From: Will Newton <will.newton@gmail.com>
To: Kim Phillips <kim.phillips@freescale.com>
Cc: "Woodhouse, David" <david.woodhouse@intel.com>,
Russell King - ARM Linux <linux@arm.linux.org.uk>,
Borislav Petkov <bp@alien8.de>,
Andrew Morton <akpm@linux-foundation.org>,
Daniel Santos <daniel.santos@pobox.com>,
David Rientjes <rientjes@google.com>,
Rusty Russell <rusty@rustcorp.com.au>,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Rob Herring <robherring2@gmail.com>
Subject: Re: [RFC] arm: use built-in byte swap function
Date: Thu, 7 Feb 2013 10:19:05 +0000 [thread overview]
Message-ID: <CAFbHwiTCN5sFadXX7z7Smwd17tEZ7WmfKhG_6b3psu0bx228ew@mail.gmail.com> (raw)
In-Reply-To: <20130206191905.ac8eb6743e69425f30888704@freescale.com>
On Thu, Feb 7, 2013 at 1:19 AM, Kim Phillips <kim.phillips@freescale.com> wrote:
> On Wed, 6 Feb 2013 09:02:04 +0000
> "Woodhouse, David" <david.woodhouse@intel.com> wrote:
>
>> On Tue, 2013-02-05 at 21:04 -0600, Kim Phillips wrote:
>> > gcc -Os emits calls to __bswapsi2 on those platforms to save space
>> > because they don't have the single rev byte swap instruction.
>>
>> Is that the right thing for GCC to do in that situation?
>
> if it saves space, why wouldn't it be?
>
> "Many of these functions are only optimized in certain cases; if they
> are not optimized in a particular case, a call to the library
> function is emitted." [1]
>
> I see "(arm_arch6 || !optimize_size)" in gcc's define_expand
> "bswapsi2" source, so GCC considers size optimization as a
> legitimate one of those cases.
>
>> If so, perhaps we should be *providing* __bswap[sd]i2 functions for it
>> to use?
>
> either that, or link with libgcc - why does arch/arm64 do this and
> arch/arm not? It's not obvious from git log.
One reason I have found, I don't know if it is the canonical one, is
that linking with libgcc allows people to use all intrinsics e.g. soft
float routines in the kernel without noticing it. If you limit the
intrinsics to the ones linked into the kernel explicitly then this
cannot happen.
I have also seen cases where the libgcc intrinsics are improved over
time, having the code in the kernel allows these improvements to be
rolled into the kernel even if the user has an older toolchain.
A number of ports link against libgcc and a roughly equal number do
not, so it isn't clear that there's any consensus on the issue.
WARNING: multiple messages have this Message-ID (diff)
From: will.newton@gmail.com (Will Newton)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC] arm: use built-in byte swap function
Date: Thu, 7 Feb 2013 10:19:05 +0000 [thread overview]
Message-ID: <CAFbHwiTCN5sFadXX7z7Smwd17tEZ7WmfKhG_6b3psu0bx228ew@mail.gmail.com> (raw)
In-Reply-To: <20130206191905.ac8eb6743e69425f30888704@freescale.com>
On Thu, Feb 7, 2013 at 1:19 AM, Kim Phillips <kim.phillips@freescale.com> wrote:
> On Wed, 6 Feb 2013 09:02:04 +0000
> "Woodhouse, David" <david.woodhouse@intel.com> wrote:
>
>> On Tue, 2013-02-05 at 21:04 -0600, Kim Phillips wrote:
>> > gcc -Os emits calls to __bswapsi2 on those platforms to save space
>> > because they don't have the single rev byte swap instruction.
>>
>> Is that the right thing for GCC to do in that situation?
>
> if it saves space, why wouldn't it be?
>
> "Many of these functions are only optimized in certain cases; if they
> are not optimized in a particular case, a call to the library
> function is emitted." [1]
>
> I see "(arm_arch6 || !optimize_size)" in gcc's define_expand
> "bswapsi2" source, so GCC considers size optimization as a
> legitimate one of those cases.
>
>> If so, perhaps we should be *providing* __bswap[sd]i2 functions for it
>> to use?
>
> either that, or link with libgcc - why does arch/arm64 do this and
> arch/arm not? It's not obvious from git log.
One reason I have found, I don't know if it is the canonical one, is
that linking with libgcc allows people to use all intrinsics e.g. soft
float routines in the kernel without noticing it. If you limit the
intrinsics to the ones linked into the kernel explicitly then this
cannot happen.
I have also seen cases where the libgcc intrinsics are improved over
time, having the code in the kernel allows these improvements to be
rolled into the kernel even if the user has an older toolchain.
A number of ports link against libgcc and a roughly equal number do
not, so it isn't clear that there's any consensus on the issue.
next prev parent reply other threads:[~2013-02-07 10:19 UTC|newest]
Thread overview: 127+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-29 1:30 [RFC] arm: use built-in byte swap function Kim Phillips
2013-01-29 1:30 ` Kim Phillips
2013-01-29 8:35 ` Borislav Petkov
2013-01-29 8:35 ` Borislav Petkov
2013-01-29 16:46 ` Woodhouse, David
2013-01-29 16:46 ` Woodhouse, David
2013-01-29 17:42 ` Borislav Petkov
2013-01-29 17:42 ` Borislav Petkov
2013-01-29 17:55 ` Woodhouse, David
2013-01-29 17:55 ` Woodhouse, David
2013-01-29 18:10 ` Borislav Petkov
2013-01-29 18:10 ` Borislav Petkov
2013-01-30 10:22 ` Woodhouse, David
2013-01-30 10:22 ` Woodhouse, David
2013-01-31 2:09 ` Kim Phillips
2013-01-31 2:09 ` Kim Phillips
2013-01-31 6:44 ` Borislav Petkov
2013-01-31 6:44 ` Borislav Petkov
2013-01-31 9:28 ` Russell King - ARM Linux
2013-01-31 9:28 ` Russell King - ARM Linux
2013-01-31 20:59 ` Kim Phillips
2013-01-31 20:59 ` Kim Phillips
2013-01-31 21:33 ` Borislav Petkov
2013-01-31 21:33 ` Borislav Petkov
2013-01-31 22:11 ` Woodhouse, David
2013-01-31 22:11 ` Woodhouse, David
2013-02-01 0:37 ` [PATCH v4] " Kim Phillips
2013-02-01 0:37 ` Kim Phillips
2013-02-01 10:46 ` Russell King - ARM Linux
2013-02-01 10:46 ` Russell King - ARM Linux
2013-02-01 1:17 ` [RFC] " Russell King - ARM Linux
2013-02-01 1:17 ` Russell King - ARM Linux
2013-02-01 7:33 ` Woodhouse, David
2013-02-01 7:33 ` Woodhouse, David
2013-02-06 3:04 ` Kim Phillips
2013-02-06 3:04 ` Kim Phillips
2013-02-06 9:02 ` Woodhouse, David
2013-02-06 9:02 ` Woodhouse, David
2013-02-07 1:19 ` Kim Phillips
2013-02-07 1:19 ` Kim Phillips
2013-02-07 10:19 ` Will Newton [this message]
2013-02-07 10:19 ` Will Newton
2013-02-07 10:43 ` Catalin Marinas
2013-02-07 10:43 ` Catalin Marinas
2013-02-07 18:13 ` Russell King - ARM Linux
2013-02-07 18:13 ` Russell King - ARM Linux
2013-02-08 17:25 ` Woodhouse, David
2013-02-08 17:25 ` Woodhouse, David
2013-02-08 20:04 ` Nicolas Pitre
2013-02-08 20:04 ` Nicolas Pitre
2013-02-08 22:40 ` Woodhouse, David
2013-02-08 22:40 ` Woodhouse, David
2013-02-08 22:47 ` Nicolas Pitre
2013-02-08 22:47 ` Nicolas Pitre
2013-02-09 1:12 ` Kim Phillips
2013-02-09 1:12 ` Kim Phillips
2013-02-09 3:16 ` Nicolas Pitre
2013-02-09 3:16 ` Nicolas Pitre
2013-02-20 2:31 ` Kim Phillips
2013-02-20 2:31 ` Kim Phillips
2013-02-20 2:38 ` Stephen Boyd
2013-02-20 2:38 ` Stephen Boyd
2013-02-20 3:17 ` Nicolas Pitre
2013-02-20 3:17 ` Nicolas Pitre
2013-02-20 10:38 ` Woodhouse, David
2013-02-20 10:38 ` Woodhouse, David
2013-02-20 13:36 ` Nicolas Pitre
2013-02-20 13:36 ` Nicolas Pitre
2013-02-20 13:44 ` Woodhouse, David
2013-02-20 13:44 ` Woodhouse, David
2013-02-20 14:06 ` Nicolas Pitre
2013-02-20 14:06 ` Nicolas Pitre
2013-02-20 14:53 ` Woodhouse, David
2013-02-20 14:53 ` Woodhouse, David
2013-02-20 15:43 ` Nicolas Pitre
2013-02-20 15:43 ` Nicolas Pitre
2013-02-21 3:49 ` Kim Phillips
2013-02-21 3:49 ` Kim Phillips
2013-02-21 4:29 ` Nicolas Pitre
2013-02-21 4:29 ` Nicolas Pitre
2013-02-21 6:52 ` Kim Phillips
2013-02-21 6:52 ` Kim Phillips
2013-02-21 16:40 ` Nicolas Pitre
2013-02-21 16:40 ` Nicolas Pitre
2013-02-22 2:33 ` Kim Phillips
2013-02-22 2:33 ` Kim Phillips
2013-02-22 3:40 ` Nicolas Pitre
2013-02-22 3:40 ` Nicolas Pitre
2013-02-23 1:40 ` [PATCH v6] " Kim Phillips
2013-02-23 1:40 ` Kim Phillips
2013-02-23 2:40 ` Nicolas Pitre
2013-02-23 2:40 ` Nicolas Pitre
2013-02-23 23:20 ` Woodhouse, David
2013-02-23 23:20 ` Woodhouse, David
2013-05-23 16:46 ` [PATCH v7] " Kim Phillips
2013-05-23 16:46 ` Kim Phillips
2013-05-23 20:09 ` Nicolas Pitre
2013-05-23 20:09 ` Nicolas Pitre
2013-05-23 23:13 ` Russell King - ARM Linux
2013-05-23 23:13 ` Russell King - ARM Linux
2013-06-06 22:12 ` Russell King - ARM Linux
2013-06-06 22:12 ` Russell King - ARM Linux
2013-06-06 22:23 ` Borislav Petkov
2013-06-06 22:23 ` Borislav Petkov
2013-06-07 0:03 ` Stephen Rothwell
2013-06-07 0:03 ` Stephen Rothwell
2013-05-26 5:38 ` Dirk Behme
2013-05-26 9:30 ` Woodhouse, David
2013-10-27 2:41 ` Nicolas Pitre
2013-10-27 2:41 ` Nicolas Pitre
2013-11-05 21:45 ` Kim Phillips
2013-11-05 21:45 ` Kim Phillips
2013-02-21 16:37 ` [RFC] " Woodhouse, David
2013-02-21 16:37 ` Woodhouse, David
2013-02-21 17:27 ` Nicolas Pitre
2013-02-21 17:27 ` Nicolas Pitre
2013-03-13 13:35 ` Woodhouse, David
2013-03-13 13:35 ` Woodhouse, David
2013-01-29 14:13 ` Russell King - ARM Linux
2013-01-29 14:13 ` Russell King - ARM Linux
2013-01-29 14:43 ` Woodhouse, David
2013-01-29 14:43 ` Woodhouse, David
2013-01-29 14:53 ` Rob Herring
2013-01-29 14:53 ` Rob Herring
2013-01-29 15:10 ` Woodhouse, David
2013-01-29 15:10 ` Woodhouse, David
2013-01-31 11:44 Woodhouse, David
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=CAFbHwiTCN5sFadXX7z7Smwd17tEZ7WmfKhG_6b3psu0bx228ew@mail.gmail.com \
--to=will.newton@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=bp@alien8.de \
--cc=daniel.santos@pobox.com \
--cc=david.woodhouse@intel.com \
--cc=kim.phillips@freescale.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=rientjes@google.com \
--cc=robherring2@gmail.com \
--cc=rusty@rustcorp.com.au \
/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.