From: Nick Piggin <nickpiggin@yahoo.com.au>
To: "Bryan O'Sullivan" <bos@pathscale.com>
Cc: Linus Torvalds <torvalds@osdl.org>,
Hugh Dickins <hugh@veritas.com>,
Roland Dreier <rdreier@cisco.com>, Andrew Morton <akpm@osdl.org>,
hch@infradead.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 10 of 20] ipath - support for userspace apps using core driver
Date: Sat, 18 Mar 2006 09:28:23 +1100 [thread overview]
Message-ID: <441B3807.8050307@yahoo.com.au> (raw)
In-Reply-To: <1142613609.28538.47.camel@serpentine.pathscale.com>
Bryan O'Sullivan wrote:
> On Fri, 2006-03-17 at 08:28 -0800, Linus Torvalds wrote:
>
>
>>kmalloc may be backed by a "struct page", but the point is that it does
>>not honor the page _count_, and as such it is totally unsuitable for any
>>VM usage.
>
>
> That's fine. We're not calling dma_free_coherent until after the page
> count goes back down to one (the driver is once again the only user).
And that's probably fine too (provided you can somehow be sure that
you're getting compound pages, which you currently can't) - you're
essentially doing your own refcounting then. However in that case you
do need to ensure get_user_pages can't operate on your mapping (use
VM_IO), because that can hijack the page lifetime (ie. hold a ref
even after all mappings have gone).
> But this doesn't seem germane to what Nick brought up, anyway.
>
Well kmalloc is one of the possible problems I saw, but there may be
others too (eg. ioremap).
--
SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com
next prev parent reply other threads:[~2006-03-17 22:28 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <71644dd19420ddb07a75.1141922823@localhost.localdomain>
2006-03-09 23:28 ` [PATCH 10 of 20] ipath - support for userspace apps using core driver Roland Dreier
2006-03-09 23:55 ` Bryan O'Sullivan
2006-03-10 0:01 ` Roland Dreier
2006-03-10 0:07 ` Bryan O'Sullivan
2006-03-10 0:32 ` Roland Dreier
2006-03-10 0:36 ` Bryan O'Sullivan
2006-03-10 0:37 ` Andrew Morton
2006-03-10 0:50 ` Bryan O'Sullivan
2006-03-16 0:56 ` Bryan O'Sullivan
2006-03-16 1:51 ` Roland Dreier
2006-03-16 2:11 ` Bryan O'Sullivan
2006-03-16 2:37 ` Roland Dreier
2006-03-16 2:52 ` Bryan O'Sullivan
2006-03-16 2:56 ` Bryan O'Sullivan
2006-03-16 3:28 ` Andrew Morton
2006-03-16 4:58 ` Bryan O'Sullivan
2006-03-16 5:38 ` Andrew Morton
2006-03-16 5:54 ` Roland Dreier
2006-03-16 6:17 ` Andrew Morton
2006-03-16 6:44 ` Nick Piggin
2006-03-16 9:39 ` Andrew Morton
2006-03-16 10:00 ` Nick Piggin
2006-03-16 7:25 ` Roland Dreier
2006-03-16 16:46 ` Linus Torvalds
2006-03-16 14:57 ` Hugh Dickins
2006-03-16 6:31 ` Nick Piggin
2006-03-16 14:34 ` Hugh Dickins
2006-03-17 0:37 ` Nick Piggin
2006-03-17 1:09 ` Roland Dreier
2006-03-17 15:27 ` Hugh Dickins
2006-03-17 22:21 ` Nick Piggin
2006-03-17 16:11 ` Bryan O'Sullivan
2006-03-17 16:28 ` Linus Torvalds
2006-03-17 16:40 ` Bryan O'Sullivan
2006-03-17 22:28 ` Nick Piggin [this message]
2006-03-17 22:14 ` Nick Piggin
2006-03-16 15:12 ` Bryan O'Sullivan
2006-03-16 17:08 ` Linus Torvalds
2006-03-16 17:46 ` Hugh Dickins
2006-03-16 17:53 ` Bryan O'Sullivan
2006-03-16 14:24 ` Hugh Dickins
2006-03-16 15:33 ` Bryan O'Sullivan
2006-03-16 17:23 ` Hugh Dickins
2006-03-16 17:40 ` Bryan O'Sullivan
2006-03-16 19:52 ` Bryan O'Sullivan
2006-03-16 20:10 ` Hugh Dickins
2006-03-16 20:35 ` Linus Torvalds
2006-03-16 20:43 ` Bryan O'Sullivan
2006-03-21 20:52 ` Bryan O'Sullivan
2006-03-21 23:20 ` Hugh Dickins
2006-03-22 15:58 ` Bryan O'Sullivan
2006-03-22 16:19 ` Linus Torvalds
2006-03-22 16:43 ` Bryan O'Sullivan
2006-03-22 17:46 ` Hugh Dickins
2006-03-22 17:53 ` Bryan O'Sullivan
2006-03-16 23:37 ` Roland Dreier
2006-03-16 23:51 ` Remapping pages mapped to userspace (was: [PATCH 10 of 20] ipath - support for userspace apps using core driver) Roland Dreier
2006-03-16 23:56 ` Bryan O'Sullivan
2006-03-17 1:10 ` Remapping pages mapped to userspace Roland Dreier
2006-03-17 1:12 ` Roland Dreier
2006-03-17 1:28 ` Alan Cox
2006-03-17 2:16 ` Roland Dreier
2006-03-17 17:13 ` Remapping pages mapped to userspace (was: [PATCH 10 of 20] ipath - support for userspace apps using core driver) Hugh Dickins
2006-03-17 17:17 ` Bryan O'Sullivan
2006-03-17 17:30 ` Linus Torvalds
2006-03-17 18:20 ` Hugh Dickins
2006-03-17 22:58 ` Remapping pages mapped to userspace Roland Dreier
2006-03-16 15:08 ` [PATCH 10 of 20] ipath - support for userspace apps using core driver Bryan O'Sullivan
2006-03-16 17:27 ` Hugh Dickins
2006-03-16 17:44 ` Bryan O'Sullivan
2006-03-16 16:52 ` Bryan O'Sullivan
2006-03-16 3:58 ` Linus Torvalds
2006-03-16 4:53 ` Roland Dreier
2006-03-16 2:28 ` Linus Torvalds
2006-03-09 23:33 ` Roland Dreier
2006-03-09 23:56 ` Bryan O'Sullivan
2006-03-10 0:35 [PATCH 0 of 20] [RFC] ipath driver - another round for review Bryan O'Sullivan
2006-03-10 0:35 ` [PATCH 10 of 20] ipath - support for userspace apps using core driver Bryan O'Sullivan
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=441B3807.8050307@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@osdl.org \
--cc=bos@pathscale.com \
--cc=hch@infradead.org \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rdreier@cisco.com \
--cc=torvalds@osdl.org \
/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