forked from Minki/linux
9c2b957db1
Pull perf events changes for v3.4 from Ingo Molnar: - New "hardware based branch profiling" feature both on the kernel and the tooling side, on CPUs that support it. (modern x86 Intel CPUs with the 'LBR' hardware feature currently.) This new feature is basically a sophisticated 'magnifying glass' for branch execution - something that is pretty difficult to extract from regular, function histogram centric profiles. The simplest mode is activated via 'perf record -b', and the result looks like this in perf report: $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf This output shows from/to branch columns and shows the highest percentage (from,to) jump combinations - i.e. the most likely taken branches in the system. "branches" can also include function calls and any other synchronous and asynchronous transitions of the instruction pointer that are not 'next instruction' - such as system calls, traps, interrupts, etc. This feature comes with (hopefully intuitive) flat ascii and TUI support in perf report. - Various 'perf annotate' visual improvements for us assembly junkies. It will now recognize function calls in the TUI and by hitting enter you can follow the call (recursively) and back, amongst other improvements. - Multiple threads/processes recording support in perf record, perf stat, perf top - which is activated via a comma-list of PIDs: perf top -p 21483,21485 perf stat -p 21483,21485 -ddd perf record -p 21483,21485 - Support for per UID views, via the --uid paramter to perf top, perf report, etc. For example 'perf top --uid mingo' will only show the tasks that I am running, excluding other users, root, etc. - Jump label restructurings and improvements - this includes the factoring out of the (hopefully much clearer) include/linux/static_key.h generic facility: struct static_key key = STATIC_KEY_INIT_FALSE; ... if (static_key_false(&key)) do unlikely code else do likely code ... static_key_slow_inc(); ... static_key_slow_inc(); ... The static_key_false() branch will be generated into the code with as little impact to the likely code path as possible. the static_key_slow_*() APIs flip the branch via live kernel code patching. This facility can now be used more widely within the kernel to micro-optimize hot branches whose likelihood matches the static-key usage and fast/slow cost patterns. - SW function tracer improvements: perf support and filtering support. - Various hardenings of the perf.data ABI, to make older perf.data's smoother on newer tool versions, to make new features integrate more smoothly, to support cross-endian recording/analyzing workflows better, etc. - Restructuring of the kprobes code, the splitting out of 'optprobes', and a corner case bugfix. - Allow the tracing of kernel console output (printk). - Improvements/fixes to user-space RDPMC support, allowing user-space self-profiling code to extract PMU counts without performing any system calls, while playing nice with the kernel side. - 'perf bench' improvements - ... and lots of internal restructurings, cleanups and fixes that made these features possible. And, as usual this list is incomplete as there were also lots of other improvements * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits) perf report: Fix annotate double quit issue in branch view mode perf report: Remove duplicate annotate choice in branch view mode perf/x86: Prettify pmu config literals perf report: Enable TUI in branch view mode perf report: Auto-detect branch stack sampling mode perf record: Add HEADER_BRANCH_STACK tag perf record: Provide default branch stack sampling mode option perf tools: Make perf able to read files from older ABIs perf tools: Fix ABI compatibility bug in print_event_desc() perf tools: Enable reading of perf.data files from different ABI rev perf: Add ABI reference sizes perf report: Add support for taken branch sampling perf record: Add support for sampling taken branch perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK x86/kprobes: Split out optprobe related code to kprobes-opt.c x86/kprobes: Fix a bug which can modify kernel code permanently x86/kprobes: Fix instruction recovery on optimized path perf: Add callback to flush branch_stack on context switch perf: Disable PERF_SAMPLE_BRANCH_* when not supported perf/x86: Add LBR software filter support for Intel CPUs ...
238 lines
5.4 KiB
C
238 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);
|
|
|
|
struct perf_record_opts {
|
|
const char *target_pid;
|
|
const char *target_tid;
|
|
uid_t uid;
|
|
bool 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 system_wide;
|
|
bool period;
|
|
unsigned int freq;
|
|
unsigned int mmap_pages;
|
|
unsigned int user_freq;
|
|
int branch_stack;
|
|
u64 default_interval;
|
|
u64 user_interval;
|
|
const char *cpu_list;
|
|
};
|
|
|
|
#endif
|