diff options
Diffstat (limited to 'tools/perf')
93 files changed, 1568 insertions, 565 deletions
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0ee6795d82cc..09df1c8a4ec9 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -863,8 +863,8 @@ ifndef NO_LIBPYTHON $(call QUIET_INSTALL, python-scripts) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \ - $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ - $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \ + $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ + $(INSTALL) scripts/python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \ $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' endif $(call QUIET_INSTALL, perf_completion-script) \ diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 93d679eaf1f4..20db635347e5 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -227,7 +227,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, * the DSO? */ if (al->sym != NULL) { - rb_erase(&al->sym->rb_node, + rb_erase_cached(&al->sym->rb_node, &al->map->dso->symbols); symbol__delete(al->sym); dso__reset_find_symbol_cache(al->map->dso); @@ -305,7 +305,7 @@ static void hists__find_annotations(struct hists *hists, struct perf_evsel *evsel, struct perf_annotate *ann) { - struct rb_node *nd = rb_first(&hists->entries), *next; + struct rb_node *nd = rb_first_cached(&hists->entries), *next; int key = K_RIGHT; while (nd) { diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index d340d2e42776..72ec0ae7d8ad 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2088,7 +2088,7 @@ static int resort_hitm_cb(struct hist_entry *he) static int hists__iterate_cb(struct hists *hists, hists__resort_cb_t cb) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_node *next = rb_first_cached(&hists->entries); int ret = 0; while (next) { @@ -2215,7 +2215,7 @@ static void print_pareto(FILE *out) if (WARN_ONCE(ret, "failed to setup sort entries\n")) return; - nd = rb_first(&c2c.hists.hists.entries); + nd = rb_first_cached(&c2c.hists.hists.entries); for (; nd; nd = rb_next(nd)) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); @@ -2283,7 +2283,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session) static void c2c_browser__update_nr_entries(struct hist_browser *hb) { u64 nr_entries = 0; - struct rb_node *nd = rb_first(&hb->hists->entries); + struct rb_node *nd = rb_first_cached(&hb->hists->entries); while (nd) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); @@ -2343,7 +2343,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) struct c2c_cacheline_browser *cl_browser; struct hist_browser *browser; int key = -1; - const char help[] = + static const char help[] = " ENTER Toggle callchains (if present) \n" " n Toggle Node details info \n" " s Toggle full length of symbol and source line columns \n" @@ -2424,7 +2424,7 @@ static int perf_c2c__hists_browse(struct hists *hists) { struct hist_browser *browser; int key = -1; - const char help[] = + static const char help[] = " d Display cacheline details \n" " ENTER Toggle callchains (if present) \n" " q Quit \n"; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 39db2ee32d48..751e1971456b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -429,7 +429,7 @@ get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt) static void hists__baseline_only(struct hists *hists) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; if (hists__has(hists, need_collapse)) @@ -437,13 +437,13 @@ static void hists__baseline_only(struct hists *hists) else root = hists->entries_in; - next = rb_first(root); + next = rb_first_cached(root); while (next != NULL) { struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); if (!hist_entry__next_pair(he)) { - rb_erase(&he->rb_node_in, root); + rb_erase_cached(&he->rb_node_in, root); hist_entry__delete(he); } } @@ -451,7 +451,7 @@ static void hists__baseline_only(struct hists *hists) static void hists__precompute(struct hists *hists) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; if (hists__has(hists, need_collapse)) @@ -459,7 +459,7 @@ static void hists__precompute(struct hists *hists) else root = hists->entries_in; - next = rb_first(root); + next = rb_first_cached(root); while (next != NULL) { struct hist_entry *he, *pair; struct data__file *d; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b63bca4b0c2a..088705c167bf 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -334,7 +334,7 @@ static int build_alloc_func_list(void) struct alloc_func *func; struct machine *machine = &kmem_session->machines.host; regex_t alloc_func_regex; - const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?"; + static const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?"; ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED); if (ret) { @@ -1924,7 +1924,7 @@ int cmd_kmem(int argc, const char **argv) NULL }; struct perf_session *session; - const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n"; + static const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n"; int ret = perf_config(kmem_config, NULL); if (ret) diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 99de91698de1..46d3c2deeb40 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -32,6 +32,7 @@ #include "perf.h" #include "builtin.h" +#include "namespaces.h" #include "util/util.h" #include "util/strlist.h" #include "util/strfilter.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 882285fb9f64..88ea11d57c6f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -41,6 +41,7 @@ #include "util/perf-hooks.h" #include "util/time-utils.h" #include "util/units.h" +#include "util/bpf-event.h" #include "asm/bug.h" #include <errno.h> @@ -1082,6 +1083,11 @@ static int record__synthesize(struct record *rec, bool tail) return err; } + err = perf_event__synthesize_bpf_events(tool, process_synthesized_event, + machine, opts); + if (err < 0) + pr_warning("Couldn't synthesize bpf events.\n"); + err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, process_synthesized_event, opts->sample_address, 1); @@ -1839,6 +1845,7 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), + OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"), OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, "Fail if the specified frequency can't be used"), OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 4958095be4fc..c9ceaf88759c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -753,7 +753,8 @@ static int tasks_print(struct report *rep, FILE *fp) for (i = 0; i < THREADS__TABLE_SIZE; i++) { struct threads *threads = &machine->threads[i]; - for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&threads->entries); nd; + nd = rb_next(nd)) { task = tasks + itask++; task->thread = rb_entry(nd, struct thread, rb_node); @@ -956,9 +957,9 @@ int cmd_report(int argc, const char **argv) int branch_mode = -1; bool branch_call_mode = false; #define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" - const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" - CALLCHAIN_REPORT_HELP - "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; + static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" + CALLCHAIN_REPORT_HELP + "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT; const char * const report_usage[] = { "perf report [<options>]", diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index cbf39dab19c1..640558e9352e 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -213,7 +213,7 @@ struct perf_sched { u64 all_runtime; u64 all_count; u64 cpu_last_switched[MAX_CPUS]; - struct rb_root atom_root, sorted_atom_root, merged_atom_root; + struct rb_root_cached atom_root, sorted_atom_root, merged_atom_root; struct list_head sort_list, cmp_pid; bool force; bool skip_merge; @@ -271,7 +271,7 @@ struct evsel_runtime { struct idle_thread_runtime { struct thread_runtime tr; struct thread *last_thread; - struct rb_root sorted_root; + struct rb_root_cached sorted_root; struct callchain_root callchain; struct callchain_cursor cursor; }; @@ -950,10 +950,10 @@ thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms * } static struct work_atoms * -thread_atoms_search(struct rb_root *root, struct thread *thread, +thread_atoms_search(struct rb_root_cached *root, struct thread *thread, struct list_head *sort_list) { - struct rb_node *node = root->rb_node; + struct rb_node *node = root->rb_root.rb_node; struct work_atoms key = { .thread = thread }; while (node) { @@ -976,10 +976,11 @@ thread_atoms_search(struct rb_root *root, struct thread *thread, } static void -__thread_latency_insert(struct rb_root *root, struct work_atoms *data, +__thread_latency_insert(struct rb_root_cached *root, struct work_atoms *data, struct list_head *sort_list) { - struct rb_node **new = &(root->rb_node), *parent = NULL; + struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL; + bool leftmost = true; while (*new) { struct work_atoms *this; @@ -992,12 +993,14 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data, if (cmp > 0) new = &((*new)->rb_left); - else + else { new = &((*new)->rb_right); + leftmost = false; + } } rb_link_node(&data->node, parent, new); - rb_insert_color(&data->node, root); + rb_insert_color_cached(&data->node, root, leftmost); } static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) @@ -1447,15 +1450,15 @@ static int sort_dimension__add(const char *tok, struct list_head *list) static void perf_sched__sort_lat(struct perf_sched *sched) { struct rb_node *node; - struct rb_root *root = &sched->atom_root; + struct rb_root_cached *root = &sched->atom_root; again: for (;;) { struct work_atoms *data; - node = rb_first(root); + node = rb_first_cached(root); if (!node) break; - rb_erase(node, root); + rb_erase_cached(node, root); data = rb_entry(node, struct work_atoms, node); __thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list); } @@ -2762,12 +2765,12 @@ static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node) return ret; } -static size_t timehist_print_idlehist_callchain(struct rb_root *root) +static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root) { size_t ret = 0; FILE *fp = stdout; struct callchain_node *chain; - struct rb_node *rb_node = rb_first(root); + struct rb_node *rb_node = rb_first_cached(root); printf(" %16s %8s %s\n", "Idle time (msec)", "Count", "Callchains"); printf(" %.16s %.8s %.50s\n", graph_dotted_line, graph_dotted_line, @@ -2868,7 +2871,7 @@ static void timehist_print_summary(struct perf_sched *sched, if (itr == NULL) continue; - callchain_param.sort(&itr->sorted_root, &itr->callchain, + callchain_param.sort(&itr->sorted_root.rb_root, &itr->callchain, 0, &callchain_param); printf(" CPU %2d:", i); @@ -3074,11 +3077,12 @@ static void print_bad_events(struct perf_sched *sched) } } -static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data) +static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *data) { - struct rb_node **new = &(root->rb_node), *parent = NULL; + struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL; struct work_atoms *this; const char *comm = thread__comm_str(data->thread), *this_comm; + bool leftmost = true; while (*new) { int cmp; @@ -3092,6 +3096,7 @@ static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data) new = &((*new)->rb_left); } else if (cmp < 0) { new = &((*new)->rb_right); + leftmost = false; } else { this->num_merged++; this->total_runtime += data->total_runtime; @@ -3109,7 +3114,7 @@ static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data) data->num_merged++; rb_link_node(&data->node, parent, new); - rb_insert_color(&data->node, root); + rb_insert_color_cached(&data->node, root, leftmost); } static void perf_sched__merge_lat(struct perf_sched *sched) @@ -3120,8 +3125,8 @@ static void perf_sched__merge_lat(struct perf_sched *sched) if (sched->skip_merge) return; - while ((node = rb_first(&sched->atom_root))) { - rb_erase(node, &sched->atom_root); + while ((node = rb_first_cached(&sched->atom_root))) { + rb_erase_cached(node, &sched->atom_root); data = rb_entry(node, struct work_atoms, node); __merge_work_atoms(&sched->merged_atom_root, data); } @@ -3143,7 +3148,7 @@ static int perf_sched__lat(struct perf_sched *sched) printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); printf(" -----------------------------------------------------------------------------------------------------------------\n"); - next = rb_first(&sched->sorted_atom_root); + next = rb_first_cached(&sched->sorted_atom_root); while (next) { struct work_atoms *work_list; @@ -3336,7 +3341,7 @@ static int __cmd_record(int argc, const char **argv) int cmd_sched(int argc, const char **argv) { - const char default_sort_order[] = "avg, max, switch, runtime"; + static const char default_sort_order[] = "avg, max, switch, runtime"; struct perf_sched sched = { .tool = { .sample = perf_sched__process_tracepoint_sample, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 63a3afc7f32b..e587808591e8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -83,7 +83,6 @@ #include <unistd.h> #include <sys/time.h> #include <sys/resource.h> -#include <sys/wait.h> #include "sane_ctype.h" diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index f64e312db787..57b1d7495d02 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -22,6 +22,7 @@ #include "perf.h" #include "util/annotate.h" +#include "util/bpf-event.h" #include "util/config.h" #include "util/color.h" #include "util/drv_configs.h" @@ -366,7 +367,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg) if (p) *p = 0; - next = rb_first(&hists->entries); + next = rb_first_cached(&hists->entries); while (next) { n = rb_entry(next, struct hist_entry, rb_node); if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) { @@ -1215,6 +1216,12 @@ static int __cmd_top(struct perf_top *top) init_process_thread(top); + ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process, + &top->session->machines.host, + &top->record_opts); + if (ret < 0) + pr_warning("Couldn't synthesize bpf events.\n"); + machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->threads, false, top->nr_threads_synthesize); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index b36061cd1ab8..3518d352dd6c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3865,7 +3865,8 @@ int cmd_trace(int argc, const char **argv) goto init_augmented_syscall_tp; } - if (strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_enter") == 0) { + if (trace.syscalls.events.augmented->priv == NULL && + strstr(perf_evsel__name(evsel), "syscalls:sys_enter")) { struct perf_evsel *augmented = trace.syscalls.events.augmented; if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) || perf_evsel__init_augmented_syscall_tp_args(augmented)) diff --git a/tools/perf/design.txt b/tools/perf/design.txt index a28dca2582aa..0453ba26cdbd 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -222,6 +222,10 @@ The 'exclude_user', 'exclude_kernel' and 'exclude_hv' bits provide a way to request that counting of events be restricted to times when the CPU is in user, kernel and/or hypervisor mode. +Furthermore the 'exclude_host' and 'exclude_guest' bits provide a way +to request counting of events restricted to guest and host contexts when +using Linux as the hypervisor. + The 'mmap' and 'munmap' bits allow recording of PROT_EXEC mmap/munmap operations, these can be used to relate userspace IP addresses to actual code, even after the mapping (or even the whole process) is gone, diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index 53c233370fae..f9b2161e1ca4 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -18,23 +18,13 @@ #include <pid_filter.h> /* bpf-output associated map */ -struct bpf_map SEC("maps") __augmented_syscalls__ = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = __NR_CPUS__, -}; +bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__); struct syscall { bool enabled; }; -struct bpf_map SEC("maps") syscalls = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct syscall), - .max_entries = 512, -}; +bpf_map(syscalls, ARRAY, int, struct syscall, 512); struct syscall_enter_args { unsigned long long common_tp_fields; @@ -141,8 +131,8 @@ int sys_enter(struct syscall_enter_args *args) len = sizeof(augmented_args.args); } - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); - return 0; + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); } SEC("raw_syscalls:sys_exit") diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c index 2ae44813ef2d..524fdb8534b3 100644 --- a/tools/perf/examples/bpf/augmented_syscalls.c +++ b/tools/perf/examples/bpf/augmented_syscalls.c @@ -19,12 +19,8 @@ #include <stdio.h> #include <linux/socket.h> -struct bpf_map SEC("maps") __augmented_syscalls__ = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = __NR_CPUS__, -}; +/* bpf-output associated map */ +bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__); struct syscall_exit_args { unsigned long long common_tp_fields; @@ -55,9 +51,9 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \ len &= sizeof(augmented_args.filename.value) - 1; \ } \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, len); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, len); \ } \ int syscall_exit(syscall)(struct syscall_exit_args *args) \ { \ @@ -125,10 +121,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ /* addrlen = augmented_args.args.addrlen; */ \ /* */ \ probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, \ - sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);\ } \ int syscall_exit(syscall)(struct syscall_exit_args *args) \ { \ diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c index b59e8812ee8c..e81b535346c0 100644 --- a/tools/perf/examples/bpf/etcsnoop.c +++ b/tools/perf/examples/bpf/etcsnoop.c @@ -21,12 +21,8 @@ #include <stdio.h> -struct bpf_map SEC("maps") __augmented_syscalls__ = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = __NR_CPUS__, -}; +/* bpf-output associated map */ +bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__); struct augmented_filename { int size; @@ -49,11 +45,11 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ args->filename_ptr); \ if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0) \ return 0; \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, \ - (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \ - augmented_args.filename.size)); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \ + augmented_args.filename.size)); \ } struct syscall_enter_openat_args { diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index e667577207dc..5df7ed9d9020 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -18,6 +18,14 @@ struct bpf_map { unsigned int numa_node; }; +#define bpf_map(name, _type, type_key, type_val, _max_entries) \ +struct bpf_map SEC("maps") name = { \ + .type = BPF_MAP_TYPE_##_type, \ + .key_size = sizeof(type_key), \ + .value_size = sizeof(type_val), \ + .max_entries = _max_entries, \ +} + /* * FIXME: this should receive .max_entries as a parameter, as careful * tuning of these limits is needed to avoid hitting limits that @@ -26,13 +34,7 @@ struct bpf_map { * For the current need, 'perf trace --filter-pids', 64 should * be good enough, but this surely needs to be revisited. */ -#define pid_map(name, value_type) \ -struct bpf_map SEC("maps") name = { \ - .type = BPF_MAP_TYPE_HASH, \ - .key_size = sizeof(pid_t), \ - .value_size = sizeof(value_type), \ - .max_entries = 64, \ -} +#define pid_map(name, value_type) bpf_map(name, HASH, pid_t, value_type, 64) static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem; static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 388c6dd128b8..5941fb6eccfc 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -66,6 +66,7 @@ struct record_opts { bool ignore_missing_thread; bool strict_freq; bool sample_id; + bool bpf_event; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index f278ce5ebab7..c3091401df91 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -1,4 +1,3 @@ -#!/usr/bin/python2 # SPDX-License-Identifier: GPL-2.0 # exported-sql-viewer.py: view data from sql database # Copyright (c) 2014-2018, Intel Corporation. diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index 3473e7f66081..3984bf51f3c5 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -1,5 +1,3 @@ -#!/usr/bin/python -# # Cpu task migration overview toy # # Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com> diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py index 8410672efb8b..a81ad8835a74 100644 --- a/tools/perf/scripts/python/stat-cpi.py +++ b/tools/perf/scripts/python/stat-cpi.py @@ -1,4 +1,3 @@ -#!/usr/bin/env python # SPDX-License-Identifier: GPL-2.0 data = {} diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index e952127e4fb0..cb39ac46bc73 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -1,4 +1,3 @@ -#! /usr/bin/python # SPDX-License-Identifier: GPL-2.0 from __future__ import print_function diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index a20cbc445426..57fc544aedb0 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -15,7 +15,6 @@ #include <sys/mman.h> #include <linux/compiler.h> #include <linux/hw_breakpoint.h> -#include <sys/ioctl.h> #include "tests.h" #include "debug.h" diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index b889a28fd80b..6b0649c8b33e 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -161,7 +161,7 @@ out: void print_hists_in(struct hists *hists) { int i = 0; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; if (hists__has(hists, need_collapse)) @@ -170,7 +170,7 @@ void print_hists_in(struct hists *hists) root = hists->entries_in; pr_info("----- %s --------\n", __func__); - node = rb_first(root); + node = rb_first_cached(root); while (node) { struct hist_entry *he; @@ -191,13 +191,13 @@ void print_hists_in(struct hists *hists) void print_hists_out(struct hists *hists) { int i = 0; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; root = &hists->entries; pr_info("----- %s --------\n", __func__); - node = rb_first(root); + node = rb_first_cached(root); while (node) { struct hist_entry *he; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 65fe02bebbee..4ca417d1a06b 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -125,8 +125,8 @@ out: static void del_hist_entries(struct hists *hists) { struct hist_entry *he; - struct rb_root *root_in; - struct rb_root *root_out; + struct rb_root_cached *root_in; + struct rb_root_cached *root_out; struct rb_node *node; if (hists__has(hists, need_collapse)) @@ -136,12 +136,12 @@ static void del_hist_entries(struct hists *hists) root_out = &hists->entries; - while (!RB_EMPTY_ROOT(root_out)) { - node = rb_first(root_out); + while (!RB_EMPTY_ROOT(&root_out->rb_root)) { + node = rb_first_cached(root_out); he = rb_entry(node, struct hist_entry, rb_node); - rb_erase(node, root_out); - rb_erase(&he->rb_node_in, root_in); + rb_erase_cached(node, root_out); + rb_erase_cached(&he->rb_node_in, root_in); hist_entry__delete(he); } } @@ -198,7 +198,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec print_hists_out(hists); } - root = &hists->entries; + root = &hists->entries.rb_root; for (node = rb_first(root), i = 0; node && (he = rb_entry(node, struct hist_entry, rb_node)); node = rb_next(node), i++) { diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 9a9d06cb0222..af633db63f4d 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -142,7 +142,7 @@ static int find_sample(struct sample *samples, size_t nr_samples, static int __validate_match(struct hists *hists) { size_t count = 0; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; /* @@ -153,7 +153,7 @@ static int __validate_match(struct hists *hists) else root = hists->entries_in; - node = rb_first(root); + node = rb_first_cached(root); while (node) { struct hist_entry *he; @@ -192,7 +192,7 @@ static int __validate_link(struct hists *hists, int idx) size_t count = 0; size_t count_pair = 0; size_t count_dummy = 0; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; /* @@ -205,7 +205,7 @@ static int __validate_link(struct hists *hists, int idx) else root = hists->entries_in; - node = rb_first(root); + node = rb_first_cached(root); while (node) { struct hist_entry *he; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index faacb4f41460..6c4bc68a77ee 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -91,8 +91,8 @@ out: static void del_hist_entries(struct hists *hists) { struct hist_entry *he; - struct rb_root *root_in; - struct rb_root *root_out; + struct rb_root_cached *root_in; + struct rb_root_cached *root_out; struct rb_node *node; if (hists__has(hists, need_collapse)) @@ -102,12 +102,12 @@ static void del_hist_entries(struct hists *hists) root_out = &hists->entries; - while (!RB_EMPTY_ROOT(root_out)) { - node = rb_first(root_out); + while (!RB_EMPTY_ROOT(&root_out->rb_root)) { + node = rb_first_cached(root_out); he = rb_entry(node, struct hist_entry, rb_node); - rb_erase(node, root_out); - rb_erase(&he->rb_node_in, root_in); + rb_erase_cached(node, root_out); + rb_erase_cached(&he->rb_node_in, root_in); hist_entry__delete(he); } } @@ -126,7 +126,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) int err; struct hists *hists = evsel__hists(evsel); struct hist_entry *he; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; field_order = NULL; @@ -162,7 +162,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) } root = &hists->entries; - node = rb_first(root); + node = rb_first_cached(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && @@ -228,7 +228,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) int err; struct hists *hists = evsel__hists(evsel); struct hist_entry *he; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; field_order = "overhead,cpu"; @@ -262,7 +262,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) } root = &hists->entries; - node = rb_first(root); + node = rb_first_cached(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", CPU(he) == 1 && PID(he) == 100 && he->stat.period == 300); @@ -284,7 +284,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) int err; struct hists *hists = evsel__hists(evsel); struct hist_entry *he; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; field_order = "comm,overhead,dso"; @@ -316,7 +316,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) } root = &hists->entries; - node = rb_first(root); + node = rb_first_cached(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && @@ -358,7 +358,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) int err; struct hists *hists = evsel__hists(evsel); struct hist_entry *he; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; field_order = "dso,sym,comm,overhead,dso"; @@ -394,7 +394,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) } root = &hists->entries; - node = rb_first(root); + node = rb_first_cached(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", !strcmp(DSO(he), "perf") && !strcmp(SYM(he), "cmd_record") && @@ -460,7 +460,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) int err; struct hists *hists = evsel__hists(evsel); struct hist_entry *he; - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *node; field_order = "cpu,pid,comm,dso,sym"; @@ -497,7 +497,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) } root = &hists->entries; - node = rb_first(root); + node = rb_first_cached(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c index d75492189acb..5aeb663dd184 100644 --- a/tools/perf/ui/browsers/header.c +++ b/tools/perf/ui/browsers/header.c @@ -35,7 +35,7 @@ static int list_menu__run(struct ui_browser *menu) { int key; unsigned long offset; - const char help[] = + static const char help[] = "h/?/F1 Show this window\n" "UP/DOWN/PGUP\n" "PGDN/SPACE\n" diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index ffac1d54a3d4..85790a4d1842 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -49,7 +49,7 @@ static int hist_browser__get_folding(struct hist_browser *browser) struct hists *hists = browser->hists; int unfolded_rows = 0; - for (nd = rb_first(&hists->entries); + for (nd = rb_first_cached(&hists->entries); (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL; nd = rb_hierarchy_next(nd)) { struct hist_entry *he = @@ -267,7 +267,7 @@ static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he, if (he->has_no_entry) return 1; - node = rb_first(&he->hroot_out); + node = rb_first_cached(&he->hroot_out); while (node) { float percent; @@ -372,7 +372,7 @@ static void hist_entry__init_have_children(struct hist_entry *he) he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain); callchain__init_have_children(&he->sorted_chain); } else { - he->has_children = !RB_EMPTY_ROOT(&he->hroot_out); + he->has_children = !RB_EMPTY_ROOT(&he->hroot_out.rb_root); } he->init_have_children = true; @@ -508,7 +508,7 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, struct hist_entry *child; int n = 0; - for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&he->hroot_out); nd; nd = rb_next(nd)) { child = rb_entry(nd, struct hist_entry, rb_node); percent = hist_entry__get_percent_limit(child); if (!child->filtered && percent >= hb->min_pcnt) @@ -566,7 +566,7 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) struct rb_node *nd; struct hist_entry *he; - nd = rb_first(&browser->hists->entries); + nd = rb_first_cached(&browser->hists->entries); while (nd) { he = rb_entry(nd, struct hist_entry, rb_node); @@ -1738,7 +1738,7 @@ static void ui_browser__hists_init_top(struct ui_browser *browser) struct hist_browser *hb; hb = container_of(browser, struct hist_browser, b); - browser->top = rb_first(&hb->hists->entries); + browser->top = rb_first_cached(&hb->hists->entries); } } @@ -2649,7 +2649,7 @@ add_socket_opt(struct hist_browser *browser, struct popup_action *act, static void hist_browser__update_nr_entries(struct hist_browser *hb) { u64 nr_entries = 0; - struct rb_node *nd = rb_first(&hb->hists->entries); + struct rb_node *nd = rb_first_cached(&hb->hists->entries); if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) { hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries; @@ -2669,7 +2669,7 @@ static void hist_browser__update_percent_limit(struct hist_browser *hb, double percent) { struct hist_entry *he; - struct rb_node *nd = rb_first(&hb->hists->entries); + struct rb_node *nd = rb_first_cached(&hb->hists->entries); u64 total = hists__total_period(hb->hists); u64 min_callchain_hits = total * (percent / 100); @@ -2748,7 +2748,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "S Zoom into current Processor Socket\n" \ /* help messages are sorted by lexical order of the hotkey */ - const char report_help[] = HIST_BROWSER_HELP_COMMON + static const char report_help[] = HIST_BROWSER_HELP_COMMON "i Show header information\n" "P Print histograms to perf.hist.N\n" "r Run available scripts\n" @@ -2756,7 +2756,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "t Zoom into current Thread\n" "V Verbose (DSO names in callchains, etc)\n" "/ Filter symbol by name"; - const char top_help[] = HIST_BROWSER_HELP_COMMON + static const char top_help[] = HIST_BROWSER_HELP_COMMON "P Print histograms to perf.hist.N\n" "t Zoom into current Thread\n" "V Verbose (DSO names in callchains, etc)\n" diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 5b8b8c637686..c70d9337405b 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -6,6 +6,7 @@ #include <linux/bitops.h> #include "../../util/util.h" #include "../../util/debug.h" +#include "../../util/map.h" #include "../../util/symbol.h" #include "../browser.h" #include "../helpline.h" diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 48428c9acd89..f22a7d142ada 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "gtk.h" +#include "util/sort.h" #include "util/debug.h" #include "util/annotate.h" #include "util/evsel.h" diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 4ab663ec3e5e..74414ccd8c84 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -353,7 +353,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, g_object_unref(GTK_TREE_MODEL(store)); - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); GtkTreeIter iter; u64 total = hists__total_period(h->hists); @@ -401,7 +401,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, } static void perf_gtk__add_hierarchy_entries(struct hists *hists, - struct rb_root *root, + struct rb_root_cached *root, GtkTreeStore *store, GtkTreeIter *parent, struct perf_hpp *hpp, @@ -415,7 +415,7 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists, u64 total = hists__total_period(hists); int size; - for (node = rb_first(root); node; node = rb_next(node)) { + for (node = rb_first_cached(root); node; node = rb_next(node)) { GtkTreeIter iter; float percent; char *bf; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 74c4ae1f0a05..2a9fa4dcbc2a 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -788,7 +788,8 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, indent = hists__overhead_width(hists) + 4; - for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) { + for (nd = rb_first_cached(&hists->entries); nd; + nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); float percent; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index af72be7f5b3b..b69d6294c88c 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -35,6 +35,7 @@ libperf-y += dso.o libperf-y += symbol.o libperf-y += symbol_fprintf.o libperf-y += color.o +libperf-y += color_config.o libperf-y += metricgroup.o libperf-y += header.o libperf-y += callchain.o @@ -44,6 +45,8 @@ libperf-y += machine.o libperf-y += map.o libperf-y += pstack.o libperf-y += session.o +libperf-y += sample-raw.o +libperf-y += s390-sample-raw.o libperf-$(CONFIG_TRACE) += syscalltbl.o libperf-y += ordered-events.o libperf-y += namespaces.o @@ -152,6 +155,8 @@ endif libperf-y += perf-hooks.o +libperf-$(CONFIG_LIBBPF) += bpf-event.o + libperf-$(CONFIG_CXX) += c++/ CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 70de8f6b3aee..3d79add5f7ae 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -9,6 +9,7 @@ #include <errno.h> #include <inttypes.h> +#include <libgen.h> #include "util.h" #include "ui/ui.h" #include "sort.h" diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index fb6463730ba4..95053cab41fe 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -4,16 +4,24 @@ #include <stdbool.h> #include <stdint.h> +#include <stdio.h> #include <linux/types.h> -#include "symbol.h" -#include "hist.h" -#include "sort.h" #include <linux/list.h> #include <linux/rbtree.h> #include <pthread.h> #include <asm/bug.h> +#include "symbol_conf.h" +struct hist_browser_timer; +struct hist_entry; struct ins_ops; +struct map; +struct map_symbol; +struct addr_map_symbol; +struct option; +struct perf_sample; +struct perf_evsel; +struct symbol; struct ins { const char *name; diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c index f1451c987eec..1be432657501 100644 --- a/tools/perf/util/block-range.c +++ b/tools/perf/util/block-range.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "block-range.h" #include "annotate.h" +#include <assert.h> +#include <stdlib.h> struct { struct rb_root root; diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h index a5ba719d69fb..ec0fb534bf56 100644 --- a/tools/perf/util/block-range.h +++ b/tools/perf/util/block-range.h @@ -2,7 +2,11 @@ #ifndef __PERF_BLOCK_RANGE_H #define __PERF_BLOCK_RANGE_H -#include "symbol.h" +#include <stdbool.h> +#include <linux/rbtree.h> +#include <linux/types.h> + +struct symbol; /* * struct block_range - non-overlapping parts of basic blocks diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c new file mode 100644 index 000000000000..796ef793f4ce --- /dev/null +++ b/tools/perf/util/bpf-event.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <stdlib.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <linux/btf.h> +#include "bpf-event.h" +#include "debug.h" +#include "symbol.h" +#include "machine.h" + +#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) + +static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len) +{ + int ret = 0; + size_t i; + + for (i = 0; i < len; i++) + ret += snprintf(buf + ret, size - ret, "%02x", data[i]); + return ret; +} + +int machine__process_bpf_event(struct machine *machine __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_bpf_event(event, stdout); + return 0; +} + +/* + * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf + * program. One PERF_RECORD_BPF_EVENT is generated for the program. And + * one PERF_RECORD_KSYMBOL is generated for each sub program. + * + * Returns: + * 0 for success; + * -1 for failures; + * -2 for lack of kernel support. + */ +static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + int fd, + union perf_event *event, + struct record_opts *opts) +{ + struct ksymbol_event *ksymbol_event = &event->ksymbol_event; + struct bpf_event *bpf_event = &event->bpf_event; + u32 sub_prog_cnt, i, func_info_rec_size = 0; + u8 (*prog_tags)[BPF_TAG_SIZE] = NULL; + struct bpf_prog_info info = { .type = 0, }; + u32 info_len = sizeof(info); + void *func_infos = NULL; + u64 *prog_addrs = NULL; + struct btf *btf = NULL; + u32 *prog_lens = NULL; + bool has_btf = false; + char errbuf[512]; + int err = 0; + + /* Call bpf_obj_get_info_by_fd() to get sizes of arrays */ + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + + if (err) { + pr_debug("%s: failed to get BPF program info: %s, aborting\n", + __func__, str_error_r(errno, errbuf, sizeof(errbuf))); + return -1; + } + if (info_len < offsetof(struct bpf_prog_info, prog_tags)) { + pr_debug("%s: the kernel is too old, aborting\n", __func__); + return -2; + } + + /* number of ksyms, func_lengths, and tags should match */ + sub_prog_cnt = info.nr_jited_ksyms; + if (sub_prog_cnt != info.nr_prog_tags || + sub_prog_cnt != info.nr_jited_func_lens) + return -1; + + /* check BTF func info support */ + if (info.btf_id && info.nr_func_info && info.func_info_rec_size) { + /* btf func info number should be same as sub_prog_cnt */ + if (sub_prog_cnt != info.nr_func_info) { + pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__); + return -1; + } + if (btf__get_from_id(info.btf_id, &btf)) { + pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id); + return -1; + } + func_info_rec_size = info.func_info_rec_size; + func_infos = calloc(sub_prog_cnt, func_info_rec_size); + if (!func_infos) { + pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__); + return -1; + } + has_btf = true; + } + + /* + * We need address, length, and tag for each sub program. + * Allocate memory and call bpf_obj_get_info_by_fd() again + */ + prog_addrs = calloc(sub_prog_cnt, sizeof(u64)); + if (!prog_addrs) { + pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__); + goto out; + } + prog_lens = calloc(sub_prog_cnt, sizeof(u32)); + if (!prog_lens) { + pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__); + goto out; + } + prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE); + if (!prog_tags) { + pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__); + goto out; + } + + memset(&info, 0, sizeof(info)); + info.nr_jited_ksyms = sub_prog_cnt; + info.nr_jited_func_lens = sub_prog_cnt; + info.nr_prog_tags = sub_prog_cnt; + info.jited_ksyms = ptr_to_u64(prog_addrs); + info.jited_func_lens = ptr_to_u64(prog_lens); + info.prog_tags = ptr_to_u64(prog_tags); + info_len = sizeof(info); + if (has_btf) { + info.nr_func_info = sub_prog_cnt; + info.func_info_rec_size = func_info_rec_size; + info.func_info = ptr_to_u64(func_infos); + } + + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (err) { + pr_debug("%s: failed to get BPF program info, aborting\n", __func__); + goto out; + } + + /* Synthesize PERF_RECORD_KSYMBOL */ + for (i = 0; i < sub_prog_cnt; i++) { + const struct bpf_func_info *finfo; + const char *short_name = NULL; + const struct btf_type *t; + int name_len; + + *ksymbol_event = (struct ksymbol_event){ + .header = { + .type = PERF_RECORD_KSYMBOL, + .size = offsetof(struct ksymbol_event, name), + }, + .addr = prog_addrs[i], + .len = prog_lens[i], + .ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF, + .flags = 0, + }; + name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN, + "bpf_prog_"); + name_len += snprintf_hex(ksymbol_event->name + name_len, + KSYM_NAME_LEN - name_len, + prog_tags[i], BPF_TAG_SIZE); + if (has_btf) { + finfo = func_infos + i * info.func_info_rec_size; + t = btf__type_by_id(btf, finfo->type_id); + short_name = btf__name_by_offset(btf, t->name_off); + } else if (i == 0 && sub_prog_cnt == 1) { + /* no subprog */ + if (info.name[0]) + short_name = info.name; + } else + short_name = "F"; + if (short_name) + name_len += snprintf(ksymbol_event->name + name_len, + KSYM_NAME_LEN - name_len, + "_%s", short_name); + + ksymbol_event->header.size += PERF_ALIGN(name_len + 1, + sizeof(u64)); + + memset((void *)event + event->header.size, 0, machine->id_hdr_size); + event->header.size += machine->id_hdr_size; + err = perf_tool__process_synth_event(tool, event, + machine, process); + } + + /* Synthesize PERF_RECORD_BPF_EVENT */ + if (opts->bpf_event) { + *bpf_event = (struct bpf_event){ + .header = { + .type = PERF_RECORD_BPF_EVENT, + .size = sizeof(struct bpf_event), + }, + .type = PERF_BPF_EVENT_PROG_LOAD, + .flags = 0, + .id = info.id, + }; + memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE); + memset((void *)event + event->header.size, 0, machine->id_hdr_size); + event->header.size += machine->id_hdr_size; + err = perf_tool__process_synth_event(tool, event, + machine, process); + } + +out: + free(prog_tags); + free(prog_lens); + free(prog_addrs); + free(func_infos); + free(btf); + return err ? -1 : 0; +} + +int perf_event__synthesize_bpf_events(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + struct record_opts *opts) +{ + union perf_event *event; + __u32 id = 0; + int err; + int fd; + + event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN + machine->id_hdr_size); + if (!event) + return -1; + while (true) { + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + pr_debug("%s: can't get next program: %s%s", + __func__, strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + /* don't report error on old kernel */ + err = (errno == EINVAL) ? 0 : -1; + break; + } + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + pr_debug("%s: failed to get fd for prog_id %u\n", + __func__, id); + continue; + } + + err = perf_event__synthesize_one_bpf_prog(tool, process, + machine, fd, + event, opts); + close(fd); + if (err) { + /* do not return error for old kernel */ + if (err == -2) + err = 0; + break; + } + } + free(event); + return err; +} diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h new file mode 100644 index 000000000000..7890067e1a37 --- /dev/null +++ b/tools/perf/util/bpf-event.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_BPF_EVENT_H +#define __PERF_BPF_EVENT_H + +#include <linux/compiler.h> +#include "event.h" + +struct machine; +union perf_event; +struct perf_sample; +struct perf_tool; +struct record_opts; + +#ifdef HAVE_LIBBPF_SUPPORT +int machine__process_bpf_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); + +int perf_event__synthesize_bpf_events(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + struct record_opts *opts); +#else +static inline int machine__process_bpf_event(struct machine *machine __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused) +{ + return 0; +} + +static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused, + struct record_opts *opts __maybe_unused) +{ + return 0; +} +#endif // HAVE_LIBBPF_SUPPORT +#endif diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index 1e3c7c5cdc63..64f96b79f1d7 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -1,8 +1,31 @@ #ifndef _PERF_BRANCH_H #define _PERF_BRANCH_H 1 +#include <stdio.h> #include <stdint.h> -#include "../perf.h" +#include <linux/perf_event.h> +#include <linux/types.h> + +struct branch_flags { + u64 mispred:1; + u64 predicted:1; + u64 in_tx:1; + u64 abort:1; + u64 cycles:16; + u64 type:4; + u64 reserved:40; +}; + +struct branch_entry { + u64 from; + u64 to; + struct branch_flags flags; +}; + +struct branch_stack { + u64 nr; + struct branch_entry entries[0]; +}; struct branch_type_stat { bool branch_to; @@ -13,8 +36,6 @@ struct branch_type_stat { u64 cross_2m; }; -struct branch_flags; - void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, u64 from, u64 to); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 04b1d53e4bf9..2ff802068f06 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include "build-id.h" #include "event.h" +#include "namespaces.h" #include "symbol.h" #include "thread.h" #include <linux/kernel.h> @@ -363,7 +364,8 @@ int perf_session__write_buildid_table(struct perf_session *session, if (err) return err; - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&session->machines.guests); nd; + nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); err = machine__write_buildid_table(pos, fd); if (err) @@ -396,7 +398,8 @@ int dsos__hit_all(struct perf_session *session) if (err) return err; - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&session->machines.guests); nd; + nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); err = machine__hit_all_dsos(pos); @@ -849,7 +852,8 @@ int perf_session__cache_build_ids(struct perf_session *session) ret = machine__cache_build_ids(&session->machines.host); - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&session->machines.guests); nd; + nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__cache_build_ids(pos); } @@ -866,7 +870,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) struct rb_node *nd; bool ret = machine__read_build_ids(&session->machines.host, with_hits); - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&session->machines.guests); nd; + nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__read_build_ids(pos, with_hits); } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index f0c565164a97..93668f38f1ed 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -6,9 +6,10 @@ #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" -#include "namespaces.h" #include <linux/types.h> +struct nsinfo; + extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; struct feat_fd; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 99d38ac019b8..8afe1622edf3 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -2,7 +2,6 @@ #ifndef __PERF_CALLCHAIN_H #define __PERF_CALLCHAIN_H -#include "../perf.h" #include <linux/list.h> #include <linux/rbtree.h> #include "event.h" diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 39e628b8938e..39b8c4ec4e2e 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include "cache.h" -#include "config.h" #include <stdlib.h> #include <stdio.h> #include "color.h" @@ -10,44 +9,6 @@ int perf_use_color_default = -1; -int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) -{ - if (value) { - if (!strcasecmp(value, "never")) - return 0; - if (!strcasecmp(value, "always")) - return 1; - if (!strcasecmp(value, "auto")) - goto auto_color; - } - - /* Missing or explicit false to turn off colorization */ - if (!perf_config_bool(var, value)) - return 0; - - /* any normal truth value defaults to 'auto' */ - auto_color: - if (stdout_is_tty < 0) - stdout_is_tty = isatty(1); - if (stdout_is_tty || pager_in_use()) { - char *term = getenv("TERM"); - if (term && strcmp(term, "dumb")) - return 1; - } - return 0; -} - -int perf_color_default_config(const char *var, const char *value, - void *cb __maybe_unused) -{ - if (!strcmp(var, "color.ui")) { - perf_use_color_default = perf_config_colorbool(var, value, -1); - return 0; - } - - return 0; -} - static int __color_vsnprintf(char *bf, size_t size, const char *color, const char *fmt, va_list args, const char *trail) { diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 22777b1812ee..01f7bed21c9b 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -3,6 +3,7 @@ #define __PERF_COLOR_H #include <stdio.h> +#include <stdarg.h> /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ #define COLOR_MAXLEN 24 diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c new file mode 100644 index 000000000000..817dc56e7e95 --- /dev/null +++ b/tools/perf/util/color_config.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include "cache.h" +#include "config.h" +#include <stdlib.h> +#include <stdio.h> +#include "color.h" +#include <math.h> +#include <unistd.h> + +int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) +{ + if (value) { + if (!strcasecmp(value, "never")) + return 0; + if (!strcasecmp(value, "always")) + return 1; + if (!strcasecmp(value, "auto")) + goto auto_color; + } + + /* Missing or explicit false to turn off colorization */ + if (!perf_config_bool(var, value)) + return 0; + + /* any normal truth value defaults to 'auto' */ + auto_color: + if (stdout_is_tty < 0) + stdout_is_tty = isatty(1); + if (stdout_is_tty || pager_in_use()) { + char *term = getenv("TERM"); + if (term && strcmp(term, "dumb")) + return 1; + } + return 0; +} + +int perf_color_default_config(const char *var, const char *value, + void *cb __maybe_unused) +{ + if (!strcmp(var, "color.ui")) { + perf_use_color_default = perf_config_colorbool(var, value, -1); + return 0; + } + + return 0; +} diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 31279a7bd919..1066de92af12 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -6,6 +6,7 @@ #include <stdio.h> #include <string.h> #include <linux/refcount.h> +#include <linux/rbtree.h> #include "rwsem.h" struct comm_str { diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h index 3e5c438fe85e..f35d8fbfa2dd 100644 --- a/tools/perf/util/comm.h +++ b/tools/perf/util/comm.h @@ -2,9 +2,9 @@ #ifndef __PERF_COMM_H #define __PERF_COMM_H -#include "../perf.h" -#include <linux/rbtree.h> #include <linux/list.h> +#include <linux/types.h> +#include <stdbool.h> struct comm_str; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 62c8cf622607..a8a54115b115 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -8,7 +8,9 @@ #include <unistd.h> #include <errno.h> #include <fcntl.h> +#include <libgen.h> #include "compress.h" +#include "namespaces.h" #include "path.h" #include "symbol.h" #include "srcline.h" @@ -1195,10 +1197,10 @@ struct dso *dso__new(const char *name) strcpy(dso->name, name); dso__set_long_name(dso, dso->name, false); dso__set_short_name(dso, dso->name, false); - dso->symbols = dso->symbol_names = RB_ROOT; + dso->symbols = dso->symbol_names = RB_ROOT_CACHED; dso->data.cache = RB_ROOT; - dso->inlined_nodes = RB_ROOT; - dso->srclines = RB_ROOT; + dso->inlined_nodes = RB_ROOT_CACHED; + dso->srclines = RB_ROOT_CACHED; dso->data.fd = -1; dso->data.status = DSO_DATA_STATUS_UNKNOWN; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; @@ -1467,7 +1469,7 @@ size_t dso__fprintf(struct dso *dso, FILE *fp) ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT "); ret += dso__fprintf_buildid(dso, fp); ret += fprintf(fp, ")\n"); - for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); ret += symbol__fprintf(pos, fp); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 8c8a7abe809d..bb417c54c25a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -7,13 +7,14 @@ #include <linux/rbtree.h> #include <sys/types.h> #include <stdbool.h> +#include <stdio.h> #include "rwsem.h" -#include <linux/types.h> #include <linux/bitops.h> -#include "map.h" -#include "namespaces.h" #include "build-id.h" +struct machine; +struct map; + enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, DSO_BINARY_TYPE__GUEST_KALLSYMS, @@ -140,10 +141,10 @@ struct dso { struct list_head node; struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root *root; /* root of rbtree that rb_node is in */ - struct rb_root symbols; - struct rb_root symbol_names; - struct rb_root inlined_nodes; - struct rb_root srclines; + struct rb_root_cached symbols; + struct rb_root_cached symbol_names; + struct rb_root_cached inlined_nodes; + struct rb_root_cached srclines; struct { u64 addr; struct symbol *symbol; @@ -235,7 +236,7 @@ bool dso__loaded(const struct dso *dso); static inline bool dso__has_symbols(const struct dso *dso) { - return !RB_EMPTY_ROOT(&dso->symbols); + return !RB_EMPTY_ROOT(&dso->symbols.rb_root); } bool dso__sorted_by_name(const struct dso *dso); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 937a5a4f71cc..1b5091a3d14f 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -24,6 +24,8 @@ #include "symbol/kallsyms.h" #include "asm/bug.h" #include "stat.h" +#include "session.h" +#include "bpf-event.h" #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500 @@ -45,6 +47,8 @@ static const char *perf_event__names[] = { [PERF_RECORD_SWITCH] = "SWITCH", [PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE", [PERF_RECORD_NAMESPACES] = "NAMESPACES", + [PERF_RECORD_KSYMBOL] = "KSYMBOL", + [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -1329,6 +1333,22 @@ int perf_event__process_switch(struct perf_tool *tool __maybe_unused, return machine__process_switch_event(machine, event); } +int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_ksymbol(machine, event, sample); +} + +int perf_event__process_bpf_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_bpf_event(machine, event, sample); +} + size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n", @@ -1461,6 +1481,21 @@ static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp) return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost); } +size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " ksymbol event with addr %" PRIx64 " len %u type %u flags 0x%x name %s\n", + event->ksymbol_event.addr, event->ksymbol_event.len, + event->ksymbol_event.ksym_type, + event->ksymbol_event.flags, event->ksymbol_event.name); +} + +size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " bpf event with type %u, flags %u, id %u\n", + event->bpf_event.type, event->bpf_event.flags, + event->bpf_event.id); +} + size_t perf_event__fprintf(union perf_event *event, FILE *fp) { size_t ret = fprintf(fp, "PERF_RECORD_%s", @@ -1496,6 +1531,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_LOST: ret += perf_event__fprintf_lost(event, fp); break; + case PERF_RECORD_KSYMBOL: + ret += perf_event__fprintf_ksymbol(event, fp); + break; + case PERF_RECORD_BPF_EVENT: + ret += perf_event__fprintf_bpf_event(event, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index eb95f3384958..feba1aa819b4 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -5,6 +5,7 @@ #include <limits.h> #include <stdio.h> #include <linux/kernel.h> +#include <linux/bpf.h> #include "../perf.h" #include "build-id.h" @@ -84,6 +85,29 @@ struct throttle_event { u64 stream_id; }; +#ifndef KSYM_NAME_LEN +#define KSYM_NAME_LEN 256 +#endif + +struct ksymbol_event { + struct perf_event_header header; + u64 addr; + u32 len; + u16 ksym_type; + u16 flags; + char name[KSYM_NAME_LEN]; +}; + +struct bpf_event { + struct perf_event_header header; + u16 type; + u16 flags; + u32 id; + + /* for bpf_prog types */ + u8 tag[BPF_TAG_SIZE]; // prog tag +}; + #define PERF_SAMPLE_MASK \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ @@ -137,26 +161,7 @@ struct ip_callchain { u64 ips[0]; }; -struct branch_flags { - u64 mispred:1; - u64 predicted:1; - u64 in_tx:1; - u64 abort:1; - u64 cycles:16; - u64 type:4; - u64 reserved:40; -}; - -struct branch_entry { - u64 from; - u64 to; - struct branch_flags flags; -}; - -struct branch_stack { - u64 nr; - struct branch_entry entries[0]; -}; +struct branch_stack; enum { PERF_IP_FLAG_BRANCH = 1ULL << 0, @@ -651,6 +656,8 @@ union perf_event { struct stat_round_event stat_round; struct time_conv_event time_conv; struct feature_event feat; + struct ksymbol_event ksymbol_event; + struct bpf_event bpf_event; }; void perf_event__print_totals(void); @@ -748,6 +755,14 @@ int perf_event__process_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_ksymbol(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_bpf_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, @@ -811,6 +826,8 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); int kallsyms__get_function_start(const char *kallsyms_filename, diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 868294491194..00ab43c6dd15 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -49,6 +49,9 @@ struct perf_evlist { struct perf_evsel *selected; struct events_stats stats; struct perf_env *env; + void (*trace_event_sample_raw)(struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample); u64 first_sample_time; u64 last_sample_time; }; @@ -314,5 +317,4 @@ void perf_evlist__force_leader(struct perf_evlist *evlist); struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, struct perf_evsel *evsel); - #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index dbc0466db368..684c893ca6bc 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1035,6 +1035,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; + attr->ksymbol = track && !perf_missing_features.ksymbol; + attr->bpf_event = track && opts->bpf_event && + !perf_missing_features.bpf_event; if (opts->record_namespaces) attr->namespaces = track; @@ -1652,6 +1655,8 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(context_switch, p_unsigned); PRINT_ATTRf(write_backward, p_unsigned); PRINT_ATTRf(namespaces, p_unsigned); + PRINT_ATTRf(ksymbol, p_unsigned); + PRINT_ATTRf(bpf_event, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); @@ -1811,6 +1816,10 @@ fallback_missing_features: PERF_SAMPLE_BRANCH_NO_CYCLES); if (perf_missing_features.group_read && evsel->attr.inherit) evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); + if (perf_missing_features.ksymbol) + evsel->attr.ksymbol = 0; + if (perf_missing_features.bpf_event) + evsel->attr.bpf_event = 0; retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1930,7 +1939,15 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.write_backward && evsel->attr.write_backward) { + if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) { + perf_missing_features.bpf_event = true; + pr_debug2("switching off bpf_event\n"); + goto fallback_missing_features; + } else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) { + perf_missing_features.ksymbol = true; + pr_debug2("switching off ksymbol\n"); + goto fallback_missing_features; + } else if (!perf_missing_features.write_backward && evsel->attr.write_backward) { perf_missing_features.write_backward = true; pr_debug2("switching off write_backward\n"); goto out_close; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 82a289ce8b0c..29c5eb68c44b 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -168,6 +168,8 @@ struct perf_missing_features { bool lbr_flags; bool write_backward; bool group_read; + bool ksymbol; + bool bpf_event; }; extern struct perf_missing_features perf_missing_features; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 8aad8330e392..9e7a8e044a0a 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -209,7 +209,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) void hists__output_recalc_col_len(struct hists *hists, int max_rows) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_node *next = rb_first_cached(&hists->entries); struct hist_entry *n; int row = 0; @@ -296,7 +296,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) if (!he->leaf) { struct hist_entry *child; - struct rb_node *node = rb_first(&he->hroot_out); + struct rb_node *node = rb_first_cached(&he->hroot_out); while (node) { child = rb_entry(node, struct hist_entry, rb_node); node = rb_next(node); @@ -311,8 +311,8 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) static void hists__delete_entry(struct hists *hists, struct hist_entry *he) { - struct rb_root *root_in; - struct rb_root *root_out; + struct rb_root_cached *root_in; + struct rb_root_cached *root_out; if (he->parent_he) { root_in = &he->parent_he->hroot_in; @@ -325,8 +325,8 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he) root_out = &hists->entries; } - rb_erase(&he->rb_node_in, root_in); - rb_erase(&he->rb_node, root_out); + rb_erase_cached(&he->rb_node_in, root_in); + rb_erase_cached(&he->rb_node, root_out); --hists->nr_entries; if (!he->filtered) @@ -337,7 +337,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he) void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_node *next = rb_first_cached(&hists->entries); struct hist_entry *n; while (next) { @@ -353,7 +353,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) void hists__delete_entries(struct hists *hists) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_node *next = rb_first_cached(&hists->entries); struct hist_entry *n; while (next) { @@ -435,8 +435,8 @@ static int hist_entry__init(struct hist_entry *he, } INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); - he->hroot_in = RB_ROOT; - he->hroot_out = RB_ROOT; + he->hroot_in = RB_ROOT_CACHED; + he->hroot_out = RB_ROOT_CACHED; if (!symbol_conf.report_hierarchy) he->leaf = true; @@ -513,8 +513,9 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, int64_t cmp; u64 period = entry->stat.period; u64 weight = entry->stat.weight; + bool leftmost = true; - p = &hists->entries_in->rb_node; + p = &hists->entries_in->rb_root.rb_node; while (*p != NULL) { parent = *p; @@ -557,8 +558,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (cmp < 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } he = hist_entry__new(entry, sample_self); @@ -570,7 +573,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); - rb_insert_color(&he->rb_node_in, hists->entries_in); + rb_insert_color_cached(&he->rb_node_in, hists->entries_in, leftmost); out: if (sample_self) he_stat__add_cpumode_period(&he->stat, al->cpumode, period); @@ -1279,16 +1282,17 @@ static void hist_entry__apply_hierarchy_filters(struct hist_entry *he) } static struct hist_entry *hierarchy_insert_entry(struct hists *hists, - struct rb_root *root, + struct rb_root_cached *root, struct hist_entry *he, struct hist_entry *parent_he, struct perf_hpp_list *hpp_list) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct hist_entry *iter, *new; struct perf_hpp_fmt *fmt; int64_t cmp; + bool leftmost = true; while (*p != NULL) { parent = *p; @@ -1308,8 +1312,10 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, if (cmp < 0) p = &parent->rb_left; - else + else { p = &parent->rb_right; + leftmost = false; + } } new = hist_entry__new(he, true); @@ -1343,12 +1349,12 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, } rb_link_node(&new->rb_node_in, parent, p); - rb_insert_color(&new->rb_node_in, root); + rb_insert_color_cached(&new->rb_node_in, root, leftmost); return new; } static int hists__hierarchy_insert_entry(struct hists *hists, - struct rb_root *root, + struct rb_root_cached *root, struct hist_entry *he) { struct perf_hpp_list_node *node; @@ -1395,13 +1401,14 @@ static int hists__hierarchy_insert_entry(struct hists *hists, } static int hists__collapse_insert_entry(struct hists *hists, - struct rb_root *root, + struct rb_root_cached *root, struct hist_entry *he) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; int64_t cmp; + bool leftmost = true; if (symbol_conf.report_hierarchy) return hists__hierarchy_insert_entry(hists, root, he); @@ -1432,19 +1439,21 @@ static int hists__collapse_insert_entry(struct hists *hists, if (cmp < 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); - rb_insert_color(&he->rb_node_in, root); + rb_insert_color_cached(&he->rb_node_in, root, leftmost); return 1; } -struct rb_root *hists__get_rotate_entries_in(struct hists *hists) +struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists) { - struct rb_root *root; + struct rb_root_cached *root; pthread_mutex_lock(&hists->lock); @@ -1467,7 +1476,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; struct hist_entry *n; int ret; @@ -1479,7 +1488,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) root = hists__get_rotate_entries_in(hists); - next = rb_first(root); + next = rb_first_cached(root); while (next) { if (session_done()) @@ -1487,7 +1496,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); - rb_erase(&n->rb_node_in, root); + rb_erase_cached(&n->rb_node_in, root); ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n); if (ret < 0) return -1; @@ -1558,7 +1567,7 @@ static void hierarchy_recalc_total_periods(struct hists *hists) struct rb_node *node; struct hist_entry *he; - node = rb_first(&hists->entries); + node = rb_first_cached(&hists->entries); hists->stats.total_period = 0; hists->stats.total_non_filtered_period = 0; @@ -1578,13 +1587,14 @@ static void hierarchy_recalc_total_periods(struct hists *hists) } } -static void hierarchy_insert_output_entry(struct rb_root *root, +static void hierarchy_insert_output_entry(struct rb_root_cached *root, struct hist_entry *he) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; struct perf_hpp_fmt *fmt; + bool leftmost = true; while (*p != NULL) { parent = *p; @@ -1592,12 +1602,14 @@ static void hierarchy_insert_output_entry(struct rb_root *root, if (hist_entry__sort(he, iter) > 0) p = &parent->rb_left; - else + else { p = &parent->rb_right; + leftmost = false; + } } rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + rb_insert_color_cached(&he->rb_node, root, leftmost); /* update column width of dynamic entry */ perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { @@ -1608,16 +1620,16 @@ static void hierarchy_insert_output_entry(struct rb_root *root, static void hists__hierarchy_output_resort(struct hists *hists, struct ui_progress *prog, - struct rb_root *root_in, - struct rb_root *root_out, + struct rb_root_cached *root_in, + struct rb_root_cached *root_out, u64 min_callchain_hits, bool use_callchain) { struct rb_node *node; struct hist_entry *he; - *root_out = RB_ROOT; - node = rb_first(root_in); + *root_out = RB_ROOT_CACHED; + node = rb_first_cached(root_in); while (node) { he = rb_entry(node, struct hist_entry, rb_node_in); @@ -1660,15 +1672,16 @@ static void hists__hierarchy_output_resort(struct hists *hists, } } -static void __hists__insert_output_entry(struct rb_root *entries, +static void __hists__insert_output_entry(struct rb_root_cached *entries, struct hist_entry *he, u64 min_callchain_hits, bool use_callchain) { - struct rb_node **p = &entries->rb_node; + struct rb_node **p = &entries->rb_root.rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; struct perf_hpp_fmt *fmt; + bool leftmost = true; if (use_callchain) { if (callchain_param.mode == CHAIN_GRAPH_REL) { @@ -1689,12 +1702,14 @@ static void __hists__insert_output_entry(struct rb_root *entries, if (hist_entry__sort(he, iter) > 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, entries); + rb_insert_color_cached(&he->rb_node, entries, leftmost); perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) { if (perf_hpp__is_dynamic_entry(fmt) && @@ -1706,7 +1721,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, static void output_resort(struct hists *hists, struct ui_progress *prog, bool use_callchain, hists__resort_cb_t cb) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *next; struct hist_entry *n; u64 callchain_total; @@ -1736,8 +1751,8 @@ static void output_resort(struct hists *hists, struct ui_progress *prog, else root = hists->entries_in; - next = rb_first(root); - hists->entries = RB_ROOT; + next = rb_first_cached(root); + hists->entries = RB_ROOT_CACHED; while (next) { n = rb_entry(next, struct hist_entry, rb_node_in); @@ -1798,7 +1813,7 @@ struct rb_node *rb_hierarchy_last(struct rb_node *node) struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node); while (can_goto_child(he, HMD_NORMAL)) { - node = rb_last(&he->hroot_out); + node = rb_last(&he->hroot_out.rb_root); he = rb_entry(node, struct hist_entry, rb_node); } return node; @@ -1809,7 +1824,7 @@ struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_di struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node); if (can_goto_child(he, hmd)) - node = rb_first(&he->hroot_out); + node = rb_first_cached(&he->hroot_out); else node = rb_next(node); @@ -1847,7 +1862,7 @@ bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit) if (he->leaf) return false; - node = rb_first(&he->hroot_out); + node = rb_first_cached(&he->hroot_out); child = rb_entry(node, struct hist_entry, rb_node); while (node && child->filtered) { @@ -1965,7 +1980,7 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil hists__reset_filter_stats(hists); hists__reset_col_len(hists); - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (filter(hists, h)) @@ -1975,13 +1990,15 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil } } -static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he) +static void resort_filtered_entry(struct rb_root_cached *root, + struct hist_entry *he) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; - struct rb_root new_root = RB_ROOT; + struct rb_root_cached new_root = RB_ROOT_CACHED; struct rb_node *nd; + bool leftmost = true; while (*p != NULL) { parent = *p; @@ -1989,22 +2006,24 @@ static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he) if (hist_entry__sort(he, iter) > 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + rb_insert_color_cached(&he->rb_node, root, leftmost); if (he->leaf || he->filtered) return; - nd = rb_first(&he->hroot_out); + nd = rb_first_cached(&he->hroot_out); while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); nd = rb_next(nd); - rb_erase(&h->rb_node, &he->hroot_out); + rb_erase_cached(&h->rb_node, &he->hroot_out); resort_filtered_entry(&new_root, h); } @@ -2015,14 +2034,14 @@ static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he) static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg) { struct rb_node *nd; - struct rb_root new_root = RB_ROOT; + struct rb_root_cached new_root = RB_ROOT_CACHED; hists->stats.nr_non_filtered_samples = 0; hists__reset_filter_stats(hists); hists__reset_col_len(hists); - nd = rb_first(&hists->entries); + nd = rb_first_cached(&hists->entries); while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); int ret; @@ -2066,12 +2085,12 @@ static void hists__filter_hierarchy(struct hists *hists, int type, const void *a * resort output after applying a new filter since filter in a lower * hierarchy can change periods in a upper hierarchy. */ - nd = rb_first(&hists->entries); + nd = rb_first_cached(&hists->entries); while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); nd = rb_next(nd); - rb_erase(&h->rb_node, &hists->entries); + rb_erase_cached(&h->rb_node, &hists->entries); resort_filtered_entry(&new_root, h); } @@ -2140,18 +2159,19 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered) static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct hist_entry *pair) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; int64_t cmp; + bool leftmost = true; if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; - p = &root->rb_node; + p = &root->rb_root.rb_node; while (*p != NULL) { parent = *p; @@ -2164,8 +2184,10 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, if (cmp < 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } he = hist_entry__new(pair, true); @@ -2175,7 +2197,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, if (symbol_conf.cumulate_callchain) memset(he->stat_acc, 0, sizeof(he->stat)); rb_link_node(&he->rb_node_in, parent, p); - rb_insert_color(&he->rb_node_in, root); + rb_insert_color_cached(&he->rb_node_in, root, leftmost); hists__inc_stats(hists, he); he->dummy = true; } @@ -2184,15 +2206,16 @@ out: } static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists, - struct rb_root *root, + struct rb_root_cached *root, struct hist_entry *pair) { struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; struct perf_hpp_fmt *fmt; + bool leftmost = true; - p = &root->rb_node; + p = &root->rb_root.rb_node; while (*p != NULL) { int64_t cmp = 0; @@ -2209,14 +2232,16 @@ static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists, if (cmp < 0) p = &parent->rb_left; - else + else { p = &parent->rb_right; + leftmost = false; + } } he = hist_entry__new(pair, true); if (he) { rb_link_node(&he->rb_node_in, parent, p); - rb_insert_color(&he->rb_node_in, root); + rb_insert_color_cached(&he->rb_node_in, root, leftmost); he->dummy = true; he->hists = hists; @@ -2233,9 +2258,9 @@ static struct hist_entry *hists__find_entry(struct hists *hists, struct rb_node *n; if (hists__has(hists, need_collapse)) - n = hists->entries_collapsed.rb_node; + n = hists->entries_collapsed.rb_root.rb_node; else - n = hists->entries_in->rb_node; + n = hists->entries_in->rb_root.rb_node; while (n) { struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in); @@ -2252,10 +2277,10 @@ static struct hist_entry *hists__find_entry(struct hists *hists, return NULL; } -static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root, +static struct hist_entry *hists__find_hierarchy_entry(struct rb_root_cached *root, struct hist_entry *he) { - struct rb_node *n = root->rb_node; + struct rb_node *n = root->rb_root.rb_node; while (n) { struct hist_entry *iter; @@ -2280,13 +2305,13 @@ static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root, return NULL; } -static void hists__match_hierarchy(struct rb_root *leader_root, - struct rb_root *other_root) +static void hists__match_hierarchy(struct rb_root_cached *leader_root, + struct rb_root_cached *other_root) { struct rb_node *nd; struct hist_entry *pos, *pair; - for (nd = rb_first(leader_root); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(leader_root); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct hist_entry, rb_node_in); pair = hists__find_hierarchy_entry(other_root, pos); @@ -2302,7 +2327,7 @@ static void hists__match_hierarchy(struct rb_root *leader_root, */ void hists__match(struct hists *leader, struct hists *other) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *nd; struct hist_entry *pos, *pair; @@ -2317,7 +2342,7 @@ void hists__match(struct hists *leader, struct hists *other) else root = leader->entries_in; - for (nd = rb_first(root); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct hist_entry, rb_node_in); pair = hists__find_entry(other, pos); @@ -2328,13 +2353,13 @@ void hists__match(struct hists *leader, struct hists *other) static int hists__link_hierarchy(struct hists *leader_hists, struct hist_entry *parent, - struct rb_root *leader_root, - struct rb_root *other_root) + struct rb_root_cached *leader_root, + struct rb_root_cached *other_root) { struct rb_node *nd; struct hist_entry *pos, *leader; - for (nd = rb_first(other_root); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(other_root); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct hist_entry, rb_node_in); if (hist_entry__has_pairs(pos)) { @@ -2377,7 +2402,7 @@ static int hists__link_hierarchy(struct hists *leader_hists, */ int hists__link(struct hists *leader, struct hists *other) { - struct rb_root *root; + struct rb_root_cached *root; struct rb_node *nd; struct hist_entry *pos, *pair; @@ -2393,7 +2418,7 @@ int hists__link(struct hists *leader, struct hists *other) else root = other->entries_in; - for (nd = rb_first(root); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct hist_entry, rb_node_in); if (!hist_entry__has_pairs(pos)) { @@ -2566,10 +2591,10 @@ int perf_hist_config(const char *var, const char *value) int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) { memset(hists, 0, sizeof(*hists)); - hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; + hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT_CACHED; hists->entries_in = &hists->entries_in_array[0]; - hists->entries_collapsed = RB_ROOT; - hists->entries = RB_ROOT; + hists->entries_collapsed = RB_ROOT_CACHED; + hists->entries = RB_ROOT_CACHED; pthread_mutex_init(&hists->lock, NULL); hists->socket_filter = -1; hists->hpp_list = hpp_list; @@ -2577,14 +2602,14 @@ int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) return 0; } -static void hists__delete_remaining_entries(struct rb_root *root) +static void hists__delete_remaining_entries(struct rb_root_cached *root) { struct rb_node *node; struct hist_entry *he; - while (!RB_EMPTY_ROOT(root)) { - node = rb_first(root); - rb_erase(node, root); + while (!RB_EMPTY_ROOT(&root->rb_root)) { + node = rb_first_cached(root); + rb_erase_cached(node, root); he = rb_entry(node, struct hist_entry, rb_node_in); hist_entry__delete(he); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 664b5eda8d51..08267af7439c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -70,10 +70,10 @@ struct thread; struct dso; struct hists { - struct rb_root entries_in_array[2]; - struct rb_root *entries_in; - struct rb_root entries; - struct rb_root entries_collapsed; + struct rb_root_cached entries_in_array[2]; + struct rb_root_cached *entries_in; + struct rb_root_cached entries; + struct rb_root_cached entries_collapsed; u64 nr_entries; u64 nr_non_filtered_entries; u64 callchain_period; @@ -230,7 +230,7 @@ static __pure inline bool hists__has_callchains(struct hists *hists) int hists__init(void); int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); -struct rb_root *hists__get_rotate_entries_in(struct hists *hists); +struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists); struct perf_hpp { char *buf; diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 85bab8735fa9..5c19ee001299 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -45,7 +45,7 @@ static inline unsigned int intlist__nr_entries(const struct intlist *ilist) /* For intlist iteration */ static inline struct int_node *intlist__first(struct intlist *ilist) { - struct rb_node *rn = rb_first(&ilist->rblist.entries); + struct rb_node *rn = rb_first_cached(&ilist->rblist.entries); return rn ? rb_entry(rn, struct int_node, rb_node) : NULL; } static inline struct int_node *intlist__next(struct int_node *in) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index bf249552a9b0..eda28d3570bc 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -2,6 +2,7 @@ #include <sys/sysmacros.h> #include <sys/types.h> #include <errno.h> +#include <libgen.h> #include <stdio.h> #include <stdlib.h> #include <string.h> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 143f7057d581..66f019fdc510 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -21,6 +21,7 @@ #include "unwind.h" #include "linux/hash.h" #include "asm/bug.h" +#include "bpf-event.h" #include "sane_ctype.h" #include <symbol/kallsyms.h> @@ -41,7 +42,7 @@ static void machine__threads_init(struct machine *machine) for (i = 0; i < THREADS__TABLE_SIZE; i++) { struct threads *threads = &machine->threads[i]; - threads->entries = RB_ROOT; + threads->entries = RB_ROOT_CACHED; init_rwsem(&threads->lock); threads->nr = 0; INIT_LIST_HEAD(&threads->dead); @@ -179,7 +180,7 @@ void machine__delete_threads(struct machine *machine) for (i = 0; i < THREADS__TABLE_SIZE; i++) { struct threads *threads = &machine->threads[i]; down_write(&threads->lock); - nd = rb_first(&threads->entries); + nd = rb_first_cached(&threads->entries); while (nd) { struct thread *t = rb_entry(nd, struct thread, rb_node); @@ -222,7 +223,7 @@ void machine__delete(struct machine *machine) void machines__init(struct machines *machines) { machine__init(&machines->host, "", HOST_KERNEL_ID); - machines->guests = RB_ROOT; + machines->guests = RB_ROOT_CACHED; } void machines__exit(struct machines *machines) @@ -234,9 +235,10 @@ void machines__exit(struct machines *machines) struct machine *machines__add(struct machines *machines, pid_t pid, const char *root_dir) { - struct rb_node **p = &machines->guests.rb_node; + struct rb_node **p = &machines->guests.rb_root.rb_node; struct rb_node *parent = NULL; struct machine *pos, *machine = malloc(sizeof(*machine)); + bool leftmost = true; if (machine == NULL) return NULL; @@ -251,12 +253,14 @@ struct machine *machines__add(struct machines *machines, pid_t pid, pos = rb_entry(parent, struct machine, rb_node); if (pid < pos->pid) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&machine->rb_node, parent, p); - rb_insert_color(&machine->rb_node, &machines->guests); + rb_insert_color_cached(&machine->rb_node, &machines->guests, leftmost); return machine; } @@ -267,7 +271,7 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec) machines->host.comm_exec = comm_exec; - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) { struct machine *machine = rb_entry(nd, struct machine, rb_node); machine->comm_exec = comm_exec; @@ -276,7 +280,7 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec) struct machine *machines__find(struct machines *machines, pid_t pid) { - struct rb_node **p = &machines->guests.rb_node; + struct rb_node **p = &machines->guests.rb_root.rb_node; struct rb_node *parent = NULL; struct machine *machine; struct machine *default_machine = NULL; @@ -339,7 +343,7 @@ void machines__process_guests(struct machines *machines, { struct rb_node *nd; - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); process(pos, data); } @@ -352,7 +356,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) machines->host.id_hdr_size = id_hdr_size; - for (node = rb_first(&machines->guests); node; node = rb_next(node)) { + for (node = rb_first_cached(&machines->guests); node; + node = rb_next(node)) { machine = rb_entry(node, struct machine, rb_node); machine->id_hdr_size = id_hdr_size; } @@ -465,9 +470,10 @@ static struct thread *____machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid, bool create) { - struct rb_node **p = &threads->entries.rb_node; + struct rb_node **p = &threads->entries.rb_root.rb_node; struct rb_node *parent = NULL; struct thread *th; + bool leftmost = true; th = threads__get_last_match(threads, machine, pid, tid); if (th) @@ -485,8 +491,10 @@ static struct thread *____machine__findnew_thread(struct machine *machine, if (tid < th->tid) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } if (!create) @@ -495,7 +503,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, th = thread__new(pid, tid); if (th != NULL) { rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, &threads->entries); + rb_insert_color_cached(&th->rb_node, &threads->entries, leftmost); /* * We have to initialize map_groups separately @@ -506,7 +514,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * leader and that would screwed the rb tree. */ if (thread__init_map_groups(th, machine)) { - rb_erase_init(&th->rb_node, &threads->entries); + rb_erase_cached(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); thread__put(th); return NULL; @@ -681,6 +689,59 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } +static int machine__process_ksymbol_register(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct symbol *sym; + struct map *map; + + map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr); + if (!map) { + map = dso__new_map(event->ksymbol_event.name); + if (!map) + return -ENOMEM; + + map->start = event->ksymbol_event.addr; + map->pgoff = map->start; + map->end = map->start + event->ksymbol_event.len; + map_groups__insert(&machine->kmaps, map); + } + + sym = symbol__new(event->ksymbol_event.addr, event->ksymbol_event.len, + 0, 0, event->ksymbol_event.name); + if (!sym) + return -ENOMEM; + dso__insert_symbol(map->dso, sym); + return 0; +} + +static int machine__process_ksymbol_unregister(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct map *map; + + map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr); + if (map) + map_groups__remove(&machine->kmaps, map); + + return 0; +} + +int machine__process_ksymbol(struct machine *machine __maybe_unused, + union perf_event *event, + struct perf_sample *sample) +{ + if (dump_trace) + perf_event__fprintf_ksymbol(event, stdout); + + if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER) + return machine__process_ksymbol_unregister(machine, event, + sample); + return machine__process_ksymbol_register(machine, event, sample); +} + static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename) { const char *dup_filename; @@ -744,7 +805,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) struct rb_node *nd; size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp); - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret += __dsos__fprintf(&pos->dsos.head, fp); } @@ -764,7 +825,7 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, struct rb_node *nd; size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm); - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm); } @@ -804,7 +865,8 @@ size_t machine__fprintf(struct machine *machine, FILE *fp) ret = fprintf(fp, "Threads: %u\n", threads->nr); - for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&threads->entries); nd; + nd = rb_next(nd)) { struct thread *pos = rb_entry(nd, struct thread, rb_node); ret += thread__fprintf(pos, fp); @@ -1107,7 +1169,7 @@ failure: void machines__destroy_kernel_maps(struct machines *machines) { - struct rb_node *next = rb_first(&machines->guests); + struct rb_node *next = rb_first_cached(&machines->guests); machine__destroy_kernel_maps(&machines->host); @@ -1115,7 +1177,7 @@ void machines__destroy_kernel_maps(struct machines *machines) struct machine *pos = rb_entry(next, struct machine, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, &machines->guests); + rb_erase_cached(&pos->rb_node, &machines->guests); machine__delete(pos); } } @@ -1680,7 +1742,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) down_write(&threads->lock); - rb_erase_init(&th->rb_node, &threads->entries); + rb_erase_cached(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); --threads->nr; /* @@ -1812,6 +1874,10 @@ int machine__process_event(struct machine *machine, union perf_event *event, case PERF_RECORD_SWITCH: case PERF_RECORD_SWITCH_CPU_WIDE: ret = machine__process_switch_event(machine, event); break; + case PERF_RECORD_KSYMBOL: + ret = machine__process_ksymbol(machine, event, sample); break; + case PERF_RECORD_BPF_EVENT: + ret = machine__process_bpf_event(machine, event, sample); break; default: ret = -1; break; @@ -2453,7 +2519,8 @@ int machine__for_each_thread(struct machine *machine, for (i = 0; i < THREADS__TABLE_SIZE; i++) { threads = &machine->threads[i]; - for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&threads->entries); nd; + nd = rb_next(nd)) { thread = rb_entry(nd, struct thread, rb_node); rc = fn(thread, priv); if (rc != 0) @@ -2480,7 +2547,7 @@ int machines__for_each_thread(struct machines *machines, if (rc != 0) return rc; - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) { struct machine *machine = rb_entry(nd, struct machine, rb_node); rc = machine__for_each_thread(machine, fn, priv); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index a5d1da60f751..e2f3df45410a 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -29,11 +29,11 @@ struct vdso_info; #define THREADS__TABLE_SIZE (1 << THREADS__TABLE_BITS) struct threads { - struct rb_root entries; - struct rw_semaphore lock; - unsigned int nr; - struct list_head dead; - struct thread *last_match; + struct rb_root_cached entries; + struct rw_semaphore lock; + unsigned int nr; + struct list_head dead; + struct thread *last_match; }; struct machine { @@ -130,6 +130,9 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); +int machine__process_ksymbol(struct machine *machine, + union perf_event *event, + struct perf_sample *sample); int machine__process_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); @@ -137,7 +140,7 @@ typedef void (*machine__process_t)(struct machine *machine, void *data); struct machines { struct machine host; - struct rb_root guests; + struct rb_root_cached guests; }; void machines__init(struct machines *machines); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 6751301a755c..cf407cc9d915 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -286,8 +286,8 @@ void map__put(struct map *map) void map__fixup_start(struct map *map) { - struct rb_root *symbols = &map->dso->symbols; - struct rb_node *nd = rb_first(symbols); + struct rb_root_cached *symbols = &map->dso->symbols; + struct rb_node *nd = rb_first_cached(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); map->start = sym->start; @@ -296,8 +296,8 @@ void map__fixup_start(struct map *map) void map__fixup_end(struct map *map) { - struct rb_root *symbols = &map->dso->symbols; - struct rb_node *nd = rb_last(symbols); + struct rb_root_cached *symbols = &map->dso->symbols; + struct rb_node *nd = rb_last(&symbols->rb_root); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); map->end = sym->end; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index a28f9b5cc4ff..8529cbd3955b 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -352,7 +352,7 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, else if (metrics && !raw) printf("\nMetrics:\n\n"); - for (node = rb_first(&groups.entries); node; node = next) { + for (node = rb_first_cached(&groups.entries); node; node = next) { struct mep *me = container_of(node, struct mep, nd); if (metricgroups) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 18a59fba97ff..4008f0cc36e5 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -35,6 +35,7 @@ #include "util.h" #include "event.h" +#include "namespaces.h" #include "strlist.h" #include "strfilter.h" #include "debug.h" @@ -3528,7 +3529,8 @@ int show_available_funcs(const char *target, struct nsinfo *nsi, /* Show all (filtered) symbols */ setup_pager(); - for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&map->dso->symbol_names); nd; + nd = rb_next(nd)) { struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); if (strfilter__compare(_filter, pos->sym.name)) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 15a98c3a2a2f..05c8d571a901 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -4,8 +4,9 @@ #include <linux/compiler.h> #include <stdbool.h> -#include "intlist.h" -#include "namespaces.h" + +struct intlist; +struct nsinfo; /* Probe related configurations */ struct probe_conf { diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 0b1195cad0e5..4062bc4412a9 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -20,6 +20,7 @@ #include <sys/types.h> #include <sys/uio.h> #include <unistd.h> +#include "namespaces.h" #include "util.h" #include "event.h" #include "strlist.h" diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h index a920f702a74d..376e86cb4c3c 100644 --- a/tools/perf/util/rb_resort.h +++ b/tools/perf/util/rb_resort.h @@ -140,12 +140,12 @@ struct __name##_sorted *__name = __name##_sorted__new /* For 'struct intlist' */ #define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \ - DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries, \ + DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root, \ __ilist->rblist.nr_entries) /* For 'struct machine->threads' */ -#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket) \ - DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries, \ - __machine->threads[hash_bucket].nr) +#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket) \ + DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries.rb_root, \ + __machine->threads[hash_bucket].nr) #endif /* _PERF_RESORT_RB_H_ */ diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c index 0efc3258c648..11e07fab20dc 100644 --- a/tools/perf/util/rblist.c +++ b/tools/perf/util/rblist.c @@ -13,8 +13,9 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry) { - struct rb_node **p = &rblist->entries.rb_node; + struct rb_node **p = &rblist->entries.rb_root.rb_node; struct rb_node *parent = NULL, *new_node; + bool leftmost = true; while (*p != NULL) { int rc; @@ -24,8 +25,10 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry) rc = rblist->node_cmp(parent, new_entry); if (rc > 0) p = &(*p)->rb_left; - else if (rc < 0) + else if (rc < 0) { p = &(*p)->rb_right; + leftmost = false; + } else return -EEXIST; } @@ -35,7 +38,7 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry) return -ENOMEM; rb_link_node(new_node, parent, p); - rb_insert_color(new_node, &rblist->entries); + rb_insert_color_cached(new_node, &rblist->entries, leftmost); ++rblist->nr_entries; return 0; @@ -43,7 +46,7 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry) void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node) { - rb_erase(rb_node, &rblist->entries); + rb_erase_cached(rb_node, &rblist->entries); --rblist->nr_entries; rblist->node_delete(rblist, rb_node); } @@ -52,8 +55,9 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist, const void *entry, bool create) { - struct rb_node **p = &rblist->entries.rb_node; + struct rb_node **p = &rblist->entries.rb_root.rb_node; struct rb_node *parent = NULL, *new_node = NULL; + bool leftmost = true; while (*p != NULL) { int rc; @@ -63,8 +67,10 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist, rc = rblist->node_cmp(parent, entry); if (rc > 0) p = &(*p)->rb_left; - else if (rc < 0) + else if (rc < 0) { p = &(*p)->rb_right; + leftmost = false; + } else return parent; } @@ -73,7 +79,8 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist, new_node = rblist->node_new(rblist, entry); if (new_node) { rb_link_node(new_node, parent, p); - rb_insert_color(new_node, &rblist->entries); + rb_insert_color_cached(new_node, + &rblist->entries, leftmost); ++rblist->nr_entries; } } @@ -94,7 +101,7 @@ struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry) void rblist__init(struct rblist *rblist) { if (rblist != NULL) { - rblist->entries = RB_ROOT; + rblist->entries = RB_ROOT_CACHED; rblist->nr_entries = 0; } @@ -103,7 +110,7 @@ void rblist__init(struct rblist *rblist) void rblist__exit(struct rblist *rblist) { - struct rb_node *pos, *next = rb_first(&rblist->entries); + struct rb_node *pos, *next = rb_first_cached(&rblist->entries); while (next) { pos = next; @@ -124,7 +131,8 @@ struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx) { struct rb_node *node; - for (node = rb_first(&rblist->entries); node; node = rb_next(node)) { + for (node = rb_first_cached(&rblist->entries); node; + node = rb_next(node)) { if (!idx--) return node; } diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h index 76df15c27f5f..14b232a4d0b6 100644 --- a/tools/perf/util/rblist.h +++ b/tools/perf/util/rblist.h @@ -20,7 +20,7 @@ */ struct rblist { - struct rb_root entries; + struct rb_root_cached entries; unsigned int nr_entries; int (*node_cmp)(struct rb_node *rbn, const void *entry); diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h new file mode 100644 index 000000000000..d4356030b504 --- /dev/null +++ b/tools/perf/util/s390-cpumcf-kernel.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Support for s390 CPU measurement counter set diagnostic facility + * + * Copyright IBM Corp. 2019 + Author(s): Hendrik Brueckner <brueckner@linux.ibm.com> + * Thomas Richter <tmricht@linux.ibm.com> + */ +#ifndef S390_CPUMCF_KERNEL_H +#define S390_CPUMCF_KERNEL_H + +#define S390_CPUMCF_DIAG_DEF 0xfeef /* Counter diagnostic entry ID */ +#define PERF_EVENT_CPUM_CF_DIAG 0xBC000 /* Event: Counter sets */ + +struct cf_ctrset_entry { /* CPU-M CF counter set entry (8 byte) */ + unsigned int def:16; /* 0-15 Data Entry Format */ + unsigned int set:16; /* 16-23 Counter set identifier */ + unsigned int ctr:16; /* 24-39 Number of stored counters */ + unsigned int res1:16; /* 40-63 Reserved */ +}; + +struct cf_trailer_entry { /* CPU-M CF trailer for raw traces (64 byte) */ + /* 0 - 7 */ + union { + struct { + unsigned int clock_base:1; /* TOD clock base */ + unsigned int speed:1; /* CPU speed */ + /* Measurement alerts */ + unsigned int mtda:1; /* Loss of MT ctr. data alert */ + unsigned int caca:1; /* Counter auth. change alert */ + unsigned int lcda:1; /* Loss of counter data alert */ + }; + unsigned long flags; /* 0-63 All indicators */ + }; + /* 8 - 15 */ + unsigned int cfvn:16; /* 64-79 Ctr First Version */ + unsigned int csvn:16; /* 80-95 Ctr Second Version */ + unsigned int cpu_speed:32; /* 96-127 CPU speed */ + /* 16 - 23 */ + unsigned long timestamp; /* 128-191 Timestamp (TOD) */ + /* 24 - 55 */ + union { + struct { + unsigned long progusage1; + unsigned long progusage2; + unsigned long progusage3; + unsigned long tod_base; + }; + unsigned long progusage[4]; + }; + /* 56 - 63 */ + unsigned int mach_type:16; /* Machine type */ + unsigned int res1:16; /* Reserved */ + unsigned int res2:32; /* Reserved */ +}; + +#define CPUMF_CTR_SET_BASIC 0 /* Basic Counter Set */ +#define CPUMF_CTR_SET_USER 1 /* Problem-State Counter Set */ +#define CPUMF_CTR_SET_CRYPTO 2 /* Crypto-Activity Counter Set */ +#define CPUMF_CTR_SET_EXT 3 /* Extended Counter Set */ +#define CPUMF_CTR_SET_MT_DIAG 4 /* MT-diagnostic Counter Set */ +#endif diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 68b2570304ec..835249c77f56 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -162,6 +162,7 @@ #include "auxtrace.h" #include "s390-cpumsf.h" #include "s390-cpumsf-kernel.h" +#include "s390-cpumcf-kernel.h" #include "config.h" struct s390_cpumsf { @@ -184,8 +185,58 @@ struct s390_cpumsf_queue { struct auxtrace_buffer *buffer; int cpu; FILE *logfile; + FILE *logfile_ctr; }; +/* Check if the raw data should be dumped to file. If this is the case and + * the file to dump to has not been opened for writing, do so. + * + * Return 0 on success and greater zero on error so processing continues. + */ +static int s390_cpumcf_dumpctr(struct s390_cpumsf *sf, + struct perf_sample *sample) +{ + struct s390_cpumsf_queue *sfq; + struct auxtrace_queue *q; + int rc = 0; + + if (!sf->use_logfile || sf->queues.nr_queues <= sample->cpu) + return rc; + + q = &sf->queues.queue_array[sample->cpu]; + sfq = q->priv; + if (!sfq) /* Queue not yet allocated */ + return rc; + + if (!sfq->logfile_ctr) { + char *name; + + rc = (sf->logdir) + ? asprintf(&name, "%s/aux.ctr.%02x", + sf->logdir, sample->cpu) + : asprintf(&name, "aux.ctr.%02x", sample->cpu); + if (rc > 0) + sfq->logfile_ctr = fopen(name, "w"); + if (sfq->logfile_ctr == NULL) { + pr_err("Failed to open counter set log file %s, " + "continue...\n", name); + rc = 1; + } + free(name); + } + + if (sfq->logfile_ctr) { + /* See comment above for -4 */ + size_t n = fwrite(sample->raw_data, sample->raw_size - 4, 1, + sfq->logfile_ctr); + if (n != 1) { + pr_err("Failed to write counter set data\n"); + rc = 1; + } + } + return rc; +} + /* Display s390 CPU measurement facility basic-sampling data entry */ static bool s390_cpumsf_basic_show(const char *color, size_t pos, struct hws_basic_entry *basic) @@ -792,7 +843,7 @@ static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample) } static int -s390_cpumsf_process_event(struct perf_session *session __maybe_unused, +s390_cpumsf_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool) @@ -801,6 +852,8 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused, struct s390_cpumsf, auxtrace); u64 timestamp = sample->time; + struct perf_evsel *ev_bc000; + int err = 0; if (dump_trace) @@ -811,6 +864,16 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused, return -EINVAL; } + if (event->header.type == PERF_RECORD_SAMPLE && + sample->raw_size) { + /* Handle event with raw data */ + ev_bc000 = perf_evlist__event2evsel(session->evlist, event); + if (ev_bc000 && + ev_bc000->attr.config == PERF_EVENT_CPUM_CF_DIAG) + err = s390_cpumcf_dumpctr(sf, sample); + return err; + } + if (event->header.type == PERF_RECORD_AUX && event->aux.flags & PERF_AUX_FLAG_TRUNCATED) return s390_cpumsf_lost(sf, sample); @@ -891,9 +954,15 @@ static void s390_cpumsf_free_queues(struct perf_session *session) struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *) queues->queue_array[i].priv; - if (sfq != NULL && sfq->logfile) { - fclose(sfq->logfile); - sfq->logfile = NULL; + if (sfq != NULL) { + if (sfq->logfile) { + fclose(sfq->logfile); + sfq->logfile = NULL; + } + if (sfq->logfile_ctr) { + fclose(sfq->logfile_ctr); + sfq->logfile_ctr = NULL; + } } zfree(&queues->queue_array[i].priv); } diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c new file mode 100644 index 000000000000..6650f599ed9c --- /dev/null +++ b/tools/perf/util/s390-sample-raw.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2019 + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Architecture specific trace_event function. Save event's bc000 raw data + * to file. File name is aux.ctr.## where ## stands for the CPU number the + * sample was taken from. + */ + +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> + +#include <sys/stat.h> +#include <linux/compiler.h> +#include <asm/byteorder.h> + +#include "debug.h" +#include "util.h" +#include "auxtrace.h" +#include "session.h" +#include "evlist.h" +#include "config.h" +#include "color.h" +#include "sample-raw.h" +#include "s390-cpumcf-kernel.h" +#include "pmu-events/pmu-events.h" + +static size_t ctrset_size(struct cf_ctrset_entry *set) +{ + return sizeof(*set) + set->ctr * sizeof(u64); +} + +static bool ctrset_valid(struct cf_ctrset_entry *set) +{ + return set->def == S390_CPUMCF_DIAG_DEF; +} + +/* CPU Measurement Counter Facility raw data is a byte stream. It is 8 byte + * aligned and might have trailing padding bytes. + * Display the raw data on screen. + */ +static bool s390_cpumcfdg_testctr(struct perf_sample *sample) +{ + size_t len = sample->raw_size, offset = 0; + unsigned char *buf = sample->raw_data; + struct cf_trailer_entry *te; + struct cf_ctrset_entry *cep, ce; + + if (!len) + return false; + while (offset < len) { + cep = (struct cf_ctrset_entry *)(buf + offset); + ce.def = be16_to_cpu(cep->def); + ce.set = be16_to_cpu(cep->set); + ce.ctr = be16_to_cpu(cep->ctr); + ce.res1 = be16_to_cpu(cep->res1); + + if (!ctrset_valid(&ce) || offset + ctrset_size(&ce) > len) { + /* Raw data for counter sets are always multiple of 8 + * bytes. Prepending a 4 bytes size field to the + * raw data block in the sample causes the perf tool + * to append 4 padding bytes to make the raw data part + * of the sample a multiple of eight bytes again. + * + * If the last entry (trailer) is 4 bytes off the raw + * area data end, all is good. + */ + if (len - offset - sizeof(*te) == 4) + break; + pr_err("Invalid counter set entry at %zd\n", offset); + return false; + } + offset += ctrset_size(&ce); + } + return true; +} + +/* Dump event bc000 on screen, already tested on correctness. */ +static void s390_cpumcfdg_dumptrail(const char *color, size_t offset, + struct cf_trailer_entry *tep) +{ + struct cf_trailer_entry te; + + te.flags = be64_to_cpu(tep->flags); + te.cfvn = be16_to_cpu(tep->cfvn); + te.csvn = be16_to_cpu(tep->csvn); + te.cpu_speed = be32_to_cpu(tep->cpu_speed); + te.timestamp = be64_to_cpu(tep->timestamp); + te.progusage1 = be64_to_cpu(tep->progusage1); + te.progusage2 = be64_to_cpu(tep->progusage2); + te.progusage3 = be64_to_cpu(tep->progusage3); + te.tod_base = be64_to_cpu(tep->tod_base); + te.mach_type = be16_to_cpu(tep->mach_type); + te.res1 = be16_to_cpu(tep->res1); + te.res2 = be32_to_cpu(tep->res2); + + color_fprintf(stdout, color, " [%#08zx] Trailer:%c%c%c%c%c" + " Cfvn:%d Csvn:%d Speed:%d TOD:%#llx\n", + offset, te.clock_base ? 'T' : ' ', + te.speed ? 'S' : ' ', te.mtda ? 'M' : ' ', + te.caca ? 'C' : ' ', te.lcda ? 'L' : ' ', + te.cfvn, te.csvn, te.cpu_speed, te.timestamp); + color_fprintf(stdout, color, "\t\t1:%lx 2:%lx 3:%lx TOD-Base:%#llx" + " Type:%x\n\n", + te.progusage1, te.progusage2, te.progusage3, + te.tod_base, te.mach_type); +} + +/* Return starting number of a counter set */ +static int get_counterset_start(int setnr) +{ + switch (setnr) { + case CPUMF_CTR_SET_BASIC: /* Basic counter set */ + return 0; + case CPUMF_CTR_SET_USER: /* Problem state counter set */ + return 32; + case CPUMF_CTR_SET_CRYPTO: /* Crypto counter set */ + return 64; + case CPUMF_CTR_SET_EXT: /* Extended counter set */ + return 128; + case CPUMF_CTR_SET_MT_DIAG: /* Diagnostic counter set */ + return 448; + default: + return -1; + } +} + +/* Scan the PMU table and extract the logical name of a counter from the + * PMU events table. Input is the counter set and counter number with in the + * set. Construct the event number and use this as key. If they match return + * the name of this counter. + * If no match is found a NULL pointer is returned. + */ +static const char *get_counter_name(int set, int nr, struct pmu_events_map *map) +{ + int rc, event_nr, wanted = get_counterset_start(set) + nr; + + if (map) { + struct pmu_event *evp = map->table; + + for (; evp->name || evp->event || evp->desc; ++evp) { + if (evp->name == NULL || evp->event == NULL) + continue; + rc = sscanf(evp->event, "event=%x", &event_nr); + if (rc == 1 && event_nr == wanted) + return evp->name; + } + } + return NULL; +} + +static void s390_cpumcfdg_dump(struct perf_sample *sample) +{ + size_t i, len = sample->raw_size, offset = 0; + unsigned char *buf = sample->raw_data; + const char *color = PERF_COLOR_BLUE; + struct cf_ctrset_entry *cep, ce; + struct pmu_events_map *map; + struct perf_pmu pmu; + u64 *p; + + memset(&pmu, 0, sizeof(pmu)); + map = perf_pmu__find_map(&pmu); + while (offset < len) { + cep = (struct cf_ctrset_entry *)(buf + offset); + + ce.def = be16_to_cpu(cep->def); + ce.set = be16_to_cpu(cep->set); + ce.ctr = be16_to_cpu(cep->ctr); + ce.res1 = be16_to_cpu(cep->res1); + + if (!ctrset_valid(&ce)) { /* Print trailer */ + s390_cpumcfdg_dumptrail(color, offset, + (struct cf_trailer_entry *)cep); + return; + } + + color_fprintf(stdout, color, " [%#08zx] Counterset:%d" + " Counters:%d\n", offset, ce.set, ce.ctr); + for (i = 0, p = (u64 *)(cep + 1); i < ce.ctr; ++i, ++p) { + const char *ev_name = get_counter_name(ce.set, i, map); + + color_fprintf(stdout, color, + "\tCounter:%03d %s Value:%#018lx\n", i, + ev_name ?: "<unknown>", be64_to_cpu(*p)); + } + offset += ctrset_size(&ce); + } +} + +/* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events + * and if the event was triggered by a counter set diagnostic event display + * its raw data. + * The function is only invoked when the dump flag -D is set. + */ +void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, union perf_event *event, + struct perf_sample *sample) +{ + struct perf_evsel *ev_bc000; + + if (event->header.type != PERF_RECORD_SAMPLE) + return; + + ev_bc000 = perf_evlist__event2evsel(evlist, event); + if (ev_bc000 == NULL || + ev_bc000->attr.config != PERF_EVENT_CPUM_CF_DIAG) + return; + + /* Display raw data on screen */ + if (!s390_cpumcfdg_testctr(sample)) { + pr_err("Invalid counter set data encountered\n"); + return; + } + s390_cpumcfdg_dump(sample); +} diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c new file mode 100644 index 000000000000..c21e1311fb0f --- /dev/null +++ b/tools/perf/util/sample-raw.c @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <string.h> +#include "evlist.h" +#include "env.h" +#include "sample-raw.h" + +/* + * Check platform the perf data file was created on and perform platform + * specific interpretation. + */ +void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist) +{ + const char *arch_pf = perf_env__arch(evlist->env); + + if (arch_pf && !strcmp("s390", arch_pf)) + evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw; +} diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h new file mode 100644 index 000000000000..95d445c87e93 --- /dev/null +++ b/tools/perf/util/sample-raw.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SAMPLE_RAW_H +#define __SAMPLE_RAW_H 1 + +struct perf_evlist; +union perf_event; +struct perf_sample; + +void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample); + +void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist); +#endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 87ef16a1b17e..7059d1be2d09 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -733,8 +733,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize( - (const char *)&evsel->attr, sizeof(evsel->attr))); + pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->attr, sizeof(evsel->attr))); pydict_set_item_string_decref(dict_sample, "pid", _PyLong_FromLong(sample->pid)); @@ -1494,34 +1493,40 @@ static void _free_command_line(wchar_t **command_line, int num) static int python_start_script(const char *script, int argc, const char **argv) { struct tables *tables = &tables_global; + PyMODINIT_FUNC (*initfunc)(void); #if PY_MAJOR_VERSION < 3 const char **command_line; #else wchar_t **command_line; #endif - char buf[PATH_MAX]; + /* + * Use a non-const name variable to cope with python 2.6's + * PyImport_AppendInittab prototype + */ + char buf[PATH_MAX], name[19] = "perf_trace_context"; int i, err = 0; FILE *fp; #if PY_MAJOR_VERSION < 3 + initfunc = initperf_trace_context; command_line = malloc((argc + 1) * sizeof(const char *)); command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; #else + initfunc = PyInit_perf_trace_context; command_line = malloc((argc + 1) * sizeof(wchar_t *)); command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); #endif + PyImport_AppendInittab(name, initfunc); Py_Initialize(); #if PY_MAJOR_VERSION < 3 - initperf_trace_context(); PySys_SetArgv(argc + 1, (char **)command_line); #else - PyInit_perf_trace_context(); PySys_SetArgv(argc + 1, command_line); #endif diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5456c84c7dd1..24fd62528a33 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -23,6 +23,7 @@ #include "auxtrace.h" #include "thread.h" #include "thread-stack.h" +#include "sample-raw.h" #include "stat.h" #include "arch/common.h" @@ -147,6 +148,8 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_session__set_id_hdr_size(session); perf_session__set_comm_exec(session); } + + perf_evlist__init_trace_event_sample_raw(session->evlist); } } else { session->machines.host.env = &perf_env; @@ -376,6 +379,10 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->itrace_start = perf_event__process_itrace_start; if (tool->context_switch == NULL) tool->context_switch = perf_event__process_switch; + if (tool->ksymbol == NULL) + tool->ksymbol = perf_event__process_ksymbol; + if (tool->bpf_event == NULL) + tool->bpf_event = perf_event__process_bpf_event; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -1065,6 +1072,8 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event, file_offset, event->header.size, event->header.type); trace_event(event); + if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw) + evlist->trace_event_sample_raw(evlist, event, sample); if (sample) perf_evlist__print_tstamp(evlist, event, sample); @@ -1305,6 +1314,10 @@ static int machines__deliver_event(struct machines *machines, case PERF_RECORD_SWITCH: case PERF_RECORD_SWITCH_CPU_WIDE: return tool->context_switch(tool, event, sample, machine); + case PERF_RECORD_KSYMBOL: + return tool->ksymbol(tool, event, sample, machine); + case PERF_RECORD_BPF_EVENT: + return tool->bpf_event(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -1820,38 +1833,35 @@ fetch_mmaped_event(struct perf_session *session, #define NUM_MMAPS 128 #endif -static int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, - u64 file_size) +struct reader { + int fd; + u64 data_size; + u64 data_offset; +}; + +static int +reader__process_events(struct reader *rd, struct perf_session *session, + struct ui_progress *prog) { - struct ordered_events *oe = &session->ordered_events; - struct perf_tool *tool = session->tool; - int fd = perf_data__fd(session->data); + u64 data_size = rd->data_size; u64 head, page_offset, file_offset, file_pos, size; - int err, mmap_prot, mmap_flags, map_idx = 0; + int err = 0, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; - struct ui_progress prog; s64 skip; - perf_tool__fill_defaults(tool); - - page_offset = page_size * (data_offset / page_size); + page_offset = page_size * (rd->data_offset / page_size); file_offset = page_offset; - head = data_offset - page_offset; + head = rd->data_offset - page_offset; - if (data_size == 0) - goto out; - - if (data_offset + data_size < file_size) - file_size = data_offset + data_size; + ui_progress__init_size(prog, data_size, "Processing events..."); - ui_progress__init_size(&prog, file_size, "Processing events..."); + data_size += rd->data_offset; mmap_size = MMAP_SIZE; - if (mmap_size > file_size) { - mmap_size = file_size; + if (mmap_size > data_size) { + mmap_size = data_size; session->one_mmap = true; } @@ -1865,12 +1875,12 @@ static int __perf_session__process_events(struct perf_session *session, mmap_flags = MAP_PRIVATE; } remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd, + buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, rd->fd, file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); err = -errno; - goto out_err; + goto out; } mmaps[map_idx] = buf; map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); @@ -1902,7 +1912,7 @@ more: file_offset + head, event->header.size, event->header.type); err = -EINVAL; - goto out_err; + goto out; } if (skip) @@ -1911,15 +1921,40 @@ more: head += size; file_pos += size; - ui_progress__update(&prog, size); + ui_progress__update(prog, size); if (session_done()) goto out; - if (file_pos < file_size) + if (file_pos < data_size) goto more; out: + return err; +} + +static int __perf_session__process_events(struct perf_session *session) +{ + struct reader rd = { + .fd = perf_data__fd(session->data), + .data_size = session->header.data_size, + .data_offset = session->header.data_offset, + }; + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = session->tool; + struct ui_progress prog; + int err; + + perf_tool__fill_defaults(tool); + + if (rd.data_size == 0) + return -1; + + ui_progress__init_size(&prog, rd.data_size, "Processing events..."); + + err = reader__process_events(&rd, session, &prog); + if (err) + goto out_err; /* do the final flush for ordered samples */ err = ordered_events__flush(oe, OE_FLUSH__FINAL); if (err) @@ -1944,20 +1979,13 @@ out_err: int perf_session__process_events(struct perf_session *session) { - u64 size = perf_data__size(session->data); - int err; - if (perf_session__register_idle_thread(session) < 0) return -ENOMEM; - if (!perf_data__is_pipe(session->data)) - err = __perf_session__process_events(session, - session->header.data_offset, - session->header.data_size, size); - else - err = __perf_session__process_pipe_events(session); + if (perf_data__is_pipe(session->data)) + return __perf_session__process_pipe_events(session); - return err; + return __perf_session__process_events(session); } bool perf_session__has_traces(struct perf_session *session, const char *msg) diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 64d1f36dee99..d3ffc18424b5 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,5 +1,3 @@ -#!/usr/bin/python - from os import getenv from subprocess import Popen, PIPE from re import sub diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 130fe37fe2df..dd6312876492 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -145,8 +145,8 @@ struct hist_entry { union { /* this is for hierarchical entry structure */ struct { - struct rb_root hroot_in; - struct rb_root hroot_out; + struct rb_root_cached hroot_in; + struct rb_root_cached hroot_out; }; /* non-leaf entries */ struct rb_root sorted_chain; /* leaf entry has callchains */ }; diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index dc86597d0cc4..00f215580b5a 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -594,11 +594,12 @@ struct srcline_node { struct rb_node rb_node; }; -void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline) +void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline) { - struct rb_node **p = &tree->rb_node; + struct rb_node **p = &tree->rb_root.rb_node; struct rb_node *parent = NULL; struct srcline_node *i, *node; + bool leftmost = true; node = zalloc(sizeof(struct srcline_node)); if (!node) { @@ -614,16 +615,18 @@ void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline) i = rb_entry(parent, struct srcline_node, rb_node); if (addr < i->addr) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&node->rb_node, parent, p); - rb_insert_color(&node->rb_node, tree); + rb_insert_color_cached(&node->rb_node, tree, leftmost); } -char *srcline__tree_find(struct rb_root *tree, u64 addr) +char *srcline__tree_find(struct rb_root_cached *tree, u64 addr) { - struct rb_node *n = tree->rb_node; + struct rb_node *n = tree->rb_root.rb_node; while (n) { struct srcline_node *i = rb_entry(n, struct srcline_node, @@ -640,15 +643,15 @@ char *srcline__tree_find(struct rb_root *tree, u64 addr) return NULL; } -void srcline__tree_delete(struct rb_root *tree) +void srcline__tree_delete(struct rb_root_cached *tree) { struct srcline_node *pos; - struct rb_node *next = rb_first(tree); + struct rb_node *next = rb_first_cached(tree); while (next) { pos = rb_entry(next, struct srcline_node, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, tree); + rb_erase_cached(&pos->rb_node, tree); free_srcline(pos->srcline); zfree(&pos); } @@ -682,28 +685,32 @@ void inline_node__delete(struct inline_node *node) free(node); } -void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines) +void inlines__tree_insert(struct rb_root_cached *tree, + struct inline_node *inlines) { - struct rb_node **p = &tree->rb_node; + struct rb_node **p = &tree->rb_root.rb_node; struct rb_node *parent = NULL; const u64 addr = inlines->addr; struct inline_node *i; + bool leftmost = true; while (*p != NULL) { parent = *p; i = rb_entry(parent, struct inline_node, rb_node); if (addr < i->addr) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&inlines->rb_node, parent, p); - rb_insert_color(&inlines->rb_node, tree); + rb_insert_color_cached(&inlines->rb_node, tree, leftmost); } -struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr) +struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr) { - struct rb_node *n = tree->rb_node; + struct rb_node *n = tree->rb_root.rb_node; while (n) { struct inline_node *i = rb_entry(n, struct inline_node, @@ -720,15 +727,15 @@ struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr) return NULL; } -void inlines__tree_delete(struct rb_root *tree) +void inlines__tree_delete(struct rb_root_cached *tree) { struct inline_node *pos; - struct rb_node *next = rb_first(tree); + struct rb_node *next = rb_first_cached(tree); while (next) { pos = rb_entry(next, struct inline_node, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, tree); + rb_erase_cached(&pos->rb_node, tree); inline_node__delete(pos); } } diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h index 5762212dc342..b11a0aaaa676 100644 --- a/tools/perf/util/srcline.h +++ b/tools/perf/util/srcline.h @@ -19,11 +19,11 @@ void free_srcline(char *srcline); char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line); /* insert the srcline into the DSO, which will take ownership */ -void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline); +void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline); /* find previously inserted srcline */ -char *srcline__tree_find(struct rb_root *tree, u64 addr); +char *srcline__tree_find(struct rb_root_cached *tree, u64 addr); /* delete all srclines within the tree */ -void srcline__tree_delete(struct rb_root *tree); +void srcline__tree_delete(struct rb_root_cached *tree); #define SRCLINE_UNKNOWN ((char *) "??:0") @@ -46,10 +46,11 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr, void inline_node__delete(struct inline_node *node); /* insert the inline node list into the DSO, which will take ownership */ -void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines); +void inlines__tree_insert(struct rb_root_cached *tree, + struct inline_node *inlines); /* find previously inserted inline node list */ -struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr); +struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr); /* delete all nodes within the tree of inline_node s */ -void inlines__tree_delete(struct rb_root *tree); +void inlines__tree_delete(struct rb_root_cached *tree); #endif /* PERF_SRCLINE_H */ diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 665ee374fc01..6d043c78f3c2 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -2,6 +2,7 @@ #include <inttypes.h> #include <linux/time64.h> #include <math.h> +#include "color.h" #include "evlist.h" #include "evsel.h" #include "stat.h" diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 3c22c58b3e90..83d8094be4fe 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -168,7 +168,7 @@ static void reset_stat(struct runtime_stat *st) struct rb_node *pos, *next; rblist = &st->value_list; - next = rb_first(&rblist->entries); + next = rb_first_cached(&rblist->entries); while (next) { pos = next; next = rb_next(pos); diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index d58f1e08b170..7e82c71dcc42 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -57,7 +57,7 @@ static inline unsigned int strlist__nr_entries(const struct strlist *slist) /* For strlist iteration */ static inline struct str_node *strlist__first(struct strlist *slist) { - struct rb_node *rn = rb_first(&slist->rblist.entries); + struct rb_node *rn = rb_first_cached(&slist->rblist.entries); return rn ? rb_entry(rn, struct str_node, rb_node) : NULL; } static inline struct str_node *strlist__next(struct str_node *sn) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 7119df77dc0b..17edbd4f6f85 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -3,6 +3,7 @@ #include "util.h" #include <errno.h> +#include <unistd.h> #include <stdio.h> #include <fcntl.h> #include <string.h> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 48efad6d0f90..bcbcbd610460 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -163,7 +163,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) return arch__choose_best_symbol(syma, symb); } -void symbols__fixup_duplicate(struct rb_root *symbols) +void symbols__fixup_duplicate(struct rb_root_cached *symbols) { struct rb_node *nd; struct symbol *curr, *next; @@ -171,7 +171,7 @@ void symbols__fixup_duplicate(struct rb_root *symbols) if (symbol_conf.allow_aliases) return; - nd = rb_first(symbols); + nd = rb_first_cached(symbols); while (nd) { curr = rb_entry(nd, struct symbol, rb_node); @@ -186,20 +186,20 @@ again: continue; if (choose_best_symbol(curr, next) == SYMBOL_A) { - rb_erase(&next->rb_node, symbols); + rb_erase_cached(&next->rb_node, symbols); symbol__delete(next); goto again; } else { nd = rb_next(&curr->rb_node); - rb_erase(&curr->rb_node, symbols); + rb_erase_cached(&curr->rb_node, symbols); symbol__delete(curr); } } } -void symbols__fixup_end(struct rb_root *symbols) +void symbols__fixup_end(struct rb_root_cached *symbols) { - struct rb_node *nd, *prevnd = rb_first(symbols); + struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; if (prevnd == NULL) @@ -282,25 +282,27 @@ void symbol__delete(struct symbol *sym) free(((void *)sym) - symbol_conf.priv_size); } -void symbols__delete(struct rb_root *symbols) +void symbols__delete(struct rb_root_cached *symbols) { struct symbol *pos; - struct rb_node *next = rb_first(symbols); + struct rb_node *next = rb_first_cached(symbols); while (next) { pos = rb_entry(next, struct symbol, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, symbols); + rb_erase_cached(&pos->rb_node, symbols); symbol__delete(pos); } } -void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel) +void __symbols__insert(struct rb_root_cached *symbols, + struct symbol *sym, bool kernel) { - struct rb_node **p = &symbols->rb_node; + struct rb_node **p = &symbols->rb_root.rb_node; struct rb_node *parent = NULL; const u64 ip = sym->start; struct symbol *s; + bool leftmost = true; if (kernel) { const char *name = sym->name; @@ -318,26 +320,28 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel) s = rb_entry(parent, struct symbol, rb_node); if (ip < s->start) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&sym->rb_node, parent, p); - rb_insert_color(&sym->rb_node, symbols); + rb_insert_color_cached(&sym->rb_node, symbols, leftmost); } -void symbols__insert(struct rb_root *symbols, struct symbol *sym) +void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym) { __symbols__insert(symbols, sym, false); } -static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) +static struct symbol *symbols__find(struct rb_root_cached *symbols, u64 ip) { struct rb_node *n; if (symbols == NULL) return NULL; - n = symbols->rb_node; + n = symbols->rb_root.rb_node; while (n) { struct symbol *s = rb_entry(n, struct symbol, rb_node); @@ -353,9 +357,9 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) return NULL; } -static struct symbol *symbols__first(struct rb_root *symbols) +static struct symbol *symbols__first(struct rb_root_cached *symbols) { - struct rb_node *n = rb_first(symbols); + struct rb_node *n = rb_first_cached(symbols); if (n) return rb_entry(n, struct symbol, rb_node); @@ -363,9 +367,9 @@ static struct symbol *symbols__first(struct rb_root *symbols) return NULL; } -static struct symbol *symbols__last(struct rb_root *symbols) +static struct symbol *symbols__last(struct rb_root_cached *symbols) { - struct rb_node *n = rb_last(symbols); + struct rb_node *n = rb_last(&symbols->rb_root); if (n) return rb_entry(n, struct symbol, rb_node); @@ -383,11 +387,12 @@ static struct symbol *symbols__next(struct symbol *sym) return NULL; } -static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym) +static void symbols__insert_by_name(struct rb_root_cached *symbols, struct symbol *sym) { - struct rb_node **p = &symbols->rb_node; + struct rb_node **p = &symbols->rb_root.rb_node; struct rb_node *parent = NULL; struct symbol_name_rb_node *symn, *s; + bool leftmost = true; symn = container_of(sym, struct symbol_name_rb_node, sym); @@ -396,19 +401,21 @@ static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym) s = rb_entry(parent, struct symbol_name_rb_node, rb_node); if (strcmp(sym->name, s->sym.name) < 0) p = &(*p)->rb_left; - else + else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&symn->rb_node, parent, p); - rb_insert_color(&symn->rb_node, symbols); + rb_insert_color_cached(&symn->rb_node, symbols, leftmost); } -static void symbols__sort_by_name(struct rb_root *symbols, - struct rb_root *source) +static void symbols__sort_by_name(struct rb_root_cached *symbols, + struct rb_root_cached *source) { struct rb_node *nd; - for (nd = rb_first(source); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(source); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); symbols__insert_by_name(symbols, pos); } @@ -431,7 +438,7 @@ int symbol__match_symbol_name(const char *name, const char *str, return arch__compare_symbol_names(name, str); } -static struct symbol *symbols__find_by_name(struct rb_root *symbols, +static struct symbol *symbols__find_by_name(struct rb_root_cached *symbols, const char *name, enum symbol_tag_include includes) { @@ -441,7 +448,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, if (symbols == NULL) return NULL; - n = symbols->rb_node; + n = symbols->rb_root.rb_node; while (n) { int cmp; @@ -644,7 +651,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, { struct symbol *sym; struct dso *dso = arg; - struct rb_root *root = &dso->symbols; + struct rb_root_cached *root = &dso->symbols; if (!symbol_type__filter(type)) return 0; @@ -681,14 +688,14 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct struct map *curr_map; struct symbol *pos; int count = 0; - struct rb_root old_root = dso->symbols; - struct rb_root *root = &dso->symbols; - struct rb_node *next = rb_first(root); + struct rb_root_cached old_root = dso->symbols; + struct rb_root_cached *root = &dso->symbols; + struct rb_node *next = rb_first_cached(root); if (!kmaps) return -1; - *root = RB_ROOT; + *root = RB_ROOT_CACHED; while (next) { char *module; @@ -696,8 +703,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct pos = rb_entry(next, struct symbol, rb_node); next = rb_next(&pos->rb_node); - rb_erase_init(&pos->rb_node, &old_root); - + rb_erase_cached(&pos->rb_node, &old_root); + RB_CLEAR_NODE(&pos->rb_node); module = strchr(pos->name, '\t'); if (module) *module = '\0'; @@ -734,8 +741,8 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, struct map *curr_map = initial_map; struct symbol *pos; int count = 0, moved = 0; - struct rb_root *root = &dso->symbols; - struct rb_node *next = rb_first(root); + struct rb_root_cached *root = &dso->symbols; + struct rb_node *next = rb_first_cached(root); int kernel_range = 0; bool x86_64; @@ -849,7 +856,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, } add_symbol: if (curr_map != initial_map) { - rb_erase(&pos->rb_node, root); + rb_erase_cached(&pos->rb_node, root); symbols__insert(&curr_map->dso->symbols, pos); ++moved; } else @@ -857,7 +864,7 @@ add_symbol: continue; discard_symbol: - rb_erase(&pos->rb_node, root); + rb_erase_cached(&pos->rb_node, root); symbol__delete(pos); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 14d9d438e7e2..56e2bcb907cc 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -5,16 +5,12 @@ #include <linux/types.h> #include <stdbool.h> #include <stdint.h> -#include "map.h" -#include "../perf.h" #include <linux/list.h> #include <linux/rbtree.h> #include <stdio.h> -#include <byteswap.h> -#include <libgen.h> -#include "build-id.h" -#include "event.h" +#include "branch.h" #include "path.h" +#include "symbol_conf.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -24,6 +20,10 @@ #include "dso.h" +struct map; +struct map_groups; +struct option; + /* * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: @@ -68,7 +68,7 @@ struct symbol { }; void symbol__delete(struct symbol *sym); -void symbols__delete(struct rb_root *symbols); +void symbols__delete(struct rb_root_cached *symbols); /* symbols__for_each_entry - iterate over symbols (rb_root) * @@ -77,7 +77,7 @@ void symbols__delete(struct rb_root *symbols); * @nd: the 'struct rb_node *' to use as a temporary storage */ #define symbols__for_each_entry(symbols, pos, nd) \ - for (nd = rb_first(symbols); \ + for (nd = rb_first_cached(symbols); \ nd && (pos = rb_entry(nd, struct symbol, rb_node)); \ nd = rb_next(nd)) @@ -89,69 +89,6 @@ static inline size_t symbol__size(const struct symbol *sym) struct strlist; struct intlist; -struct symbol_conf { - unsigned short priv_size; - bool try_vmlinux_path, - init_annotation, - force, - ignore_vmlinux, - ignore_vmlinux_buildid, - show_kernel_path, - use_modules, - allow_aliases, - sort_by_name, - show_nr_samples, - show_total_period, - use_callchain, - cumulate_callchain, - show_branchflag_count, - exclude_other, - show_cpu_utilization, - initialized, - kptr_restrict, - event_group, - demangle, - demangle_kernel, - filter_relative, - show_hist_headers, - branch_callstack, - has_filter, - show_ref_callgraph, - hide_unresolved, - raw_trace, - report_hierarchy, - inline_name; - const char *vmlinux_name, - *kallsyms_name, - *source_prefix, - *field_sep, - *graph_function; - const char *default_guest_vmlinux_name, - *default_guest_kallsyms, - *default_guest_modules; - const char *guestmount; - const char *dso_list_str, - *comm_list_str, - *pid_list_str, - *tid_list_str, - *sym_list_str, - *col_width_list_str, - *bt_stop_list_str; - struct strlist *dso_list, - *comm_list, - *sym_list, - *dso_from_list, - *dso_to_list, - *sym_from_list, - *sym_to_list, - *bt_stop_list; - struct intlist *pid_list, - *tid_list; - const char *symfs; -}; - -extern struct symbol_conf symbol_conf; - struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -310,10 +247,11 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name); -void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); -void symbols__insert(struct rb_root *symbols, struct symbol *sym); -void symbols__fixup_duplicate(struct rb_root *symbols); -void symbols__fixup_end(struct rb_root *symbols); +void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, + bool kernel); +void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); +void symbols__fixup_duplicate(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols); void map_groups__fixup_end(struct map_groups *mg); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h new file mode 100644 index 000000000000..fffea68c1203 --- /dev/null +++ b/tools/perf/util/symbol_conf.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_SYMBOL_CONF +#define __PERF_SYMBOL_CONF 1 + +#include <stdbool.h> + +struct strlist; +struct intlist; + +struct symbol_conf { + unsigned short priv_size; + bool try_vmlinux_path, + init_annotation, + force, + ignore_vmlinux, + ignore_vmlinux_buildid, + show_kernel_path, + use_modules, + allow_aliases, + sort_by_name, + show_nr_samples, + show_total_period, + use_callchain, + cumulate_callchain, + show_branchflag_count, + exclude_other, + show_cpu_utilization, + initialized, + kptr_restrict, + event_group, + demangle, + demangle_kernel, + filter_relative, + show_hist_headers, + branch_callstack, + has_filter, + show_ref_callgraph, + hide_unresolved, + raw_trace, + report_hierarchy, + inline_name; + const char *vmlinux_name, + *kallsyms_name, + *source_prefix, + *field_sep, + *graph_function; + const char *default_guest_vmlinux_name, + *default_guest_kallsyms, + *default_guest_modules; + const char *guestmount; + const char *dso_list_str, + *comm_list_str, + *pid_list_str, + *tid_list_str, + *sym_list_str, + *col_width_list_str, + *bt_stop_list_str; + struct strlist *dso_list, + *comm_list, + *sym_list, + *dso_from_list, + *dso_to_list, + *sym_from_list, + *sym_to_list, + *bt_stop_list; + struct intlist *pid_list, + *tid_list; + const char *symfs; +}; + +extern struct symbol_conf symbol_conf; + +#endif // __PERF_SYMBOL_CONF diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index ed0205cc7942..02e89b02c2ce 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -3,6 +3,7 @@ #include <inttypes.h> #include <stdio.h> +#include "map.h" #include "symbol.h" size_t symbol__fprintf(struct symbol *sym, FILE *fp) @@ -64,7 +65,7 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso, struct rb_node *nd; struct symbol_name_rb_node *pos; - for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) { + for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); fprintf(fp, "%s\n", pos->sym.name); } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 712dd48cc0ca..f3c939150f90 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -13,6 +13,7 @@ #include <intlist.h> #include "rwsem.h" +struct namespaces_event; struct thread_stack; struct unwind_libunwind_ops; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 56e4ca54020a..250391672f9f 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -53,7 +53,10 @@ struct perf_tool { itrace_start, context_switch, throttle, - unthrottle; + unthrottle, + ksymbol, + bpf_event; + event_attr_op attr; event_attr_op event_update; event_op2 tracing_data; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 093352e93d50..320b0fef249a 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -2,6 +2,7 @@ #include "../perf.h" #include "util.h" #include "debug.h" +#include "namespaces.h" #include <api/fs/fs.h> #include <sys/mman.h> #include <sys/stat.h> diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 902ce6384f57..512ad7c09b13 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -6,7 +6,6 @@ #include <sys/mman.h> #include <zlib.h> #include <linux/compiler.h> -#include <unistd.h> #include "util/compress.h" #include "util/util.h" |