From d4957633bf9dab70e566e7dbb2b8d0c61c3a2f1e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 18 Jul 2015 08:24:48 -0700 Subject: perf report: Add infrastructure for a cycles histogram This adds the basic infrastructure to keep track of cycle counts per basic block for annotate. We allocate an array similar to the normal accounting, and then account branch cycles there. We handle two cases: cycles per basic block with start and cycles per branch (these are later used for either IPC or just cycles per BB) In the start case we cannot handle overlaps, so always the longest basic block wins. For the cycles per branch case everything is accurately accounted. v2: Remove unnecessary checks. Slight restructure. Move symbol__get_annotation to another patch. Move histogram allocation. v3: Merged with current tree Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1437233094-12844-4-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/builtin-annotate.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 2c1bec39c30e..467a23b14e2f 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -187,6 +187,7 @@ find_next: * symbol, free he->ms.sym->src to signal we already * processed this symbol. */ + zfree(¬es->src->cycles_hist); zfree(¬es->src); } } -- cgit v1.2.2 From f9db0d0f1b2cf030083c83d3ed3a4bbae6bdc8b7 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 11 Aug 2015 06:30:48 -0400 Subject: perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/builtin-annotate.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 467a23b14e2f..a32a64ef08e2 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -239,6 +239,8 @@ static int __cmd_annotate(struct perf_annotate *ann) if (nr_samples > 0) { total_nr_samples += nr_samples; hists__collapse_resort(hists, NULL); + /* Don't sort callchain */ + perf_evsel__reset_sample_bit(pos, CALLCHAIN); hists__output_resort(hists, NULL); if (symbol_conf.event_group && -- cgit v1.2.2 From c0b4dffbc529244d3e4e3bd392f2bffa2d8531a7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 24 Aug 2015 13:33:14 -0300 Subject: perf annotate: Reset the dso find_symbol cache when removing symbols The 'annotate' tool does some filtering in the entries in a DSO but forgot to reset the cache done in dso__find_symbol(), cauxing a SEGV: [root@zoo ~]# perf annotate netlink_poll perf: Segmentation fault -------- backtrace -------- perf[0x526ceb] /lib64/libc.so.6(+0x34960)[0x7faedfbe0960] perf(rb_erase+0x223)[0x499d63] perf[0x4213e9] perf[0x4bc123] perf[0x4bc621] perf[0x4bf26b] perf[0x4bc855] perf(perf_session__process_events+0x340)[0x4bddc0] perf(cmd_annotate+0x6bb)[0x421b5b] perf[0x479063] perf(main+0x60a)[0x42098a] /lib64/libc.so.6(__libc_start_main+0xf0)[0x7faedfbcbfe0] perf[0x420aa9] [0x0] [root@zoo ~]# Fix it by reseting the find cache when removing symbols. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Fixes: b685ac22b436 ("perf symbols: Add front end cache for DSO symbol lookup") Link: http://lkml.kernel.org/n/tip-b2y9x46y0t8yem1ive41zqyp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/builtin-annotate.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index a32a64ef08e2..8edc205ff9a7 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -67,6 +67,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, rb_erase(&al->sym->rb_node, &al->map->dso->symbols[al->map->type]); symbol__delete(al->sym); + dso__reset_find_symbol_cache(al->map->dso); } return 0; } -- cgit v1.2.2