATCH] drm/exynos: Use selected dma_dev default iommu domain instead of a fake one Marek Szyprowski
2018-09-28 16:09 ` Marek Szyprowski
2018-09-28 16:13 ` Robin Murphy
2018-09-28 16:13 ` Robin Murphy
2018-09-12 15:24 ` [PATCH v2 3/3] arm64/dma-mapping: Mildly optimise non-coherent IOMMU ops Robin Murphy
2018-09-12 15:24 ` Robin Murphy
2018-09-14 12:48 ` [PATCH v2 0/3] iommu: Avoid DMA ops domain refcount contention Will Deacon
2018-09-14 12:48 ` Will Deacon
[not found] ` <20180914124858.GA4010-5wv7dgnIgG8@public.gmane.org>
2018-09-17 11:20 ` John Garry
2018-09-17 11:20 ` John Garry
[not found] ` <dbb9e48f-e31b-b8a1-0287-378c35e9fdb9-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2018-09-20 12:51 ` John Garry
2018-09-20 12:51 ` John Garry
2018-09-17 13:33 ` Christoph Hellwig
2018-09-17 13:33 ` Christoph Hellwig
[not found] ` <20180917133359.GA972-jcswGhMUV9g@public.gmane.org>
2018-09-18 13:28 ` Tom Murphy
2018-09-18 13:28 ` Tom Murphy
2018-09-25 8:24 ` Joerg Roedel
2018-09-25 8:24 ` Joerg Roedel
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=cover.1536764440.git.robin.murphy@arm.com \
--to=robin.murphy-5wv7dgnigg8@public.gmane.org \
--cc=catalin.marinas-5wv7dgnIgG8@public.gmane.org \
--cc=guohanjun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
--cc=hch-jcswGhMUV9g@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org \
--cc=linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linuxarm-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
--cc=will.deacon-5wv7dgnIgG8@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.