All of lore.kernel.org
 help / color / mirror / Atom feed
From: Anton Vorontsov <avorontsov@ru.mvista.com>
To: Steven Rostedt <srostedt@redhat.com>, Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>,
	linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org
Subject: [PATCH] ftrace: On PowerPC we don't need frame pointers for CALLER_ADDRs
Date: Sat, 31 Jan 2009 22:06:50 +0300	[thread overview]
Message-ID: <20090131190650.GA4284@oksana.dev.rtsoft.ru> (raw)

According to this discussion:

http://lkml.org/lkml/2008/7/25/338
http://lkml.org/lkml/2008/7/26/72

Frame pointers do nothing useful on PowerPC, so lib/Kconfig.debug
makes CONFIG_FRAME_POINTER unselectable on PPC targets. But ftrace.h
requires CONFIG_FRAME_POINTER for CALLER_ADDR macros. Therefore
tracing is completely useless on PowerPC:

[...]
  <idle>-0       0X.h3    2us+:      0:140:R   + [000]  1733:120:S mvtsd
  <idle>-0       0X.h3    9us+: 0 (0)
  <idle>-0       0X..3   72us : 0 (0)
  <idle>-0       0X..3   73us :      0:140:R ==> [000]  1733:120:R mvtsd

On PPC we can safely use __builtin_return_address(1..6) w/o frame
pointers, and with this patch the trace output looks OK:

[...]
  <idle>-0       0X.h3    2us+:      0:140:R   + [000]  1740:120:S mvtsd
  <idle>-0       0X.h3    9us+: hrtimer_wakeup (__run_hrtimer)
  <idle>-0       0X..3   87us : cpu_idle (__got2_end)
  <idle>-0       0X..3   89us :      0:140:R ==> [000]  1740:120:R mvtsd

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
---

Btw, on PowerPC tracing is also broken w/o "ring-buffer: fix alignment
problem" patch (currently collecting dust in the -tip tree, commit
082605de5f82eb692cc90f7fda071cc01bb5ac34). Any chance the fix go into
Linus' tree, to not waste other people's time bisecting and debugging
the problem? ;-)

For google: tracing, regression, "ring-buffer: move some metadata
into buffer page", commit abc9b56d66fbd4d93302ef4bf6fa726e1b8255f9,
answer is here.

 include/linux/ftrace.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9c5bc6b..13eba02 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -146,7 +146,7 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifdef CONFIG_FRAME_POINTER
+#if defined(CONFIG_FRAME_POINTER) || defined(CONFIG_PPC)
 /* TODO: need to fix this for ARM */
 # define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
 # define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-- 
1.5.6.5

WARNING: multiple messages have this Message-ID (diff)
From: Anton Vorontsov <avorontsov@ru.mvista.com>
To: Steven Rostedt <srostedt@redhat.com>, Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	linuxppc-dev@ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH] ftrace: On PowerPC we don't need frame pointers for CALLER_ADDRs
Date: Sat, 31 Jan 2009 22:06:50 +0300	[thread overview]
Message-ID: <20090131190650.GA4284@oksana.dev.rtsoft.ru> (raw)

According to this discussion:

http://lkml.org/lkml/2008/7/25/338
http://lkml.org/lkml/2008/7/26/72

Frame pointers do nothing useful on PowerPC, so lib/Kconfig.debug
makes CONFIG_FRAME_POINTER unselectable on PPC targets. But ftrace.h
requires CONFIG_FRAME_POINTER for CALLER_ADDR macros. Therefore
tracing is completely useless on PowerPC:

[...]
  <idle>-0       0X.h3    2us+:      0:140:R   + [000]  1733:120:S mvtsd
  <idle>-0       0X.h3    9us+: 0 (0)
  <idle>-0       0X..3   72us : 0 (0)
  <idle>-0       0X..3   73us :      0:140:R ==> [000]  1733:120:R mvtsd

On PPC we can safely use __builtin_return_address(1..6) w/o frame
pointers, and with this patch the trace output looks OK:

[...]
  <idle>-0       0X.h3    2us+:      0:140:R   + [000]  1740:120:S mvtsd
  <idle>-0       0X.h3    9us+: hrtimer_wakeup (__run_hrtimer)
  <idle>-0       0X..3   87us : cpu_idle (__got2_end)
  <idle>-0       0X..3   89us :      0:140:R ==> [000]  1740:120:R mvtsd

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
---

Btw, on PowerPC tracing is also broken w/o "ring-buffer: fix alignment
problem" patch (currently collecting dust in the -tip tree, commit
082605de5f82eb692cc90f7fda071cc01bb5ac34). Any chance the fix go into
Linus' tree, to not waste other people's time bisecting and debugging
the problem? ;-)

For google: tracing, regression, "ring-buffer: move some metadata
into buffer page", commit abc9b56d66fbd4d93302ef4bf6fa726e1b8255f9,
answer is here.

 include/linux/ftrace.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9c5bc6b..13eba02 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -146,7 +146,7 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifdef CONFIG_FRAME_POINTER
+#if defined(CONFIG_FRAME_POINTER) || defined(CONFIG_PPC)
 /* TODO: need to fix this for ARM */
 # define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
 # define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-- 
1.5.6.5

             reply	other threads:[~2009-01-31 19:06 UTC|newest]

Thread overview: 106+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-31 19:06 Anton Vorontsov [this message]
2009-01-31 19:06 ` [PATCH] ftrace: On PowerPC we don't need frame pointers for CALLER_ADDRs Anton Vorontsov
2009-02-02  0:35 ` Benjamin Herrenschmidt
2009-02-02  0:35   ` Benjamin Herrenschmidt
2009-02-02 14:04   ` Steven Rostedt
2009-02-02 14:04     ` Steven Rostedt
2009-02-03 14:56     ` [PATCH v2] " Anton Vorontsov
2009-02-03 14:56       ` Anton Vorontsov
2009-02-03 16:06       ` Ingo Molnar
2009-02-03 16:06         ` Ingo Molnar
2009-02-03 16:19         ` Anton Vorontsov
2009-02-03 16:19           ` Anton Vorontsov
2009-02-03 16:32           ` Steven Rostedt
2009-02-03 16:32             ` Steven Rostedt
2009-02-03 18:59             ` Anton Vorontsov
2009-02-03 18:59               ` Anton Vorontsov
2009-02-04  0:34               ` Benjamin Herrenschmidt
2009-02-04  0:34                 ` Benjamin Herrenschmidt
2009-02-04 15:07           ` Anton Vorontsov
2009-02-04 15:07             ` Anton Vorontsov
2009-02-04 15:08             ` [PATCH 1/3] Makefile: Include arch Makefiles as late as possible Anton Vorontsov
2009-02-04 15:08               ` Anton Vorontsov
2009-02-04 15:08               ` Anton Vorontsov
2009-02-04 21:26               ` Ingo Molnar
2009-02-04 21:26               ` Ingo Molnar
2009-02-04 21:26               ` Ingo Molnar
2009-02-04 21:26               ` Ingo Molnar
2009-02-04 21:26                 ` Ingo Molnar
2009-02-11  3:51                 ` Benjamin Herrenschmidt
2009-02-11  3:51                 ` Benjamin Herrenschmidt
2009-02-11  3:51                 ` Benjamin Herrenschmidt
2009-02-11  3:51                   ` Benjamin Herrenschmidt
2009-02-11 13:23                   ` Ingo Molnar
2009-02-11 13:23                     ` Ingo Molnar
2009-02-11 14:11                     ` Steven Rostedt
2009-02-11 14:11                       ` Steven Rostedt
2009-02-11 14:11                     ` Steven Rostedt
2009-02-11 14:11                     ` Steven Rostedt
2009-02-11 14:11                     ` Steven Rostedt
2009-02-14 19:58                   ` Sam Ravnborg
2009-02-14 19:58                     ` Sam Ravnborg
2009-02-11  3:51                 ` Benjamin Herrenschmidt
2009-02-14 19:57                 ` Sam Ravnborg
2009-02-14 19:57                   ` Sam Ravnborg
2009-02-14 22:03                   ` Ingo Molnar
2009-02-14 22:03                     ` Ingo Molnar
2009-02-15  0:19                     ` Benjamin Herrenschmidt
2009-02-15  0:19                     ` Benjamin Herrenschmidt
2009-02-15  0:19                     ` Benjamin Herrenschmidt
2009-02-15  0:19                     ` Benjamin Herrenschmidt
2009-02-15  0:19                       ` Benjamin Herrenschmidt
2009-02-15  8:09                       ` Ingo Molnar
2009-02-15  8:09                         ` Ingo Molnar
2009-02-16 14:20                   ` Anton Vorontsov
2009-02-16 14:20                     ` Anton Vorontsov
2009-02-16 14:20                     ` Anton Vorontsov
2009-02-16 14:53                     ` Anton Vorontsov
2009-02-16 14:53                       ` Anton Vorontsov
2009-02-16 20:04                       ` Sam Ravnborg
2009-02-16 20:04                         ` Sam Ravnborg
2009-02-16 16:08                     ` Anton Vorontsov
2009-02-16 16:08                       ` Anton Vorontsov
2009-02-16 17:22                       ` Ingo Molnar
2009-02-16 17:22                         ` Ingo Molnar
2009-02-04 15:08             ` [PATCH 2/3] powerpc: Make it possible to safely select CONFIG_FRAME_POINTER Anton Vorontsov
2009-02-04 15:08               ` Anton Vorontsov
2009-02-05  0:31               ` Benjamin Herrenschmidt
2009-02-05  0:31               ` Benjamin Herrenschmidt
2009-02-05  0:31               ` Benjamin Herrenschmidt
2009-02-05  0:31               ` Benjamin Herrenschmidt
2009-02-05  0:31                 ` Benjamin Herrenschmidt
2009-02-05  0:35                 ` Steven Rostedt
2009-02-05  0:35                   ` Steven Rostedt
2009-02-05  1:12                   ` Anton Vorontsov
2009-02-05  1:12                     ` Anton Vorontsov
2009-02-05  1:15                   ` Benjamin Herrenschmidt
2009-02-05  1:15                   ` Benjamin Herrenschmidt
2009-02-05  1:15                   ` Benjamin Herrenschmidt
2009-02-05  1:15                   ` Benjamin Herrenschmidt
2009-02-05  1:15                     ` Benjamin Herrenschmidt
2009-02-05  1:15                     ` Benjamin Herrenschmidt
2009-02-05  1:30                     ` Anton Vorontsov
2009-02-05  1:30                       ` Anton Vorontsov
2009-02-05 15:45                       ` Anton Vorontsov
2009-02-05 15:45                         ` Anton Vorontsov
2009-02-04 15:08             ` [PATCH 3/3] tracing: Tracers that use CALLER_ADDR macros should select FRAME_POINTER Anton Vorontsov
2009-02-04 15:08               ` Anton Vorontsov
2009-02-04 15:26               ` Frédéric Weisbecker
2009-02-04 15:26                 ` Frédéric Weisbecker
2009-02-04 15:26                 ` Frédéric Weisbecker
2009-02-04 15:31                 ` Steven Rostedt
2009-02-04 15:31                 ` Steven Rostedt
2009-02-04 15:31                 ` Steven Rostedt
2009-02-04 15:31                   ` Steven Rostedt
2009-02-04 15:31                   ` Steven Rostedt
2009-02-04 15:31                 ` Steven Rostedt
2009-02-04 15:36                 ` Anton Vorontsov
2009-02-04 15:36                   ` Anton Vorontsov
2009-02-04 15:36                   ` Anton Vorontsov
2009-02-04 16:50                   ` Frédéric Weisbecker
2009-02-04 16:50                     ` Frédéric Weisbecker
2009-02-04 16:50                     ` Frédéric Weisbecker
2009-02-04  8:17       ` [PATCH v2] ftrace: On PowerPC we don't need frame pointers forCALLER_ADDRs Usha Rani Konudula
2009-02-04  8:17         ` Usha Rani Konudula
2009-02-04  8:37         ` Usha Rani Konudula
2009-02-04  8:37           ` Usha Rani Konudula

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=20090131190650.GA4284@oksana.dev.rtsoft.ru \
    --to=avorontsov@ru.mvista.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --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.