From: Alan Cox <alan@lxorguk.ukuu.org.uk>
To: Roland Dreier <rdreier@cisco.com>
Cc: "Bryan O'Sullivan" <bos@pathscale.com>,
Hugh Dickins <hugh@veritas.com>, Andrew Morton <akpm@osdl.org>,
torvalds@osdl.org, hch@infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: Remapping pages mapped to userspace
Date: Fri, 17 Mar 2006 01:28:28 +0000 [thread overview]
Message-ID: <1142558909.23236.11.camel@localhost.localdomain> (raw)
In-Reply-To: <adapsklnaby.fsf@cisco.com>
On Iau, 2006-03-16 at 17:12 -0800, Roland Dreier wrote:
> Oh yeah... but getting rid of the mapping so userspace gets a segfault
> might be a good idea too. However, leaving the old PCI mapping there
> seems rather risky to me: I think it's entirely possible that accesses
> to that area after the device is gone could trigger machine checks or
> worse.
Not really. After all the hot remove can race an actual mmio cycle so
you can't close that window to nothing. In other words if it does make
the PCI bridge burp at you - well hotplug has to handle it.
That means on the positive side that all you need to do is refcount
properly and destroy the PCI device when you have finished with it. If a
mapping continues to exist then fine, because the device is still
logically there. If the device is logically there then the resources
have not been unmapped. If the resources have not been unmapped they are
not free for allocation to another device.
Config space looks more problematic but memory maps of PCI space appear
to be ok.
Alan
next prev parent reply other threads:[~2006-03-17 1:22 UTC|newest]
Thread overview: 76+ 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
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 [this message]
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
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=1142558909.23236.11.camel@localhost.localdomain \
--to=alan@lxorguk.ukuu.org.uk \
--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
Powered by JetHome