linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Cc: devicetree <devicetree@vger.kernel.org>,
	Florian Fainelli <f.fainelli@gmail.com>,
	Rob Herring <robh@kernel.org>,
	linux-pci <linux-pci@vger.kernel.org>,
	Neil Armstrong <narmstrong@baylibre.com>,
	Christoph Hellwig <hch@infradead.org>,
	Bjorn Helgaas <helgaas@kernel.org>,
	linux-rpi-kernel <linux-rpi-kernel@lists.infradead.org>,
	bcm-kernel-feedback-list <bcm-kernel-feedback-list@broadcom.com>,
	Robin Murphy <robin.murphy@arm.com>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	Robin Murphy <robin.murphy@arm.con>
Subject: Re: RPi4 can't deal with 64 bit PCI accesses
Date: Fri, 26 Feb 2021 05:32:23 +0000	[thread overview]
Message-ID: <20210226053223.GA2763268@infradead.org> (raw)
In-Reply-To: <01091991523dac4c0c7e40f40e95c887af84f560.camel@suse.de>

On Thu, Feb 25, 2021 at 12:35:27PM +0100, Nicolas Saenz Julienne wrote:
> Yes, that's what I had in mind myself. All in all, why penalize the rest of
> busses in the system. What I'm planning is to introduce a '64bit-mmio-broken'
> DT property that'll utimately live somwhere in 'struct device.'
> 
> WRT why not defaulting to 32-bit accesses for distro images if they support
> RPi4. My *un-educated* guess is that, the performance penalty of checking for a
> device flag is (way) lower than having to resort to two distinct write
> operations with their assorted memory barriers. I'm sure you can
> comment/correct me here.

Various high performance devices rely on the fact that 64-bit MMIO
writes are atomic, and will have to use an extra lock and/or an entirely
different programming model if they are not supported.

If that is not the case just using 32-bit accesses always is certainly
easier, that's what we did for the slow-path only 64-bit registers in
NVMe.

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2021-02-26  5:33 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-22 15:47 RPi4 can't deal with 64 bit PCI accesses Nicolas Saenz Julienne
2021-02-22 16:18 ` Ard Biesheuvel
2021-02-22 16:36   ` Nicolas Saenz Julienne
2021-02-22 16:56 ` Robin Murphy
2021-02-24 16:55   ` Florian Fainelli
2021-02-24 20:25     ` Christoph Hellwig
2021-02-24 20:35       ` Florian Fainelli
2021-02-25 10:29         ` Neil Armstrong
2021-02-25 11:10           ` Robin Murphy
2021-02-25 11:35             ` Nicolas Saenz Julienne
2021-02-26  5:32               ` Christoph Hellwig [this message]
2021-02-25 10:41       ` David Woodhouse
2021-02-22 17:55 ` Russell King - ARM Linux admin

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=20210226053223.GA2763268@infradead.org \
    --to=hch@infradead.org \
    --cc=bcm-kernel-feedback-list@broadcom.com \
    --cc=devicetree@vger.kernel.org \
    --cc=f.fainelli@gmail.com \
    --cc=helgaas@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-rpi-kernel@lists.infradead.org \
    --cc=narmstrong@baylibre.com \
    --cc=nsaenzjulienne@suse.de \
    --cc=robh@kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=robin.murphy@arm.con \
    /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;
as well as URLs for NNTP newsgroup(s).