<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/arch/arm/include/asm/perf_event.h, branch v4.10</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>arm: perf: Fix callchain parse error with kernel tracepoint events</title>
<updated>2015-05-27T15:12:05+00:00</updated>
<author>
<name>Hou Pengyang</name>
<email>houpengyang@huawei.com</email>
</author>
<published>2015-05-08T05:43:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=b3eac0265bf6258f08dcd4ac7fa7f87cc050defc'/>
<id>b3eac0265bf6258f08dcd4ac7fa7f87cc050defc</id>
<content type='text'>
For ARM, when tracing with tracepoint events, the IP and cpsr are set
to 0, preventing the perf code parsing the callchain and resolving the
symbols correctly.

 ./perf record -e sched:sched_switch -g --call-graph dwarf ls
    [ perf record: Captured and wrote 0.006 MB perf.data ]
 ./perf report -f
    Samples: 5  of event 'sched:sched_switch', Event count (approx.): 5
    Children      Self    Command  Shared Object     Symbol
    100.00%       100.00%  ls       [unknown]         [.] 00000000

The fix is to implement perf_arch_fetch_caller_regs for ARM, which fills
several necessary registers used for callchain unwinding, including pc,sp,
fp and cpsr.

With this patch, callchain can be parsed correctly as :

   .....
-  100.00%   100.00%  ls       [kernel.kallsyms]  [k] __sched_text_start
   + __sched_text_start
+   20.00%     0.00%  ls       libc-2.18.so       [.] _dl_addr
+   20.00%     0.00%  ls       libc-2.18.so       [.] write
   .....

Jean Pihet found this in ARM and come up with a patch:
http://thread.gmane.org/gmane.linux.kernel/1734283/focus=1734280

This patch rewrite Jean's patch in C.

Signed-off-by: Hou Pengyang &lt;houpengyang@huawei.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
For ARM, when tracing with tracepoint events, the IP and cpsr are set
to 0, preventing the perf code parsing the callchain and resolving the
symbols correctly.

 ./perf record -e sched:sched_switch -g --call-graph dwarf ls
    [ perf record: Captured and wrote 0.006 MB perf.data ]
 ./perf report -f
    Samples: 5  of event 'sched:sched_switch', Event count (approx.): 5
    Children      Self    Command  Shared Object     Symbol
    100.00%       100.00%  ls       [unknown]         [.] 00000000

The fix is to implement perf_arch_fetch_caller_regs for ARM, which fills
several necessary registers used for callchain unwinding, including pc,sp,
fp and cpsr.

With this patch, callchain can be parsed correctly as :

   .....
-  100.00%   100.00%  ls       [kernel.kallsyms]  [k] __sched_text_start
   + __sched_text_start
+   20.00%     0.00%  ls       libc-2.18.so       [.] _dl_addr
+   20.00%     0.00%  ls       libc-2.18.so       [.] write
   .....

Jean Pihet found this in ARM and come up with a patch:
http://thread.gmane.org/gmane.linux.kernel/1734283/focus=1734280

This patch rewrite Jean's patch in C.

Signed-off-by: Hou Pengyang &lt;houpengyang@huawei.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm: perf: factor out callchain code</title>
<updated>2014-10-30T12:16:58+00:00</updated>
<author>
<name>Mark Rutland</name>
<email>mark.rutland@arm.com</email>
</author>
<published>2014-09-29T16:15:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=d39976f0fd144d1cef4830d696e2a1e6d8058dc6'/>
<id>d39976f0fd144d1cef4830d696e2a1e6d8058dc6</id>
<content type='text'>
The ARM callchain handling code is currently bundled with the ARM PMU
management code, despite the two having no dependency on each other.
This bundling has the unfortunate property of making callchain handling
depend on CONFIG_HW_PERF_EVENTS, even though the callchain handling
could be applied to software events in the absence of PMU hardware
support.

This patch separates the two, placing the callchain handling in
perf_callchain.c and making it depend on CONFIG_PERF_EVENTS rather than
CONFIG_HW_PERF_EVENTS, enabling callchain recording on kernels built
without hardware perf event support.

Signed-off-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Reviewed-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The ARM callchain handling code is currently bundled with the ARM PMU
management code, despite the two having no dependency on each other.
This bundling has the unfortunate property of making callchain handling
depend on CONFIG_HW_PERF_EVENTS, even though the callchain handling
could be applied to software events in the absence of PMU hardware
support.

This patch separates the two, placing the callchain handling in
perf_callchain.c and making it depend on CONFIG_PERF_EVENTS rather than
CONFIG_HW_PERF_EVENTS, enabling callchain recording on kernels built
without hardware perf event support.

Signed-off-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Reviewed-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm: perf: move event map macros to pmu.h</title>
<updated>2014-07-02T14:46:37+00:00</updated>
<author>
<name>Mark Rutland</name>
<email>mark.rutland@arm.com</email>
</author>
<published>2014-05-28T17:08:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=ac8674dc0a8b97d564f293ae57cdf2d1e416b698'/>
<id>ac8674dc0a8b97d564f293ae57cdf2d1e416b698</id>
<content type='text'>
A few PMU-related macros are now looking a little lonely in
asm/perf_event.h now that all other PMU-specific structs, function
prototypes and macros live in pmu.h.

So as to make their placement consistent and to make it easier to build
atop of the current PMU functionality, let's reunite the entire family in
pmu.h

Acked-by: Will Deacon &lt;will.deacon@arm.com&gt;
Tested-by: Christopher Covington &lt;cov@codeaurora.org&gt;
Signed-off-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
A few PMU-related macros are now looking a little lonely in
asm/perf_event.h now that all other PMU-specific structs, function
prototypes and macros live in pmu.h.

So as to make their placement consistent and to make it easier to build
atop of the current PMU functionality, let's reunite the entire family in
pmu.h

Acked-by: Will Deacon &lt;will.deacon@arm.com&gt;
Tested-by: Christopher Covington &lt;cov@codeaurora.org&gt;
Signed-off-by: Mark Rutland &lt;mark.rutland@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>ARM: 7584/1: perf: fix link error when CONFIG_HW_PERF_EVENTS is not selected</title>
<updated>2012-11-23T13:01:30+00:00</updated>
<author>
<name>Marc Zyngier</name>
<email>Marc.Zyngier@arm.com</email>
</author>
<published>2012-11-22T12:05:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=c7cc504bc351e41e871e317ca7f032f4562f34ad'/>
<id>c7cc504bc351e41e871e317ca7f032f4562f34ad</id>
<content type='text'>
Commit e50c541 (ARM: perf: add guest vs host discrimination) broken the
link as perf_instruction_pointer and perf_misc_flags are not defined
when CONFIG_HW_PERF_EVENTS is not selected.

As it make little sense to try and profile a guest without any HW event,
just fallback to the original code when this config option is not selected.

Reported-by: Russell King &lt;linux@arm.linux.org.uk&gt;
Acked-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Commit e50c541 (ARM: perf: add guest vs host discrimination) broken the
link as perf_instruction_pointer and perf_misc_flags are not defined
when CONFIG_HW_PERF_EVENTS is not selected.

As it make little sense to try and profile a guest without any HW event,
just fallback to the original code when this config option is not selected.

Reported-by: Russell King &lt;linux@arm.linux.org.uk&gt;
Acked-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>ARM: perf: add guest vs host discrimination</title>
<updated>2012-11-09T11:37:24+00:00</updated>
<author>
<name>Marc Zyngier</name>
<email>Marc.Zyngier@arm.com</email>
</author>
<published>2012-09-13T15:40:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=e50c54189f7c6211a99539156e3978474f0b1a0b'/>
<id>e50c54189f7c6211a99539156e3978474f0b1a0b</id>
<content type='text'>
Add minimal guest support to perf, so it can distinguish whether
the PMU interrupt was in the host or the guest, as well as collecting
some very basic information (guest PC, user vs kernel mode).

This is not feature complete though, as it doesn't support backtracing
in the guest.

Based on the x86 implementation, tested with KVM/ARM.

Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add minimal guest support to perf, so it can distinguish whether
the PMU interrupt was in the host or the guest, as well as collecting
some very basic information (guest PC, user vs kernel mode).

This is not feature complete though, as it doesn't support backtracing
in the guest.

Based on the x86 implementation, tested with KVM/ARM.

Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>ARM: perf: prepare for moving CPU PMU code into separate file</title>
<updated>2012-08-23T10:35:52+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will.deacon@arm.com</email>
</author>
<published>2012-07-29T11:36:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=6dbc00297095122ea89e016ce6affad0b7c0ddac'/>
<id>6dbc00297095122ea89e016ce6affad0b7c0ddac</id>
<content type='text'>
The CPU PMU code is tightly coupled with generic ARM PMU handling code.
This makes it cumbersome when trying to add support for other ARM PMUs
(e.g. interconnect, L2 cache controller, bus) as the generic parts of
the code are not readily reusable.

This patch cleans up perf_event.c so that reusable code is exposed via
header files to other potential PMU drivers. The CPU code is
consistently named to identify it as such and also to prepare for moving
it into a separate file.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The CPU PMU code is tightly coupled with generic ARM PMU handling code.
This makes it cumbersome when trying to add support for other ARM PMUs
(e.g. interconnect, L2 cache controller, bus) as the generic parts of
the code are not readily reusable.

This patch cleans up perf_event.c so that reusable code is exposed via
header files to other potential PMU drivers. The CPU code is
consistently named to identify it as such and also to prepare for moving
it into a separate file.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>ARM: 7448/1: perf: remove arm_perf_pmu_ids global enumeration</title>
<updated>2012-07-09T16:41:10+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will.deacon@arm.com</email>
</author>
<published>2012-07-06T14:45:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=4295b898f5a5c7e62ae68e7a4ecc4b414622ffe6'/>
<id>4295b898f5a5c7e62ae68e7a4ecc4b414622ffe6</id>
<content type='text'>
In order to provide PMU name strings compatible with the OProfile
user ABI, an enumeration of all PMUs is currently used by perf to
identify each PMU uniquely. Unfortunately, this does not scale well
in the presence of multiple PMUs and creates a single, global namespace
across all PMUs in the system.

This patch removes the enumeration and instead uses the name string
for the PMU to map onto the OProfile variant. perf_pmu_name is
implemented for CPU PMUs, which is all that OProfile cares about anyway.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
In order to provide PMU name strings compatible with the OProfile
user ABI, an enumeration of all PMUs is currently used by perf to
identify each PMU uniquely. Unfortunately, this does not scale well
in the presence of multiple PMUs and creates a single, global namespace
across all PMUs in the system.

This patch removes the enumeration and instead uses the name string
for the PMU to map onto the OProfile variant. perf_pmu_name is
implemented for CPU PMUs, which is all that OProfile cares about anyway.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm</title>
<updated>2012-03-29T23:53:48+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2012-03-29T23:53:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=12679a2d7e3bfbdc7586e3e86d1ca90c46659363'/>
<id>12679a2d7e3bfbdc7586e3e86d1ca90c46659363</id>
<content type='text'>
Pull more ARM updates from Russell King.

This got a fair number of conflicts with the &lt;asm/system.h&gt; split, but
also with some other sparse-irq and header file include cleanups.  They
all looked pretty trivial, though.

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (59 commits)
  ARM: fix Kconfig warning for HAVE_BPF_JIT
  ARM: 7361/1: provide XIP_VIRT_ADDR for no-MMU builds
  ARM: 7349/1: integrator: convert to sparse irqs
  ARM: 7259/3: net: JIT compiler for packet filters
  ARM: 7334/1: add jump label support
  ARM: 7333/2: jump label: detect %c support for ARM
  ARM: 7338/1: add support for early console output via semihosting
  ARM: use set_current_blocked() and block_sigmask()
  ARM: exec: remove redundant set_fs(USER_DS)
  ARM: 7332/1: extract out code patch function from kprobes
  ARM: 7331/1: extract out insn generation code from ftrace
  ARM: 7330/1: ftrace: use canonical Thumb-2 wide instruction format
  ARM: 7351/1: ftrace: remove useless memory checks
  ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path
  ARM: Versatile Express: add NO_IOPORT
  ARM: get rid of asm/irq.h in asm/prom.h
  ARM: 7319/1: Print debug info for SIGBUS in user faults
  ARM: 7318/1: gic: refactor irq_start assignment
  ARM: 7317/1: irq: avoid NULL check in for_each_irq_desc loop
  ARM: 7315/1: perf: add support for the Cortex-A7 PMU
  ...
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull more ARM updates from Russell King.

This got a fair number of conflicts with the &lt;asm/system.h&gt; split, but
also with some other sparse-irq and header file include cleanups.  They
all looked pretty trivial, though.

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (59 commits)
  ARM: fix Kconfig warning for HAVE_BPF_JIT
  ARM: 7361/1: provide XIP_VIRT_ADDR for no-MMU builds
  ARM: 7349/1: integrator: convert to sparse irqs
  ARM: 7259/3: net: JIT compiler for packet filters
  ARM: 7334/1: add jump label support
  ARM: 7333/2: jump label: detect %c support for ARM
  ARM: 7338/1: add support for early console output via semihosting
  ARM: use set_current_blocked() and block_sigmask()
  ARM: exec: remove redundant set_fs(USER_DS)
  ARM: 7332/1: extract out code patch function from kprobes
  ARM: 7331/1: extract out insn generation code from ftrace
  ARM: 7330/1: ftrace: use canonical Thumb-2 wide instruction format
  ARM: 7351/1: ftrace: remove useless memory checks
  ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path
  ARM: Versatile Express: add NO_IOPORT
  ARM: get rid of asm/irq.h in asm/prom.h
  ARM: 7319/1: Print debug info for SIGBUS in user faults
  ARM: 7318/1: gic: refactor irq_start assignment
  ARM: 7317/1: irq: avoid NULL check in for_each_irq_desc loop
  ARM: 7315/1: perf: add support for the Cortex-A7 PMU
  ...
</pre>
</div>
</content>
</entry>
<entry>
<title>ARM: 7315/1: perf: add support for the Cortex-A7 PMU</title>
<updated>2012-03-24T09:38:53+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will.deacon@arm.com</email>
</author>
<published>2012-02-03T13:46:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=d33c88c659d708e7c5d518a05ef9349a36217bb2'/>
<id>d33c88c659d708e7c5d518a05ef9349a36217bb2</id>
<content type='text'>
Cortex-A7 implements an ARMv7-compatible PMU compliant with the PMUv2
architecture specification.

This patch adds support for the PMU to the ARM perf backend.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Cortex-A7 implements an ARMv7-compatible PMU compliant with the PMUv2
architecture specification.

This patch adds support for the PMU to the ARM perf backend.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Signed-off-by: Russell King &lt;rmk+kernel@arm.linux.org.uk&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branch 'perf/fast' into perf/core</title>
<updated>2012-01-27T11:08:09+00:00</updated>
<author>
<name>Ingo Molnar</name>
<email>mingo@elte.hu</email>
</author>
<published>2012-01-27T11:07:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=44a683971119bafb5bc30778f92ee773680ebb6f'/>
<id>44a683971119bafb5bc30778f92ee773680ebb6f</id>
<content type='text'>
Merge reason: Lets ready it for v3.4

Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Merge reason: Lets ready it for v3.4

Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</pre>
</div>
</content>
</entry>
</feed>
