From f07a2d32b521a54635c8efeb0a3180b0afcf780a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Apr 2018 10:49:50 -0300 Subject: perf thread: Introduce thread__find_map() Out of thread__find_add_map(..., MAP__FUNCTION, ...), idea here is to continue removing references to MAP__{FUNCTION,VARIABLE} ahead of getting both types of symbols in the same rbtree, as various places do two lookups, looking first at MAP__FUNCTION, then at MAP__VARIABLE. So thread__find_map() will eventually do just that, and 'struct symbol' will have the symbol type, for code that cares about that. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-q27xee34l4izpfau49w103s6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e0a9845b6cbc..5ec1c73bbfaf 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -717,8 +717,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, if (PRINT_FIELD(DSO)) { memset(&alf, 0, sizeof(alf)); memset(&alt, 0, sizeof(alt)); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + thread__find_map(thread, sample->cpumode, from, &alf); + thread__find_map(thread, sample->cpumode, to, &alt); } printed += fprintf(fp, " 0x%"PRIx64, from); @@ -764,11 +764,11 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + thread__find_map(thread, sample->cpumode, from, &alf); if (alf.map) alf.sym = map__find_symbol(alf.map, alf.addr); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + thread__find_map(thread, sample->cpumode, to, &alt); if (alt.map) alt.sym = map__find_symbol(alt.map, alt.addr); @@ -814,11 +814,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + thread__find_map(thread, sample->cpumode, from, &alf); if (alf.map && !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + thread__find_map(thread, sample->cpumode, to, &alt); if (alt.map && !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); @@ -882,7 +882,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al); + thread__find_map(thread, *cpumode, start, &al); if (!al.map || !al.map->dso) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; @@ -933,10 +933,9 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); + thread__find_map(thread, cpumode, addr, &al); if (!al.map) - thread__find_addr_map(thread, cpumode, MAP__VARIABLE, - addr, &al); + __thread__find_map(thread, cpumode, MAP__VARIABLE, addr, &al); if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) return 0; -- cgit From cc5f02f2be8d3354986bad5703ee8a983872f140 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Apr 2018 11:32:30 -0300 Subject: perf script: Use thread__find_symbol() instead of ad-hoc equivalent In dc323ce8e72d ("perf script: Enable printing of branch stack") it first tries to find the map for an address, then the symbol in the DSO backing that map, for that address, well, this is what thread__find_symbol() does, so just use it and make the code shorter. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-03nx3aod955yqnf9l06im28j@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5ec1c73bbfaf..ffd02faee87b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -764,13 +764,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_map(thread, sample->cpumode, from, &alf); - if (alf.map) - alf.sym = map__find_symbol(alf.map, alf.addr); - - thread__find_map(thread, sample->cpumode, to, &alt); - if (alt.map) - alt.sym = map__find_symbol(alt.map, alt.addr); + thread__find_symbol(thread, sample->cpumode, from, &alf); + thread__find_symbol(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); if (PRINT_FIELD(DSO)) { -- cgit From 71a84b5aedf5023f4009c3bbf28ecba256201f87 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Apr 2018 11:58:56 -0300 Subject: perf thread: Make thread__find_map() return the map It was returning the searched map just on the addr_location passed, with the function itself returning void. Make it return the map so that we can make the code more compact. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-tzlrrzdeoof4i6ktyqv1t6ks@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 4 +--- tools/perf/builtin-script.c | 14 ++++++-------- tools/perf/tests/code-reading.c | 3 +-- tools/perf/util/build-id.c | 4 +--- tools/perf/util/cs-etm.c | 4 +--- tools/perf/util/event.c | 16 ++++++++-------- tools/perf/util/intel-bts.c | 3 +-- tools/perf/util/intel-pt.c | 6 ++---- tools/perf/util/thread.h | 10 +++++----- tools/perf/util/unwind-libdw.c | 3 +-- tools/perf/util/unwind-libunwind-local.c | 3 +-- 11 files changed, 28 insertions(+), 42 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 92677d8f9eae..a3b346359ba0 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, goto repipe; } - thread__find_map(thread, sample->cpumode, sample->ip, &al); - - if (al.map != NULL) { + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) { if (!al.map->dso->hit) { al.map->dso->hit = 1; if (map__load(al.map) >= 0) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ffd02faee87b..07cb083ac89c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -809,12 +809,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_map(thread, sample->cpumode, from, &alf); - if (alf.map && !alf.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, from, &alf) && + !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - thread__find_map(thread, sample->cpumode, to, &alt); - if (alt.map && !alt.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, to, &alt) && + !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); @@ -877,8 +877,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - thread__find_map(thread, *cpumode, start, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } @@ -928,8 +927,7 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_map(thread, cpumode, addr, &al); - if (!al.map) + if (!thread__find_map(thread, cpumode, addr, &al)) __thread__find_map(thread, cpumode, MAP__VARIABLE, addr, &al); if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) return 0; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 5b0a55499486..afa4ce21ba7c 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -236,8 +236,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - thread__find_map(thread, cpumode, addr, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); return 0; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index b512dc8fa6c3..04b1d53e4bf9 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } - thread__find_map(thread, sample->cpumode, sample->ip, &al); - - if (al.map != NULL) + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) al.map->dso->hit = 1; thread__put(thread); diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 8fe573d040b6..6533b1adb50b 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -269,9 +269,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, thread = etmq->etm->unknown_thread; } - thread__find_map(thread, cpumode, address, &al); - - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso) return 0; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2d860fbeb227..48e4b252f6ff 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1489,8 +1489,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -void __thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, - u64 addr, struct addr_location *al) +struct map *__thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, + u64 addr, struct addr_location *al) { struct map_groups *mg = thread->mg; struct machine *machine = mg->machine; @@ -1504,7 +1504,7 @@ void __thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, if (machine == NULL) { al->map = NULL; - return; + return NULL; } if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { @@ -1532,7 +1532,7 @@ void __thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, !perf_host) al->filtered |= (1 << HIST_FILTER__HOST); - return; + return NULL; } try_again: al->map = map_groups__find(mg, type, al->addr); @@ -1562,14 +1562,15 @@ try_again: map__load(al->map); al->addr = al->map->map_ip(al->map, al->addr); } + + return al->map; } void __thread__find_symbol(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { - __thread__find_map(thread, cpumode, type, addr, al); - if (al->map != NULL) + if (__thread__find_map(thread, cpumode, type, addr, al)) al->sym = map__find_symbol(al->map, al->addr); else al->sym = NULL; @@ -1668,8 +1669,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - thread__find_map(thread, sample->cpumode, sample->addr, al); - if (!al->map) { + if (!thread__find_map(thread, sample->cpumode, sample->addr, al)) { __thread__find_map(thread, sample->cpumode, MAP__VARIABLE, sample->addr, al); } diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index ea0ce8572bf2..7f0c83b6332b 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip) if (!thread) return -1; - thread__find_map(thread, cpumode, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) goto out_put; len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 441e681a46a0..a272b35f6c5a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -442,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, } while (1) { - thread__find_map(thread, cpumode, *ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso) return -EINVAL; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && @@ -596,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread) return -EINVAL; - thread__find_map(thread, cpumode, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) return -EINVAL; offset = al.map->map_ip(al.map, ip); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index b69e65c821f9..1961e4bc1c2c 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -92,13 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp); struct thread *thread__main_thread(struct machine *machine, struct thread *thread); -void __thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, - u64 addr, struct addr_location *al); +struct map *__thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, + u64 addr, struct addr_location *al); -static inline void thread__find_map(struct thread *thread, u8 cpumode, - u64 addr, struct addr_location *al) +static inline struct map *thread__find_map(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al) { - __thread__find_map(thread, cpumode, MAP__FUNCTION, addr, al); + return __thread__find_map(thread, cpumode, MAP__FUNCTION, addr, al); } void __thread__find_symbol(struct thread *thread, u8 cpumode, enum map_type type, diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index bdc22f1864df..17401922cd42 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -104,8 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, struct addr_location al; ssize_t size; - thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al); - if (!al.map) { + if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { /* * We've seen cases (softice) where DWARF unwinder went * through non executable mmaps, which we need to lookup diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 0007c64f3220..4662590ef091 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -367,8 +367,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); - if (!al.map) { + if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al)) { /* * We've seen cases (softice) where DWARF unwinder went * through non executable mmaps, which we need to lookup -- cgit From 404eb5a436c4cbdc3b76896a28a3b72b7ad9294e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Apr 2018 09:34:37 -0300 Subject: perf thread: Make thread__find_map() search all maps We still have the split internally, but users don't see it anymore, simplifying the growing number of cases where we end up searching in the MAP__VARIABLE maps. This further paves the way for ditching the split. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-86mfxrztf310konutxvhr5ua@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 4 ++-- tools/perf/util/event.c | 19 +++++++++++-------- tools/perf/util/thread.h | 10 ++-------- tools/perf/util/unwind-libdw.c | 10 ---------- tools/perf/util/unwind-libunwind-local.c | 12 +----------- 5 files changed, 16 insertions(+), 39 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 07cb083ac89c..fa2c7a288750 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -927,8 +927,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, memset(&al, 0, sizeof(al)); - if (!thread__find_map(thread, cpumode, addr, &al)) - __thread__find_map(thread, cpumode, MAP__VARIABLE, addr, &al); + thread__find_map(thread, cpumode, addr, &al); + if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) return 0; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 7b67771cd478..7831c2266118 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1488,8 +1488,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -struct map *__thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, - u64 addr, struct addr_location *al) +static struct map *__thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, + u64 addr, struct addr_location *al) { struct map_groups *mg = thread->mg; struct machine *machine = mg->machine; @@ -1565,12 +1565,18 @@ try_again: return al->map; } +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) +{ + struct map *map = __thread__find_map(thread, cpumode, MAP__FUNCTION, addr, al); + return map ?: __thread__find_map(thread, cpumode, MAP__VARIABLE, addr, al); +} + struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { al->sym = NULL; - if (__thread__find_map(thread, cpumode, MAP__FUNCTION, addr, al) || - __thread__find_map(thread, cpumode, MAP__VARIABLE, addr, al)) + if (thread__find_map(thread, cpumode, addr, al)) al->sym = map__find_symbol(al->map, al->addr); return al->sym; } @@ -1668,10 +1674,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - if (!thread__find_map(thread, sample->cpumode, sample->addr, al)) { - __thread__find_map(thread, sample->cpumode, MAP__VARIABLE, - sample->addr, al); - } + thread__find_map(thread, sample->cpumode, sample->addr, al); al->cpu = sample->cpu; al->sym = NULL; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 54aa24d6151e..07606aa6998d 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -92,14 +92,8 @@ size_t thread__fprintf(struct thread *thread, FILE *fp); struct thread *thread__main_thread(struct machine *machine, struct thread *thread); -struct map *__thread__find_map(struct thread *thread, u8 cpumode, enum map_type type, - u64 addr, struct addr_location *al); - -static inline struct map *thread__find_map(struct thread *thread, u8 cpumode, - u64 addr, struct addr_location *al) -{ - return __thread__find_map(thread, cpumode, MAP__FUNCTION, addr, al); -} +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al); struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 17401922cd42..538db4e5d1e6 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -105,16 +105,6 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, ssize_t size; if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - __thread__find_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, addr, &al); - } - - if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 2afb22b0a1a9..6a11bc7e6b27 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -366,17 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - - if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al)) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - __thread__find_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, ip, &al); - } - return al.map; + return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); } static int -- cgit From 7903a70867230d9edbd5e886cd8b8a2b248f418f Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 17 May 2018 12:03:26 +0530 Subject: perf script: Show symbol offsets by default Since the ip shown for a symbol is now always a virtual address, it becomes difficult to correlate this with objdump output and determine the exact instruction address. So, we always show the offset from the start of the symbol. This can be verified on a powerpc64le system running Fedora 27 as follows: # perf probe -a sys_write # perf record -e probe:sys_write -g ~/test Before applying this patch: # perf script test 9710 [013] 95614.332431: probe:sys_write: (c0000000004025b0) c0000000004025b0 sys_write (/lib/modules/4.17.0-rc4+/build/vmlinux) c00000000000b9e0 system_call (/lib/modules/4.17.0-rc4+/build/vmlinux) 7fffb70d8234 __GI___libc_write (/usr/lib64/libc-2.26.so) 7fffb7052c74 _IO_file_write@@GLIBC_2.17 (/usr/lib64/libc-2.26.so) 5afc1818 [unknown] ([unknown]) 7fffb7051a60 new_do_write (/usr/lib64/libc-2.26.so) 7fffb7054638 _IO_do_write@@GLIBC_2.17 (/usr/lib64/libc-2.26.so) 7fffb7054bbc _IO_file_overflow@@GLIBC_2.17 (/usr/lib64/libc-2.26.so) 7fffb7055a24 __overflow (/usr/lib64/libc-2.26.so) 7fffb7044548 _IO_puts (/usr/lib64/libc-2.26.so) 10000440 main (/home/sandipan/test) 7fffb6fe36a0 generic_start_main.isra.0 (/usr/lib64/libc-2.26.so) 7fffb6fe3898 __libc_start_main (/usr/lib64/libc-2.26.so) 0 [unknown] ([unknown]) ... After applying this patch: # perf script test 9710 [013] 95614.332431: probe:sys_write: (c0000000004025b0) c0000000004025b0 sys_write+0x10 (/lib/modules/4.17.0-rc4+/build/vmlinux) c00000000000b9e0 system_call+0x58 (/lib/modules/4.17.0-rc4+/build/vmlinux) 7fffb70d8234 __GI___libc_write+0x24 (/usr/lib64/libc-2.26.so) 7fffb7052c74 _IO_file_write@@GLIBC_2.17+0x44 (/usr/lib64/libc-2.26.so) 5afc1818 [unknown] ([unknown]) 7fffb7051a60 new_do_write+0x90 (/usr/lib64/libc-2.26.so) 7fffb7054638 _IO_do_write@@GLIBC_2.17+0x38 (/usr/lib64/libc-2.26.so) 7fffb7054bbc _IO_file_overflow@@GLIBC_2.17+0x14c (/usr/lib64/libc-2.26.so) 7fffb7055a24 __overflow+0x64 (/usr/lib64/libc-2.26.so) 7fffb7044548 _IO_puts+0x218 (/usr/lib64/libc-2.26.so) 10000440 main+0x20 (/home/sandipan/test) 7fffb6fe36a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so) 7fffb6fe3898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so) 0 [unknown] ([unknown]) ... Signed-off-by: Sandipan Das Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Naveen N. Rao Cc: Ravi Bangoria Link: http://lkml.kernel.org/r/20180517063326.6319-2-sandipan@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 26 ++++++++++++---------- .../tests/shell/record+probe_libc_inet_pton.sh | 12 +++++----- 2 files changed, 20 insertions(+), 18 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index fa2c7a288750..cefc8813e91e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -153,8 +153,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -165,8 +165,9 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_BPF_OUTPUT, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -185,10 +186,10 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | - PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | - PERF_OUTPUT_PHYS_ADDR, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | + PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -199,8 +200,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -211,8 +212,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_SYNTH, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -544,6 +545,7 @@ static int perf_session__check_output_opt(struct perf_session *session) if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) { output[j].fields |= PERF_OUTPUT_IP; output[j].fields |= PERF_OUTPUT_SYM; + output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; set_print_ip_opts(attr); goto out; diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index ee86473643be..650b208f700f 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -16,18 +16,18 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { idx=0 expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" - expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$" + expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" case "$(uname -m)" in s390x) eventattr='call-graph=dwarf,max-stack=4' - expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$" - expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$" - expected[4]="main[[:space:]]\(.*/bin/ping.*\)$" + expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" + expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" + expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" ;; *) eventattr='max-stack=3' - expected[2]="getaddrinfo[[:space:]]\($libc\)$" - expected[3]=".*\(.*/bin/ping.*\)$" + expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" + expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" ;; esac -- cgit From 27de9b2bd996de0ca4079c42c81c85158e10145c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 28 May 2018 16:00:29 -0300 Subject: perf evsel: Add has_callchain() helper to make code more compact/clear Its common to have the (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN), so add an evsel__has_callchain(evsel) helper. This will actually get more uses as we check that instead of symbol_conf.use_callchain in places where that produces the same result but makes this decision to be more fine grained, per evsel. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-145340oytbthatpfeaq1do18@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 3 +-- tools/perf/builtin-script.c | 10 +++------- tools/perf/builtin-trace.c | 2 +- tools/perf/tests/parse-events.c | 4 ++-- tools/perf/util/evsel.c | 4 ++-- tools/perf/util/evsel.h | 5 +++++ tools/perf/util/hist.c | 2 +- tools/perf/util/session.c | 2 +- 8 files changed, 16 insertions(+), 16 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 4dfdee668b0c..97f9e755e8e6 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2933,8 +2933,7 @@ static int timehist_check_attr(struct perf_sched *sched, return -1; } - if (sched->show_callchain && - !(evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (sched->show_callchain && !evsel__has_callchain(evsel)) { pr_info("Samples do not have callchains.\n"); sched->show_callchain = 0; symbol_conf.use_callchain = 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index cefc8813e91e..48e940efb3cb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -517,7 +517,7 @@ static int perf_session__check_output_opt(struct perf_session *session) evlist__for_each_entry(session->evlist, evsel) { not_pipe = true; - if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { use_callchain = true; break; } @@ -532,22 +532,18 @@ static int perf_session__check_output_opt(struct perf_session *session) */ if (symbol_conf.use_callchain && !output[PERF_TYPE_TRACEPOINT].user_set) { - struct perf_event_attr *attr; - j = PERF_TYPE_TRACEPOINT; evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.type != j) continue; - attr = &evsel->attr; - - if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { output[j].fields |= PERF_OUTPUT_IP; output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(attr); + set_print_ip_opts(&evsel->attr); goto out; } } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 560aed7da36a..6a748eca2edb 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2491,7 +2491,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) * to override an explicitely set --max-stack global setting. */ evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) && + if (evsel__has_callchain(evsel) && evsel->attr.sample_max_stack == 0) evsel->attr.sample_max_stack = trace->max_stack; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index b9ebe15afb13..7d4077068454 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -499,7 +499,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); /* cpu/config=2,call-graph=no,time=0,period=2000/ */ @@ -512,7 +512,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); return 0; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 150db5ed7400..94fce4f537e9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2197,7 +2197,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } - if (type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); OVERFLOW_CHECK_u64(array); @@ -2857,7 +2857,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "Hint: Try again after reducing the number of events.\n" "Hint: Try increasing the limit with 'ulimit -n '"); case ENOMEM: - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 && + if (evsel__has_callchain(evsel) && access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0) return scnprintf(msg, size, "Not enough memory to setup event with callchain.\n" diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index b13f5f234c8f..d277930b19a1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -459,6 +459,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evs return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } +static inline bool evsel__has_callchain(const struct perf_evsel *evsel) +{ + return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; +} + typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 95333b068109..34864c87cd3c 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1757,7 +1757,7 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro bool use_callchain; if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) - use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + use_callchain = evsel__has_callchain(evsel); else use_callchain = symbol_conf.use_callchain; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index b998bb475589..8b9369303561 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1094,7 +1094,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_type = evsel->attr.sample_type; - if (sample_type & PERF_SAMPLE_CALLCHAIN) + if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) -- cgit From b879833cbaac85b1437f574791b8855d26b0dc80 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Jun 2018 10:34:20 -0300 Subject: perf script: Check if evsel has callchains before trying to use it We were checking just if callchain processing was asked for by the user, not if the evsel itself has callchains, and since we can have some evsels with callchains and others without, check that. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-inxl7k49q9f9w1se039fbxuw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 48e940efb3cb..b3bf35512d21 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -606,7 +606,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, if (PRINT_FIELD(COMM)) { if (latency_format) printed += fprintf(fp, "%8.8s ", thread__comm_str(thread)); - else if (PRINT_FIELD(IP) && symbol_conf.use_callchain) + else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) printed += fprintf(fp, "%s ", thread__comm_str(thread)); else printed += fprintf(fp, "%16s ", thread__comm_str(thread)); -- cgit From fad76d4333fe73cf3f73704aa34d4ce523b1c458 Mon Sep 17 00:00:00 2001 From: Seeteena Thoufeek Date: Fri, 8 Jun 2018 16:32:28 +0530 Subject: perf script: Show hw-cache events 'perf script' fails to report hardware cache events (PERF_TYPE_HW_CACHE) where as 'perf report' shows the samples. Fix it. Ex, # perf record -e L1-dcache-loads ./a.out [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (11 samples)] Before patch: # perf script | wc -l 0 After patch: # perf script | wc -l 11 Committer testing: [root@jouet ~]# perf script | head -30 | tail Timer 9803 [2] 8.963330: 1554 L1-dcache-loads: 7ffef89baae4 __vdso_clock_gettime+0xf4 ([vdso]) swapper 0 [2] 8.963343: 5626 L1-dcache-loads: ffffffffa66f4f6b cpuidle_not_av+0xb (/lib/modules/4.17.0-rc5/build/vmlinux) firefox 4853 [2] 8.964070: 18935 L1-dcache-loads: 7f0b9a00dc30 xcb_poll_for_event+0x0 (/usr/lib64/libxcb.so.1.1.0) Softwar~cTh 4928 [2] 8.964548: 15928 L1-dcache-loads: ffffffffa60d795c update_curr+0x10c (/lib/modules/4.17.0-rc5/build/vmlinux) firefox 4853 [2] 8.964675: 14978 L1-dcache-loads: ffffffffa6897018 mutex_unlock+0x18 (/lib/modules/4.17.0-rc5/build/vmlinux) gnome-shell 2026 [3] 8.964693: 50670 L1-dcache-loads: 7fa08854de6d g_source_iter_next+0x6d (/usr/lib64/libglib-2.0.so.0.5400.3) Compositor 4929 [1] 8.964784: 71772 L1-dcache-loads: 7f0b936bf078 [unknown] (/usr/lib64/firefox/libxul.so) Xwayland 2096 [2] 8.964919: 16799 L1-dcache-loads: 7f68ce2fcb8a glXGetCurrentContext+0x1a (/usr/lib64/libGLX.so.0.0.0) gnome-shell 2026 [3] 8.964997: 50670 L1-dcache-loads: 7fa08854de6d g_source_iter_next+0x6d (/usr/lib64/libglib-2.0.so.0.5400.3) [root@jouet ~]# Signed-off-by: Seeteena Thoufeek Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1528455748-20087-1-git-send-email-s1seetee@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b3bf35512d21..a31d7082188e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -180,6 +180,18 @@ static struct { PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE }, + [PERF_TYPE_HW_CACHE] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, + [PERF_TYPE_RAW] = { .user_set = false, -- cgit From 10e9cec905f96fdf47f398be70726e2931b376cd Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 25 Jun 2018 18:12:18 +0530 Subject: perf script: Add missing output fields in a hint A few fields are missing in a perf script -F hint. Add them. Signed-off-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: David Carrillo-Cisneros Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20180625124220.6434-2-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a31d7082188e..f3fefbcc4503 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3125,8 +3125,9 @@ int cmd_script(int argc, const char **argv) "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr", + "addr,symoff,srcline,period,iregs,uregs,brstack," + "brstacksym,flags,bpf-output,brstackinsn,brstackoff," + "callindent,insn,insnlen,synth,phys_addr,metric,misc", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), -- cgit From a3af66f51bd0bca72881ead4bf2bd19cb366582b Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 25 Jun 2018 18:12:19 +0530 Subject: perf script: Fix crash because of missing evsel->priv 'perf script' in piped mode is crashing because evsel->priv is not set properly. Fix it. Before: # perf record -o - -- ls | perf script Segmentation fault (core dumped) # After: # perf record -o - -- ls | perf script ls 2282 1031.731974: 250000 cpu-clock:uhH: 7effe4b3d29e ls 2282 1031.732222: 250000 cpu-clock:uhH: 7effe4b3a650 # Signed-off-by: Ravi Bangoria Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: David Carrillo-Cisneros Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Fixes: a14390fde64e ("perf script: Allow creating per-event dump files") Link: http://lkml.kernel.org/r/20180625124220.6434-3-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index f3fefbcc4503..ad2ac1300420 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist *evlist; struct perf_evsel *evsel, *pos; int err; + static struct perf_evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) @@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evlist = *pevlist; evsel = perf_evlist__last(*pevlist); + if (!evsel->priv) { + if (scr->per_event_dump) { + evsel->priv = perf_evsel_script__new(evsel, + scr->session->data); + } else { + es = zalloc(sizeof(*es)); + if (!es) + return -ENOMEM; + es->fp = stdout; + evsel->priv = es; + } + } + if (evsel->attr.type >= PERF_TYPE_MAX && evsel->attr.type != PERF_TYPE_SYNTH) return 0; -- cgit From 92ead7ee30c80f8852d28735cbcb9d79bc85f715 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 25 Jun 2018 18:12:20 +0530 Subject: perf tools: Fix crash caused by accessing feat_ops[HEADER_LAST_FEATURE] perf_event__process_feature() accesses feat_ops[HEADER_LAST_FEATURE] which is not defined and thus perf is crashing. HEADER_LAST_FEATURE is used as an end marker for the perf report but it's unused for perf script/annotate. Ignore HEADER_LAST_FEATURE for perf script/annotate, just like it is done in 'perf report'. Before: # perf record -o - ls | perf script Segmentation fault (core dumped) # After: # perf record -o - ls | perf script Segmentation fault (core dumped) ls 7031 4392.099856: 250000 cpu-clock:uhH: 7f5e0ce7cd60 ls 7031 4392.100355: 250000 cpu-clock:uhH: 7f5e0c706ef7 # Signed-off-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: David Carrillo-Cisneros Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Fixes: 57b5de463925 ("perf report: Support forced leader feature in pipe mode") Link: http://lkml.kernel.org/r/20180625124220.6434-4-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 11 ++++++++++- tools/perf/builtin-report.c | 3 ++- tools/perf/builtin-script.c | 11 ++++++++++- tools/perf/util/header.c | 2 +- 4 files changed, 23 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 5eb22cc56363..8180319285af 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -283,6 +283,15 @@ out_put: return ret; } +static int process_feature_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session) +{ + if (event->feat.feat_id < HEADER_LAST_FEATURE) + return perf_event__process_feature(tool, event, session); + return 0; +} + static int hist_entry__tty_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct perf_annotate *ann) @@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv) .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, .tracing_data = perf_event__process_tracing_data, - .feature = perf_event__process_feature, + .feature = process_feature_event, .ordered_events = true, .ordering_requires_timestamps = true, }, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index cdb5b6949832..c04dc7b53797 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool, } /* - * All features are received, we can force the + * (feat_id = HEADER_LAST_FEATURE) is the end marker which + * means all features are received, now we can force the * group if needed. */ setup_forced_leader(rep, session->evlist); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ad2ac1300420..568ddfac3213 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3044,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } +static int process_feature_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session) +{ + if (event->feat.feat_id < HEADER_LAST_FEATURE) + return perf_event__process_feature(tool, event, session); + return 0; +} + #ifdef HAVE_AUXTRACE_SUPPORT static int perf_script__process_auxtrace_info(struct perf_tool *tool, union perf_event *event, @@ -3088,7 +3097,7 @@ int cmd_script(int argc, const char **argv) .attr = process_attr, .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, - .feature = perf_event__process_feature, + .feature = process_feature_event, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, .auxtrace_info = perf_script__process_auxtrace_info, diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 59fcc790c865..653ff65aa2c3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3464,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool, pr_warning("invalid record type %d in pipe-mode\n", type); return 0; } - if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) { + if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) { pr_warning("invalid record type %d in pipe-mode\n", type); return -1; } -- cgit