linux/tools/perf/perf.h
Jiri Olsa 26d330226b perf tools: Support for DWARF mode callchain
This patch enables perf to use the DWARF unwind code.

It extends the perf record '-g' option with following arguments:
  'fp'           - provides framepointer based user
                   stack backtrace
  'dwarf[,size]' - provides DWARF (libunwind) based user stack
                   backtrace. The size specifies the size of the
                   user stack dump. If omitted it is 8192 by default.

If libunwind is found during the perf build, then the 'dwarf' argument
becomes available for record command. The 'fp' stays as default option
in any case.

Examples: (perf compiled with libunwind)

   perf record -g dwarf ls
      - provides dwarf unwind with 8192 as stack dump size

   perf record -g dwarf,4096 ls
      - provides dwarf unwind with 4096 as stack dump size

   perf record -g -- ls
   perf record -g fp ls
      - provides frame pointer unwind

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-11 15:07:18 -03:00

242 lines
5.4 KiB
C

#ifndef _PERF_PERF_H
#define _PERF_PERF_H
struct winsize;
void get_term_dimensions(struct winsize *ws);
#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");
#define CPUINFO_PROC "model name"
#ifndef __NR_perf_event_open
# define __NR_perf_event_open 336
#endif
#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");
#define CPUINFO_PROC "model name"
#ifndef __NR_perf_event_open
# define __NR_perf_event_open 298
#endif
#endif
#ifdef __powerpc__
#include "../../arch/powerpc/include/asm/unistd.h"
#define rmb() asm volatile ("sync" ::: "memory")
#define cpu_relax() asm volatile ("" ::: "memory");
#define CPUINFO_PROC "cpu"
#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")
#define CPUINFO_PROC "cpu type"
#endif
#ifdef __hppa__
#include "../../arch/parisc/include/asm/unistd.h"
#define rmb() asm volatile("" ::: "memory")
#define cpu_relax() asm volatile("" ::: "memory");
#define CPUINFO_PROC "cpu"
#endif
#ifdef __sparc__
#include "../../arch/sparc/include/asm/unistd.h"
#define rmb() asm volatile("":::"memory")
#define cpu_relax() asm volatile("":::"memory")
#define CPUINFO_PROC "cpu"
#endif
#ifdef __alpha__
#include "../../arch/alpha/include/asm/unistd.h"
#define rmb() asm volatile("mb" ::: "memory")
#define cpu_relax() asm volatile("" ::: "memory")
#define CPUINFO_PROC "cpu model"
#endif
#ifdef __ia64__
#include "../../arch/ia64/include/asm/unistd.h"
#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("hint @pause" ::: "memory")
#define CPUINFO_PROC "model name"
#endif
#ifdef __arm__
#include "../../arch/arm/include/asm/unistd.h"
/*
* Use the __kuser_memory_barrier helper in the CPU helper page. See
* arch/arm/kernel/entry-armv.S in the kernel source for details.
*/
#define rmb() ((void(*)(void))0xffff0fa0)()
#define cpu_relax() asm volatile("":::"memory")
#define CPUINFO_PROC "Processor"
#endif
#ifdef __mips__
#include "../../arch/mips/include/asm/unistd.h"
#define rmb() asm volatile( \
".set mips2\n\t" \
"sync\n\t" \
".set mips0" \
: /* no output */ \
: /* no input */ \
: "memory")
#define cpu_relax() asm volatile("" ::: "memory")
#define CPUINFO_PROC "cpu model"
#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"
#include <stdbool.h>
struct perf_mmap {
void *base;
int mask;
unsigned int prev;
};
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->base;
int head = pc->data_head;
rmb();
return head;
}
static inline void perf_mmap__write_tail(struct perf_mmap *md,
unsigned long tail)
{
struct perf_event_mmap_page *pc = md->base;
/*
* ensure all reads are done before we write the tail out.
*/
/* mb(); */
pc->data_tail = tail;
}
/*
* 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 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)
{
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];
};
struct branch_flags {
u64 mispred:1;
u64 predicted:1;
u64 reserved:62;
};
struct branch_entry {
u64 from;
u64 to;
struct branch_flags flags;
};
struct branch_stack {
u64 nr;
struct branch_entry entries[0];
};
extern bool perf_host, perf_guest;
extern const char perf_version_string[];
void pthread__unblock_sigwinch(void);
#include "util/target.h"
enum perf_call_graph_mode {
CALLCHAIN_NONE,
CALLCHAIN_FP,
CALLCHAIN_DWARF
};
struct perf_record_opts {
struct perf_target target;
int call_graph;
bool group;
bool inherit_stat;
bool no_delay;
bool no_inherit;
bool no_samples;
bool pipe_output;
bool raw_samples;
bool sample_address;
bool sample_time;
bool sample_id_all_missing;
bool exclude_guest_missing;
bool period;
unsigned int freq;
unsigned int mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 default_interval;
u64 user_interval;
u16 stack_dump_size;
};
#endif