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

222 lines
6 KiB
C
Raw Normal View History

#ifndef __PERF_MAP_H
#define __PERF_MAP_H
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
#include <stdbool.h>
#include <linux/types.h>
enum map_type {
MAP__FUNCTION = 0,
MAP__VARIABLE,
};
#define MAP__NR_TYPES (MAP__VARIABLE + 1)
extern const char *map_type__name[MAP__NR_TYPES];
struct dso;
struct ip_callchain;
struct ref_reloc_sym;
struct map_groups;
struct machine;
struct perf_evsel;
struct map {
union {
struct rb_node rb_node;
struct list_head node;
};
u64 start;
u64 end;
u8 /* enum map_type */ type;
bool referenced;
bool erange_warned;
u32 priv;
u32 prot;
u32 flags;
u64 pgoff;
u64 reloc;
u32 maj, min; /* only valid for MMAP2 record */
u64 ino; /* only valid for MMAP2 record */
u64 ino_generation;/* only valid for MMAP2 record */
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-03 18:52:07 +00:00
/* ip -> dso rip */
u64 (*map_ip)(struct map *, u64);
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-03 18:52:07 +00:00
/* dso rip -> ip */
u64 (*unmap_ip)(struct map *, u64);
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-03 18:52:07 +00:00
struct dso *dso;
struct map_groups *groups;
};
struct kmap {
struct ref_reloc_sym *ref_reloc_sym;
struct map_groups *kmaps;
};
struct map_groups {
struct rb_root maps[MAP__NR_TYPES];
struct list_head removed_maps[MAP__NR_TYPES];
struct machine *machine;
int refcnt;
};
struct map_groups *map_groups__new(void);
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)
{
++mg->refcnt;
return mg;
}
void map_groups__put(struct map_groups *mg);
static inline struct kmap *map__kmap(struct map *map)
{
return (struct kmap *)(map + 1);
}
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;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
{
return ip;
}
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-03 18:52:07 +00:00
perf top: Fix annotate for userspace First, for programs and prelinked libraries, annotate code was fooled by objdump output IPs (src->eip in the code) being wrongly converted to absolute IPs. In such case there were no conversion needed, but in src->eip = strtoull(src->line, NULL, 16); src->eip = map->unmap_ip(map, src->eip); // = eip + map->start - map->pgoff we were reading absolute address from objdump (e.g. 8048604) and then almost doubling it, because eip & map->start are approximately close for small programs. Needless to say, that later, in record_precise_ip() there was no matching with real runtime IPs. And second, like with `perf annotate` the problem with non-prelinked *.so was that we were doing rip -> objdump address conversion wrong. Also, because unlike `perf annotate`, `perf top` code does annotation based on absolute IPs for performance reasons(*), new helper for mapping objdump addresse to IP is introduced. (*) we get samples info in absolute IPs, and since we do lots of hit-testing on absolute IPs at runtime in record_precise_ip(), it's better to convert objdump addresses to IPs once and do no conversion at runtime. I also had to fix how objdump output is parsed (with hardcoded 8/16 characters format, which was inappropriate for ET_DYN dsos with small addresses like '4ac') Also note, that not all objdump output lines has associtated IPs, e.g. look at source lines here: 000004ac <my_strlen>: extern "C" int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { int len = 0; 4b2: c7 45 fc 00 00 00 00 movl $0x0,-0x4(%ebp) 4b9: eb 08 jmp 4c3 <my_strlen+0x17> while (*s) { ++len; 4bb: 83 45 fc 01 addl $0x1,-0x4(%ebp) ++s; 4bf: 83 45 08 01 addl $0x1,0x8(%ebp) So we mark them with eip=0, and ignore such lines in annotate lookup code. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> [ Note: one hunk of this patch was applied by Mike in 57d8188 ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265550376-12665-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-07 13:46:15 +00:00
/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-03 18:52:07 +00:00
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;
perf probe: Allow to add events on the local functions Allow to add events on the local functions without debuginfo. (With the debuginfo, we can add events even on inlined functions) Currently, probing on local functions requires debuginfo to locate actual address. It is also possible without debuginfo since we have symbol maps. Without this change; ---- # ./perf probe -a t_show Added new event: probe:t_show (on t_show) You can now use it in all perf tools, such as: perf record -e probe:t_show -aR sleep 1 # ./perf probe -x perf -a identity__map_ip no symbols found in /kbuild/ksrc/linux-3/tools/perf/perf, maybe install a debug package? Failed to load map. Error: Failed to add events. (-22) ---- As the above results, perf probe just put one event on the first found symbol for kprobe event. Moreover, for uprobe event, perf probe failed to find local functions. With this change; ---- # ./perf probe -a t_show Added new events: probe:t_show (on t_show) probe:t_show_1 (on t_show) probe:t_show_2 (on t_show) probe:t_show_3 (on t_show) You can now use it in all perf tools, such as: perf record -e probe:t_show_3 -aR sleep 1 # ./perf probe -x perf -a identity__map_ip Added new events: probe_perf:identity__map_ip (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_1 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_2 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_3 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:identity__map_ip_3 -aR sleep 1 ---- Now we succeed to put events on every given local functions for both kprobes and uprobes. :) Note that this also introduces some symbol rbtree iteration macros; symbols__for_each, dso__for_each_symbol, and map__for_each_symbol. These are for walking through the symbol list in a map. Changes from v2: - Fix add_exec_to_probe_trace_events() not to convert address to tp->symbol any more. - Fix to set kernel probes based on ref_reloc_sym. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: David Ahern <dsahern@gmail.com> Cc: "David A. Long" <dave.long@linaro.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20140206053225.29635.15026.stgit@kbuild-fedora.yrl.intra.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-02-06 05:32:25 +00:00
/* 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->type)
typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
u64 ino_gen, u32 prot, u32 flags,
char *filename, enum map_type type, struct thread *thread);
struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *map);
struct map *map__clone(struct map *map);
int map__overlap(struct map *l, struct map *r);
size_t map__fprintf(struct map *map, FILE *fp);
size_t map__fprintf_dsoname(struct map *map, FILE *fp);
perf script: Add an option to print the source line number Add field 'srcline' that displays the source file name and line number associated with the sample ip. The information displayed is the same as from addr2line. $ perf script -f comm,tid,pid,time,ip,sym,dso,symoff,srcline grep 10701/10701 2497321.421013: ffffffff81043ffa native_write_msr_safe+0xa ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/msr.h:95 grep 10701/10701 2497321.421984: ffffffff8165b6b3 _raw_spin_lock+0x13 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/spinlock.h:54 grep 10701/10701 2497321.421990: ffffffff810b64b3 tick_sched_timer+0x53 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/time/tick-sched.c:840 grep 10701/10701 2497321.421992: ffffffff8106f63f run_timer_softirq+0x2f ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/timer.c:1372 Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1386315778-11633-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-12-06 07:42:57 +00:00
int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
FILE *fp);
int map__load(struct map *map, symbol_filter_t filter);
struct symbol *map__find_symbol(struct map *map,
u64 addr, symbol_filter_t filter);
struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
symbol_filter_t filter);
void map__fixup_start(struct map *map);
void map__fixup_end(struct map *map);
void map__reloc_vmlinux(struct map *map);
size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
FILE *fp);
void maps__insert(struct rb_root *maps, struct map *map);
void maps__remove(struct rb_root *maps, struct map *map);
struct map *maps__find(struct rb_root *maps, u64 addr);
struct map *maps__first(struct rb_root *maps);
struct map *maps__next(struct map *map);
void map_groups__init(struct map_groups *mg);
void map_groups__exit(struct map_groups *mg);
int map_groups__clone(struct map_groups *mg,
struct map_groups *parent, enum map_type type);
size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
u64 addr);
static inline void map_groups__insert(struct map_groups *mg, struct map *map)
{
maps__insert(&mg->maps[map->type], map);
map->groups = mg;
}
static inline void map_groups__remove(struct map_groups *mg, struct map *map)
{
maps__remove(&mg->maps[map->type], map);
}
static inline struct map *map_groups__find(struct map_groups *mg,
enum map_type type, u64 addr)
{
return maps__find(&mg->maps[type], addr);
}
static inline struct map *map_groups__first(struct map_groups *mg,
enum map_type type)
{
return maps__first(&mg->maps[type]);
}
static inline struct map *map_groups__next(struct map *map)
{
return maps__next(map);
}
struct symbol *map_groups__find_symbol(struct map_groups *mg,
enum map_type type, u64 addr,
struct map **mapp,
symbol_filter_t filter);
struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
enum map_type type,
const char *name,
struct map **mapp,
symbol_filter_t filter);
struct addr_map_symbol;
int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
static inline
struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
const char *name, struct map **mapp,
symbol_filter_t filter)
{
return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
}
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,
enum map_type type, const char *name);
void map_groups__flush(struct map_groups *mg);
#endif /* __PERF_MAP_H */