2008-12-03 09:39:53 +00:00
|
|
|
/*
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* Performance events x86 architecture code
|
2008-12-03 09:39:53 +00:00
|
|
|
*
|
2009-04-29 12:52:50 +00:00
|
|
|
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
|
|
|
|
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
|
|
|
|
* Copyright (C) 2009 Jaswinder Singh Rajput
|
|
|
|
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
|
|
|
|
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
2009-07-21 13:56:48 +00:00
|
|
|
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
|
2010-01-18 08:58:01 +00:00
|
|
|
* Copyright (C) 2009 Google, Inc., Stephane Eranian
|
2008-12-03 09:39:53 +00:00
|
|
|
*
|
|
|
|
* For licencing details see kernel-base/COPYING
|
|
|
|
*/
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
#include <linux/perf_event.h>
|
2008-12-03 09:39:53 +00:00
|
|
|
#include <linux/capability.h>
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
#include <linux/hardirq.h>
|
|
|
|
#include <linux/kprobes.h>
|
2008-12-09 20:43:39 +00:00
|
|
|
#include <linux/module.h>
|
2008-12-03 09:39:53 +00:00
|
|
|
#include <linux/kdebug.h>
|
|
|
|
#include <linux/sched.h>
|
2009-03-30 17:07:15 +00:00
|
|
|
#include <linux/uaccess.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
|
|
|
#include <linux/slab.h>
|
2009-07-21 13:56:48 +00:00
|
|
|
#include <linux/cpu.h>
|
2010-01-22 15:32:17 +00:00
|
|
|
#include <linux/bitops.h>
|
2011-11-20 22:30:47 +00:00
|
|
|
#include <linux/device.h>
|
2008-12-03 09:39:53 +00:00
|
|
|
|
|
|
|
#include <asm/apic.h>
|
2009-03-30 17:07:15 +00:00
|
|
|
#include <asm/stacktrace.h>
|
2009-03-30 17:07:16 +00:00
|
|
|
#include <asm/nmi.h>
|
2011-03-03 02:34:50 +00:00
|
|
|
#include <asm/smp.h>
|
2011-04-16 00:27:55 +00:00
|
|
|
#include <asm/alternative.h>
|
2011-11-21 10:43:53 +00:00
|
|
|
#include <asm/timer.h>
|
2012-07-10 07:42:15 +00:00
|
|
|
#include <asm/desc.h>
|
|
|
|
#include <asm/ldt.h>
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
#include "perf_event.h"
|
|
|
|
|
|
|
|
struct x86_pmu x86_pmu __read_mostly;
|
2011-06-06 14:57:03 +00:00
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
|
2009-03-05 17:08:27 +00:00
|
|
|
.enabled = 1,
|
|
|
|
};
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
u64 __read_mostly hw_cache_event_ids
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
[PERF_COUNT_HW_CACHE_MAX]
|
|
|
|
[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
|
|
[PERF_COUNT_HW_CACHE_RESULT_MAX];
|
2011-08-30 23:41:05 +00:00
|
|
|
u64 __read_mostly hw_cache_extra_regs
|
2011-03-03 02:34:48 +00:00
|
|
|
[PERF_COUNT_HW_CACHE_MAX]
|
|
|
|
[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
|
|
[PERF_COUNT_HW_CACHE_RESULT_MAX];
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
|
2008-12-13 08:00:03 +00:00
|
|
|
/*
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* Propagate event elapsed time into the generic event.
|
|
|
|
* Can only be executed on the CPU where the event is active.
|
2008-12-13 08:00:03 +00:00
|
|
|
* Returns the delta events processed.
|
|
|
|
*/
|
2011-08-30 23:41:05 +00:00
|
|
|
u64 x86_perf_event_update(struct perf_event *event)
|
2008-12-13 08:00:03 +00:00
|
|
|
{
|
2010-03-02 19:18:39 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
2010-03-29 16:36:50 +00:00
|
|
|
int shift = 64 - x86_pmu.cntval_bits;
|
2009-05-13 07:45:19 +00:00
|
|
|
u64 prev_raw_count, new_raw_count;
|
2010-03-02 19:18:39 +00:00
|
|
|
int idx = hwc->idx;
|
2009-05-13 07:45:19 +00:00
|
|
|
s64 delta;
|
2008-12-13 08:00:03 +00:00
|
|
|
|
2012-06-20 18:46:33 +00:00
|
|
|
if (idx == INTEL_PMC_IDX_FIXED_BTS)
|
2009-07-21 13:56:48 +00:00
|
|
|
return 0;
|
|
|
|
|
2008-12-13 08:00:03 +00:00
|
|
|
/*
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* Careful: an NMI might modify the previous event value.
|
2008-12-13 08:00:03 +00:00
|
|
|
*
|
|
|
|
* Our tactic to handle this is to first atomically read and
|
|
|
|
* exchange a new raw count - then add that new-prev delta
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* count to the generic event atomically:
|
2008-12-13 08:00:03 +00:00
|
|
|
*/
|
|
|
|
again:
|
2010-05-21 12:43:08 +00:00
|
|
|
prev_raw_count = local64_read(&hwc->prev_count);
|
2012-03-01 22:28:14 +00:00
|
|
|
rdpmcl(hwc->event_base_rdpmc, new_raw_count);
|
2008-12-13 08:00:03 +00:00
|
|
|
|
2010-05-21 12:43:08 +00:00
|
|
|
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
|
2008-12-13 08:00:03 +00:00
|
|
|
new_raw_count) != prev_raw_count)
|
|
|
|
goto again;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now we have the new raw value and have updated the prev
|
|
|
|
* timestamp already. We can now calculate the elapsed delta
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* (event-)time and add that to the generic event.
|
2008-12-13 08:00:03 +00:00
|
|
|
*
|
|
|
|
* Careful, not all hw sign-extends above the physical width
|
2009-05-13 07:45:19 +00:00
|
|
|
* of the count.
|
2008-12-13 08:00:03 +00:00
|
|
|
*/
|
2009-05-13 07:45:19 +00:00
|
|
|
delta = (new_raw_count << shift) - (prev_raw_count << shift);
|
|
|
|
delta >>= shift;
|
2008-12-13 08:00:03 +00:00
|
|
|
|
2010-05-21 12:43:08 +00:00
|
|
|
local64_add(delta, &event->count);
|
|
|
|
local64_sub(delta, &hwc->period_left);
|
2009-04-29 10:47:22 +00:00
|
|
|
|
|
|
|
return new_raw_count;
|
2008-12-13 08:00:03 +00:00
|
|
|
}
|
|
|
|
|
2011-03-03 02:34:47 +00:00
|
|
|
/*
|
|
|
|
* Find and validate any extra registers to set up.
|
|
|
|
*/
|
|
|
|
static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
|
|
|
|
{
|
2011-06-06 14:57:03 +00:00
|
|
|
struct hw_perf_event_extra *reg;
|
2011-03-03 02:34:47 +00:00
|
|
|
struct extra_reg *er;
|
|
|
|
|
2011-06-06 14:57:03 +00:00
|
|
|
reg = &event->hw.extra_reg;
|
2011-03-03 02:34:47 +00:00
|
|
|
|
|
|
|
if (!x86_pmu.extra_regs)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (er = x86_pmu.extra_regs; er->msr; er++) {
|
|
|
|
if (er->event != (config & er->config_mask))
|
|
|
|
continue;
|
|
|
|
if (event->attr.config1 & ~er->valid_mask)
|
|
|
|
return -EINVAL;
|
2011-06-06 14:57:03 +00:00
|
|
|
|
|
|
|
reg->idx = er->idx;
|
|
|
|
reg->config = event->attr.config1;
|
|
|
|
reg->reg = er->msr;
|
2011-03-03 02:34:47 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
static atomic_t active_events;
|
2009-03-30 17:07:16 +00:00
|
|
|
static DEFINE_MUTEX(pmc_reserve_mutex);
|
|
|
|
|
2010-03-17 11:49:10 +00:00
|
|
|
#ifdef CONFIG_X86_LOCAL_APIC
|
|
|
|
|
2009-03-30 17:07:16 +00:00
|
|
|
static bool reserve_pmc_hardware(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (i = 0; i < x86_pmu.num_counters; i++) {
|
2011-02-02 16:40:57 +00:00
|
|
|
if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
|
2009-03-30 17:07:16 +00:00
|
|
|
goto perfctr_fail;
|
|
|
|
}
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (i = 0; i < x86_pmu.num_counters; i++) {
|
2011-02-02 16:40:57 +00:00
|
|
|
if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
|
2009-03-30 17:07:16 +00:00
|
|
|
goto eventsel_fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
|
|
|
|
eventsel_fail:
|
|
|
|
for (i--; i >= 0; i--)
|
2011-02-02 16:40:57 +00:00
|
|
|
release_evntsel_nmi(x86_pmu_config_addr(i));
|
2009-03-30 17:07:16 +00:00
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
i = x86_pmu.num_counters;
|
2009-03-30 17:07:16 +00:00
|
|
|
|
|
|
|
perfctr_fail:
|
|
|
|
for (i--; i >= 0; i--)
|
2011-02-02 16:40:57 +00:00
|
|
|
release_perfctr_nmi(x86_pmu_event_addr(i));
|
2009-03-30 17:07:16 +00:00
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void release_pmc_hardware(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (i = 0; i < x86_pmu.num_counters; i++) {
|
2011-02-02 16:40:57 +00:00
|
|
|
release_perfctr_nmi(x86_pmu_event_addr(i));
|
|
|
|
release_evntsel_nmi(x86_pmu_config_addr(i));
|
2009-03-30 17:07:16 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-03-17 11:49:10 +00:00
|
|
|
#else
|
|
|
|
|
|
|
|
static bool reserve_pmc_hardware(void) { return true; }
|
|
|
|
static void release_pmc_hardware(void) {}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
2010-11-22 21:55:23 +00:00
|
|
|
static bool check_hw_exists(void)
|
|
|
|
{
|
2012-06-20 18:46:36 +00:00
|
|
|
u64 val, val_new = ~0;
|
2010-12-08 14:56:23 +00:00
|
|
|
int i, reg, ret = 0;
|
2010-11-22 21:55:23 +00:00
|
|
|
|
2010-12-08 14:56:23 +00:00
|
|
|
/*
|
|
|
|
* Check to see if the BIOS enabled any of the counters, if so
|
|
|
|
* complain and bail.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < x86_pmu.num_counters; i++) {
|
2011-02-02 16:40:57 +00:00
|
|
|
reg = x86_pmu_config_addr(i);
|
2010-12-08 14:56:23 +00:00
|
|
|
ret = rdmsrl_safe(reg, &val);
|
|
|
|
if (ret)
|
|
|
|
goto msr_fail;
|
|
|
|
if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
|
|
|
|
goto bios_fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (x86_pmu.num_counters_fixed) {
|
|
|
|
reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
|
|
|
|
ret = rdmsrl_safe(reg, &val);
|
|
|
|
if (ret)
|
|
|
|
goto msr_fail;
|
|
|
|
for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
|
|
|
|
if (val & (0x03 << i*4))
|
|
|
|
goto bios_fail;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now write a value and read it back to see if it matches,
|
|
|
|
* this is needed to detect certain hardware emulators (qemu/kvm)
|
|
|
|
* that don't trap on the MSR access and always return 0s.
|
|
|
|
*/
|
2010-11-22 21:55:23 +00:00
|
|
|
val = 0xabcdUL;
|
2012-06-20 18:46:36 +00:00
|
|
|
reg = x86_pmu_event_addr(0);
|
|
|
|
ret = wrmsrl_safe(reg, val);
|
|
|
|
ret |= rdmsrl_safe(reg, &val_new);
|
2010-11-22 21:55:23 +00:00
|
|
|
if (ret || val != val_new)
|
2010-12-08 14:56:23 +00:00
|
|
|
goto msr_fail;
|
2010-11-22 21:55:23 +00:00
|
|
|
|
|
|
|
return true;
|
2010-12-08 14:56:23 +00:00
|
|
|
|
|
|
|
bios_fail:
|
2011-03-25 09:24:23 +00:00
|
|
|
/*
|
|
|
|
* We still allow the PMU driver to operate:
|
|
|
|
*/
|
|
|
|
printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
|
2010-12-08 14:56:23 +00:00
|
|
|
printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
|
2011-03-25 09:24:23 +00:00
|
|
|
|
|
|
|
return true;
|
2010-12-08 14:56:23 +00:00
|
|
|
|
|
|
|
msr_fail:
|
|
|
|
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
|
2012-06-20 18:46:36 +00:00
|
|
|
printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
|
2011-03-25 09:24:23 +00:00
|
|
|
|
2010-12-08 14:56:23 +00:00
|
|
|
return false;
|
2010-11-22 21:55:23 +00:00
|
|
|
}
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
static void hw_perf_event_destroy(struct perf_event *event)
|
2009-03-30 17:07:16 +00:00
|
|
|
{
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
|
2009-03-30 17:07:16 +00:00
|
|
|
release_pmc_hardware();
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
release_ds_buffers();
|
2009-03-30 17:07:16 +00:00
|
|
|
mutex_unlock(&pmc_reserve_mutex);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-04-29 10:47:20 +00:00
|
|
|
static inline int x86_pmu_initialized(void)
|
|
|
|
{
|
|
|
|
return x86_pmu.handle_irq != NULL;
|
|
|
|
}
|
|
|
|
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
static inline int
|
2011-03-03 02:34:48 +00:00
|
|
|
set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
{
|
2011-03-03 02:34:48 +00:00
|
|
|
struct perf_event_attr *attr = &event->attr;
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
unsigned int cache_type, cache_op, cache_result;
|
|
|
|
u64 config, val;
|
|
|
|
|
|
|
|
config = attr->config;
|
|
|
|
|
|
|
|
cache_type = (config >> 0) & 0xff;
|
|
|
|
if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
cache_op = (config >> 8) & 0xff;
|
|
|
|
if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
cache_result = (config >> 16) & 0xff;
|
|
|
|
if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
val = hw_cache_event_ids[cache_type][cache_op][cache_result];
|
|
|
|
|
|
|
|
if (val == 0)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
if (val == -1)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
hwc->config |= val;
|
2011-03-03 02:34:48 +00:00
|
|
|
attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
|
|
|
|
return x86_pmu_extra_regs(val, event);
|
perf_counter: Implement generalized cache event types
Extend generic event enumeration with the PERF_TYPE_HW_CACHE
method.
This is a 3-dimensional space:
{ L1-D, L1-I, L2, ITLB, DTLB, BPU } x
{ load, store, prefetch } x
{ accesses, misses }
User-space passes in the 3 coordinates and the kernel provides
a counter. (if the hardware supports that type and if the
combination makes sense.)
Combinations that make no sense produce a -EINVAL.
Combinations that are not supported by the hardware produce -ENOTSUP.
Extend the tools to deal with this, and rewrite the event symbol
parsing code with various popular aliases for the units and
access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
both valid aliases.
( x86 is supported for now, with the Nehalem event table filled in,
and with Core2 and Atom having placeholder tables. )
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-05 18:22:46 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
int x86_setup_perfctr(struct perf_event *event)
|
2010-04-13 20:23:11 +00:00
|
|
|
{
|
|
|
|
struct perf_event_attr *attr = &event->attr;
|
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
|
|
u64 config;
|
|
|
|
|
2010-11-23 15:21:43 +00:00
|
|
|
if (!is_sampling_event(event)) {
|
2010-04-13 20:23:11 +00:00
|
|
|
hwc->sample_period = x86_pmu.max_period;
|
|
|
|
hwc->last_period = hwc->sample_period;
|
2010-05-21 12:43:08 +00:00
|
|
|
local64_set(&hwc->period_left, hwc->sample_period);
|
2010-04-13 20:23:11 +00:00
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* If we have a PMU initialized but no APIC
|
|
|
|
* interrupts, we cannot sample hardware
|
|
|
|
* events (user-space has to fall back and
|
|
|
|
* sample via a hrtimer based software event):
|
|
|
|
*/
|
|
|
|
if (!x86_pmu.apic)
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (attr->type == PERF_TYPE_RAW)
|
2011-11-14 09:03:25 +00:00
|
|
|
return x86_pmu_extra_regs(event->attr.config, event);
|
2010-04-13 20:23:11 +00:00
|
|
|
|
|
|
|
if (attr->type == PERF_TYPE_HW_CACHE)
|
2011-03-03 02:34:48 +00:00
|
|
|
return set_ext_hw_attr(hwc, event);
|
2010-04-13 20:23:11 +00:00
|
|
|
|
|
|
|
if (attr->config >= x86_pmu.max_events)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The generic map:
|
|
|
|
*/
|
|
|
|
config = x86_pmu.event_map(attr->config);
|
|
|
|
|
|
|
|
if (config == 0)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
if (config == -1LL)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Branch tracing:
|
|
|
|
*/
|
2011-04-26 11:24:33 +00:00
|
|
|
if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
|
|
|
|
!attr->freq && hwc->sample_period == 1) {
|
2010-04-13 20:23:11 +00:00
|
|
|
/* BTS is not supported by this architecture. */
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!x86_pmu.bts_active)
|
2010-04-13 20:23:11 +00:00
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
/* BTS is currently only allowed for user-mode. */
|
|
|
|
if (!attr->exclude_kernel)
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
}
|
|
|
|
|
|
|
|
hwc->config |= config;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2010-04-13 20:23:10 +00:00
|
|
|
|
2012-02-09 22:20:54 +00:00
|
|
|
/*
|
|
|
|
* check that branch_sample_type is compatible with
|
|
|
|
* settings needed for precise_ip > 1 which implies
|
|
|
|
* using the LBR to capture ALL taken branches at the
|
|
|
|
* priv levels of the measurement
|
|
|
|
*/
|
|
|
|
static inline int precise_br_compat(struct perf_event *event)
|
|
|
|
{
|
|
|
|
u64 m = event->attr.branch_sample_type;
|
|
|
|
u64 b = 0;
|
|
|
|
|
|
|
|
/* must capture all branches */
|
|
|
|
if (!(m & PERF_SAMPLE_BRANCH_ANY))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
|
|
|
|
|
|
|
|
if (!event->attr.exclude_user)
|
|
|
|
b |= PERF_SAMPLE_BRANCH_USER;
|
|
|
|
|
|
|
|
if (!event->attr.exclude_kernel)
|
|
|
|
b |= PERF_SAMPLE_BRANCH_KERNEL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
|
|
|
|
*/
|
|
|
|
|
|
|
|
return m == b;
|
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
int x86_pmu_hw_config(struct perf_event *event)
|
2010-03-11 16:54:39 +00:00
|
|
|
{
|
2010-04-08 21:03:20 +00:00
|
|
|
if (event->attr.precise_ip) {
|
|
|
|
int precise = 0;
|
|
|
|
|
|
|
|
/* Support for constant skid */
|
2012-06-08 12:50:50 +00:00
|
|
|
if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
|
2010-04-08 21:03:20 +00:00
|
|
|
precise++;
|
|
|
|
|
2010-10-19 12:38:11 +00:00
|
|
|
/* Support for IP fixup */
|
|
|
|
if (x86_pmu.lbr_nr)
|
|
|
|
precise++;
|
|
|
|
}
|
2010-04-08 21:03:20 +00:00
|
|
|
|
|
|
|
if (event->attr.precise_ip > precise)
|
|
|
|
return -EOPNOTSUPP;
|
2012-02-09 22:20:54 +00:00
|
|
|
/*
|
|
|
|
* check that PEBS LBR correction does not conflict with
|
|
|
|
* whatever the user is asking with attr->branch_sample_type
|
|
|
|
*/
|
|
|
|
if (event->attr.precise_ip > 1) {
|
|
|
|
u64 *br_type = &event->attr.branch_sample_type;
|
|
|
|
|
|
|
|
if (has_branch_stack(event)) {
|
|
|
|
if (!precise_br_compat(event))
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
/* branch_sample_type is compatible */
|
|
|
|
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* user did not specify branch_sample_type
|
|
|
|
*
|
|
|
|
* For PEBS fixups, we capture all
|
|
|
|
* the branches at the priv level of the
|
|
|
|
* event.
|
|
|
|
*/
|
|
|
|
*br_type = PERF_SAMPLE_BRANCH_ANY;
|
|
|
|
|
|
|
|
if (!event->attr.exclude_user)
|
|
|
|
*br_type |= PERF_SAMPLE_BRANCH_USER;
|
|
|
|
|
|
|
|
if (!event->attr.exclude_kernel)
|
|
|
|
*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
|
|
|
|
}
|
|
|
|
}
|
2010-04-08 21:03:20 +00:00
|
|
|
}
|
|
|
|
|
2010-03-11 16:54:39 +00:00
|
|
|
/*
|
|
|
|
* Generate PMC IRQs:
|
|
|
|
* (keep 'enabled' bit clear for now)
|
|
|
|
*/
|
2010-03-30 15:00:06 +00:00
|
|
|
event->hw.config = ARCH_PERFMON_EVENTSEL_INT;
|
2010-03-11 16:54:39 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Count user and OS events unless requested not to
|
|
|
|
*/
|
2010-03-30 15:00:06 +00:00
|
|
|
if (!event->attr.exclude_user)
|
|
|
|
event->hw.config |= ARCH_PERFMON_EVENTSEL_USR;
|
|
|
|
if (!event->attr.exclude_kernel)
|
|
|
|
event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
|
2010-03-11 16:54:39 +00:00
|
|
|
|
2010-03-30 15:00:06 +00:00
|
|
|
if (event->attr.type == PERF_TYPE_RAW)
|
|
|
|
event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
|
2010-03-11 16:54:39 +00:00
|
|
|
|
2010-04-13 20:23:12 +00:00
|
|
|
return x86_setup_perfctr(event);
|
2010-03-30 09:28:21 +00:00
|
|
|
}
|
|
|
|
|
2008-12-03 09:39:53 +00:00
|
|
|
/*
|
2009-06-02 17:22:16 +00:00
|
|
|
* Setup the hardware configuration for a given attr_type
|
2008-12-03 09:39:53 +00:00
|
|
|
*/
|
2010-06-11 11:35:08 +00:00
|
|
|
static int __x86_pmu_event_init(struct perf_event *event)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
2009-03-30 17:07:16 +00:00
|
|
|
int err;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-04-29 10:47:20 +00:00
|
|
|
if (!x86_pmu_initialized())
|
|
|
|
return -ENODEV;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-03-30 17:07:16 +00:00
|
|
|
err = 0;
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
if (!atomic_inc_not_zero(&active_events)) {
|
2009-03-30 17:07:16 +00:00
|
|
|
mutex_lock(&pmc_reserve_mutex);
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
if (atomic_read(&active_events) == 0) {
|
2009-07-21 13:56:48 +00:00
|
|
|
if (!reserve_pmc_hardware())
|
|
|
|
err = -EBUSY;
|
2010-10-19 12:50:02 +00:00
|
|
|
else
|
|
|
|
reserve_ds_buffers();
|
2009-07-21 13:56:48 +00:00
|
|
|
}
|
|
|
|
if (!err)
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
atomic_inc(&active_events);
|
2009-03-30 17:07:16 +00:00
|
|
|
mutex_unlock(&pmc_reserve_mutex);
|
|
|
|
}
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
event->destroy = hw_perf_event_destroy;
|
2009-09-09 08:04:47 +00:00
|
|
|
|
2010-04-13 20:23:10 +00:00
|
|
|
event->hw.idx = -1;
|
|
|
|
event->hw.last_cpu = -1;
|
|
|
|
event->hw.last_tag = ~0ULL;
|
2009-10-06 14:42:09 +00:00
|
|
|
|
2011-06-06 14:57:03 +00:00
|
|
|
/* mark unused */
|
|
|
|
event->hw.extra_reg.idx = EXTRA_REG_NONE;
|
2012-02-09 22:20:53 +00:00
|
|
|
event->hw.branch_reg.idx = EXTRA_REG_NONE;
|
|
|
|
|
2010-04-13 20:23:12 +00:00
|
|
|
return x86_pmu.hw_config(event);
|
2010-04-13 20:23:10 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
void x86_pmu_disable_all(void)
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
{
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
2009-05-13 14:21:38 +00:00
|
|
|
int idx;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
2009-03-05 17:08:27 +00:00
|
|
|
u64 val;
|
|
|
|
|
2009-04-29 14:55:56 +00:00
|
|
|
if (!test_bit(idx, cpuc->active_mask))
|
2009-04-29 10:47:01 +00:00
|
|
|
continue;
|
2011-02-02 16:40:57 +00:00
|
|
|
rdmsrl(x86_pmu_config_addr(idx), val);
|
2010-03-01 13:21:23 +00:00
|
|
|
if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
|
2009-04-29 10:47:01 +00:00
|
|
|
continue;
|
2010-03-01 13:21:23 +00:00
|
|
|
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
|
2011-02-02 16:40:57 +00:00
|
|
|
wrmsrl(x86_pmu_config_addr(idx), val);
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static void x86_pmu_disable(struct pmu *pmu)
|
2009-02-27 12:39:09 +00:00
|
|
|
{
|
2010-01-18 08:58:01 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
|
2009-04-29 10:47:20 +00:00
|
|
|
if (!x86_pmu_initialized())
|
2009-05-13 14:21:38 +00:00
|
|
|
return;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
2010-01-27 22:07:47 +00:00
|
|
|
if (!cpuc->enabled)
|
|
|
|
return;
|
|
|
|
|
|
|
|
cpuc->n_added = 0;
|
|
|
|
cpuc->enabled = 0;
|
|
|
|
barrier();
|
2010-01-18 08:58:01 +00:00
|
|
|
|
|
|
|
x86_pmu.disable_all();
|
2009-02-27 12:39:09 +00:00
|
|
|
}
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
void x86_pmu_enable_all(int added)
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
{
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
int idx;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
2011-02-02 16:40:56 +00:00
|
|
|
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
|
2009-03-05 17:08:27 +00:00
|
|
|
|
2009-04-29 14:55:56 +00:00
|
|
|
if (!test_bit(idx, cpuc->active_mask))
|
2009-04-29 10:47:01 +00:00
|
|
|
continue;
|
2009-07-10 07:59:56 +00:00
|
|
|
|
2011-02-02 16:40:56 +00:00
|
|
|
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-06-11 11:35:57 +00:00
|
|
|
static struct pmu pmu;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
|
|
|
static inline int is_x86_event(struct perf_event *event)
|
|
|
|
{
|
|
|
|
return event->pmu == &pmu;
|
|
|
|
}
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
/*
|
|
|
|
* Event scheduler state:
|
|
|
|
*
|
|
|
|
* Assign events iterating over all events and counters, beginning
|
|
|
|
* with events with least weights first. Keep the current iterator
|
|
|
|
* state in struct sched_state.
|
|
|
|
*/
|
|
|
|
struct sched_state {
|
|
|
|
int weight;
|
|
|
|
int event; /* event index */
|
|
|
|
int counter; /* counter index */
|
|
|
|
int unassigned; /* number of events to be assigned left */
|
|
|
|
unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
|
|
|
|
};
|
|
|
|
|
2011-11-18 11:35:22 +00:00
|
|
|
/* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */
|
|
|
|
#define SCHED_STATES_MAX 2
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
struct perf_sched {
|
|
|
|
int max_weight;
|
|
|
|
int max_events;
|
|
|
|
struct event_constraint **constraints;
|
|
|
|
struct sched_state state;
|
2011-11-18 11:35:22 +00:00
|
|
|
int saved_states;
|
|
|
|
struct sched_state saved[SCHED_STATES_MAX];
|
2011-11-18 11:35:21 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Initialize interator that runs through all events and counters.
|
|
|
|
*/
|
|
|
|
static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c,
|
|
|
|
int num, int wmin, int wmax)
|
|
|
|
{
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
memset(sched, 0, sizeof(*sched));
|
|
|
|
sched->max_events = num;
|
|
|
|
sched->max_weight = wmax;
|
|
|
|
sched->constraints = c;
|
|
|
|
|
|
|
|
for (idx = 0; idx < num; idx++) {
|
|
|
|
if (c[idx]->weight == wmin)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
sched->state.event = idx; /* start with min weight */
|
|
|
|
sched->state.weight = wmin;
|
|
|
|
sched->state.unassigned = num;
|
|
|
|
}
|
|
|
|
|
2011-11-18 11:35:22 +00:00
|
|
|
static void perf_sched_save_state(struct perf_sched *sched)
|
|
|
|
{
|
|
|
|
if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX))
|
|
|
|
return;
|
|
|
|
|
|
|
|
sched->saved[sched->saved_states] = sched->state;
|
|
|
|
sched->saved_states++;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool perf_sched_restore_state(struct perf_sched *sched)
|
|
|
|
{
|
|
|
|
if (!sched->saved_states)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
sched->saved_states--;
|
|
|
|
sched->state = sched->saved[sched->saved_states];
|
|
|
|
|
|
|
|
/* continue with next counter: */
|
|
|
|
clear_bit(sched->state.counter++, sched->state.used);
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
/*
|
|
|
|
* Select a counter for the current event to schedule. Return true on
|
|
|
|
* success.
|
|
|
|
*/
|
2011-11-18 11:35:22 +00:00
|
|
|
static bool __perf_sched_find_counter(struct perf_sched *sched)
|
2011-11-18 11:35:21 +00:00
|
|
|
{
|
|
|
|
struct event_constraint *c;
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
if (!sched->state.unassigned)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (sched->state.event >= sched->max_events)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
c = sched->constraints[sched->state.event];
|
|
|
|
|
2011-11-10 14:15:42 +00:00
|
|
|
/* Prefer fixed purpose counters */
|
2012-06-20 18:46:33 +00:00
|
|
|
if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
|
|
|
|
idx = INTEL_PMC_IDX_FIXED;
|
2012-03-23 22:02:03 +00:00
|
|
|
for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) {
|
2011-11-10 14:15:42 +00:00
|
|
|
if (!__test_and_set_bit(idx, sched->state.used))
|
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
}
|
2011-11-18 11:35:21 +00:00
|
|
|
/* Grab the first unused counter starting with idx */
|
|
|
|
idx = sched->state.counter;
|
2012-06-20 18:46:33 +00:00
|
|
|
for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
|
2011-11-18 11:35:21 +00:00
|
|
|
if (!__test_and_set_bit(idx, sched->state.used))
|
2011-11-10 14:15:42 +00:00
|
|
|
goto done;
|
2011-11-18 11:35:21 +00:00
|
|
|
}
|
|
|
|
|
2011-11-10 14:15:42 +00:00
|
|
|
return false;
|
|
|
|
|
|
|
|
done:
|
|
|
|
sched->state.counter = idx;
|
2011-11-18 11:35:21 +00:00
|
|
|
|
2011-11-18 11:35:22 +00:00
|
|
|
if (c->overlap)
|
|
|
|
perf_sched_save_state(sched);
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool perf_sched_find_counter(struct perf_sched *sched)
|
|
|
|
{
|
|
|
|
while (!__perf_sched_find_counter(sched)) {
|
|
|
|
if (!perf_sched_restore_state(sched))
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Go through all unassigned events and find the next one to schedule.
|
|
|
|
* Take events with the least weight first. Return true on success.
|
|
|
|
*/
|
|
|
|
static bool perf_sched_next_event(struct perf_sched *sched)
|
|
|
|
{
|
|
|
|
struct event_constraint *c;
|
|
|
|
|
|
|
|
if (!sched->state.unassigned || !--sched->state.unassigned)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
do {
|
|
|
|
/* next event */
|
|
|
|
sched->state.event++;
|
|
|
|
if (sched->state.event >= sched->max_events) {
|
|
|
|
/* next weight */
|
|
|
|
sched->state.event = 0;
|
|
|
|
sched->state.weight++;
|
|
|
|
if (sched->state.weight > sched->max_weight)
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
c = sched->constraints[sched->state.event];
|
|
|
|
} while (c->weight != sched->state.weight);
|
|
|
|
|
|
|
|
sched->state.counter = 0; /* start with first counter */
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Assign a counter for each event.
|
|
|
|
*/
|
2012-06-15 06:31:30 +00:00
|
|
|
int perf_assign_events(struct event_constraint **constraints, int n,
|
|
|
|
int wmin, int wmax, int *assign)
|
2011-11-18 11:35:21 +00:00
|
|
|
{
|
|
|
|
struct perf_sched sched;
|
|
|
|
|
|
|
|
perf_sched_init(&sched, constraints, n, wmin, wmax);
|
|
|
|
|
|
|
|
do {
|
|
|
|
if (!perf_sched_find_counter(&sched))
|
|
|
|
break; /* failed */
|
|
|
|
if (assign)
|
|
|
|
assign[sched.state.event] = sched.state.counter;
|
|
|
|
} while (perf_sched_next_event(&sched));
|
|
|
|
|
|
|
|
return sched.state.unassigned;
|
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
|
2010-01-18 08:58:01 +00:00
|
|
|
{
|
2010-01-22 15:32:17 +00:00
|
|
|
struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
|
2010-01-18 08:58:01 +00:00
|
|
|
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
|
2011-11-18 11:35:21 +00:00
|
|
|
int i, wmin, wmax, num = 0;
|
2010-01-18 08:58:01 +00:00
|
|
|
struct hw_perf_event *hwc;
|
|
|
|
|
|
|
|
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
|
2010-02-01 14:36:30 +00:00
|
|
|
c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
|
|
|
|
constraints[i] = c;
|
2011-11-18 11:35:21 +00:00
|
|
|
wmin = min(wmin, c->weight);
|
|
|
|
wmax = max(wmax, c->weight);
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
|
2010-01-21 15:39:01 +00:00
|
|
|
/*
|
|
|
|
* fastpath, try to reuse previous register
|
|
|
|
*/
|
2010-01-22 15:40:12 +00:00
|
|
|
for (i = 0; i < n; i++) {
|
2010-01-21 15:39:01 +00:00
|
|
|
hwc = &cpuc->event_list[i]->hw;
|
2010-01-22 13:55:22 +00:00
|
|
|
c = constraints[i];
|
2010-01-21 15:39:01 +00:00
|
|
|
|
|
|
|
/* never assigned */
|
|
|
|
if (hwc->idx == -1)
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* constraint still honored */
|
2010-01-22 15:32:17 +00:00
|
|
|
if (!test_bit(hwc->idx, c->idxmsk))
|
2010-01-21 15:39:01 +00:00
|
|
|
break;
|
|
|
|
|
|
|
|
/* not already used */
|
|
|
|
if (test_bit(hwc->idx, used_mask))
|
|
|
|
break;
|
|
|
|
|
2010-03-02 20:16:55 +00:00
|
|
|
__set_bit(hwc->idx, used_mask);
|
2010-01-21 15:39:01 +00:00
|
|
|
if (assign)
|
|
|
|
assign[i] = hwc->idx;
|
|
|
|
}
|
|
|
|
|
2011-11-18 11:35:21 +00:00
|
|
|
/* slow path */
|
|
|
|
if (i != n)
|
|
|
|
num = perf_assign_events(constraints, n, wmin, wmax, assign);
|
2010-01-21 15:39:01 +00:00
|
|
|
|
2010-01-18 08:58:01 +00:00
|
|
|
/*
|
|
|
|
* scheduling failed or is just a simulation,
|
|
|
|
* free resources if necessary
|
|
|
|
*/
|
|
|
|
if (!assign || num) {
|
|
|
|
for (i = 0; i < n; i++) {
|
|
|
|
if (x86_pmu.put_event_constraints)
|
|
|
|
x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
|
|
|
|
}
|
|
|
|
}
|
2011-11-09 16:56:37 +00:00
|
|
|
return num ? -EINVAL : 0;
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* dogrp: true if must collect siblings events (group)
|
|
|
|
* returns total number of events and error code
|
|
|
|
*/
|
|
|
|
static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
|
|
|
|
{
|
|
|
|
struct perf_event *event;
|
|
|
|
int n, max_count;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
|
|
|
/* current number of events already accepted */
|
|
|
|
n = cpuc->n_events;
|
|
|
|
|
|
|
|
if (is_x86_event(leader)) {
|
|
|
|
if (n >= max_count)
|
2011-11-09 16:56:37 +00:00
|
|
|
return -EINVAL;
|
2010-01-18 08:58:01 +00:00
|
|
|
cpuc->event_list[n] = leader;
|
|
|
|
n++;
|
|
|
|
}
|
|
|
|
if (!dogrp)
|
|
|
|
return n;
|
|
|
|
|
|
|
|
list_for_each_entry(event, &leader->sibling_list, group_entry) {
|
|
|
|
if (!is_x86_event(event) ||
|
2010-01-21 15:39:01 +00:00
|
|
|
event->state <= PERF_EVENT_STATE_OFF)
|
2010-01-18 08:58:01 +00:00
|
|
|
continue;
|
|
|
|
|
|
|
|
if (n >= max_count)
|
2011-11-09 16:56:37 +00:00
|
|
|
return -EINVAL;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
|
|
|
cpuc->event_list[n] = event;
|
|
|
|
n++;
|
|
|
|
}
|
|
|
|
return n;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void x86_assign_hw_event(struct perf_event *event,
|
2010-02-01 12:50:01 +00:00
|
|
|
struct cpu_hw_events *cpuc, int i)
|
2010-01-18 08:58:01 +00:00
|
|
|
{
|
2010-02-01 12:50:01 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
|
|
|
|
|
|
hwc->idx = cpuc->assign[i];
|
|
|
|
hwc->last_cpu = smp_processor_id();
|
|
|
|
hwc->last_tag = ++cpuc->tags[i];
|
2010-01-18 08:58:01 +00:00
|
|
|
|
2012-06-20 18:46:33 +00:00
|
|
|
if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
|
2010-01-18 08:58:01 +00:00
|
|
|
hwc->config_base = 0;
|
|
|
|
hwc->event_base = 0;
|
2012-06-20 18:46:33 +00:00
|
|
|
} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
|
2010-01-18 08:58:01 +00:00
|
|
|
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
|
2012-06-20 18:46:33 +00:00
|
|
|
hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
|
|
|
|
hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
|
2010-01-18 08:58:01 +00:00
|
|
|
} else {
|
2011-02-02 16:40:59 +00:00
|
|
|
hwc->config_base = x86_pmu_config_addr(hwc->idx);
|
|
|
|
hwc->event_base = x86_pmu_event_addr(hwc->idx);
|
2012-06-15 17:06:44 +00:00
|
|
|
hwc->event_base_rdpmc = hwc->idx;
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-02-01 12:50:01 +00:00
|
|
|
static inline int match_prev_assignment(struct hw_perf_event *hwc,
|
|
|
|
struct cpu_hw_events *cpuc,
|
|
|
|
int i)
|
|
|
|
{
|
|
|
|
return hwc->idx == cpuc->assign[i] &&
|
|
|
|
hwc->last_cpu == smp_processor_id() &&
|
|
|
|
hwc->last_tag == cpuc->tags[i];
|
|
|
|
}
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static void x86_pmu_start(struct perf_event *event, int flags);
|
2010-01-25 14:58:43 +00:00
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static void x86_pmu_enable(struct pmu *pmu)
|
2008-12-13 08:00:03 +00:00
|
|
|
{
|
2010-01-18 08:58:01 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
struct perf_event *event;
|
|
|
|
struct hw_perf_event *hwc;
|
2010-03-26 13:08:44 +00:00
|
|
|
int i, added = cpuc->n_added;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
2009-04-29 10:47:20 +00:00
|
|
|
if (!x86_pmu_initialized())
|
2008-12-14 17:36:30 +00:00
|
|
|
return;
|
2010-01-27 22:07:47 +00:00
|
|
|
|
|
|
|
if (cpuc->enabled)
|
|
|
|
return;
|
|
|
|
|
2010-01-18 08:58:01 +00:00
|
|
|
if (cpuc->n_added) {
|
2010-03-06 12:20:40 +00:00
|
|
|
int n_running = cpuc->n_events - cpuc->n_added;
|
2010-01-18 08:58:01 +00:00
|
|
|
/*
|
|
|
|
* apply assignment obtained either from
|
|
|
|
* hw_perf_group_sched_in() or x86_pmu_enable()
|
|
|
|
*
|
|
|
|
* step1: save events moving to new counters
|
|
|
|
* step2: reprogram moved events into new counters
|
|
|
|
*/
|
2010-03-06 12:20:40 +00:00
|
|
|
for (i = 0; i < n_running; i++) {
|
2010-01-18 08:58:01 +00:00
|
|
|
event = cpuc->event_list[i];
|
|
|
|
hwc = &event->hw;
|
|
|
|
|
2010-02-01 12:50:01 +00:00
|
|
|
/*
|
|
|
|
* we can avoid reprogramming counter if:
|
|
|
|
* - assigned same counter as last time
|
|
|
|
* - running on same CPU as last time
|
|
|
|
* - no other event has used the counter since
|
|
|
|
*/
|
|
|
|
if (hwc->idx == -1 ||
|
|
|
|
match_prev_assignment(hwc, cpuc, i))
|
2010-01-18 08:58:01 +00:00
|
|
|
continue;
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
/*
|
|
|
|
* Ensure we don't accidentally enable a stopped
|
|
|
|
* counter simply because we rescheduled.
|
|
|
|
*/
|
|
|
|
if (hwc->state & PERF_HES_STOPPED)
|
|
|
|
hwc->state |= PERF_HES_ARCH;
|
|
|
|
|
|
|
|
x86_pmu_stop(event, PERF_EF_UPDATE);
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < cpuc->n_events; i++) {
|
|
|
|
event = cpuc->event_list[i];
|
|
|
|
hwc = &event->hw;
|
|
|
|
|
2010-03-11 12:40:30 +00:00
|
|
|
if (!match_prev_assignment(hwc, cpuc, i))
|
2010-02-01 12:50:01 +00:00
|
|
|
x86_assign_hw_event(event, cpuc, i);
|
2010-03-11 12:40:30 +00:00
|
|
|
else if (i < n_running)
|
|
|
|
continue;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
if (hwc->state & PERF_HES_ARCH)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
x86_pmu_start(event, PERF_EF_RELOAD);
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
cpuc->n_added = 0;
|
|
|
|
perf_events_lapic_init();
|
|
|
|
}
|
2010-01-27 22:07:47 +00:00
|
|
|
|
|
|
|
cpuc->enabled = 1;
|
|
|
|
barrier();
|
|
|
|
|
2010-03-26 13:08:44 +00:00
|
|
|
x86_pmu.enable_all(added);
|
2008-12-13 08:00:03 +00:00
|
|
|
}
|
|
|
|
|
2009-06-24 06:13:48 +00:00
|
|
|
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2008-12-13 08:00:03 +00:00
|
|
|
/*
|
|
|
|
* Set the next IRQ period, based on the hwc->period_left value.
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* To be called with the event disabled in hw:
|
2008-12-13 08:00:03 +00:00
|
|
|
*/
|
2011-08-30 23:41:05 +00:00
|
|
|
int x86_perf_event_set_period(struct perf_event *event)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
2010-03-02 19:16:01 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
2010-05-21 12:43:08 +00:00
|
|
|
s64 left = local64_read(&hwc->period_left);
|
2009-06-02 14:08:20 +00:00
|
|
|
s64 period = hwc->sample_period;
|
2010-03-08 12:51:31 +00:00
|
|
|
int ret = 0, idx = hwc->idx;
|
2008-12-13 08:00:03 +00:00
|
|
|
|
2012-06-20 18:46:33 +00:00
|
|
|
if (idx == INTEL_PMC_IDX_FIXED_BTS)
|
2009-07-21 13:56:48 +00:00
|
|
|
return 0;
|
|
|
|
|
2008-12-13 08:00:03 +00:00
|
|
|
/*
|
tree-wide: fix assorted typos all over the place
That is "success", "unknown", "through", "performance", "[re|un]mapping"
, "access", "default", "reasonable", "[con]currently", "temperature"
, "channel", "[un]used", "application", "example","hierarchy", "therefore"
, "[over|under]flow", "contiguous", "threshold", "enough" and others.
Signed-off-by: André Goddard Rosa <andre.goddard@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2009-11-14 15:09:05 +00:00
|
|
|
* If we are way outside a reasonable range then just skip forward:
|
2008-12-13 08:00:03 +00:00
|
|
|
*/
|
|
|
|
if (unlikely(left <= -period)) {
|
|
|
|
left = period;
|
2010-05-21 12:43:08 +00:00
|
|
|
local64_set(&hwc->period_left, left);
|
2009-06-10 19:34:59 +00:00
|
|
|
hwc->last_period = period;
|
2009-06-02 14:08:20 +00:00
|
|
|
ret = 1;
|
2008-12-13 08:00:03 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(left <= 0)) {
|
|
|
|
left += period;
|
2010-05-21 12:43:08 +00:00
|
|
|
local64_set(&hwc->period_left, left);
|
2009-06-10 19:34:59 +00:00
|
|
|
hwc->last_period = period;
|
2009-06-02 14:08:20 +00:00
|
|
|
ret = 1;
|
2008-12-13 08:00:03 +00:00
|
|
|
}
|
2009-05-15 06:25:22 +00:00
|
|
|
/*
|
2009-09-21 09:31:35 +00:00
|
|
|
* Quirk: certain CPUs dont like it if just 1 hw_event is left:
|
2009-05-15 06:25:22 +00:00
|
|
|
*/
|
|
|
|
if (unlikely(left < 2))
|
|
|
|
left = 2;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-06-02 14:08:20 +00:00
|
|
|
if (left > x86_pmu.max_period)
|
|
|
|
left = x86_pmu.max_period;
|
|
|
|
|
2009-06-24 06:13:48 +00:00
|
|
|
per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
|
2008-12-13 08:00:03 +00:00
|
|
|
|
|
|
|
/*
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* The hw event starts counting from this event offset,
|
2008-12-13 08:00:03 +00:00
|
|
|
* mark it to be able to extra future deltas:
|
|
|
|
*/
|
2010-05-21 12:43:08 +00:00
|
|
|
local64_set(&hwc->prev_count, (u64)-left);
|
2008-12-13 08:00:03 +00:00
|
|
|
|
2011-02-02 16:40:59 +00:00
|
|
|
wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
|
2010-06-02 21:23:04 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Due to erratum on certan cpu we need
|
|
|
|
* a second write to be sure the register
|
|
|
|
* is updated properly
|
|
|
|
*/
|
|
|
|
if (x86_pmu.perfctr_second_write) {
|
2011-02-02 16:40:59 +00:00
|
|
|
wrmsrl(hwc->event_base,
|
2010-03-29 16:36:50 +00:00
|
|
|
(u64)(-left) & x86_pmu.cntval_mask);
|
2010-06-02 21:23:04 +00:00
|
|
|
}
|
2009-06-02 14:08:20 +00:00
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
perf_event_update_userpage(event);
|
2009-06-22 14:35:24 +00:00
|
|
|
|
2009-06-02 14:08:20 +00:00
|
|
|
return ret;
|
2008-12-22 10:10:42 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
void x86_pmu_enable_event(struct perf_event *event)
|
2009-04-29 10:47:18 +00:00
|
|
|
{
|
2010-12-18 15:28:55 +00:00
|
|
|
if (__this_cpu_read(cpu_hw_events.enabled))
|
2010-04-13 20:23:14 +00:00
|
|
|
__x86_pmu_enable_event(&event->hw,
|
|
|
|
ARCH_PERFMON_EVENTSEL_ENABLE);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
2009-10-06 14:42:09 +00:00
|
|
|
/*
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
* Add a single event to the PMU.
|
2010-01-18 08:58:01 +00:00
|
|
|
*
|
|
|
|
* The event is added to the group of enabled events
|
|
|
|
* but only if it can be scehduled with existing events.
|
2009-10-08 09:56:07 +00:00
|
|
|
*/
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static int x86_pmu_add(struct perf_event *event, int flags)
|
2009-10-08 09:56:07 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
2010-01-18 08:58:01 +00:00
|
|
|
struct hw_perf_event *hwc;
|
|
|
|
int assign[X86_PMC_IDX_MAX];
|
|
|
|
int n, n0, ret;
|
2009-10-08 09:56:07 +00:00
|
|
|
|
2010-01-18 08:58:01 +00:00
|
|
|
hwc = &event->hw;
|
2009-10-08 09:56:07 +00:00
|
|
|
|
2010-06-14 06:49:00 +00:00
|
|
|
perf_pmu_disable(event->pmu);
|
2010-01-18 08:58:01 +00:00
|
|
|
n0 = cpuc->n_events;
|
2010-06-11 15:32:03 +00:00
|
|
|
ret = n = collect_events(cpuc, event, false);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
2009-05-25 19:41:28 +00:00
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
|
|
|
|
if (!(flags & PERF_EF_START))
|
|
|
|
hwc->state |= PERF_HES_ARCH;
|
|
|
|
|
2010-04-23 05:56:12 +00:00
|
|
|
/*
|
|
|
|
* If group events scheduling transaction was started,
|
2011-03-17 19:24:16 +00:00
|
|
|
* skip the schedulability test here, it will be performed
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
* at commit time (->commit_txn) as a whole
|
2010-04-23 05:56:12 +00:00
|
|
|
*/
|
2010-05-25 15:49:05 +00:00
|
|
|
if (cpuc->group_flag & PERF_EVENT_TXN)
|
2010-06-11 15:32:03 +00:00
|
|
|
goto done_collect;
|
2010-04-23 05:56:12 +00:00
|
|
|
|
2010-03-11 16:54:39 +00:00
|
|
|
ret = x86_pmu.schedule_events(cpuc, n, assign);
|
2010-01-18 08:58:01 +00:00
|
|
|
if (ret)
|
2010-06-11 15:32:03 +00:00
|
|
|
goto out;
|
2010-01-18 08:58:01 +00:00
|
|
|
/*
|
|
|
|
* copy new assignment, now we know it is possible
|
|
|
|
* will be used by hw_perf_enable()
|
|
|
|
*/
|
|
|
|
memcpy(cpuc->assign, assign, n*sizeof(int));
|
2008-12-09 10:40:46 +00:00
|
|
|
|
2010-06-11 15:32:03 +00:00
|
|
|
done_collect:
|
2010-01-18 08:58:01 +00:00
|
|
|
cpuc->n_events = n;
|
2010-03-06 12:49:56 +00:00
|
|
|
cpuc->n_added += n - n0;
|
perf_events: Fix event scheduling issues introduced by transactional API
The transactional API patch between the generic and model-specific
code introduced several important bugs with event scheduling, at
least on X86. If you had pinned events, e.g., watchdog, and were
over-committing the PMU, you would get bogus counts. The bug was
showing up on Intel CPU because events would move around more
often that on AMD. But the problem also existed on AMD, though
harder to expose.
The issues were:
- group_sched_in() was missing a cancel_txn() in the error path
- cpuc->n_added was not properly maintained, leading to missing
actions in hw_perf_enable(), i.e., n_running being 0. You cannot
update n_added until you know the transaction has succeeded. In
case of failed transaction n_added was not adjusted back.
- in case of failed transactions, event_sched_out() was called
and eventually invoked x86_disable_event() to touch the HW reg.
But with transactions, on X86, event_sched_in() does not touch
HW registers, it simply collects events into a list. Thus, you
could end up calling x86_disable_event() on a counter which
did not correspond to the current event when idx != -1.
The patch modifies the generic and X86 code to avoid all those problems.
First, we keep track of the number of events added last. In case the
transaction fails, we substract them from n_added. This approach is
necessary (as opposed to delaying updates to n_added) because not all
event updates use the transaction API, e.g., single events.
Second, we encapsulate the event_sched_in() and event_sched_out() in
group_sched_in() inside the transaction. That makes the operations
symmetrical and you can also detect that you are inside a transaction
and skip the HW reg access by checking cpuc->group_flag.
With this patch, you can now overcommit the PMU even with pinned
system-wide events present and still get valid counts.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1274796225.5882.1389.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-25 14:23:10 +00:00
|
|
|
cpuc->n_txn += n - n0;
|
2008-12-21 12:50:42 +00:00
|
|
|
|
2010-06-11 15:32:03 +00:00
|
|
|
ret = 0;
|
|
|
|
out:
|
2010-06-14 06:49:00 +00:00
|
|
|
perf_pmu_enable(event->pmu);
|
2010-06-11 15:32:03 +00:00
|
|
|
return ret;
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static void x86_pmu_start(struct perf_event *event, int flags)
|
2010-02-08 15:06:01 +00:00
|
|
|
{
|
2010-03-06 12:19:24 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
int idx = event->hw.idx;
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (WARN_ON_ONCE(idx == -1))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (flags & PERF_EF_RELOAD) {
|
|
|
|
WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
|
|
|
|
x86_perf_event_set_period(event);
|
|
|
|
}
|
|
|
|
|
|
|
|
event->hw.state = 0;
|
2010-02-08 15:06:01 +00:00
|
|
|
|
2010-03-06 12:19:24 +00:00
|
|
|
cpuc->events[idx] = event;
|
|
|
|
__set_bit(idx, cpuc->active_mask);
|
2010-09-15 16:20:34 +00:00
|
|
|
__set_bit(idx, cpuc->running);
|
2010-03-02 19:32:08 +00:00
|
|
|
x86_pmu.enable(event);
|
2010-03-06 12:19:24 +00:00
|
|
|
perf_event_update_userpage(event);
|
2009-05-25 15:39:05 +00:00
|
|
|
}
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
void perf_event_print_debug(void)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
2008-12-22 10:10:42 +00:00
|
|
|
u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
u64 pebs;
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
struct cpu_hw_events *cpuc;
|
2009-05-13 06:12:51 +00:00
|
|
|
unsigned long flags;
|
2008-12-09 11:18:18 +00:00
|
|
|
int cpu, idx;
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
if (!x86_pmu.num_counters)
|
2008-12-09 11:18:18 +00:00
|
|
|
return;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-05-13 06:12:51 +00:00
|
|
|
local_irq_save(flags);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
|
|
|
cpu = smp_processor_id();
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
cpuc = &per_cpu(cpu_hw_events, cpu);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-04-29 10:47:13 +00:00
|
|
|
if (x86_pmu.version >= 2) {
|
2009-02-28 13:15:39 +00:00
|
|
|
rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
|
|
|
|
rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
|
|
|
|
rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
|
|
|
|
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
|
2009-02-28 13:15:39 +00:00
|
|
|
|
|
|
|
pr_info("\n");
|
|
|
|
pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl);
|
|
|
|
pr_info("CPU#%d: status: %016llx\n", cpu, status);
|
|
|
|
pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow);
|
|
|
|
pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs);
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
}
|
2010-03-08 12:51:31 +00:00
|
|
|
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
2011-02-02 16:40:57 +00:00
|
|
|
rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
|
|
|
|
rdmsrl(x86_pmu_event_addr(idx), pmc_count);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-06-24 06:13:48 +00:00
|
|
|
prev_left = per_cpu(pmc_prev_left[idx], cpu);
|
2008-12-03 09:39:53 +00:00
|
|
|
|
2009-02-28 13:15:39 +00:00
|
|
|
pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n",
|
2008-12-03 09:39:53 +00:00
|
|
|
cpu, idx, pmc_ctrl);
|
2009-02-28 13:15:39 +00:00
|
|
|
pr_info("CPU#%d: gen-PMC%d count: %016llx\n",
|
2008-12-03 09:39:53 +00:00
|
|
|
cpu, idx, pmc_count);
|
2009-02-28 13:15:39 +00:00
|
|
|
pr_info("CPU#%d: gen-PMC%d left: %016llx\n",
|
2008-12-13 08:00:03 +00:00
|
|
|
cpu, idx, prev_left);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
2010-03-29 16:36:50 +00:00
|
|
|
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
|
2008-12-22 10:10:42 +00:00
|
|
|
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
|
|
|
|
|
2009-02-28 13:15:39 +00:00
|
|
|
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
|
2008-12-22 10:10:42 +00:00
|
|
|
cpu, idx, pmc_count);
|
|
|
|
}
|
2009-05-13 06:12:51 +00:00
|
|
|
local_irq_restore(flags);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
void x86_pmu_stop(struct perf_event *event, int flags)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
2010-02-08 15:06:01 +00:00
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
|
|
|
|
x86_pmu.disable(event);
|
|
|
|
cpuc->events[hwc->idx] = NULL;
|
|
|
|
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
|
|
|
|
hwc->state |= PERF_HES_STOPPED;
|
|
|
|
}
|
2009-07-21 13:56:48 +00:00
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
|
|
|
|
/*
|
|
|
|
* Drain the remaining delta count out of a event
|
|
|
|
* that we are disabling:
|
|
|
|
*/
|
|
|
|
x86_perf_event_update(event);
|
|
|
|
hwc->state |= PERF_HES_UPTODATE;
|
|
|
|
}
|
2010-01-25 14:58:43 +00:00
|
|
|
}
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
static void x86_pmu_del(struct perf_event *event, int flags)
|
2010-01-25 14:58:43 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
int i;
|
|
|
|
|
perf_events: Fix event scheduling issues introduced by transactional API
The transactional API patch between the generic and model-specific
code introduced several important bugs with event scheduling, at
least on X86. If you had pinned events, e.g., watchdog, and were
over-committing the PMU, you would get bogus counts. The bug was
showing up on Intel CPU because events would move around more
often that on AMD. But the problem also existed on AMD, though
harder to expose.
The issues were:
- group_sched_in() was missing a cancel_txn() in the error path
- cpuc->n_added was not properly maintained, leading to missing
actions in hw_perf_enable(), i.e., n_running being 0. You cannot
update n_added until you know the transaction has succeeded. In
case of failed transaction n_added was not adjusted back.
- in case of failed transactions, event_sched_out() was called
and eventually invoked x86_disable_event() to touch the HW reg.
But with transactions, on X86, event_sched_in() does not touch
HW registers, it simply collects events into a list. Thus, you
could end up calling x86_disable_event() on a counter which
did not correspond to the current event when idx != -1.
The patch modifies the generic and X86 code to avoid all those problems.
First, we keep track of the number of events added last. In case the
transaction fails, we substract them from n_added. This approach is
necessary (as opposed to delaying updates to n_added) because not all
event updates use the transaction API, e.g., single events.
Second, we encapsulate the event_sched_in() and event_sched_out() in
group_sched_in() inside the transaction. That makes the operations
symmetrical and you can also detect that you are inside a transaction
and skip the HW reg access by checking cpuc->group_flag.
With this patch, you can now overcommit the PMU even with pinned
system-wide events present and still get valid counts.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1274796225.5882.1389.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-25 14:23:10 +00:00
|
|
|
/*
|
|
|
|
* If we're called during a txn, we don't need to do anything.
|
|
|
|
* The events never got scheduled and ->cancel_txn will truncate
|
|
|
|
* the event_list.
|
|
|
|
*/
|
2010-05-25 15:49:05 +00:00
|
|
|
if (cpuc->group_flag & PERF_EVENT_TXN)
|
perf_events: Fix event scheduling issues introduced by transactional API
The transactional API patch between the generic and model-specific
code introduced several important bugs with event scheduling, at
least on X86. If you had pinned events, e.g., watchdog, and were
over-committing the PMU, you would get bogus counts. The bug was
showing up on Intel CPU because events would move around more
often that on AMD. But the problem also existed on AMD, though
harder to expose.
The issues were:
- group_sched_in() was missing a cancel_txn() in the error path
- cpuc->n_added was not properly maintained, leading to missing
actions in hw_perf_enable(), i.e., n_running being 0. You cannot
update n_added until you know the transaction has succeeded. In
case of failed transaction n_added was not adjusted back.
- in case of failed transactions, event_sched_out() was called
and eventually invoked x86_disable_event() to touch the HW reg.
But with transactions, on X86, event_sched_in() does not touch
HW registers, it simply collects events into a list. Thus, you
could end up calling x86_disable_event() on a counter which
did not correspond to the current event when idx != -1.
The patch modifies the generic and X86 code to avoid all those problems.
First, we keep track of the number of events added last. In case the
transaction fails, we substract them from n_added. This approach is
necessary (as opposed to delaying updates to n_added) because not all
event updates use the transaction API, e.g., single events.
Second, we encapsulate the event_sched_in() and event_sched_out() in
group_sched_in() inside the transaction. That makes the operations
symmetrical and you can also detect that you are inside a transaction
and skip the HW reg access by checking cpuc->group_flag.
With this patch, you can now overcommit the PMU even with pinned
system-wide events present and still get valid counts.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1274796225.5882.1389.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-25 14:23:10 +00:00
|
|
|
return;
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
x86_pmu_stop(event, PERF_EF_UPDATE);
|
2009-06-22 14:35:24 +00:00
|
|
|
|
2010-01-18 08:58:01 +00:00
|
|
|
for (i = 0; i < cpuc->n_events; i++) {
|
|
|
|
if (event == cpuc->event_list[i]) {
|
|
|
|
|
|
|
|
if (x86_pmu.put_event_constraints)
|
|
|
|
x86_pmu.put_event_constraints(cpuc, event);
|
|
|
|
|
|
|
|
while (++i < cpuc->n_events)
|
|
|
|
cpuc->event_list[i-1] = cpuc->event_list[i];
|
|
|
|
|
|
|
|
--cpuc->n_events;
|
2010-01-25 10:57:25 +00:00
|
|
|
break;
|
2010-01-18 08:58:01 +00:00
|
|
|
}
|
|
|
|
}
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
perf_event_update_userpage(event);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
int x86_pmu_handle_irq(struct pt_regs *regs)
|
2009-04-29 10:47:21 +00:00
|
|
|
{
|
2009-06-10 19:02:22 +00:00
|
|
|
struct perf_sample_data data;
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
struct cpu_hw_events *cpuc;
|
|
|
|
struct perf_event *event;
|
2009-07-08 21:46:14 +00:00
|
|
|
int idx, handled = 0;
|
2009-05-15 06:26:20 +00:00
|
|
|
u64 val;
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
cpuc = &__get_cpu_var(cpu_hw_events);
|
2009-05-13 11:21:36 +00:00
|
|
|
|
2011-04-27 10:32:33 +00:00
|
|
|
/*
|
|
|
|
* Some chipsets need to unmask the LVTPC in a particular spot
|
|
|
|
* inside the nmi handler. As a result, the unmasking was pushed
|
|
|
|
* into all the nmi handlers.
|
|
|
|
*
|
|
|
|
* This generic handler doesn't seem to have any issues where the
|
|
|
|
* unmasking occurs so it was left at the top.
|
|
|
|
*/
|
|
|
|
apic_write(APIC_LVTPC, APIC_DM_NMI);
|
|
|
|
|
2010-03-29 16:36:50 +00:00
|
|
|
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
2010-09-15 16:20:34 +00:00
|
|
|
if (!test_bit(idx, cpuc->active_mask)) {
|
|
|
|
/*
|
|
|
|
* Though we deactivated the counter some cpus
|
|
|
|
* might still deliver spurious interrupts still
|
|
|
|
* in flight. Catch them:
|
|
|
|
*/
|
|
|
|
if (__test_and_clear_bit(idx, cpuc->running))
|
|
|
|
handled++;
|
2009-04-29 10:47:21 +00:00
|
|
|
continue;
|
2010-09-15 16:20:34 +00:00
|
|
|
}
|
2009-05-13 11:21:36 +00:00
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
event = cpuc->events[idx];
|
2009-05-14 12:52:17 +00:00
|
|
|
|
2010-03-02 19:18:39 +00:00
|
|
|
val = x86_perf_event_update(event);
|
2010-03-29 16:36:50 +00:00
|
|
|
if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
|
2009-05-25 15:39:04 +00:00
|
|
|
continue;
|
2009-05-13 11:21:36 +00:00
|
|
|
|
2009-06-10 19:34:59 +00:00
|
|
|
/*
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
* event overflow
|
2009-06-10 19:34:59 +00:00
|
|
|
*/
|
perf, x86: Try to handle unknown nmis with an enabled PMU
When the PMU is enabled it is valid to have unhandled nmis, two
events could trigger 'simultaneously' raising two back-to-back
NMIs. If the first NMI handles both, the latter will be empty
and daze the CPU.
The solution to avoid an 'unknown nmi' massage in this case was
simply to stop the nmi handler chain when the PMU is enabled by
stating the nmi was handled. This has the drawback that a) we
can not detect unknown nmis anymore, and b) subsequent nmi
handlers are not called.
This patch addresses this. Now, we check this unknown NMI if it
could be a PMU back-to-back NMI. Otherwise we pass it and let
the kernel handle the unknown nmi.
This is a debug log:
cpu #6, nmi #32333, skip_nmi #32330, handled = 1, time = 1934364430
cpu #6, nmi #32334, skip_nmi #32330, handled = 1, time = 1934704616
cpu #6, nmi #32335, skip_nmi #32336, handled = 2, time = 1936032320
cpu #6, nmi #32336, skip_nmi #32336, handled = 0, time = 1936034139
cpu #6, nmi #32337, skip_nmi #32336, handled = 1, time = 1936120100
cpu #6, nmi #32338, skip_nmi #32336, handled = 1, time = 1936404607
cpu #6, nmi #32339, skip_nmi #32336, handled = 1, time = 1937983416
cpu #6, nmi #32340, skip_nmi #32341, handled = 2, time = 1938201032
cpu #6, nmi #32341, skip_nmi #32341, handled = 0, time = 1938202830
cpu #6, nmi #32342, skip_nmi #32341, handled = 1, time = 1938443743
cpu #6, nmi #32343, skip_nmi #32341, handled = 1, time = 1939956552
cpu #6, nmi #32344, skip_nmi #32341, handled = 1, time = 1940073224
cpu #6, nmi #32345, skip_nmi #32341, handled = 1, time = 1940485677
cpu #6, nmi #32346, skip_nmi #32347, handled = 2, time = 1941947772
cpu #6, nmi #32347, skip_nmi #32347, handled = 1, time = 1941949818
cpu #6, nmi #32348, skip_nmi #32347, handled = 0, time = 1941951591
Uhhuh. NMI received for unknown reason 00 on CPU 6.
Do you have a strange power saving mode enabled?
Dazed and confused, but trying to continue
Deltas:
nmi #32334 340186
nmi #32335 1327704
nmi #32336 1819 <<<< back-to-back nmi [1]
nmi #32337 85961
nmi #32338 284507
nmi #32339 1578809
nmi #32340 217616
nmi #32341 1798 <<<< back-to-back nmi [2]
nmi #32342 240913
nmi #32343 1512809
nmi #32344 116672
nmi #32345 412453
nmi #32346 1462095 <<<< 1st nmi (standard) handling 2 counters
nmi #32347 2046 <<<< 2nd nmi (back-to-back) handling one
counter nmi #32348 1773 <<<< 3rd nmi (back-to-back)
handling no counter! [3]
For back-to-back nmi detection there are the following rules:
The PMU nmi handler was handling more than one counter and no
counter was handled in the subsequent nmi (see [1] and [2]
above).
There is another case if there are two subsequent back-to-back
nmis [3]. The 2nd is detected as back-to-back because the first
handled more than one counter. If the second handles one counter
and the 3rd handles nothing, we drop the 3rd nmi because it
could be a back-to-back nmi.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ renamed nmi variable to pmu_nmi to avoid clash with .nmi in entry.S ]
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: gorcunov@gmail.com
Cc: fweisbec@gmail.com
Cc: ying.huang@intel.com
Cc: ming.m.lin@intel.com
Cc: eranian@google.com
LKML-Reference: <1283454469-1909-3-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-02 19:07:48 +00:00
|
|
|
handled++;
|
2012-04-02 18:19:08 +00:00
|
|
|
perf_sample_data_init(&data, 0, event->hw.last_period);
|
2009-06-10 19:34:59 +00:00
|
|
|
|
2010-03-02 19:16:01 +00:00
|
|
|
if (!x86_perf_event_set_period(event))
|
2009-06-02 14:08:20 +00:00
|
|
|
continue;
|
|
|
|
|
2011-06-27 12:41:57 +00:00
|
|
|
if (perf_event_overflow(event, &data, regs))
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
x86_pmu_stop(event, 0);
|
2009-04-29 10:47:21 +00:00
|
|
|
}
|
2009-05-13 11:21:36 +00:00
|
|
|
|
2009-06-10 19:34:59 +00:00
|
|
|
if (handled)
|
|
|
|
inc_irq_stat(apic_perf_irqs);
|
|
|
|
|
2009-04-29 10:47:21 +00:00
|
|
|
return handled;
|
|
|
|
}
|
2009-04-29 10:47:05 +00:00
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
void perf_events_lapic_init(void)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
2009-08-11 08:40:08 +00:00
|
|
|
if (!x86_pmu.apic || !x86_pmu_initialized())
|
2008-12-03 09:39:53 +00:00
|
|
|
return;
|
2009-04-29 10:47:20 +00:00
|
|
|
|
2008-12-03 09:39:53 +00:00
|
|
|
/*
|
2009-05-29 05:28:35 +00:00
|
|
|
* Always use NMI for PMU
|
2008-12-03 09:39:53 +00:00
|
|
|
*/
|
2009-05-29 05:28:35 +00:00
|
|
|
apic_write(APIC_LVTPC, APIC_DM_NMI);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __kprobes
|
2011-09-30 19:06:21 +00:00
|
|
|
perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
|
2008-12-03 09:39:53 +00:00
|
|
|
{
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
if (!atomic_read(&active_events))
|
2011-09-30 19:06:21 +00:00
|
|
|
return NMI_DONE;
|
perf, x86: Try to handle unknown nmis with an enabled PMU
When the PMU is enabled it is valid to have unhandled nmis, two
events could trigger 'simultaneously' raising two back-to-back
NMIs. If the first NMI handles both, the latter will be empty
and daze the CPU.
The solution to avoid an 'unknown nmi' massage in this case was
simply to stop the nmi handler chain when the PMU is enabled by
stating the nmi was handled. This has the drawback that a) we
can not detect unknown nmis anymore, and b) subsequent nmi
handlers are not called.
This patch addresses this. Now, we check this unknown NMI if it
could be a PMU back-to-back NMI. Otherwise we pass it and let
the kernel handle the unknown nmi.
This is a debug log:
cpu #6, nmi #32333, skip_nmi #32330, handled = 1, time = 1934364430
cpu #6, nmi #32334, skip_nmi #32330, handled = 1, time = 1934704616
cpu #6, nmi #32335, skip_nmi #32336, handled = 2, time = 1936032320
cpu #6, nmi #32336, skip_nmi #32336, handled = 0, time = 1936034139
cpu #6, nmi #32337, skip_nmi #32336, handled = 1, time = 1936120100
cpu #6, nmi #32338, skip_nmi #32336, handled = 1, time = 1936404607
cpu #6, nmi #32339, skip_nmi #32336, handled = 1, time = 1937983416
cpu #6, nmi #32340, skip_nmi #32341, handled = 2, time = 1938201032
cpu #6, nmi #32341, skip_nmi #32341, handled = 0, time = 1938202830
cpu #6, nmi #32342, skip_nmi #32341, handled = 1, time = 1938443743
cpu #6, nmi #32343, skip_nmi #32341, handled = 1, time = 1939956552
cpu #6, nmi #32344, skip_nmi #32341, handled = 1, time = 1940073224
cpu #6, nmi #32345, skip_nmi #32341, handled = 1, time = 1940485677
cpu #6, nmi #32346, skip_nmi #32347, handled = 2, time = 1941947772
cpu #6, nmi #32347, skip_nmi #32347, handled = 1, time = 1941949818
cpu #6, nmi #32348, skip_nmi #32347, handled = 0, time = 1941951591
Uhhuh. NMI received for unknown reason 00 on CPU 6.
Do you have a strange power saving mode enabled?
Dazed and confused, but trying to continue
Deltas:
nmi #32334 340186
nmi #32335 1327704
nmi #32336 1819 <<<< back-to-back nmi [1]
nmi #32337 85961
nmi #32338 284507
nmi #32339 1578809
nmi #32340 217616
nmi #32341 1798 <<<< back-to-back nmi [2]
nmi #32342 240913
nmi #32343 1512809
nmi #32344 116672
nmi #32345 412453
nmi #32346 1462095 <<<< 1st nmi (standard) handling 2 counters
nmi #32347 2046 <<<< 2nd nmi (back-to-back) handling one
counter nmi #32348 1773 <<<< 3rd nmi (back-to-back)
handling no counter! [3]
For back-to-back nmi detection there are the following rules:
The PMU nmi handler was handling more than one counter and no
counter was handled in the subsequent nmi (see [1] and [2]
above).
There is another case if there are two subsequent back-to-back
nmis [3]. The 2nd is detected as back-to-back because the first
handled more than one counter. If the second handles one counter
and the 3rd handles nothing, we drop the 3rd nmi because it
could be a back-to-back nmi.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ renamed nmi variable to pmu_nmi to avoid clash with .nmi in entry.S ]
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: gorcunov@gmail.com
Cc: fweisbec@gmail.com
Cc: ying.huang@intel.com
Cc: ming.m.lin@intel.com
Cc: eranian@google.com
LKML-Reference: <1283454469-1909-3-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-02 19:07:48 +00:00
|
|
|
|
2011-09-30 19:06:21 +00:00
|
|
|
return x86_pmu.handle_irq(regs);
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
|
|
|
|
2011-08-30 23:41:05 +00:00
|
|
|
struct event_constraint emptyconstraint;
|
|
|
|
struct event_constraint unconstrained;
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
|
2010-03-05 12:01:18 +00:00
|
|
|
static int __cpuinit
|
|
|
|
x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
|
|
|
|
{
|
|
|
|
unsigned int cpu = (long)hcpu;
|
2011-07-22 11:41:54 +00:00
|
|
|
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
|
2010-03-23 18:31:15 +00:00
|
|
|
int ret = NOTIFY_OK;
|
2010-03-05 12:01:18 +00:00
|
|
|
|
|
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
|
|
case CPU_UP_PREPARE:
|
2011-07-22 11:41:54 +00:00
|
|
|
cpuc->kfree_on_online = NULL;
|
2010-03-05 12:01:18 +00:00
|
|
|
if (x86_pmu.cpu_prepare)
|
2010-03-23 18:31:15 +00:00
|
|
|
ret = x86_pmu.cpu_prepare(cpu);
|
2010-03-05 12:01:18 +00:00
|
|
|
break;
|
|
|
|
|
|
|
|
case CPU_STARTING:
|
2011-11-20 22:30:47 +00:00
|
|
|
if (x86_pmu.attr_rdpmc)
|
|
|
|
set_in_cr4(X86_CR4_PCE);
|
2010-03-05 12:01:18 +00:00
|
|
|
if (x86_pmu.cpu_starting)
|
|
|
|
x86_pmu.cpu_starting(cpu);
|
|
|
|
break;
|
|
|
|
|
2011-07-22 11:41:54 +00:00
|
|
|
case CPU_ONLINE:
|
|
|
|
kfree(cpuc->kfree_on_online);
|
|
|
|
break;
|
|
|
|
|
2010-03-05 12:01:18 +00:00
|
|
|
case CPU_DYING:
|
|
|
|
if (x86_pmu.cpu_dying)
|
|
|
|
x86_pmu.cpu_dying(cpu);
|
|
|
|
break;
|
|
|
|
|
2010-03-23 18:31:15 +00:00
|
|
|
case CPU_UP_CANCELED:
|
2010-03-05 12:01:18 +00:00
|
|
|
case CPU_DEAD:
|
|
|
|
if (x86_pmu.cpu_dead)
|
|
|
|
x86_pmu.cpu_dead(cpu);
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2010-03-23 18:31:15 +00:00
|
|
|
return ret;
|
2010-03-05 12:01:18 +00:00
|
|
|
}
|
|
|
|
|
2009-12-10 16:56:34 +00:00
|
|
|
static void __init pmu_check_apic(void)
|
|
|
|
{
|
|
|
|
if (cpu_has_apic)
|
|
|
|
return;
|
|
|
|
|
|
|
|
x86_pmu.apic = 0;
|
|
|
|
pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
|
|
|
|
pr_info("no hardware sampling interrupt available.\n");
|
|
|
|
}
|
|
|
|
|
2012-03-15 19:09:14 +00:00
|
|
|
static struct attribute_group x86_pmu_format_group = {
|
|
|
|
.name = "format",
|
|
|
|
.attrs = NULL,
|
|
|
|
};
|
|
|
|
|
2011-01-21 23:30:01 +00:00
|
|
|
static int __init init_hw_perf_events(void)
|
2009-02-27 12:39:09 +00:00
|
|
|
{
|
2011-12-06 13:07:15 +00:00
|
|
|
struct x86_pmu_quirk *quirk;
|
2009-04-29 10:47:10 +00:00
|
|
|
int err;
|
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
pr_info("Performance Events: ");
|
2009-05-29 09:25:09 +00:00
|
|
|
|
2009-02-27 12:39:09 +00:00
|
|
|
switch (boot_cpu_data.x86_vendor) {
|
|
|
|
case X86_VENDOR_INTEL:
|
2009-04-29 10:47:10 +00:00
|
|
|
err = intel_pmu_init();
|
2009-02-27 12:39:09 +00:00
|
|
|
break;
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
case X86_VENDOR_AMD:
|
2009-04-29 10:47:10 +00:00
|
|
|
err = amd_pmu_init();
|
x86: AMD Support for perf_counter
Supported basic performance counter for AMD K7 and later:
$ perfstat -e 0,1,2,3,4,5,-1,-2,-3,-4,-5 ls > /dev/null
Performance counter stats for 'ls':
12.298610 task clock ticks (msecs)
3298477 CPU cycles (events)
1406354 instructions (events)
749035 cache references (events)
16939 cache misses (events)
100589 branches (events)
11159 branch misses (events)
7.627540 cpu clock ticks (msecs)
12.298610 task clock ticks (msecs)
500 pagefaults (events)
6 context switches (events)
3 CPU migrations (events)
Wall-clock time elapsed: 8.672290 msecs
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-27 14:45:14 +00:00
|
|
|
break;
|
2009-04-29 10:47:00 +00:00
|
|
|
default:
|
2010-11-25 17:38:29 +00:00
|
|
|
return 0;
|
2009-02-27 12:39:09 +00:00
|
|
|
}
|
2009-05-29 09:25:09 +00:00
|
|
|
if (err != 0) {
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
pr_cont("no PMU driver, software events only.\n");
|
2010-11-25 17:38:29 +00:00
|
|
|
return 0;
|
2009-05-29 09:25:09 +00:00
|
|
|
}
|
2009-02-27 12:39:09 +00:00
|
|
|
|
2009-12-10 16:56:34 +00:00
|
|
|
pmu_check_apic();
|
|
|
|
|
2010-11-22 21:55:23 +00:00
|
|
|
/* sanity check that the hardware exists or is emulated */
|
2010-12-08 14:56:23 +00:00
|
|
|
if (!check_hw_exists())
|
2010-11-25 17:38:29 +00:00
|
|
|
return 0;
|
2010-11-22 21:55:23 +00:00
|
|
|
|
2009-05-29 09:25:09 +00:00
|
|
|
pr_cont("%s PMU driver.\n", x86_pmu.name);
|
2009-04-29 10:47:13 +00:00
|
|
|
|
2011-12-06 13:07:15 +00:00
|
|
|
for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
|
|
|
|
quirk->func();
|
2010-03-04 20:49:01 +00:00
|
|
|
|
2012-06-20 18:46:34 +00:00
|
|
|
if (!x86_pmu.intel_ctrl)
|
|
|
|
x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
|
2008-12-03 09:39:53 +00:00
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
perf_events_lapic_init();
|
2011-09-30 19:06:21 +00:00
|
|
|
register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
|
2009-05-29 09:25:09 +00:00
|
|
|
|
2010-01-22 15:32:17 +00:00
|
|
|
unconstrained = (struct event_constraint)
|
2010-03-29 16:36:50 +00:00
|
|
|
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
|
2011-11-18 11:35:22 +00:00
|
|
|
0, x86_pmu.num_counters, 0);
|
2010-01-22 15:32:17 +00:00
|
|
|
|
2011-11-20 22:30:47 +00:00
|
|
|
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
|
2012-03-15 19:09:14 +00:00
|
|
|
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
|
2011-11-20 22:30:47 +00:00
|
|
|
|
2009-09-21 10:20:38 +00:00
|
|
|
pr_info("... version: %d\n", x86_pmu.version);
|
2010-03-29 16:36:50 +00:00
|
|
|
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
|
|
|
|
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
|
|
|
|
pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
|
2009-09-21 10:20:38 +00:00
|
|
|
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
|
2010-03-29 16:36:50 +00:00
|
|
|
pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed);
|
2010-03-17 11:49:13 +00:00
|
|
|
pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl);
|
2010-03-05 12:01:18 +00:00
|
|
|
|
2010-11-17 22:17:36 +00:00
|
|
|
perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
|
2010-03-05 12:01:18 +00:00
|
|
|
perf_cpu_notifier(x86_pmu_notifier);
|
2010-11-25 17:38:29 +00:00
|
|
|
|
|
|
|
return 0;
|
2008-12-03 09:39:53 +00:00
|
|
|
}
|
2010-11-25 17:38:29 +00:00
|
|
|
early_initcall(init_hw_perf_events);
|
2008-12-11 11:46:46 +00:00
|
|
|
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
static inline void x86_pmu_read(struct perf_event *event)
|
2008-12-13 08:00:03 +00:00
|
|
|
{
|
2010-03-02 19:18:39 +00:00
|
|
|
x86_perf_event_update(event);
|
2008-12-13 08:00:03 +00:00
|
|
|
}
|
|
|
|
|
2010-04-23 05:56:12 +00:00
|
|
|
/*
|
|
|
|
* Start group events scheduling transaction
|
|
|
|
* Set the flag to make pmu::enable() not perform the
|
|
|
|
* schedulability test, it will be performed at commit time
|
|
|
|
*/
|
2010-06-11 11:35:57 +00:00
|
|
|
static void x86_pmu_start_txn(struct pmu *pmu)
|
2010-04-23 05:56:12 +00:00
|
|
|
{
|
2010-06-14 06:49:00 +00:00
|
|
|
perf_pmu_disable(pmu);
|
2010-12-18 15:28:55 +00:00
|
|
|
__this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN);
|
|
|
|
__this_cpu_write(cpu_hw_events.n_txn, 0);
|
2010-04-23 05:56:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Stop group events scheduling transaction
|
|
|
|
* Clear the flag and pmu::enable() will perform the
|
|
|
|
* schedulability test.
|
|
|
|
*/
|
2010-06-11 11:35:57 +00:00
|
|
|
static void x86_pmu_cancel_txn(struct pmu *pmu)
|
2010-04-23 05:56:12 +00:00
|
|
|
{
|
2010-12-18 15:28:55 +00:00
|
|
|
__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
|
perf_events: Fix event scheduling issues introduced by transactional API
The transactional API patch between the generic and model-specific
code introduced several important bugs with event scheduling, at
least on X86. If you had pinned events, e.g., watchdog, and were
over-committing the PMU, you would get bogus counts. The bug was
showing up on Intel CPU because events would move around more
often that on AMD. But the problem also existed on AMD, though
harder to expose.
The issues were:
- group_sched_in() was missing a cancel_txn() in the error path
- cpuc->n_added was not properly maintained, leading to missing
actions in hw_perf_enable(), i.e., n_running being 0. You cannot
update n_added until you know the transaction has succeeded. In
case of failed transaction n_added was not adjusted back.
- in case of failed transactions, event_sched_out() was called
and eventually invoked x86_disable_event() to touch the HW reg.
But with transactions, on X86, event_sched_in() does not touch
HW registers, it simply collects events into a list. Thus, you
could end up calling x86_disable_event() on a counter which
did not correspond to the current event when idx != -1.
The patch modifies the generic and X86 code to avoid all those problems.
First, we keep track of the number of events added last. In case the
transaction fails, we substract them from n_added. This approach is
necessary (as opposed to delaying updates to n_added) because not all
event updates use the transaction API, e.g., single events.
Second, we encapsulate the event_sched_in() and event_sched_out() in
group_sched_in() inside the transaction. That makes the operations
symmetrical and you can also detect that you are inside a transaction
and skip the HW reg access by checking cpuc->group_flag.
With this patch, you can now overcommit the PMU even with pinned
system-wide events present and still get valid counts.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1274796225.5882.1389.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-25 14:23:10 +00:00
|
|
|
/*
|
|
|
|
* Truncate the collected events.
|
|
|
|
*/
|
2010-12-18 15:28:55 +00:00
|
|
|
__this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
|
|
|
|
__this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
|
2010-06-14 06:49:00 +00:00
|
|
|
perf_pmu_enable(pmu);
|
2010-04-23 05:56:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Commit group events scheduling transaction
|
|
|
|
* Perform the group schedulability test as a whole
|
|
|
|
* Return 0 if success
|
|
|
|
*/
|
2010-06-11 11:35:57 +00:00
|
|
|
static int x86_pmu_commit_txn(struct pmu *pmu)
|
2010-04-23 05:56:12 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
int assign[X86_PMC_IDX_MAX];
|
|
|
|
int n, ret;
|
|
|
|
|
|
|
|
n = cpuc->n_events;
|
|
|
|
|
|
|
|
if (!x86_pmu_initialized())
|
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
ret = x86_pmu.schedule_events(cpuc, n, assign);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* copy new assignment, now we know it is possible
|
|
|
|
* will be used by hw_perf_enable()
|
|
|
|
*/
|
|
|
|
memcpy(cpuc->assign, assign, n*sizeof(int));
|
|
|
|
|
2010-05-25 15:49:05 +00:00
|
|
|
cpuc->group_flag &= ~PERF_EVENT_TXN;
|
2010-06-14 06:49:00 +00:00
|
|
|
perf_pmu_enable(pmu);
|
2010-04-23 05:56:12 +00:00
|
|
|
return 0;
|
|
|
|
}
|
2011-06-06 14:57:08 +00:00
|
|
|
/*
|
|
|
|
* a fake_cpuc is used to validate event groups. Due to
|
|
|
|
* the extra reg logic, we need to also allocate a fake
|
|
|
|
* per_core and per_cpu structure. Otherwise, group events
|
|
|
|
* using extra reg may conflict without the kernel being
|
|
|
|
* able to catch this when the last event gets added to
|
|
|
|
* the group.
|
|
|
|
*/
|
|
|
|
static void free_fake_cpuc(struct cpu_hw_events *cpuc)
|
|
|
|
{
|
|
|
|
kfree(cpuc->shared_regs);
|
|
|
|
kfree(cpuc);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct cpu_hw_events *allocate_fake_cpuc(void)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc;
|
|
|
|
int cpu = raw_smp_processor_id();
|
|
|
|
|
|
|
|
cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL);
|
|
|
|
if (!cpuc)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
|
|
|
|
/* only needed, if we have extra_regs */
|
|
|
|
if (x86_pmu.extra_regs) {
|
|
|
|
cpuc->shared_regs = allocate_shared_regs(cpu);
|
|
|
|
if (!cpuc->shared_regs)
|
|
|
|
goto error;
|
|
|
|
}
|
2012-06-05 13:30:31 +00:00
|
|
|
cpuc->is_fake = 1;
|
2011-06-06 14:57:08 +00:00
|
|
|
return cpuc;
|
|
|
|
error:
|
|
|
|
free_fake_cpuc(cpuc);
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
}
|
2010-04-23 05:56:12 +00:00
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
/*
|
|
|
|
* validate that we can schedule this event
|
|
|
|
*/
|
|
|
|
static int validate_event(struct perf_event *event)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *fake_cpuc;
|
|
|
|
struct event_constraint *c;
|
|
|
|
int ret = 0;
|
|
|
|
|
2011-06-06 14:57:08 +00:00
|
|
|
fake_cpuc = allocate_fake_cpuc();
|
|
|
|
if (IS_ERR(fake_cpuc))
|
|
|
|
return PTR_ERR(fake_cpuc);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
c = x86_pmu.get_event_constraints(fake_cpuc, event);
|
|
|
|
|
|
|
|
if (!c || !c->weight)
|
2011-11-09 16:56:37 +00:00
|
|
|
ret = -EINVAL;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
if (x86_pmu.put_event_constraints)
|
|
|
|
x86_pmu.put_event_constraints(fake_cpuc, event);
|
|
|
|
|
2011-06-06 14:57:08 +00:00
|
|
|
free_fake_cpuc(fake_cpuc);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-01-18 08:58:01 +00:00
|
|
|
/*
|
|
|
|
* validate a single event group
|
|
|
|
*
|
|
|
|
* validation include:
|
2010-01-27 07:39:39 +00:00
|
|
|
* - check events are compatible which each other
|
|
|
|
* - events do not compete for the same counter
|
|
|
|
* - number of events <= number of counters
|
2010-01-18 08:58:01 +00:00
|
|
|
*
|
|
|
|
* validation ensures the group can be loaded onto the
|
|
|
|
* PMU if it was the only group available.
|
|
|
|
*/
|
2009-10-08 09:56:07 +00:00
|
|
|
static int validate_group(struct perf_event *event)
|
|
|
|
{
|
2010-01-18 08:58:01 +00:00
|
|
|
struct perf_event *leader = event->group_leader;
|
2010-01-22 13:35:46 +00:00
|
|
|
struct cpu_hw_events *fake_cpuc;
|
2011-11-09 16:56:37 +00:00
|
|
|
int ret = -EINVAL, n;
|
2009-10-08 09:56:07 +00:00
|
|
|
|
2011-06-06 14:57:08 +00:00
|
|
|
fake_cpuc = allocate_fake_cpuc();
|
|
|
|
if (IS_ERR(fake_cpuc))
|
|
|
|
return PTR_ERR(fake_cpuc);
|
2010-01-18 08:58:01 +00:00
|
|
|
/*
|
|
|
|
* the event is not yet connected with its
|
|
|
|
* siblings therefore we must first collect
|
|
|
|
* existing siblings, then add the new event
|
|
|
|
* before we can simulate the scheduling
|
|
|
|
*/
|
2010-01-22 13:35:46 +00:00
|
|
|
n = collect_events(fake_cpuc, leader, true);
|
2010-01-18 08:58:01 +00:00
|
|
|
if (n < 0)
|
2011-06-06 14:57:08 +00:00
|
|
|
goto out;
|
2009-10-08 09:56:07 +00:00
|
|
|
|
2010-01-22 13:35:46 +00:00
|
|
|
fake_cpuc->n_events = n;
|
|
|
|
n = collect_events(fake_cpuc, event, false);
|
2010-01-18 08:58:01 +00:00
|
|
|
if (n < 0)
|
2011-06-06 14:57:08 +00:00
|
|
|
goto out;
|
2009-10-08 09:56:07 +00:00
|
|
|
|
2010-01-22 13:35:46 +00:00
|
|
|
fake_cpuc->n_events = n;
|
2010-01-18 08:58:01 +00:00
|
|
|
|
2010-03-11 16:54:39 +00:00
|
|
|
ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
|
2010-01-22 13:35:46 +00:00
|
|
|
|
|
|
|
out:
|
2011-06-06 14:57:08 +00:00
|
|
|
free_fake_cpuc(fake_cpuc);
|
2010-01-22 13:35:46 +00:00
|
|
|
return ret;
|
2009-10-08 09:56:07 +00:00
|
|
|
}
|
|
|
|
|
2011-01-21 23:30:01 +00:00
|
|
|
static int x86_pmu_event_init(struct perf_event *event)
|
2008-12-11 11:46:46 +00:00
|
|
|
{
|
2010-06-11 11:35:57 +00:00
|
|
|
struct pmu *tmp;
|
2008-12-11 11:46:46 +00:00
|
|
|
int err;
|
|
|
|
|
2010-06-11 11:35:08 +00:00
|
|
|
switch (event->attr.type) {
|
|
|
|
case PERF_TYPE_RAW:
|
|
|
|
case PERF_TYPE_HARDWARE:
|
|
|
|
case PERF_TYPE_HW_CACHE:
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = __x86_pmu_event_init(event);
|
2009-10-08 09:56:07 +00:00
|
|
|
if (!err) {
|
2010-01-21 15:39:01 +00:00
|
|
|
/*
|
|
|
|
* we temporarily connect event to its pmu
|
|
|
|
* such that validate_group() can classify
|
|
|
|
* it as an x86 event using is_x86_event()
|
|
|
|
*/
|
|
|
|
tmp = event->pmu;
|
|
|
|
event->pmu = &pmu;
|
|
|
|
|
2009-10-08 09:56:07 +00:00
|
|
|
if (event->group_leader != event)
|
|
|
|
err = validate_group(event);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
else
|
|
|
|
err = validate_event(event);
|
2010-01-21 15:39:01 +00:00
|
|
|
|
|
|
|
event->pmu = tmp;
|
2009-10-08 09:56:07 +00:00
|
|
|
}
|
2009-09-09 08:04:47 +00:00
|
|
|
if (err) {
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
if (event->destroy)
|
|
|
|
event->destroy(event);
|
2009-09-09 08:04:47 +00:00
|
|
|
}
|
2008-12-11 11:46:46 +00:00
|
|
|
|
2010-06-11 11:35:08 +00:00
|
|
|
return err;
|
2008-12-11 11:46:46 +00:00
|
|
|
}
|
2009-03-30 17:07:15 +00:00
|
|
|
|
2011-11-20 19:44:06 +00:00
|
|
|
static int x86_pmu_event_idx(struct perf_event *event)
|
|
|
|
{
|
|
|
|
int idx = event->hw.idx;
|
|
|
|
|
2012-03-22 16:26:36 +00:00
|
|
|
if (!x86_pmu.attr_rdpmc)
|
|
|
|
return 0;
|
|
|
|
|
2012-06-20 18:46:33 +00:00
|
|
|
if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) {
|
|
|
|
idx -= INTEL_PMC_IDX_FIXED;
|
2011-11-20 19:44:06 +00:00
|
|
|
idx |= 1 << 30;
|
|
|
|
}
|
|
|
|
|
|
|
|
return idx + 1;
|
|
|
|
}
|
|
|
|
|
2011-11-20 22:30:47 +00:00
|
|
|
static ssize_t get_attr_rdpmc(struct device *cdev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
char *buf)
|
|
|
|
{
|
|
|
|
return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void change_rdpmc(void *info)
|
|
|
|
{
|
|
|
|
bool enable = !!(unsigned long)info;
|
|
|
|
|
|
|
|
if (enable)
|
|
|
|
set_in_cr4(X86_CR4_PCE);
|
|
|
|
else
|
|
|
|
clear_in_cr4(X86_CR4_PCE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t set_attr_rdpmc(struct device *cdev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
const char *buf, size_t count)
|
|
|
|
{
|
2012-06-11 03:13:41 +00:00
|
|
|
unsigned long val;
|
|
|
|
ssize_t ret;
|
|
|
|
|
|
|
|
ret = kstrtoul(buf, 0, &val);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2011-11-20 22:30:47 +00:00
|
|
|
|
|
|
|
if (!!val != !!x86_pmu.attr_rdpmc) {
|
|
|
|
x86_pmu.attr_rdpmc = !!val;
|
|
|
|
smp_call_function(change_rdpmc, (void *)val, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
|
|
|
static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
|
|
|
|
|
|
|
|
static struct attribute *x86_pmu_attrs[] = {
|
|
|
|
&dev_attr_rdpmc.attr,
|
|
|
|
NULL,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct attribute_group x86_pmu_attr_group = {
|
|
|
|
.attrs = x86_pmu_attrs,
|
|
|
|
};
|
|
|
|
|
|
|
|
static const struct attribute_group *x86_pmu_attr_groups[] = {
|
|
|
|
&x86_pmu_attr_group,
|
2012-03-15 19:09:14 +00:00
|
|
|
&x86_pmu_format_group,
|
2011-11-20 22:30:47 +00:00
|
|
|
NULL,
|
|
|
|
};
|
|
|
|
|
2012-02-09 22:21:00 +00:00
|
|
|
static void x86_pmu_flush_branch_stack(void)
|
|
|
|
{
|
|
|
|
if (x86_pmu.flush_branch_stack)
|
|
|
|
x86_pmu.flush_branch_stack();
|
|
|
|
}
|
|
|
|
|
2012-06-08 12:50:50 +00:00
|
|
|
void perf_check_microcode(void)
|
|
|
|
{
|
|
|
|
if (x86_pmu.check_microcode)
|
|
|
|
x86_pmu.check_microcode();
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(perf_check_microcode);
|
|
|
|
|
2010-06-11 11:35:08 +00:00
|
|
|
static struct pmu pmu = {
|
2012-02-09 22:21:00 +00:00
|
|
|
.pmu_enable = x86_pmu_enable,
|
|
|
|
.pmu_disable = x86_pmu_disable,
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
|
2012-06-08 12:50:50 +00:00
|
|
|
.attr_groups = x86_pmu_attr_groups,
|
2011-11-20 22:30:47 +00:00
|
|
|
|
2012-06-08 12:50:50 +00:00
|
|
|
.event_init = x86_pmu_event_init,
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
|
2012-02-09 22:21:00 +00:00
|
|
|
.add = x86_pmu_add,
|
|
|
|
.del = x86_pmu_del,
|
|
|
|
.start = x86_pmu_start,
|
|
|
|
.stop = x86_pmu_stop,
|
|
|
|
.read = x86_pmu_read,
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
|
2012-06-08 12:50:50 +00:00
|
|
|
.start_txn = x86_pmu_start_txn,
|
|
|
|
.cancel_txn = x86_pmu_cancel_txn,
|
|
|
|
.commit_txn = x86_pmu_commit_txn,
|
2011-11-20 19:44:06 +00:00
|
|
|
|
2012-06-08 12:50:50 +00:00
|
|
|
.event_idx = x86_pmu_event_idx,
|
2012-02-09 22:21:00 +00:00
|
|
|
.flush_branch_stack = x86_pmu_flush_branch_stack,
|
2010-06-11 11:35:08 +00:00
|
|
|
};
|
|
|
|
|
2012-03-22 16:26:36 +00:00
|
|
|
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
|
2011-11-21 10:43:53 +00:00
|
|
|
{
|
2012-03-22 16:26:36 +00:00
|
|
|
userpg->cap_usr_time = 0;
|
|
|
|
userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
|
|
|
|
userpg->pmc_width = x86_pmu.cntval_bits;
|
|
|
|
|
2011-11-21 10:43:53 +00:00
|
|
|
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
|
|
|
|
return;
|
|
|
|
|
2012-03-22 16:26:36 +00:00
|
|
|
userpg->cap_usr_time = 1;
|
2011-11-21 10:43:53 +00:00
|
|
|
userpg->time_mult = this_cpu_read(cyc2ns);
|
|
|
|
userpg->time_shift = CYC2NS_SCALE_FACTOR;
|
|
|
|
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
|
|
|
|
}
|
|
|
|
|
2009-03-30 17:07:15 +00:00
|
|
|
/*
|
|
|
|
* callchain support
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int backtrace_stack(void *data, char *name)
|
|
|
|
{
|
2009-06-15 07:57:59 +00:00
|
|
|
return 0;
|
2009-03-30 17:07:15 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void backtrace_address(void *data, unsigned long addr, int reliable)
|
|
|
|
{
|
|
|
|
struct perf_callchain_entry *entry = data;
|
|
|
|
|
2010-06-29 17:34:05 +00:00
|
|
|
perf_callchain_store(entry, addr);
|
2009-03-30 17:07:15 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static const struct stacktrace_ops backtrace_ops = {
|
|
|
|
.stack = backtrace_stack,
|
|
|
|
.address = backtrace_address,
|
2009-12-17 04:40:34 +00:00
|
|
|
.walk_stack = print_context_stack_bp,
|
2009-03-30 17:07:15 +00:00
|
|
|
};
|
|
|
|
|
2010-06-30 21:03:51 +00:00
|
|
|
void
|
|
|
|
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
|
2009-03-30 17:07:15 +00:00
|
|
|
{
|
2010-07-01 14:20:36 +00:00
|
|
|
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
|
|
|
|
/* TODO: We don't support guest os callchain now */
|
2010-08-20 12:30:41 +00:00
|
|
|
return;
|
2010-07-01 14:20:36 +00:00
|
|
|
}
|
|
|
|
|
2010-06-29 17:34:05 +00:00
|
|
|
perf_callchain_store(entry, regs->ip);
|
2009-03-30 17:07:15 +00:00
|
|
|
|
2011-03-18 02:40:06 +00:00
|
|
|
dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
|
2009-03-30 17:07:15 +00:00
|
|
|
}
|
|
|
|
|
2012-04-20 22:41:35 +00:00
|
|
|
static inline int
|
|
|
|
valid_user_frame(const void __user *fp, unsigned long size)
|
|
|
|
{
|
|
|
|
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
|
|
|
|
}
|
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
static unsigned long get_segment_base(unsigned int segment)
|
|
|
|
{
|
|
|
|
struct desc_struct *desc;
|
|
|
|
int idx = segment >> 3;
|
|
|
|
|
|
|
|
if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
|
|
|
|
if (idx > LDT_ENTRIES)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (idx > current->active_mm->context.size)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
desc = current->active_mm->context.ldt;
|
|
|
|
} else {
|
|
|
|
if (idx > GDT_ENTRIES)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
desc = __this_cpu_ptr(&gdt_page.gdt[0]);
|
|
|
|
}
|
|
|
|
|
|
|
|
return get_desc_base(desc + idx);
|
|
|
|
}
|
|
|
|
|
2010-03-17 10:07:16 +00:00
|
|
|
#ifdef CONFIG_COMPAT
|
2012-02-19 18:06:34 +00:00
|
|
|
|
|
|
|
#include <asm/compat.h>
|
|
|
|
|
2010-03-17 10:07:16 +00:00
|
|
|
static inline int
|
|
|
|
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
|
2009-06-15 11:07:24 +00:00
|
|
|
{
|
2010-03-17 10:07:16 +00:00
|
|
|
/* 32-bit process in 64-bit kernel. */
|
2012-07-10 07:42:15 +00:00
|
|
|
unsigned long ss_base, cs_base;
|
2010-03-17 10:07:16 +00:00
|
|
|
struct stack_frame_ia32 frame;
|
|
|
|
const void __user *fp;
|
2009-06-15 11:07:24 +00:00
|
|
|
|
2010-03-17 10:07:16 +00:00
|
|
|
if (!test_thread_flag(TIF_IA32))
|
|
|
|
return 0;
|
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
cs_base = get_segment_base(regs->cs);
|
|
|
|
ss_base = get_segment_base(regs->ss);
|
|
|
|
|
|
|
|
fp = compat_ptr(ss_base + regs->bp);
|
2010-03-17 10:07:16 +00:00
|
|
|
while (entry->nr < PERF_MAX_STACK_DEPTH) {
|
|
|
|
unsigned long bytes;
|
|
|
|
frame.next_frame = 0;
|
|
|
|
frame.return_address = 0;
|
|
|
|
|
|
|
|
bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
|
|
|
|
if (bytes != sizeof(frame))
|
|
|
|
break;
|
2009-06-15 11:07:24 +00:00
|
|
|
|
2012-04-20 22:41:35 +00:00
|
|
|
if (!valid_user_frame(fp, sizeof(frame)))
|
|
|
|
break;
|
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
perf_callchain_store(entry, cs_base + frame.return_address);
|
|
|
|
fp = compat_ptr(ss_base + frame.next_frame);
|
2010-03-17 10:07:16 +00:00
|
|
|
}
|
|
|
|
return 1;
|
2009-03-30 17:07:15 +00:00
|
|
|
}
|
2010-03-17 10:07:16 +00:00
|
|
|
#else
|
|
|
|
static inline int
|
|
|
|
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif
|
2009-03-30 17:07:15 +00:00
|
|
|
|
2010-06-30 21:03:51 +00:00
|
|
|
void
|
|
|
|
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
|
2009-03-30 17:07:15 +00:00
|
|
|
{
|
|
|
|
struct stack_frame frame;
|
|
|
|
const void __user *fp;
|
|
|
|
|
2010-07-01 14:20:36 +00:00
|
|
|
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
|
|
|
|
/* TODO: We don't support guest os callchain now */
|
2010-08-20 12:30:41 +00:00
|
|
|
return;
|
2010-07-01 14:20:36 +00:00
|
|
|
}
|
2009-05-29 09:25:09 +00:00
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
/*
|
|
|
|
* We don't know what to do with VM86 stacks.. ignore them for now.
|
|
|
|
*/
|
|
|
|
if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
|
|
|
|
return;
|
|
|
|
|
2009-06-15 11:07:24 +00:00
|
|
|
fp = (void __user *)regs->bp;
|
2009-03-30 17:07:15 +00:00
|
|
|
|
2010-06-29 17:34:05 +00:00
|
|
|
perf_callchain_store(entry, regs->ip);
|
2009-03-30 17:07:15 +00:00
|
|
|
|
2011-08-30 08:32:36 +00:00
|
|
|
if (!current->mm)
|
|
|
|
return;
|
|
|
|
|
2010-03-17 10:07:16 +00:00
|
|
|
if (perf_callchain_user32(regs, entry))
|
|
|
|
return;
|
|
|
|
|
2009-06-18 20:20:52 +00:00
|
|
|
while (entry->nr < PERF_MAX_STACK_DEPTH) {
|
2010-03-17 10:07:16 +00:00
|
|
|
unsigned long bytes;
|
2009-06-15 07:57:59 +00:00
|
|
|
frame.next_frame = NULL;
|
2009-03-30 17:07:15 +00:00
|
|
|
frame.return_address = 0;
|
|
|
|
|
2010-03-17 10:07:16 +00:00
|
|
|
bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
|
|
|
|
if (bytes != sizeof(frame))
|
2009-03-30 17:07:15 +00:00
|
|
|
break;
|
|
|
|
|
2012-04-20 22:41:35 +00:00
|
|
|
if (!valid_user_frame(fp, sizeof(frame)))
|
|
|
|
break;
|
|
|
|
|
2010-06-29 17:34:05 +00:00
|
|
|
perf_callchain_store(entry, frame.return_address);
|
2009-06-15 07:57:59 +00:00
|
|
|
fp = frame.next_frame;
|
2009-03-30 17:07:15 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
/*
|
|
|
|
* Deal with code segment offsets for the various execution modes:
|
|
|
|
*
|
|
|
|
* VM86 - the good olde 16 bit days, where the linear address is
|
|
|
|
* 20 bits and we use regs->ip + 0x10 * regs->cs.
|
|
|
|
*
|
|
|
|
* IA32 - Where we need to look at GDT/LDT segment descriptor tables
|
|
|
|
* to figure out what the 32bit base address is.
|
|
|
|
*
|
|
|
|
* X32 - has TIF_X32 set, but is running in x86_64
|
|
|
|
*
|
|
|
|
* X86_64 - CS,DS,SS,ES are all zero based.
|
|
|
|
*/
|
|
|
|
static unsigned long code_segment_base(struct pt_regs *regs)
|
2010-04-19 05:32:41 +00:00
|
|
|
{
|
2012-07-10 07:42:15 +00:00
|
|
|
/*
|
|
|
|
* If we are in VM86 mode, add the segment offset to convert to a
|
|
|
|
* linear address.
|
|
|
|
*/
|
|
|
|
if (regs->flags & X86_VM_MASK)
|
|
|
|
return 0x10 * regs->cs;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For IA32 we look at the GDT/LDT segment base to convert the
|
|
|
|
* effective IP to a linear address.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
if (user_mode(regs) && regs->cs != __USER_CS)
|
|
|
|
return get_segment_base(regs->cs);
|
|
|
|
#else
|
|
|
|
if (test_thread_flag(TIF_IA32)) {
|
|
|
|
if (user_mode(regs) && regs->cs != __USER32_CS)
|
|
|
|
return get_segment_base(regs->cs);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
return 0;
|
|
|
|
}
|
2010-04-20 02:13:58 +00:00
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
unsigned long perf_instruction_pointer(struct pt_regs *regs)
|
|
|
|
{
|
2010-04-19 05:32:41 +00:00
|
|
|
if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
|
2012-07-10 07:42:15 +00:00
|
|
|
return perf_guest_cbs->get_guest_ip();
|
2010-04-20 02:13:58 +00:00
|
|
|
|
2012-07-10 07:42:15 +00:00
|
|
|
return regs->ip + code_segment_base(regs);
|
2010-04-19 05:32:41 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long perf_misc_flags(struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
int misc = 0;
|
2010-04-20 02:13:58 +00:00
|
|
|
|
2010-04-19 05:32:41 +00:00
|
|
|
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
|
2010-04-20 02:13:58 +00:00
|
|
|
if (perf_guest_cbs->is_user_mode())
|
|
|
|
misc |= PERF_RECORD_MISC_GUEST_USER;
|
|
|
|
else
|
|
|
|
misc |= PERF_RECORD_MISC_GUEST_KERNEL;
|
|
|
|
} else {
|
2012-07-10 07:42:15 +00:00
|
|
|
if (user_mode(regs))
|
2010-04-20 02:13:58 +00:00
|
|
|
misc |= PERF_RECORD_MISC_USER;
|
|
|
|
else
|
|
|
|
misc |= PERF_RECORD_MISC_KERNEL;
|
|
|
|
}
|
|
|
|
|
2010-04-19 05:32:41 +00:00
|
|
|
if (regs->flags & PERF_EFLAGS_EXACT)
|
2010-04-08 21:03:20 +00:00
|
|
|
misc |= PERF_RECORD_MISC_EXACT_IP;
|
2010-04-19 05:32:41 +00:00
|
|
|
|
|
|
|
return misc;
|
|
|
|
}
|
2011-11-10 12:57:27 +00:00
|
|
|
|
|
|
|
void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
|
|
|
|
{
|
|
|
|
cap->version = x86_pmu.version;
|
|
|
|
cap->num_counters_gp = x86_pmu.num_counters;
|
|
|
|
cap->num_counters_fixed = x86_pmu.num_counters_fixed;
|
|
|
|
cap->bit_width_gp = x86_pmu.cntval_bits;
|
|
|
|
cap->bit_width_fixed = x86_pmu.cntval_bits;
|
|
|
|
cap->events_mask = (unsigned int)x86_pmu.events_maskl;
|
|
|
|
cap->events_mask_len = x86_pmu.events_mask_len;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability);
|