From: Anton Blanchard <anton@samba.org>
To: David Laight <David.Laight@ACULAB.COM>
Cc: "'Aneesh Kumar K.V'" <aneesh.kumar@linux.vnet.ibm.com>,
"benh@kernel.crashing.org" <benh@kernel.crashing.org>,
"paulus@samba.org" <paulus@samba.org>,
"mpe@ellerman.id.au" <mpe@ellerman.id.au>,
"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>
Subject: Re: [PATCH for-4.8 03/12] powerpc/mm: use _raw variant of page table accessors
Date: Sun, 17 Jul 2016 15:22:12 +1000 [thread overview]
Message-ID: <20160717152212.78f008bb@kryten> (raw)
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D5F4F8E51@AcuExch.aculab.com>
Hi David,
> > This switch few of the page table accessor to use the __raw variant
> > and does the cpu to big endian conversion of constants. This helps
> > in generating better code.
>
> It might be better to say that checks for a value being 0 don't depend
> on the endianness.
>
> In which case you want a function that return !!xxx_raw() itself.
>
> OTOH it might be worth finding out why the cpu's byteswapping memory
> accessors aren't used - which might save the byteswap instruction
> sequence in all paths.
There was a discussion about this on the list. In short, we found a
couple of reasons. Accesses often use READ_ONCE() which might cause
problems. The bigger issue is if the pte is accessed via larx/stcx. We
have no byte reversed larx/stcx instructions.
Anton
next prev parent reply other threads:[~2016-07-17 5:22 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-13 9:35 [PATCH for-4.8_set1 00/12] Radix fixes for 4.8 Aneesh Kumar K.V
2016-07-13 9:35 ` [PATCH for-4.8 01/12] Fix .long's in mm/tlb-radix.c to more meaningful Aneesh Kumar K.V
2016-07-17 10:28 ` [for-4.8,01/12] " Michael Ellerman
2016-07-13 9:35 ` [PATCH for-4.8 02/12] powerpc/mm/radix: Update LPCR HR bit as per ISA Aneesh Kumar K.V
2016-07-14 3:30 ` Balbir Singh
2016-07-13 9:35 ` [PATCH for-4.8 03/12] powerpc/mm: use _raw variant of page table accessors Aneesh Kumar K.V
2016-07-14 3:42 ` Balbir Singh
2016-07-15 11:42 ` David Laight
2016-07-17 5:22 ` Anton Blanchard [this message]
2016-07-13 9:35 ` [PATCH for-4.8 04/12] powerpc/mm: Compile out radix related functions if RADIX_MMU is disabled Aneesh Kumar K.V
2016-07-13 9:35 ` [PATCH for-4.8 05/12] powerpc/mm: Clear top 16 bits of va only on older cpus Aneesh Kumar K.V
2016-07-14 3:50 ` Balbir Singh
2016-07-13 9:35 ` [PATCH for-4.8 06/12] powerpc/mm: Print formation regarding the the MMU mode Aneesh Kumar K.V
2016-07-14 4:03 ` Balbir Singh
2016-07-13 9:35 ` [PATCH for-4.8 07/12] powerpc/mm/hash: Update SDR1 size encoding as documented in ISA 3.0 Aneesh Kumar K.V
2016-07-14 4:29 ` Balbir Singh
2016-07-13 9:35 ` [PATCH for-4.8 08/12] powerpc/mm/radix: Update PID switch sequence Aneesh Kumar K.V
2016-07-13 9:35 ` [PATCH for-4.8 09/12] powerpc/mm/radix: Update machine call back to support new HCALL Aneesh Kumar K.V
2016-07-13 9:35 ` [PATCH for-4.8 10/12] powerpc/mm/radix: Add LPID based tlb flush helpers Aneesh Kumar K.V
2016-07-14 5:12 ` Balbir Singh
2016-07-13 9:35 ` [PATCH for-4.8 11/12] powerpc/mm: Cleanup LPCR defines Aneesh Kumar K.V
2016-07-13 9:35 ` [PATCH for-4.8 12/12] powerpc/mm/radix: Add a kernel command line to disable radix Aneesh Kumar K.V
2016-07-14 5:02 ` Balbir Singh
2016-07-14 8:43 ` Aneesh Kumar K.V
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=20160717152212.78f008bb@kryten \
--to=anton@samba.org \
--cc=David.Laight@ACULAB.COM \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--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;
as well as URLs for NNTP newsgroup(s).