From 48c65bda95d692076de7e5eae3188ddae8635dca Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 20 Feb 2014 10:32:53 +0900 Subject: perf annotate: Check availability of annotate when processing samples The TUI of perf report and top support annotation, but stdio and GTK don't. So it should be checked before calling hist_entry__inc_addr_ samples() to avoid wasting resources that will never be used. perf annotate need it regardless of UI and sort keys, so the check of whether to allocate resources should be on the tools that have annotate as an option in the TUI, 'report' and 'top', not on the function called by all of them. It caused perf annotate on ppc64 to produce zero output, since the buckets were not being allocated. Reported-by: Anton Blanchard Signed-off-by: Namhyung Kim Cc: Anton Blanchard Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1392859976-32760-1-git-send-email-namhyung@kernel.org [ Renamed (report,top)__needs_annotate() to ui__has_annotation() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 9 ++++++++- tools/perf/util/annotate.h | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 469eb679fb9..3aa555ff9d8 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -8,6 +8,8 @@ */ #include "util.h" +#include "ui/ui.h" +#include "sort.h" #include "build-id.h" #include "color.h" #include "cache.h" @@ -489,7 +491,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, { struct annotation *notes; - if (sym == NULL || use_browser != 1 || !sort__has_sym) + if (sym == NULL) return 0; notes = symbol__annotation(sym); @@ -1399,3 +1401,8 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) { return symbol__annotate(he->ms.sym, he->ms.map, privsize); } + +bool ui__has_annotation(void) +{ + return use_browser == 1 && sort__has_sym; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index b2aef59d6bb..56ad4f5287d 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -151,6 +151,8 @@ void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void disasm__purge(struct list_head *head); +bool ui__has_annotation(void); + int symbol__tty_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool print_lines, bool full_paths, int min_pcnt, int max_lines); -- cgit v1.2.3-18-g5258 From 98e9f03bbf2cb21a60f94b8b700eb5d38470819d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 20 Feb 2014 10:32:54 +0900 Subject: perf symbols: Destroy unused symsrcs Stephane reported that perf report and annotate failed to process data using lots of (> 500) shared libraries. It was because of the limit on number of open files (ulimit -n). Currently when perf loads a DSO, it'll look for normal and dynamic symbol tables. And if it fails to find out both tables, it'll iterate all of possible symtab types. But many of them are useless since they have no additional information and the problem is that it's not closing those files even though they're not used. Fix it. Reported-by: Stephane Eranian Signed-off-by: Namhyung Kim Cc: Cody P Schafer Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1392859976-32760-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a9d758a3b37..e89afc097d8 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1336,6 +1336,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (syms_ss && runtime_ss) break; + } else { + symsrc__destroy(ss); } } -- cgit v1.2.3-18-g5258 From b39c2a57a00a841f057a75b41df4c26173288b66 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 26 Feb 2014 18:14:26 +0100 Subject: perf tools: Fix strict alias issue for find_first_bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When compiling perf tool code with gcc 4.4.7 I'm getting following error: CC util/session.o cc1: warnings being treated as errors util/session.c: In function ‘perf_session_deliver_event’: tools/perf/util/include/linux/bitops.h:109: error: dereferencing pointer ‘p’ does break strict-aliasing rules tools/perf/util/include/linux/bitops.h:101: error: dereferencing pointer ‘p’ does break strict-aliasing rules util/session.c:697: note: initialized from here tools/perf/util/include/linux/bitops.h:101: note: initialized from here make[1]: *** [util/session.o] Error 1 make: *** [util/session.o] Error 2 The aliased types here are u64 and unsigned long pointers, which is safe for the find_first_bit processing. This error shows up for me only for gcc 4.4 on 32bit x86, even for -Wstrict-aliasing=3, while newer gcc are quiet and scream here for -Wstrict-aliasing={2,1}. Looks like newer gcc changed the rules for strict alias warnings. The gcc documentation offers workaround for valid aliasing by using __may_alias__ attribute: http://gcc.gnu.org/onlinedocs/gcc-4.4.0/gcc/Type-Attributes.html Using this workaround for the find_first_bit function. Signed-off-by: Jiri Olsa Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1393434867-20271-1-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/include/linux/bitops.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index 45cf10a562b..dadfa7e5428 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -87,13 +87,15 @@ static __always_inline unsigned long __ffs(unsigned long word) return num; } +typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; + /* * Find the first set bit in a memory region. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { - const unsigned long *p = addr; + long_alias_t *p = (long_alias_t *) addr; unsigned long result = 0; unsigned long tmp; -- cgit v1.2.3-18-g5258 From 155b3a13a65d4217316dbe094843f2a7df0711fa Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 2 Mar 2014 14:32:07 +0100 Subject: perf symbols: Fix crash in elf_section_by_name Fixing crash in elf_section_by_name function caused by missing section name in elf binary. Reported-by: Albert Strasheim Signed-off-by: Jiri Olsa Cc: Albert Strasheim Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1393767127-599-1-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 3e9f336740f..516d19fb999 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -151,15 +151,15 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, gelf_getshdr(sec, shp); str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); - if (!strcmp(name, str)) { + if (str && !strcmp(name, str)) { if (idx) *idx = cnt; - break; + return sec; } ++cnt; } - return sec; + return NULL; } #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ -- cgit v1.2.3-18-g5258 From fdf57dd052d5cbd415533ae98f4d423286a85220 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 25 Feb 2014 22:43:45 -0500 Subject: perf machine: Use map as success in ip__resolve_ams When trying to map a bunch of instruction addresses to their respective threads, I kept getting a lot of bogus entries [I forget the exact reason as I patched my code months ago]. Looking through ip__resolve_ams, I noticed the check for if (al.sym) and realized, most times I have an al.map definition but sometimes an al.sym is undefined. In the cases where al.sym is undefined, the loop keeps going even though a valid al.map exists. Modify this check to use the more reliable al.map. This fixed my bogus entries. Signed-off-by: Don Zickus Cc: Jiri Olsa Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1393386227-149412-2-git-send-email-dzickus@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c872991e0f6..620a1983b76 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1213,7 +1213,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, */ thread__find_addr_location(thread, machine, m, MAP__FUNCTION, ip, &al); - if (al.sym) + if (al.map) goto found; } found: -- cgit v1.2.3-18-g5258