linux_dsm_epyc7002/tools/perf/util/parse-events.l
Andi Kleen 44b1e60ab5 perf stat: Basic support for TopDown in perf stat
Add basic plumbing for TopDown in perf stat

TopDown is intended to replace the frontend cycles idle/ backend cycles
idle metrics in standard perf stat output.  These metrics are not
reliable in many workloads, due to out of order effects.

This implements a new --topdown mode in perf stat (similar to
--transaction) that measures the pipe line bottlenecks using
standardized formulas. The measurement can be all done with 5 counters
(one fixed counter)

The result are four metrics:

FrontendBound, BackendBound, BadSpeculation, Retiring

that describe the CPU pipeline behavior on a high level.

The full top down methology has many hierarchical metrics.  This
implementation only supports level 1 which can be collected without
multiplexing. A full implementation of top down on top of perf is
available in pmu-tools toplev.  (http://github.com/andikleen/pmu-tools)

The current version works on Intel Core CPUs starting with Sandy Bridge,
and Atom CPUs starting with Silvermont.  In principle the generic
metrics should be also implementable on other out of order CPUs.

TopDown level 1 uses a set of abstracted metrics which are generic to
out of order CPU cores (although some CPUs may not implement all of
them):

  topdown-total-slots       Available slots in the pipeline
  topdown-slots-issued      Slots issued into the pipeline
  topdown-slots-retired     Slots successfully retired
  topdown-fetch-bubbles     Pipeline gaps in the frontend
  topdown-recovery-bubbles  Pipeline gaps during recovery
                            from misspeculation

These metrics then allow to compute four useful metrics:

FrontendBound, BackendBound, Retiring, BadSpeculation.

Add a new --topdown options to enable events.  When --topdown is
specified set up events for all topdown events supported by the kernel.
Add topdown-* as a special case to the event parser, as is needed for
all events containing -.

The actual code to compute the metrics is in follow-on patches.

v2: Use standard sysctl read function.
v3: Move x86 specific code to arch/
v4: Enable --metric-only implicitly for topdown.
v5: Add --single-thread option to not force per core mode
v6: Fix output order of topdown metrics
v7: Allow combining with -d
v8: Remove --single-thread again
v9: Rename functions, adding arch_ and topdown_.
v10: Expand man page and describe TopDown better
Paste intro into commit description.
Print error when malloc fails.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1464119559-17203-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-06-06 17:04:15 -03:00

305 lines
9.0 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;
}
#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)
bpf_source .*\.c
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\-_*?.:]*
/* If you add a modifier you need to update check_modifier() */
modifier_event [ukhpPGHSDI]+
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); }
, { return ','; }
"/" { BEGIN(INITIAL); return '/'; }
{name_minus} { return str(yyscanner, PE_NAME); }
\[all\] { return PE_ARRAY_ALL; }
"[" { BEGIN(array); return '['; }
}
<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} { return str(yyscanner, PE_BPF_OBJECT); }
{bpf_source} { 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;
}