From ee84a3032b74055feed192a727e872b0a18d1140 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 8 Jun 2023 16:28:00 -0700 Subject: perf thread: Add accessor functions for thread Using accessors will make it easier to add reference count checking in later patches. Committer notes: thread->nsinfo wasn't wrapped as it is used together with nsinfo__zput(), where does a trick to set the field with a refcount being dropped to NULL, and that doesn't work well with using thread__nsinfo(thread), that loses the &thread->nsinfo pointer. When refcount checking is added to 'struct thread', later in this series, nsinfo__zput(RC_CHK_ACCESS(thread)->nsinfo) will be used to check the thread pointer. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ali Saidi Cc: Andi Kleen Cc: Athira Rajeev Cc: Brian Robbins Cc: Changbin Du Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song Cc: German Gomez Cc: Ingo Molnar Cc: Ivan Babrou Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Liam Howlett Cc: Mark Rutland Cc: Miguel Ojeda Cc: Mike Leach Cc: Namhyung Kim Cc: Naveen N. Rao Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Suzuki Poulouse Cc: Wenyu Liu Cc: Will Deacon Cc: Yang Jihong Cc: Ye Xingchen Cc: Yuan Can Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/db-export.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/db-export.c') diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 84c970c11794..751fd53bfd93 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -64,13 +64,13 @@ int db_export__thread(struct db_export *dbe, struct thread *thread, { u64 main_thread_db_id = 0; - if (thread->db_id) + if (thread__db_id(thread)) return 0; - thread->db_id = ++dbe->thread_last_db_id; + thread__set_db_id(thread, ++dbe->thread_last_db_id); if (main_thread) - main_thread_db_id = main_thread->db_id; + main_thread_db_id = thread__db_id(main_thread); if (dbe->export_thread) return dbe->export_thread(dbe, thread, main_thread_db_id, @@ -251,7 +251,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, */ al.sym = node->ms.sym; al.map = node->ms.map; - al.maps = thread->maps; + al.maps = thread__maps(thread); al.addr = node->ip; if (al.map && !al.sym) @@ -321,7 +321,7 @@ static int db_export__threads(struct db_export *dbe, struct thread *thread, * For a non-main thread, db_export__comm_thread() must be * called only if thread has not previously been exported. */ - bool export_comm_thread = comm && !thread->db_id; + bool export_comm_thread = comm && !thread__db_id(thread); err = db_export__thread(dbe, thread, machine, main_thread); if (err) @@ -529,16 +529,16 @@ static int db_export__pid_tid(struct db_export *dbe, struct machine *machine, struct thread *main_thread; int err = 0; - if (!thread || !thread->comm_set) + if (!thread || !thread__comm_set(thread)) goto out_put; - *is_idle = !thread->pid_ && !thread->tid; + *is_idle = !thread__pid(thread) && !thread__tid(thread); main_thread = thread__main_thread(machine, thread); err = db_export__threads(dbe, thread, main_thread, machine, comm_ptr); - *db_id = thread->db_id; + *db_id = thread__db_id(thread); thread__put(main_thread); out_put: -- cgit From 0dd5041c9a0eaf8c5c3fd46df4ee60f877799f44 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 8 Jun 2023 16:28:03 -0700 Subject: perf addr_location: Add init/exit/copy functions struct addr_location holds references to multiple reference counted objects. Add init/exit functions to make maintenance of those more consistent with the rest of the code and to try to avoid leaks. Modification of thread reference counts isn't included in this change. Committer notes: I needed to initialize result to sample->ip to make sure is set to something, fixing a compile time error, mostly keeping the previous logic as build_alloc_func_list() already does debugging/error prints about what went wrong if it takes the 'goto out'. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ali Saidi Cc: Andi Kleen Cc: Athira Rajeev Cc: Brian Robbins Cc: Changbin Du Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song Cc: German Gomez Cc: Ingo Molnar Cc: Ivan Babrou Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Liam Howlett Cc: Mark Rutland Cc: Miguel Ojeda Cc: Mike Leach Cc: Namhyung Kim Cc: Naveen N. Rao Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Suzuki Poulouse Cc: Wenyu Liu Cc: Will Deacon Cc: Yang Jihong Cc: Ye Xingchen Cc: Yuan Can Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 28 +++++--- tools/perf/builtin-c2c.c | 12 ++-- tools/perf/builtin-diff.c | 16 +++-- tools/perf/builtin-inject.c | 2 + tools/perf/builtin-kmem.c | 10 ++- tools/perf/builtin-kwork.c | 15 +++-- tools/perf/builtin-mem.c | 4 +- tools/perf/builtin-report.c | 6 +- tools/perf/builtin-sched.c | 2 + tools/perf/builtin-script.c | 77 +++++++++++++--------- tools/perf/builtin-timechart.c | 11 ++-- tools/perf/builtin-top.c | 6 +- tools/perf/builtin-trace.c | 10 ++- tools/perf/tests/code-reading.c | 3 +- tools/perf/tests/hists_cumulate.c | 17 +++-- tools/perf/tests/hists_filter.c | 11 ++-- tools/perf/tests/hists_link.c | 18 +++-- tools/perf/tests/hists_output.c | 10 ++- tools/perf/tests/mmap-thread-lookup.c | 4 +- tools/perf/util/addr_location.c | 30 ++++++++- tools/perf/util/addr_location.h | 5 +- tools/perf/util/build-id.c | 2 + tools/perf/util/cs-etm.c | 20 +++--- tools/perf/util/data-convert-json.c | 8 ++- tools/perf/util/db-export.c | 4 +- tools/perf/util/dlfilter.c | 13 +++- tools/perf/util/event.c | 16 +++-- tools/perf/util/evsel_fprintf.c | 8 ++- tools/perf/util/hist.c | 8 ++- tools/perf/util/intel-pt.c | 66 +++++++++++++------ tools/perf/util/machine.c | 35 +++++----- .../util/scripting-engines/trace-event-python.c | 10 ++- tools/perf/util/thread.c | 13 +++- tools/perf/util/unwind-libdw.c | 21 ++++-- tools/perf/util/unwind-libunwind-local.c | 13 +++- 35 files changed, 368 insertions(+), 166 deletions(-) (limited to 'tools/perf/util/db-export.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 425a7e2fd6fb..aeeb801f1ed7 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -184,7 +184,7 @@ out: static int process_branch_callback(struct evsel *evsel, struct perf_sample *sample, - struct addr_location *al __maybe_unused, + struct addr_location *al, struct perf_annotate *ann, struct machine *machine) { @@ -195,21 +195,29 @@ static int process_branch_callback(struct evsel *evsel, .hide_unresolved = symbol_conf.hide_unresolved, .ops = &hist_iter_branch, }; - struct addr_location a; + int ret; - if (machine__resolve(machine, &a, sample) < 0) - return -1; + addr_location__init(&a); + if (machine__resolve(machine, &a, sample) < 0) { + ret = -1; + goto out; + } - if (a.sym == NULL) - return 0; + if (a.sym == NULL) { + ret = 0; + goto out; + } if (a.map != NULL) map__dso(a.map)->hit = 1; hist__account_cycles(sample->branch_stack, al, sample, false, NULL); - return hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann); + ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann); +out: + addr_location__exit(&a); + return ret; } static bool has_annotation(struct perf_annotate *ann) @@ -272,10 +280,12 @@ static int process_sample_event(struct perf_tool *tool, struct addr_location al; int ret = 0; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out_put; } if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap)) @@ -288,7 +298,7 @@ static int process_sample_event(struct perf_tool *tool, ret = -1; } out_put: - addr_location__put(&al); + addr_location__exit(&al); return ret; } diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index ee41a96f0c73..530a44a59f41 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -286,10 +286,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct mem_info *mi, *mi_dup; int ret; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out; } if (c2c.stitch_lbr) @@ -301,8 +303,10 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, goto out; mi = sample__resolve_mem(sample, &al); - if (mi == NULL) - return -ENOMEM; + if (mi == NULL) { + ret = -ENOMEM; + goto out; + } /* * The mi object is released in hists__add_entry_ops, @@ -368,7 +372,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, } out: - addr_location__put(&al); + addr_location__exit(&al); return ret; free_mi: diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index dbb0562d6a4f..ca39657ee407 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -409,15 +409,17 @@ static int diff__process_sample_event(struct perf_tool *tool, return 0; } + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out; } if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) { ret = 0; - goto out_put; + goto out; } switch (compute) { @@ -426,7 +428,7 @@ static int diff__process_sample_event(struct perf_tool *tool, NULL, NULL, NULL, sample, true)) { pr_warning("problem incrementing symbol period, " "skipping event\n"); - goto out_put; + goto out; } hist__account_cycles(sample->branch_stack, &al, sample, false, @@ -437,7 +439,7 @@ static int diff__process_sample_event(struct perf_tool *tool, if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, NULL)) { pr_debug("problem adding hist entry, skipping event\n"); - goto out_put; + goto out; } break; @@ -446,7 +448,7 @@ static int diff__process_sample_event(struct perf_tool *tool, true)) { pr_warning("problem incrementing symbol period, " "skipping event\n"); - goto out_put; + goto out; } } @@ -460,8 +462,8 @@ static int diff__process_sample_event(struct perf_tool *tool, if (!al.filtered) hists->stats.total_non_filtered_period += sample->period; ret = 0; -out_put: - addr_location__put(&al); +out: + addr_location__exit(&al); return ret; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index d9e96d4624c6..d19a1b862306 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -743,6 +743,7 @@ int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, struct addr_location al; struct thread *thread; + addr_location__init(&al); thread = machine__findnew_thread(machine, sample->pid, sample->tid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -763,6 +764,7 @@ int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, thread__put(thread); repipe: perf_event__repipe(tool, event, sample, machine); + addr_location__exit(&al); return 0; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index fe9439a4fd66..96a6611e4e53 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -399,7 +399,9 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) struct addr_location al; struct machine *machine = &kmem_session->machines.host; struct callchain_cursor_node *node; + u64 result = sample->ip; + addr_location__init(&al); if (alloc_func_list == NULL) { if (build_alloc_func_list() < 0) goto out; @@ -427,16 +429,18 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) else addr = node->ip; - return addr; + result = addr; + goto out; } else pr_debug3("skipping alloc function: %s\n", caller->name); callchain_cursor_advance(&callchain_cursor); } -out: pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip); - return sample->ip; +out: + addr_location__exit(&al); + return result; } struct sort_dimension { diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index a9395c52b23b..2d80aef4eccc 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -739,17 +739,22 @@ static int timehist_exit_event(struct perf_kwork *kwork, struct kwork_atom *atom = NULL; struct kwork_work *work = NULL; struct addr_location al; + int ret = 0; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_debug("Problem processing event, skipping it\n"); - return -1; + ret = -1; + goto out; } atom = work_pop_atom(kwork, class, KWORK_TRACE_EXIT, KWORK_TRACE_ENTRY, evsel, sample, machine, &work); - if (work == NULL) - return -1; + if (work == NULL) { + ret = -1; + goto out; + } if (atom != NULL) { work->nr_atoms++; @@ -757,7 +762,9 @@ static int timehist_exit_event(struct perf_kwork *kwork, atom_del(atom); } - return 0; +out: + addr_location__exit(&al); + return ret; } static struct kwork_class kwork_irq; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 960bfd4b732a..51499c20da01 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -199,9 +199,11 @@ dump_raw_samples(struct perf_tool *tool, char str[PAGE_SIZE_NAME_LEN]; struct dso *dso = NULL; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); + addr_location__exit(&al); return -1; } @@ -256,7 +258,7 @@ dump_raw_samples(struct perf_tool *tool, dso ? dso->long_name : "???", al.sym ? al.sym->name : "???"); out_put: - addr_location__put(&al); + addr_location__exit(&al); return 0; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8ea6ab18534a..0b091a8983a5 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -285,10 +285,12 @@ static int process_sample_event(struct perf_tool *tool, if (evswitch__discard(&rep->evswitch, evsel)) return 0; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out_put; } if (rep->stitch_lbr) @@ -331,7 +333,7 @@ static int process_sample_event(struct perf_tool *tool, if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); out_put: - addr_location__put(&al); + addr_location__exit(&al); return ret; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index fd37468c4f62..c75ad82a6729 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2584,6 +2584,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, int rc = 0; int state = evsel__intval(evsel, sample, "prev_state"); + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_err("problem processing %d event. skipping it\n", event->header.type); @@ -2692,6 +2693,7 @@ out: evsel__save_time(evsel, sample->time, sample->cpu); + addr_location__exit(&al); return rc; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e756290de2ac..784d478c2e05 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -919,7 +919,6 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -930,20 +929,22 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, from = entries[i].from; to = entries[i].to; + printed += fprintf(fp, " 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + struct addr_location alf, alt; + + addr_location__init(&alf); + addr_location__init(&alt); thread__find_map_fb(thread, sample->cpumode, from, &alf); thread__find_map_fb(thread, sample->cpumode, to, &alt); - } - printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); - - printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) + printed += fprintf(fp, "/0x%"PRIx64, to); printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); + addr_location__exit(&alt); + addr_location__exit(&alf); + } else + printed += fprintf(fp, "/0x%"PRIx64, to); printed += print_bstack_flags(fp, entries + i); } @@ -957,7 +958,6 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -965,9 +965,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + addr_location__init(&alf); + addr_location__init(&alt); from = entries[i].from; to = entries[i].to; @@ -982,6 +983,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, if (PRINT_FIELD(DSO)) printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); + addr_location__exit(&alt); + addr_location__exit(&alf); } return printed; @@ -993,7 +996,6 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -1001,9 +1003,10 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + addr_location__init(&alf); + addr_location__init(&alt); from = entries[i].from; to = entries[i].to; @@ -1022,6 +1025,8 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, if (PRINT_FIELD(DSO)) printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); + addr_location__exit(&alt); + addr_location__exit(&alf); } return printed; @@ -1036,6 +1041,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, struct addr_location al; bool kernel; struct dso *dso; + int ret = 0; if (!start || !end) return 0; @@ -1057,7 +1063,6 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return -ENXIO; } - memset(&al, 0, sizeof(al)); if (end - start > MAXBB - MAXINSN) { if (last) pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); @@ -1066,13 +1071,14 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } + addr_location__init(&al); if (!thread__find_map(thread, *cpumode, start, &al) || (dso = map__dso(al.map)) == NULL) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } if (dso->data.status == DSO_DATA_STATUS_ERROR) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } /* Load maps to ensure dso->is_64_bit has been updated */ @@ -1086,7 +1092,10 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, if (len <= 0) pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", start, end); - return len; + ret = len; +out: + addr_location__exit(&al); + return ret; } static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srccode_state *state) @@ -1137,14 +1146,16 @@ static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) struct addr_location al; int ret = 0; - memset(&al, 0, sizeof(al)); + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if (!al.map) - return 0; + goto out; ret = map__fprintf_srccode(al.map, al.addr, stdout, thread__srccode_state(thread)); if (ret) ret += printf("\n"); +out: + addr_location__exit(&al); return ret; } @@ -1179,14 +1190,13 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, struct perf_event_attr *attr, FILE *fp) { struct addr_location al; - int off, printed = 0; - - memset(&al, 0, sizeof(al)); + int off, printed = 0, ret = 0; + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) - return 0; + goto out; al.cpu = cpu; al.sym = NULL; @@ -1194,7 +1204,7 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, al.sym = map__find_symbol(al.map, al.addr); if (!al.sym) - return 0; + goto out; if (al.addr < al.sym->end) off = al.addr - al.sym->start; @@ -1209,7 +1219,10 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, printed += fprintf(fp, "\n"); *lastsym = al.sym; - return printed; + ret = printed; +out: + addr_location__exit(&al); + return ret; } static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, @@ -1371,6 +1384,7 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample, struct addr_location al; int printed = fprintf(fp, "%16" PRIx64, sample->addr); + addr_location__init(&al); if (!sample_addr_correlates_sym(attr)) goto out; @@ -1387,6 +1401,7 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample, if (PRINT_FIELD(DSO)) printed += map__fprintf_dsoname_dsoff(al.map, PRINT_FIELD(DSOFF), al.addr, fp); out: + addr_location__exit(&al); return printed; } @@ -2338,8 +2353,8 @@ static int process_sample_event(struct perf_tool *tool, int ret = 0; /* Set thread to NULL to indicate addr_al and al are not initialized */ - addr_al.thread = NULL; - al.thread = NULL; + addr_location__init(&al); + addr_location__init(&addr_al); ret = dlfilter__filter_event_early(dlfilter, event, sample, evsel, machine, &al, &addr_al); if (ret) { @@ -2405,8 +2420,8 @@ static int process_sample_event(struct perf_tool *tool, } out_put: - if (al.thread) - addr_location__put(&al); + addr_location__exit(&addr_al); + addr_location__exit(&al); return ret; } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 829d99fecfd0..19d4542ea18a 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -498,7 +498,6 @@ static const char *cat_backtrace(union perf_event *event, char *p = NULL; size_t p_len; u8 cpumode = PERF_RECORD_MISC_USER; - struct addr_location tal; struct ip_callchain *chain = sample->callchain; FILE *f = open_memstream(&p, &p_len); @@ -507,6 +506,7 @@ static const char *cat_backtrace(union perf_event *event, return NULL; } + addr_location__init(&al); if (!chain) goto exit; @@ -518,6 +518,7 @@ static const char *cat_backtrace(union perf_event *event, for (i = 0; i < chain->nr; i++) { u64 ip; + struct addr_location tal; if (callchain_param.order == ORDER_CALLEE) ip = chain->ips[i]; @@ -544,20 +545,22 @@ static const char *cat_backtrace(union perf_event *event, * Discard all. */ zfree(&p); - goto exit_put; + goto exit; } continue; } + addr_location__init(&tal); tal.filtered = 0; if (thread__find_symbol(al.thread, cpumode, ip, &tal)) fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name); else fprintf(f, "..... %016" PRIx64 "\n", ip); + + addr_location__exit(&tal); } -exit_put: - addr_location__put(&al); exit: + addr_location__exit(&al); fclose(f); return p; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9d3cbebb9b79..99010dfa5760 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -773,8 +773,9 @@ static void perf_event__process_sample(struct perf_tool *tool, if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) top->exact_samples++; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) - return; + goto out; if (top->stitch_lbr) thread__set_lbr_stitch_enable(al.thread, true); @@ -848,7 +849,8 @@ static void perf_event__process_sample(struct perf_tool *tool, mutex_unlock(&hists->lock); } - addr_location__put(&al); +out: + addr_location__exit(&al); } static void diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4c9bec39423b..6a1e75f06832 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2418,13 +2418,15 @@ static int trace__resolve_callchain(struct trace *trace, struct evsel *evsel, int max_stack = evsel->core.attr.sample_max_stack ? evsel->core.attr.sample_max_stack : trace->max_stack; - int err; + int err = -1; + addr_location__init(&al); if (machine__resolve(trace->host, &al, sample) < 0) - return -1; + goto out; err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack); - addr_location__put(&al); +out: + addr_location__exit(&al); return err; } @@ -2893,6 +2895,7 @@ static int trace__pgfault(struct trace *trace, int err = -1; int callchain_ret = 0; + addr_location__init(&al); thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); if (sample->callchain) { @@ -2953,6 +2956,7 @@ out: err = 0; out_put: thread__put(thread); + addr_location__exit(&al); return err; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9d8eefbebd48..2a7b2b6f5286 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -241,6 +241,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); + addr_location__init(&al); if (!thread__find_map(thread, cpumode, addr, &al) || !map__dso(al.map)) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); @@ -366,7 +367,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, } pr_debug("Bytes read match those read by objdump\n"); out: - map__put(al.map); + addr_location__exit(&al); return err; } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 62b9c6461ea6..71dacb0fec4d 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -8,8 +8,8 @@ #include "util/evsel.h" #include "util/evlist.h" #include "util/machine.h" -#include "util/thread.h" #include "util/parse-events.h" +#include "util/thread.h" #include "tests/tests.h" #include "tests/hists_common.h" #include @@ -84,6 +84,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) struct perf_sample sample = { .period = 1000, }; size_t i; + addr_location__init(&al); for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { struct hist_entry_iter iter = { .evsel = evsel, @@ -107,20 +108,22 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { - addr_location__put(&al); goto out; } - fake_samples[i].thread = al.thread; + thread__put(fake_samples[i].thread); + fake_samples[i].thread = thread__get(al.thread); map__put(fake_samples[i].map); - fake_samples[i].map = al.map; + fake_samples[i].map = map__get(al.map); fake_samples[i].sym = al.sym; } + addr_location__exit(&al); return TEST_OK; out: pr_debug("Not enough memory for adding a hist entry\n"); + addr_location__exit(&al); return TEST_FAIL; } @@ -152,8 +155,10 @@ static void put_fake_samples(void) { size_t i; - for (i = 0; i < ARRAY_SIZE(fake_samples); i++) - map__put(fake_samples[i].map); + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { + map__zput(fake_samples[i].map); + thread__zput(fake_samples[i].thread); + } } typedef int (*test_fn_t)(struct evsel *, struct machine *); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 98eff5935a1c..4b2e4f2fbe48 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -8,6 +8,7 @@ #include "util/evlist.h" #include "util/machine.h" #include "util/parse-events.h" +#include "util/thread.h" #include "tests/tests.h" #include "tests/hists_common.h" #include @@ -53,6 +54,7 @@ static int add_hist_entries(struct evlist *evlist, struct perf_sample sample = { .period = 100, }; size_t i; + addr_location__init(&al); /* * each evsel will have 10 samples but the 4th sample * (perf [perf] main) will be collapsed to an existing entry @@ -84,21 +86,22 @@ static int add_hist_entries(struct evlist *evlist, al.socket = fake_samples[i].socket; if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { - addr_location__put(&al); goto out; } - fake_samples[i].thread = al.thread; + thread__put(fake_samples[i].thread); + fake_samples[i].thread = thread__get(al.thread); map__put(fake_samples[i].map); - fake_samples[i].map = al.map; + fake_samples[i].map = map__get(al.map); fake_samples[i].sym = al.sym; } } - + addr_location__exit(&al); return 0; out: pr_debug("Not enough memory for adding a hist entry\n"); + addr_location__exit(&al); return TEST_FAIL; } diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 141e2972e34f..12bad8840699 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -8,6 +8,7 @@ #include "machine.h" #include "map.h" #include "parse-events.h" +#include "thread.h" #include "hists_common.h" #include "util/mmap.h" #include @@ -70,6 +71,7 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) struct perf_sample sample = { .period = 1, .weight = 1, }; size_t i = 0, k; + addr_location__init(&al); /* * each evsel will have 10 samples - 5 common and 5 distinct. * However the second evsel also has a collapsed entry for @@ -90,13 +92,13 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) he = hists__add_entry(hists, &al, NULL, NULL, NULL, NULL, &sample, true); if (he == NULL) { - addr_location__put(&al); goto out; } - fake_common_samples[k].thread = al.thread; + thread__put(fake_common_samples[k].thread); + fake_common_samples[k].thread = thread__get(al.thread); map__put(fake_common_samples[k].map); - fake_common_samples[k].map = al.map; + fake_common_samples[k].map = map__get(al.map); fake_common_samples[k].sym = al.sym; } @@ -110,20 +112,22 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) he = hists__add_entry(hists, &al, NULL, NULL, NULL, NULL, &sample, true); if (he == NULL) { - addr_location__put(&al); goto out; } - fake_samples[i][k].thread = al.thread; - fake_samples[i][k].map = al.map; + thread__put(fake_samples[i][k].thread); + fake_samples[i][k].thread = thread__get(al.thread); + map__put(fake_samples[i][k].map); + fake_samples[i][k].map = map__get(al.map); fake_samples[i][k].sym = al.sym; } i++; } + addr_location__exit(&al); return 0; - out: + addr_location__exit(&al); pr_debug("Not enough memory for adding a hist entry\n"); return -1; } diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index cd2094c13e1e..ba1cccf57049 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -54,6 +54,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) struct perf_sample sample = { .period = 100, }; size_t i; + addr_location__init(&al); for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { struct hist_entry_iter iter = { .evsel = evsel, @@ -73,20 +74,21 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { - addr_location__put(&al); goto out; } fake_samples[i].thread = al.thread; map__put(fake_samples[i].map); - fake_samples[i].map = al.map; + fake_samples[i].map = map__get(al.map); fake_samples[i].sym = al.sym; } + addr_location__exit(&al); return TEST_OK; out: pr_debug("Not enough memory for adding a hist entry\n"); + addr_location__exit(&al); return TEST_FAIL; } @@ -118,8 +120,10 @@ static void put_fake_samples(void) { size_t i; - for (i = 0; i < ARRAY_SIZE(fake_samples); i++) + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { map__put(fake_samples[i].map); + fake_samples[i].map = NULL; + } } typedef int (*test_fn_t)(struct evsel *, struct machine *); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 898eda55b7a8..3891a2a3b46f 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -187,6 +187,7 @@ static int mmap_events(synth_cb synth) struct addr_location al; struct thread *thread; + addr_location__init(&al); thread = machine__findnew_thread(machine, getpid(), td->tid); pr_debug("looking for map %p\n", td->map); @@ -199,11 +200,12 @@ static int mmap_events(synth_cb synth) if (!al.map) { pr_debug("failed, couldn't find map\n"); err = -1; + addr_location__exit(&al); break; } pr_debug("map %p, addr %" PRIx64 "\n", al.map, map__start(al.map)); - map__put(al.map); + addr_location__exit(&al); } machine__delete_threads(machine); diff --git a/tools/perf/util/addr_location.c b/tools/perf/util/addr_location.c index c73fc2aa236c..51825ef8c0ab 100644 --- a/tools/perf/util/addr_location.c +++ b/tools/perf/util/addr_location.c @@ -1,16 +1,44 @@ // SPDX-License-Identifier: GPL-2.0 #include "addr_location.h" #include "map.h" +#include "maps.h" #include "thread.h" +void addr_location__init(struct addr_location *al) +{ + al->thread = NULL; + al->maps = NULL; + al->map = NULL; + al->sym = NULL; + al->srcline = NULL; + al->addr = 0; + al->level = 0; + al->filtered = 0; + al->cpumode = 0; + al->cpu = 0; + al->socket = 0; +} + /* * The preprocess_sample method will return with reference counts for the * in it, when done using (and perhaps getting ref counts if needing to * keep a pointer to one of those entries) it must be paired with * addr_location__put(), so that the refcounts can be decremented. */ -void addr_location__put(struct addr_location *al) +void addr_location__exit(struct addr_location *al) { map__zput(al->map); thread__zput(al->thread); + maps__zput(al->maps); +} + +void addr_location__copy(struct addr_location *dst, struct addr_location *src) +{ + thread__put(dst->thread); + maps__put(dst->maps); + map__put(dst->map); + *dst = *src; + dst->thread = thread__get(src->thread); + dst->maps = maps__get(src->maps); + dst->map = map__get(src->map); } diff --git a/tools/perf/util/addr_location.h b/tools/perf/util/addr_location.h index 7dfa7417c0fe..d8ac0428dff2 100644 --- a/tools/perf/util/addr_location.h +++ b/tools/perf/util/addr_location.h @@ -23,6 +23,9 @@ struct addr_location { s32 socket; }; -void addr_location__put(struct addr_location *al); +void addr_location__init(struct addr_location *al); +void addr_location__exit(struct addr_location *al); + +void addr_location__copy(struct addr_location *dst, struct addr_location *src); #endif /* __PERF_ADDR_LOCATION */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 06a8cd88cbef..36728222a5b4 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -58,9 +58,11 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } + addr_location__init(&al); if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) map__dso(al.map)->hit = 1; + addr_location__exit(&al); thread__put(thread); return 0; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index b550c7393155..416f2ddc3895 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -910,33 +910,35 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, struct addr_location al; struct dso *dso; struct cs_etm_traceid_queue *tidq; + int ret = 0; if (!etmq) return 0; + addr_location__init(&al); machine = etmq->etm->machine; cpumode = cs_etm__cpu_mode(etmq, address); tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id); if (!tidq) - return 0; + goto out; thread = tidq->thread; if (!thread) { if (cpumode != PERF_RECORD_MISC_KERNEL) - return 0; + goto out; thread = etmq->etm->unknown_thread; } if (!thread__find_map(thread, cpumode, address, &al)) - return 0; + goto out; dso = map__dso(al.map); if (!dso) - return 0; + goto out; if (dso->data.status == DSO_DATA_STATUS_ERROR && dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) - return 0; + goto out; offset = map__map_ip(al.map, address); @@ -953,10 +955,12 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, dso->long_name ? dso->long_name : "Unknown"); dso->auxtrace_warned = true; } - return 0; + goto out; } - - return len; + ret = len; +out: + addr_location__exit(&al); + return ret; } static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c index 291591e303cd..5bb3c2ba95ca 100644 --- a/tools/perf/util/data-convert-json.c +++ b/tools/perf/util/data-convert-json.c @@ -154,12 +154,14 @@ static int process_sample_event(struct perf_tool *tool, { struct convert_json *c = container_of(tool, struct convert_json, tool); FILE *out = c->out; - struct addr_location al, tal; + struct addr_location al; u64 sample_type = __evlist__combined_sample_type(evsel->evlist); u8 cpumode = PERF_RECORD_MISC_USER; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_err("Sample resolution failed!\n"); + addr_location__exit(&al); return -1; } @@ -190,6 +192,7 @@ static int process_sample_event(struct perf_tool *tool, for (i = 0; i < sample->callchain->nr; ++i) { u64 ip = sample->callchain->ips[i]; + struct addr_location tal; if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -215,8 +218,10 @@ static int process_sample_event(struct perf_tool *tool, else fputc(',', out); + addr_location__init(&tal); ok = thread__find_symbol(al.thread, cpumode, ip, &tal); output_sample_callchain_entry(tool, ip, ok ? &tal : NULL); + addr_location__exit(&tal); } } else { output_sample_callchain_entry(tool, sample->ip, &al); @@ -245,6 +250,7 @@ static int process_sample_event(struct perf_tool *tool, } #endif output_json_format(out, false, 2, "}"); + addr_location__exit(&al); return 0; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 751fd53bfd93..6184696dc266 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -239,16 +239,17 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, struct addr_location al; u64 dso_db_id = 0, sym_db_id = 0, offset = 0; - memset(&al, 0, sizeof(al)); node = callchain_cursor_current(&callchain_cursor); if (!node) break; + /* * Handle export of symbol and dso for this node by * constructing an addr_location struct and then passing it to * db_ids_from_al() to perform the export. */ + addr_location__init(&al); al.sym = node->ms.sym; al.map = node->ms.map; al.maps = thread__maps(thread); @@ -265,6 +266,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, kernel_start); callchain_cursor_advance(&callchain_cursor); + addr_location__exit(&al); } /* Reset the callchain order to its prior value. */ diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 8016f21dc0b8..46f74b2344db 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -258,6 +258,7 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) struct addr_location a; struct map *map; u64 offset; + __s32 ret; if (!d->ctx_valid) return -1; @@ -272,16 +273,22 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) machine__kernel_ip(d->machine, ip) == machine__kernel_ip(d->machine, d->sample->ip)) goto have_map; + addr_location__init(&a); thread__find_map_fb(al->thread, d->sample->cpumode, ip, &a); - if (!a.map) - return -1; + if (!a.map) { + ret = -1; + goto out; + } map = a.map; have_map: offset = map__map_ip(map, ip); if (ip + len >= map__end(map)) len = map__end(map) - ip; - return dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); + ret = dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); +out: + addr_location__exit(&a); + return ret; } static const struct perf_dlfilter_fns perf_dlfilter_fns = { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6ee23145ee7e..2fcfba38fc48 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -486,6 +486,7 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma if (machine) { struct addr_location al; + addr_location__init(&al); al.map = map__get(maps__find(machine__kernel_maps(machine), tp->addr)); if (al.map && map__load(al.map) >= 0) { al.addr = map__map_ip(al.map, tp->addr); @@ -493,7 +494,7 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma if (al.sym) ret += symbol__fprintf_symname_offs(al.sym, &al, fp); } - map__put(al.map); + addr_location__exit(&al); } ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len); old = true; @@ -577,8 +578,10 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct machine *machine = maps__machine(maps); bool load_map = false; - al->maps = maps; - al->thread = thread; + maps__zput(al->maps); + map__zput(al->map); + thread__zput(al->thread); + al->addr = addr; al->cpumode = cpumode; al->filtered = 0; @@ -590,13 +593,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - al->maps = maps = machine__kernel_maps(machine); + maps = machine__kernel_maps(machine); load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - al->maps = maps = machine__kernel_maps(machine); + maps = machine__kernel_maps(machine); load_map = true; } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { al->level = 'u'; @@ -615,7 +618,8 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } - + al->maps = maps__get(maps); + al->thread = thread__get(thread); al->map = map__get(maps__find(maps, al->addr)); if (al->map != NULL) { /* diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index a1655fd7ed9b..cf45ca0e768f 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -128,8 +128,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, bool first = true; if (sample->callchain) { - struct addr_location node_al; - callchain_cursor_commit(cursor); while (1) { @@ -159,9 +157,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); if (print_sym) { + struct addr_location node_al; + + addr_location__init(&node_al); printed += fprintf(fp, " "); node_al.addr = addr; - node_al.map = map; + node_al.map = map__get(map); if (print_symoffset) { printed += __symbol__fprintf_symname_offs(sym, &node_al, @@ -171,6 +172,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, printed += __symbol__fprintf_symname(sym, &node_al, print_unknown_as_addr, fp); } + addr_location__exit(&node_al); } if (print_dso && (!sym || !sym->inlined)) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 4bc3affbe891..a4c1b617f6e4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -588,7 +588,7 @@ static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *entry, - struct addr_location *al, + const struct addr_location *al, bool sample_self) { struct rb_node **p; @@ -927,8 +927,10 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) if (iter->curr >= iter->total) return 0; - al->maps = bi[i].to.ms.maps; - al->map = bi[i].to.ms.map; + maps__put(al->maps); + al->maps = maps__get(bi[i].to.ms.maps); + map__put(al->map); + al->map = map__get(bi[i].to.ms.map); al->sym = bi[i].to.ms.sym; al->addr = bi[i].to.addr; return 1; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 45c7e7722916..783ce61c6d25 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -754,13 +754,15 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, struct addr_location al; unsigned char buf[INTEL_PT_INSN_BUF_SZ]; ssize_t len; - int x86_64; + int x86_64, ret = 0; u8 cpumode; u64 offset, start_offset, start_ip; u64 insn_cnt = 0; bool one_map = true; bool nr; + + addr_location__init(&al); intel_pt_insn->length = 0; if (to_ip && *ip == to_ip) @@ -773,19 +775,22 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, if (ptq->pt->have_guest_sideband) { if (!ptq->guest_machine || ptq->guest_machine_pid != ptq->pid) { intel_pt_log("ERROR: guest sideband but no guest machine\n"); - return -EINVAL; + ret = -EINVAL; + goto out_ret; } } else if ((!symbol_conf.guest_code && cpumode != PERF_RECORD_MISC_GUEST_KERNEL) || intel_pt_get_guest(ptq)) { intel_pt_log("ERROR: no guest machine\n"); - return -EINVAL; + ret = -EINVAL; + goto out_ret; } machine = ptq->guest_machine; thread = ptq->guest_thread; if (!thread) { if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL) { intel_pt_log("ERROR: no guest thread\n"); - return -EINVAL; + ret = -EINVAL; + goto out_ret; } thread = ptq->unknown_guest_thread; } @@ -794,7 +799,8 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, if (!thread) { if (cpumode != PERF_RECORD_MISC_KERNEL) { intel_pt_log("ERROR: no thread\n"); - return -EINVAL; + ret = -EINVAL; + goto out_ret; } thread = ptq->pt->unknown_thread; } @@ -808,13 +814,17 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, intel_pt_log("ERROR: thread has no dso for %#" PRIx64 "\n", *ip); else intel_pt_log("ERROR: thread has no map for %#" PRIx64 "\n", *ip); - return -EINVAL; + addr_location__exit(&al); + ret = -EINVAL; + goto out_ret; } dso = map__dso(al.map); if (dso->data.status == DSO_DATA_STATUS_ERROR && - dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) - return -ENOENT; + dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) { + ret = -ENOENT; + goto out_ret; + } offset = map__map_ip(al.map, *ip); @@ -833,7 +843,8 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, intel_pt_insn->rel = e->rel; memcpy(intel_pt_insn->buf, e->insn, INTEL_PT_INSN_BUF_SZ); intel_pt_log_insn_no_data(intel_pt_insn, *ip); - return 0; + ret = 0; + goto out_ret; } } @@ -854,11 +865,14 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, offset); if (intel_pt_enable_logging) dso__fprintf(dso, intel_pt_log_fp()); - return -EINVAL; + ret = -EINVAL; + goto out_ret; } - if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn)) - return -EINVAL; + if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn)) { + ret = -EINVAL; + goto out_ret; + } intel_pt_log_insn(intel_pt_insn, *ip); @@ -909,17 +923,20 @@ out: e = intel_pt_cache_lookup(map__dso(al.map), machine, start_offset); if (e) - return 0; + goto out_ret; } /* Ignore cache errors */ intel_pt_cache_add(map__dso(al.map), machine, start_offset, insn_cnt, *ip - start_ip, intel_pt_insn); - return 0; +out_ret: + addr_location__exit(&al); + return ret; out_no_cache: *insn_cnt_ptr = insn_cnt; + addr_location__exit(&al); return 0; } @@ -968,6 +985,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) struct addr_location al; u8 cpumode; u64 offset; + int res; if (ptq->state->to_nr) { if (intel_pt_guest_kernel_ip(ip)) @@ -984,12 +1002,15 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread) return -EINVAL; + addr_location__init(&al); if (!thread__find_map(thread, cpumode, ip, &al) || !map__dso(al.map)) return -EINVAL; offset = map__map_ip(al.map, ip); - return intel_pt_match_pgd_ip(ptq->pt, ip, offset, map__dso(al.map)->long_name); + res = intel_pt_match_pgd_ip(ptq->pt, ip, offset, map__dso(al.map)->long_name); + addr_location__exit(&al); + return res; } static bool intel_pt_pgd_ip(uint64_t ip, void *data) @@ -3372,20 +3393,22 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) /* Assume text poke begins in a basic block no more than 4096 bytes */ int cnt = 4096 + event->text_poke.new_len; struct thread *thread = pt->unknown_thread; - struct addr_location al = { .map = NULL }; + struct addr_location al; struct machine *machine = pt->machine; struct intel_pt_cache_entry *e; u64 offset; + int ret = 0; + addr_location__init(&al); if (!event->text_poke.new_len) - return 0; + goto out; for (; cnt; cnt--, addr--) { struct dso *dso; if (intel_pt_find_map(thread, cpumode, addr, &al)) { if (addr < event->text_poke.addr) - return 0; + goto out; continue; } @@ -3406,15 +3429,16 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) * branch instruction before the text poke address. */ if (e->branch != INTEL_PT_BR_NO_BRANCH) - return 0; + goto out; } else { intel_pt_cache_invalidate(dso, machine, offset); intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n", dso->long_name, addr); } } - - return 0; +out: + addr_location__exit(&al); + return ret; } static int intel_pt_process_event(struct perf_session *session, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8972c852d3bd..9fcf357a4d53 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2221,7 +2221,7 @@ static void ip__resolve_ams(struct thread *thread, { struct addr_location al; - memset(&al, 0, sizeof(al)); + addr_location__init(&al); /* * We cannot use the header.misc hint to determine whether a * branch stack address is user, kernel, guest, hypervisor. @@ -2234,11 +2234,12 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; ams->al_level = al.level; - ams->ms.maps = al.maps; + ams->ms.maps = maps__get(al.maps); ams->ms.sym = al.sym; - ams->ms.map = al.map; + ams->ms.map = map__get(al.map); ams->phys_addr = 0; ams->data_page_size = 0; + addr_location__exit(&al); } static void ip__resolve_data(struct thread *thread, @@ -2247,18 +2248,19 @@ static void ip__resolve_data(struct thread *thread, { struct addr_location al; - memset(&al, 0, sizeof(al)); + addr_location__init(&al); thread__find_symbol(thread, m, addr, &al); ams->addr = addr; ams->al_addr = al.addr; ams->al_level = al.level; - ams->ms.maps = al.maps; + ams->ms.maps = maps__get(al.maps); ams->ms.sym = al.sym; - ams->ms.map = al.map; + ams->ms.map = map__get(al.map); ams->phys_addr = phys_addr; ams->data_page_size = daddr_page_size; + addr_location__exit(&al); } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -2319,10 +2321,11 @@ static int add_callchain_ip(struct thread *thread, { struct map_symbol ms; struct addr_location al; - int nr_loop_iter = 0, err; + int nr_loop_iter = 0, err = 0; u64 iter_cycles = 0; const char *srcline = NULL; + addr_location__init(&al); al.filtered = 0; al.sym = NULL; al.srcline = NULL; @@ -2348,9 +2351,10 @@ static int add_callchain_ip(struct thread *thread, * Discard all. */ callchain_cursor_reset(cursor); - return 1; + err = 1; + goto out; } - return 0; + goto out; } thread__find_symbol(thread, *cpumode, ip, &al); } @@ -2363,31 +2367,32 @@ static int add_callchain_ip(struct thread *thread, symbol__match_regex(al.sym, &ignore_callees_regex)) { /* Treat this symbol as the root, forgetting its callees. */ - *root_al = al; + addr_location__copy(root_al, &al); callchain_cursor_reset(cursor); } } if (symbol_conf.hide_unresolved && al.sym == NULL) - return 0; + goto out; if (iter) { nr_loop_iter = iter->nr_loop_iter; iter_cycles = iter->cycles; } - ms.maps = al.maps; - ms.map = al.map; + ms.maps = maps__get(al.maps); + ms.map = map__get(al.map); ms.sym = al.sym; if (!branch && append_inlines(cursor, &ms, ip) == 0) - return 0; + goto out; srcline = callchain_srcline(&ms, al.addr); err = callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, iter_cycles, branch_from, srcline); - map__put(al.map); +out: + addr_location__exit(&al); return err; } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index f3d262e871ac..d7c99028c6e6 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -469,9 +469,11 @@ static PyObject *python_process_callchain(struct perf_sample *sample, struct addr_location node_al; unsigned long offset; + addr_location__init(&node_al); node_al.addr = map__map_ip(map, node->ip); - node_al.map = map; + node_al.map = map__get(map); offset = get_offset(node->ms.sym, &node_al); + addr_location__exit(&node_al); pydict_set_item_string_decref( pyelem, "sym_off", @@ -539,6 +541,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "cycles", PyLong_FromUnsignedLongLong(entries[i].flags.cycles)); + addr_location__init(&al); thread__find_map_fb(thread, sample->cpumode, entries[i].from, &al); dsoname = get_dsoname(al.map); @@ -551,6 +554,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "to_dsoname", _PyUnicode_FromString(dsoname)); + addr_location__exit(&al); PyList_Append(pylist, pyelem); Py_DECREF(pyelem); } @@ -594,7 +598,6 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample, PyObject *pylist; u64 i; char bf[512]; - struct addr_location al; pylist = PyList_New(0); if (!pylist) @@ -605,7 +608,9 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample, for (i = 0; i < br->nr; i++) { PyObject *pyelem; + struct addr_location al; + addr_location__init(&al); pyelem = PyDict_New(); if (!pyelem) Py_FatalError("couldn't create Python dictionary"); @@ -644,6 +649,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample, PyList_Append(pylist, pyelem); Py_DECREF(pyelem); + addr_location__exit(&al); } exit: diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 9a1db3be6436..bee4ac1051ee 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -432,18 +432,25 @@ int thread__memcpy(struct thread *thread, struct machine *machine, if (machine__kernel_ip(machine, ip)) cpumode = PERF_RECORD_MISC_KERNEL; - if (!thread__find_map(thread, cpumode, ip, &al)) - return -1; + addr_location__init(&al); + if (!thread__find_map(thread, cpumode, ip, &al)) { + addr_location__exit(&al); + return -1; + } dso = map__dso(al.map); - if( !dso || dso->data.status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) + if (!dso || dso->data.status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) { + addr_location__exit(&al); return -1; + } offset = map__map_ip(al.map, ip); if (is64bit) *is64bit = dso->is_64_bit; + addr_location__exit(&al); + return dso__data_read_offset(dso, machine, offset, buf, len); } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 3723b5e31b2a..83eea968482e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -90,8 +90,12 @@ static int __report_module(struct addr_location *al, u64 ip, static int report_module(u64 ip, struct unwind_info *ui) { struct addr_location al; + int res; - return __report_module(&al, ip, ui); + addr_location__init(&al); + res = __report_module(&al, ip, ui); + addr_location__exit(&al); + return res; } /* @@ -104,8 +108,11 @@ static int entry(u64 ip, struct unwind_info *ui) struct unwind_entry *e = &ui->entries[ui->idx++]; struct addr_location al; - if (__report_module(&al, ip, ui)) + addr_location__init(&al); + if (__report_module(&al, ip, ui)) { + addr_location__exit(&al); return -1; + } e->ip = ip; e->ms.maps = al.maps; @@ -116,6 +123,7 @@ static int entry(u64 ip, struct unwind_info *ui) al.sym ? al.sym->name : "''", ip, al.map ? map__map_ip(al.map, ip) : (u64) 0); + addr_location__exit(&al); return 0; } @@ -136,17 +144,22 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, ssize_t size; struct dso *dso; + addr_location__init(&al); if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); - return -1; + goto out_fail; } dso = map__dso(al.map); if (!dso) - return -1; + goto out_fail; size = dso__data_read_addr(dso, al.map, ui->machine, addr, (u8 *) data, sizeof(*data)); + addr_location__exit(&al); return !(size == sizeof(*data)); +out_fail: + addr_location__exit(&al); + return -1; } static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result, diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 11f3fc95aa11..36bf5100bad2 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -416,7 +416,12 @@ 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; - return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); + struct map *ret; + + addr_location__init(&al); + ret = thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); + addr_location__exit(&al); + return ret; } static int @@ -631,7 +636,9 @@ static int entry(u64 ip, struct thread *thread, { struct unwind_entry e; struct addr_location al; + int ret; + addr_location__init(&al); e.ms.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); e.ip = ip; e.ms.map = al.map; @@ -642,7 +649,9 @@ static int entry(u64 ip, struct thread *thread, ip, al.map ? map__map_ip(al.map, ip) : (u64) 0); - return cb(&e, arg); + ret = cb(&e, arg); + addr_location__exit(&al); + return ret; } static void display_error(int err) -- cgit From 8ab12a2038e36beda4062a8e7562a8cfe9655553 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 8 Jun 2023 16:28:21 -0700 Subject: perf callchain: Use pthread keys for tls callchain_cursor Pthread keys are more portable than __thread and allow the association of a destructor with the key. Use the destructor to clean up TLS callchain cursors to aid understanding memory leaks. Committer notes: Had to fixup a series of unconverted places and also check for the return of get_tls_callchain_cursor() as it may fail and return NULL. In that unlikely case we now either print something to a file, if the caller was expecting to print a callchain, or return an error code to state that resolving the callchain isn't possible. In some cases this was made easier because thread__resolve_callchain() already can fail for other reasons, so this new one (cursor == NULL) can be added and the callers don't have to explicitely check for this new condition. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ali Saidi Cc: Andi Kleen Cc: Athira Rajeev Cc: Brian Robbins Cc: Changbin Du Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song Cc: German Gomez Cc: Ingo Molnar Cc: Ivan Babrou Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Liam Howlett Cc: Mark Rutland Cc: Miguel Ojeda Cc: Mike Leach Cc: Namhyung Kim Cc: Naveen N. Rao Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Suzuki Poulouse Cc: Wenyu Liu Cc: Will Deacon Cc: Yang Jihong Cc: Ye Xingchen Cc: Yuan Can Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-25-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 4 +- tools/perf/builtin-kmem.c | 14 +++++-- tools/perf/builtin-kwork.c | 12 +++++- tools/perf/builtin-lock.c | 7 +++- tools/perf/builtin-sched.c | 14 +++++-- tools/perf/builtin-script.c | 24 ++++++----- tools/perf/builtin-trace.c | 20 ++++++---- tools/perf/util/callchain.c | 45 ++++++++++++++++++++- tools/perf/util/callchain.h | 8 ++-- tools/perf/util/db-export.c | 10 +++-- tools/perf/util/evsel_fprintf.c | 3 ++ tools/perf/util/hist.c | 46 +++++++++++++++------- tools/perf/util/machine.c | 3 ++ .../perf/util/scripting-engines/trace-event-perl.c | 11 ++++-- .../util/scripting-engines/trace-event-python.c | 10 +++-- 15 files changed, 170 insertions(+), 61 deletions(-) (limited to 'tools/perf/util/db-export.c') diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 530a44a59f41..a4cf9de7a7b5 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -284,6 +284,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct hist_entry *he; struct addr_location al; struct mem_info *mi, *mi_dup; + struct callchain_cursor *cursor; int ret; addr_location__init(&al); @@ -297,7 +298,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, if (c2c.stitch_lbr) thread__set_lbr_stitch_enable(al.thread, true); - ret = sample__resolve_callchain(sample, &callchain_cursor, NULL, + cursor = get_tls_callchain_cursor(); + ret = sample__resolve_callchain(sample, cursor, NULL, evsel, &al, sysctl_perf_event_max_stack); if (ret) goto out; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 96a6611e4e53..9714327fd0ea 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -399,6 +399,7 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) struct addr_location al; struct machine *machine = &kmem_session->machines.host; struct callchain_cursor_node *node; + struct callchain_cursor *cursor; u64 result = sample->ip; addr_location__init(&al); @@ -408,14 +409,19 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) } al.thread = machine__findnew_thread(machine, sample->pid, sample->tid); - sample__resolve_callchain(sample, &callchain_cursor, NULL, evsel, &al, 16); - callchain_cursor_commit(&callchain_cursor); + cursor = get_tls_callchain_cursor(); + if (cursor == NULL) + goto out; + + sample__resolve_callchain(sample, cursor, NULL, evsel, &al, 16); + + callchain_cursor_commit(cursor); while (true) { struct alloc_func key, *caller; u64 addr; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(cursor); if (node == NULL) break; @@ -434,7 +440,7 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) } else pr_debug3("skipping alloc function: %s\n", caller->name); - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(cursor); } pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip); diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index 2d80aef4eccc..14bf7a8429e7 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -589,7 +589,7 @@ static void timehist_save_callchain(struct perf_kwork *kwork, struct symbol *sym; struct thread *thread; struct callchain_cursor_node *node; - struct callchain_cursor *cursor = &callchain_cursor; + struct callchain_cursor *cursor; if (!kwork->show_callchain || sample->callchain == NULL) return; @@ -601,6 +601,8 @@ static void timehist_save_callchain(struct perf_kwork *kwork, return; } + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, kwork->max_stack + 2) != 0) { pr_debug("Failed to resolve callchain, skipping\n"); @@ -686,12 +688,18 @@ static void timehist_print_event(struct perf_kwork *kwork, * callchain */ if (kwork->show_callchain) { + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + if (cursor == NULL) + return; + printf(" "); + sample__fprintf_sym(sample, al, 0, EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE | EVSEL__PRINT_CALLCHAIN_ARROW | EVSEL__PRINT_SKIP_IGNORED, - &callchain_cursor, symbol_conf.bt_stop_list, + cursor, symbol_conf.bt_stop_list, stdout); } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fc8356bd6e3a..8b505e1e5002 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -911,7 +911,7 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl char *buf, int size) { struct thread *thread; - struct callchain_cursor *cursor = &callchain_cursor; + struct callchain_cursor *cursor; struct machine *machine = &session->machines.host; struct symbol *sym; int skip = 0; @@ -925,6 +925,8 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl if (thread == NULL) return -1; + cursor = get_tls_callchain_cursor(); + /* use caller function name from the callchain */ ret = thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, max_stack_depth); @@ -962,7 +964,7 @@ next: static u64 callchain_id(struct evsel *evsel, struct perf_sample *sample) { - struct callchain_cursor *cursor = &callchain_cursor; + struct callchain_cursor *cursor; struct machine *machine = &session->machines.host; struct thread *thread; u64 hash = 0; @@ -973,6 +975,7 @@ static u64 callchain_id(struct evsel *evsel, struct perf_sample *sample) if (thread == NULL) return -1; + cursor = get_tls_callchain_cursor(); /* use caller function name from the callchain */ ret = thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, max_stack_depth); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index cd79068200e5..c9ddf73689cd 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2111,7 +2111,7 @@ static void timehist_print_sample(struct perf_sched *sched, EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE | EVSEL__PRINT_CALLCHAIN_ARROW | EVSEL__PRINT_SKIP_IGNORED, - &callchain_cursor, symbol_conf.bt_stop_list, stdout); + get_tls_callchain_cursor(), symbol_conf.bt_stop_list, stdout); out: printf("\n"); @@ -2196,7 +2196,7 @@ static void save_task_callchain(struct perf_sched *sched, struct evsel *evsel, struct machine *machine) { - struct callchain_cursor *cursor = &callchain_cursor; + struct callchain_cursor *cursor; struct thread *thread; /* want main thread for process - has maps */ @@ -2209,6 +2209,8 @@ static void save_task_callchain(struct perf_sched *sched, if (!sched->show_callchain || sample->callchain == NULL) return; + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { if (verbose > 0) @@ -2338,10 +2340,16 @@ static void save_idle_callchain(struct perf_sched *sched, struct idle_thread_runtime *itr, struct perf_sample *sample) { + struct callchain_cursor *cursor; + if (!sched->show_callchain || sample->callchain == NULL) return; - callchain_cursor__copy(&itr->cursor, &callchain_cursor); + cursor = get_tls_callchain_cursor(); + if (cursor == NULL) + return; + + callchain_cursor__copy(&itr->cursor, cursor); } static struct thread *timehist_get_thread(struct perf_sched *sched, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 784d478c2e05..e3f435e6a7d0 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1557,11 +1557,13 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; - if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; - + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) + cursor = NULL; + } if (cursor == NULL) { printed += fprintf(fp, " "); if (print_opts & EVSEL__PRINT_SRCLINE) { @@ -2203,11 +2205,13 @@ static void process_event(struct perf_script *script, if (script->stitch_lbr) thread__set_lbr_stitch_enable(al->thread, true); - if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; - + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) + cursor = NULL; + } fputc(cursor ? '\n' : ' ', fp); sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, symbol_conf.bt_stop_list, fp); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a1e75f06832..6e73d0e95715 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2437,7 +2437,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam EVSEL__PRINT_DSO | EVSEL__PRINT_UNKNOWN_AS_ADDR; - return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, symbol_conf.bt_stop_list, trace->output); + return sample__fprintf_callchain(sample, 38, print_opts, get_tls_callchain_cursor(), symbol_conf.bt_stop_list, trace->output); } static const char *errno_to_name(struct evsel *evsel, int err) @@ -2491,9 +2491,11 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel, goto out; if (sample->callchain) { - callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor); if (callchain_ret == 0) { - if (callchain_cursor.nr < trace->min_stack) + if (cursor->nr < trace->min_stack) goto out; callchain_ret = 1; } @@ -2795,9 +2797,11 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel, thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); if (sample->callchain) { - callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor); if (callchain_ret == 0) { - if (callchain_cursor.nr < trace->min_stack) + if (cursor->nr < trace->min_stack) goto out; callchain_ret = 1; } @@ -2899,9 +2903,11 @@ static int trace__pgfault(struct trace *trace, thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); if (sample->callchain) { - callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor); if (callchain_ret == 0) { - if (callchain_cursor.nr < trace->min_stack) + if (cursor->nr < trace->min_stack) goto out_put; callchain_ret = 1; } diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 909f62b3b266..aee937d14fbb 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -58,7 +58,8 @@ struct callchain_param callchain_param_default = { CALLCHAIN_PARAM_DEFAULT }; -__thread struct callchain_cursor callchain_cursor; +/* Used for thread-local struct callchain_cursor. */ +static pthread_key_t callchain_cursor; int parse_callchain_record_opt(const char *arg, struct callchain_param *param) { @@ -986,6 +987,9 @@ int callchain_append(struct callchain_root *root, struct callchain_cursor *cursor, u64 period) { + if (cursor == NULL) + return -1; + if (!cursor->nr) return 0; @@ -1116,7 +1120,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp if ((!symbol_conf.use_callchain || sample->callchain == NULL) && !symbol_conf.show_branchflag_count) return 0; - return callchain_append(he->callchain, &callchain_cursor, sample->period); + return callchain_append(he->callchain, get_tls_callchain_cursor(), sample->period); } int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, @@ -1570,6 +1574,43 @@ out: return -ENOMEM; } +static void callchain_cursor__delete(void *vcursor) +{ + struct callchain_cursor *cursor = vcursor; + struct callchain_cursor_node *node, *next; + + callchain_cursor_reset(cursor); + for (node = cursor->first; node != NULL; node = next) { + next = node->next; + free(node); + } + free(cursor); +} + +static void init_callchain_cursor_key(void) +{ + if (pthread_key_create(&callchain_cursor, callchain_cursor__delete)) { + pr_err("callchain cursor creation failed"); + abort(); + } +} + +struct callchain_cursor *get_tls_callchain_cursor(void) +{ + static pthread_once_t once_control = PTHREAD_ONCE_INIT; + struct callchain_cursor *cursor; + + pthread_once(&once_control, init_callchain_cursor_key); + cursor = pthread_getspecific(callchain_cursor); + if (!cursor) { + cursor = zalloc(sizeof(*cursor)); + if (!cursor) + pr_debug3("%s: not enough memory\n", __func__); + pthread_setspecific(callchain_cursor, cursor); + } + return cursor; +} + int callchain_cursor__copy(struct callchain_cursor *dst, struct callchain_cursor *src) { diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index d95615daed73..d2618a47deca 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -168,8 +168,6 @@ struct callchain_cursor { struct callchain_cursor_node *curr; }; -extern __thread struct callchain_cursor callchain_cursor; - static inline void callchain_init(struct callchain_root *root) { INIT_LIST_HEAD(&root->node.val); @@ -211,6 +209,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, /* Close a cursor writing session. Initialize for the reader */ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) { + if (cursor == NULL) + return; cursor->curr = cursor->first; cursor->pos = 0; } @@ -219,7 +219,7 @@ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) static inline struct callchain_cursor_node * callchain_cursor_current(struct callchain_cursor *cursor) { - if (cursor->pos == cursor->nr) + if (cursor == NULL || cursor->pos == cursor->nr) return NULL; return cursor->curr; @@ -231,6 +231,8 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) cursor->pos++; } +struct callchain_cursor *get_tls_callchain_cursor(void); + int callchain_cursor__copy(struct callchain_cursor *dst, struct callchain_cursor *src); diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 6184696dc266..b9fb71ab7a73 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -215,6 +215,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, u64 kernel_start = machine__kernel_start(machine); struct call_path *current = &dbe->cpr->call_path; enum chain_order saved_order = callchain_param.order; + struct callchain_cursor *cursor; int err; if (!symbol_conf.use_callchain || !sample->callchain) @@ -226,13 +227,14 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, * the callchain starting with the root node and ending with the leaf. */ callchain_param.order = ORDER_CALLER; - err = thread__resolve_callchain(thread, &callchain_cursor, evsel, + cursor = get_tls_callchain_cursor(); + err = thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, PERF_MAX_STACK_DEPTH); if (err) { callchain_param.order = saved_order; return NULL; } - callchain_cursor_commit(&callchain_cursor); + callchain_cursor_commit(cursor); while (1) { struct callchain_cursor_node *node; @@ -240,7 +242,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, u64 dso_db_id = 0, sym_db_id = 0, offset = 0; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(cursor); if (!node) break; @@ -265,7 +267,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, al.sym, node->ip, kernel_start); - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(cursor); addr_location__exit(&al); } diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index cf45ca0e768f..8719b3cb5646 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -127,6 +127,9 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, char s = print_oneline ? ' ' : '\t'; bool first = true; + if (cursor == NULL) + return fprintf(fp, "%s", print_oneline ? "" : "\n"); + if (sample->callchain) { callchain_cursor_commit(cursor); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index fb218b3e8a7c..efaf7ac784fc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1029,15 +1029,19 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { struct hist_entry **he_cache; + struct callchain_cursor *cursor = get_tls_callchain_cursor(); - callchain_cursor_commit(&callchain_cursor); + if (cursor == NULL) + return -ENOMEM; + + callchain_cursor_commit(cursor); /* * This is for detecting cycles or recursions so that they're * cumulated only one time to prevent entries more than 100% * overhead. */ - he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1)); + he_cache = malloc(sizeof(*he_cache) * (cursor->nr + 1)); if (he_cache == NULL) return -ENOMEM; @@ -1072,7 +1076,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, * We need to re-initialize the cursor since callchain_append() * advanced the cursor to the end. */ - callchain_cursor_commit(&callchain_cursor); + callchain_cursor_commit(get_tls_callchain_cursor()); hists__inc_nr_samples(hists, he->filtered); @@ -1085,7 +1089,7 @@ iter_next_cumulative_entry(struct hist_entry_iter *iter, { struct callchain_cursor_node *node; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(get_tls_callchain_cursor()); if (node == NULL) return 0; @@ -1131,12 +1135,15 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .raw_size = sample->raw_size, }; int i; - struct callchain_cursor cursor; + struct callchain_cursor cursor, *tls_cursor = get_tls_callchain_cursor(); bool fast = hists__has(he_tmp.hists, sym); - callchain_cursor_snapshot(&cursor, &callchain_cursor); + if (tls_cursor == NULL) + return -ENOMEM; + + callchain_cursor_snapshot(&cursor, tls_cursor); - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(tls_cursor); /* * Check if there's duplicate entries in the callchain. @@ -1222,7 +1229,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, if (al) alm = map__get(al->map); - err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, + err = sample__resolve_callchain(iter->sample, get_tls_callchain_cursor(), &iter->parent, iter->evsel, al, max_stack_depth); if (err) { map__put(alm); @@ -1568,8 +1575,13 @@ static int hists__hierarchy_insert_entry(struct hists *hists, if (hist_entry__has_callchains(new_he) && symbol_conf.use_callchain) { - callchain_cursor_reset(&callchain_cursor); - if (callchain_merge(&callchain_cursor, + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + if (cursor == NULL) + return -1; + + callchain_cursor_reset(cursor); + if (callchain_merge(cursor, new_he->callchain, he->callchain) < 0) ret = -1; @@ -1610,11 +1622,15 @@ static int hists__collapse_insert_entry(struct hists *hists, he_stat__add_stat(iter->stat_acc, he->stat_acc); if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { - callchain_cursor_reset(&callchain_cursor); - if (callchain_merge(&callchain_cursor, - iter->callchain, - he->callchain) < 0) - ret = -1; + struct callchain_cursor *cursor = get_tls_callchain_cursor(); + + if (cursor != NULL) { + callchain_cursor_reset(cursor); + if (callchain_merge(cursor, iter->callchain, he->callchain) < 0) + ret = -1; + } else { + ret = 0; + } } hist_entry__delete(he); return ret; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index bdad4b8bf77d..4e62843d51b7 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -3180,6 +3180,9 @@ int thread__resolve_callchain(struct thread *thread, { int ret = 0; + if (cursor == NULL) + return -ENOMEM; + callchain_cursor_reset(cursor); if (callchain_param.order == ORDER_CALLEE) { diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 65b761d83a1f..603091317bed 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -260,6 +260,7 @@ static SV *perl_process_callchain(struct perf_sample *sample, struct evsel *evsel, struct addr_location *al) { + struct callchain_cursor *cursor; AV *list; list = newAV(); @@ -269,18 +270,20 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + cursor = get_tls_callchain_cursor(); + + if (thread__resolve_callchain(al->thread, cursor, evsel, sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } - callchain_cursor_commit(&callchain_cursor); + callchain_cursor_commit(cursor); while (1) { HV *elem; struct callchain_cursor_node *node; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(cursor); if (!node) break; @@ -328,7 +331,7 @@ static SV *perl_process_callchain(struct perf_sample *sample, } } - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(cursor); av_push(list, newRV_noinc((SV*)elem)); } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index d96e5c0fef45..59063ec98619 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -417,6 +417,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, struct addr_location *al) { PyObject *pylist; + struct callchain_cursor *cursor; pylist = PyList_New(0); if (!pylist) @@ -425,19 +426,20 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } - callchain_cursor_commit(&callchain_cursor); + callchain_cursor_commit(cursor); while (1) { PyObject *pyelem; struct callchain_cursor_node *node; - node = callchain_cursor_current(&callchain_cursor); + node = callchain_cursor_current(cursor); if (!node) break; @@ -493,7 +495,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, _PyUnicode_FromString(dsoname)); } - callchain_cursor_advance(&callchain_cursor); + callchain_cursor_advance(cursor); PyList_Append(pylist, pyelem); Py_DECREF(pyelem); } -- cgit