All of lore.kernel.org
 help / color / mirror / Atom feed
From: Scott Wood <scottwood@freescale.com>
To: David Miller <davem@davemloft.net>
Cc: proski@gnu.org, a.p.zijlstra@chello.nl, sandmann@redhat.com,
	pq@iki.fi, linux-kernel@vger.kernel.org, rostedt@goodmis.org,
	linuxppc-dev@ozlabs.org, srostedt@redhat.com, paulus@samba.org,
	mingo@elte.hu
Subject: Re: [PATCH 2/2] ftrace: support for PowerPC
Date: Thu, 15 May 2008 11:48:02 -0500	[thread overview]
Message-ID: <20080515164802.GA2664@loki.buserror.net> (raw)
In-Reply-To: <20080514.222857.246967279.davem@davemloft.net>

On Wed, May 14, 2008 at 10:28:57PM -0700, David Miller wrote:
> From: Steven Rostedt <rostedt@goodmis.org>
> Date: Wed, 14 May 2008 23:49:44 -0400
> 
> > +#ifdef CONFIG_FTRACE
> > +#ifdef CONFIG_DYNAMIC_FTRACE
> > +_GLOBAL(mcount)
> > +_GLOBAL(_mcount)
> > +	stwu	r1,-48(r1)
> > +	stw	r3, 12(r1)
> > +	stw	r4, 16(r1)
> > +	stw	r5, 20(r1)
> > +	stw	r6, 24(r1)
> > +	mflr	r3
> > +	stw	r7, 28(r1)
> > +	mfcr	r5
> > +	stw	r8, 32(r1)
> > +	stw	r9, 36(r1)
> > +	stw	r10,40(r1)
> > +	stw	r3, 44(r1)
> > +	stw	r5, 8(r1)
> 
> Yikes, that's really expensive.
> 
> Can't you do a tail call and let the function you end
> up calling do all the callee-saved register pops onto
> the stack?

The PPC32 ABI seems to (unfortunately) suggest that, with mcount, all
registers are callee-saved (except for the modifiable-during-function-linkage
registers like r0, r11, and r12) -- so mcount has to save the registers that
the callee won't (because they're normally volatile).

-Scott

WARNING: multiple messages have this Message-ID (diff)
From: Scott Wood <scottwood@freescale.com>
To: David Miller <davem@davemloft.net>
Cc: rostedt@goodmis.org, proski@gnu.org, a.p.zijlstra@chello.nl,
	pq@iki.fi, linux-kernel@vger.kernel.org, srostedt@redhat.com,
	linuxppc-dev@ozlabs.org, sandmann@redhat.com, paulus@samba.org,
	mingo@elte.hu
Subject: Re: [PATCH 2/2] ftrace: support for PowerPC
Date: Thu, 15 May 2008 11:48:02 -0500	[thread overview]
Message-ID: <20080515164802.GA2664@loki.buserror.net> (raw)
In-Reply-To: <20080514.222857.246967279.davem@davemloft.net>

On Wed, May 14, 2008 at 10:28:57PM -0700, David Miller wrote:
> From: Steven Rostedt <rostedt@goodmis.org>
> Date: Wed, 14 May 2008 23:49:44 -0400
> 
> > +#ifdef CONFIG_FTRACE
> > +#ifdef CONFIG_DYNAMIC_FTRACE
> > +_GLOBAL(mcount)
> > +_GLOBAL(_mcount)
> > +	stwu	r1,-48(r1)
> > +	stw	r3, 12(r1)
> > +	stw	r4, 16(r1)
> > +	stw	r5, 20(r1)
> > +	stw	r6, 24(r1)
> > +	mflr	r3
> > +	stw	r7, 28(r1)
> > +	mfcr	r5
> > +	stw	r8, 32(r1)
> > +	stw	r9, 36(r1)
> > +	stw	r10,40(r1)
> > +	stw	r3, 44(r1)
> > +	stw	r5, 8(r1)
> 
> Yikes, that's really expensive.
> 
> Can't you do a tail call and let the function you end
> up calling do all the callee-saved register pops onto
> the stack?

The PPC32 ABI seems to (unfortunately) suggest that, with mcount, all
registers are callee-saved (except for the modifiable-during-function-linkage
registers like r0, r11, and r12) -- so mcount has to save the registers that
the callee won't (because they're normally volatile).

-Scott

  parent reply	other threads:[~2008-05-15 16:49 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-15  3:49 [PATCH 0/2] ftrace ported to PPC Steven Rostedt
2008-05-15  3:49 ` Steven Rostedt
2008-05-15  3:49 ` [PATCH 1/2] ftrace ppc: add irqs_disabled_flags to ppc Steven Rostedt
2008-05-15  3:49   ` Steven Rostedt
2008-05-16 12:05   ` Ingo Molnar
2008-05-16 12:05     ` Ingo Molnar
2008-05-15  3:49 ` [PATCH 2/2] ftrace: support for PowerPC Steven Rostedt
2008-05-15  3:49   ` Steven Rostedt
2008-05-15  5:28   ` David Miller
2008-05-15  5:28     ` David Miller
2008-05-15 13:38     ` Steven Rostedt
2008-05-15 13:38       ` Steven Rostedt
2008-05-15 16:48     ` Scott Wood [this message]
2008-05-15 16:48       ` Scott Wood
2008-05-16 12:06   ` Ingo Molnar
2008-05-16 12:06     ` Ingo Molnar
2008-05-20 14:04   ` Michael Ellerman
2008-05-20 14:04     ` Michael Ellerman
2008-05-20 14:17     ` Benjamin Herrenschmidt
2008-05-20 14:17       ` Benjamin Herrenschmidt
2008-05-20 14:51       ` Steven Rostedt
2008-05-20 14:51         ` Steven Rostedt
2008-05-20 14:32     ` Steven Rostedt
2008-05-20 14:32       ` Steven Rostedt
2008-05-22 18:31     ` [PATCH] ftrace: powerpc clean ups Steven Rostedt
2008-05-22 18:31       ` Steven Rostedt
2008-05-27 15:36       ` Thomas Gleixner
2008-05-27 15:36         ` Thomas Gleixner
2008-06-02  2:15       ` Michael Ellerman
2008-06-02  2:15         ` Michael Ellerman
2008-05-15  4:40 ` [PATCH 0/2] ftrace ported to PPC Paul Mackerras
2008-05-15  4:40   ` Paul Mackerras
2008-05-16 12:05   ` Ingo Molnar
2008-05-16 12:05     ` Ingo Molnar

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=20080515164802.GA2664@loki.buserror.net \
    --to=scottwood@freescale.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=pq@iki.fi \
    --cc=proski@gnu.org \
    --cc=rostedt@goodmis.org \
    --cc=sandmann@redhat.com \
    --cc=srostedt@redhat.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 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.