From 73c5d224b4514575abe0dd89b43adbde937429c3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 7 Nov 2014 22:57:56 +0900 Subject: [PATCH 01/16] perf build-id: Move disable_buildid_cache() to util/build-id.c Also move static variable no_buildid_cache and check it in the perf_session_cache_build_ids(). Signed-off-by: Namhyung Kim Cc: Aravinda Prasad Cc: Brendan Gregg Cc: Hemant Kumar Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Vasant Hegde Cc: systemtap@sourceware.org Link: http://lkml.kernel.org/r/1415368677-3794-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 11 +++++++++++ tools/perf/util/build-id.h | 1 + tools/perf/util/header.c | 10 +--------- tools/perf/util/util.h | 1 - 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index dd2a3e52ada1..e8d79e5bfaf7 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -18,6 +18,9 @@ #include "header.h" #include "vdso.h" + +static bool no_buildid_cache; + int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -251,6 +254,11 @@ int dsos__hit_all(struct perf_session *session) return 0; } +void disable_buildid_cache(void) +{ + no_buildid_cache = true; +} + int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms, bool is_vdso) { @@ -404,6 +412,9 @@ int perf_session__cache_build_ids(struct perf_session *session) int ret; char debugdir[PATH_MAX]; + if (no_buildid_cache) + return 0; + snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 666a3bd4f64e..8236319514d5 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -25,5 +25,6 @@ int perf_session__cache_build_ids(struct perf_session *session); int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); +void disable_buildid_cache(void); #endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 05fab7a188dc..b20e40c74468 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -24,8 +24,6 @@ #include "build-id.h" #include "data.h" -static bool no_buildid_cache = false; - static u32 header_argc; static const char **header_argv; @@ -191,8 +189,7 @@ static int write_build_id(int fd, struct perf_header *h, pr_debug("failed to write buildid table\n"); return err; } - if (!no_buildid_cache) - perf_session__cache_build_ids(session); + perf_session__cache_build_ids(session); return 0; } @@ -2791,8 +2788,3 @@ int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, session); return 0; } - -void disable_buildid_cache(void) -{ - no_buildid_cache = true; -} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 7dc44cfe25b3..76d23d83eae5 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -154,7 +154,6 @@ extern void set_die_routine(void (*routine)(const char *err, va_list params) NOR extern int prefixcmp(const char *str, const char *prefix); extern void set_buildid_dir(void); -extern void disable_buildid_cache(void); static inline const char *skip_prefix(const char *str, const char *prefix) { From 5e2d4d0e88dac4003cf96aca00d63aff2314391e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 7 Nov 2014 14:20:06 +0900 Subject: [PATCH 02/16] perf tools: Clean up libelf feature support code Current EXTLIBS contains -lelf by default and removes it when libelf is not detected. This is little bit confusing since we can now build perf without libelf so there's no need to handle it differently than other libraries. Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1415337606-2186-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 -- tools/perf/config/Makefile | 5 +++-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index aecf61dcd754..478efa9b2364 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -497,8 +497,6 @@ ifneq ($(OUTPUT),) endif ifdef NO_LIBELF -EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) - # Remove ELF/DWARF dependent codes LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 79f906c7124e..5d4b039fe1ed 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -150,7 +150,7 @@ CFLAGS += -std=gnu99 # adding assembler files missing the .GNU-stack linker note. LDFLAGS += -Wl,-z,noexecstack -EXTLIBS = -lelf -lpthread -lrt -lm -ldl +EXTLIBS = -lpthread -lrt -lm -ldl ifneq ($(OUTPUT),) OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/ @@ -354,6 +354,7 @@ endif # NO_LIBELF ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT + EXTLIBS += -lelf ifeq ($(feature-libelf-mmap), 1) CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT @@ -373,7 +374,7 @@ ifndef NO_LIBELF else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) LDFLAGS += $(LIBDW_LDFLAGS) - EXTLIBS += -lelf -ldw + EXTLIBS += -ldw endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF endif # NO_LIBELF From 162bcc17bb876772793ca070ebd6488cfdae09bf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 11 Nov 2014 11:25:28 -0300 Subject: [PATCH 03/16] perf symbols: Fallback to kallsyms when using the minimal 'ELF' loader The minimal ELF loader should not return 1 when it manages to read the vmlinux build-id, it should instead return 0, meaning that it hasn't loaded any symbols, since it doesn't parses ELF at all. That way, the main symbol.c routines will understand that it is necessary to continue looking for a file with symbols, and when no libelf is linked, that means it will eventually try kallsyms. Reported-by: Peter Zijlstra Tested-by: Peter Zijlstra Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20141111130326.GT18464@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-minimal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index c9541fea9514..fa585c63f56a 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -341,7 +341,6 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { dso__set_build_id(dso, build_id); - return 1; } return 0; } From 887e73d7f42c6a146b572a0577e9875ccca66f37 Mon Sep 17 00:00:00 2001 From: WANG Chao Date: Wed, 12 Nov 2014 16:27:05 +0800 Subject: [PATCH 04/16] perf test: fix typo in python test Library loading in python syntax should be 'import perf', not 'use perf'. Signed-off-by: WANG Chao Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jean Pihet Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1415780826-13250-1-git-send-email-chaowang@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/builtin-test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 162c978f1491..4b7d9ab0f049 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -85,7 +85,7 @@ static struct test { .func = test__hists_link, }, { - .desc = "Try 'use perf' in python, checking link problems", + .desc = "Try 'import perf' in python, checking link problems", .func = test__python_use, }, { From ee205503f2333d639550eaed37abb455733510a3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 11 Nov 2014 12:04:54 +0200 Subject: [PATCH 05/16] perf tools: Fix annotation with kcore Patch "perf tools: Fix build-id matching on vmlinux" breaks annotation with kcore. The problem is that symbol__annotate() first gets the filename based on the build-id which was previously not set. This patch provides a quick fix, however there should probably be only one way to determine the filename. e.g. symbol__annotate() should use the same way as dso__data_fd(). Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415700294-30816-1-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 7dabde14ea54..873c8778db20 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -915,6 +915,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) return -ENOMEM; } goto fallback; + } else if (dso__is_kcore(dso)) { + goto fallback; } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || strstr(command, "[kernel.kallsyms]") || access(symfs_filename, R_OK)) { From 37592b8afb7151994e760d1727c264329d9c13c8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:19 -0800 Subject: [PATCH 06/16] perf callchain: Factor out adding new call chain entries Move the code to resolve and add a new callchain entry into a new add_callchain_ip function. This will be used in the next patches to add LBRs too. No change in behavior. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-2-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 51 ++++++++++++++++++++++++--------------- 1 file changed, 32 insertions(+), 19 deletions(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 52e94902afb1..84390eecab06 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1381,6 +1381,34 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return mi; } +static int add_callchain_ip(struct thread *thread, + struct symbol **parent, + struct addr_location *root_al, + int cpumode, + u64 ip) +{ + struct addr_location al; + + al.filtered = 0; + al.sym = NULL; + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + ip, &al); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + symbol__match_regex(al.sym, &parent_regex)) + *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } + } + + return callchain_cursor_append(&callchain_cursor, ip, al.map, al.sym); +} + struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al) { @@ -1427,7 +1455,6 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < chain_nr; i++) { u64 ip; - struct addr_location al; if (callchain_param.order == ORDER_CALLEE) j = i; @@ -1464,24 +1491,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, continue; } - al.filtered = 0; - thread__find_addr_location(thread, cpumode, - MAP__FUNCTION, ip, &al); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_regex(al.sym, &parent_regex)) - *parent = al.sym; - else if (have_ignore_callees && root_al && - symbol__match_regex(al.sym, &ignore_callees_regex)) { - /* Treat this symbol as the root, - forgetting its callees. */ - *root_al = al; - callchain_cursor_reset(&callchain_cursor); - } - } - - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); + err = add_callchain_ip(thread, parent, root_al, + cpumode, ip); + if (err == -EINVAL) + break; if (err) return err; } From 5550171b2a9f8df26ff483051d060db06376b26d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:21 -0800 Subject: [PATCH 07/16] perf callchain: Use al.addr to set up call chain Use the relative address, this makes get_srcline work correctly in the end. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-4-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 84390eecab06..d97309c87bd6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1406,7 +1406,7 @@ static int add_callchain_ip(struct thread *thread, } } - return callchain_cursor_append(&callchain_cursor, ip, al.map, al.sym); + return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, From 2989ccaac48f8c3da7f77101bbf98e0ea8773d83 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:23 -0800 Subject: [PATCH 08/16] perf callchain: Use a common function to resolve symbol or name Refactor the duplicated code to resolve the symbol name or the address of a symbol into a single function. Used in next patch to add common functionality. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-6-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 17 ----------------- tools/perf/ui/gtk/hists.c | 11 +---------- tools/perf/ui/stdio/hist.c | 23 +++++++++-------------- tools/perf/util/callchain.c | 19 +++++++++++++++++++ tools/perf/util/callchain.h | 3 +++ 5 files changed, 32 insertions(+), 41 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index cfb976b3de3a..12c17c5a3d68 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -463,23 +463,6 @@ out: return key; } -static char *callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize, bool show_dso) -{ - int printed; - - if (cl->ms.sym) - printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); - else - printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); - - if (show_dso) - scnprintf(bf + printed, bfsize - printed, " %s", - cl->ms.map ? cl->ms.map->dso->short_name : "unknown"); - - return bf; -} - struct callchain_print_arg { /* for hists browser */ off_t row_offset; diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index fc654fb77ace..4b3585eed1e8 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -89,15 +89,6 @@ void perf_gtk__init_hpp(void) perf_gtk__hpp_color_overhead_acc; } -static void callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize) -{ - if (cl->ms.sym) - scnprintf(bf, bfsize, "%s", cl->ms.sym->name); - else - scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); -} - static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, GtkTreeIter *parent, int col, u64 total) { @@ -128,7 +119,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, scnprintf(buf, sizeof(buf), "%5.2f%%", percent); gtk_tree_store_set(store, &iter, 0, buf, -1); - callchain_list__sym_name(chain, buf, sizeof(buf)); + callchain_list__sym_name(chain, buf, sizeof(buf), false); gtk_tree_store_set(store, &iter, col, buf, -1); if (need_new_parent) { diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 15b451acbde6..dfcbc90146ef 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -41,6 +41,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, { int i; size_t ret = 0; + char bf[1024]; ret += callchain__fprintf_left_margin(fp, left_margin); for (i = 0; i < depth; i++) { @@ -56,11 +57,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, } else ret += fprintf(fp, "%s", " "); } - if (chain->ms.sym) - ret += fprintf(fp, "%s\n", chain->ms.sym->name); - else - ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip); - + fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp); + fputc('\n', fp); return ret; } @@ -168,6 +166,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, struct rb_node *node; int i = 0; int ret = 0; + char bf[1024]; /* * If have one single callchain root, don't bother printing @@ -196,10 +195,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, } else ret += callchain__fprintf_left_margin(fp, left_margin); - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); + ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf), + false)); if (++entries_printed == callchain_param.print_limit) break; @@ -219,6 +216,7 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node, { struct callchain_list *chain; size_t ret = 0; + char bf[1024]; if (!node) return 0; @@ -229,11 +227,8 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node, list_for_each_entry(chain, &node->val, list) { if (chain->ip >= PERF_CONTEXT_MAX) continue; - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", - (void *)(long)chain->ip); + ret += fprintf(fp, " %s\n", callchain_list__sym_name(chain, + bf, sizeof(bf), false)); } return ret; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 00229809a904..38da69c8c1ff 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -808,3 +808,22 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * out: return 1; } + +char *callchain_list__sym_name(struct callchain_list *cl, + char *bf, size_t bfsize, bool show_dso) +{ + int printed; + + if (cl->ms.sym) { + printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); + } else + printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); + + if (show_dso) + scnprintf(bf + printed, bfsize - printed, " %s", + cl->ms.map ? + cl->ms.map->dso->short_name : + "unknown"); + + return bf; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 3caccc2c173c..3e1ed15d11f1 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -193,4 +193,7 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, } #endif +char *callchain_list__sym_name(struct callchain_list *cl, + char *bf, size_t bfsize, bool show_dso); + #endif /* __PERF_CALLCHAIN_H */ From 2de217688e8f086bf6d920d530401b56fcbc6eff Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:25 -0800 Subject: [PATCH 09/16] perf tools: Only print base source file for srcline For perf report with --sort srcline only print the base source file name. This makes the results generally fit much better to the screen. The path is usually not that useful anyways because it is often from different systems. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-8-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f3e4bc5fe5d2..77c180637138 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -274,7 +274,7 @@ char *get_srcline(struct dso *dso, unsigned long addr) if (!addr2line(dso_name, addr, &file, &line, dso)) goto out; - if (asprintf(&srcline, "%s:%u", file, line) < 0) { + if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) { free(file); goto out; } From e592488c01d51763de847fcecb3d969231a483a9 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:26 -0800 Subject: [PATCH 10/16] perf annotate: Support source line numbers in annotate With srcline key/sort'ing it's useful to have line numbers in the annotate window. This patch implements this. Use objdump -l to request the line numbers and save them in the line structure. Then the browser displays them for source lines. The line numbers are not displayed by default, but can be toggled on with 'k' There is one unfortunate problem with this setup. For lines not containing source and which are outside functions objdump -l reports line numbers off by a few: it always reports the first line number in the next function even for lines that are outside the function. I haven't found a nice way to detect/correct this. Probably objdump has to be fixed. See https://sourceware.org/bugzilla/show_bug.cgi?id=16433 The line numbers are still useful even with these problems, as most are correct and the ones which are not are nearby. v2: Fix help text. Handle (discriminator...) output in objdump. Left align the line numbers. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-9-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/annotate.c | 13 ++++++++++++- tools/perf/util/annotate.c | 30 +++++++++++++++++++++++++----- tools/perf/util/annotate.h | 1 + 3 files changed, 38 insertions(+), 6 deletions(-) diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index f0697a3aede0..1e0a2fd80115 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -27,6 +27,7 @@ static struct annotate_browser_opt { bool hide_src_code, use_offset, jump_arrows, + show_linenr, show_nr_jumps; } annotate_browser__opts = { .use_offset = true, @@ -128,7 +129,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int if (!*dl->line) slsmg_write_nstring(" ", width - pcnt_width); else if (dl->offset == -1) { - printed = scnprintf(bf, sizeof(bf), "%*s ", + if (dl->line_nr && annotate_browser__opts.show_linenr) + printed = scnprintf(bf, sizeof(bf), "%-*d ", + ab->addr_width + 1, dl->line_nr); + else + printed = scnprintf(bf, sizeof(bf), "%*s ", ab->addr_width, " "); slsmg_write_nstring(bf, printed); slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1); @@ -733,6 +738,7 @@ static int annotate_browser__run(struct annotate_browser *browser, "o Toggle disassembler output/simplified view\n" "s Toggle source code view\n" "/ Search string\n" + "k Toggle line numbers\n" "r Run available scripts\n" "? Search string backwards\n"); continue; @@ -741,6 +747,10 @@ static int annotate_browser__run(struct annotate_browser *browser, script_browse(NULL); continue; } + case 'k': + annotate_browser__opts.show_linenr = + !annotate_browser__opts.show_linenr; + break; case 'H': nd = browser->curr_hot; break; @@ -984,6 +994,7 @@ static struct annotate_config { } annotate__configs[] = { ANNOTATE_CFG(hide_src_code), ANNOTATE_CFG(jump_arrows), + ANNOTATE_CFG(show_linenr), ANNOTATE_CFG(show_nr_jumps), ANNOTATE_CFG(use_offset), }; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 873c8778db20..e5670f1af737 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,11 +17,13 @@ #include "debug.h" #include "annotate.h" #include "evsel.h" +#include #include #include const char *disassembler_style; const char *objdump_path; +static regex_t file_lineno; static struct ins *ins__find(const char *name); static int disasm_line__parse(char *line, char **namep, char **rawp); @@ -570,13 +572,15 @@ out_free_name: return -1; } -static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize) +static struct disasm_line *disasm_line__new(s64 offset, char *line, + size_t privsize, int line_nr) { struct disasm_line *dl = zalloc(sizeof(*dl) + privsize); if (dl != NULL) { dl->offset = offset; dl->line = strdup(line); + dl->line_nr = line_nr; if (dl->line == NULL) goto out_delete; @@ -788,13 +792,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st * The ops.raw part will be parsed further according to type of the instruction. */ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, - FILE *file, size_t privsize) + FILE *file, size_t privsize, + int *line_nr) { struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; char *line = NULL, *parsed_line, *tmp, *tmp2, *c; size_t line_len; s64 line_ip, offset = -1; + regmatch_t match[2]; if (getline(&line, &line_len, file) < 0) return -1; @@ -812,6 +818,12 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, line_ip = -1; parsed_line = line; + /* /filename:linenr ? Save line number and ignore. */ + if (regexec(&file_lineno, line, 2, match, 0) == 0) { + *line_nr = atoi(line + match[1].rm_so); + return 0; + } + /* * Strip leading spaces: */ @@ -842,8 +854,9 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, parsed_line = tmp2 + 1; } - dl = disasm_line__new(offset, parsed_line, privsize); + dl = disasm_line__new(offset, parsed_line, privsize, *line_nr); free(line); + (*line_nr)++; if (dl == NULL) return -1; @@ -869,6 +882,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, return 0; } +static __attribute__((constructor)) void symbol__init_regexpr(void) +{ + regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED); +} + static void delete_last_nop(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); @@ -904,6 +922,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) char symfs_filename[PATH_MAX]; struct kcore_extract kce; bool delete_extract = false; + int lineno = 0; if (filename) symbol__join_symfs(symfs_filename, filename); @@ -984,7 +1003,7 @@ fallback: snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -d %s %s -C %s 2>/dev/null|grep -v %s|expand", + " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -1001,7 +1020,8 @@ fallback: goto out_free_filename; while (!feof(file)) - if (symbol__parse_objdump_line(sym, map, file, privsize) < 0) + if (symbol__parse_objdump_line(sym, map, file, privsize, + &lineno) < 0) break; /* diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 112d6e268150..0784a9420528 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -58,6 +58,7 @@ struct disasm_line { char *line; char *name; struct ins *ins; + int line_nr; struct ins_operands ops; }; From b2d53671cdb0cf5070d56359821eb812669bb1ad Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 18 Nov 2014 18:02:51 -0300 Subject: [PATCH 11/16] perf hists: Fix up srcline histogram key formatting Problem introduced in: commit 5b5916696051 "perf report: Honor column width setting" Where the left justification signal was after the width, which ended up, when the width was, say, 11, always printing: %11.11-s Instead of src:line left justified and limited to 11 chars. Resulting in a like: 70.93% %11.11-s [.] f2 tcall When it should instead be: 70.93% tcall.c:5 [.] f2 tcall Cc: Adrian Hunter Cc: Andi Kleen Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-2xnt0vqkoox52etq2qhyetr0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9402885a77f3..82a5596241a7 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -309,7 +309,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline); + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline); } struct sort_entry sort_srcline = { From 68ca9d65b88420c2c97948a0640bad13405129e7 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 18 Nov 2014 11:38:18 -0500 Subject: [PATCH 12/16] perf diff: Add missing handler for PERF_RECORD_MMAP2 events Without mmap2, perf diff fails to find the symbol name. The default symbol sort key doesn't work well. Signed-off-by: Kan Liang Acked-by: Namhyung Kim Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1416328700-1836-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 25114c9a6801..1ce425d101a9 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -357,6 +357,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, static struct perf_tool tool = { .sample = diff__process_sample_event, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, From f140373bc904d9541e3f8e985d3810864e34c735 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 13 Nov 2014 18:21:03 +0100 Subject: [PATCH 13/16] perf evsel: Fix ftrace:function event recording Following patch fails (-EINVAL) ftrace:function with enabled user space callchains: cfa77bc4af2c perf: Disallow user-space callchains for function trace events We need to follow in perf tool itself and explicitly set the perf_event_attr::exclude_callchain_user flag for ftrace:function event. Reported-by: Steven Rostedt 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 Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1415899263-24820-1-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 34344ffa79ca..f2dc91fb87fa 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -658,6 +658,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (perf_evsel__is_function_event(evsel)) + evsel->attr.exclude_callchain_user = 1; + if (callchain_param.enabled && !evsel->no_aux_samples) perf_evsel__config_callgraph(evsel); From f90d194a867a5a1db51789b8c4e99bcd196be6bb Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 11 Nov 2014 16:16:39 +0200 Subject: [PATCH 14/16] perf evlist: Do not poll events that use the system_wide flag The system_wide flag causes a selected event to be opened always without a pid. Consequently it will never get a POLLHUP, but it is used for tracking in combination with other events, so it should not need to be polled anyway. Therefore don't add it for polling. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415715423-15563-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7e23dae54f1d..cfbe2b99b9aa 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -816,7 +816,15 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, perf_evlist__mmap_get(evlist, idx); } - if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) { + /* + * The system_wide flag causes a selected event to be opened + * always without a pid. Consequently it will never get a + * POLLHUP, but it is used for tracking in combination with + * other events, so it should not need to be polled anyway. + * Therefore don't add it for polling. + */ + if (!evsel->system_wide && + __perf_evlist__add_pollfd(evlist, fd, idx) < 0) { perf_evlist__mmap_put(evlist, idx); return -1; } From 4b34f19b66ad29f10af90ad396131adbd16d737f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 11 Nov 2014 16:16:40 +0200 Subject: [PATCH 15/16] perf tools: Add perf-read-vdso32 and perf-read-vdsox32 to .gitignore Recently added executables Add perf-read-vdso32 and perf-read-vdsox32 need to be added to .gitignore. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415715423-15563-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/.gitignore | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 717221e98450..40399c3d97d6 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -2,6 +2,8 @@ PERF-CFLAGS PERF-GUI-VARS PERF-VERSION-FILE perf +perf-read-vdso32 +perf-read-vdsox32 perf-help perf-record perf-report From a84808083688d82d7f1e5786ccf5df0ff7d448cb Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 11 Nov 2014 16:16:41 +0200 Subject: [PATCH 16/16] perf tools: Only override the default :tid comm entry Events may still be ordered even if there are no timestamps e.g. if the data is recorded per-thread. Also synthesized COMM events have a timestamp of zero. Consequently it is better to keep comm entries even if they have a timestamp of zero. However, when a struct thread is created the command string is not known and a comm entry with a string of the form ":" is used. In that case thread->comm_set is false and the comm entry should be overridden. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415715423-15563-4-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index a2157f0ef1df..9ebc8b1f9be5 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -103,15 +103,14 @@ struct comm *thread__exec_comm(const struct thread *thread) return last; } -/* CHECKME: time should always be 0 if event aren't ordered */ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); int err; - /* Override latest entry if it had no specific time coverage */ - if (!curr->start && !curr->exec) { + /* Override the default :tid entry */ + if (!thread->comm_set) { err = comm__override(curr, str, timestamp, exec); if (err) return err;