<?xml version="1.0" encoding="UTF-8" standalone="yes" ?>
<!DOCTYPE bugzilla SYSTEM "https://bugzilla.yoctoproject.org/page.cgi?id=bugzilla.dtd">

<bugzilla version="5.0.6"
          urlbase="https://bugzilla.yoctoproject.org/"
          
          maintainer="it-coreprojects-helpdesk@linuxfoundation.org"
>

    <bug>
          <bug_id>4511</bug_id>
          
          <creation_ts>2013-05-18 11:23:53 +0000</creation_ts>
          <short_desc>error for using oprofile.ko to profiling</short_desc>
          <delta_ts>2014-05-27 12:43:01 +0000</delta_ts>
          <reporter_accessible>1</reporter_accessible>
          <cclist_accessible>1</cclist_accessible>
          <classification_id>7</classification_id>
          <classification>Build System, Metadata &amp; Runtime</classification>
          <product>BSPs</product>
          <component>bsps-meta-fsl-arm</component>
          <version>1.5</version>
          <rep_platform>Other</rep_platform>
          <op_sys>arm</op_sys>
          <bug_status>RESOLVED</bug_status>
          <resolution>WONTFIX</resolution>
          
          
          <bug_file_loc></bug_file_loc>
          <status_whiteboard></status_whiteboard>
          <keywords></keywords>
          <priority>Low</priority>
          <bug_severity>normal</bug_severity>
          <target_milestone>1.5 M3</target_milestone>
          
          
          <everconfirmed>1</everconfirmed>
          <reporter name="jojo">rjiejie</reporter>
          <assigned_to name="Daiane">angolini</assigned_to>
          <cc>otavio</cc>
    
    <cc>umar</cc>
          
          
          <cf_os>---</cf_os>
          <cf_regression_type>New (Never tested)</cf_regression_type>
          
          <cf_docchange>Yes (doc changes required)</cf_docchange>

      

      

      

          <comment_sort_order>oldest_to_newest</comment_sort_order>  
          <long_desc isprivate="0" >
    <commentid>33143</commentid>
    <comment_count>0</comment_count>
    <who name="jojo">rjiejie</who>
    <bug_when>2013-05-18 11:23:53 +0000</bug_when>
    <thetext>Hi,
	I use the oprofile to measured the performance of my application, there something wrong to use the oprofile.ko as following in yocto &quot;dylan&quot;:

	It&apos;s known issue or bug ?

root@imx6qsabresd:~# opcontrol --start --separate=lib --no-vmlinux -c 5
oprofile: using arm/armv7-ca9
ATTENTION: Use of opcontrol is discouraged.  Please see the man page for operf.
Detected stale lock file. Removing.
Using default event: CPU_CYCLES:100000:0:1:1
Using 2.6+ OProfile kernel interface.
Using log file /var/lib/oprofile/samples/oprofiled.log
Daemon started.
irq 126: nobody cared (try booting with the &quot;irqpoll&quot; option)
[&lt;800478f0&gt;] (unwind_backtrace+0x0/0xf8) from [&lt;800b08e4&gt;] (__report_bad_irq+0x24/0xc0)
[&lt;800b08e4&gt;] (__report_bad_irq+0x24/0xc0) from [&lt;800b0c2c&gt;] (note_interrupt+0x1ec/0x248)
[&lt;800b0c2c&gt;] (note_interrupt+0x1ec/0x248) from [&lt;800af168&gt;] (handle_irq_event_percpu+0xa8/0x180)
[&lt;800af168&gt;] (handle_irq_event_percpu+0xa8/0x180) from [&lt;800af27c&gt;] (handle_irq_event+0x3c/0x5c)
[&lt;800af27c&gt;] (handle_irq_event+0x3c/0x5c) from [&lt;800b15f0&gt;] (handle_fasteoi_irq+0x98/0x158)
[&lt;800b15f0&gt;] (handle_fasteoi_irq+0x98/0x158) from [&lt;800aea68&gt;] (generic_handle_irq+0x20/0x34)
[&lt;800aea68&gt;] (generic_handle_irq+0x20/0x34) from [&lt;800419b0&gt;] (handle_IRQ+0x4c/0xb0)
[&lt;800419b0&gt;] (handle_IRQ+0x4c/0xb0) from [&lt;80040b4c&gt;] (__irq_svc+0x4c/0xe8)
[&lt;80040b4c&gt;] (__irq_svc+0x4c/0xe8) from [&lt;80079618&gt;] (__do_softirq+0x50/0x150)
[&lt;80079618&gt;] (__do_softirq+0x50/0x150) from [&lt;80079ba0&gt;] (irq_exit+0x94/0x9c)
[&lt;80079ba0&gt;] (irq_exit+0x94/0x9c) from [&lt;8003b1c8&gt;] (do_local_timer+0x70/0x94)
[&lt;8003b1c8&gt;] (do_local_timer+0x70/0x94) from [&lt;80040b4c&gt;] (__irq_svc+0x4c/0xe8)
Exception stack(0xba99bd68 to 0xba99bdb0)
bd60:                   bf1b5800 bf1b6000 00000020 0000001f bf4ac000 bf1b5000
bd80: 2ad3e000 8bfe36a0 0004f4ac ba954ab0 bac5aea0 00000002 00000000 ba99bdb0
bda0: 8004dc08 8004dad0 800f0113 ffffffff
[&lt;80040b4c&gt;] (__irq_svc+0x4c/0xe8) from [&lt;8004dad0&gt;] (v7_flush_kern_dcache_area+0x28/0x3c)
[&lt;8004dad0&gt;] (v7_flush_kern_dcache_area+0x28/0x3c) from [&lt;8004dc08&gt;] (v6_copy_user_highpage_nonaliasing+0x40/0x54)
[&lt;8004dc08&gt;] (v6_copy_user_highpage_nonaliasing+0x40/0x54) from [&lt;800dc8d8&gt;] (do_wp_page+0xe4/0x72c)
[&lt;800dc8d8&gt;] (do_wp_page+0xe4/0x72c) from [&lt;800de8d8&gt;] (handle_pte_fault+0x3b0/0x7d8)
[&lt;800de8d8&gt;] (handle_pte_fault+0x3b0/0x7d8) from [&lt;800dedd0&gt;] (handle_mm_fault+0xd0/0x120)
[&lt;800dedd0&gt;] (handle_mm_fault+0xd0/0x120) from [&lt;8004b3a0&gt;] (do_page_fault+0x18c/0x2f8)
[&lt;8004b3a0&gt;] (do_page_fault+0x18c/0x2f8) from [&lt;8003b370&gt;] (do_DataAbort+0x34/0x98)
[&lt;8003b370&gt;] (do_DataAbort+0x34/0x98) from [&lt;80041084&gt;] (ret_from_exception+0x0/0x10)
Exception stack(0xba99bfb0 to 0xba99bff8)
bfa0:                                     00000328 00000000 00000000 0000029d
bfc0: 00000328 00000000 47f01400 00000078 2ad3e4c0 0016b948 0000029d 7ee649c4
bfe0: 00000000 7ee649a8 2ad3e000 47e6bf20 600f0010 ffffffff
handlers:
[&lt;80049c24&gt;] armv7pmu_handle_irq
Disabling IRQ #126
Profiler running.

root@imx6qsabresd:~# testprogram

root@imx6qsabresd:~# opcontrol --stop
Stopping profiling.
root@imx6qsabresd:~# opreport -l testprogram &gt; ~/imx6.op.txt
Using /var/lib/oprofile/samples/ for samples directory.
error: no sample files found: profile specification too strict ?</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>34653</commentid>
    <comment_count>1</comment_count>
    <who name="Umar">umar</who>
    <bug_when>2013-07-17 23:03:19 +0000</bug_when>
    <thetext>I am getting the same error.  I cross compiled oprofile 0.9.8 and upon running operf, I get this crash:
 
irq 126: nobody cared (try booting with the &quot;irqpoll&quot; option)
[&lt;80048854&gt;] (unwind_backtrace+0x0/0xf8) from [&lt;800acf20&gt;] (__report_bad_irq+0x28/0xc4)
[&lt;800acf20&gt;] (__report_bad_irq+0x28/0xc4) from [&lt;800ad264&gt;] (note_interrupt+0x1e4/0x240)
[&lt;800ad264&gt;] (note_interrupt+0x1e4/0x240) from [&lt;800ab7b0&gt;] (handle_irq_event_percpu+0xa8/0x180)
[&lt;800ab7b0&gt;] (handle_irq_event_percpu+0xa8/0x180) from [&lt;800ab8c4&gt;] (handle_irq_event+0x3c/0x5c)
[&lt;800ab8c4&gt;] (handle_irq_event+0x3c/0x5c) from [&lt;800adc48&gt;] (handle_fasteoi_irq+0xbc/0x154)
[&lt;800adc48&gt;] (handle_fasteoi_irq+0xbc/0x154) from [&lt;800ab0c0&gt;] (generic_handle_irq+0x28/0x3c)
[&lt;800ab0c0&gt;] (generic_handle_irq+0x28/0x3c) from [&lt;80042870&gt;] (handle_IRQ+0x4c/0xac)
[&lt;80042870&gt;] (handle_IRQ+0x4c/0xac) from [&lt;80041a0c&gt;] (__irq_svc+0x4c/0xe8)
[&lt;80041a0c&gt;] (__irq_svc+0x4c/0xe8) from [&lt;80106c94&gt;] (sys_select+0xc4/0x10c)
[&lt;80106c94&gt;] (sys_select+0xc4/0x10c) from [&lt;80041fc0&gt;] (ret_fast_syscall+0x0/0x30)
handlers:
[&lt;8004ab24&gt;] armv7pmu_handle_irq
Disabling IRQ #126
 
My hardware is SabreSD with i.MX6Q and 4.0.0 Linux BSP.
I was really hoping to profile my app to see where I need to optimize.  Is there a fix/workaround for this? 
 
Please advise.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>34654</commentid>
    <comment_count>2</comment_count>
    <who name="Otavio Salvador">otavio</who>
    <bug_when>2013-07-18 00:36:56 +0000</bug_when>
    <thetext>I don&apos;t have any know workaround or fix for this;  Daiane, do you know if it is a new or a known issue?</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>36288</commentid>
    <comment_count>3</comment_count>
    <who name="Otavio Salvador">otavio</who>
    <bug_when>2013-09-04 19:42:42 +0000</bug_when>
    <thetext>It is a known issue and must to be documented.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>37018</commentid>
    <comment_count>4</comment_count>
    <who name="Daiane">angolini</who>
    <bug_when>2013-09-20 13:31:12 +0000</bug_when>
    <thetext>https://community.freescale.com/message/302071#302071
https://community.freescale.com/thread/307450

The error is described on ERR006259

The proposed workaround is:

Symbol: HW_PERF_EVENTS [=y]
  │ Type  : boolean  
  │ Prompt: Enable hardware performance counter support for perf events
  │   Defined at arch/arm/Kconfig:1582 
  │   Depends on: PERF_EVENTS [=y] &amp;&amp; CPU_HAS_PMU [=y]
  │   Location: 
  │     -&gt; Kernel Features</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>43599</commentid>
    <comment_count>5</comment_count>
    <who name="Daiane">angolini</who>
    <bug_when>2014-05-27 12:06:20 +0000</bug_when>
    <thetext>It´s not going to be fixed because there is no fix, only a workaround.

I´m &quot;ACCEPTING&quot; this, if anything else should be added in future, it can be reopened or changed on demand.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>43600</commentid>
    <comment_count>6</comment_count>
    <who name="Otavio Salvador">otavio</who>
    <bug_when>2014-05-27 12:43:01 +0000</bug_when>
    <thetext>I changed it to won&apos;t fix.</thetext>
  </long_desc>
      
      

    </bug>

</bugzilla>