Linux Renesas SOC kernel development
 help / color / mirror / Atom feed
From: Richard Weinberger <richard@nod.at>
To: Christian Loehle <CLoehle@hyperstone.com>
Cc: Biju Das <biju.das.jz@bp.renesas.com>,
	linux-mmc <linux-mmc@vger.kernel.org>,
	linux-renesas-soc <linux-renesas-soc@vger.kernel.org>,
	wsa+renesas <wsa+renesas@sang-engineering.com>,
	ulf hansson <ulf.hansson@linaro.org>
Subject: Re: Poor write performance to boot area using rcar-gen3-sdhi
Date: Thu, 20 Apr 2023 17:18:00 +0200 (CEST)	[thread overview]
Message-ID: <1273293952.226564.1682003880265.JavaMail.zimbra@nod.at> (raw)
In-Reply-To: <1186364892.150923.1681819136247.JavaMail.zimbra@nod.at>

----- Ursprüngliche Mail -----
> ----- Ursprüngliche Mail -----
>> Von: "Christian Loehle" <CLoehle@hyperstone.com>
>>> Can it be that rcar-gen3-sdhi changes some timings after switching?
>>> Either in software or on hardware.
>> 
>> Neither should be aware of the notion of a boot or user area partition.
>> Anything below mmc/core isn't, if we exclude the boot operation which is read
>> only, so not applicable to your problem.
>> So also a
>> while true; do dd if=/dev/zero of=/dev/mmcblkXboot0 bs=128K status=progress;
>> done
>> gives you like ~50KB/s consistently?
> 
> Exactly.
> 
> On the other hand, the very same command on /dev/mmcblk1p13 gives me always
> between
> 17 and 20 MB/s.

I did further tracing and on Linux I see clearly that tmio_mmc_irq() always much
later when writing to the boot area.

Another idea, since u-boot does not really support interrupts it polls various
status bits to detect completion of commands and data transfers.
Crazy idea: Maybe u-boot writes are faster than they should because it polls not always the
right bits?

...or Linux is too conservative and it matters for the boot area.

Thanks,
//richard

  reply	other threads:[~2023-04-20 15:18 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-17 20:08 Poor write performance to boot area using rcar-gen3-sdhi Richard Weinberger
2023-04-18  6:09 ` Biju Das
2023-04-18  6:16   ` Richard Weinberger
2023-04-18  7:48     ` Christian Loehle
2023-04-18  8:11       ` Richard Weinberger
2023-04-18  8:36         ` Christian Loehle
2023-04-18 11:58           ` Richard Weinberger
2023-04-20 15:18             ` Richard Weinberger [this message]
2023-04-21 16:23               ` Christian Loehle
2023-05-09 11:28                 ` Richard Weinberger
2023-05-11  9:46                   ` Christian Loehle
2023-05-11 10:35                     ` Richard Weinberger
2023-04-18  8:12       ` Biju Das

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=1273293952.226564.1682003880265.JavaMail.zimbra@nod.at \
    --to=richard@nod.at \
    --cc=CLoehle@hyperstone.com \
    --cc=biju.das.jz@bp.renesas.com \
    --cc=linux-mmc@vger.kernel.org \
    --cc=linux-renesas-soc@vger.kernel.org \
    --cc=ulf.hansson@linaro.org \
    --cc=wsa+renesas@sang-engineering.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