linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Josh Boyer <jwboyer@linux.vnet.ibm.com>
To: torez <lnxtorez@linux.vnet.ibm.com>
Cc: linuxppc-dev@ozlabs.org
Subject: Re: indications for oprofile in compact mode
Date: Mon, 07 Jul 2008 16:37:52 -0400	[thread overview]
Message-ID: <1215463072.20774.63.camel@weaponx> (raw)
In-Reply-To: <487267D8.5010605@linux.vnet.ibm.com>

On Mon, 2008-07-07 at 14:00 -0500, torez wrote:
> plain text document attachment (Indications oprofile in compact
> mode.txt)

Please don't send patches at attachments.

> This patch allows Performance monitoring driver to detect when
> operating in PowerPC compliance mode.

And why is that needed?  The reason should be included in the changelog
for the patch.

> use patch -p0 to apply.

This seems wrong.  The patch looks like a -p1 to me.

You're missing your Signed-off-by line.  See
Documentation/SubmittingPatches.

> 
> ==========================================================================
> diff -urN linux-2.6.26-rc7.orig/arch/powerpc/kernel/cputable.c linux-2.6.26-rc7/arch/powerpc/kernel/cputable.c
> --- linux-2.6.26-rc7.orig/arch/powerpc/kernel/cputable.c	2008-07-07 11:37:40.000000000 -0500
> +++ linux-2.6.26-rc7/arch/powerpc/kernel/cputable.c	2008-07-07 11:27:09.000000000 -0500
> @@ -352,6 +352,7 @@
>  		.icache_bsize		= 128,
>  		.dcache_bsize		= 128,
>  		.machine_check		= machine_check_generic,
> +		.oprofile_cpu_type	= "ppc64/compat-power5+",
>  		.platform		= "power5+",
>  	},
>  	{	/* Power6 */
> @@ -383,6 +384,7 @@
>  		.icache_bsize		= 128,
>  		.dcache_bsize		= 128,
>  		.machine_check		= machine_check_generic,
> +		.oprofile_cpu_type	= "ppc64/compat-power6",
>  		.platform		= "power6",
>  	},
>  	{	/* 2.06-compliant processor, i.e. Power7 "architected" mode */
> @@ -394,6 +396,7 @@
>  		.icache_bsize		= 128,
>  		.dcache_bsize		= 128,
>  		.machine_check		= machine_check_generic,
> +		.oprofile_cpu_type	= "ppc64/compat-power7",
>  		.platform		= "power7",
>  	},
>  	{	/* Power7 */
> @@ -1593,6 +1596,12 @@
>  			 * from the real PVR with a new value obtained
>  			 * using a logical PVR value, don't modify the
>  			 * performance monitor fields.
> +			 * The performance monitor sub-system needs to have
> +			 * access to the values from the real PVR, but, at 
> +			 * the same time it needs to be aware it may be running
> +			 * in compatibility mode. We we are changing the values
                                                When ^ ?

> +			 * for the real PVR to those of the compatibility PVR,
> +			 * change the oprofile_cpu_type field as well.

You might want to change the original comment to not say "...don't
modify the performance monitor fields."  Your addition explains why, but
it doesn't flow well with the original comment.

josh

      reply	other threads:[~2008-07-07 20:38 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-07 19:00 indications for oprofile in compact mode torez
2008-07-07 20:37 ` Josh Boyer [this message]

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=1215463072.20774.63.camel@weaponx \
    --to=jwboyer@linux.vnet.ibm.com \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=lnxtorez@linux.vnet.ibm.com \
    /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).