From: Nick Piggin <npiggin@suse.de>
To: Andi Kleen <andi@firstfloor.org>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Wu Fengguang <fengguang.wu@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [RFC][PATCH] HWPOISON: remove the unsafe __set_page_locked()
Date: Mon, 28 Sep 2009 04:57:41 +0200 [thread overview]
Message-ID: <20090928025741.GI6327@wotan.suse.de> (raw)
In-Reply-To: <20090928011943.GB1656@one.firstfloor.org>
On Mon, Sep 28, 2009 at 03:19:43AM +0200, Andi Kleen wrote:
> > There is no real rush AFAIKS to fix this one single pagecache site
> > while we have problems with slab allocators and all other unaudited
> > places that nonatomically modify page flags with an elevated
>
> hwpoison ignores slab pages.
"ignores" them *after* it has already written to page flags?
By that time it's too late.
> > page reference ... just mark HWPOISON as broken for the moment, or
> > cut it down to do something much simpler I guess?
>
> Erm no. These cases are *EXTREMLY* unlikely to hit.
Well it's fundamentally badly buggy, rare or not. We could avoid
lots of nasty atomic operations if we just care that it works
most of the time. I guess it's a matter of perspective but I
won't push for one thing or the other in hwpoison code so long
as it stays out of core code for the most part.
WARNING: multiple messages have this Message-ID (diff)
From: Nick Piggin <npiggin@suse.de>
To: Andi Kleen <andi@firstfloor.org>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Wu Fengguang <fengguang.wu@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [RFC][PATCH] HWPOISON: remove the unsafe __set_page_locked()
Date: Mon, 28 Sep 2009 04:57:41 +0200 [thread overview]
Message-ID: <20090928025741.GI6327@wotan.suse.de> (raw)
In-Reply-To: <20090928011943.GB1656@one.firstfloor.org>
On Mon, Sep 28, 2009 at 03:19:43AM +0200, Andi Kleen wrote:
> > There is no real rush AFAIKS to fix this one single pagecache site
> > while we have problems with slab allocators and all other unaudited
> > places that nonatomically modify page flags with an elevated
>
> hwpoison ignores slab pages.
"ignores" them *after* it has already written to page flags?
By that time it's too late.
> > page reference ... just mark HWPOISON as broken for the moment, or
> > cut it down to do something much simpler I guess?
>
> Erm no. These cases are *EXTREMLY* unlikely to hit.
Well it's fundamentally badly buggy, rare or not. We could avoid
lots of nasty atomic operations if we just care that it works
most of the time. I guess it's a matter of perspective but I
won't push for one thing or the other in hwpoison code so long
as it stays out of core code for the most part.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2009-09-28 2:57 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-26 3:15 [RFC][PATCH] HWPOISON: remove the unsafe __set_page_locked() Wu Fengguang
2009-09-26 3:15 ` Wu Fengguang
2009-09-26 3:49 ` Andi Kleen
2009-09-26 3:49 ` Andi Kleen
2009-09-26 10:52 ` Wu Fengguang
2009-09-26 10:52 ` Wu Fengguang
2009-09-26 11:31 ` Wu Fengguang
2009-09-26 11:31 ` Wu Fengguang
2009-09-27 10:47 ` Wu Fengguang
2009-09-27 10:47 ` Wu Fengguang
2009-09-27 19:20 ` Nick Piggin
2009-09-27 19:20 ` Nick Piggin
2009-09-28 8:44 ` Wu Fengguang
2009-09-28 8:44 ` Wu Fengguang
2009-09-29 5:16 ` Wu Fengguang
2009-09-29 5:16 ` Wu Fengguang
2009-10-01 2:02 ` Nick Piggin
2009-10-01 2:02 ` Nick Piggin
2009-10-02 10:54 ` Wu Fengguang
2009-10-02 10:54 ` Wu Fengguang
2009-09-26 11:09 ` Hugh Dickins
2009-09-26 11:09 ` Hugh Dickins
2009-09-26 11:48 ` Wu Fengguang
2009-09-26 11:48 ` Wu Fengguang
2009-09-26 11:58 ` Hugh Dickins
2009-09-26 11:58 ` Hugh Dickins
2009-09-26 15:05 ` Andi Kleen
2009-09-26 15:05 ` Andi Kleen
2009-09-26 19:12 ` Nick Piggin
2009-09-26 19:12 ` Nick Piggin
2009-09-26 19:14 ` Nick Piggin
2009-09-26 19:14 ` Nick Piggin
2009-09-26 19:06 ` Nick Piggin
2009-09-26 19:06 ` Nick Piggin
2009-09-26 21:32 ` Andi Kleen
2009-09-26 21:32 ` Andi Kleen
2009-09-27 16:26 ` Hugh Dickins
2009-09-27 16:26 ` Hugh Dickins
2009-09-27 19:22 ` Nick Piggin
2009-09-27 19:22 ` Nick Piggin
2009-09-27 21:57 ` Hugh Dickins
2009-09-27 21:57 ` Hugh Dickins
2009-09-27 23:01 ` Nick Piggin
2009-09-27 23:01 ` Nick Piggin
2009-09-28 1:19 ` Andi Kleen
2009-09-28 1:19 ` Andi Kleen
2009-09-28 1:52 ` Wu Fengguang
2009-09-28 1:52 ` Wu Fengguang
2009-09-28 2:57 ` Nick Piggin [this message]
2009-09-28 2:57 ` Nick Piggin
2009-09-28 4:11 ` Andi Kleen
2009-09-28 4:11 ` Andi Kleen
2009-09-28 4:29 ` Nick Piggin
2009-09-28 4:29 ` Nick Piggin
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=20090928025741.GI6327@wotan.suse.de \
--to=npiggin@suse.de \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=fengguang.wu@intel.com \
--cc=hugh.dickins@tiscali.co.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.