diff options
Diffstat (limited to 'tools/perf/arch/x86/util/intel-pt.c')
| -rw-r--r-- | tools/perf/arch/x86/util/intel-pt.c | 120 |
1 files changed, 64 insertions, 56 deletions
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 74b70fd379df..b394ad9cc635 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -12,13 +12,13 @@ #include <linux/log2.h> #include <linux/zalloc.h> #include <linux/err.h> -#include <cpuid.h> #include "../../../util/session.h" #include "../../../util/event.h" #include "../../../util/evlist.h" #include "../../../util/evsel.h" #include "../../../util/evsel_config.h" +#include "../../../util/config.h" #include "../../../util/cpumap.h" #include "../../../util/mmap.h" #include <subcmd/parse-options.h> @@ -32,6 +32,8 @@ #include "../../../util/tsc.h" #include <internal/lib.h> // page_size #include "../../../util/intel-pt.h" +#include <api/fs/fs.h> +#include "cpuid.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -51,6 +53,7 @@ struct intel_pt_recording { struct perf_pmu *intel_pt_pmu; int have_sched_switch; struct evlist *evlist; + bool all_switch_events; bool snapshot_mode; bool snapshot_init_done; size_t snapshot_size; @@ -60,43 +63,35 @@ struct intel_pt_recording { size_t priv_size; }; -static int intel_pt_parse_terms_with_default(const char *pmu_name, - struct list_head *formats, +static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu, const char *str, u64 *config) { - struct list_head *terms; + struct parse_events_terms terms; struct perf_event_attr attr = { .size = 0, }; int err; - terms = malloc(sizeof(struct list_head)); - if (!terms) - return -ENOMEM; - - INIT_LIST_HEAD(terms); - - err = parse_events_terms(terms, str); + parse_events_terms__init(&terms); + err = parse_events_terms(&terms, str); if (err) goto out_free; attr.config = *config; - err = perf_pmu__config_terms(pmu_name, formats, &attr, terms, true, - NULL); + err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*apply_hardcoded=*/false, + /*err=*/NULL); if (err) goto out_free; *config = attr.config; out_free: - parse_events_terms__delete(terms); + parse_events_terms__exit(&terms); return err; } -static int intel_pt_parse_terms(const char *pmu_name, struct list_head *formats, - const char *str, u64 *config) +static int intel_pt_parse_terms(const struct perf_pmu *pmu, const char *str, u64 *config) { *config = 0; - return intel_pt_parse_terms_with_default(pmu_name, formats, str, - config); + return intel_pt_parse_terms_with_default(pmu, str, config); } static u64 intel_pt_masked_bits(u64 mask, u64 bits) @@ -126,7 +121,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, *res = 0; - mask = perf_pmu__format_bits(&intel_pt_pmu->format, str); + mask = perf_pmu__format_bits(intel_pt_pmu, str); if (!mask) return -EINVAL; @@ -186,7 +181,7 @@ static int intel_pt_pick_bit(int bits, int target) return pick; } -static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) +static u64 intel_pt_default_config(const struct perf_pmu *intel_pt_pmu) { char buf[256]; int mtc, mtc_periods = 0, mtc_period; @@ -236,8 +231,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, buf, - &config); + intel_pt_parse_terms(intel_pt_pmu, buf, &config); close(dirfd); return config; @@ -266,20 +260,17 @@ static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr, return 0; } -struct perf_event_attr * -intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) +void intel_pt_pmu_default_config(const struct perf_pmu *intel_pt_pmu, + struct perf_event_attr *attr) { - struct perf_event_attr *attr; - - attr = zalloc(sizeof(struct perf_event_attr)); - if (!attr) - return NULL; + static u64 config; + static bool initialized; - attr->config = intel_pt_default_config(intel_pt_pmu); - - intel_pt_pmu->selectable = true; - - return attr; + if (!initialized) { + config = intel_pt_default_config(intel_pt_pmu); + initialized = true; + } + attr->config = config; } static const char *intel_pt_find_filter(struct evlist *evlist, @@ -320,7 +311,7 @@ static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d) { unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0; - __get_cpuid(0x15, &eax, &ebx, &ecx, &edx); + cpuid(0x15, 0, &eax, &ebx, &ecx, &edx); *n = ebx; *d = eax; } @@ -348,16 +339,11 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, if (priv_size != ptr->priv_size) return -EINVAL; - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "tsc", &tsc_bit); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "noretcomp", &noretcomp_bit); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "mtc", &mtc_bit); - mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format, - "mtc_period"); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "cyc", &cyc_bit); + intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit); + intel_pt_parse_terms(intel_pt_pmu, "noretcomp", &noretcomp_bit); + intel_pt_parse_terms(intel_pt_pmu, "mtc", &mtc_bit); + mtc_freq_bits = perf_pmu__format_bits(intel_pt_pmu, "mtc_period"); + intel_pt_parse_terms(intel_pt_pmu, "cyc", &cyc_bit); intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d); @@ -387,7 +373,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus); + per_cpu_mmaps = !perf_cpu_map__is_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -446,6 +432,16 @@ static int intel_pt_track_switches(struct evlist *evlist) } #endif +static bool intel_pt_exclude_guest(void) +{ + int pt_mode; + + if (sysfs__read_int("module/kvm_intel/parameters/pt_mode", &pt_mode)) + pt_mode = 0; + + return pt_mode == 1; +} + static void intel_pt_valid_str(char *str, size_t len, u64 valid) { unsigned int val, last = 0, state = 1; @@ -511,7 +507,7 @@ static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, int dirfd, valid |= 1; - bits = perf_pmu__format_bits(&intel_pt_pmu->format, name); + bits = perf_pmu__format_bits(intel_pt_pmu, name); config &= bits; @@ -638,6 +634,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq = 0; evsel->core.attr.sample_period = 1; + evsel->core.attr.exclude_guest = intel_pt_exclude_guest(); evsel->no_aux_samples = true; evsel->needs_auxtrace_mmap = true; intel_pt_evsel = evsel; @@ -776,13 +773,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, } if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) { - u32 aux_watermark = opts->auxtrace_mmap_pages * page_size / 4; + size_t aw = opts->auxtrace_mmap_pages * (size_t)page_size / 4; + u32 aux_watermark = aw > UINT_MAX ? UINT_MAX : aw; intel_pt_evsel->core.attr.aux_watermark = aux_watermark; } - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "tsc", &tsc_bit); + intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit); if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit)) have_timing_info = true; @@ -793,13 +790,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Per-cpu recording needs sched_switch events to distinguish different * threads. */ - if (have_timing_info && !perf_cpu_map__empty(cpus) && + if (have_timing_info && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) && !record_opts__no_switch_events(opts)) { if (perf_can_record_switch_events()) { bool cpu_wide = !target__none(&opts->target) && !target__has_task(&opts->target); - if (!cpu_wide && perf_can_record_cpu_wide()) { + if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) { struct evsel *switch_evsel; switch_evsel = evlist__add_dummy_on_all_cpus(evlist); @@ -851,7 +848,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) evsel__set_sample_bit(intel_pt_evsel, CPU); } @@ -877,7 +874,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->immediate = true; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) { + if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); /* And the CPU for switch events */ evsel__set_sample_bit(tracking_evsel, CPU); @@ -889,7 +886,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Warn the user when we do not have enough information to decode i.e. * per-cpu with no sched_switch (except workload-only). */ - if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) && + if (!ptr->have_sched_switch && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) && !target__none(&opts->target) && !intel_pt_evsel->core.attr.exclude_user) ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); @@ -1183,6 +1180,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) return rdtsc(); } +static int intel_pt_perf_config(const char *var, const char *value, void *data) +{ + struct intel_pt_recording *ptr = data; + + if (!strcmp(var, "intel-pt.all-switch-events")) + ptr->all_switch_events = perf_config_bool(var, value); + + return 0; +} + struct auxtrace_record *intel_pt_recording_init(int *err) { struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); @@ -1202,8 +1209,9 @@ struct auxtrace_record *intel_pt_recording_init(int *err) return NULL; } + perf_config(intel_pt_perf_config, ptr); + ptr->intel_pt_pmu = intel_pt_pmu; - ptr->itr.pmu = intel_pt_pmu; ptr->itr.recording_options = intel_pt_recording_options; ptr->itr.info_priv_size = intel_pt_info_priv_size; ptr->itr.info_fill = intel_pt_info_fill; |
