linux_dsm_epyc7002/tools/perf/util/parse-events.l
Andi Kleen 5a5dfe4b85 perf tools: Support weak groups in 'perf stat'
Setting up groups can be complicated due to the complicated scheduling
restrictions of different PMUs.

User tools usually don't understand all these restrictions.

Still in many cases it is useful to set up groups and they work most of
the time. However if the group is set up wrong some members will not
report any value because they never get scheduled.

Add a concept of a 'weak group': try to set up a group, but if it's not
schedulable fallback to not using a group. That gives us the best of
both worlds: groups if they work, but still a usable fallback if they
don't.

In theory it would be possible to have more complex fallback strategies
(e.g. try to split the group in half), but the simple fallback of not
using a group seems to work for now.

So far the weak group is only implemented for perf stat, not for record.

Here's an unschedulable group (on IvyBridge with SMT on)

  % perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1

        73,806,067      branches
         4,848,144      branch-misses             #    6.57% of all branches
        14,754,458      l1d.replacement
        24,905,558      l2_lines_in.all
   <not supported>      l2_rqsts.all_code_rd         <------- will never report anything

With the weak group:

  % perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1

       125,366,055      branches                                                      (80.02%)
         9,208,402      branch-misses             #    7.35% of all branches          (80.01%)
        24,560,249      l1d.replacement                                               (80.00%)
        43,174,971      l2_lines_in.all                                               (80.05%)
        31,891,457      l2_rqsts.all_code_rd                                          (79.92%)

The extra event scheduled with some extra multiplexing

v2: Move fallback code to separate function.
Add comment on for_each_group_member
Adjust to new perf_evsel__close interface
v3: Fix debug print out.

Committer testing:

Before:

  # perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1

   Performance counter stats for 'system wide':

     <not counted>      branches
     <not counted>      branch-misses
     <not counted>      l1d.replacement
     <not counted>      l2_lines_in.all
   <not supported>      l2_rqsts.all_code_rd

       1.002147212 seconds time elapsed

  # perf stat -e '{branches,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1

   Performance counter stats for 'system wide':

        83,207,892      branches
        11,065,444      l1d.replacement
        28,484,024      l2_lines_in.all
        12,186,179      l2_rqsts.all_code_rd

       1.001739493 seconds time elapsed

After:

  # perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}':W -a sleep 1

   Performance counter stats for 'system wide':

       543,323,909      branches                                                      (80.01%)
        27,100,512      branch-misses             #    4.99% of all branches          (80.02%)
        50,402,905      l1d.replacement                                               (80.03%)
        67,385,892      l2_lines_in.all                                               (80.01%)
        21,352,885      l2_rqsts.all_code_rd                                          (79.94%)

       1.001086658 seconds time elapsed

  #

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20170831194036.30146-2-andi@firstfloor.org
[ Add a "'perf stat' only, for now" comment in the man page, suggested by Jiri ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-13 09:49:12 -03:00

344 lines
10 KiB
Plaintext

%option reentrant
%option bison-bridge
%option prefix="parse_events_"
%option stack
%option bison-locations
%option yylineno
%{
#include <errno.h>
#include "../perf.h"
#include "parse-events.h"
#include "parse-events-bison.h"
char *parse_events_get_text(yyscan_t yyscanner);
YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
static int __value(YYSTYPE *yylval, char *str, int base, int token)
{
u64 num;
errno = 0;
num = strtoull(str, NULL, base);
if (errno)
return PE_ERROR;
yylval->num = num;
return token;
}
static int value(yyscan_t scanner, int base)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
return __value(yylval, text, base, PE_VALUE);
}
static int raw(yyscan_t scanner)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
return __value(yylval, text + 1, 16, PE_RAW);
}
static int str(yyscan_t scanner, int token)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
yylval->str = strdup(text);
return token;
}
static bool isbpf(yyscan_t scanner)
{
char *text = parse_events_get_text(scanner);
int len = strlen(text);
if (len < 2)
return false;
if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
text[len - 2] == '.')
return true;
if (len > 4 && !strcmp(text + len - 4, ".obj"))
return true;
return false;
}
/*
* This function is called when the parser gets two kind of input:
*
* @cfg1 or @cfg2=config
*
* The leading '@' is stripped off before 'cfg1' and 'cfg2=config' are given to
* bison. In the latter case it is necessary to keep the string intact so that
* the PMU kernel driver can determine what configurable is associated to
* 'config'.
*/
static int drv_str(yyscan_t scanner, int token)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
/* Strip off the '@' */
yylval->str = strdup(text + 1);
return token;
}
#define REWIND(__alloc) \
do { \
YYSTYPE *__yylval = parse_events_get_lval(yyscanner); \
char *text = parse_events_get_text(yyscanner); \
\
if (__alloc) \
__yylval->str = strdup(text); \
\
yycolumn -= strlen(text); \
yyless(0); \
} while (0)
static int pmu_str_check(yyscan_t scanner)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
yylval->str = strdup(text);
switch (perf_pmu__parse_check(text)) {
case PMU_EVENT_SYMBOL_PREFIX:
return PE_PMU_EVENT_PRE;
case PMU_EVENT_SYMBOL_SUFFIX:
return PE_PMU_EVENT_SUF;
case PMU_EVENT_SYMBOL:
return PE_KERNEL_PMU_EVENT;
default:
return PE_NAME;
}
}
static int sym(yyscan_t scanner, int type, int config)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
yylval->num = (type << 16) + config;
return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
}
static int term(yyscan_t scanner, int type)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
yylval->num = type;
return PE_TERM;
}
#define YY_USER_ACTION \
do { \
yylloc->last_column = yylloc->first_column; \
yylloc->first_column = yycolumn; \
yycolumn += yyleng; \
} while (0);
%}
%x mem
%s config
%x event
%x array
group [^,{}/]*[{][^}]*[}][^,{}/]*
event_pmu [^,{}/]+[/][^/]*[/][^,{}/]*
event [^,{}/]+
bpf_object [^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
bpf_source [^,{}]+\.c[a-zA-Z0-9._]*
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
num_raw_hex [a-fA-F0-9]+
name [a-zA-Z_*?][a-zA-Z0-9_*?.]*
name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
/* If you add a modifier you need to update check_modifier() */
modifier_event [ukhpPGHSDIW]+
modifier_bp [rwx]{1,3}
%%
%{
{
int start_token;
start_token = parse_events_get_extra(yyscanner);
if (start_token == PE_START_TERMS)
BEGIN(config);
else if (start_token == PE_START_EVENTS)
BEGIN(event);
if (start_token) {
parse_events_set_extra(NULL, yyscanner);
/*
* The flex parser does not init locations variable
* via the scan_string interface, so we need do the
* init in here.
*/
yycolumn = 0;
return start_token;
}
}
%}
<event>{
{group} {
BEGIN(INITIAL);
REWIND(0);
}
{event_pmu} |
{bpf_object} |
{bpf_source} |
{event} {
BEGIN(INITIAL);
REWIND(1);
return PE_EVENT_NAME;
}
<<EOF>> {
BEGIN(INITIAL);
REWIND(0);
}
}
<array>{
"]" { BEGIN(config); return ']'; }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
, { return ','; }
"\.\.\." { return PE_ARRAY_RANGE; }
}
<config>{
/*
* Please update config_term_names when new static term is added.
*/
config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
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); }
call-graph { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
stack-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
max-stack { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
, { return ','; }
"/" { BEGIN(INITIAL); return '/'; }
{name_minus} { return str(yyscanner, PE_NAME); }
\[all\] { return PE_ARRAY_ALL; }
"[" { BEGIN(array); return '['; }
@{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); }
}
<mem>{
{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
: { return ':'; }
"/" { return '/'; }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
/*
* We need to separate 'mem:' scanner part, in order to get specific
* modifier bits parsed out. Otherwise we would need to handle PE_NAME
* and we'd need to parse it manually. During the escape from <mem>
* state we need to put the escaping char back, so we dont miss it.
*/
. { unput(*yytext); BEGIN(INITIAL); }
/*
* We destroy the scanner after reaching EOF,
* but anyway just to be sure get back to INIT state.
*/
<<EOF>> { BEGIN(INITIAL); }
}
cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
/*
* We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
* Because the prefix cycles is mixed up with cpu-cycles.
* loads and stores are mixed up with cache event
*/
cycles-ct { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
cycles-t { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
mem-loads { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
mem-stores { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
topdown-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
L1-dcache|l1-d|l1d|L1-data |
L1-icache|l1-i|l1i|L1-instruction |
LLC|L2 |
dTLB|d-tlb|Data-TLB |
iTLB|i-tlb|Instruction-TLB |
branch|branches|bpu|btb|bpc |
node { return str(yyscanner, PE_NAME_CACHE_TYPE); }
load|loads|read |
store|stores|write |
prefetch|prefetches |
speculative-read|speculative-load |
refs|Reference|ops|access |
misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
mem: { BEGIN(mem); return PE_PREFIX_MEM; }
r{num_raw_hex} { return raw(yyscanner); }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
{bpf_object} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
{bpf_source} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
{name} { return pmu_str_check(yyscanner); }
"/" { BEGIN(config); return '/'; }
- { return '-'; }
, { BEGIN(event); return ','; }
: { return ':'; }
"{" { BEGIN(event); return '{'; }
"}" { return '}'; }
= { return '='; }
\n { }
. { }
%%
int parse_events_wrap(void *scanner __maybe_unused)
{
return 1;
}