Message-ID: <51FC31AF.1070802@caviumnetworks.com>
Date: Fri, 2 Aug 2013 15:24:47 -0700
From: David Daney <ddaney@caviumnetworks.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130625 Thunderbird/17.0.7
MIME-Version: 1.0
To: Andrew Morton <akpm@linux-foundation.org>, <linux-kernel@vger.kernel.org>
CC: David Daney <david.daney@cavium.com>
Subject: Re: [PATCH 3/3] smp.h: Move !SMP version of on_each_cpu() out-of-line
References: <1375477776-13302-1-git-send-email-ddaney.cavm@gmail.com> <1375477776-13302-4-git-send-email-ddaney.cavm@gmail.com>
In-Reply-To: <1375477776-13302-4-git-send-email-ddaney.cavm@gmail.com>
Content-Type: text/plain; charset="ISO-8859-1"; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1290
Lines: 34

On 08/02/2013 02:09 PM, David Daney wrote:
> From: David Daney <david.daney@cavium.com>
>
> All of the other non-trivial !SMP versions of functions in smp.h are
>  out-of-line in up.c.  Move on_each_cpu() there as well.
>
> This allows us to get rid of the #include <linux/irqflags.h>.  The
> drawback is that this makes both the x86_64 and i386 defconfig !SMP
> kernels about 200 bytes larger each.

I looked at the cause of the size difference and there are several main
parts to it.

1) kallsym data (28 bytes).

2) with the patch generating a function pointer to pass to on_each_cpu 
vs. direct call (7 bytes * 22 call sites) and generating the the ignored 
third parameter (5 bytes * 22 call sites); without the patch 
local_irq_save/local_irq_restore(5 bytes * 22 call sites)  for a total 
of 7 * 22 == 154 bytes.

3) Other (21 bytes).

>
> Signed-off-by: David Daney <david.daney@cavium.com> ---
> include/linux/smp.h | 21 +++++---------------- kernel/up.c         |
> 11 +++++++++++ 2 files changed, 16 insertions(+), 16 deletions(-)
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/