cdd6c482c9
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>
110 lines
2.6 KiB
C
110 lines
2.6 KiB
C
#ifndef _PERF_PERF_H
|
|
#define _PERF_PERF_H
|
|
|
|
#if defined(__i386__)
|
|
#include "../../arch/x86/include/asm/unistd.h"
|
|
#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
|
|
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
|
|
#endif
|
|
|
|
#if defined(__x86_64__)
|
|
#include "../../arch/x86/include/asm/unistd.h"
|
|
#define rmb() asm volatile("lfence" ::: "memory")
|
|
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
|
|
#endif
|
|
|
|
#ifdef __powerpc__
|
|
#include "../../arch/powerpc/include/asm/unistd.h"
|
|
#define rmb() asm volatile ("sync" ::: "memory")
|
|
#define cpu_relax() asm volatile ("" ::: "memory");
|
|
#endif
|
|
|
|
#ifdef __s390__
|
|
#include "../../arch/s390/include/asm/unistd.h"
|
|
#define rmb() asm volatile("bcr 15,0" ::: "memory")
|
|
#define cpu_relax() asm volatile("" ::: "memory");
|
|
#endif
|
|
|
|
#ifdef __sh__
|
|
#include "../../arch/sh/include/asm/unistd.h"
|
|
#if defined(__SH4A__) || defined(__SH5__)
|
|
# define rmb() asm volatile("synco" ::: "memory")
|
|
#else
|
|
# define rmb() asm volatile("" ::: "memory")
|
|
#endif
|
|
#define cpu_relax() asm volatile("" ::: "memory")
|
|
#endif
|
|
|
|
#ifdef __hppa__
|
|
#include "../../arch/parisc/include/asm/unistd.h"
|
|
#define rmb() asm volatile("" ::: "memory")
|
|
#define cpu_relax() asm volatile("" ::: "memory");
|
|
#endif
|
|
|
|
#ifdef __sparc__
|
|
#include "../../arch/sparc/include/asm/unistd.h"
|
|
#define rmb() asm volatile("":::"memory")
|
|
#define cpu_relax() asm volatile("":::"memory")
|
|
#endif
|
|
|
|
#include <time.h>
|
|
#include <unistd.h>
|
|
#include <sys/types.h>
|
|
#include <sys/syscall.h>
|
|
|
|
#include "../../include/linux/perf_event.h"
|
|
#include "util/types.h"
|
|
|
|
/*
|
|
* prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
|
|
* counters in the current task.
|
|
*/
|
|
#define PR_TASK_PERF_EVENTS_DISABLE 31
|
|
#define PR_TASK_PERF_EVENTS_ENABLE 32
|
|
|
|
#ifndef NSEC_PER_SEC
|
|
# define NSEC_PER_SEC 1000000000ULL
|
|
#endif
|
|
|
|
static inline unsigned long long rdclock(void)
|
|
{
|
|
struct timespec ts;
|
|
|
|
clock_gettime(CLOCK_MONOTONIC, &ts);
|
|
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
|
|
}
|
|
|
|
/*
|
|
* Pick up some kernel type conventions:
|
|
*/
|
|
#define __user
|
|
#define asmlinkage
|
|
|
|
#define __used __attribute__((__unused__))
|
|
|
|
#define unlikely(x) __builtin_expect(!!(x), 0)
|
|
#define min(x, y) ({ \
|
|
typeof(x) _min1 = (x); \
|
|
typeof(y) _min2 = (y); \
|
|
(void) (&_min1 == &_min2); \
|
|
_min1 < _min2 ? _min1 : _min2; })
|
|
|
|
static inline int
|
|
sys_perf_event_open(struct perf_event_attr *attr,
|
|
pid_t pid, int cpu, int group_fd,
|
|
unsigned long flags)
|
|
{
|
|
attr->size = sizeof(*attr);
|
|
return syscall(__NR_perf_event_open, attr, pid, cpu,
|
|
group_fd, flags);
|
|
}
|
|
|
|
#define MAX_COUNTERS 256
|
|
#define MAX_NR_CPUS 256
|
|
|
|
struct ip_callchain {
|
|
u64 nr;
|
|
u64 ips[0];
|
|
};
|
|
|
|
#endif
|