From: Andrew Morton <akpm@digeo.com>
To: Hugh Dickins <hugh@veritas.com>
Cc: rmk@arm.linux.org.uk, LW@KARO-electronics.de,
linux-kernel@vger.kernel.org
Subject: Re: [patch] cache flush bug in mm/filemap.c (all kernels >= 2.5.30(at least))
Date: Fri, 23 May 2003 11:29:26 -0700 [thread overview]
Message-ID: <20030523112926.7c864263.akpm@digeo.com> (raw)
In-Reply-To: <Pine.LNX.4.44.0305231821460.1690-100000@localhost.localdomain>
Hugh Dickins <hugh@veritas.com> wrote:
>
> On Fri, 23 May 2003, Russell King wrote:
> >
> > No, I think there is a flush missing somewhere in this path.
> >
> > What I think is happening is that Lothar is using the PXA with the cache
> > in write allocate write back mode (Xscale is the first ARM-arch cpu to
> > have allocate on write caches.)
> >
> > This means that when IDE copies the data into the buffer using insw or
> > whatever, it ends up in the VIVT cache rather than memory. Since we
> > don't seem to be calling flush_dcache_page(), we never write this data
> > back to memory for user space to access it via their mapping.
That sounds distinctly possible.
> I believe (DaveM will speak with authority) that hitherto it has been
> assumed that I/O (well, Input) brings data actually into memory: we use
> flush_dcache_page if kernel memsets or memcpys data, not if it's read in.
Vague statement of principle: The device driver layer takes care of these
issues for DMA transfers, and hence should also take care of them for PIO.
Is this sensible and/or possible?
> If this mode+architecture departs from that, then we would need another
> macro, which translates to flush_dcache_page (sufficient?) for that,
> and is a nop for everything else.
>
> And where would it be placed? I think not where the flush_page_to_ram
> used to be in filemap_nopage, but after the ->readpage. Or... would
> this tie in with Martin's s390 request for a SetPageUptodate hook?
>
IDE?
next prev parent reply other threads:[~2003-05-23 18:13 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-05-22 12:34 [patch] cache flush bug in mm/filemap.c (all kernels >= 2.5.30(at least)) LW
2003-05-22 14:03 ` Russell King
2003-05-22 14:11 ` Russell King
2003-05-23 8:02 ` David S. Miller
2003-05-23 9:12 ` Andrew Morton
2003-05-23 9:49 ` David S. Miller
2003-05-23 10:04 ` Andrew Morton
2003-05-23 10:15 ` David S. Miller
2003-05-23 8:20 ` Lothar Wassmann
2003-05-23 9:24 ` Andrew Morton
2003-05-23 10:04 ` Lothar Wassmann
2003-05-23 10:45 ` Andrew Morton
2003-05-23 11:22 ` Paul Mackerras
2003-05-23 16:54 ` Russell King
2003-05-23 17:31 ` Hugh Dickins
2003-05-23 18:29 ` Andrew Morton [this message]
2003-05-23 18:34 ` Russell King
2003-05-26 3:19 ` David S. Miller
2003-05-26 5:07 ` Mika Penttilä
2003-05-26 5:08 ` David S. Miller
2003-05-26 5:36 ` Mika Penttilä
2003-05-26 5:36 ` David S. Miller
2003-05-26 13:18 ` Roman Zippel
2003-05-26 22:34 ` David S. Miller
2003-05-27 10:53 ` Roman Zippel
2003-05-27 21:22 ` David S. Miller
2003-05-28 16:35 ` Roman Zippel
2003-05-28 22:47 ` David S. Miller
2003-05-29 0:12 ` Roman Zippel
2003-05-29 1:37 ` David S. Miller
2003-05-29 7:13 ` Russell King
2003-05-29 7:15 ` David S. Miller
2003-05-29 17:49 ` Roman Zippel
2003-05-29 21:09 ` David S. Miller
2003-05-26 8:55 ` Russell King
2003-05-26 13:08 ` Lothar Wassmann
2003-05-26 22:19 ` Russell King
2003-05-26 13:25 ` Jens Axboe
2003-05-26 22:35 ` David S. Miller
2003-05-26 3:20 ` David S. Miller
2003-05-23 11:13 ` Russell King
2003-05-23 12:46 ` Lothar Wassmann
2003-05-23 15:42 ` Hugh Dickins
2003-05-25 17:10 ` David Woodhouse
2003-05-26 11:44 ` Lothar Wassmann
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=20030523112926.7c864263.akpm@digeo.com \
--to=akpm@digeo.com \
--cc=LW@KARO-electronics.de \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rmk@arm.linux.org.uk \
/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).