From: Geoff Levand <geoffrey.levand@am•sony.com>
To: Arnd Bergmann <arnd@arndb•de>
Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom•com>,
linuxppc-dev@ozlabs•org, Paul Mackerras <paulus@samba•org>,
"Noguchi, Masato" <Masato.Noguchi@jp•sony.com>
Subject: Re: [patch 05/18] PS3: Fix sparse warnings
Date: Thu, 07 Jun 2007 07:34:21 -0700 [thread overview]
Message-ID: <4668176D.7060002@am.sony.com> (raw)
In-Reply-To: <200706061621.59963.arnd@arndb.de>
Arnd Bergmann wrote:
> On Wednesday 06 June 2007, Geoff Levand wrote:
>> -=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BDspu->l=
ocal_store =3D ioremap(spu->local_store_phys, LS_SIZE);
>> +=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BDspu->l=
ocal_store =3D (__force void *)ioremap(spu->local_store_phys,
>> +=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=
=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=
=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=
=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=
=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=
=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD=EF=BF=BD =EF=BF=BD LS_SIZE)=
;
>=20
> I haven't noticed this before, but it seems to be a preexisting bug:
> You map the local_store as with the guarded page table bit set, which
> causes a performance degradation when accessing the memory from kernel
> space.
>=20
> If you're lucky, your hypervisor knows this and will fix it up for
> you, but I would replace the ioremap call with an
> ioremap_flags(..., _PAGE_NO_CACHE); to be on the safe side.
>=20
> If you want to measure the impact, I'd suggest timing a user space
> read() on the mem file of a running SPU context.
Hi Arnd,
I asked Noguchi-san to check the performance and below is his
report and test program. I'll add the change into my patch set.
-Geoff
-------- Original Message --------
Subject: RE: [patch 05/18] PS3: Fix sparse warnings
Date: Thu, 7 Jun 2007 05:39:43 -0700
From: Noguchi, Masato <Masato.Noguchi@jp•sony.com>
To: Levand, Geoff <Geoffrey.Levand@am•sony.com>
<< A time to read a whole of LS by read system call >>
not patched: avg. 21053.7800 tick ( 263.831830 microseconds )
patched: avg. 20809.2412 tick ( 260.767434 microseconds )
about 1% faster.=20
I think it's a valid difference. (not a measurement error.)
FYI,=20
The attached file is source code to measure it.
I run it 10000 times and calc an average.
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/mman.h>
#include <sys/wait.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdio.h>
#include <signal.h>
#include <string.h>
#include <stdint.h>
#include <stdlib.h>
#include <pthread.h>
#define __NR_spe_run 278
#define __NR_spe_create 279
#define LS_SIZE 0x40000
#define SPENODE "/spu/stoplooptest"
#define MFTB(RA) __asm__ volatile("mftb %0":"=3Dr"(RA))
long long do_test(void)
{
int spefd =3D -1, lsfd =3D -1;
int npc, status;
long long ret =3D -1;
char buf[LS_SIZE];
int n;
uint32_t t1, t2;
/* create context */
spefd =3D syscall(__NR_spe_create, SPENODE, 0,
S_IRUSR | S_IWUSR | S_IXUSR);
if (spefd < 0) goto out;
/* run once to assign physical spe */
npc =3D 0;
syscall(__NR_spe_run, spefd, &npc, &status);
/* get /mem file descriptor */
lsfd =3D open(SPENODE "/mem", O_RDWR,
S_IRUSR | S_IWUSR);
if (lsfd < 0) goto out;
/* read mem */
MFTB(t1);
if (read(lsfd, buf, LS_SIZE) !=3D LS_SIZE) {
goto out;
}
MFTB(t2);
ret =3D t2 - t1;
out:
if ( lsfd >=3D 0 ) close(lsfd);
if ( spefd >=3D 0 ) close(spefd);
return ret;
}
int main(int argc, char *argv[])
{
long long r;
r =3D do_test();
printf("%lld\n", r);
return 0;
}
next prev parent reply other threads:[~2007-06-07 14:34 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20070606024407.786638029@am.sony.com>
2007-06-06 2:59 ` [patch 01/18] Cell: Add spu shutdown method Geoff Levand
2007-06-06 4:08 ` Michael Ellerman
2007-06-06 14:41 ` André Detsch
2007-06-06 2:59 ` [patch 02/18] PS3: Rename IPI symbols Geoff Levand
2007-06-06 3:11 ` Stephen Rothwell
2007-06-06 14:48 ` Will Schmidt
2007-06-06 20:47 ` Geoff Levand
2007-06-06 20:49 ` Geoff Levand
2007-06-06 2:59 ` [patch 03/18] PS3: Use __maybe_unused Geoff Levand
2007-06-06 4:05 ` Michael Ellerman
2007-06-06 22:37 ` Geoff Levand
2007-06-06 2:59 ` [patch 04/18] PS3: Compare firmware version Geoff Levand
2007-06-06 2:59 ` [patch 05/18] PS3: Fix sparse warnings Geoff Levand
2007-06-06 14:21 ` Arnd Bergmann
2007-06-07 14:34 ` Geoff Levand [this message]
2007-06-08 5:59 ` Takao Shinohara
2007-06-06 2:59 ` [patch 06/18] PS3: Add support for HDMI RGB Full Range mode Geoff Levand
2007-06-06 3:00 ` [patch 07/18] PS3: Make ps3av.h usable from user space Geoff Levand
2007-06-06 7:46 ` Christoph Hellwig
2007-06-06 11:27 ` Geert Uytterhoeven
2007-06-06 16:44 ` Geoff Levand
2007-06-07 19:15 ` Christoph Hellwig
2007-06-06 3:00 ` [patch 08/18] PS3: Kexec support Geoff Levand
2007-06-06 4:01 ` Michael Ellerman
2007-06-06 21:55 ` Geoff Levand
2007-06-07 1:25 ` Stephen Rothwell
2007-06-07 1:33 ` Geoff Levand
2007-06-07 2:48 ` Stephen Rothwell
2007-06-07 2:31 ` Michael Ellerman
2007-06-07 2:54 ` Benjamin Herrenschmidt
2007-06-10 0:13 ` Geoff Levand
2007-06-09 8:17 ` [patch 08/18] PS3: Kexec support (and a tutoral on the kexec flow for 64 bit powerpc) Milton Miller
2007-06-09 22:47 ` Geoff Levand
2007-06-06 3:00 ` [patch 09/18] PS3: System-bus rework Geoff Levand
2007-06-06 6:43 ` Geert Uytterhoeven
2007-06-11 7:07 ` Milton Miller
2007-06-11 15:39 ` Geoff Levand
2007-06-11 15:45 ` Geert Uytterhoeven
2007-06-06 3:00 ` [patch 10/18] PS3: System-bus uevent Geoff Levand
2007-06-06 3:00 ` [patch 11/18] PS3: System-bus modinfo attribute Geoff Levand
2007-06-06 3:17 ` Stephen Rothwell
2007-06-06 3:00 ` [patch 12/18] PS3: Repository probe cleanups Geoff Levand
2007-06-06 3:01 ` [patch 13/18] PS3: USB system-bus rework Geoff Levand
2007-06-06 3:01 ` [patch 14/18] PS3: Vuart rework Geoff Levand
2007-06-06 3:01 ` [patch 15/18] PS3: System manager re-work Geoff Levand
2007-06-06 6:51 ` Geert Uytterhoeven
2007-06-06 3:01 ` [patch 16/18] PS3: Rework AV settings driver Geoff Levand
2007-06-06 6:49 ` Geert Uytterhoeven
2007-06-06 3:01 ` [patch 17/18] PS3: Frame buffer system-bus rework Geoff Levand
2007-06-06 6:51 ` Geert Uytterhoeven
2007-06-06 15:56 ` [Linux-fbdev-devel] " Antonino A. Daplas
2007-06-06 23:08 ` Geoff Levand
2007-06-06 23:37 ` Antonino A. Daplas
2007-06-06 3:01 ` [patch 18/18] PS3: Device registration routines Geoff Levand
2007-06-06 6:57 ` Geert Uytterhoeven
2007-06-06 12:21 ` Geert Uytterhoeven
2007-06-06 3:04 ` [patch 13/18] PS3: USB system-bus rework Geoff Levand
2007-06-08 23:22 ` [patch] PS3: Fix USB return value Geoff Levand
2007-06-25 7:30 ` Greg KH
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=4668176D.7060002@am.sony.com \
--to=geoffrey.levand@am$(echo .)sony.com \
--cc=Geert.Uytterhoeven@sonycom$(echo .)com \
--cc=Masato.Noguchi@jp$(echo .)sony.com \
--cc=arnd@arndb$(echo .)de \
--cc=linuxppc-dev@ozlabs$(echo .)org \
--cc=paulus@samba$(echo .)org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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