2019-01-27 20:44:29 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#ifndef __PERF_MAP_GROUPS_H
|
|
|
|
#define __PERF_MAP_GROUPS_H
|
|
|
|
|
|
|
|
#include <linux/refcount.h>
|
|
|
|
#include <linux/rbtree.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdbool.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include "rwsem.h"
|
|
|
|
|
|
|
|
struct ref_reloc_sym;
|
|
|
|
struct machine;
|
|
|
|
struct map;
|
|
|
|
struct thread;
|
|
|
|
|
|
|
|
struct maps {
|
|
|
|
struct rb_root entries;
|
|
|
|
struct rw_semaphore lock;
|
|
|
|
};
|
|
|
|
|
|
|
|
void maps__insert(struct maps *maps, struct map *map);
|
|
|
|
void maps__remove(struct maps *maps, struct map *map);
|
perf map_groups: Auto sort maps by name, if needed
There are still lots of lookups by name, even if just when loading
vmlinux, till that code is studied to figure out if its possible to do
away with those map lookup by names, provide a way to sort it using
libc's qsort/bsearch.
Doing it at the first lookup defers the sorting a bit, and as the code
stands now, is never done for user maps, just for the kernel ones.
# perf probe -l
# perf probe -x ~/bin/perf -L __map_groups__find_by_name
<__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
struct map **mapp;
4 if (mg->maps_by_name == NULL &&
5 map__groups__sort_by_name_from_rbtree(mg))
6 return NULL;
8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
9 if (mapp)
10 return *mapp;
11 return NULL;
12 }
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
{
# perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string'
Added new event:
probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:found -aR sleep 1
#
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
/*
* If we have mg->maps_by_name, then the name isn't in the rbtree,
* as mg->maps_by_name mirrors the rbtree when lookups by name are
* made.
*/
16 map = __map_groups__find_by_name(mg, name);
17 if (map || mg->maps_by_name != NULL)
18 goto out_unlock;
/* Fallback to traversing the rbtree... */
21 maps__for_each_entry(maps, map)
22 if (strcmp(map->dso->short_name, name) == 0) {
23 mg->last_search_by_name = map;
24 goto out_unlock;
}
27 map = NULL;
out_unlock:
30 up_read(&maps->lock);
31 return map;
32 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
# perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string'
Added new events:
probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fallback_1 -aR sleep 1
#
# perf probe -l
probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string)
#
# perf stat -e probe_perf:*
Now run 'perf top' in another term and then, after a while, stop 'perf stat':
Furthermore, if we ask for interval printing, we can see that that is done just
at the start of the workload:
# perf stat -I1000 -e probe_perf:*
# time counts unit events
1.000319513 0 probe_perf:found
1.000319513 0 probe_perf:fallback_1
1.000319513 0 probe_perf:fallback
2.001868092 23,251 probe_perf:found
2.001868092 0 probe_perf:fallback_1
2.001868092 0 probe_perf:fallback
3.002901597 0 probe_perf:found
3.002901597 0 probe_perf:fallback_1
3.002901597 0 probe_perf:fallback
4.003358591 0 probe_perf:found
4.003358591 0 probe_perf:fallback_1
4.003358591 0 probe_perf:fallback
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
|
|
|
void __maps__remove(struct maps *maps, struct map *map);
|
2019-01-27 20:44:29 +08:00
|
|
|
struct map *maps__find(struct maps *maps, u64 addr);
|
|
|
|
struct map *maps__first(struct maps *maps);
|
|
|
|
struct map *map__next(struct map *map);
|
2019-10-28 22:31:38 +08:00
|
|
|
|
|
|
|
#define maps__for_each_entry(maps, map) \
|
|
|
|
for (map = maps__first(maps); map; map = map__next(map))
|
|
|
|
|
|
|
|
#define maps__for_each_entry_safe(maps, map, next) \
|
|
|
|
for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map))
|
|
|
|
|
2019-01-27 20:44:29 +08:00
|
|
|
struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp);
|
|
|
|
|
|
|
|
struct map_groups {
|
|
|
|
struct maps maps;
|
|
|
|
struct machine *machine;
|
perf map_groups: Add a front end cache for map lookups by name
Lets see if it helps:
First look at the probeable lines for the function that does lookups by
name in a map_groups struct:
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
12 maps__for_each_entry(maps, map)
13 if (strcmp(map->dso->short_name, name) == 0) {
14 mg->last_search_by_name = map;
15 goto out_unlock;
}
18 map = NULL;
out_unlock:
21 up_read(&maps->lock);
22 return map;
23 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
#
Now add a probe to the place where we reuse the last search:
# perf probe -x ~/bin/perf map_groups__find_by_name:8
Added new event:
probe_perf:map_groups__find_by_name (on map_groups__find_by_name:8 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:map_groups__find_by_name -aR sleep 1
#
Now lets do a system wide 'perf stat' counting those events:
# perf stat -e probe_perf:*
Leave it running and lets do a 'perf top', then, after a while, stop the
'perf stat':
# perf stat -e probe_perf:*
^C
Performance counter stats for 'system wide':
3,603 probe_perf:map_groups__find_by_name
44.565253139 seconds time elapsed
#
yeah, good to have.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-tcz37g3nxv3tvxw3q90vga3p@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-14 03:33:33 +08:00
|
|
|
struct map *last_search_by_name;
|
perf map_groups: Auto sort maps by name, if needed
There are still lots of lookups by name, even if just when loading
vmlinux, till that code is studied to figure out if its possible to do
away with those map lookup by names, provide a way to sort it using
libc's qsort/bsearch.
Doing it at the first lookup defers the sorting a bit, and as the code
stands now, is never done for user maps, just for the kernel ones.
# perf probe -l
# perf probe -x ~/bin/perf -L __map_groups__find_by_name
<__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
struct map **mapp;
4 if (mg->maps_by_name == NULL &&
5 map__groups__sort_by_name_from_rbtree(mg))
6 return NULL;
8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
9 if (mapp)
10 return *mapp;
11 return NULL;
12 }
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
{
# perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string'
Added new event:
probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:found -aR sleep 1
#
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
/*
* If we have mg->maps_by_name, then the name isn't in the rbtree,
* as mg->maps_by_name mirrors the rbtree when lookups by name are
* made.
*/
16 map = __map_groups__find_by_name(mg, name);
17 if (map || mg->maps_by_name != NULL)
18 goto out_unlock;
/* Fallback to traversing the rbtree... */
21 maps__for_each_entry(maps, map)
22 if (strcmp(map->dso->short_name, name) == 0) {
23 mg->last_search_by_name = map;
24 goto out_unlock;
}
27 map = NULL;
out_unlock:
30 up_read(&maps->lock);
31 return map;
32 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
# perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string'
Added new events:
probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fallback_1 -aR sleep 1
#
# perf probe -l
probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string)
#
# perf stat -e probe_perf:*
Now run 'perf top' in another term and then, after a while, stop 'perf stat':
Furthermore, if we ask for interval printing, we can see that that is done just
at the start of the workload:
# perf stat -I1000 -e probe_perf:*
# time counts unit events
1.000319513 0 probe_perf:found
1.000319513 0 probe_perf:fallback_1
1.000319513 0 probe_perf:fallback
2.001868092 23,251 probe_perf:found
2.001868092 0 probe_perf:fallback_1
2.001868092 0 probe_perf:fallback
3.002901597 0 probe_perf:found
3.002901597 0 probe_perf:fallback_1
3.002901597 0 probe_perf:fallback
4.003358591 0 probe_perf:found
4.003358591 0 probe_perf:fallback_1
4.003358591 0 probe_perf:fallback
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
|
|
|
struct map **maps_by_name;
|
2019-01-27 20:44:29 +08:00
|
|
|
refcount_t refcnt;
|
perf map_groups: Auto sort maps by name, if needed
There are still lots of lookups by name, even if just when loading
vmlinux, till that code is studied to figure out if its possible to do
away with those map lookup by names, provide a way to sort it using
libc's qsort/bsearch.
Doing it at the first lookup defers the sorting a bit, and as the code
stands now, is never done for user maps, just for the kernel ones.
# perf probe -l
# perf probe -x ~/bin/perf -L __map_groups__find_by_name
<__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
struct map **mapp;
4 if (mg->maps_by_name == NULL &&
5 map__groups__sort_by_name_from_rbtree(mg))
6 return NULL;
8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
9 if (mapp)
10 return *mapp;
11 return NULL;
12 }
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
{
# perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string'
Added new event:
probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:found -aR sleep 1
#
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
/*
* If we have mg->maps_by_name, then the name isn't in the rbtree,
* as mg->maps_by_name mirrors the rbtree when lookups by name are
* made.
*/
16 map = __map_groups__find_by_name(mg, name);
17 if (map || mg->maps_by_name != NULL)
18 goto out_unlock;
/* Fallback to traversing the rbtree... */
21 maps__for_each_entry(maps, map)
22 if (strcmp(map->dso->short_name, name) == 0) {
23 mg->last_search_by_name = map;
24 goto out_unlock;
}
27 map = NULL;
out_unlock:
30 up_read(&maps->lock);
31 return map;
32 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
# perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string'
Added new events:
probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fallback_1 -aR sleep 1
#
# perf probe -l
probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string)
#
# perf stat -e probe_perf:*
Now run 'perf top' in another term and then, after a while, stop 'perf stat':
Furthermore, if we ask for interval printing, we can see that that is done just
at the start of the workload:
# perf stat -I1000 -e probe_perf:*
# time counts unit events
1.000319513 0 probe_perf:found
1.000319513 0 probe_perf:fallback_1
1.000319513 0 probe_perf:fallback
2.001868092 23,251 probe_perf:found
2.001868092 0 probe_perf:fallback_1
2.001868092 0 probe_perf:fallback
3.002901597 0 probe_perf:found
3.002901597 0 probe_perf:fallback_1
3.002901597 0 probe_perf:fallback
4.003358591 0 probe_perf:found
4.003358591 0 probe_perf:fallback_1
4.003358591 0 probe_perf:fallback
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
|
|
|
unsigned int nr_maps;
|
|
|
|
unsigned int nr_maps_allocated;
|
2019-08-15 18:01:45 +08:00
|
|
|
#ifdef HAVE_LIBUNWIND_SUPPORT
|
|
|
|
void *addr_space;
|
|
|
|
struct unwind_libunwind_ops *unwind_libunwind_ops;
|
|
|
|
#endif
|
2019-01-27 20:44:29 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#define KMAP_NAME_LEN 256
|
|
|
|
|
|
|
|
struct kmap {
|
|
|
|
struct ref_reloc_sym *ref_reloc_sym;
|
|
|
|
struct map_groups *kmaps;
|
|
|
|
char name[KMAP_NAME_LEN];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct map_groups *map_groups__new(struct machine *machine);
|
|
|
|
void map_groups__delete(struct map_groups *mg);
|
|
|
|
bool map_groups__empty(struct map_groups *mg);
|
|
|
|
|
|
|
|
static inline struct map_groups *map_groups__get(struct map_groups *mg)
|
|
|
|
{
|
|
|
|
if (mg)
|
|
|
|
refcount_inc(&mg->refcnt);
|
|
|
|
return mg;
|
|
|
|
}
|
|
|
|
|
|
|
|
void map_groups__put(struct map_groups *mg);
|
|
|
|
void map_groups__init(struct map_groups *mg, struct machine *machine);
|
|
|
|
void map_groups__exit(struct map_groups *mg);
|
|
|
|
int map_groups__clone(struct thread *thread, struct map_groups *parent);
|
|
|
|
size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
|
|
|
|
|
|
|
|
void map_groups__insert(struct map_groups *mg, struct map *map);
|
|
|
|
|
perf map_groups: Add a front end cache for map lookups by name
Lets see if it helps:
First look at the probeable lines for the function that does lookups by
name in a map_groups struct:
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
12 maps__for_each_entry(maps, map)
13 if (strcmp(map->dso->short_name, name) == 0) {
14 mg->last_search_by_name = map;
15 goto out_unlock;
}
18 map = NULL;
out_unlock:
21 up_read(&maps->lock);
22 return map;
23 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
#
Now add a probe to the place where we reuse the last search:
# perf probe -x ~/bin/perf map_groups__find_by_name:8
Added new event:
probe_perf:map_groups__find_by_name (on map_groups__find_by_name:8 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:map_groups__find_by_name -aR sleep 1
#
Now lets do a system wide 'perf stat' counting those events:
# perf stat -e probe_perf:*
Leave it running and lets do a 'perf top', then, after a while, stop the
'perf stat':
# perf stat -e probe_perf:*
^C
Performance counter stats for 'system wide':
3,603 probe_perf:map_groups__find_by_name
44.565253139 seconds time elapsed
#
yeah, good to have.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-tcz37g3nxv3tvxw3q90vga3p@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-14 03:33:33 +08:00
|
|
|
void map_groups__remove(struct map_groups *mg, struct map *map);
|
2019-01-27 20:44:29 +08:00
|
|
|
|
|
|
|
static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
|
|
|
|
{
|
|
|
|
return maps__find(&mg->maps, addr);
|
|
|
|
}
|
|
|
|
|
2019-10-28 22:55:28 +08:00
|
|
|
#define map_groups__for_each_entry(mg, map) \
|
|
|
|
for (map = maps__first(&mg->maps); map; map = map__next(map))
|
2019-01-27 20:44:29 +08:00
|
|
|
|
2019-10-28 22:55:28 +08:00
|
|
|
#define map_groups__for_each_entry_safe(mg, map, next) \
|
|
|
|
for (map = maps__first(&mg->maps), next = map__next(map); map; map = next, next = map__next(map))
|
2019-01-27 20:44:29 +08:00
|
|
|
|
|
|
|
struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp);
|
|
|
|
struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp);
|
|
|
|
|
|
|
|
struct addr_map_symbol;
|
|
|
|
|
2019-11-04 21:14:05 +08:00
|
|
|
int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams);
|
2019-01-27 20:44:29 +08:00
|
|
|
|
|
|
|
int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp);
|
|
|
|
|
|
|
|
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
|
|
|
|
|
2019-05-08 21:20:07 +08:00
|
|
|
int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map);
|
|
|
|
|
perf map_groups: Auto sort maps by name, if needed
There are still lots of lookups by name, even if just when loading
vmlinux, till that code is studied to figure out if its possible to do
away with those map lookup by names, provide a way to sort it using
libc's qsort/bsearch.
Doing it at the first lookup defers the sorting a bit, and as the code
stands now, is never done for user maps, just for the kernel ones.
# perf probe -l
# perf probe -x ~/bin/perf -L __map_groups__find_by_name
<__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
struct map **mapp;
4 if (mg->maps_by_name == NULL &&
5 map__groups__sort_by_name_from_rbtree(mg))
6 return NULL;
8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
9 if (mapp)
10 return *mapp;
11 return NULL;
12 }
struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
{
# perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string'
Added new event:
probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:found -aR sleep 1
#
# perf probe -x ~/bin/perf -L map_groups__find_by_name
<map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
1 {
2 struct maps *maps = &mg->maps;
struct map *map;
5 down_read(&maps->lock);
7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
8 map = mg->last_search_by_name;
9 goto out_unlock;
}
/*
* If we have mg->maps_by_name, then the name isn't in the rbtree,
* as mg->maps_by_name mirrors the rbtree when lookups by name are
* made.
*/
16 map = __map_groups__find_by_name(mg, name);
17 if (map || mg->maps_by_name != NULL)
18 goto out_unlock;
/* Fallback to traversing the rbtree... */
21 maps__for_each_entry(maps, map)
22 if (strcmp(map->dso->short_name, name) == 0) {
23 mg->last_search_by_name = map;
24 goto out_unlock;
}
27 map = NULL;
out_unlock:
30 up_read(&maps->lock);
31 return map;
32 }
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
# perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string'
Added new events:
probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fallback_1 -aR sleep 1
#
# perf probe -l
probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string)
#
# perf stat -e probe_perf:*
Now run 'perf top' in another term and then, after a while, stop 'perf stat':
Furthermore, if we ask for interval printing, we can see that that is done just
at the start of the workload:
# perf stat -I1000 -e probe_perf:*
# time counts unit events
1.000319513 0 probe_perf:found
1.000319513 0 probe_perf:fallback_1
1.000319513 0 probe_perf:fallback
2.001868092 23,251 probe_perf:found
2.001868092 0 probe_perf:fallback_1
2.001868092 0 probe_perf:fallback
3.002901597 0 probe_perf:found
3.002901597 0 probe_perf:fallback_1
3.002901597 0 probe_perf:fallback
4.003358591 0 probe_perf:found
4.003358591 0 probe_perf:fallback_1
4.003358591 0 probe_perf:fallback
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
|
|
|
void __map_groups__sort_by_name(struct map_groups *mg);
|
|
|
|
|
2019-01-27 20:44:29 +08:00
|
|
|
#endif // __PERF_MAP_GROUPS_H
|