linux_dsm_epyc7002/tools/perf/util/symbol.h

251 lines
5.8 KiB
C
Raw Normal View History

#ifndef __PERF_SYMBOL
#define __PERF_SYMBOL 1
#include <linux/types.h>
#include <stdbool.h>
#include <stdint.h>
#include "map.h"
#include "../perf.h"
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
perf symbols: Handle different endians properly during symbol load Currently we dont care about the file object's endianness. It's possible we read buildid file object from different architecture than we are currentlly running on. So we need to care about properly reading such object's data - handle different endianness properly. Adding: needs_swap DSO field dso__swap_init function to initialize DSO's needs_swap DSO__SWAP to read the data with proper swaps Together with other endianity patches, this change fixies perf report discrepancies on origin and target systems as described in test 1 below, e.g. following perf report diff: ... 0.12% ps [kernel.kallsyms] [k] clear_page - 0.12% awk bash [.] alloc_word_desc + 0.12% awk bash [.] yyparse 0.11% beah-rhts-task libpython2.6.so.1.0 [.] 0x5560e 0.10% perf libc-2.12.so [.] __ctype_toupper_loc - 0.09% rhts-test-runne bash [.] maybe_make_export_env + 0.09% rhts-test-runne bash [.] 0x385a0 0.09% ps [kernel.kallsyms] [k] page_fault ... Note, running following to test perf endianity handling: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 1) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338380624-7443-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 19:23:42 +07:00
#include <byteswap.h>
#include <libgen.h>
#include "build-id.h"
#ifdef LIBELF_SUPPORT
#include <libelf.h>
#include <gelf.h>
#endif
#include <elf.h>
#include "dso.h"
#ifdef HAVE_CPLUS_DEMANGLE
extern char *cplus_demangle(const char *, int);
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>
2012-09-11 05:15:03 +07:00
static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
{
return cplus_demangle(c, i);
}
#else
#ifdef NO_DEMANGLE
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>
2012-09-11 05:15:03 +07:00
static inline char *bfd_demangle(void __maybe_unused *v,
const char __maybe_unused *c,
int __maybe_unused i)
{
return NULL;
}
#else
#define PACKAGE 'perf'
#include <bfd.h>
#endif
#endif
/*
* libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
* for newer versions we can use mmap to reduce memory usage:
*/
#ifdef LIBELF_MMAP
# define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define PERF_ELF_C_READ_MMAP ELF_C_READ
#endif
#ifndef DMGL_PARAMS
#define DMGL_PARAMS (1 << 0) /* Include function args */
#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */
#endif
/** struct symbol - symtab entry
*
* @ignore - resolvable but tools ignore it (e.g. idle routines)
*/
struct symbol {
struct rb_node rb_node;
u64 start;
u64 end;
u16 namelen;
u8 binding;
bool ignore;
char name[0];
};
void symbol__delete(struct symbol *sym);
void symbols__delete(struct rb_root *symbols);
static inline size_t symbol__size(const struct symbol *sym)
{
return sym->end - sym->start + 1;
}
struct strlist;
struct symbol_conf {
unsigned short priv_size;
unsigned short nr_events;
bool try_vmlinux_path,
show_kernel_path,
use_modules,
sort_by_name,
show_nr_samples,
show_total_period,
use_callchain,
exclude_other,
show_cpu_utilization,
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 19:53:51 +07:00
initialized,
kptr_restrict,
annotate_asm_raw,
annotate_src,
event_group,
demangle;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
*field_sep;
const char *default_guest_vmlinux_name,
*default_guest_kallsyms,
*default_guest_modules;
const char *guestmount;
const char *dso_list_str,
*comm_list_str,
*sym_list_str,
*col_width_list_str;
struct strlist *dso_list,
*comm_list,
*sym_list,
*dso_from_list,
*dso_to_list,
*sym_from_list,
*sym_to_list;
const char *symfs;
};
extern struct symbol_conf symbol_conf;
extern int vmlinux_path__nr_entries;
extern char **vmlinux_path;
static inline void *symbol__priv(struct symbol *sym)
{
return ((void *)sym) - symbol_conf.priv_size;
}
struct ref_reloc_sym {
const char *name;
u64 addr;
u64 unrelocated_addr;
};
struct map_symbol {
struct map *map;
struct symbol *sym;
bool unfolded;
bool has_children;
};
struct addr_map_symbol {
struct map *map;
struct symbol *sym;
u64 addr;
u64 al_addr;
};
struct branch_info {
struct addr_map_symbol from;
struct addr_map_symbol to;
struct branch_flags flags;
};
struct mem_info {
struct addr_map_symbol iaddr;
struct addr_map_symbol daddr;
union perf_mem_data_src data_src;
};
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 01:29:23 +07:00
struct addr_location {
struct thread *thread;
struct map *map;
struct symbol *sym;
u64 addr;
char level;
bool filtered;
u8 cpumode;
s32 cpu;
};
struct symsrc {
char *name;
int fd;
enum dso_binary_type type;
#ifdef LIBELF_SUPPORT
Elf *elf;
GElf_Ehdr ehdr;
Elf_Scn *opdsec;
size_t opdidx;
GElf_Shdr opdshdr;
Elf_Scn *symtab;
GElf_Shdr symshdr;
Elf_Scn *dynsym;
size_t dynsym_idx;
GElf_Shdr dynshdr;
bool adjust_symbols;
#endif
};
void symsrc__destroy(struct symsrc *ss);
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
enum dso_binary_type type);
bool symsrc__has_symtab(struct symsrc *ss);
perf symbols: Use both runtime and debug images We keep both a 'runtime' elf image as well as a 'debug' elf image around and generate symbols by looking at both of these. This eliminates the need for the want_symtab/goto restart mechanism combined with iterating over and reopening the elf images a second time. Also give dso__synthsize_plt_symbols() the runtime image (which has dynsyms) instead of the symbol image (which may only have a symtab and no dynsyms). Previously if a debug image was found all runtime images were ignored. This fixes 2 issues: - Symbol resolution to failure on PowerPC systems with debug symbols installed, as the debug images lack a '.opd' section which contains function descriptors. - On all archs, plt synthesis failed when a debug image was loaded and that debug image lacks a dynsym section while a runtime image has a dynsym section. Assumptions: - If a .opd section exists, it is contained in the highest priority image with a dynsym section. - This generally implies that the debug image lacks a dynsym section (ie: it is marked as NO_BITS). Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Hansen <dave@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Hellsley <matthltc@us.ibm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1344637382-22789-17-git-send-email-cody@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-11 05:23:02 +07:00
bool symsrc__possibly_runtime(struct symsrc *ss);
int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, symbol_filter_t filter);
int dso__load_vmlinux_path(struct dso *dso, struct map *map,
symbol_filter_t filter);
int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
symbol_filter_t filter);
struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name);
int filename__read_build_id(const char *filename, void *bf, size_t size);
int sysfs__read_build_id(const char *filename, void *bf, size_t size);
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start));
int filename__read_debuglink(const char *filename, char *debuglink,
size_t size);
int symbol__init(void);
void symbol__exit(void);
void symbol__elf_init(void);
struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
size_t symbol__fprintf_symname_offs(const struct symbol *sym,
const struct addr_location *al, FILE *fp);
size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
size_t symbol__fprintf(struct symbol *sym, FILE *fp);
bool symbol_type__is_a(char symbol_type, enum map_type map_type);
bool symbol__restricted_filename(const char *filename,
const char *restricted_filename);
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, symbol_filter_t filter,
int kmodule);
int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
struct map *map, symbol_filter_t filter);
void symbols__insert(struct rb_root *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root *symbols);
void symbols__fixup_end(struct rb_root *symbols);
void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
#endif /* __PERF_SYMBOL */