From: Trond Myklebust <Trond.Myklebust@netapp.com>
To: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: "Linus Torvalds" <torvalds@linux-foundation.org>,
"Russell King - ARM Linux" <linux@arm.linux.org.uk>,
linux-nfs@vger.kernel.org, linux-kernel@vger.kernel.org,
"Marc Kleine-Budde" <mkl@pengutronix.de>,
"Uwe Kleine-König" <u.kleine-koenig@pengutronix.de>,
"Marc Kleine-Budde" <m.kleine-budde@pengutronix.de>,
linux-arm-kernel@lists.infradead.org,
"Parisc List" <linux-parisc@vger.kernel.org>,
linux-arch@vger.kernel.org
Subject: Re: still nfs problems [Was: Linux 2.6.37-rc8]
Date: Thu, 06 Jan 2011 12:47:34 -0500 [thread overview]
Message-ID: <1294336054.2905.1.camel@heimdal.trondhjem.org> (raw)
In-Reply-To: <1294335614.22825.154.camel@mulgrave.site>
On Thu, 2011-01-06 at 11:40 -0600, James Bottomley wrote:
> On Wed, 2011-01-05 at 23:28 +0000, James Bottomley wrote:
> > Can you explain how the code works? it looks to me like you read the xdr
> > stuff through the vmap region then write it out directly to the pages?
>
> OK, I think I see how this is supposed to work: It's a sequential loop
> of reading in via the pages (i.e. through the kernel mapping) and then
> updating those pages via the vmap. In which case, I think this patch is
> what you need.
>
> The theory of operation is that the readdir on pages actually uses the
> network DMA operations to perform, so when it's finished, the underlying
> page is up to date. After this you invalidate the vmap range, so we
> have no cache lines above it (so it picks up the values from the
> uptodate page). Finally, after the operation on the vmap region has
> finished, you flush it so that any updated contents go back to the pages
> themselves before the next iteration begins.
>
> Does this look right to people? I've verified it fixes the issues on
> parisc.
>
> James
>
> ---
>
> diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
> index 996dd89..bde1911 100644
> --- a/fs/nfs/dir.c
> +++ b/fs/nfs/dir.c
> @@ -587,12 +587,16 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
> if (status < 0)
> break;
> pglen = status;
> +
> + invalidate_kernel_vmap_range(pages_ptr, pglen);
> +
> status = nfs_readdir_page_filler(desc, &entry, pages_ptr, page, pglen);
> if (status < 0) {
> if (status == -ENOSPC)
> status = 0;
> break;
> }
> + flush_kernel_vmap_range(pages_ptr, pglen);
Why is this line needed? We're not writing through the virtual mapping.
We checked using just the invalidate_kernel_vmap_range(), and that
appeared to suffice to fix the problem on ARM.
Cheers
Trond
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@netapp.com
www.netapp.com
next prev parent reply other threads:[~2011-01-06 17:47 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-05 19:05 still nfs problems [Was: Linux 2.6.37-rc8] James Bottomley
2011-01-05 19:18 ` Linus Torvalds
[not found] ` <AANLkTi=VZUxNFd7n-qwf5aiOeK5rkk8qBmo+kOpgg7up-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2011-01-05 19:36 ` James Bottomley
2011-01-05 19:36 ` James Bottomley
2011-01-05 19:49 ` Linus Torvalds
2011-01-05 20:35 ` James Bottomley
[not found] ` <1294256169.16957.18.camel-0iu6Cu4xQGLYCGPCin2YbQ@public.gmane.org>
2011-01-05 20:00 ` Russell King - ARM Linux
2011-01-05 20:00 ` Russell King - ARM Linux
2011-01-05 20:33 ` James Bottomley
2011-01-05 20:33 ` James Bottomley
2011-01-05 20:48 ` Linus Torvalds
[not found] ` <AANLkTimzzBsdtWcZtP5E_CH1hUZugGMoaHOiMdQJf764-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2011-01-05 21:04 ` Russell King - ARM Linux
2011-01-05 21:04 ` Russell King - ARM Linux
2011-01-05 21:08 ` Linus Torvalds
2011-01-05 21:08 ` Linus Torvalds
[not found] ` <AANLkTi=EXXBTW7oWHq3D+PHsx=thF1CpkRjn0ax2p5rm-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2011-01-05 21:16 ` Trond Myklebust
2011-01-05 21:16 ` Trond Myklebust
[not found] ` <1294262208.2952.4.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2011-01-05 21:30 ` Linus Torvalds
2011-01-05 21:30 ` Linus Torvalds
2011-01-05 23:06 ` Trond Myklebust
2011-01-05 23:06 ` Trond Myklebust
2011-01-05 23:28 ` James Bottomley
2011-01-06 17:40 ` James Bottomley
2011-01-06 17:47 ` Trond Myklebust [this message]
2011-01-06 17:51 ` James Bottomley
2011-01-06 17:55 ` Linus Torvalds
2011-01-06 17:55 ` Linus Torvalds
2011-01-07 18:53 ` Trond Myklebust
[not found] ` <1294426405.2929.23.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2011-01-07 19:02 ` Russell King - ARM Linux
2011-01-07 19:02 ` Russell King - ARM Linux
2011-01-07 19:11 ` James Bottomley
2011-01-07 19:11 ` James Bottomley
[not found] ` <1294427467.4895.66.camel-0iu6Cu4xQGLYCGPCin2YbQ@public.gmane.org>
2011-01-08 16:49 ` Trond Myklebust
2011-01-08 16:49 ` Trond Myklebust
2011-01-08 23:15 ` Trond Myklebust
2011-01-08 23:15 ` Trond Myklebust
[not found] ` <1294528551.4181.19.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2011-01-10 10:50 ` Uwe Kleine-König
2011-01-10 10:50 ` Uwe Kleine-König
2011-01-10 16:25 ` Trond Myklebust
[not found] ` <1294676734.3349.10.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2011-01-10 17:08 ` Marc Kleine-Budde
2011-01-10 17:08 ` Marc Kleine-Budde
2011-01-10 17:20 ` Trond Myklebust
[not found] ` <1294680035.3349.19.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2011-01-10 17:26 ` Marc Kleine-Budde
2011-01-10 17:26 ` Marc Kleine-Budde
2011-01-10 19:25 ` Uwe Kleine-König
[not found] ` <20110110192552.GG24920-bIcnvbaLZ9MEGnE8C9+IrQ@public.gmane.org>
2011-01-10 19:29 ` Trond Myklebust
2011-01-10 19:29 ` Trond Myklebust
2011-01-10 19:31 ` James Bottomley
2011-01-10 19:34 ` Linus Torvalds
2011-01-10 19:34 ` Linus Torvalds
2011-01-10 20:15 ` Trond Myklebust
2011-01-10 12:44 ` Marc Kleine-Budde
2011-01-10 12:44 ` Marc Kleine-Budde
2011-01-07 19:13 ` Trond Myklebust
2011-01-07 19:05 ` James Bottomley
[not found] ` <1294335614.22825.154.camel-0iu6Cu4xQGLYCGPCin2YbQ@public.gmane.org>
2011-01-06 18:05 ` Russell King - ARM Linux
2011-01-06 18:05 ` Russell King - ARM Linux
2011-01-06 18:14 ` James Bottomley
2011-01-06 18:14 ` James Bottomley
[not found] ` <1294337670.22825.199.camel-0iu6Cu4xQGLYCGPCin2YbQ@public.gmane.org>
2011-01-06 18:25 ` James Bottomley
2011-01-06 18:25 ` James Bottomley
2011-01-06 21:07 ` James Bottomley
2011-01-06 21:07 ` James Bottomley
2011-01-06 20:19 ` John Stoffel
2011-01-06 20:19 ` John Stoffel
2011-01-05 23:28 ` Linus Torvalds
2011-01-05 23:28 ` Linus Torvalds
[not found] ` <AANLkTi=SjMinMp+m726GS1iehj6cQgNy1RqSoUqKhjtv-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2011-01-05 23:59 ` Russell King - ARM Linux
2011-01-05 23:59 ` Russell King - ARM Linux
2011-01-05 21:16 ` James Bottomley
2011-01-05 21:16 ` James Bottomley
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=1294336054.2905.1.camel@heimdal.trondhjem.org \
--to=trond.myklebust@netapp.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-parisc@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=m.kleine-budde@pengutronix.de \
--cc=mkl@pengutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=u.kleine-koenig@pengutronix.de \
/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).