2012-03-15 23:09:15 +04:00
2012-06-15 10:31:39 +04:00
%option reentrant
%option bison-bridge
2012-03-15 23:09:15 +04:00
%option prefix="parse_events_"
2012-05-21 11:12:52 +04:00
%option stack
2015-04-22 22:10:17 +03:00
%option bison-locations
%option yylineno
2017-11-08 18:43:09 +03:00
%option reject
2012-03-15 23:09:15 +04:00
%{
#include <errno.h>
2017-10-13 11:37:35 +03:00
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
2012-03-15 23:09:15 +04:00
#include "../perf.h"
2012-03-15 23:09:16 +04:00
#include "parse-events.h"
perf tools: Enable indices setting syntax for BPF map
This patch introduces a new syntax to perf event parser:
# perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
By utilizing the basic facilities in bpf-loader.c which allow setting
different slots in a BPF map separately, the newly introduced syntax
allows perf to control specific elements in a BPF map.
Test result:
# cat ./test_bpf_map_3.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
(void *)BPF_FUNC_map_lookup_elem;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(unsigned char),
.max_entries = 100,
};
SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
int func(void *ctx, int err, long nsec)
{
char fmt[] = "%ld\n";
long usec = nsec * 0x10624dd3 >> 38; // nsec / 1000
int key = (int)usec;
unsigned char *pval = map_lookup_elem(&channel, &key);
if (!pval)
return 0;
trace_printk(fmt, sizeof(fmt), (unsigned char)*pval);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Normal case:
# echo "" > /sys/kernel/debug/tracing/trace
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 15
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
# ./perf record -e './test_bpf_map_3.c/map:channel.value[all]=104/' usleep 99
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
usleep-1537 [003] d... 2745538.053737: : 104
Error case:
# ./perf record -e './test_bpf_map_3.c/map:channel.value[10...1000]=104/' usleep 99
event syntax error: '..annel.value[10...1000]=104/'
\___ Index too large
Hint: Valid config terms:
map:[<arraymap>].value<indices>=[value]
map:[<eventmap>].event<indices>=[event]
where <indices> is something like [0,3...5] or [all]
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-9-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:35 +03:00
#include "parse-events-bison.h"
2019-03-27 01:18:21 +03:00
#include "evsel.h"
2012-03-15 23:09:15 +04:00
2012-06-15 10:31:39 +04:00
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)
2012-03-15 23:09:15 +04:00
{
2012-08-07 21:43:13 +04:00
u64 num;
2012-03-15 23:09:15 +04:00
errno = 0;
2012-08-07 21:43:13 +04:00
num = strtoull(str, NULL, base);
2012-03-15 23:09:15 +04:00
if (errno)
return PE_ERROR;
2012-06-15 10:31:39 +04:00
yylval->num = num;
2012-03-15 23:09:15 +04:00
return token;
}
2012-06-15 10:31:39 +04:00
static int value(yyscan_t scanner, int base)
2012-03-15 23:09:15 +04:00
{
2012-06-15 10:31:39 +04:00
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
return __value(yylval, text, base, PE_VALUE);
2012-03-15 23:09:15 +04:00
}
2012-06-15 10:31:39 +04:00
static int raw(yyscan_t scanner)
2012-03-15 23:09:15 +04:00
{
2012-06-15 10:31:39 +04:00
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
return __value(yylval, text + 1, 16, PE_RAW);
2012-03-15 23:09:15 +04:00
}
2012-06-15 10:31:39 +04:00
static int str(yyscan_t scanner, int token)
2012-03-15 23:09:15 +04:00
{
2012-06-15 10:31:39 +04:00
YYSTYPE *yylval = parse_events_get_lval(scanner);
char *text = parse_events_get_text(scanner);
perf record: Enable arbitrary event names thru name= modifier
Enable complex event names containing [.:=,] symbols to be encoded into Perf
trace using name= modifier e.g. like this:
perf record -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',\
period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
Below is how it looks like in the report output. Please note explicit escaped
quoting at cmdline string in the header so that thestring can be directly reused
for another collection in shell:
perf report --header
# ========
...
# cmdline : /root/abudanko/kernel/tip/tools/perf/perf record -v -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
# event : name = OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM, , type = 4, size = 112, config = 0x100003c, { sample_period, sample_freq } = 3500000, sample_type = IP|TID|TIME, disabled = 1, inh
...
# ========
#
#
# Total Lost Samples: 0
#
# Samples: 24K of event 'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM'
# Event count (approx.): 86492000000
#
# Overhead Command Shared Object Symbol
# ........ ....... ................ ..............................................
#
14.75% futex [kernel.vmlinux] [k] __entry_trampoline_start
...
perf stat -e cpu/name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
10000000 process context switches in 16678890291ns (1667.9ns/ctxsw)
Performance counter stats for './futex':
88,095,770,571 CPU_CLK_UNHALTED.THREAD:cmask=0x1
16.679542407 seconds time elapsed
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/c194b060-761d-0d50-3b21-bb4ed680002d@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04 09:50:56 +03:00
if (text[0] != '\'') {
yylval->str = strdup(text);
} else {
/*
* If a text tag specified on the command line
* contains opening single quite ' then it is
* expected that the tag ends with single quote
* as well, like this:
* name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\'
* quotes need to be escaped to bypass shell
* processing.
*/
yylval->str = strndup(&text[1], strlen(text) - 2);
}
2012-03-15 23:09:15 +04:00
return token;
}
2017-10-13 11:37:35 +03:00
static bool isbpf_suffix(char *text)
perf bpf: Tighten detection of BPF events
perf stat -e cpu/uops_executed.core,cmask=1/
would be detected as a BPF source event because the .c matches the .c
source BPF pattern.
v2:
Originally I tried to use lex lookahead, but it doesn't seem to work.
This now extends the BPF pattern to match longer events, but then does
an extra check in the C code to reject BPF matches that do not end with
.c/.o/.obj
This uses REJECT, which makes the flex scanner slower, but that
shouldn't be a big problem for the perf events.
Committer testing:
# perf trace -e write -e /home/acme/bpf/tracepoint.c cat /etc/passwd > /dev/null
0.000 ( 0.006 ms): cat/18485 write(fd: 1, buf: 0x7f59eebe1000, count: 3494 ) ...
0.006 ( ): raw_syscalls:sys_enter:NR 1 (1, 7f59eebe1000, da6, 22, 7f59eebe0010, 0))
0.008 ( ): perf_bpf_probe:_write:(ffffffff9626b2c0))
0.000 ( 0.010 ms): cat/18485 ... [continued]: write()) = 3494
#
It continues doing what was expected, i.e. identifying
/home/acme/bpf/tracepoint.c as a BPF event and activates the clang
machinery to build an eBPF object and then uses sys_bpf() to hook it up
to the raw_syscalls:sys_enter tracepoint, etc.
Andi forgot to add Wang to the CC list, fix it.
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>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170811232634.30465-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-12 02:26:19 +03:00
{
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;
}
2017-10-13 11:37:35 +03:00
static bool isbpf(yyscan_t scanner)
{
char *text = parse_events_get_text(scanner);
struct stat st;
if (!isbpf_suffix(text))
return false;
return stat(text, &st) == 0;
}
2016-09-06 19:37:15 +03:00
/*
* 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;
}
2015-04-22 22:10:17 +03:00
#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)
2014-10-07 19:08:51 +04:00
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;
}
}
2012-06-15 10:31:39 +04:00
static int sym(yyscan_t scanner, int type, int config)
2012-03-15 23:09:15 +04:00
{
2012-06-15 10:31:39 +04:00
YYSTYPE *yylval = parse_events_get_lval(scanner);
yylval->num = (type << 16) + config;
2012-07-04 02:00:43 +04:00
return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
2012-03-15 23:09:15 +04:00
}
2019-03-27 01:18:21 +03:00
static int tool(yyscan_t scanner, enum perf_tool_event event)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
yylval->num = event;
return PE_VALUE_SYM_TOOL;
}
2012-06-15 10:31:39 +04:00
static int term(yyscan_t scanner, int type)
2012-03-15 23:09:16 +04:00
{
2012-06-15 10:31:39 +04:00
YYSTYPE *yylval = parse_events_get_lval(scanner);
yylval->num = type;
2012-03-15 23:09:16 +04:00
return PE_TERM;
}
2015-04-22 22:10:17 +03:00
#define YY_USER_ACTION \
do { \
yylloc->last_column = yylloc->first_column; \
yylloc->first_column = yycolumn; \
yycolumn += yyleng; \
} while (0);
2017-10-12 18:03:38 +03:00
#define USER_REJECT \
yycolumn -= yyleng; \
REJECT
2012-03-15 23:09:15 +04:00
%}
2012-05-21 11:12:52 +04:00
%x mem
2012-08-16 23:10:21 +04:00
%s config
%x event
perf tools: Enable indices setting syntax for BPF map
This patch introduces a new syntax to perf event parser:
# perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
By utilizing the basic facilities in bpf-loader.c which allow setting
different slots in a BPF map separately, the newly introduced syntax
allows perf to control specific elements in a BPF map.
Test result:
# cat ./test_bpf_map_3.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
(void *)BPF_FUNC_map_lookup_elem;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(unsigned char),
.max_entries = 100,
};
SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
int func(void *ctx, int err, long nsec)
{
char fmt[] = "%ld\n";
long usec = nsec * 0x10624dd3 >> 38; // nsec / 1000
int key = (int)usec;
unsigned char *pval = map_lookup_elem(&channel, &key);
if (!pval)
return 0;
trace_printk(fmt, sizeof(fmt), (unsigned char)*pval);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Normal case:
# echo "" > /sys/kernel/debug/tracing/trace
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 15
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
# ./perf record -e './test_bpf_map_3.c/map:channel.value[all]=104/' usleep 99
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
usleep-1537 [003] d... 2745538.053737: : 104
Error case:
# ./perf record -e './test_bpf_map_3.c/map:channel.value[10...1000]=104/' usleep 99
event syntax error: '..annel.value[10...1000]=104/'
\___ Index too large
Hint: Valid config terms:
map:[<arraymap>].value<indices>=[value]
map:[<eventmap>].event<indices>=[event]
where <indices> is something like [0,3...5] or [all]
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-9-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:35 +03:00
%x array
2012-08-16 23:10:21 +04:00
group [^,{}/]*[{][^}]*[}][^,{}/]*
event_pmu [^,{}/]+[/][^/]*[/][^,{}/]*
event [^,{}/]+
perf bpf: Tighten detection of BPF events
perf stat -e cpu/uops_executed.core,cmask=1/
would be detected as a BPF source event because the .c matches the .c
source BPF pattern.
v2:
Originally I tried to use lex lookahead, but it doesn't seem to work.
This now extends the BPF pattern to match longer events, but then does
an extra check in the C code to reject BPF matches that do not end with
.c/.o/.obj
This uses REJECT, which makes the flex scanner slower, but that
shouldn't be a big problem for the perf events.
Committer testing:
# perf trace -e write -e /home/acme/bpf/tracepoint.c cat /etc/passwd > /dev/null
0.000 ( 0.006 ms): cat/18485 write(fd: 1, buf: 0x7f59eebe1000, count: 3494 ) ...
0.006 ( ): raw_syscalls:sys_enter:NR 1 (1, 7f59eebe1000, da6, 22, 7f59eebe0010, 0))
0.008 ( ): perf_bpf_probe:_write:(ffffffff9626b2c0))
0.000 ( 0.010 ms): cat/18485 ... [continued]: write()) = 3494
#
It continues doing what was expected, i.e. identifying
/home/acme/bpf/tracepoint.c as a BPF event and activates the clang
machinery to build an eBPF object and then uses sys_bpf() to hook it up
to the raw_syscalls:sys_enter tracepoint, etc.
Andi forgot to add Wang to the CC list, fix it.
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>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170811232634.30465-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-12 02:26:19 +03:00
bpf_object [^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
bpf_source [^,{}]+\.c[a-zA-Z0-9._]*
2012-05-21 11:12:52 +04:00
2012-03-15 23:09:15 +04:00
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
num_raw_hex [a-fA-F0-9]+
2018-03-06 17:04:42 +03:00
name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
perf record: Enable arbitrary event names thru name= modifier
Enable complex event names containing [.:=,] symbols to be encoded into Perf
trace using name= modifier e.g. like this:
perf record -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',\
period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
Below is how it looks like in the report output. Please note explicit escaped
quoting at cmdline string in the header so that thestring can be directly reused
for another collection in shell:
perf report --header
# ========
...
# cmdline : /root/abudanko/kernel/tip/tools/perf/perf record -v -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
# event : name = OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM, , type = 4, size = 112, config = 0x100003c, { sample_period, sample_freq } = 3500000, sample_type = IP|TID|TIME, disabled = 1, inh
...
# ========
#
#
# Total Lost Samples: 0
#
# Samples: 24K of event 'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM'
# Event count (approx.): 86492000000
#
# Overhead Command Shared Object Symbol
# ........ ....... ................ ..............................................
#
14.75% futex [kernel.vmlinux] [k] __entry_trampoline_start
...
perf stat -e cpu/name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
10000000 process context switches in 16678890291ns (1667.9ns/ctxsw)
Performance counter stats for './futex':
88,095,770,571 CPU_CLK_UNHALTED.THREAD:cmask=0x1
16.679542407 seconds time elapsed
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/c194b060-761d-0d50-3b21-bb4ed680002d@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04 09:50:56 +03:00
name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
perf tools: Enable BPF object configure syntax
This patch adds the final step for BPF map configuration. A new syntax
is appended into parser so user can config BPF objects through '/' '/'
enclosed config terms.
After this patch, following syntax is available:
# perf record -e ./test_bpf_map_1.c/map:channel.value=10/ ...
It would takes effect after appling following commits.
Test result:
# cat ./test_bpf_map_1.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
(void *)BPF_FUNC_map_lookup_elem;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1,
};
SEC("func=sys_nanosleep")
int func(void *ctx)
{
int key = 0;
char fmt[] = "%d\n";
int *pval = map_lookup_elem(&channel, &key);
if (!pval)
return 0;
trace_printk(fmt, sizeof(fmt), *pval);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
- Normal case:
# ./perf record -e './test_bpf_map_1.c/map:channel.value=10/' usleep 10
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
- Error case:
# ./perf record -e './test_bpf_map_1.c/map:channel.value/' usleep 10
event syntax error: '..ps:channel:value/'
\___ Config value not set (missing '=')
Hint: Valid config term:
map:[<arraymap>]:value=[value]
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
# ./perf record -e './test_bpf_map_1.c/xmap:channel.value=10/' usleep 10
event syntax error: '..pf_map_1.c/xmap:channel.value=10/'
\___ Invalid object config option
[SNIP]
# ./perf record -e './test_bpf_map_1.c/map:xchannel.value=10/' usleep 10
event syntax error: '..p_1.c/map:xchannel.value=10/'
\___ Target map not exist
[SNIP]
# ./perf record -e './test_bpf_map_1.c/map:channel.xvalue=10/' usleep 10
event syntax error: '..ps:channel.xvalue=10/'
\___ Invalid object map config option
[SNIP]
# ./perf record -e './test_bpf_map_1.c/map:channel.value=x10/' usleep 10
event syntax error: '..nnel.value=x10/'
\___ Incorrect value type for map
[SNIP]
Change BPF_MAP_TYPE_ARRAY to '1' in test_bpf_map_1.c:
# ./perf record -e './test_bpf_map_1.c/map:channel.value=10/' usleep 10
event syntax error: '..ps:channel.value=10/'
\___ Can't use this config term to this type of map
Hint: Valid config term:
map:[<arraymap>].value=[value]
(add -v to see detail)
Signed-off-by: Wang Nan <wangnan0@huawei.com>
[for parser part]
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-5-git-send-email-wangnan0@huawei.com
Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:31 +03:00
name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
2016-09-06 19:37:15 +03:00
drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
perf tools: Add support for pinned modifier
This commit adds support for a new modifier "D", which requests that the
event, or group of events, be pinned to the PMU.
The "p" modifier is already taken for precise, and "P" may be used in
future to mean "fully precise".
So we use "D", which stands for pinneD - and looks like a padlock, or if
you're using the ":D" syntax perf smiles at you.
This is an oft-requested feature from our HW folks, who want to be able
to run a large number of events, but also want 100% accurate results for
instructions per cycle.
Comparison of results with and without pinning:
$ perf stat -e '{cycles,instructions}:D' -e cycles,instructions,...
79,590,480,683 cycles # 0.000 GHz
166,123,716,524 instructions # 2.09 insns per cycle
# 0.11 stalled cycles per insn
79,352,134,463 cycles # 0.000 GHz [11.11%]
165,178,301,818 instructions # 2.08 insns per cycle
# 0.11 stalled cycles per insn [11.13%]
As you can see although perf does a very good job of scaling the values
in the non-pinned case, there is some small discrepancy.
The patch is fairly straight forward, the one detail is that we need to
make sure we only request pinning for the group leader when we have a
group.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1375795686-4226-1-git-send-email-michael@ellerman.id.au
[ Use perf_evsel__is_group_leader instead of open coded equivalent, as
suggested by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-06 17:28:05 +04:00
/* If you add a modifier you need to update check_modifier() */
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>
2017-08-31 22:40:26 +03:00
modifier_event [ukhpPGHSDIW]+
2012-06-29 11:22:54 +04:00
modifier_bp [rwx]{1,3}
2012-03-15 23:09:15 +04:00
%%
2012-06-15 10:31:40 +04:00
%{
{
int start_token;
2012-08-16 23:10:21 +04:00
start_token = parse_events_get_extra(yyscanner);
if (start_token == PE_START_TERMS)
BEGIN(config);
else if (start_token == PE_START_EVENTS)
BEGIN(event);
2012-06-15 10:31:40 +04:00
if (start_token) {
parse_events_set_extra(NULL, yyscanner);
2015-04-22 22:10:17 +03:00
/*
* The flex parser does not init locations variable
* via the scan_string interface, so we need do the
* init in here.
*/
yycolumn = 0;
2012-06-15 10:31:40 +04:00
return start_token;
}
}
%}
2012-08-16 23:10:21 +04:00
<event>{
{group} {
2015-04-22 22:10:17 +03:00
BEGIN(INITIAL);
REWIND(0);
2012-08-16 23:10:21 +04:00
}
{event_pmu} |
perf tools: Enable passing bpf object file to --event
By introducing new rules in tools/perf/util/parse-events.[ly], this
patch enables 'perf record --event bpf_file.o' to select events by an
eBPF object file. It calls parse_events_load_bpf() to load that file,
which uses bpf__prepare_load() and finally calls bpf_object__open() for
the object files.
After applying this patch, commands like:
# perf record --event foo.o sleep
become possible.
However, at this point it is unable to link any useful things onto the
evsel list because the creating of probe points and BPF program
attaching have not been implemented. Before real events are possible to
be extracted, to avoid perf report error because of empty evsel list,
this patch link a dummy evsel. The dummy event related code will be
removed when probing and extracting code is ready.
Commiter notes:
Using it:
$ ls -la foo.o
ls: cannot access foo.o: No such file or directory
$ perf record --event foo.o sleep
libbpf: failed to open foo.o: No such file or directory
event syntax error: 'foo.o'
\___ BPF object file 'foo.o' is invalid
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
$
$ file /tmp/build/perf/perf.o
/tmp/build/perf/perf.o: ELF 64-bit LSB relocatable, x86-64, version 1 (SYSV), not stripped
$ perf record --event /tmp/build/perf/perf.o sleep
libbpf: /tmp/build/perf/perf.o is not an eBPF object file
event syntax error: '/tmp/build/perf/perf.o'
\___ BPF object file '/tmp/build/perf/perf.o' is invalid
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
$
$ file /tmp/foo.o
/tmp/foo.o: ELF 64-bit LSB relocatable, no machine, version 1 (SYSV), not stripped
$ perf record --event /tmp/foo.o sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.013 MB perf.data ]
$ perf evlist
/tmp/foo.o
$ perf evlist -v
/tmp/foo.o: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
$
So, type 1 is PERF_TYPE_SOFTWARE, config 0x9 is PERF_COUNT_SW_DUMMY, ok.
$ perf report --stdio
Error:
The perf.data file has no samples!
# To display the perf.data header info, please use --header/--header-only options.
#
$
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1444826502-49291-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 15:41:14 +03:00
{bpf_object} |
2015-10-14 15:41:20 +03:00
{bpf_source} |
2012-08-16 23:10:21 +04:00
{event} {
2015-04-22 22:10:17 +03:00
BEGIN(INITIAL);
REWIND(1);
2012-08-16 23:10:21 +04:00
return PE_EVENT_NAME;
}
<<EOF>> {
2015-04-22 22:10:17 +03:00
BEGIN(INITIAL);
REWIND(0);
2012-08-16 23:10:21 +04:00
}
}
perf tools: Enable indices setting syntax for BPF map
This patch introduces a new syntax to perf event parser:
# perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
By utilizing the basic facilities in bpf-loader.c which allow setting
different slots in a BPF map separately, the newly introduced syntax
allows perf to control specific elements in a BPF map.
Test result:
# cat ./test_bpf_map_3.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
(void *)BPF_FUNC_map_lookup_elem;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(unsigned char),
.max_entries = 100,
};
SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
int func(void *ctx, int err, long nsec)
{
char fmt[] = "%ld\n";
long usec = nsec * 0x10624dd3 >> 38; // nsec / 1000
int key = (int)usec;
unsigned char *pval = map_lookup_elem(&channel, &key);
if (!pval)
return 0;
trace_printk(fmt, sizeof(fmt), (unsigned char)*pval);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Normal case:
# echo "" > /sys/kernel/debug/tracing/trace
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 15
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
# ./perf record -e './test_bpf_map_3.c/map:channel.value[all]=104/' usleep 99
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
usleep-1537 [003] d... 2745538.053737: : 104
Error case:
# ./perf record -e './test_bpf_map_3.c/map:channel.value[10...1000]=104/' usleep 99
event syntax error: '..annel.value[10...1000]=104/'
\___ Index too large
Hint: Valid config terms:
map:[<arraymap>].value<indices>=[value]
map:[<eventmap>].event<indices>=[event]
where <indices> is something like [0,3...5] or [all]
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-9-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:35 +03:00
<array>{
"]" { BEGIN(config); return ']'; }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
, { return ','; }
"\.\.\." { return PE_ARRAY_RANGE; }
}
2013-09-27 20:29:58 +04:00
<config>{
perf tools: Add term support for parse_events_error
Allowing event's term processing to report back error, like:
$ perf record -e 'cpu/even=0x1/' ls
event syntax error: 'cpu/even=0x1/'
\___ unknown term
valid terms: pc,any,inv,edge,cmask,event,in_tx,ldlat,umask,in_tx_cp,offcore_rsp,config,config1,config2,name,period,branch_type
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1429729824-13932-7-git-send-email-jolsa@kernel.org
[ Renamed 'error' variables to 'err', not to clash with util.h error() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-22 22:10:21 +03:00
/*
2016-02-19 14:43:57 +03:00
* Please update config_term_names when new static term is added.
perf tools: Add term support for parse_events_error
Allowing event's term processing to report back error, like:
$ perf record -e 'cpu/even=0x1/' ls
event syntax error: 'cpu/even=0x1/'
\___ unknown term
valid terms: pc,any,inv,edge,cmask,event,in_tx,ldlat,umask,in_tx_cp,offcore_rsp,config,config1,config2,name,period,branch_type
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1429729824-13932-7-git-send-email-jolsa@kernel.org
[ Renamed 'error' variables to 'err', not to clash with util.h error() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-22 22:10:21 +03:00
*/
2013-09-27 20:29:58 +04:00
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); }
2015-08-09 09:45:23 +03:00
freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); }
2013-09-27 20:29:58 +04:00
branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
2015-08-04 11:30:19 +03:00
time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
perf callchain: Per-event type selection support
This patchkit adds the ability to set callgraph mode (fp, dwarf, lbr) per
event. This in term can reduce sampling overhead and the size of the
perf.data.
Here is an example.
perf record -e 'cpu/cpu-cycles,period=1000,call-graph=fp,time=1/,cpu/instructions,call-graph=lbr/' sleep 1
perf evlist -v
cpu/cpu-cycles,period=1000,call-graph=fp,time=1/: type: 4, size: 112,
config: 0x3c, { sample_period, sample_freq }: 1000, sample_type:
IP|TID|TIME|CALLCHAIN|PERIOD|IDENTIFIER, read_format: ID, disabled: 1,
inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all:
1, exclude_guest: 1, mmap2: 1, comm_exec: 1
cpu/instructions,call-graph=lbr/: type: 4, size: 112, config: 0xc0, {
sample_period, sample_freq }: 4000, sample_type:
IP|TID|TIME|CALLCHAIN|PERIOD|BRANCH_STACK|IDENTIFIER, read_format: ID,
disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1,
exclude_guest: 1
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1439289050-40510-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 13:30:47 +03:00
call-graph { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
stack-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
perf tools: Per event max-stack settings
The tooling counterpart, now it is possible to do:
# perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ]
# perf evlist -v
sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10
cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4
cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024
# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events
Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should
be further configurable by means of some .perfconfig knob.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-29 01:03:42 +03:00
max-stack { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
perf evsel: Introduce per event max_events property
This simply adds the field to 'struct perf_evsel' and allows setting
it via the event parser, to test it lets trace trace:
First look at where in a function that receives an evsel we can put a probe
to read how evsel->max_events was setup:
# perf probe -x ~/bin/perf -L trace__event_handler
<trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0>
0 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
3 {
4 struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
5 int callchain_ret = 0;
7 if (sample->callchain) {
8 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
9 if (callchain_ret == 0) {
10 if (callchain_cursor.nr < trace->min_stack)
11 goto out;
12 callchain_ret = 1;
}
}
See what variables we can probe at line 7:
# perf probe -x ~/bin/perf -V trace__event_handler:7
Available variables at trace__event_handler:7
@<trace__event_handler+89>
int callchain_ret
struct perf_evsel* evsel
struct perf_sample* sample
struct thread* thread
struct trace* trace
union perf_event* event
Add a probe at that line asking for evsel->max_events to be collected and named
as "max_events":
# perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events'
Added new event:
probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events)
You can now use it in all perf tools, such as:
perf record -e probe_perf:trace__event_handler -aR sleep 1
Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e.
the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event,
while the traced trace is tracing all scheduler tracepoints, will stop at two
events (--max-events 2) and will just set evsel->max_events for all the sched
tracepoints to 9, we will see the output of both traces intermixed:
# trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000
0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000
0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
#
Now, if the traced trace sends its output to /dev/null, we'll see just
what the first level trace outputs: that evsel->max_events is indeed
being set to 9:
# trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/
0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
#
Now that we can set evsel->max_events, we can go to the next step, honour that
per-event property in 'perf trace'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 21:47:34 +03:00
nr { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
perf tools: Enable pre-event inherit setting by config terms
This patch allows perf record setting event's attr.inherit bit by
config terms like:
# perf record -e cycles/no-inherit/ ...
# perf record -e cycles/inherit/ ...
So user can control inherit bit for each event separately.
In following example, a.out fork()s in main then do some complex
CPU intensive computations in both of its children.
Basic result with and without inherit:
# perf record -e cycles -e instructions ./a.out
[ perf record: Woken up 9 times to write data ]
[ perf record: Captured and wrote 2.205 MB perf.data (47920 samples) ]
# perf report --stdio
# ...
# Samples: 23K of event 'cycles'
# Event count (approx.): 23641752891
...
# Samples: 24K of event 'instructions'
# Event count (approx.): 30428312415
# perf record -i -e cycles -e instructions ./a.out
[ perf record: Woken up 5 times to write data ]
[ perf record: Captured and wrote 1.111 MB perf.data (24019 samples) ]
...
# Samples: 12K of event 'cycles'
# Event count (approx.): 11699501775
...
# Samples: 12K of event 'instructions'
# Event count (approx.): 15058023559
Cancel inherit for one event when globally enable:
# perf record -e cycles/no-inherit/ -e instructions ./a.out
[ perf record: Woken up 7 times to write data ]
[ perf record: Captured and wrote 1.660 MB perf.data (36004 samples) ]
...
# Samples: 12K of event 'cycles/no-inherit/'
# Event count (approx.): 11895759282
...
# Samples: 24K of event 'instructions'
# Event count (approx.): 30668000441
Enable inherit for one event when globally disable:
# perf record -i -e cycles/inherit/ -e instructions ./a.out
[ perf record: Woken up 7 times to write data ]
[ perf record: Captured and wrote 1.654 MB perf.data (35868 samples) ]
...
# Samples: 23K of event 'cycles/inherit/'
# Event count (approx.): 23285400229
...
# Samples: 11K of event 'instructions'
# Event count (approx.): 14969050259
Committer note:
One can check if the bit was set, in addition to seeing the result in
the perf.data file size as above by doing one of:
# perf record -e cycles -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.911 MB perf.data (63 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
#
So, the inherit bit was set in both, now, if we disable it globally using
--no-inherit:
# perf record --no-inherit -e cycles -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.910 MB perf.data (56 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
No inherit bit set, then disabling it and setting just on the cycles event:
# perf record --no-inherit -e cycles/inherit/ -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.909 MB perf.data (48 samples) ]
# perf evlist -v
cycles/inherit/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
#
We can see it as well in by using a more verbose level of debug messages in
the tool that sets up the perf_event_attr, 'perf record' in this case:
[root@zoo ~]# perf record -vv --no-inherit -e cycles/inherit/ -e instructions -a usleep 1
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|ID|CPU|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
task 1
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
------------------------------------------------------------
perf_event_attr:
size 112
config 0x1
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|ID|CPU|PERIOD
read_format ID
disabled 1
freq 1
sample_id_all 1
exclude_guest 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
<SNIP>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446029705-199659-2-git-send-email-wangnan0@huawei.com
[ s/u64/bool/ for the perf_evsel_config_term inherit field - jolsa]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-28 13:55:02 +03:00
inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
perf tools: Enable overwrite settings
This patch allows following config terms and option:
Globally setting events to overwrite;
# perf record --overwrite ...
Set specific events to be overwrite or no-overwrite.
# perf record --event cycles/overwrite/ ...
# perf record --event cycles/no-overwrite/ ...
Add missing config terms and update the config term array size because
the longest string length has changed.
For overwritable events, it automatically selects attr.write_backward
since perf requires it to be backward for reading.
Test result:
# perf record --overwrite -e syscalls:*enter_nanosleep* usleep 1
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ]
# perf evlist -v
syscalls:sys_enter_nanosleep: type: 2, size: 112, config: 0x134, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, write_backward: 1
# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1468485287-33422-14-git-send-email-wangnan0@huawei.com
Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-14 11:34:45 +03:00
overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
2019-04-12 16:59:47 +03:00
percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
2019-08-06 11:46:05 +03:00
aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
2019-11-15 15:42:17 +03:00
aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
2013-09-27 20:29:58 +04:00
, { return ','; }
"/" { BEGIN(INITIAL); return '/'; }
{name_minus} { return str(yyscanner, PE_NAME); }
perf tools: Enable indices setting syntax for BPF map
This patch introduces a new syntax to perf event parser:
# perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
By utilizing the basic facilities in bpf-loader.c which allow setting
different slots in a BPF map separately, the newly introduced syntax
allows perf to control specific elements in a BPF map.
Test result:
# cat ./test_bpf_map_3.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
static void *(*map_lookup_elem)(struct bpf_map_def *, void *) =
(void *)BPF_FUNC_map_lookup_elem;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(unsigned char),
.max_entries = 100,
};
SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
int func(void *ctx, int err, long nsec)
{
char fmt[] = "%ld\n";
long usec = nsec * 0x10624dd3 >> 38; // nsec / 1000
int key = (int)usec;
unsigned char *pval = map_lookup_elem(&channel, &key);
if (!pval)
return 0;
trace_printk(fmt, sizeof(fmt), (unsigned char)*pval);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Normal case:
# echo "" > /sys/kernel/debug/tracing/trace
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# ./perf record -e './test_bpf_map_3.c/map:channel.value[0...9,20...29]=102,map:channel.value[10...19]=103/' usleep 15
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data ]
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
# ./perf record -e './test_bpf_map_3.c/map:channel.value[all]=104/' usleep 99
# cat /sys/kernel/debug/tracing/trace | grep usleep
usleep-405 [004] d... 2745423.547822: : 101
usleep-655 [006] d... 2745434.122814: : 102
usleep-904 [006] d... 2745439.916264: : 103
usleep-1537 [003] d... 2745538.053737: : 104
Error case:
# ./perf record -e './test_bpf_map_3.c/map:channel.value[10...1000]=104/' usleep 99
event syntax error: '..annel.value[10...1000]=104/'
\___ Index too large
Hint: Valid config terms:
map:[<arraymap>].value<indices>=[value]
map:[<eventmap>].event<indices>=[event]
where <indices> is something like [0,3...5] or [all]
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-9-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:35 +03:00
\[all\] { return PE_ARRAY_ALL; }
"[" { BEGIN(array); return '['; }
2016-09-06 19:37:15 +03:00
@{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); }
2013-09-27 20:29:58 +04:00
}
<mem>{
{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
: { return ':'; }
2014-05-29 19:26:51 +04:00
"/" { return '/'; }
2013-09-27 20:29:58 +04:00
{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); }
}
2012-06-15 10:31:39 +04:00
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); }
2013-08-31 22:50:52 +04:00
dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
2019-03-27 01:18:21 +03:00
duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
perf tools: Introduce bpf-output event
Commit a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
adds a helper to enable a BPF program to output data to a perf ring
buffer through a new type of perf event, PERF_COUNT_SW_BPF_OUTPUT. This
patch enables perf to create events of that type. Now a perf user can
use the following cmdline to receive output data from BPF programs:
# perf record -a -e bpf-output/no-inherit,name=evt/ \
-e ./test_bpf_output.c/map:channel.event=evt/ ls /
# perf script
perf 1560 [004] 347747.086295: evt: ffffffff811fd201 sys_write ...
perf 1560 [004] 347747.086300: evt: ffffffff811fd201 sys_write ...
perf 1560 [004] 347747.086315: evt: ffffffff811fd201 sys_write ...
...
Test result:
# cat test_bpf_output.c
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
#define SEC(NAME) __attribute__((section(NAME), used))
static u64 (*ktime_get_ns)(void) =
(void *)BPF_FUNC_ktime_get_ns;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
static int (*get_smp_processor_id)(void) =
(void *)BPF_FUNC_get_smp_processor_id;
static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
(void *)BPF_FUNC_perf_event_output;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
SEC("func_write=sys_write")
int func_write(void *ctx)
{
struct {
u64 ktime;
int cpuid;
} __attribute__((packed)) output_data;
char error_data[] = "Error: failed to output: %d\n";
output_data.cpuid = get_smp_processor_id();
output_data.ktime = ktime_get_ns();
int err = perf_event_output(ctx, &channel, get_smp_processor_id(),
&output_data, sizeof(output_data));
if (err)
trace_printk(error_data, sizeof(error_data), err);
return 0;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************ END ***************************/
# perf record -a -e bpf-output/no-inherit,name=evt/ \
-e ./test_bpf_output.c/map:channel.event=evt/ ls /
# perf script | grep ls
ls 2242 [003] 347851.557563: evt: ffffffff811fd201 sys_write ...
ls 2242 [003] 347851.557571: evt: ffffffff811fd201 sys_write ...
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-11-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 12:10:37 +03:00
bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
2012-03-15 23:09:15 +04:00
2014-10-07 19:08:51 +04:00
/*
* 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); }
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>
2016-05-30 18:49:42 +03:00
topdown-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
2014-10-07 19:08:51 +04:00
2012-03-15 23:09:15 +04:00
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 |
2012-06-15 10:31:39 +04:00
node { return str(yyscanner, PE_NAME_CACHE_TYPE); }
2012-03-15 23:09:15 +04:00
load|loads|read |
store|stores|write |
prefetch|prefetches |
speculative-read|speculative-load |
refs|Reference|ops|access |
2012-06-15 10:31:39 +04:00
misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
2012-03-15 23:09:15 +04:00
2012-05-21 11:12:52 +04:00
mem: { BEGIN(mem); return PE_PREFIX_MEM; }
2012-06-15 10:31:39 +04:00
r{num_raw_hex} { return raw(yyscanner); }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
2012-03-15 23:09:15 +04:00
2012-06-15 10:31:39 +04:00
{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
perf tools: Fix eBPF event specification parsing
Looks like I've reached the new level of stupidity, adding missing braces.
Committer testing:
Given the following eBPF C filter, that will add a record when it
returns true, i.e. when the tv_nsec variable is > 2000ns, should be
built and installed via sys_bpf(), but fails to do so before this patch:
# cat filter.c
#include <uapi/linux/bpf.h>
#define SEC(NAME) __attribute__((section(NAME), used))
SEC("func=hrtimer_nanosleep rqtp->tv_nsec")
int func(void *ctx, int err, long nsec)
{
return nsec > 1000;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
#
# perf trace -e nanosleep,filter.c usleep 1
invalid or unsupported event: 'filter.c'
Run 'perf list' for a list of valid events
Usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
-e, --event <event> event/syscall selector. use 'perf list' to list available events
#
And works again after it is applied, the nothing is inserted when the co
# perf trace -e *sleep,filter.c usleep 1
0.000 ( 0.066 ms): usleep/23994 nanosleep(rqtp: 0x7ffead94a0d0) = 0
# perf trace -e *sleep,filter.c usleep 2
0.000 ( 0.008 ms): usleep/24378 nanosleep(rqtp: 0x7fffa021ba50) ...
0.008 ( ): perf_bpf_probe:func:(ffffffffb410cb30) tv_nsec=2000)
0.000 ( 0.066 ms): usleep/24378 ... [continued]: nanosleep()) = 0
#
The intent of 9445464bb831 is kept:
# perf stat -e 'cpu/uops_executed.core,krava/' true
event syntax error: '..cuted.core,krava/'
\___ unknown term
valid terms: cmask,pc,event,edge,in_tx,any,ldlat,inv,umask,in_tx_cp,offcore_rsp,config,config1,config2,name,period
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
#
# perf stat -e 'cpu/uops_executed.core,period=1/' true
Performance counter stats for 'true':
808,332 cpu/uops_executed.core,period=1/
0.002997237 seconds time elapsed
#
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 9445464bb831 ("perf tools: Unwind properly location after REJECT")
Link: http://lkml.kernel.org/n/tip-diea0ihbwpxfw6938huv3whj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-11-09 12:02:10 +03:00
{bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
{bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
2014-10-07 19:08:51 +04:00
{name} { return pmu_str_check(yyscanner); }
perf record: Enable arbitrary event names thru name= modifier
Enable complex event names containing [.:=,] symbols to be encoded into Perf
trace using name= modifier e.g. like this:
perf record -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',\
period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
Below is how it looks like in the report output. Please note explicit escaped
quoting at cmdline string in the header so that thestring can be directly reused
for another collection in shell:
perf report --header
# ========
...
# cmdline : /root/abudanko/kernel/tip/tools/perf/perf record -v -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
# event : name = OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM, , type = 4, size = 112, config = 0x100003c, { sample_period, sample_freq } = 3500000, sample_type = IP|TID|TIME, disabled = 1, inh
...
# ========
#
#
# Total Lost Samples: 0
#
# Samples: 24K of event 'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM'
# Event count (approx.): 86492000000
#
# Overhead Command Shared Object Symbol
# ........ ....... ................ ..............................................
#
14.75% futex [kernel.vmlinux] [k] __entry_trampoline_start
...
perf stat -e cpu/name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
10000000 process context switches in 16678890291ns (1667.9ns/ctxsw)
Performance counter stats for './futex':
88,095,770,571 CPU_CLK_UNHALTED.THREAD:cmask=0x1
16.679542407 seconds time elapsed
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/c194b060-761d-0d50-3b21-bb4ed680002d@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04 09:50:56 +03:00
{name_tag} { return str(yyscanner, PE_NAME); }
2012-08-16 23:10:21 +04:00
"/" { BEGIN(config); return '/'; }
2012-03-15 23:09:15 +04:00
- { return '-'; }
2012-08-16 23:10:21 +04:00
, { BEGIN(event); return ','; }
2012-03-15 23:09:15 +04:00
: { return ':'; }
2012-08-16 23:10:21 +04:00
"{" { BEGIN(event); return '{'; }
2012-08-08 14:14:14 +04:00
"}" { return '}'; }
2012-03-15 23:09:15 +04:00
= { return '='; }
2012-07-04 02:00:39 +04:00
\n { }
2013-09-27 20:29:58 +04:00
. { }
2012-05-21 11:12:52 +04:00
2012-03-15 23:09:15 +04:00
%%
2012-09-11 02:15:03 +04:00
int parse_events_wrap(void *scanner __maybe_unused)
2012-03-15 23:09:15 +04:00
{
return 1;
}