mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 06:00:52 +07:00
e7b60c5a0c
No need to load symbols in a DSO when injecting build-id. I guess the reason was to check the DSO is a special file like anon files. Use some helper functions in map.c to check them before reading build-id. Also pass sample event's cpumode to a new build-id event. It brought a speedup in the benchmark of 25 -> 21 msec on my laptop. Also the memory usage (Max RSS) went down by ~200 KB. # Running 'internals/inject-build-id' benchmark: Average build-id injection took: 21.389 msec (+- 0.138 msec) Average time per event: 2.097 usec (+- 0.014 usec) Average memory usage: 8225 KB (+- 0 KB) Committer notes: Before: $ perf stat -r5 perf bench internals inject-build-id > /dev/null Performance counter stats for 'perf bench internals inject-build-id' (5 runs): 4,020.56 msec task-clock:u # 1.271 CPUs utilized ( +- 0.74% ) 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/sec 123,354 page-faults:u # 0.031 M/sec ( +- 0.81% ) 7,119,951,568 cycles:u # 1.771 GHz ( +- 1.74% ) (83.27%) 230,086,969 stalled-cycles-frontend:u # 3.23% frontend cycles idle ( +- 1.97% ) (83.41%) 1,168,298,765 stalled-cycles-backend:u # 16.41% backend cycles idle ( +- 1.13% ) (83.44%) 11,173,083,669 instructions:u # 1.57 insn per cycle # 0.10 stalled cycles per insn ( +- 1.58% ) (83.31%) 2,413,908,936 branches:u # 600.392 M/sec ( +- 1.69% ) (83.26%) 46,576,289 branch-misses:u # 1.93% of all branches ( +- 2.20% ) (83.31%) 3.1638 +- 0.0309 seconds time elapsed ( +- 0.98% ) $ After: $ perf stat -r5 perf bench internals inject-build-id > /dev/null Performance counter stats for 'perf bench internals inject-build-id' (5 runs): 2,379.94 msec task-clock:u # 1.473 CPUs utilized ( +- 0.18% ) 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/sec 62,584 page-faults:u # 0.026 M/sec ( +- 0.07% ) 2,372,389,668 cycles:u # 0.997 GHz ( +- 0.29% ) (83.14%) 106,937,862 stalled-cycles-frontend:u # 4.51% frontend cycles idle ( +- 4.89% ) (83.20%) 581,697,915 stalled-cycles-backend:u # 24.52% backend cycles idle ( +- 0.71% ) (83.47%) 3,659,692,199 instructions:u # 1.54 insn per cycle # 0.16 stalled cycles per insn ( +- 0.10% ) (83.63%) 791,372,961 branches:u # 332.518 M/sec ( +- 0.27% ) (83.39%) 10,648,083 branch-misses:u # 1.35% of all branches ( +- 0.22% ) (83.16%) 1.61570 +- 0.00172 seconds time elapsed ( +- 0.11% ) $ Signed-off-by: Namhyung Kim <namhyung@kernel.org> Original-patch-by: Stephane Eranian <eranian@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20201012070214.2074921-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
189 lines
5.0 KiB
C
189 lines
5.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __PERF_MAP_H
|
|
#define __PERF_MAP_H
|
|
|
|
#include <linux/refcount.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/list.h>
|
|
#include <linux/rbtree.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <stdbool.h>
|
|
#include <linux/types.h>
|
|
|
|
struct dso;
|
|
struct maps;
|
|
struct machine;
|
|
|
|
struct map {
|
|
union {
|
|
struct rb_node rb_node;
|
|
struct list_head node;
|
|
};
|
|
u64 start;
|
|
u64 end;
|
|
bool erange_warned:1;
|
|
bool priv:1;
|
|
u32 prot;
|
|
u64 pgoff;
|
|
u64 reloc;
|
|
|
|
/* ip -> dso rip */
|
|
u64 (*map_ip)(struct map *, u64);
|
|
/* dso rip -> ip */
|
|
u64 (*unmap_ip)(struct map *, u64);
|
|
|
|
struct dso *dso;
|
|
refcount_t refcnt;
|
|
u32 flags;
|
|
};
|
|
|
|
struct kmap;
|
|
|
|
struct kmap *__map__kmap(struct map *map);
|
|
struct kmap *map__kmap(struct map *map);
|
|
struct maps *map__kmaps(struct map *map);
|
|
|
|
static inline u64 map__map_ip(struct map *map, u64 ip)
|
|
{
|
|
return ip - map->start + map->pgoff;
|
|
}
|
|
|
|
static inline u64 map__unmap_ip(struct map *map, u64 ip)
|
|
{
|
|
return ip + map->start - map->pgoff;
|
|
}
|
|
|
|
static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
|
|
{
|
|
return ip;
|
|
}
|
|
|
|
static inline size_t map__size(const struct map *map)
|
|
{
|
|
return map->end - map->start;
|
|
}
|
|
|
|
/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
|
|
u64 map__rip_2objdump(struct map *map, u64 rip);
|
|
|
|
/* objdump address -> memory address */
|
|
u64 map__objdump_2mem(struct map *map, u64 ip);
|
|
|
|
struct symbol;
|
|
struct thread;
|
|
|
|
/* map__for_each_symbol - iterate over the symbols in the given map
|
|
*
|
|
* @map: the 'struct map *' in which symbols itereated
|
|
* @pos: the 'struct symbol *' to use as a loop cursor
|
|
* @n: the 'struct rb_node *' to use as a temporary storage
|
|
* Note: caller must ensure map->dso is not NULL (map is loaded).
|
|
*/
|
|
#define map__for_each_symbol(map, pos, n) \
|
|
dso__for_each_symbol(map->dso, pos, n)
|
|
|
|
/* map__for_each_symbol_with_name - iterate over the symbols in the given map
|
|
* that have the given name
|
|
*
|
|
* @map: the 'struct map *' in which symbols itereated
|
|
* @sym_name: the symbol name
|
|
* @pos: the 'struct symbol *' to use as a loop cursor
|
|
*/
|
|
#define __map__for_each_symbol_by_name(map, sym_name, pos) \
|
|
for (pos = map__find_symbol_by_name(map, sym_name); \
|
|
pos && \
|
|
!symbol__match_symbol_name(pos->name, sym_name, \
|
|
SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \
|
|
pos = symbol__next_by_name(pos))
|
|
|
|
#define map__for_each_symbol_by_name(map, sym_name, pos) \
|
|
__map__for_each_symbol_by_name(map, sym_name, (pos))
|
|
|
|
void map__init(struct map *map,
|
|
u64 start, u64 end, u64 pgoff, struct dso *dso);
|
|
|
|
struct dso_id;
|
|
|
|
struct map *map__new(struct machine *machine, u64 start, u64 len,
|
|
u64 pgoff, struct dso_id *id, u32 prot, u32 flags,
|
|
char *filename, struct thread *thread);
|
|
struct map *map__new2(u64 start, struct dso *dso);
|
|
void map__delete(struct map *map);
|
|
struct map *map__clone(struct map *map);
|
|
|
|
static inline struct map *map__get(struct map *map)
|
|
{
|
|
if (map)
|
|
refcount_inc(&map->refcnt);
|
|
return map;
|
|
}
|
|
|
|
void map__put(struct map *map);
|
|
|
|
static inline void __map__zput(struct map **map)
|
|
{
|
|
map__put(*map);
|
|
*map = NULL;
|
|
}
|
|
|
|
#define map__zput(map) __map__zput(&map)
|
|
|
|
size_t map__fprintf(struct map *map, FILE *fp);
|
|
size_t map__fprintf_dsoname(struct map *map, FILE *fp);
|
|
char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
|
|
int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
|
|
FILE *fp);
|
|
|
|
int map__load(struct map *map);
|
|
struct symbol *map__find_symbol(struct map *map, u64 addr);
|
|
struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
|
|
void map__fixup_start(struct map *map);
|
|
void map__fixup_end(struct map *map);
|
|
|
|
int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
|
|
u64 addr);
|
|
|
|
bool __map__is_kernel(const struct map *map);
|
|
bool __map__is_extra_kernel_map(const struct map *map);
|
|
bool __map__is_bpf_prog(const struct map *map);
|
|
bool __map__is_bpf_image(const struct map *map);
|
|
bool __map__is_ool(const struct map *map);
|
|
|
|
static inline bool __map__is_kmodule(const struct map *map)
|
|
{
|
|
return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
|
|
!__map__is_bpf_prog(map) && !__map__is_ool(map) &&
|
|
!__map__is_bpf_image(map);
|
|
}
|
|
|
|
bool map__has_symbols(const struct map *map);
|
|
|
|
#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
|
|
|
|
static inline bool is_entry_trampoline(const char *name)
|
|
{
|
|
return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
|
|
}
|
|
|
|
static inline bool is_bpf_image(const char *name)
|
|
{
|
|
return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
|
|
strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
|
|
}
|
|
|
|
static inline int is_anon_memory(const char *filename)
|
|
{
|
|
return !strcmp(filename, "//anon") ||
|
|
!strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
|
|
!strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
|
|
}
|
|
|
|
static inline int is_no_dso_memory(const char *filename)
|
|
{
|
|
return !strncmp(filename, "[stack", 6) ||
|
|
!strncmp(filename, "/SYSV", 5) ||
|
|
!strcmp(filename, "[heap]");
|
|
}
|
|
#endif /* __PERF_MAP_H */
|