Commit 5f1230c9 authored by Ingo Molnar's avatar Ingo Molnar

Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Introduce 'srcfile' sort key: (Andi Kleen)

    # perf record -F 10000 usleep 1
    # perf report --stdio --dsos '[kernel.vmlinux]' -s srcfile
    <SNIP>
    # Overhead  Source File
        26.49%  copy_page_64.S
         5.49%  signal.c
         0.51%  msr.h
    #

    It can be combined with other fields, for instance, experiment with
    '-s srcfile,symbol'.

    There are some oddities in some distros and with some specific DSOs, being
    investigated, so your mileage may vary.

  - Update the column width for the "srcline" sort key (Arnaldo Carvalho de Melo)

  - Support per-event 'freq' term: (Namhyung Kim)

    $ perf record -e 'cpu/instructions,freq=1234/',cycles -c 1000 sleep 1
    $ perf evlist -F
    cpu/instructions,freq=1234/: sample_freq=1234
    cycles: sample_period=1000
    $

Infrastructure changes:

  - Move perf_counts struct and functions into separate object (Jiri Olsa)

  - Unset perf_event_attr::freq when period term is set (Jiri Olsa)

  - Move callchain option parsing code to util.c (Kan Liang)
Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents 709bc871 4605bb55
......@@ -49,6 +49,7 @@ OPTIONS
These params can be used to overload default config values per event.
Here is a list of the params.
- 'period': Set event sampling period
- 'freq': Set event sampling frequency
- 'time': Disable/enable time stamping. Acceptable values are 1 for
enabling time stamping. 0 for disabling time stamping.
The default is 1.
......
......@@ -81,6 +81,8 @@ OPTIONS
- cpu: cpu number the task ran at the time of sample
- srcline: filename and line number executed at the time of sample. The
DWARF debugging info must be provided.
- srcfile: file name of the source file of the same. Requires dwarf
information.
- weight: Event specific weight, e.g. memory latency or transaction
abort cost. This is the global weight.
- local_weight: Local weight version of the weight above.
......@@ -354,6 +356,8 @@ OPTIONS
To disable decoding entirely, use --no-itrace.
--full-source-path::
Show the full path for source files for srcline output.
include::callchain-overhead-calculation.txt[]
......
......@@ -260,6 +260,9 @@ OPTIONS
To disable decoding entirely, use --no-itrace.
--full-source-path::
Show the full path for source files for srcline output.
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
......
......@@ -738,6 +738,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
"Instruction Tracing options",
itrace_parse_synth_opts),
OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
"Show full source file name path for source lines"),
OPT_END()
};
struct perf_data_file file = {
......
......@@ -1653,6 +1653,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
"Instruction Tracing options",
itrace_parse_synth_opts),
OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
"Show full source file name path for source lines"),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
......
......@@ -58,6 +58,7 @@
#include "util/cpumap.h"
#include "util/thread.h"
#include "util/thread_map.h"
#include "util/counts.h"
#include <stdlib.h>
#include <sys/prctl.h>
......
......@@ -68,6 +68,7 @@ libperf-y += target.o
libperf-y += rblist.o
libperf-y += intlist.o
libperf-y += vdso.o
libperf-y += counts.o
libperf-y += stat.o
libperf-y += stat-shadow.o
libperf-y += record.o
......
......@@ -25,96 +25,9 @@
__thread struct callchain_cursor callchain_cursor;
#ifdef HAVE_DWARF_UNWIND_SUPPORT
static int get_stack_size(const char *str, unsigned long *_size)
{
char *endptr;
unsigned long size;
unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
size = strtoul(str, &endptr, 0);
do {
if (*endptr)
break;
size = round_up(size, sizeof(u64));
if (!size || size > max_size)
break;
*_size = size;
return 0;
} while (0);
pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
max_size, str);
return -1;
}
#endif /* HAVE_DWARF_UNWIND_SUPPORT */
int parse_callchain_record_opt(const char *arg, struct callchain_param *param)
{
char *tok, *name, *saveptr = NULL;
char *buf;
int ret = -1;
/* We need buffer that we know we can write to. */
buf = malloc(strlen(arg) + 1);
if (!buf)
return -ENOMEM;
strcpy(buf, arg);
tok = strtok_r((char *)buf, ",", &saveptr);
name = tok ? : (char *)buf;
do {
/* Framepointer style */
if (!strncmp(name, "fp", sizeof("fp"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_FP;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph fp\n");
break;
#ifdef HAVE_DWARF_UNWIND_SUPPORT
/* Dwarf style */
} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
const unsigned long default_stack_dump_size = 8192;
ret = 0;
param->record_mode = CALLCHAIN_DWARF;
param->dump_size = default_stack_dump_size;
tok = strtok_r(NULL, ",", &saveptr);
if (tok) {
unsigned long size = 0;
ret = get_stack_size(tok, &size);
param->dump_size = size;
}
#endif /* HAVE_DWARF_UNWIND_SUPPORT */
} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_LBR;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph lbr\n");
break;
} else {
pr_err("callchain: Unknown --call-graph option "
"value: %s\n", arg);
break;
}
} while (0);
free(buf);
return ret;
return parse_callchain_record(arg, param);
}
static int parse_callchain_mode(const char *value)
......
......@@ -177,6 +177,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
bool hide_unresolved);
extern const char record_callchain_help[];
extern int parse_callchain_record(const char *arg, struct callchain_param *param);
int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
int parse_callchain_report_opt(const char *arg);
int perf_callchain_config(const char *var, const char *value);
......
#include <stdlib.h>
#include "evsel.h"
#include "counts.h"
struct perf_counts *perf_counts__new(int ncpus, int nthreads)
{
struct perf_counts *counts = zalloc(sizeof(*counts));
if (counts) {
struct xyarray *values;
values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
if (!values) {
free(counts);
return NULL;
}
counts->values = values;
}
return counts;
}
void perf_counts__delete(struct perf_counts *counts)
{
if (counts) {
xyarray__delete(counts->values);
free(counts);
}
}
static void perf_counts__reset(struct perf_counts *counts)
{
xyarray__reset(counts->values);
}
void perf_evsel__reset_counts(struct perf_evsel *evsel)
{
perf_counts__reset(evsel->counts);
}
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
{
evsel->counts = perf_counts__new(ncpus, nthreads);
return evsel->counts != NULL ? 0 : -ENOMEM;
}
void perf_evsel__free_counts(struct perf_evsel *evsel)
{
perf_counts__delete(evsel->counts);
evsel->counts = NULL;
}
#ifndef __PERF_COUNTS_H
#define __PERF_COUNTS_H
#include "xyarray.h"
struct perf_counts_values {
union {
struct {
u64 val;
u64 ena;
u64 run;
};
u64 values[3];
};
};
struct perf_counts {
s8 scaled;
struct perf_counts_values aggr;
struct xyarray *values;
};
static inline struct perf_counts_values*
perf_counts(struct perf_counts *counts, int cpu, int thread)
{
return xyarray__entry(counts->values, cpu, thread);
}
struct perf_counts *perf_counts__new(int ncpus, int nthreads);
void perf_counts__delete(struct perf_counts *counts);
void perf_evsel__reset_counts(struct perf_evsel *evsel);
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
void perf_evsel__free_counts(struct perf_evsel *evsel);
#endif /* __PERF_COUNTS_H */
......@@ -598,6 +598,11 @@ static void apply_config_terms(struct perf_evsel *evsel)
switch (term->type) {
case PERF_EVSEL__CONFIG_TERM_PERIOD:
attr->sample_period = term->val.period;
attr->freq = 0;
break;
case PERF_EVSEL__CONFIG_TERM_FREQ:
attr->sample_freq = term->val.freq;
attr->freq = 1;
break;
case PERF_EVSEL__CONFIG_TERM_TIME:
if (term->val.time)
......@@ -2153,8 +2158,13 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
printed += perf_event_attr__fprintf(fp, &evsel->attr,
__print_attr__fprintf, &first);
} else if (details->freq) {
printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
(u64)evsel->attr.sample_freq);
const char *term = "sample_freq";
if (!evsel->attr.freq)
term = "sample_period";
printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
term, (u64)evsel->attr.sample_freq);
}
out:
fputc('\n', fp);
......
......@@ -9,7 +9,7 @@
#include "xyarray.h"
#include "symbol.h"
#include "cpumap.h"
#include "stat.h"
#include "counts.h"
struct perf_evsel;
......@@ -39,6 +39,7 @@ struct cgroup_sel;
*/
enum {
PERF_EVSEL__CONFIG_TERM_PERIOD,
PERF_EVSEL__CONFIG_TERM_FREQ,
PERF_EVSEL__CONFIG_TERM_TIME,
PERF_EVSEL__CONFIG_TERM_MAX,
};
......@@ -48,6 +49,7 @@ struct perf_evsel_config_term {
int type;
union {
u64 period;
u64 freq;
bool time;
} val;
};
......
......@@ -151,6 +151,12 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
if (h->srcline)
hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline));
if (h->srcfile)
hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile));
if (h->transaction)
hists__new_col_len(hists, HISTC_TRANSACTION,
hist_entry__transaction_len());
......@@ -761,6 +767,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
struct hist_entry **he_cache = iter->priv;
struct hist_entry *he;
struct hist_entry he_tmp = {
.hists = evsel__hists(evsel),
.cpu = al->cpu,
.thread = al->thread,
.comm = thread__comm(al->thread),
......@@ -945,6 +952,8 @@ void hist_entry__delete(struct hist_entry *he)
zfree(&he->stat_acc);
free_srcline(he->srcline);
if (he->srcfile && he->srcfile[0])
free(he->srcfile);
free_callchain(he->callchain);
free(he);
}
......
......@@ -30,6 +30,7 @@ enum hist_column {
HISTC_PARENT,
HISTC_CPU,
HISTC_SRCLINE,
HISTC_SRCFILE,
HISTC_MISPREDICT,
HISTC_IN_TX,
HISTC_ABORT,
......
......@@ -597,6 +597,9 @@ do { \
case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
CHECK_TYPE_VAL(NUM);
break;
case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
CHECK_TYPE_VAL(NUM);
break;
case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
/*
* TODO uncomment when the field is available
......@@ -659,6 +662,9 @@ do { \
case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
ADD_CONFIG_TERM(PERIOD, period, term->val.num);
break;
case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
ADD_CONFIG_TERM(FREQ, freq, term->val.num);
break;
case PARSE_EVENTS__TERM_TYPE_TIME:
ADD_CONFIG_TERM(TIME, time, term->val.num);
break;
......
......@@ -62,6 +62,7 @@ enum {
PARSE_EVENTS__TERM_TYPE_CONFIG2,
PARSE_EVENTS__TERM_TYPE_NAME,
PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ,
PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
PARSE_EVENTS__TERM_TYPE_TIME,
};
......
......@@ -182,6 +182,7 @@ config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); }
branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
, { return ','; }
......
......@@ -634,7 +634,7 @@ static char *formats_error_string(struct list_head *formats)
{
struct perf_pmu_format *format;
char *err, *str;
static const char *static_terms = "config,config1,config2,name,period,branch_type,time\n";
static const char *static_terms = "config,config1,config2,name,period,freq,branch_type,time\n";
unsigned i = 0;
if (!asprintf(&str, "valid terms:"))
......
......@@ -16,7 +16,7 @@ util/util.c
util/xyarray.c
util/cgroup.c
util/rblist.c
util/stat.c
util/counts.c
util/strlist.c
util/trace-event.c
../lib/rbtree.c
......
......@@ -319,6 +319,57 @@ struct sort_entry sort_srcline = {
.se_width_idx = HISTC_SRCLINE,
};
/* --sort srcfile */
static char no_srcfile[1];
static char *get_srcfile(struct hist_entry *e)
{
char *sf, *p;
struct map *map = e->ms.map;
sf = get_srcline(map->dso, map__rip_2objdump(map, e->ip),
e->ms.sym, true);
p = strchr(sf, ':');
if (p && *sf) {
*p = 0;
return sf;
}
free(sf);
return no_srcfile;
}
static int64_t
sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (!left->srcfile) {
if (!left->ms.map)
left->srcfile = no_srcfile;
else
left->srcfile = get_srcfile(left);
}
if (!right->srcfile) {
if (!right->ms.map)
right->srcfile = no_srcfile;
else
right->srcfile = get_srcfile(right);
}
return strcmp(right->srcfile, left->srcfile);
}
static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
}
struct sort_entry sort_srcfile = {
.se_header = "Source File",
.se_cmp = sort__srcfile_cmp,
.se_snprintf = hist_entry__srcfile_snprintf,
.se_width_idx = HISTC_SRCFILE,
};
/* --sort parent */
static int64_t
......@@ -1196,6 +1247,7 @@ static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
DIM(SORT_SRCLINE, "srcline", sort_srcline),
DIM(SORT_SRCFILE, "srcfile", sort_srcfile),
DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
DIM(SORT_TRANSACTION, "transaction", sort_transaction),
......
......@@ -114,6 +114,7 @@ struct hist_entry {
};
};
char *srcline;
char *srcfile;
struct symbol *parent;
struct rb_root sorted_chain;
struct branch_info *branch_info;
......@@ -172,6 +173,7 @@ enum sort_type {
SORT_PARENT,
SORT_CPU,
SORT_SRCLINE,
SORT_SRCFILE,
SORT_LOCAL_WEIGHT,
SORT_GLOBAL_WEIGHT,
SORT_TRANSACTION,
......
......@@ -10,6 +10,8 @@
#include "symbol.h"
bool srcline_full_filename;
#ifdef HAVE_LIBBFD_SUPPORT
/*
......@@ -277,7 +279,9 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
if (!addr2line(dso_name, addr, &file, &line, dso))
goto out;
if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) {
if (asprintf(&srcline, "%s:%u",
srcline_full_filename ? file : basename(file),
line) < 0) {
free(file);
goto out;
}
......
......@@ -97,55 +97,6 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
}
}
struct perf_counts *perf_counts__new(int ncpus, int nthreads)
{
struct perf_counts *counts = zalloc(sizeof(*counts));
if (counts) {
struct xyarray *values;
values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
if (!values) {
free(counts);
return NULL;
}
counts->values = values;
}
return counts;
}
void perf_counts__delete(struct perf_counts *counts)
{
if (counts) {
xyarray__delete(counts->values);
free(counts);
}
}
static void perf_counts__reset(struct perf_counts *counts)
{
xyarray__reset(counts->values);
}
void perf_evsel__reset_counts(struct perf_evsel *evsel)
{
perf_counts__reset(evsel->counts);
}
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
{
evsel->counts = perf_counts__new(ncpus, nthreads);
return evsel->counts != NULL ? 0 : -ENOMEM;
}
void perf_evsel__free_counts(struct perf_evsel *evsel)
{
perf_counts__delete(evsel->counts);
evsel->counts = NULL;
}
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
{
int i;
......
......@@ -33,23 +33,6 @@ enum aggr_mode {
AGGR_THREAD,
};
struct perf_counts_values {
union {
struct {
u64 val;
u64 ena;
u64 run;
};
u64 values[3];
};
};
struct perf_counts {
s8 scaled;
struct perf_counts_values aggr;
struct xyarray *values;
};
struct perf_stat_config {
enum aggr_mode aggr_mode;
bool scale;
......@@ -57,12 +40,6 @@ struct perf_stat_config {
unsigned int interval;
};
static inline struct perf_counts_values*
perf_counts(struct perf_counts *counts, int cpu, int thread)
{
return xyarray__entry(counts->values, cpu, thread);
}
void update_stats(struct stats *stats, u64 val);
double avg_stats(struct stats *stats);
double stddev_stats(struct stats *stats);
......@@ -96,13 +73,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
double avg, int cpu, enum aggr_mode aggr);
struct perf_counts *perf_counts__new(int ncpus, int nthreads);
void perf_counts__delete(struct perf_counts *counts);
void perf_evsel__reset_counts(struct perf_evsel *evsel);
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
void perf_evsel__free_counts(struct perf_evsel *evsel);
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
......
......@@ -566,6 +566,96 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
return (unsigned long) -1;
}
int get_stack_size(const char *str, unsigned long *_size)
{
char *endptr;
unsigned long size;
unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
size = strtoul(str, &endptr, 0);
do {
if (*endptr)
break;
size = round_up(size, sizeof(u64));
if (!size || size > max_size)
break;
*_size = size;
return 0;
} while (0);
pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
max_size, str);
return -1;
}
int parse_callchain_record(const char *arg, struct callchain_param *param)
{
char *tok, *name, *saveptr = NULL;
char *buf;
int ret = -1;
/* We need buffer that we know we can write to. */
buf = malloc(strlen(arg) + 1);
if (!buf)
return -ENOMEM;
strcpy(buf, arg);
tok = strtok_r((char *)buf, ",", &saveptr);
name = tok ? : (char *)buf;
do {
/* Framepointer style */
if (!strncmp(name, "fp", sizeof("fp"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_FP;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph fp\n");
break;
#ifdef HAVE_DWARF_UNWIND_SUPPORT
/* Dwarf style */
} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
const unsigned long default_stack_dump_size = 8192;
ret = 0;
param->record_mode = CALLCHAIN_DWARF;
param->dump_size = default_stack_dump_size;
tok = strtok_r(NULL, ",", &saveptr);
if (tok) {
unsigned long size = 0;
ret = get_stack_size(tok, &size);
param->dump_size = size;
}
#endif /* HAVE_DWARF_UNWIND_SUPPORT */
} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_LBR;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph lbr\n");
break;
} else {
pr_err("callchain: Unknown --call-graph option "
"value: %s\n", arg);
break;
}
} while (0);
free(buf);
return ret;
}
int filename__read_str(const char *filename, char **buf, size_t *sizep)
{
size_t size = 0, alloc_size = 0;
......
......@@ -318,6 +318,7 @@ static inline int path__join3(char *bf, size_t size,
struct dso;
struct symbol;
extern bool srcline_full_filename;
char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
bool show_sym);
void free_srcline(char *srcline);
......@@ -351,4 +352,6 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
return asprintf_expr_inout_ints(var, false, nints, ints);
}
int get_stack_size(const char *str, unsigned long *_size);
#endif /* GIT_COMPAT_UTIL_H */
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment