mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Christoph Hellwig <hch@lst.de>,
	LEROY Christophe <christophe.leroy2@cs-soprasteria.com>
Cc: Christian Lamparter <christian.lamparter@isd.uni-stuttgart.de>,
	Paul Mackerras <paulus@samba.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
	Stan Johnson <userm57@yahoo.com>,
	Finn Thain <fthain@linux-m68k.org>
Subject: Re: [PATCH v2] powerpc: warn on emulation of dcbz instruction in kernel mode
Date: Thu, 22 Aug 2024 19:53:42 +1000	[thread overview]
Message-ID: <8c7980d11a2141a90669b063ce8569736e4675ae.camel@kernel.crashing.org> (raw)
In-Reply-To: <20240822071443.GA6395@lst.de>

On Thu, 2024-08-22 at 09:14 +0200, Christoph Hellwig wrote:
> 
> I'd suggest two things:
> 
>  1) remove the warning.  The use case is perfectly valid and everything
>     using uncached memory is already slow, so people will just have to
>     deal with it.  Maybe offer a trace point instead if people care about
>     it.

Well... there's slow and extremely slow .. :-) dcbz() on uncached
memory will take an exception for every "cache line" of zeros which
will then need to be emulated. We are talking about hundreds to
thousands of cycle per cache line. 

(Do we have an optimisation to detect memset in the emulation code and
force it to return to a non-dcbz'ing version ? If not, that's doable
and would at least limit it to one exception per memset() instead of
one per cache-line). 

Cheers,
Ben.

  reply	other threads:[~2024-08-22 10:24 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-16 14:52 Christophe Leroy
2021-11-02 10:11 ` Michael Ellerman
2024-08-21 22:39 ` Christian Lamparter
2024-08-22  5:25   ` LEROY Christophe
2024-08-22  5:32     ` Christoph Hellwig
2024-08-22  6:39       ` LEROY Christophe
2024-08-22  7:14         ` Christoph Hellwig
2024-08-22  9:53           ` Benjamin Herrenschmidt [this message]
2024-08-22 18:19           ` Christian Lamparter
2024-08-23  8:07             ` Christoph Hellwig
2024-08-23 13:06         ` Segher Boessenkool
2024-08-23 13:54           ` Christoph Hellwig
2024-08-23 19:19             ` Segher Boessenkool
2024-08-23 23:43               ` Christian Lamparter
2024-08-24  9:01               ` LEROY Christophe
2024-08-24 17:17                 ` Segher Boessenkool
2024-08-27  7:29                   ` Christoph Hellwig

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=8c7980d11a2141a90669b063ce8569736e4675ae.camel@kernel.crashing.org \
    --to=benh@kernel.crashing.org \
    --cc=christian.lamparter@isd.uni-stuttgart.de \
    --cc=christophe.leroy2@cs-soprasteria.com \
    --cc=fthain@linux-m68k.org \
    --cc=hch@lst.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    --cc=userm57@yahoo.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

all inboxes | Powered by JetHome®