Average instruction length in x86-built kernel?

Average instruction length in x86-built kernel?

[Karim Yaghmour]

I'm wondering if anyone's ever done an analysis on the average length
of instructions in an x86-built kernel.

Googling around, I can find references claiming that the average
instruction length on x86 is anywhere from 2.7 to 3.5 bytes, but I
can't find anything studying Linux specifically.

Just curious,

Karim
-- 
Author, Speaker, Developer, Consultant
Pushing Embedded and Real-Time Linux Systems Beyond the Limits
http://www.opersys.com || karim@opersys.com || 1-866-677-4546

Re: Average instruction length in x86-built kernel?

[Ingo Oeser]

[-- Attachment #1: Type: text/plain, Size: 785 bytes --]

Hi Karim,

On Friday 29 July 2005 23:32, Karim Yaghmour wrote:
> Googling around, I can find references claiming that the average
> instruction length on x86 is anywhere from 2.7 to 3.5 bytes, but I
> can't find anything studying Linux specifically.

This is not that hard to find out yourself:

Just study the output od objdump -d and average the differences
of the first hex number in a line printed, which are followed by a ":"

e.g.


scripts/kconfig/mconf.o:     file format elf32-i386

Disassembly of section .text:

00000000 <init_wsize>:
       0:	83 ec 1c             	sub    $0x1c,%esp
       3:	8d 44 24 10          	lea    0x10(%esp),%eax
       7:	89 44 24 08          	mov    %eax,0x8(%esp)

so avg(3-7, 3-0) = 2.5

and so on...


Happy analyzing!


Regards

Ingo Oeser


[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: Average instruction length in x86-built kernel?

[Karim Yaghmour]

Hello Ingo,

Ingo Oeser wrote:
> Just study the output od objdump -d and average the differences
> of the first hex number in a line printed, which are followed by a ":"

Here's a script that does what I was looking for:
#!/bin/bash

# Dissassemble
objdump -d $1 -j .text > $2-dissassembled-kernel

# Remove non-instruction lines:
sed /^[^c].*/d $2-dissassembled-kernel > $2-stage-1

# Remove empty lines:
sed /^'\t'*$/d $2-stage-1 > $2-stage-2

# Remove function names:
sed /^c[0-9,a-f]*' '\<.*\>:$/d $2-stage-2 > $2-stage-3

# Remove addresses:
sed s/^c[0-9,a-f]*:'\t'// $2-stage-3 > $2-stage-4

# Remove instruction text:
sed s/'\t'.*// $2-stage-4 > $2-stage-5

# Remove trailing whitespace:
sed s/'\s'*$// $2-stage-5 > $2-stage-6

# Separate instructions depending on size:
egrep "([0-9a-f]{2}[' ']*){5}" $2-stage-6 > $2-more-or-eq-5
egrep "^([0-9a-f]{2}[' ']*){0,4}$" $2-stage-6 > $2-less-or-eq-4

# Find out how much of each we've got:
wc -l $2-stage-6
wc -l $2-more-or-eq-5
wc -l $2-less-or-eq-4

The last part can easily be changed to iterate through and separate
those that are 1 byte, 2 bytes, etc. and automatically come up with
stats, but this was fine for what I was looking for.

I ran it on a 2.4.x and a 2.6.x kernel and about 3/4 of instructions
are 4 bytes or less.

Karim
-- 
Author, Speaker, Developer, Consultant
Pushing Embedded and Real-Time Linux Systems Beyond the Limits
http://www.opersys.com || karim@opersys.com || 1-866-677-4546

Re: Average instruction length in x86-built kernel?

[David Weinehall]

On Sat, Jul 30, 2005 at 03:57:25PM -0400, Karim Yaghmour wrote:
[snip]
> # Remove non-instruction lines:
> sed /^[^c].*/d $2-dissassembled-kernel > $2-stage-1
> 
> # Remove empty lines:
> sed /^'\t'*$/d $2-stage-1 > $2-stage-2
> 
> # Remove function names:
> sed /^c[0-9,a-f]*' '\<.*\>:$/d $2-stage-2 > $2-stage-3
> 
> # Remove addresses:
> sed s/^c[0-9,a-f]*:'\t'// $2-stage-3 > $2-stage-4
> 
> # Remove instruction text:
> sed s/'\t'.*// $2-stage-4 > $2-stage-5
> 
> # Remove trailing whitespace:
> sed s/'\s'*$// $2-stage-5 > $2-stage-6

Uhm, you do know that sed allows you to execute several commands after
eachother, right?

sed -e 's/foo/bar/;s/baz/omph/'

That way you should be able to save a few stages.
Also, your script is, as far as I could see, a clean sh-script;
no need for /bin/bash; use /bin/sh instead.


Regards: David Weinehall
-- 
 /) David Weinehall <tao@acc.umu.se> /) Northern lights wander      (\
//  Maintainer of the v2.0 kernel   //  Dance across the winter sky //
\)  http://www.acc.umu.se/~tao/    (/   Full colour fire           (/

Re: Average instruction length in x86-built kernel?

[Bodo Eggert]

Karim Yaghmour <karim@opersys.com> wrote:

> Here's a script that does what I was looking for:
<snip>

#!/bin/bash
for a in "$@"
do
        objdump -d "$a" -j .text 
done | perl -ne'
BEGIN{%h=();$b=0};
END{if($b){$h{$b}++};print map("$_: $h{$_}\n", sort(keys(%h)))};
if(/\tnop    $/){$h{nop}++}
elsif(/^[\s0-9a-f]{8}:\t([^\t]+) (\t?)/){
 $b+=split(" ",$1);if($2){$h{$b}++;$b=0}}'

-- 
Ich danke GMX dafür, die Verwendung meiner Adressen mittels per SPF
verbreiteten Lügen zu sabotieren.

Re: Average instruction length in x86-built kernel?

[Jan Engelhardt]

>> Here's a script that does what I was looking for:
><snip>

Mmmmh, perlgolf?

>#!/bin/bash
>for a in "$@"
>do
>        objdump -d "$a" -j .text 
>done | perl -ne'
>BEGIN{%h=();$b=0};
>END{if($b){$h{$b}++};print map("$_: $h{$_}\n", sort(keys(%h)))};
>if(/\tnop    $/){$h{nop}++}
>elsif(/^[\s0-9a-f]{8}:\t([^\t]+) (\t?)/){
> $b+=split(" ",$1);if($2){$h{$b}++;$b=0}}'

objdump -j .text -d "$@" | perl -ne '
END{$h{$b}++if$b;print map"$_: $h{$_}\n",sort keys%h};
if(/\tnop\s*$/){$h{nop}++}    
elsif(/^.*?:\t([^\t]+) (\t?)/){
 $b+=split/ /,$1;if($2){$h{$b}++;$b=0}}'



Jan Engelhardt
-- 
| Alphagate Systems, http://alphagate.hopto.org/