From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: "David S. Miller" <davem@davemloft.net>,
Paul Mackerras <paulus@samba.org>, Andrew Morton <akpm@osdl.org>,
clameter@sgi.com,
Linux Kernel list <linux-kernel@vger.kernel.org>,
linux-ia64@vger.kernel.org, Anton Blanchard <anton@samba.org>
Subject: Re: Page fault scalability patch V18: Drop first acquisition of ptl
Date: Fri, 04 Mar 2005 04:19:35 +1100 [thread overview]
Message-ID: <42274727.2070200@yahoo.com.au> (raw)
In-Reply-To: <1109829248.5679.178.camel@gaston>
Benjamin Herrenschmidt wrote:
>>However, if this pte_cmpxchg() thing is used for removing access, then
>>sparc64 can't use it. In such a case a race in the TLB handler would
>>result in using an invalid PTE. I could "spin" on some lock bit, but
>>there is no way I'm adding instructions to the carefully constructed
>>TLB miss handler assembler on sparc64 just for that :-)
>>
>
>Can't you add a lock bit in the PTE itself like we do on ppc64 hash
>refill ?
>
>
You don't want to do that for all architectures, as I said earlier.
eg. i386 can concurrently set the dirty bit with the MMU (which won't
honour the lock).
So you then need an atomic lock, atomic pte operations, and atomic
unlock where previously you had only the atomic pte operation. This is
disastrous for performance.
next prev parent reply other threads:[~2005-03-03 6:31 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-03-02 3:49 Page fault scalability patch V18: Overview Christoph Lameter
2005-03-02 3:50 ` Page fault scalability patch V18: atomic pte ops, pte_cmpxchg and pte_xchg Christoph Lameter
2005-03-02 3:51 ` Page fault scalability patch V18: abstract rss counter ops Christoph Lameter
2005-03-02 3:51 ` Page fault scalability patch V18: Drop first acquisition of ptl Christoph Lameter
2005-03-03 1:45 ` Andrew Morton
2005-03-03 2:13 ` Christoph Lameter
2005-03-03 2:55 ` Andrew Morton
2005-03-03 3:17 ` Christoph Lameter
2005-03-03 4:14 ` Andrew Morton
2005-03-03 4:27 ` Christoph Lameter
2005-03-03 4:56 ` Andrew Morton
2005-03-03 5:17 ` Christoph Lameter
2005-03-03 5:37 ` Andrew Morton
2005-03-03 5:48 ` Christoph Lameter
2005-03-03 6:13 ` Christoph Lameter
2005-03-03 6:20 ` Andrew Morton
2005-03-03 16:54 ` Christoph Lameter
2005-03-03 21:20 ` Andrew Morton
2005-03-03 22:14 ` Christoph Lameter
2005-03-04 16:44 ` Christoph Lameter
2005-03-04 17:09 ` Hugh Dickins
2005-03-04 18:29 ` Christoph Lameter
2005-03-04 19:08 ` Hugh Dickins
2005-03-31 6:55 ` Avoid spurious page faults by avoiding pte_clear -> set pte Christoph Lameter
2005-03-04 16:46 ` Page fault scalability patch V18: Drop first acquisition of ptl Christoph Lameter
2005-03-03 5:00 ` Paul Mackerras
2005-03-03 5:19 ` Christoph Lameter
2005-03-03 5:38 ` David S. Miller
2005-03-03 5:51 ` Christoph Lameter
2005-03-03 6:11 ` Benjamin Herrenschmidt
2005-03-03 16:52 ` Christoph Lameter
2005-03-03 5:54 ` Benjamin Herrenschmidt
2005-03-03 17:19 ` Nick Piggin [this message]
2005-03-03 6:30 ` Benjamin Herrenschmidt
2005-03-03 7:44 ` Nick Piggin
2005-03-03 17:43 ` David S. Miller
2005-03-03 5:24 ` Nick Piggin
2005-03-02 3:52 ` Page fault scalability patch V18: No page table lock in do_anonymous_page Christoph Lameter
2005-03-04 2:18 ` Page fault scalability patch V18: Overview Darren Williams
2005-03-04 2:47 ` Darren Williams
2005-03-04 16:15 ` Christoph Lameter
2005-03-06 21:49 ` Darren Williams
2005-03-06 23:59 ` Christoph Lameter
2005-03-07 3:32 ` Darren Williams
2005-03-08 4:03 ` Christoph Lameter
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=42274727.2070200@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@osdl.org \
--cc=anton@samba.org \
--cc=benh@kernel.crashing.org \
--cc=clameter@sgi.com \
--cc=davem@davemloft.net \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paulus@samba.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