<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Tahoma
}
--></style>
</head>
<body class='hmmessage'>
Hi, <br><br>I'm just being curious : do these patches change the way those chips should be supported, that do not have a PMU-like IP, but implement PC-sampling thanks to a general purpose timer (not the system timer) ?<br><br>Thanks and Regards,<br>Marc. <br><br><br>> From: matt@console-pimps.org<br>> To: robert.richter@amd.com<br>> Subject: [PATCH V3 0/6] Generalise ARM perf-events backend for oprofile<br>> Date: Mon, 13 Sep 2010 07:07:31 +0100<br>> CC: linux-arch@vger.kernel.org; linux@arm.linux.org.uk; linux-sh@vger.kernel.org; peterz@infradead.org; fweisbec@gmail.com; will.deacon@arm.com; acme@redhat.com; lethal@linux-sh.org; mingo@elte.hu; linux-arm-kernel@lists.infradead.org<br>> <br>> The perf-events backend for OProfile that Will Deacon wrote in<br>> 8c1fc96f6fd1f361428ba805103af0d0eee65179 ("ARM: 6072/1: oprofile: use<br>> perf-events framework as backend") is of use to more architectures<br>> than just ARM. Move the code into drivers/oprofile/ so that SH can use<br>> it instead of the nearly identical copy of its OProfile code.<br>> <br>> The benefit of the backend is that it becomes necessary to only<br>> maintain one copy of the PMU accessor functions for each architecture,<br>> with bug fixes and new features benefiting both OProfile and perf.<br>> <br>> Note that I haven't been able to test these patches on an ARM board to<br>> see if I've caused any regressions. If anyone else could do that I'd<br>> appreciate it. Though, I have been able to compile this version of the<br>> series.<br>> <br>> This patch series is based on,<br>> <br>> git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile.git core<br>> <br>> These patches can also be found at,<br>> <br>> git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/sh-2.6.git perf-oprofile<br>> <br>> Changes from v2:<br>> - Rebased against Robert's oprofile core branch<br>> - Moved even more of the ARM code into the generic oprofile code<br>> - Broke the patches up into more logical steps<br>> <br>> Changes from v1:<br>> - Prefix the new functons with "oprofile_" instead of "op_".<br>> - Fix ARM compilation errors<br>> - Move all the oprofile-perf logic into oprofile_perf.c<br>> - Include cleanup patch from Will<br>> <br>> Matt Fleming (6):<br>> perf: Add helper function to return number of counters<br>> ARM: oprofile: Rename op_arm to oprofile_perf<br>> ARM: oprofile: Move non-ARM code into separate init/exit functions<br>> oprofile: Abstract the perf-events backend<br>> ARM: Make oprofile depend on CONFIG_HW_PERF_EVENTS<br>> sh: oprofile: Use perf-events oprofile backend<br>> <br>> arch/arm/Kconfig | 2 +-<br>> arch/arm/kernel/perf_event.c | 6 +<br>> arch/arm/oprofile/Makefile | 2 +-<br>> arch/arm/oprofile/common.c | 315 +------------------------------------<br>> arch/sh/Kconfig | 2 +-<br>> arch/sh/kernel/perf_event.c | 17 ++<br>> arch/sh/oprofile/Makefile | 2 +-<br>> arch/sh/oprofile/common.c | 104 ++-----------<br>> arch/sh/oprofile/op_impl.h | 33 ----<br>> drivers/oprofile/oprofile_perf.c | 322 ++++++++++++++++++++++++++++++++++++++<br>> include/linux/oprofile.h | 6 +<br>> include/linux/perf_event.h | 1 +<br>> 12 files changed, 368 insertions(+), 444 deletions(-)<br>> delete mode 100644 arch/sh/oprofile/op_impl.h<br>> create mode 100644 drivers/oprofile/oprofile_perf.c<br>> <br>> <br>> _______________________________________________<br>> linux-arm-kernel mailing list<br>> linux-arm-kernel@lists.infradead.org<br>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel<br> </body>
</html>