2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2025-01-23 22:25:40 +08:00
linux-next/tools/perf/util/srcline.c

689 lines
13 KiB
C
Raw Normal View History

#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <linux/kernel.h>
#include "util/dso.h"
#include "util/util.h"
#include "util/debug.h"
#include "util/callchain.h"
#include "srcline.h"
#include "symbol.h"
bool srcline_full_filename;
static const char *dso__name(struct dso *dso)
{
const char *dso_name;
if (dso->symsrc_filename)
dso_name = dso->symsrc_filename;
else
dso_name = dso->long_name;
if (dso_name[0] == '[')
return NULL;
if (!strncmp(dso_name, "/tmp/perf-", 10))
return NULL;
return dso_name;
}
static int inline_list__append(struct symbol *symbol, char *srcline,
struct inline_node *node)
{
struct inline_list *ilist;
ilist = zalloc(sizeof(*ilist));
if (ilist == NULL)
return -1;
ilist->symbol = symbol;
ilist->srcline = srcline;
if (callchain_param.order == ORDER_CALLEE)
list_add_tail(&ilist->list, &node->val);
else
list_add(&ilist->list, &node->val);
return 0;
}
/* basename version that takes a const input string */
static const char *gnu_basename(const char *path)
{
const char *base = strrchr(path, '/');
return base ? base + 1 : path;
}
static char *srcline_from_fileline(const char *file, unsigned int line)
{
char *srcline;
if (!file)
return NULL;
if (!srcline_full_filename)
file = gnu_basename(file);
if (asprintf(&srcline, "%s:%u", file, line) < 0)
return NULL;
return srcline;
}
#ifdef HAVE_LIBBFD_SUPPORT
/*
* Implement addr2line using libbfd.
*/
#define PACKAGE "perf"
#include <bfd.h>
struct a2l_data {
const char *input;
u64 addr;
bool found;
const char *filename;
const char *funcname;
unsigned line;
bfd *abfd;
asymbol **syms;
};
static int bfd_error(const char *string)
{
const char *errmsg;
errmsg = bfd_errmsg(bfd_get_error());
fflush(stdout);
if (string)
pr_debug("%s: %s\n", string, errmsg);
else
pr_debug("%s\n", errmsg);
return -1;
}
static int slurp_symtab(bfd *abfd, struct a2l_data *a2l)
{
long storage;
long symcount;
asymbol **syms;
bfd_boolean dynamic = FALSE;
if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0)
return bfd_error(bfd_get_filename(abfd));
storage = bfd_get_symtab_upper_bound(abfd);
if (storage == 0L) {
storage = bfd_get_dynamic_symtab_upper_bound(abfd);
dynamic = TRUE;
}
if (storage < 0L)
return bfd_error(bfd_get_filename(abfd));
syms = malloc(storage);
if (dynamic)
symcount = bfd_canonicalize_dynamic_symtab(abfd, syms);
else
symcount = bfd_canonicalize_symtab(abfd, syms);
if (symcount < 0) {
free(syms);
return bfd_error(bfd_get_filename(abfd));
}
a2l->syms = syms;
return 0;
}
static void find_address_in_section(bfd *abfd, asection *section, void *data)
{
bfd_vma pc, vma;
bfd_size_type size;
struct a2l_data *a2l = data;
if (a2l->found)
return;
if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0)
return;
pc = a2l->addr;
vma = bfd_get_section_vma(abfd, section);
size = bfd_get_section_size(section);
if (pc < vma || pc >= vma + size)
return;
a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
&a2l->filename, &a2l->funcname,
&a2l->line);
if (a2l->filename && !strlen(a2l->filename))
a2l->filename = NULL;
}
static struct a2l_data *addr2line_init(const char *path)
{
bfd *abfd;
struct a2l_data *a2l = NULL;
abfd = bfd_openr(path, NULL);
if (abfd == NULL)
return NULL;
if (!bfd_check_format(abfd, bfd_object))
goto out;
a2l = zalloc(sizeof(*a2l));
if (a2l == NULL)
goto out;
a2l->abfd = abfd;
a2l->input = strdup(path);
if (a2l->input == NULL)
goto out;
if (slurp_symtab(abfd, a2l))
goto out;
return a2l;
out:
if (a2l) {
zfree((char **)&a2l->input);
free(a2l);
}
bfd_close(abfd);
return NULL;
}
static void addr2line_cleanup(struct a2l_data *a2l)
{
if (a2l->abfd)
bfd_close(a2l->abfd);
zfree((char **)&a2l->input);
zfree(&a2l->syms);
free(a2l);
}
#define MAX_INLINE_NEST 1024
static struct symbol *new_inline_sym(struct dso *dso,
struct symbol *base_sym,
const char *funcname)
{
struct symbol *inline_sym;
char *demangled = NULL;
if (dso) {
demangled = dso__demangle_sym(dso, 0, funcname);
if (demangled)
funcname = demangled;
}
if (base_sym && strcmp(funcname, base_sym->name) == 0) {
/* reuse the real, existing symbol */
inline_sym = base_sym;
/* ensure that we don't alias an inlined symbol, which could
* lead to double frees in inline_node__delete
*/
assert(!base_sym->inlined);
} else {
/* create a fake symbol for the inline frame */
inline_sym = symbol__new(base_sym ? base_sym->start : 0,
base_sym ? base_sym->end : 0,
base_sym ? base_sym->binding : 0,
funcname);
if (inline_sym)
inline_sym->inlined = 1;
}
free(demangled);
return inline_sym;
}
perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper<true>::_S_do_it<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:654 double std::norm<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:28 +08:00
static int inline_list__append_dso_a2l(struct dso *dso,
struct inline_node *node,
struct symbol *sym)
perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper<true>::_S_do_it<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:654 double std::norm<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:28 +08:00
{
struct a2l_data *a2l = dso->a2l;
struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
char *srcline = NULL;
perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper<true>::_S_do_it<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:654 double std::norm<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:28 +08:00
if (a2l->filename)
srcline = srcline_from_fileline(a2l->filename, a2l->line);
return inline_list__append(inline_sym, srcline, node);
perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper<true>::_S_do_it<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:654 double std::norm<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:28 +08:00
}
static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line, struct dso *dso,
bool unwind_inlines, struct inline_node *node,
struct symbol *sym)
{
int ret = 0;
struct a2l_data *a2l = dso->a2l;
if (!a2l) {
dso->a2l = addr2line_init(dso_name);
a2l = dso->a2l;
}
if (a2l == NULL) {
pr_warning("addr2line_init failed for %s\n", dso_name);
return 0;
}
a2l->addr = addr;
a2l->found = false;
bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
perf report: Fix memory leak in addr2line when called by addr2inlines When a filename was found in addr2line it was duplicated via strdup() but never freed. Now we pass NULL and handle this gracefully in addr2line. Detected by Valgrind: ==16331== 1,680 bytes in 21 blocks are definitely lost in loss record 148 of 220 ==16331== at 0x4C2AF1F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) ==16331== by 0x672FA69: strdup (in /usr/lib/libc-2.25.so) ==16331== by 0x52769F: addr2line (srcline.c:256) ==16331== by 0x52769F: addr2inlines (srcline.c:294) ==16331== by 0x52769F: dso__parse_addr_inlines (srcline.c:502) ==16331== by 0x574D7A: inline__fprintf (hist.c:41) ==16331== by 0x574D7A: ipchain__fprintf_graph (hist.c:147) ==16331== by 0x57518A: __callchain__fprintf_graph (hist.c:212) ==16331== by 0x5753CF: callchain__fprintf_graph.constprop.6 (hist.c:337) ==16331== by 0x57738E: hist_entry__fprintf (hist.c:628) ==16331== by 0x57738E: hists__fprintf (hist.c:882) ==16331== by 0x44A20F: perf_evlist__tty_browse_hists (builtin-report.c:399) ==16331== by 0x44A20F: report__browse_hists (builtin-report.c:491) ==16331== by 0x44A20F: __cmd_report (builtin-report.c:624) ==16331== by 0x44A20F: cmd_report (builtin-report.c:1054) ==16331== by 0x4A49CE: run_builtin (perf.c:296) ==16331== by 0x4A4CC0: handle_internal_command (perf.c:348) ==16331== by 0x434371: run_argv (perf.c:392) ==16331== by 0x434371: main (perf.c:530) Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-3-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:24 +08:00
if (!a2l->found)
return 0;
if (unwind_inlines) {
int cnt = 0;
if (node && inline_list__append_dso_a2l(dso, node, sym))
perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper<true>::_S_do_it<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:654 double std::norm<double>(std::complex<double> const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs<double> std::_Norm_helper<true>::_S_do_it<double> std::norm<double> main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:28 +08:00
return 0;
while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
&a2l->funcname, &a2l->line) &&
cnt++ < MAX_INLINE_NEST) {
if (a2l->filename && !strlen(a2l->filename))
a2l->filename = NULL;
if (node != NULL) {
if (inline_list__append_dso_a2l(dso, node, sym))
return 0;
perf report: Fix memory leak in addr2line when called by addr2inlines When a filename was found in addr2line it was duplicated via strdup() but never freed. Now we pass NULL and handle this gracefully in addr2line. Detected by Valgrind: ==16331== 1,680 bytes in 21 blocks are definitely lost in loss record 148 of 220 ==16331== at 0x4C2AF1F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) ==16331== by 0x672FA69: strdup (in /usr/lib/libc-2.25.so) ==16331== by 0x52769F: addr2line (srcline.c:256) ==16331== by 0x52769F: addr2inlines (srcline.c:294) ==16331== by 0x52769F: dso__parse_addr_inlines (srcline.c:502) ==16331== by 0x574D7A: inline__fprintf (hist.c:41) ==16331== by 0x574D7A: ipchain__fprintf_graph (hist.c:147) ==16331== by 0x57518A: __callchain__fprintf_graph (hist.c:212) ==16331== by 0x5753CF: callchain__fprintf_graph.constprop.6 (hist.c:337) ==16331== by 0x57738E: hist_entry__fprintf (hist.c:628) ==16331== by 0x57738E: hists__fprintf (hist.c:882) ==16331== by 0x44A20F: perf_evlist__tty_browse_hists (builtin-report.c:399) ==16331== by 0x44A20F: report__browse_hists (builtin-report.c:491) ==16331== by 0x44A20F: __cmd_report (builtin-report.c:624) ==16331== by 0x44A20F: cmd_report (builtin-report.c:1054) ==16331== by 0x4A49CE: run_builtin (perf.c:296) ==16331== by 0x4A4CC0: handle_internal_command (perf.c:348) ==16331== by 0x434371: run_argv (perf.c:392) ==16331== by 0x434371: main (perf.c:530) Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-3-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:24 +08:00
// found at least one inline frame
ret = 1;
}
}
}
perf report: Fix memory leak in addr2line when called by addr2inlines When a filename was found in addr2line it was duplicated via strdup() but never freed. Now we pass NULL and handle this gracefully in addr2line. Detected by Valgrind: ==16331== 1,680 bytes in 21 blocks are definitely lost in loss record 148 of 220 ==16331== at 0x4C2AF1F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) ==16331== by 0x672FA69: strdup (in /usr/lib/libc-2.25.so) ==16331== by 0x52769F: addr2line (srcline.c:256) ==16331== by 0x52769F: addr2inlines (srcline.c:294) ==16331== by 0x52769F: dso__parse_addr_inlines (srcline.c:502) ==16331== by 0x574D7A: inline__fprintf (hist.c:41) ==16331== by 0x574D7A: ipchain__fprintf_graph (hist.c:147) ==16331== by 0x57518A: __callchain__fprintf_graph (hist.c:212) ==16331== by 0x5753CF: callchain__fprintf_graph.constprop.6 (hist.c:337) ==16331== by 0x57738E: hist_entry__fprintf (hist.c:628) ==16331== by 0x57738E: hists__fprintf (hist.c:882) ==16331== by 0x44A20F: perf_evlist__tty_browse_hists (builtin-report.c:399) ==16331== by 0x44A20F: report__browse_hists (builtin-report.c:491) ==16331== by 0x44A20F: __cmd_report (builtin-report.c:624) ==16331== by 0x44A20F: cmd_report (builtin-report.c:1054) ==16331== by 0x4A49CE: run_builtin (perf.c:296) ==16331== by 0x4A4CC0: handle_internal_command (perf.c:348) ==16331== by 0x434371: run_argv (perf.c:392) ==16331== by 0x434371: main (perf.c:530) Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-3-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:24 +08:00
if (file) {
*file = a2l->filename ? strdup(a2l->filename) : NULL;
ret = *file ? 1 : 0;
}
perf report: Fix memory leak in addr2line when called by addr2inlines When a filename was found in addr2line it was duplicated via strdup() but never freed. Now we pass NULL and handle this gracefully in addr2line. Detected by Valgrind: ==16331== 1,680 bytes in 21 blocks are definitely lost in loss record 148 of 220 ==16331== at 0x4C2AF1F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) ==16331== by 0x672FA69: strdup (in /usr/lib/libc-2.25.so) ==16331== by 0x52769F: addr2line (srcline.c:256) ==16331== by 0x52769F: addr2inlines (srcline.c:294) ==16331== by 0x52769F: dso__parse_addr_inlines (srcline.c:502) ==16331== by 0x574D7A: inline__fprintf (hist.c:41) ==16331== by 0x574D7A: ipchain__fprintf_graph (hist.c:147) ==16331== by 0x57518A: __callchain__fprintf_graph (hist.c:212) ==16331== by 0x5753CF: callchain__fprintf_graph.constprop.6 (hist.c:337) ==16331== by 0x57738E: hist_entry__fprintf (hist.c:628) ==16331== by 0x57738E: hists__fprintf (hist.c:882) ==16331== by 0x44A20F: perf_evlist__tty_browse_hists (builtin-report.c:399) ==16331== by 0x44A20F: report__browse_hists (builtin-report.c:491) ==16331== by 0x44A20F: __cmd_report (builtin-report.c:624) ==16331== by 0x44A20F: cmd_report (builtin-report.c:1054) ==16331== by 0x4A49CE: run_builtin (perf.c:296) ==16331== by 0x4A4CC0: handle_internal_command (perf.c:348) ==16331== by 0x434371: run_argv (perf.c:392) ==16331== by 0x434371: main (perf.c:530) Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-3-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 14:21:24 +08:00
if (line)
*line = a2l->line;
return ret;
}
void dso__free_a2l(struct dso *dso)
{
struct a2l_data *a2l = dso->a2l;
if (!a2l)
return;
addr2line_cleanup(a2l);
dso->a2l = NULL;
}
static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
struct dso *dso, struct symbol *sym)
{
struct inline_node *node;
node = zalloc(sizeof(*node));
if (node == NULL) {
perror("not enough memory for the inline node");
return NULL;
}
INIT_LIST_HEAD(&node->val);
node->addr = addr;
perf report: Cache failed lookups of inlined frames When no inlined frames could be found for a given address, we did not store this information anywhere. That means we potentially do the costly inliner lookup repeatedly for cases where we know it can never succeed. This patch makes dso__parse_addr_inlines always return a valid inline_node. It will be empty when no inliners are found. This enables us to cache the empty list in the DSO, thereby improving the performance when many addresses fail to find the inliners. For my trivial example, the performance impact is already quite significant: Before: ~~~~~ Performance counter stats for 'perf report --stdio --inline -g srcline -s srcline' (5 runs): 594.804032 task-clock (msec) # 0.998 CPUs utilized ( +- 0.07% ) 53 context-switches # 0.089 K/sec ( +- 4.09% ) 0 cpu-migrations # 0.000 K/sec ( +-100.00% ) 5,687 page-faults # 0.010 M/sec ( +- 0.02% ) 2,300,918,213 cycles # 3.868 GHz ( +- 0.09% ) 4,395,839,080 instructions # 1.91 insn per cycle ( +- 0.00% ) 939,177,205 branches # 1578.969 M/sec ( +- 0.00% ) 11,824,633 branch-misses # 1.26% of all branches ( +- 0.10% ) 0.596246531 seconds time elapsed ( +- 0.07% ) ~~~~~ After: ~~~~~ Performance counter stats for 'perf report --stdio --inline -g srcline -s srcline' (5 runs): 113.111405 task-clock (msec) # 0.990 CPUs utilized ( +- 0.89% ) 29 context-switches # 0.255 K/sec ( +- 54.25% ) 0 cpu-migrations # 0.000 K/sec 5,380 page-faults # 0.048 M/sec ( +- 0.01% ) 432,378,779 cycles # 3.823 GHz ( +- 0.75% ) 670,057,633 instructions # 1.55 insn per cycle ( +- 0.01% ) 141,001,247 branches # 1246.570 M/sec ( +- 0.01% ) 2,346,845 branch-misses # 1.66% of all branches ( +- 0.19% ) 0.114222393 seconds time elapsed ( +- 1.19% ) ~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20171019113836.5548-3-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-19 19:38:33 +08:00
addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
return node;
}
#else /* HAVE_LIBBFD_SUPPORT */
static int filename_split(char *filename, unsigned int *line_nr)
{
char *sep;
sep = strchr(filename, '\n');
if (sep)
*sep = '\0';
if (!strcmp(filename, "??:0"))
return 0;
sep = strchr(filename, ':');
if (sep) {
*sep++ = '\0';
*line_nr = strtoul(sep, NULL, 0);
return 1;
}
return 0;
}
static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line_nr,
struct dso *dso __maybe_unused,
bool unwind_inlines __maybe_unused,
struct inline_node *node __maybe_unused,
struct symbol *sym __maybe_unused)
{
FILE *fp;
char cmd[PATH_MAX];
char *filename = NULL;
size_t len;
int ret = 0;
scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
dso_name, addr);
fp = popen(cmd, "r");
if (fp == NULL) {
pr_warning("popen failed for %s\n", dso_name);
return 0;
}
if (getline(&filename, &len, fp) < 0 || !len) {
pr_warning("addr2line has no output for %s\n", dso_name);
goto out;
}
ret = filename_split(filename, line_nr);
if (ret != 1) {
free(filename);
goto out;
}
*file = filename;
out:
pclose(fp);
return ret;
}
void dso__free_a2l(struct dso *dso __maybe_unused)
{
}
static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
struct dso *dso __maybe_unused,
struct symbol *sym)
{
FILE *fp;
char cmd[PATH_MAX];
struct inline_node *node;
char *filename = NULL;
size_t len;
unsigned int line_nr = 0;
scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
dso_name, addr);
fp = popen(cmd, "r");
if (fp == NULL) {
pr_err("popen failed for %s\n", dso_name);
return NULL;
}
node = zalloc(sizeof(*node));
if (node == NULL) {
perror("not enough memory for the inline node");
goto out;
}
INIT_LIST_HEAD(&node->val);
node->addr = addr;
while (getline(&filename, &len, fp) != -1) {
char *srcline;
if (filename_split(filename, &line_nr) != 1) {
free(filename);
goto out;
}
srcline = srcline_from_fileline(filename, line_nr);
if (inline_list__append(sym, srcline, node) != 0)
goto out;
filename = NULL;
}
out:
pclose(fp);
return node;
}
#endif /* HAVE_LIBBFD_SUPPORT */
/*
* Number of addr2line failures (without success) before disabling it for that
* dso.
*/
#define A2L_FAIL_LIMIT 123
char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 05:49:28 +08:00
bool show_sym, bool show_addr, bool unwind_inlines)
{
char *file = NULL;
unsigned line = 0;
char *srcline;
const char *dso_name;
if (!dso->has_srcline)
goto out;
dso_name = dso__name(dso);
if (dso_name == NULL)
goto out;
if (!addr2line(dso_name, addr, &file, &line, dso,
unwind_inlines, NULL, sym))
goto out;
srcline = srcline_from_fileline(file, line);
free(file);
if (!srcline)
goto out;
dso->a2l_fails = 0;
return srcline;
out:
if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
dso->has_srcline = 0;
dso__free_a2l(dso);
}
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 05:49:28 +08:00
if (!show_addr)
return (show_sym && sym) ?
strndup(sym->name, sym->namelen) : NULL;
if (sym) {
if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
addr - sym->start) < 0)
return SRCLINE_UNKNOWN;
} else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
return SRCLINE_UNKNOWN;
return srcline;
}
void free_srcline(char *srcline)
{
if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
free(srcline);
}
char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 05:49:28 +08:00
bool show_sym, bool show_addr)
{
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 05:49:28 +08:00
return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
}
perf report: Cache srclines for callchain nodes On one hand this ensures that the memory is properly freed when the DSO gets freed. On the other hand this significantly speeds up the processing of the callchain nodes when lots of srclines are requested. For one of my data files e.g.: Before: Performance counter stats for 'perf report -s srcline -g srcline --stdio': 52496.495043 task-clock (msec) # 0.999 CPUs utilized 634 context-switches # 0.012 K/sec 2 cpu-migrations # 0.000 K/sec 191,561 page-faults # 0.004 M/sec 165,074,498,235 cycles # 3.144 GHz 334,170,832,408 instructions # 2.02 insn per cycle 90,220,029,745 branches # 1718.591 M/sec 654,525,177 branch-misses # 0.73% of all branches 52.533273822 seconds time elapsedProcessed 236605 events and lost 40 chunks! After: Performance counter stats for 'perf report -s srcline -g srcline --stdio': 22606.323706 task-clock (msec) # 1.000 CPUs utilized 31 context-switches # 0.001 K/sec 0 cpu-migrations # 0.000 K/sec 185,471 page-faults # 0.008 M/sec 71,188,113,681 cycles # 3.149 GHz 133,204,943,083 instructions # 1.87 insn per cycle 34,886,384,979 branches # 1543.214 M/sec 278,214,495 branch-misses # 0.80% of all branches 22.609857253 seconds time elapsed Note that the difference is only this large when `--inline` is not passed. In such situations, we would use the inliner cache and thus do not run this code path that often. I think that this cache should actually be used in other places, too. When looking at the valgrind leak report for perf report, we see tons of srclines being leaked, most notably from calls to hist_entry__get_srcline. The problem is that get_srcline has many different formatting options (show_sym, show_addr, potentially even unwind_inlines when calling __get_srcline directly). As such, the srcline cannot easily be cached for all calls, or we'd have to add caches for all formatting combinations (6 so far). An alternative would be to remove the formatting options and handle that on a different level - i.e. print the sym/addr on demand wherever we actually output something. And the unwind_inlines could be moved into a separate function that does not return the srcline. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20171019113836.5548-4-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-19 19:38:34 +08:00
struct srcline_node {
u64 addr;
char *srcline;
struct rb_node rb_node;
};
void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
{
struct rb_node **p = &tree->rb_node;
struct rb_node *parent = NULL;
struct srcline_node *i, *node;
node = zalloc(sizeof(struct srcline_node));
if (!node) {
perror("not enough memory for the srcline node");
return;
}
node->addr = addr;
node->srcline = srcline;
while (*p != NULL) {
parent = *p;
i = rb_entry(parent, struct srcline_node, rb_node);
if (addr < i->addr)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&node->rb_node, parent, p);
rb_insert_color(&node->rb_node, tree);
}
char *srcline__tree_find(struct rb_root *tree, u64 addr)
{
struct rb_node *n = tree->rb_node;
while (n) {
struct srcline_node *i = rb_entry(n, struct srcline_node,
rb_node);
if (addr < i->addr)
n = n->rb_left;
else if (addr > i->addr)
n = n->rb_right;
else
return i->srcline;
}
return NULL;
}
void srcline__tree_delete(struct rb_root *tree)
{
struct srcline_node *pos;
struct rb_node *next = rb_first(tree);
while (next) {
pos = rb_entry(next, struct srcline_node, rb_node);
next = rb_next(&pos->rb_node);
rb_erase(&pos->rb_node, tree);
free_srcline(pos->srcline);
zfree(&pos);
}
}
struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
struct symbol *sym)
{
const char *dso_name;
dso_name = dso__name(dso);
if (dso_name == NULL)
return NULL;
return addr2inlines(dso_name, addr, dso, sym);
}
void inline_node__delete(struct inline_node *node)
{
struct inline_list *ilist, *tmp;
list_for_each_entry_safe(ilist, tmp, &node->val, list) {
list_del_init(&ilist->list);
free_srcline(ilist->srcline);
/* only the inlined symbols are owned by the list */
if (ilist->symbol && ilist->symbol->inlined)
symbol__delete(ilist->symbol);
free(ilist);
}
free(node);
}
void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
{
struct rb_node **p = &tree->rb_node;
struct rb_node *parent = NULL;
const u64 addr = inlines->addr;
struct inline_node *i;
while (*p != NULL) {
parent = *p;
i = rb_entry(parent, struct inline_node, rb_node);
if (addr < i->addr)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&inlines->rb_node, parent, p);
rb_insert_color(&inlines->rb_node, tree);
}
struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
{
struct rb_node *n = tree->rb_node;
while (n) {
struct inline_node *i = rb_entry(n, struct inline_node,
rb_node);
if (addr < i->addr)
n = n->rb_left;
else if (addr > i->addr)
n = n->rb_right;
else
return i;
}
return NULL;
}
void inlines__tree_delete(struct rb_root *tree)
{
struct inline_node *pos;
struct rb_node *next = rb_first(tree);
while (next) {
pos = rb_entry(next, struct inline_node, rb_node);
next = rb_next(&pos->rb_node);
rb_erase(&pos->rb_node, tree);
inline_node__delete(pos);
}
}