linux-stable/tools/perf/util/maps.h

88 lines
2.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERF_MAPS_H
#define __PERF_MAPS_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 maps;
struct thread;
struct map *maps__find(struct maps *maps, u64 addr);
struct map *maps__first(struct maps *maps);
struct map *map__next(struct map *map);
#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))
struct maps {
struct rb_root entries;
struct rw_semaphore lock;
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>
2019-11-13 19:33:33 +00:00
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 14:38:13 +00:00
struct map **maps_by_name;
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 14:38:13 +00:00
unsigned int nr_maps;
unsigned int nr_maps_allocated;
perf unwind: Fix libunwind when tid != pid Commit e5adfc3e7e77 ("perf map: Synthesize maps only for thread group leader") changed the recording side so that we no longer get mmap events for threads other than the thread group leader (when synthesising these events for threads which exist before perf is started). When a file recorded after this change is loaded, the lack of mmap records mean that unwinding is not set up for any other threads. This can be seen in a simple record/report scenario: perf record --call-graph=dwarf -t $TID perf report If $TID is a process ID then the report will show call graphs, but if $TID is a secondary thread the output is as if --call-graph=none was specified. Following the rationale in that commit, move the libunwind fields into struct map_groups and update the libunwind functions to take this instead of the struct thread. This is only required for unwind__finish_access which must now be called from map_groups__delete and the others are changed for symmetry. Note that unwind__get_entries keeps the thread argument since it is required for symbol lookup and the libdw unwind provider uses the thread ID. Signed-off-by: John Keeping <john@metanate.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: e5adfc3e7e77 ("perf map: Synthesize maps only for thread group leader") Link: http://lkml.kernel.org/r/20190815100146.28842-2-john@metanate.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-15 10:01:45 +00:00
#ifdef HAVE_LIBUNWIND_SUPPORT
void *addr_space;
struct unwind_libunwind_ops *unwind_libunwind_ops;
#endif
};
#define KMAP_NAME_LEN 256
struct kmap {
struct ref_reloc_sym *ref_reloc_sym;
struct maps *kmaps;
char name[KMAP_NAME_LEN];
};
struct maps *maps__new(struct machine *machine);
void maps__delete(struct maps *maps);
bool maps__empty(struct maps *maps);
static inline struct maps *maps__get(struct maps *maps)
{
if (maps)
refcount_inc(&maps->refcnt);
return maps;
}
void maps__put(struct maps *maps);
void maps__init(struct maps *maps, struct machine *machine);
void maps__exit(struct maps *maps);
int maps__clone(struct thread *thread, struct maps *parent);
size_t maps__fprintf(struct maps *maps, FILE *fp);
void maps__insert(struct maps *maps, struct map *map);
void maps__remove(struct maps *maps, struct map *map);
struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp);
struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp);
struct addr_map_symbol;
int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams);
int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp);
struct map *maps__find_by_name(struct maps *maps, const char *name);
int maps__merge_in(struct maps *kmaps, struct map *new_map);
void __maps__sort_by_name(struct maps *maps);
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 14:38:13 +00:00
#endif // __PERF_MAPS_H