Linux SCSI subsystem development
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
	Jaegeuk Kim <jaegeuk@kernel.org>,
	Avri Altman <avri.altman@wdc.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Christoph Hellwig <hch@lst.de>, Ming Lei <ming.lei@redhat.com>
Subject: Re: [PATCH v3 0/9] Add support for segments smaller than one page
Date: Wed, 18 Jan 2023 20:43:10 -0800	[thread overview]
Message-ID: <0e120274-29d8-cb53-2190-d82eabf4c431@acm.org> (raw)
In-Reply-To: <52073ee8-72ab-f424-1738-c56bc8d5cd67@kernel.dk>

On 1/18/23 17:18, Jens Axboe wrote:
> On 1/18/23 3:54?PM, Bart Van Assche wrote:
>> Hi Jens,
>>
>> Several embedded storage controllers need support for DMA segments that are
>> smaller than the size of one virtual memory page. Hence this patch series.
>> Please consider this patch series for the next merge window.
> 
> Before any real reviews are done, I have to ask "why?". This is pretty
> hairy code in the middle of the fast path for some obscure controller.
> Why would anyone ship that with > 4k page sizes rather than ship it with
> a controller that is sane?

Hi Jens,

The new config variable CONFIG_BLK_SUB_PAGE_SEGMENTS has been introduced 
to make sure that the hot path is *not* affected if that config variable 
is disabled.

Regarding the question "why": the Google Android team would like to 
improve performance by switching from 4 KiB pages to 16 KiB pages. One 
of the widely used UFS controllers (Exynos) has a maximum segment size 
of 4 KiB. Hence this patch series.

This patch series is not only useful for phones but also for Tesla cars 
since Tesla cars use an Exynos UFS controller.

A contributor to the MMC driver told me that this patch series would 
allow to simplify the MMC driver significantly (I have not yet double 
checked this).

Bart.



      reply	other threads:[~2023-01-19  4:49 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-18 22:54 [PATCH v3 0/9] Add support for segments smaller than one page Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 1/9] block: Introduce QUEUE_FLAG_SUB_PAGE_SEGMENTS and CONFIG_BLK_SUB_PAGE_SEGMENTS Bart Van Assche
2023-01-18 23:02   ` Jens Axboe
2023-01-18 23:40     ` Bart Van Assche
2023-01-21  0:11     ` Bart Van Assche
2023-01-21  2:43       ` Jens Axboe
2023-01-23 19:58         ` Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 2/9] block: Support configuring limits below the page size Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 3/9] block: Support submitting passthrough requests with small segments Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 4/9] block: Add support for filesystem requests and " Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 5/9] block: Add support for small segments in blk_rq_map_user_iov() Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 6/9] scsi_debug: Support configuring the maximum segment size Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 7/9] null_blk: " Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 8/9] scsi: core: Set BLK_SUB_PAGE_SEGMENTS for small max_segment_size values Bart Van Assche
2023-01-19  5:38   ` Christoph Hellwig
2023-01-19 17:27     ` Bart Van Assche
2023-01-18 22:54 ` [PATCH v3 9/9] scsi: ufs: exynos: Select CONFIG_BLK_SUB_PAGE_SEGMENTS for lage page sizes Bart Van Assche
2023-01-28  3:55   ` Ming Lei
2023-01-29  1:09     ` Bart Van Assche
2023-01-19  1:18 ` [PATCH v3 0/9] Add support for segments smaller than one page Jens Axboe
2023-01-19  4:43   ` Bart Van Assche [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=0e120274-29d8-cb53-2190-d82eabf4c431@acm.org \
    --to=bvanassche@acm.org \
    --cc=adrian.hunter@intel.com \
    --cc=avri.altman@wdc.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=jaegeuk@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=ming.lei@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox