diff options
Diffstat (limited to 'tools/perf/util')
46 files changed, 988 insertions, 191 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 1a909b53dc15..2d4fa1304178 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -141,6 +141,7 @@ perf-y += clockid.o perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index abe1499a9164..aa04a3655236 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -961,7 +961,7 @@ static int symbol__inc_addr_samples(struct map_symbol *ms, if (sym == NULL) return 0; src = symbol__hists(sym, evsel->evlist->core.nr_entries); - return src ? __symbol__inc_addr_samples(ms, src, evsel->idx, addr, sample) : 0; + return src ? __symbol__inc_addr_samples(ms, src, evsel->core.idx, addr, sample) : 0; } static int symbol__account_cycles(u64 addr, u64 start, @@ -2159,7 +2159,7 @@ static void annotation__calc_percent(struct annotation *notes, BUG_ON(i >= al->data_nr); - sym_hist = annotation__histogram(notes, evsel->idx); + sym_hist = annotation__histogram(notes, evsel->core.idx); data = &al->data[i++]; calc_percent(sym_hist, hists, data, al->offset, end); @@ -2340,7 +2340,7 @@ static void print_summary(struct rb_root *root, const char *filename) static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evsel->idx); + struct sym_hist *h = annotation__histogram(notes, evsel->core.idx); u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) @@ -2373,7 +2373,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, const char *d_filename; const char *evsel_name = evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evsel->idx); + struct sym_hist *h = annotation__histogram(notes, evsel->core.idx); struct annotation_line *pos, *queue = NULL; u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0, addr_fmt_width; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9350eeb3a3fc..cb19669d2a5b 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -73,8 +73,8 @@ static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct e grp = false; evlist__for_each_entry(evlist, evsel) { if (grp) { - if (!(evsel->leader == leader || - (evsel->leader == evsel && + if (!(evsel__leader(evsel) == leader || + (evsel__leader(evsel) == evsel && evsel->core.nr_members <= 1))) return -EINVAL; } else if (evsel == leader) { @@ -87,8 +87,8 @@ static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct e grp = false; evlist__for_each_entry(evlist, evsel) { if (grp) { - if (evsel->leader != leader) { - evsel->leader = leader; + if (!evsel__has_leader(evsel, leader)) { + evsel__set_leader(evsel, leader); if (leader->core.nr_members < 1) leader->core.nr_members = 1; leader->core.nr_members += 1; @@ -1231,11 +1231,11 @@ static void unleader_evsel(struct evlist *evlist, struct evsel *leader) /* Find new leader for the group */ evlist__for_each_entry(evlist, evsel) { - if (evsel->leader != leader || evsel == leader) + if (!evsel__has_leader(evsel, leader) || evsel == leader) continue; if (!new_leader) new_leader = evsel; - evsel->leader = new_leader; + evsel__set_leader(evsel, new_leader); } /* Update group information */ diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 21c8e71162b1..8150e03367bb 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -18,6 +18,7 @@ #include "evsel.h" #include "evlist.h" #include "target.h" +#include "cgroup.h" #include "cpumap.h" #include "thread_map.h" @@ -352,7 +353,7 @@ static int bperf_check_target(struct evsel *evsel, enum bperf_filter_type *filter_type, __u32 *filter_entry_cnt) { - if (evsel->leader->core.nr_members > 1) { + if (evsel->core.leader->nr_members > 1) { pr_err("bpf managed perf events do not yet support groups.\n"); return -1; } @@ -742,6 +743,8 @@ struct bpf_counter_ops bperf_ops = { .destroy = bperf__destroy, }; +extern struct bpf_counter_ops bperf_cgrp_ops; + static inline bool bpf_counter_skip(struct evsel *evsel) { return list_empty(&evsel->bpf_counter_list) && @@ -759,6 +762,8 @@ int bpf_counter__load(struct evsel *evsel, struct target *target) { if (target->bpf_str) evsel->bpf_counter_ops = &bpf_program_profiler_ops; + else if (cgrp_event_expanded && target->use_bpf) + evsel->bpf_counter_ops = &bperf_cgrp_ops; else if (target->use_bpf || evsel->bpf_counter || evsel__match_bpf_counter_events(evsel->name)) evsel->bpf_counter_ops = &bperf_ops; diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c new file mode 100644 index 000000000000..89aa5e71db1a --- /dev/null +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (c) 2021 Facebook */ +/* Copyright (c) 2021 Google */ + +#include <assert.h> +#include <limits.h> +#include <unistd.h> +#include <sys/file.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <linux/err.h> +#include <linux/zalloc.h> +#include <linux/perf_event.h> +#include <api/fs/fs.h> +#include <perf/bpf_perf.h> + +#include "affinity.h" +#include "bpf_counter.h" +#include "cgroup.h" +#include "counts.h" +#include "debug.h" +#include "evsel.h" +#include "evlist.h" +#include "target.h" +#include "cpumap.h" +#include "thread_map.h" + +#include "bpf_skel/bperf_cgroup.skel.h" + +static struct perf_event_attr cgrp_switch_attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CGROUP_SWITCHES, + .size = sizeof(cgrp_switch_attr), + .sample_period = 1, + .disabled = 1, +}; + +static struct evsel *cgrp_switch; +static struct bperf_cgroup_bpf *skel; + +#define FD(evt, cpu) (*(int *)xyarray__entry(evt->core.fd, cpu, 0)) + +static int bperf_load_program(struct evlist *evlist) +{ + struct bpf_link *link; + struct evsel *evsel; + struct cgroup *cgrp, *leader_cgrp; + __u32 i, cpu; + __u32 nr_cpus = evlist->core.all_cpus->nr; + int total_cpus = cpu__max_cpu(); + int map_size, map_fd; + int prog_fd, err; + + skel = bperf_cgroup_bpf__open(); + if (!skel) { + pr_err("Failed to open cgroup skeleton\n"); + return -1; + } + + skel->rodata->num_cpus = total_cpus; + skel->rodata->num_events = evlist->core.nr_entries / nr_cgroups; + + BUG_ON(evlist->core.nr_entries % nr_cgroups != 0); + + /* we need one copy of events per cpu for reading */ + map_size = total_cpus * evlist->core.nr_entries / nr_cgroups; + bpf_map__resize(skel->maps.events, map_size); + bpf_map__resize(skel->maps.cgrp_idx, nr_cgroups); + /* previous result is saved in a per-cpu array */ + map_size = evlist->core.nr_entries / nr_cgroups; + bpf_map__resize(skel->maps.prev_readings, map_size); + /* cgroup result needs all events (per-cpu) */ + map_size = evlist->core.nr_entries; + bpf_map__resize(skel->maps.cgrp_readings, map_size); + + set_max_rlimit(); + + err = bperf_cgroup_bpf__load(skel); + if (err) { + pr_err("Failed to load cgroup skeleton\n"); + goto out; + } + + if (cgroup_is_v2("perf_event") > 0) + skel->bss->use_cgroup_v2 = 1; + + err = -1; + + cgrp_switch = evsel__new(&cgrp_switch_attr); + if (evsel__open_per_cpu(cgrp_switch, evlist->core.all_cpus, -1) < 0) { + pr_err("Failed to open cgroup switches event\n"); + goto out; + } + + for (i = 0; i < nr_cpus; i++) { + link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch, + FD(cgrp_switch, i)); + if (IS_ERR(link)) { + pr_err("Failed to attach cgroup program\n"); + err = PTR_ERR(link); + goto out; + } + } + + /* + * Update cgrp_idx map from cgroup-id to event index. + */ + cgrp = NULL; + i = 0; + + evlist__for_each_entry(evlist, evsel) { + if (cgrp == NULL || evsel->cgrp == leader_cgrp) { + leader_cgrp = evsel->cgrp; + evsel->cgrp = NULL; + + /* open single copy of the events w/o cgroup */ + err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1); + if (err) { + pr_err("Failed to open first cgroup events\n"); + goto out; + } + + map_fd = bpf_map__fd(skel->maps.events); + for (cpu = 0; cpu < nr_cpus; cpu++) { + int fd = FD(evsel, cpu); + __u32 idx = evsel->core.idx * total_cpus + + evlist->core.all_cpus->map[cpu]; + + err = bpf_map_update_elem(map_fd, &idx, &fd, + BPF_ANY); + if (err < 0) { + pr_err("Failed to update perf_event fd\n"); + goto out; + } + } + + evsel->cgrp = leader_cgrp; + } + evsel->supported = true; + + if (evsel->cgrp == cgrp) + continue; + + cgrp = evsel->cgrp; + + if (read_cgroup_id(cgrp) < 0) { + pr_err("Failed to get cgroup id\n"); + err = -1; + goto out; + } + + map_fd = bpf_map__fd(skel->maps.cgrp_idx); + err = bpf_map_update_elem(map_fd, &cgrp->id, &i, BPF_ANY); + if (err < 0) { + pr_err("Failed to update cgroup index map\n"); + goto out; + } + + i++; + } + + /* + * bperf uses BPF_PROG_TEST_RUN to get accurate reading. Check + * whether the kernel support it + */ + prog_fd = bpf_program__fd(skel->progs.trigger_read); + err = bperf_trigger_reading(prog_fd, 0); + if (err) { + pr_warning("The kernel does not support test_run for raw_tp BPF programs.\n" + "Therefore, --for-each-cgroup might show inaccurate readings\n"); + err = 0; + } + +out: + return err; +} + +static int bperf_cgrp__load(struct evsel *evsel, + struct target *target __maybe_unused) +{ + static bool bperf_loaded = false; + + evsel->bperf_leader_prog_fd = -1; + evsel->bperf_leader_link_fd = -1; + + if (!bperf_loaded && bperf_load_program(evsel->evlist)) + return -1; + + bperf_loaded = true; + /* just to bypass bpf_counter_skip() */ + evsel->follower_skel = (struct bperf_follower_bpf *)skel; + + return 0; +} + +static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused, + int cpu __maybe_unused, int fd __maybe_unused) +{ + /* nothing to do */ + return 0; +} + +/* + * trigger the leader prog on each cpu, so the cgrp_reading map could get + * the latest results. + */ +static int bperf_cgrp__sync_counters(struct evlist *evlist) +{ + int i, cpu; + int nr_cpus = evlist->core.all_cpus->nr; + int prog_fd = bpf_program__fd(skel->progs.trigger_read); + + for (i = 0; i < nr_cpus; i++) { + cpu = evlist->core.all_cpus->map[i]; + bperf_trigger_reading(prog_fd, cpu); + } + + return 0; +} + +static int bperf_cgrp__enable(struct evsel *evsel) +{ + if (evsel->core.idx) + return 0; + + bperf_cgrp__sync_counters(evsel->evlist); + + skel->bss->enabled = 1; + return 0; +} + +static int bperf_cgrp__disable(struct evsel *evsel) +{ + if (evsel->core.idx) + return 0; + + bperf_cgrp__sync_counters(evsel->evlist); + + skel->bss->enabled = 0; + return 0; +} + +static int bperf_cgrp__read(struct evsel *evsel) +{ + struct evlist *evlist = evsel->evlist; + int i, cpu, nr_cpus = evlist->core.all_cpus->nr; + int total_cpus = cpu__max_cpu(); + struct perf_counts_values *counts; + struct bpf_perf_event_value *values; + int reading_map_fd, err = 0; + __u32 idx; + + if (evsel->core.idx) + return 0; + + bperf_cgrp__sync_counters(evsel->evlist); + + values = calloc(total_cpus, sizeof(*values)); + if (values == NULL) + return -ENOMEM; + + reading_map_fd = bpf_map__fd(skel->maps.cgrp_readings); + + evlist__for_each_entry(evlist, evsel) { + idx = evsel->core.idx; + err = bpf_map_lookup_elem(reading_map_fd, &idx, values); + if (err) { + pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n", + idx, evsel__name(evsel), evsel->cgrp->name); + goto out; + } + + for (i = 0; i < nr_cpus; i++) { + cpu = evlist->core.all_cpus->map[i]; + + counts = perf_counts(evsel->counts, i, 0); + counts->val = values[cpu].counter; + counts->ena = values[cpu].enabled; + counts->run = values[cpu].running; + } + } + +out: + free(values); + return err; +} + +static int bperf_cgrp__destroy(struct evsel *evsel) +{ + if (evsel->core.idx) + return 0; + + bperf_cgroup_bpf__destroy(skel); + evsel__delete(cgrp_switch); // it'll destroy on_switch progs too + + return 0; +} + +struct bpf_counter_ops bperf_cgrp_ops = { + .load = bperf_cgrp__load, + .enable = bperf_cgrp__enable, + .disable = bperf_cgrp__disable, + .read = bperf_cgrp__read, + .install_pe = bperf_cgrp__install_pe, + .destroy = bperf_cgrp__destroy, +}; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c new file mode 100644 index 000000000000..292c430768b5 --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Facebook +// Copyright (c) 2021 Google +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define MAX_LEVELS 10 // max cgroup hierarchy level: arbitrary +#define MAX_EVENTS 32 // max events per cgroup: arbitrary + +// NOTE: many of map and global data will be modified before loading +// from the userspace (perf tool) using the skeleton helpers. + +// single set of global perf events to measure +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 1); +} events SEC(".maps"); + +// from cgroup id to event index +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u32)); + __uint(max_entries, 1); +} cgrp_idx SEC(".maps"); + +// per-cpu event snapshots to calculate delta +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); +} prev_readings SEC(".maps"); + +// aggregated event values for each cgroup (per-cpu) +// will be read from the user-space +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); +} cgrp_readings SEC(".maps"); + +const volatile __u32 num_events = 1; +const volatile __u32 num_cpus = 1; + +int enabled = 0; +int use_cgroup_v2 = 0; + +static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) +{ + struct task_struct *p = (void *)bpf_get_current_task(); + struct cgroup *cgrp; + register int i = 0; + __u32 *elem; + int level; + int cnt; + + cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup); + level = BPF_CORE_READ(cgrp, level); + + for (cnt = 0; i < MAX_LEVELS; i++) { + __u64 cgrp_id; + + if (i > level) + break; + + // convert cgroup-id to a map index + cgrp_id = BPF_CORE_READ(cgrp, ancestor_ids[i]); + elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id); + if (!elem) + continue; + + cgrps[cnt++] = *elem; + if (cnt == size) + break; + } + + return cnt; +} + +static inline int get_cgroup_v2_idx(__u32 *cgrps, int size) +{ + register int i = 0; + __u32 *elem; + int cnt; + + for (cnt = 0; i < MAX_LEVELS; i++) { + __u64 cgrp_id = bpf_get_current_ancestor_cgroup_id(i); + + if (cgrp_id == 0) + break; + + // convert cgroup-id to a map index + elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id); + if (!elem) + continue; + + cgrps[cnt++] = *elem; + if (cnt == size) + break; + } + + return cnt; +} + +static int bperf_cgroup_count(void) +{ + register __u32 idx = 0; // to have it in a register to pass BPF verifier + register int c = 0; + struct bpf_perf_event_value val, delta, *prev_val, *cgrp_val; + __u32 cpu = bpf_get_smp_processor_id(); + __u32 cgrp_idx[MAX_LEVELS]; + int cgrp_cnt; + __u32 key, cgrp; + long err; + + if (use_cgroup_v2) + cgrp_cnt = get_cgroup_v2_idx(cgrp_idx, MAX_LEVELS); + else + cgrp_cnt = get_cgroup_v1_idx(cgrp_idx, MAX_LEVELS); + + for ( ; idx < MAX_EVENTS; idx++) { + if (idx == num_events) + break; + + // XXX: do not pass idx directly (for verifier) + key = idx; + // this is per-cpu array for diff + prev_val = bpf_map_lookup_elem(&prev_readings, &key); + if (!prev_val) { + val.counter = val.enabled = val.running = 0; + bpf_map_update_elem(&prev_readings, &key, &val, BPF_ANY); + + prev_val = bpf_map_lookup_elem(&prev_readings, &key); + if (!prev_val) + continue; + } + + // read from global perf_event array + key = idx * num_cpus + cpu; + err = bpf_perf_event_read_value(&events, key, &val, sizeof(val)); + if (err) + continue; + + if (enabled) { + delta.counter = val.counter - prev_val->counter; + delta.enabled = val.enabled - prev_val->enabled; + delta.running = val.running - prev_val->running; + + for (c = 0; c < MAX_LEVELS; c++) { + if (c == cgrp_cnt) + break; + + cgrp = cgrp_idx[c]; + + // aggregate the result by cgroup + key = cgrp * num_events + idx; + cgrp_val = bpf_map_lookup_elem(&cgrp_readings, &key); + if (cgrp_val) { + cgrp_val->counter += delta.counter; + cgrp_val->enabled += delta.enabled; + cgrp_val->running += delta.running; + } else { + bpf_map_update_elem(&cgrp_readings, &key, + &delta, BPF_ANY); + } + } + } + + *prev_val = val; + } + return 0; +} + +// This will be attached to cgroup-switches event for each cpu +SEC("perf_events") +int BPF_PROG(on_cgrp_switch) +{ + return bperf_cgroup_count(); +} + +SEC("raw_tp/sched_switch") +int BPF_PROG(trigger_read) +{ + return bperf_cgroup_count(); +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index e819a4f30fc2..e99b41f9be45 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -18,6 +18,7 @@ #include <regex.h> int nr_cgroups; +bool cgrp_event_expanded; /* used to match cgroup name with patterns */ struct cgroup_name { @@ -458,7 +459,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, if (evsel__is_group_leader(pos)) leader = evsel; - evsel->leader = leader; + evsel__set_leader(evsel, leader); evlist__add(tmp_list, evsel); } @@ -484,6 +485,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, } ret = 0; + cgrp_event_expanded = true; out_err: evlist__delete(orig_list); diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index de5b272560ab..12256b78608c 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -18,6 +18,7 @@ struct cgroup { }; extern int nr_cgroups; /* number of explicit cgroups defined */ +extern bool cgrp_event_expanded; struct cgroup *cgroup__get(struct cgroup *cgroup); void cgroup__put(struct cgroup *cgroup); diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 32ad92d3e454..22f8326547eb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2683,6 +2683,172 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset, return metadata; } +/** + * Puts a fragment of an auxtrace buffer into the auxtrace queues based + * on the bounds of aux_event, if it matches with the buffer that's at + * file_offset. + * + * Normally, whole auxtrace buffers would be added to the queue. But we + * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder + * is reset across each buffer, so splitting the buffers up in advance has + * the same effect. + */ +static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz, + struct perf_record_aux *aux_event, struct perf_sample *sample) +{ + int err; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *auxtrace_event_union; + struct perf_record_auxtrace *auxtrace_event; + union perf_event auxtrace_fragment; + __u64 aux_offset, aux_size; + + struct cs_etm_auxtrace *etm = container_of(session->auxtrace, + struct cs_etm_auxtrace, + auxtrace); + + /* + * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got + * from looping through the auxtrace index. + */ + err = perf_session__peek_event(session, file_offset, buf, + PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL); + if (err) + return err; + auxtrace_event = &auxtrace_event_union->auxtrace; + if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE) + return -EINVAL; + + if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) || + auxtrace_event->header.size != sz) { + return -EINVAL; + } + + /* + * In per-thread mode, CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + */ + if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || + auxtrace_event->cpu != sample->cpu) + return 1; + + if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { + /* + * Clamp size in snapshot mode. The buffer size is clamped in + * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect + * the buffer size. + */ + aux_size = min(aux_event->aux_size, auxtrace_event->size); + + /* + * In this mode, the head also points to the end of the buffer so aux_offset + * needs to have the size subtracted so it points to the beginning as in normal mode + */ + aux_offset = aux_event->aux_offset - aux_size; + } else { + aux_size = aux_event->aux_size; + aux_offset = aux_event->aux_offset; + } + + if (aux_offset >= auxtrace_event->offset && + aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) { + /* + * If this AUX event was inside this buffer somewhere, create a new auxtrace event + * based on the sizes of the aux event, and queue that fragment. + */ + auxtrace_fragment.auxtrace = *auxtrace_event; + auxtrace_fragment.auxtrace.size = aux_size; + auxtrace_fragment.auxtrace.offset = aux_offset; + file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size; + + pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu); + return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment, + file_offset, NULL); + } + + /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */ + return 1; +} + +static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + struct perf_sample sample; + int ret; + struct auxtrace_index_entry *ent; + struct auxtrace_index *auxtrace_index; + struct evsel *evsel; + size_t i; + + /* Don't care about any other events, we're only queuing buffers for AUX events */ + if (event->header.type != PERF_RECORD_AUX) + return 0; + + if (event->header.size < sizeof(struct perf_record_aux)) + return -EINVAL; + + /* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */ + if (!event->aux.aux_size) + return 0; + + /* + * Parse the sample, we need the sample_id_all data that comes after the event so that the + * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID. + */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + ret = evsel__parse_sample(evsel, event, &sample); + if (ret) + return ret; + + /* + * Loop through the auxtrace index to find the buffer that matches up with this aux event. + */ + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { + for (i = 0; i < auxtrace_index->nr; i++) { + ent = &auxtrace_index->entries[i]; + ret = cs_etm__queue_aux_fragment(session, ent->file_offset, + ent->sz, &event->aux, &sample); + /* + * Stop search on error or successful values. Continue search on + * 1 ('not found') + */ + if (ret != 1) + return ret; + } + } + + /* + * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but + * don't exit with an error because it will still be possible to decode other aux records. + */ + pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); + return 0; +} + +static int cs_etm__queue_aux_records(struct perf_session *session) +{ + struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index, + struct auxtrace_index, list); + if (index && index->nr > 0) + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__queue_aux_records_cb, NULL); + + /* + * We would get here if there are no entries in the index (either no auxtrace + * buffers or no index at all). Fail silently as there is the possibility of + * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still + * false. + * + * In that scenario, buffers will not be split by AUX records. + */ + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2883,7 +3049,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - err = auxtrace_queues__process_index(&etm->queues, session); + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index a9c102e8e3c0..f5d260b1df4d 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -20,7 +20,7 @@ static void close_dir(struct perf_data_file *files, int nr) { - while (--nr >= 1) { + while (--nr >= 0) { close(files[nr].fd); zfree(&files[nr].path); } diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d786cf6b0cfa..ee15db2be2f4 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1154,8 +1154,10 @@ struct map *dso__new_map(const char *name) struct map *map = NULL; struct dso *dso = dso__new(name); - if (dso) + if (dso) { map = map__new2(0, dso); + dso__put(dso); + } return map; } diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7d2ba8419b0c..609ca1671501 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -113,14 +113,14 @@ static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) * * Find a line number and file name for @addr in @cu_die. */ -int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, - const char **fname, int *lineno) +int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr, + const char **fname, int *lineno) { Dwarf_Line *line; Dwarf_Die die_mem; Dwarf_Addr faddr; - if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem) + if (die_find_realfunc(cu_die, addr, &die_mem) && die_entrypc(&die_mem, &faddr) == 0 && faddr == addr) { *fname = dwarf_decl_file(&die_mem); @@ -128,7 +128,7 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, goto out; } - line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr); + line = cu_getsrc_die(cu_die, addr); if (line && dwarf_lineno(line, lineno) == 0) { *fname = dwarf_linesrc(line, NULL, NULL); if (!*fname) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index cb99646843a9..7ee0fa19b5c4 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -19,7 +19,7 @@ const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname); const char *cu_get_comp_dir(Dwarf_Die *cu_die); /* Get a line number and file name for given address */ -int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, +int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr, const char **fname, int *lineno); /* Walk on functions at given address */ diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index ebc5e9ad35db..cec2e6cad8aa 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -186,10 +186,12 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cpuid); zfree(&env->cmdline); zfree(&env->cmdline_argv); + zfree(&env->sibling_dies); zfree(&env->sibling_cores); zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->cpu_pmu_caps); zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6ba9664089bd..47581a237c7a 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -165,11 +165,9 @@ void evlist__delete(struct evlist *evlist) void evlist__add(struct evlist *evlist, struct evsel *entry) { - entry->evlist = evlist; - entry->idx = evlist->core.nr_entries; - entry->tracking = !entry->idx; - perf_evlist__add(&evlist->core, &entry->core); + entry->evlist = evlist; + entry->tracking = !entry->core.idx; if (evlist->core.nr_entries == 1) evlist__set_id_pos(evlist); @@ -194,7 +192,7 @@ void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list) } __evlist__for_each_entry_safe(list, temp, evsel) { - if (evsel->leader == leader) { + if (evsel__has_leader(evsel, leader)) { list_del_init(&evsel->core.node); evlist__add(evlist, evsel); } @@ -225,26 +223,9 @@ out: return err; } -void __evlist__set_leader(struct list_head *list) -{ - struct evsel *evsel, *leader; - - leader = list_entry(list->next, struct evsel, core.node); - evsel = list_entry(list->prev, struct evsel, core.node); - - leader->core.nr_members = evsel->idx - leader->idx + 1; - - __evlist__for_each_entry(list, evsel) { - evsel->leader = leader; - } -} - void evlist__set_leader(struct evlist *evlist) { - if (evlist->core.nr_entries) { - evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0; - __evlist__set_leader(&evlist->core.entries); - } + perf_evlist__set_leader(&evlist->core); } int __evlist__add_default(struct evlist *evlist, bool precise) @@ -1626,7 +1607,7 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel) return; evlist__for_each_entry_safe(evlist, n, evsel) { - if (evsel->leader == move_evsel->leader) + if (evsel__leader(evsel) == evsel__leader(move_evsel)) list_move_tail(&evsel->core.node, &move); } @@ -1750,7 +1731,7 @@ bool evlist__exclude_kernel(struct evlist *evlist) */ void evlist__force_leader(struct evlist *evlist) { - if (!evlist->nr_groups) { + if (!evlist->core.nr_groups) { struct evsel *leader = evlist__first(evlist); evlist__set_leader(evlist); @@ -1763,7 +1744,8 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel * struct evsel *c2, *leader; bool is_open = true; - leader = evsel->leader; + leader = evsel__leader(evsel); + pr_debug("Weak group for %s/%d failed\n", leader->name, leader->core.nr_members); @@ -1774,10 +1756,10 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel * evlist__for_each_entry(evsel_list, c2) { if (c2 == evsel) is_open = false; - if (c2->leader == leader) { + if (evsel__has_leader(c2, leader)) { if (is_open && close) perf_evsel__close(&c2->core); - c2->leader = c2; + evsel__set_leader(c2, c2); c2->core.nr_members = 0; /* * Set this for all former members of the group @@ -2137,7 +2119,7 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->idx == idx) + if (evsel->core.idx == idx) return evsel; } return NULL; @@ -2174,13 +2156,13 @@ void evlist__check_mem_load_aux(struct evlist *evlist) * any valid memory load information. */ evlist__for_each_entry(evlist, evsel) { - leader = evsel->leader; + leader = evsel__leader(evsel); if (leader == evsel) continue; if (leader->name && strstr(leader->name, "mem-loads-aux")) { for_each_group_evsel(pos, leader) { - pos->leader = pos; + evsel__set_leader(pos, pos); pos->core.nr_members = 0; } } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 2073cfa79f79..5c22383489ae 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -50,7 +50,6 @@ enum bkw_mmap_state { struct evlist { struct perf_evlist core; - int nr_groups; bool enabled; int id_pos; int is_pos; @@ -202,7 +201,6 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel); int evlist__create_maps(struct evlist *evlist, struct target *target); int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); -void __evlist__set_leader(struct list_head *list); void evlist__set_leader(struct evlist *evlist); u64 __evlist__combined_sample_type(struct evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index b1c930eca40f..f61e5dd53f5d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -239,10 +239,8 @@ bool evsel__is_function_event(struct evsel *evsel) void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx) { - perf_evsel__init(&evsel->core, attr); - evsel->idx = idx; + perf_evsel__init(&evsel->core, attr, idx); evsel->tracking = !idx; - evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; evsel->max_events = ULONG_MAX; @@ -410,7 +408,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->cgrp = cgroup__get(orig->cgrp); evsel->tp_format = orig->tp_format; evsel->handler = orig->handler; - evsel->leader = orig->leader; + evsel->core.leader = orig->core.leader; evsel->max_events = orig->max_events; evsel->tool_event = orig->tool_event; @@ -1075,7 +1073,7 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel) void evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain) { - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); struct perf_event_attr *attr = &evsel->core.attr; int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; @@ -1593,7 +1591,7 @@ static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other, static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu) { - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) || (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) { @@ -1605,7 +1603,7 @@ static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu) static int get_group_fd(struct evsel *evsel, int cpu, int thread) { - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); int fd; if (evsel__is_group_leader(evsel)) @@ -2851,3 +2849,23 @@ bool evsel__is_hybrid(struct evsel *evsel) { return evsel->pmu_name && perf_pmu__is_hybrid(evsel->pmu_name); } + +struct evsel *evsel__leader(struct evsel *evsel) +{ + return container_of(evsel->core.leader, struct evsel, core); +} + +bool evsel__has_leader(struct evsel *evsel, struct evsel *leader) +{ + return evsel->core.leader == &leader->core; +} + +bool evsel__is_leader(struct evsel *evsel) +{ + return evsel__has_leader(evsel, evsel); +} + +void evsel__set_leader(struct evsel *evsel, struct evsel *leader) +{ + evsel->core.leader = &leader->core; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index bdad52a06438..80383096d51c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -49,7 +49,6 @@ struct evsel { struct perf_evsel core; struct evlist *evlist; off_t id_offset; - int idx; int id_pos; int is_pos; unsigned int sample_size; @@ -119,7 +118,6 @@ struct evsel { bool reset_group; bool errored; struct hashmap *per_pkg_mask; - struct evsel *leader; int err; int cpu_iter; struct { @@ -368,7 +366,7 @@ static inline struct evsel *evsel__prev(struct evsel *evsel) */ static inline bool evsel__is_group_leader(const struct evsel *evsel) { - return evsel->leader == evsel; + return evsel->core.leader == &evsel->core; } /** @@ -406,19 +404,19 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, static inline int evsel__group_idx(struct evsel *evsel) { - return evsel->idx - evsel->leader->idx; + return evsel->core.idx - evsel->core.leader->idx; } /* Iterates group WITHOUT the leader. */ #define for_each_group_member(_evsel, _leader) \ for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \ - (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) && (_evsel)->core.leader == (&_leader->core); \ (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) /* Iterates group WITH the leader. */ #define for_each_group_evsel(_evsel, _leader) \ for ((_evsel) = _leader; \ - (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) && (_evsel)->core.leader == (&_leader->core); \ (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) static inline bool evsel__has_branch_callstack(const struct evsel *evsel) @@ -463,4 +461,8 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); void evsel__zero_per_pkg(struct evsel *evsel); bool evsel__is_hybrid(struct evsel *evsel); +struct evsel *evsel__leader(struct evsel *evsel); +bool evsel__has_leader(struct evsel *evsel, struct evsel *leader); +bool evsel__is_leader(struct evsel *evsel); +void evsel__set_leader(struct evsel *evsel, struct evsel *leader); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 0158d2945bab..44249027507a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -778,7 +778,7 @@ static int write_pmu_mappings(struct feat_fd *ff, static int write_group_desc(struct feat_fd *ff, struct evlist *evlist) { - u32 nr_groups = evlist->nr_groups; + u32 nr_groups = evlist->core.nr_groups; struct evsel *evsel; int ret; @@ -789,7 +789,7 @@ static int write_group_desc(struct feat_fd *ff, evlist__for_each_entry(evlist, evsel) { if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) { const char *name = evsel->group_name ?: "{anon_group}"; - u32 leader_idx = evsel->idx; + u32 leader_idx = evsel->core.idx; u32 nr_members = evsel->core.nr_members; ret = do_write_string(ff, name); @@ -1844,7 +1844,7 @@ static struct evsel *read_event_desc(struct feat_fd *ff) msz = sz; for (i = 0, evsel = events; i < nre; evsel++, i++) { - evsel->idx = i; + evsel->core.idx = i; /* * must read entire on-file attr struct to @@ -2379,7 +2379,7 @@ static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->idx == idx) + if (evsel->core.idx == idx) return evsel; } @@ -2393,7 +2393,7 @@ static void evlist__set_event_name(struct evlist *evlist, struct evsel *event) if (!event->name) return; - evsel = evlist__find_by_index(evlist, event->idx); + evsel = evlist__find_by_index(evlist, event->core.idx); if (!evsel) return; @@ -2735,12 +2735,12 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) * Rebuild group relationship based on the group_desc */ session = container_of(ff->ph, struct perf_session, header); - session->evlist->nr_groups = nr_groups; + session->evlist->core.nr_groups = nr_groups; i = nr = 0; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->idx == (int) desc[i].leader_idx) { - evsel->leader = evsel; + if (evsel->core.idx == (int) desc[i].leader_idx) { + evsel__set_leader(evsel, evsel); /* {anon_group} is a dummy name */ if (strcmp(desc[i].name, "{anon_group}")) { evsel->group_name = desc[i].name; @@ -2758,7 +2758,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) i++; } else if (nr) { /* This is a group member */ - evsel->leader = leader; + evsel__set_leader(evsel, leader); nr--; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index cb2520abf261..5ab631702769 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -41,8 +41,11 @@ #define INTEL_PT_RETURN 1 -/* Maximum number of loops with no packets consumed i.e. stuck in a loop */ -#define INTEL_PT_MAX_LOOPS 10000 +/* + * Default maximum number of loops with no packets consumed i.e. stuck in a + * loop. + */ +#define INTEL_PT_MAX_LOOPS 100000 struct intel_pt_blk { struct intel_pt_blk *prev; @@ -220,6 +223,7 @@ struct intel_pt_decoder { uint64_t timestamp_insn_cnt; uint64_t sample_insn_cnt; uint64_t stuck_ip; + int max_loops; int no_progress; int stuck_ip_prd; int stuck_ip_cnt; @@ -315,6 +319,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->vm_tm_corr_dry_run = params->vm_tm_corr_dry_run; decoder->first_timestamp = params->first_timestamp; decoder->last_reliable_timestamp = params->first_timestamp; + decoder->max_loops = params->max_loops ? params->max_loops : INTEL_PT_MAX_LOOPS; decoder->flags = params->flags; @@ -483,7 +488,7 @@ static const char *intel_pt_err_msgs[] = { [INTEL_PT_ERR_OVR] = "Overflow packet", [INTEL_PT_ERR_LOST] = "Lost trace data", [INTEL_PT_ERR_UNK] = "Unknown error!", - [INTEL_PT_ERR_NELOOP] = "Never-ending loop", + [INTEL_PT_ERR_NELOOP] = "Never-ending loop (refer perf config intel-pt.max-loops)", }; int intel_pt__strerror(int code, char *buf, size_t buflen) @@ -1168,7 +1173,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->stuck_ip = decoder->state.to_ip; decoder->stuck_ip_prd = 1; decoder->stuck_ip_cnt = 1; - } else if (cnt > INTEL_PT_MAX_LOOPS || + } else if (cnt > decoder->max_loops || decoder->state.to_ip == decoder->stuck_ip) { intel_pt_log_at("ERROR: Never-ending loop", decoder->state.to_ip); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index 714c475808c0..4b5e79fcf557 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -270,6 +270,7 @@ struct intel_pt_params { uint32_t tsc_ctc_ratio_d; enum intel_pt_param_flags flags; unsigned int quick; + int max_loops; }; struct intel_pt_decoder; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 154a1077f22e..6f852b305e92 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -123,6 +123,7 @@ struct intel_pt { u64 noretcomp_bit; unsigned max_non_turbo_ratio; unsigned cbr2khz; + int max_loops; unsigned long num_events; @@ -1200,6 +1201,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.vm_time_correlation = pt->synth_opts.vm_time_correlation; params.vm_tm_corr_dry_run = pt->synth_opts.vm_tm_corr_dry_run; params.first_timestamp = pt->first_timestamp; + params.max_loops = pt->max_loops; if (pt->filts.cnt > 0) params.pgd_ip = intel_pt_pgd_ip; @@ -3431,6 +3433,9 @@ static int intel_pt_perf_config(const char *var, const char *value, void *data) if (!strcmp(var, "intel-pt.mispred-all")) pt->mispred_all = perf_config_bool(var, value); + if (!strcmp(var, "intel-pt.max-loops")) + perf_config_int(&pt->max_loops, var, value); + return 0; } diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 39062df02629..51424cdc3b68 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -69,7 +69,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ferror(infile)) { pr_err("lzma: read error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } if (feof(infile)) @@ -83,7 +83,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (writen(output_fd, buf_out, write_size) != write_size) { pr_err("lzma: write error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } strm.next_out = buf_out; @@ -95,11 +95,13 @@ int lzma_decompress_to_file(const char *input, int output_fd) break; pr_err("lzma: failed %s\n", lzma_strerror(ret)); - goto err_fclose; + goto err_lzma_end; } } err = 0; +err_lzma_end: + lzma_end(&strm); err_fclose: fclose(infile); return err; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8af693d9678c..72e7f3616157 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -192,6 +192,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (!(prot & PROT_EXEC)) dso__set_loaded(dso); } + + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; if (build_id__is_defined(bid)) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index d3cf2dee36c8..99d047c5ead0 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -219,9 +219,9 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (has_constraint && ev->weak_group) continue; /* Ignore event if already used and merging is disabled. */ - if (metric_no_merge && test_bit(ev->idx, evlist_used)) + if (metric_no_merge && test_bit(ev->core.idx, evlist_used)) continue; - if (!has_constraint && ev->leader != current_leader) { + if (!has_constraint && !evsel__has_leader(ev, current_leader)) { /* * Start of a new group, discard the whole match and * start again. @@ -229,7 +229,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, matched_events = 0; memset(metric_events, 0, sizeof(struct evsel *) * idnum); - current_leader = ev->leader; + current_leader = evsel__leader(ev); } /* * Check for duplicate events with the same name. For example, @@ -269,7 +269,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, for (i = 0; i < idnum; i++) { ev = metric_events[i]; /* Don't free the used events. */ - set_bit(ev->idx, evlist_used); + set_bit(ev->core.idx, evlist_used); /* * The metric leader points to the identically named event in * metric_events. @@ -287,11 +287,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, * when then group is left. */ if (!has_constraint && - ev->leader != metric_events[i]->leader && - evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader)) + ev->core.leader != metric_events[i]->core.leader && + evsel_same_pmu_or_none(evsel__leader(ev), evsel__leader(metric_events[i]))) break; if (!strcmp(metric_events[i]->name, ev->name)) { - set_bit(ev->idx, evlist_used); + set_bit(ev->core.idx, evlist_used); ev->metric_leader = metric_events[i]; } } @@ -391,7 +391,7 @@ static int metricgroup__setup_events(struct list_head *groups, } evlist__for_each_entry_safe(perf_evlist, tmp, evsel) { - if (!test_bit(evsel->idx, evlist_used)) { + if (!test_bit(evsel->core.idx, evlist_used)) { evlist__remove(perf_evlist, evsel); evsel__delete(evsel); } @@ -1312,7 +1312,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, nd = rblist__entry(old_metric_events, i); old_me = container_of(nd, struct metric_event, nd); - evsel = evlist__find_evsel(evlist, old_me->evsel->idx); + evsel = evlist__find_evsel(evlist, old_me->evsel->core.idx); if (!evsel) return -EINVAL; new_me = metricgroup__lookup(new_metric_events, evsel, true); @@ -1320,7 +1320,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, return -ENOMEM; pr_debug("copying metric event for cgroup '%s': %s (idx=%d)\n", - cgrp ? cgrp->name : "root", evsel->name, evsel->idx); + cgrp ? cgrp->name : "root", evsel->name, evsel->core.idx); list_for_each_entry(old_expr, &old_me->head, nd) { new_expr = malloc(sizeof(*new_expr)); @@ -1363,7 +1363,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, /* copy evsel in the same position */ for (idx = 0; idx < nr; idx++) { evsel = old_expr->metric_events[idx]; - evsel = evlist__find_evsel(evlist, evsel->idx); + evsel = evlist__find_evsel(evlist, evsel->core.idx); if (evsel == NULL) { free(new_expr->metric_events); free(new_expr->metric_refs); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 84108c17f48d..e5eae23cfceb 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1740,7 +1740,7 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, leader = list_first_entry(list, struct evsel, core.node); evsel = list_last_entry(list, struct evsel, core.node); - total_members = evsel->idx - leader->idx + 1; + total_members = evsel->core.idx - leader->core.idx + 1; leaders = calloc(total_members, sizeof(uintptr_t)); if (WARN_ON(!leaders)) @@ -1800,7 +1800,7 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, __evlist__for_each_entry(list, evsel) { if (i >= nr_pmu) i = 0; - evsel->leader = (struct evsel *) leaders[i++]; + evsel__set_leader(evsel, (struct evsel *) leaders[i++]); } /* The number of members and group name are same for each group */ @@ -1833,7 +1833,7 @@ void parse_events__set_leader(char *name, struct list_head *list, if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) return; - __evlist__set_leader(list); + __perf_evlist__set_leader(list); leader = list_entry(list->next, struct evsel, core.node); leader->group_name = name ? strdup(name) : NULL; } @@ -2285,7 +2285,7 @@ int __parse_events(struct evlist *evlist, const char *str, if (!ret) { struct evsel *last; - evlist->nr_groups += parse_state.nr_groups; + evlist->core.nr_groups += parse_state.nr_groups; last = evlist__last(evlist); last->cmdline_group_boundary = true; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index aba12a4d488e..9321bd0e2f76 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -316,7 +316,7 @@ event_pmu_name opt_pmu_config if (!strncmp(name, "uncore_", 7) && strncmp($1, "uncore_", 7)) name += 7; - if (!fnmatch(pattern, name, 0)) { + if (!perf_pmu__match(pattern, name, $1)) { if (parse_events_copy_term_list(orig_terms, &terms)) CLEANUP_YYABORT; if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index 6eef6dfeaa57..756295dedccc 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -99,7 +99,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_leader = evsel; if (grp_evt > -1) { - evsel->leader = grp_leader; + evsel__set_leader(evsel, grp_leader); grp_leader->core.nr_members++; grp_evt++; } @@ -110,7 +110,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, "cannot close a non-existing event group\n"); goto error; } - evlist->nr_groups++; + evlist->core.nr_groups++; grp_leader = NULL; grp_evt = -1; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 88c8ecdc60b0..a1bd7007a8b4 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -3,6 +3,7 @@ #include <linux/compiler.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <linux/ctype.h> #include <subcmd/pager.h> #include <sys/types.h> #include <errno.h> @@ -17,6 +18,7 @@ #include <locale.h> #include <regex.h> #include <perf/cpumap.h> +#include <fnmatch.h> #include "debug.h" #include "evsel.h" #include "pmu.h" @@ -740,6 +742,27 @@ struct pmu_events_map *__weak pmu_events_map__find(void) return perf_pmu__find_map(NULL); } +static bool perf_pmu__valid_suffix(char *pmu_name, char *tok) +{ + char *p; + + if (strncmp(pmu_name, tok, strlen(tok))) + return false; + + p = pmu_name + strlen(tok); + if (*p == 0) + return true; + + if (*p != '_') + return false; + + ++p; + if (*p == 0 || !isdigit(*p)) + return false; + + return true; +} + bool pmu_uncore_alias_match(const char *pmu_name, const char *name) { char *tmp = NULL, *tok, *str; @@ -768,7 +791,7 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name) */ for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) { name = strstr(name, tok); - if (!name) { + if (!name || !perf_pmu__valid_suffix((char *)name, tok)) { res = false; goto out; } @@ -927,6 +950,13 @@ static struct perf_pmu *pmu_lookup(const char *name) LIST_HEAD(format); LIST_HEAD(aliases); __u32 type; + bool is_hybrid = perf_pmu__hybrid_mounted(name); + + /* + * Check pmu name for hybrid and the pmu may be invalid in sysfs + */ + if (!strncmp(name, "cpu_", 4) && !is_hybrid) + return NULL; /* * The pmu data we store & need consists of the pmu @@ -955,7 +985,7 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->is_uncore = pmu_is_uncore(name); if (pmu->is_uncore) pmu->id = pmu_id(name); - pmu->is_hybrid = perf_pmu__hybrid_mounted(name); + pmu->is_hybrid = is_hybrid; pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); @@ -1872,3 +1902,14 @@ bool perf_pmu__has_hybrid(void) return !list_empty(&perf_pmu__hybrid_pmus); } + +int perf_pmu__match(char *pattern, char *name, char *tok) +{ + if (fnmatch(pattern, name, 0)) + return -1; + + if (tok && !perf_pmu__valid_suffix(name, tok)) + return -1; + + return 0; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a790ef758171..926da483a141 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -133,5 +133,6 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, char *name); bool perf_pmu__has_hybrid(void); +int perf_pmu__match(char *pattern, char *name, char *tok); #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c14e1d228e56..b2a02c9ab8ea 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -179,8 +179,10 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) struct map *map; map = dso__new_map(target); - if (map && map->dso) + if (map && map->dso) { + nsinfo__put(map->dso->nsinfo); map->dso->nsinfo = nsinfo__get(nsi); + } return map; } else { return kernel_get_module_map(target); @@ -237,8 +239,8 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) clear_probe_trace_event(tevs + i); } -static bool kprobe_blacklist__listed(unsigned long address); -static bool kprobe_warn_out_range(const char *symbol, unsigned long address) +static bool kprobe_blacklist__listed(u64 address); +static bool kprobe_warn_out_range(const char *symbol, u64 address) { struct map *map; bool ret = false; @@ -398,8 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, pr_debug("Symbol %s address found : %" PRIx64 "\n", pp->function, address); - ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, - result); + ret = debuginfo__find_probe_point(dinfo, address, result); if (ret <= 0) ret = (!ret) ? -ENOENT : ret; else { @@ -587,7 +588,7 @@ static void debuginfo_cache__exit(void) } -static int get_text_start_address(const char *exec, unsigned long *address, +static int get_text_start_address(const char *exec, u64 *address, struct nsinfo *nsi) { Elf *elf; @@ -632,7 +633,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, bool is_kprobe) { struct debuginfo *dinfo = NULL; - unsigned long stext = 0; + u64 stext = 0; u64 addr = tp->address; int ret = -ENOENT; @@ -660,8 +661,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, dinfo = debuginfo_cache__open(tp->module, verbose <= 0); if (dinfo) - ret = debuginfo__find_probe_point(dinfo, - (unsigned long)addr, pp); + ret = debuginfo__find_probe_point(dinfo, addr, pp); else ret = -ENOENT; @@ -676,7 +676,7 @@ error: /* Adjust symbol name and address */ static int post_process_probe_trace_point(struct probe_trace_point *tp, - struct map *map, unsigned long offs) + struct map *map, u64 offs) { struct symbol *sym; u64 addr = tp->address - offs; @@ -719,7 +719,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *pathname) { struct map *map; - unsigned long stext = 0; + u64 stext = 0; int i, ret = 0; /* Prepare a map for offline binary */ @@ -745,7 +745,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, struct nsinfo *nsi) { int i, ret = 0; - unsigned long stext = 0; + u64 stext = 0; if (!exec) return 0; @@ -790,7 +790,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs, mod_name = find_module_name(module); for (i = 0; i < ntevs; i++) { ret = post_process_probe_trace_point(&tevs[i].point, - map, (unsigned long)text_offs); + map, text_offs); if (ret < 0) break; tevs[i].point.module = @@ -1534,7 +1534,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) * so tmp[1] should always valid (but could be '\0'). */ if (tmp && !strncmp(tmp, "0x", 2)) { - pp->abs_address = strtoul(pp->function, &tmp, 0); + pp->abs_address = strtoull(pp->function, &tmp, 0); if (*tmp != '\0') { semantic_error("Invalid absolute address.\n"); return -EINVAL; @@ -1909,7 +1909,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) argv[i] = NULL; argc -= 1; } else - tp->address = strtoul(fmt1_str, NULL, 0); + tp->address = strtoull(fmt1_str, NULL, 0); } else { /* Only the symbol-based probe has offset */ tp->symbol = strdup(fmt1_str); @@ -2155,7 +2155,7 @@ synthesize_uprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) return -EINVAL; /* Use the tp->address for uprobes */ - err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address); + err = strbuf_addf(buf, "%s:0x%" PRIx64, tp->module, tp->address); if (err >= 0 && tp->ref_ctr_offset) { if (!uprobe_ref_ctr_is_supported()) @@ -2170,7 +2170,7 @@ synthesize_kprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) { if (!strncmp(tp->symbol, "0x", 2)) { /* Absolute address. See try_to_find_absolute_address() */ - return strbuf_addf(buf, "%s%s0x%lx", tp->module ?: "", + return strbuf_addf(buf, "%s%s0x%" PRIx64, tp->module ?: "", tp->module ? ":" : "", tp->address); } else { return strbuf_addf(buf, "%s%s%s+%lu", tp->module ?: "", @@ -2269,7 +2269,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, pp->function = strdup(tp->symbol); pp->offset = tp->offset; } else { - ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + ret = e_snprintf(buf, 128, "0x%" PRIx64, tp->address); if (ret < 0) return ret; pp->function = strdup(buf); @@ -2450,8 +2450,8 @@ void clear_probe_trace_event(struct probe_trace_event *tev) struct kprobe_blacklist_node { struct list_head list; - unsigned long start; - unsigned long end; + u64 start; + u64 end; char *symbol; }; @@ -2496,7 +2496,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } INIT_LIST_HEAD(&node->list); list_add_tail(&node->list, blacklist); - if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + if (sscanf(buf, "0x%" PRIx64 "-0x%" PRIx64, &node->start, &node->end) != 2) { ret = -EINVAL; break; } @@ -2512,7 +2512,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) ret = -ENOMEM; break; } - pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + pr_debug2("Blacklist: 0x%" PRIx64 "-0x%" PRIx64 ", %s\n", node->start, node->end, node->symbol); ret++; } @@ -2524,8 +2524,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } static struct kprobe_blacklist_node * -kprobe_blacklist__find_by_address(struct list_head *blacklist, - unsigned long address) +kprobe_blacklist__find_by_address(struct list_head *blacklist, u64 address) { struct kprobe_blacklist_node *node; @@ -2553,7 +2552,7 @@ static void kprobe_blacklist__release(void) kprobe_blacklist__delete(&kprobe_blacklist); } -static bool kprobe_blacklist__listed(unsigned long address) +static bool kprobe_blacklist__listed(u64 address) { return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address); } @@ -3221,7 +3220,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, * In __add_probe_trace_events, a NULL symbol is interpreted as * invalid. */ - if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0) + if (asprintf(&tp->symbol, "0x%" PRIx64, tp->address) < 0) goto errout; /* For kprobe, check range */ @@ -3232,7 +3231,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, goto errout; } - if (asprintf(&tp->realname, "abs_%lx", tp->address) < 0) + if (asprintf(&tp->realname, "abs_%" PRIx64, tp->address) < 0) goto errout; if (pev->target) { diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 65769d7949a3..8ad5b1579f1d 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -33,7 +33,7 @@ struct probe_trace_point { char *module; /* Module name */ unsigned long offset; /* Offset from symbol */ unsigned long ref_ctr_offset; /* SDT reference counter offset */ - unsigned long address; /* Actual address of the trace point */ + u64 address; /* Actual address of the trace point */ bool retprobe; /* Return probe flag */ }; @@ -70,7 +70,7 @@ struct perf_probe_point { bool retprobe; /* Return probe flag */ char *lazy_line; /* Lazy matching pattern */ unsigned long offset; /* Offset from function entry */ - unsigned long abs_address; /* Absolute address of the point */ + u64 abs_address; /* Absolute address of the point */ }; /* Perf probe probing argument field chain */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index f9a6cbcd6415..3d50de3217d5 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -377,11 +377,11 @@ int probe_file__del_events(int fd, struct strfilter *filter) ret = probe_file__get_events(fd, filter, namelist); if (ret < 0) - return ret; + goto out; ret = probe_file__del_strlist(fd, namelist); +out: strlist__delete(namelist); - return ret; } diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index b029c29ce227..50d861a80f57 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -118,12 +118,17 @@ struct debuginfo *debuginfo__new(const char *path) char buf[PATH_MAX], nil = '\0'; struct dso *dso; struct debuginfo *dinfo = NULL; + struct build_id bid; /* Try to open distro debuginfo files */ dso = dso__new(path); if (!dso) goto out; + /* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */ + if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0) + dso__set_build_id(dso, &bid); + for (type = distro_dwarf_types; !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; type++) { @@ -663,7 +668,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, } tp->offset = (unsigned long)(paddr - eaddr); - tp->address = (unsigned long)paddr; + tp->address = paddr; tp->symbol = strdup(symbol); if (!tp->symbol) return -ENOMEM; @@ -1702,7 +1707,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, } /* Reverse search */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; @@ -1715,14 +1720,14 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - pr_warning("Failed to find debug information for address %lx\n", + pr_warning("Failed to find debug information for address %" PRIx64 "\n", addr); ret = -EINVAL; goto end; } /* Find a corresponding line (filename and lineno) */ - cu_find_lineinfo(&cudie, addr, &fname, &lineno); + cu_find_lineinfo(&cudie, (Dwarf_Addr)addr, &fname, &lineno); /* Don't care whether it failed or not */ /* Find a corresponding function (name, baseline and baseaddr) */ @@ -1737,7 +1742,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, } fname = dwarf_decl_file(&spdie); - if (addr == (unsigned long)baseaddr) { + if (addr == baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; goto post; @@ -1783,7 +1788,7 @@ post: if (lineno) ppt->line = lineno - baseline; else if (basefunc) { - ppt->offset = addr - (unsigned long)baseaddr; + ppt->offset = addr - baseaddr; func = basefunc; } @@ -1823,8 +1828,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, } static int line_range_walk_cb(const char *fname, int lineno, - Dwarf_Addr addr __maybe_unused, - void *data) + Dwarf_Addr addr, void *data) { struct line_finder *lf = data; const char *__fname; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 2febb5875678..8bc1c80d3c1c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -46,7 +46,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, struct probe_trace_event **tevs); /* Find a perf_probe_point from debuginfo */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt); int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 412f8e79e409..8feef3a05af7 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1032,7 +1032,7 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, Py_INCREF(pevsel); evsel = &((struct pyrf_evsel *)pevsel)->evsel; - evsel->idx = evlist->core.nr_entries; + evsel->core.idx = evlist->core.nr_entries; evlist__add(evlist, evsel); return Py_BuildValue("i", evlist->core.nr_entries); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 43e5b563dee8..bff669b615ee 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -25,12 +25,12 @@ */ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evlist) { - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); if (evsel__is_aux_event(leader) || arch_topdown_sample_read(leader) || is_mem_loads_aux_event(leader)) { evlist__for_each_entry(evlist, evsel) { - if (evsel->leader == leader && evsel != evsel->leader) + if (evsel__leader(evsel) == leader && evsel != evsel__leader(evsel)) return evsel; } } @@ -53,7 +53,7 @@ static u64 evsel__config_term_mask(struct evsel *evsel) static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist) { struct perf_event_attr *attr = &evsel->core.attr; - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); struct evsel *read_sampler; u64 term_types, freq_mask; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 164d2f45028c..69129e2aa7a1 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -687,7 +687,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict, _PyUnicode_FromString(decode)); } -static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) +static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) { unsigned int i = 0, r; int printed = 0; @@ -695,7 +695,7 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) bf[0] = 0; if (!regs || !regs->regs) - return 0; + return; for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { u64 val = regs->regs[i++]; @@ -704,8 +704,6 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) "%5s:0x%" PRIx64 " ", perf_reg_name(r), val); } - - return printed; } static void set_regs_in_dict(PyObject *dict, @@ -713,7 +711,16 @@ static void set_regs_in_dict(PyObject *dict, struct evsel *evsel) { struct perf_event_attr *attr = &evsel->core.attr; - char bf[512]; + + /* + * Here value 28 is a constant size which can be used to print + * one register value and its corresponds to: + * 16 chars is to specify 64 bit register in hexadecimal. + * 2 chars is for appending "0x" to the hexadecimal value and + * 10 chars is for register name. + */ + int size = __sw_hweight64(attr->sample_regs_intr) * 28; + char bf[size]; regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e9c929a39973..51f727402912 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -306,6 +306,7 @@ void perf_session__delete(struct perf_session *session) evlist__delete(session->evlist); perf_data__close(session->data); } + trace_event__cleanup(&session->tevent); free(session); } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 88ce47f2547e..568a88c001c6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3370,7 +3370,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int add_key(sb, s[i].name, llen); } -const char *sort_help(const char *prefix) +char *sort_help(const char *prefix) { struct strbuf sb; char *s; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 87a092645aa7..b67c469aba79 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -302,7 +302,7 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); -const char *sort_help(const char *prefix); +char *sort_help(const char *prefix); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index c588a6b7a8db..588601000f3f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -19,6 +19,7 @@ #include "util.h" #include "iostat.h" #include "pmu-hybrid.h" +#include "evlist-hybrid.h" #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" @@ -465,9 +466,11 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int config->csv_sep); if (counter->supported) { - config->print_free_counters_hint = 1; - if (is_mixed_hw_group(counter)) - config->print_mixed_hw_group_error = 1; + if (!evlist__has_hybrid(counter->evlist)) { + config->print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + config->print_mixed_hw_group_error = 1; + } } fprintf(config->output, "%-*s%s", @@ -593,6 +596,18 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c } } +static bool is_uncore(struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + return pmu && pmu->is_uncore; +} + +static bool hybrid_uniquify(struct evsel *evsel) +{ + return perf_pmu__has_hybrid() && !is_uncore(evsel); +} + static bool collect_data(struct perf_stat_config *config, struct evsel *counter, void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), @@ -601,7 +616,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter, if (counter->merged_stat) return false; cb(config, counter, data, true); - if (config->no_merge) + if (config->no_merge || hybrid_uniquify(counter)) uniquify_event_name(counter); else if (counter->auto_merge_stats) collect_all_aliases(config, counter, cb, data); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 39967a45f55b..34a7f5c1fff7 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -379,7 +379,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) evlist__for_each_entry(evsel_list, counter) { bool invalid = false; - leader = counter->leader; + leader = evsel__leader(counter); if (!counter->metric_expr) continue; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index d3ec2624e036..09ea334586f2 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -534,7 +534,7 @@ int create_perf_stat_counter(struct evsel *evsel, int cpu) { struct perf_event_attr *attr = &evsel->core.attr; - struct evsel *leader = evsel->leader; + struct evsel *leader = evsel__leader(evsel); attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; diff --git a/tools/perf/util/stream.c b/tools/perf/util/stream.c index 4bd5e5a00aa5..545e44981a27 100644 --- a/tools/perf/util/stream.c +++ b/tools/perf/util/stream.c @@ -139,7 +139,7 @@ static int evlist__init_callchain_streams(struct evlist *evlist, hists__output_resort(hists, NULL); init_hot_callchain(hists, &es[i]); - es[i].evsel_idx = pos->idx; + es[i].evsel_idx = pos->core.idx; i++; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a73345730ba9..31cd59a2b66e 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1074,14 +1074,15 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, return 0; } -int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, - struct symsrc *runtime_ss, int kmodule) +static int +dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, + struct symsrc *runtime_ss, int kmodule, int dynsym) { struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; struct maps *kmaps = kmap ? map__kmaps(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = dso; - Elf_Data *symstrs, *secstrs; + Elf_Data *symstrs, *secstrs, *secstrs_run, *secstrs_sym; uint32_t nr_syms; int err = -1; uint32_t idx; @@ -1098,34 +1099,15 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, if (kmap && !kmaps) return -1; - dso->symtab_type = syms_ss->type; - dso->is_64_bit = syms_ss->is_64_bit; - dso->rel = syms_ss->ehdr.e_type == ET_REL; - - /* - * Modules may already have symbols from kallsyms, but those symbols - * have the wrong values for the dso maps, so remove them. - */ - if (kmodule && syms_ss->symtab) - symbols__delete(&dso->symbols); - - if (!syms_ss->symtab) { - /* - * If the vmlinux is stripped, fail so we will fall back - * to using kallsyms. The vmlinux runtime symbols aren't - * of much use. - */ - if (dso->kernel) - goto out_elf_end; - - syms_ss->symtab = syms_ss->dynsym; - syms_ss->symshdr = syms_ss->dynshdr; - } - elf = syms_ss->elf; ehdr = syms_ss->ehdr; - sec = syms_ss->symtab; - shdr = syms_ss->symshdr; + if (dynsym) { + sec = syms_ss->dynsym; + shdr = syms_ss->dynshdr; + } else { + sec = syms_ss->symtab; + shdr = syms_ss->symshdr; + } if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr, ".text", NULL)) @@ -1150,8 +1132,16 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, if (sec_strndx == NULL) goto out_elf_end; - secstrs = elf_getdata(sec_strndx, NULL); - if (secstrs == NULL) + secstrs_run = elf_getdata(sec_strndx, NULL); + if (secstrs_run == NULL) + goto out_elf_end; + + sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs_sym = elf_getdata(sec_strndx, NULL); + if (secstrs_sym == NULL) goto out_elf_end; nr_syms = shdr.sh_size / shdr.sh_entsize; @@ -1237,6 +1227,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, gelf_getshdr(sec, &shdr); + secstrs = secstrs_sym; + /* * We have to fallback to runtime when syms' section header has * NOBITS set. NOBITS results in file offset (sh_offset) not @@ -1249,6 +1241,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, goto out_elf_end; gelf_getshdr(sec, &shdr); + secstrs = secstrs_run; } if (is_label && !elf_sec__filter(&shdr, secstrs)) @@ -1312,6 +1305,50 @@ out_elf_end: return err; } +int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, + struct symsrc *runtime_ss, int kmodule) +{ + int nr = 0; + int err = -1; + + dso->symtab_type = syms_ss->type; + dso->is_64_bit = syms_ss->is_64_bit; + dso->rel = syms_ss->ehdr.e_type == ET_REL; + + /* + * Modules may already have symbols from kallsyms, but those symbols + * have the wrong values for the dso maps, so remove them. + */ + if (kmodule && syms_ss->symtab) + symbols__delete(&dso->symbols); + + if (!syms_ss->symtab) { + /* + * If the vmlinux is stripped, fail so we will fall back + * to using kallsyms. The vmlinux runtime symbols aren't + * of much use. + */ + if (dso->kernel) + return err; + } else { + err = dso__load_sym_internal(dso, map, syms_ss, runtime_ss, + kmodule, 0); + if (err < 0) + return err; + nr = err; + } + + if (syms_ss->dynsym) { + err = dso__load_sym_internal(dso, map, syms_ss, runtime_ss, + kmodule, 1); + if (err < 0) + return err; + err += nr; + } + + return err; +} + static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data) { GElf_Phdr phdr; |