From: Wolfram Sang <wsa@the-dreams.de>
To: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Cc: joro@8bytes.org, axboe@kernel.dk, ulf.hansson@linaro.org,
wsa+renesas@sang-engineering.com, hch@lst.de,
iommu@lists.linux-foundation.org, linux-block@vger.kernel.org,
linux-mmc@vger.kernel.org, linux-renesas-soc@vger.kernel.org
Subject: Re: [RFC PATCH v6 0/5] treewide: improve R-Car SDHI performance
Date: Thu, 13 Jun 2019 21:36:28 +0200 [thread overview]
Message-ID: <20190613193628.GA6863@kunai> (raw)
In-Reply-To: <1560421215-10750-1-git-send-email-yoshihiro.shimoda.uh@renesas.com>
[-- Attachment #1: Type: text/plain, Size: 1596 bytes --]
On Thu, Jun 13, 2019 at 07:20:10PM +0900, Yoshihiro Shimoda wrote:
> This patch series is based on iommu.git / next branch.
>
> Since SDHI host internal DMAC of the R-Car Gen3 cannot handle two or
> more segments, the performance rate (especially, eMMC HS400 reading)
> is not good. However, if IOMMU is enabled on the DMAC, since IOMMU will
> map multiple scatter gather buffers as one contignous iova, the DMAC can
> handle the iova as well and then the performance rate is possible to
> improve. In fact, I have measured the performance by using bonnie++,
> "Sequential Input - block" rate was improved on r8a7795.
>
> To achieve this, this patch series modifies IOMMU and Block subsystem
> at first. Since I'd like to get any feedback from each subsystem whether
> this way is acceptable for upstream, I submit it to treewide with RFC.
>
> Changes from v5:
> - Almost all patches are new code.
> - [4/5 for MMC] This is a refactor patch so that I don't add any
> {Tested,Reviewed}-by tags.
> - [5/5 for MMC] Modify MMC subsystem to use bigger segments instead of
> the renesas_sdhi driver.
> - [5/5 for MMC] Use BLK_MAX_SEGMENTS (128) instead of local value
> SDHI_MAX_SEGS_IN_IOMMU (512). Even if we use BLK_MAX_SEGMENTS,
> the performance is still good.
Thanks for your hard work, Shimoda-san!
I may not be the biggest DMA, IOMMU, and block layer expert, but I
really like how this simplifies the SDHI driver and enhances the MMC
core. So, I'll add my two cents to the patches although I can't really
comment on the main functionality.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: Wolfram Sang <wsa-z923LK4zBo2bacvFa/9K2g@public.gmane.org>
To: Yoshihiro Shimoda
<yoshihiro.shimoda.uh-zM6kxYcvzFBBDgjK7y7TUQ@public.gmane.org>
Cc: axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org,
linux-renesas-soc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org,
linux-mmc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
wsa+renesas-jBu1N2QxHDJrcw3mvpCnnVaTQe2KTcn/@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
hch-jcswGhMUV9g@public.gmane.org
Subject: Re: [RFC PATCH v6 0/5] treewide: improve R-Car SDHI performance
Date: Thu, 13 Jun 2019 21:36:28 +0200 [thread overview]
Message-ID: <20190613193628.GA6863@kunai> (raw)
In-Reply-To: <1560421215-10750-1-git-send-email-yoshihiro.shimoda.uh-zM6kxYcvzFBBDgjK7y7TUQ@public.gmane.org>
[-- Attachment #1.1: Type: text/plain, Size: 1596 bytes --]
On Thu, Jun 13, 2019 at 07:20:10PM +0900, Yoshihiro Shimoda wrote:
> This patch series is based on iommu.git / next branch.
>
> Since SDHI host internal DMAC of the R-Car Gen3 cannot handle two or
> more segments, the performance rate (especially, eMMC HS400 reading)
> is not good. However, if IOMMU is enabled on the DMAC, since IOMMU will
> map multiple scatter gather buffers as one contignous iova, the DMAC can
> handle the iova as well and then the performance rate is possible to
> improve. In fact, I have measured the performance by using bonnie++,
> "Sequential Input - block" rate was improved on r8a7795.
>
> To achieve this, this patch series modifies IOMMU and Block subsystem
> at first. Since I'd like to get any feedback from each subsystem whether
> this way is acceptable for upstream, I submit it to treewide with RFC.
>
> Changes from v5:
> - Almost all patches are new code.
> - [4/5 for MMC] This is a refactor patch so that I don't add any
> {Tested,Reviewed}-by tags.
> - [5/5 for MMC] Modify MMC subsystem to use bigger segments instead of
> the renesas_sdhi driver.
> - [5/5 for MMC] Use BLK_MAX_SEGMENTS (128) instead of local value
> SDHI_MAX_SEGS_IN_IOMMU (512). Even if we use BLK_MAX_SEGMENTS,
> the performance is still good.
Thanks for your hard work, Shimoda-san!
I may not be the biggest DMA, IOMMU, and block layer expert, but I
really like how this simplifies the SDHI driver and enhances the MMC
core. So, I'll add my two cents to the patches although I can't really
comment on the main functionality.
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
[-- Attachment #2: Type: text/plain, Size: 0 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: Wolfram Sang <wsa@the-dreams.de>
To: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Cc: axboe@kernel.dk, linux-renesas-soc@vger.kernel.org,
ulf.hansson@linaro.org, linux-mmc@vger.kernel.org,
linux-block@vger.kernel.org, wsa+renesas@sang-engineering.com,
iommu@lists.linux-foundation.org, hch@lst.de
Subject: Re: [RFC PATCH v6 0/5] treewide: improve R-Car SDHI performance
Date: Thu, 13 Jun 2019 21:36:28 +0200 [thread overview]
Message-ID: <20190613193628.GA6863@kunai> (raw)
In-Reply-To: <1560421215-10750-1-git-send-email-yoshihiro.shimoda.uh@renesas.com>
[-- Attachment #1.1: Type: text/plain, Size: 1596 bytes --]
On Thu, Jun 13, 2019 at 07:20:10PM +0900, Yoshihiro Shimoda wrote:
> This patch series is based on iommu.git / next branch.
>
> Since SDHI host internal DMAC of the R-Car Gen3 cannot handle two or
> more segments, the performance rate (especially, eMMC HS400 reading)
> is not good. However, if IOMMU is enabled on the DMAC, since IOMMU will
> map multiple scatter gather buffers as one contignous iova, the DMAC can
> handle the iova as well and then the performance rate is possible to
> improve. In fact, I have measured the performance by using bonnie++,
> "Sequential Input - block" rate was improved on r8a7795.
>
> To achieve this, this patch series modifies IOMMU and Block subsystem
> at first. Since I'd like to get any feedback from each subsystem whether
> this way is acceptable for upstream, I submit it to treewide with RFC.
>
> Changes from v5:
> - Almost all patches are new code.
> - [4/5 for MMC] This is a refactor patch so that I don't add any
> {Tested,Reviewed}-by tags.
> - [5/5 for MMC] Modify MMC subsystem to use bigger segments instead of
> the renesas_sdhi driver.
> - [5/5 for MMC] Use BLK_MAX_SEGMENTS (128) instead of local value
> SDHI_MAX_SEGS_IN_IOMMU (512). Even if we use BLK_MAX_SEGMENTS,
> the performance is still good.
Thanks for your hard work, Shimoda-san!
I may not be the biggest DMA, IOMMU, and block layer expert, but I
really like how this simplifies the SDHI driver and enhances the MMC
core. So, I'll add my two cents to the patches although I can't really
comment on the main functionality.
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
[-- Attachment #2: Type: text/plain, Size: 156 bytes --]
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2019-06-13 19:36 UTC|newest]
Thread overview: 93+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-13 10:20 [RFC PATCH v6 0/5] treewide: improve R-Car SDHI performance Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` [RFC PATCH v6 1/5] iommu: add an exported function to get minimum page size for a domain Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 19:37 ` Wolfram Sang
2019-06-13 19:37 ` Wolfram Sang
2019-06-13 19:37 ` Wolfram Sang
2019-06-14 7:16 ` Christoph Hellwig
2019-06-14 7:16 ` Christoph Hellwig
2019-06-14 7:16 ` Christoph Hellwig
2019-06-17 5:08 ` Yoshihiro Shimoda
2019-06-17 5:08 ` Yoshihiro Shimoda
2019-06-17 5:08 ` Yoshihiro Shimoda
2019-06-14 9:41 ` Robin Murphy
2019-06-14 9:41 ` Robin Murphy
2019-06-14 9:41 ` Robin Murphy
2019-06-17 5:23 ` Yoshihiro Shimoda
2019-06-17 5:23 ` Yoshihiro Shimoda
2019-06-17 5:23 ` Yoshihiro Shimoda
2019-06-13 10:20 ` [RFC PATCH v6 2/5] block: sort headers on blk-setting.c Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 19:40 ` Wolfram Sang
2019-06-13 19:40 ` Wolfram Sang
2019-06-13 19:40 ` Wolfram Sang
2019-06-13 10:20 ` [RFC PATCH v6 3/5] block: add a helper function to merge the segments by an IOMMU Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-14 7:22 ` Christoph Hellwig
2019-06-14 7:22 ` Christoph Hellwig
2019-06-14 7:22 ` Christoph Hellwig
2019-06-14 9:54 ` Robin Murphy
2019-06-14 9:54 ` Robin Murphy
2019-06-14 9:54 ` Robin Murphy
2019-06-17 6:29 ` Yoshihiro Shimoda
2019-06-17 6:29 ` Yoshihiro Shimoda
2019-06-17 6:29 ` Yoshihiro Shimoda
2019-06-13 10:20 ` [RFC PATCH v6 4/5] mmc: tmio: Use dma_max_mapping_size() instead of a workaround Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 19:45 ` Wolfram Sang
2019-06-13 19:45 ` Wolfram Sang
2019-06-13 19:45 ` Wolfram Sang
2019-06-17 4:25 ` Yoshihiro Shimoda
2019-06-17 4:25 ` Yoshihiro Shimoda
2019-06-17 4:25 ` Yoshihiro Shimoda
2019-06-13 20:35 ` Geert Uytterhoeven
2019-06-13 20:35 ` Geert Uytterhoeven
2019-06-13 20:35 ` Geert Uytterhoeven
2019-06-14 7:18 ` Christoph Hellwig
2019-06-14 7:18 ` Christoph Hellwig
2019-06-14 7:18 ` Christoph Hellwig
2019-06-14 7:27 ` Geert Uytterhoeven
2019-06-14 7:27 ` Geert Uytterhoeven
2019-06-14 7:27 ` Geert Uytterhoeven
2019-06-17 4:54 ` Yoshihiro Shimoda
2019-06-17 4:54 ` Yoshihiro Shimoda
2019-06-17 4:54 ` Yoshihiro Shimoda
2019-06-17 6:23 ` Geert Uytterhoeven
2019-06-17 6:23 ` Geert Uytterhoeven
2019-06-17 6:23 ` Geert Uytterhoeven
2019-06-17 6:54 ` Yoshihiro Shimoda
2019-06-17 6:54 ` Yoshihiro Shimoda
2019-06-17 6:54 ` Yoshihiro Shimoda
2019-06-13 10:20 ` [RFC PATCH v6 5/5] mmc: queue: Use bigger segments if IOMMU can merge the segments Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 10:20 ` Yoshihiro Shimoda
2019-06-13 19:58 ` Wolfram Sang
2019-06-13 19:58 ` Wolfram Sang
2019-06-13 19:58 ` Wolfram Sang
2019-06-17 6:38 ` Yoshihiro Shimoda
2019-06-17 6:38 ` Yoshihiro Shimoda
2019-06-17 6:38 ` Yoshihiro Shimoda
2019-06-14 7:24 ` Christoph Hellwig
2019-06-14 7:24 ` Christoph Hellwig
2019-06-14 7:24 ` Christoph Hellwig
2019-06-14 10:42 ` Wolfram Sang
2019-06-14 10:42 ` Wolfram Sang
2019-06-14 10:42 ` Wolfram Sang
2019-06-17 6:46 ` Yoshihiro Shimoda
2019-06-17 6:46 ` Yoshihiro Shimoda
2019-06-17 6:46 ` Yoshihiro Shimoda
2019-06-17 6:53 ` Christoph Hellwig
2019-06-17 6:53 ` Christoph Hellwig
2019-06-17 6:53 ` Christoph Hellwig
2019-06-17 7:02 ` Yoshihiro Shimoda
2019-06-17 7:02 ` Yoshihiro Shimoda
2019-06-17 7:02 ` Yoshihiro Shimoda
2019-06-13 19:36 ` Wolfram Sang [this message]
2019-06-13 19:36 ` [RFC PATCH v6 0/5] treewide: improve R-Car SDHI performance Wolfram Sang
2019-06-13 19:36 ` Wolfram Sang
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=20190613193628.GA6863@kunai \
--to=wsa@the-dreams.de \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=iommu@lists.linux-foundation.org \
--cc=joro@8bytes.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-mmc@vger.kernel.org \
--cc=linux-renesas-soc@vger.kernel.org \
--cc=ulf.hansson@linaro.org \
--cc=wsa+renesas@sang-engineering.com \
--cc=yoshihiro.shimoda.uh@renesas.com \
/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.