diff options
| -rw-r--r-- | tools/perf/arch/x86/util/Build | 2 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/intel-pt.c | 752 | ||||
| -rw-r--r-- | tools/perf/util/Build | 1 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt.c | 1911 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt.h | 51 |
5 files changed, 2717 insertions, 0 deletions
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index cfbccc4e3187..139608878888 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -6,3 +6,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o + +libperf-$(CONFIG_AUXTRACE) += intel-pt.o diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c new file mode 100644 index 000000000000..da7d2c15e611 --- /dev/null +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -0,0 +1,752 @@ +/* + * intel_pt.c: Intel Processor Trace support + * Copyright (c) 2013-2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/log2.h> + +#include "../../perf.h" +#include "../../util/session.h" +#include "../../util/event.h" +#include "../../util/evlist.h" +#include "../../util/evsel.h" +#include "../../util/cpumap.h" +#include "../../util/parse-options.h" +#include "../../util/parse-events.h" +#include "../../util/pmu.h" +#include "../../util/debug.h" +#include "../../util/auxtrace.h" +#include "../../util/tsc.h" +#include "../../util/intel-pt.h" + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) +#define KiB_MASK(x) (KiB(x) - 1) +#define MiB_MASK(x) (MiB(x) - 1) + +#define INTEL_PT_DEFAULT_SAMPLE_SIZE KiB(4) + +#define INTEL_PT_MAX_SAMPLE_SIZE KiB(60) + +#define INTEL_PT_PSB_PERIOD_NEAR 256 + +struct intel_pt_snapshot_ref { + void *ref_buf; + size_t ref_offset; + bool wrapped; +}; + +struct intel_pt_recording { + struct auxtrace_record itr; + struct perf_pmu *intel_pt_pmu; + int have_sched_switch; + struct perf_evlist *evlist; + bool snapshot_mode; + bool snapshot_init_done; + size_t snapshot_size; + size_t snapshot_ref_buf_size; + int snapshot_ref_cnt; + struct intel_pt_snapshot_ref *snapshot_refs; +}; + +static int intel_pt_parse_terms_with_default(struct list_head *formats, + const char *str, + u64 *config) +{ + struct list_head *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); + if (err) + goto out_free; + + attr.config = *config; + err = perf_pmu__config_terms(formats, &attr, terms, true, NULL); + if (err) + goto out_free; + + *config = attr.config; +out_free: + parse_events__free_terms(terms); + return err; +} + +static int intel_pt_parse_terms(struct list_head *formats, const char *str, + u64 *config) +{ + *config = 0; + return intel_pt_parse_terms_with_default(formats, str, config); +} + +static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return 256; +} + +static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) +{ + u64 config; + + intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &config); + return config; +} + +static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr, + struct record_opts *opts, + const char *str) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + + ptr->snapshot_size = snapshot_size; + + return 0; +} + +struct perf_event_attr * +intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) +{ + struct perf_event_attr *attr; + + attr = zalloc(sizeof(struct perf_event_attr)); + if (!attr) + return NULL; + + attr->config = intel_pt_default_config(intel_pt_pmu); + + intel_pt_pmu->selectable = true; + + return attr; +} + +static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused) +{ + return INTEL_PT_AUXTRACE_PRIV_SIZE; +} + +static int intel_pt_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct auxtrace_info_event *auxtrace_info, + size_t priv_size) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; + struct perf_event_mmap_page *pc; + struct perf_tsc_conversion tc = { .time_mult = 0, }; + bool cap_user_time_zero = false, per_cpu_mmaps; + u64 tsc_bit, noretcomp_bit; + int err; + + if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE) + return -EINVAL; + + intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); + intel_pt_parse_terms(&intel_pt_pmu->format, "noretcomp", + &noretcomp_bit); + + if (!session->evlist->nr_mmaps) + return -EINVAL; + + pc = session->evlist->mmap[0].base; + if (pc) { + err = perf_read_tsc_conversion(pc, &tc); + if (err) { + if (err != -EOPNOTSUPP) + return err; + } else { + cap_user_time_zero = tc.time_mult != 0; + } + if (!cap_user_time_zero) + ui__warning("Intel Processor Trace: TSC not available\n"); + } + + per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus); + + auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; + auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; + auxtrace_info->priv[INTEL_PT_TIME_SHIFT] = tc.time_shift; + auxtrace_info->priv[INTEL_PT_TIME_MULT] = tc.time_mult; + auxtrace_info->priv[INTEL_PT_TIME_ZERO] = tc.time_zero; + auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO] = cap_user_time_zero; + auxtrace_info->priv[INTEL_PT_TSC_BIT] = tsc_bit; + auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT] = noretcomp_bit; + auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH] = ptr->have_sched_switch; + auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE] = ptr->snapshot_mode; + auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS] = per_cpu_mmaps; + + return 0; +} + +static int intel_pt_track_switches(struct perf_evlist *evlist) +{ + const char *sched_switch = "sched:sched_switch"; + struct perf_evsel *evsel; + int err; + + if (!perf_evlist__can_select_event(evlist, sched_switch)) + return -EPERM; + + err = parse_events(evlist, sched_switch, NULL); + if (err) { + pr_debug2("%s: failed to parse %s, error %d\n", + __func__, sched_switch, err); + return err; + } + + evsel = perf_evlist__last(evlist); + + perf_evsel__set_sample_bit(evsel, CPU); + perf_evsel__set_sample_bit(evsel, TIME); + + evsel->system_wide = true; + evsel->no_aux_samples = true; + evsel->immediate = true; + + return 0; +} + +static int intel_pt_recording_options(struct auxtrace_record *itr, + struct perf_evlist *evlist, + struct record_opts *opts) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; + bool have_timing_info; + struct perf_evsel *evsel, *intel_pt_evsel = NULL; + const struct cpu_map *cpus = evlist->cpus; + bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + u64 tsc_bit; + + ptr->evlist = evlist; + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type == intel_pt_pmu->type) { + if (intel_pt_evsel) { + pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n"); + return -EINVAL; + } + evsel->attr.freq = 0; + evsel->attr.sample_period = 1; + intel_pt_evsel = evsel; + opts->full_auxtrace = true; + } + } + + if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) { + pr_err("Snapshot mode (-S option) requires " INTEL_PT_PMU_NAME " PMU event (-e " INTEL_PT_PMU_NAME ")\n"); + return -EINVAL; + } + + if (opts->use_clockid) { + pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n"); + return -EINVAL; + } + + if (!opts->full_auxtrace) + return 0; + + /* Set default sizes for snapshot mode */ + if (opts->auxtrace_snapshot_mode) { + size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist); + + if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && + opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + if (!opts->auxtrace_snapshot_size) + opts->auxtrace_snapshot_size = + opts->auxtrace_mmap_pages * (size_t)page_size; + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } + if (opts->auxtrace_snapshot_size > + opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + pr_debug2("Intel PT snapshot size: %zu\n", + opts->auxtrace_snapshot_size); + if (psb_period && + opts->auxtrace_snapshot_size <= psb_period + + INTEL_PT_PSB_PERIOD_NEAR) + ui__warning("Intel PT snapshot size (%zu) may be too small for PSB period (%zu)\n", + opts->auxtrace_snapshot_size, psb_period); + } + + /* Set default sizes for full trace mode */ + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } + + /* Validate auxtrace_mmap_pages */ + if (opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; + size_t min_sz; + + if (opts->auxtrace_snapshot_mode) + min_sz = KiB(4); + else + min_sz = KiB(8); + + if (sz < min_sz || !is_power_of_2(sz)) { + pr_err("Invalid mmap size for Intel Processor Trace: must be at least %zuKiB and a power of 2\n", + min_sz / 1024); + return -EINVAL; + } + } + + intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); + + if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit)) + have_timing_info = true; + else + have_timing_info = false; + + /* + * Per-cpu recording needs sched_switch events to distinguish different + * threads. + */ + if (have_timing_info && !cpu_map__empty(cpus)) { + int err; + + err = intel_pt_track_switches(evlist); + if (err == -EPERM) + pr_debug2("Unable to select sched:sched_switch\n"); + else if (err) + return err; + else + ptr->have_sched_switch = 1; + } + + if (intel_pt_evsel) { + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, intel_pt_evsel); + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(intel_pt_evsel, CPU); + } + + /* Add dummy event to keep tracking */ + if (opts->full_auxtrace) { + struct perf_evsel *tracking_evsel; + int err; + + err = parse_events(evlist, "dummy:u", NULL); + if (err) + return err; + + tracking_evsel = perf_evlist__last(evlist); + + perf_evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->attr.freq = 0; + tracking_evsel->attr.sample_period = 1; + + /* In per-cpu case, always need the time of mmap events etc */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(tracking_evsel, TIME); + } + + /* + * 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 && !cpu_map__empty(cpus) && + !target__none(&opts->target)) + ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); + + return 0; +} + +static int intel_pt_snapshot_start(struct auxtrace_record *itr) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->intel_pt_pmu->type) + return perf_evlist__disable_event(ptr->evlist, evsel); + } + return -EINVAL; +} + +static int intel_pt_snapshot_finish(struct auxtrace_record *itr) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->intel_pt_pmu->type) + return perf_evlist__enable_event(ptr->evlist, evsel); + } + return -EINVAL; +} + +static int intel_pt_alloc_snapshot_refs(struct intel_pt_recording *ptr, int idx) +{ + const size_t sz = sizeof(struct intel_pt_snapshot_ref); + int cnt = ptr->snapshot_ref_cnt, new_cnt = cnt * 2; + struct intel_pt_snapshot_ref *refs; + + if (!new_cnt) + new_cnt = 16; + + while (new_cnt <= idx) + new_cnt *= 2; + + refs = calloc(new_cnt, sz); + if (!refs) + return -ENOMEM; + + memcpy(refs, ptr->snapshot_refs, cnt * sz); + + ptr->snapshot_refs = refs; + ptr->snapshot_ref_cnt = new_cnt; + + return 0; +} + +static void intel_pt_free_snapshot_refs(struct intel_pt_recording *ptr) +{ + int i; + + for (i = 0; i < ptr->snapshot_ref_cnt; i++) + zfree(&ptr->snapshot_refs[i].ref_buf); + zfree(&ptr->snapshot_refs); +} + +static void intel_pt_recording_free(struct auxtrace_record *itr) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + + intel_pt_free_snapshot_refs(ptr); + free(ptr); +} + +static int intel_pt_alloc_snapshot_ref(struct intel_pt_recording *ptr, int idx, + size_t snapshot_buf_size) +{ + size_t ref_buf_size = ptr->snapshot_ref_buf_size; + void *ref_buf; + + ref_buf = zalloc(ref_buf_size); + if (!ref_buf) + return -ENOMEM; + + ptr->snapshot_refs[idx].ref_buf = ref_buf; + ptr->snapshot_refs[idx].ref_offset = snapshot_buf_size - ref_buf_size; + + return 0; +} + +static size_t intel_pt_snapshot_ref_buf_size(struct intel_pt_recording *ptr, + size_t snapshot_buf_size) +{ + const size_t max_size = 256 * 1024; + size_t buf_size = 0, psb_period; + + if (ptr->snapshot_size <= 64 * 1024) + return 0; + + psb_period = intel_pt_psb_period(ptr->intel_pt_pmu, ptr->evlist); + if (psb_period) + buf_size = psb_period * 2; + + if (!buf_size || buf_size > max_size) + buf_size = max_size; + + if (buf_size >= snapshot_buf_size) + return 0; + + if (buf_size >= ptr->snapshot_size / 2) + return 0; + + return buf_size; +} + +static int intel_pt_snapshot_init(struct intel_pt_recording *ptr, + size_t snapshot_buf_size) +{ + if (ptr->snapshot_init_done) + return 0; + + ptr->snapshot_init_done = true; + + ptr->snapshot_ref_buf_size = intel_pt_snapshot_ref_buf_size(ptr, + snapshot_buf_size); + + return 0; +} + +/** + * intel_pt_compare_buffers - compare bytes in a buffer to a circular buffer. + * @buf1: first buffer + * @compare_size: number of bytes to compare + * @buf2: second buffer (a circular buffer) + * @offs2: offset in second buffer + * @buf2_size: size of second buffer + * + * The comparison allows for the possibility that the bytes to compare in the + * circular buffer are not contiguous. It is assumed that @compare_size <= + * @buf2_size. This function returns %false if the bytes are identical, %true + * otherwise. + */ +static bool intel_pt_compare_buffers(void *buf1, size_t compare_size, + void *buf2, size_t offs2, size_t buf2_size) +{ + size_t end2 = offs2 + compare_size, part_size; + + if (end2 <= buf2_size) + return memcmp(buf1, buf2 + offs2, compare_size); + + part_size = end2 - buf2_size; + if (memcmp(buf1, buf2 + offs2, part_size)) + return true; + + compare_size -= part_size; + + return memcmp(buf1 + part_size, buf2, compare_size); +} + +static bool intel_pt_compare_ref(void *ref_buf, size_t ref_offset, + size_t ref_size, size_t buf_size, + void *data, size_t head) +{ + size_t ref_end = ref_offset + ref_size; + + if (ref_end > buf_size) { + if (head > ref_offset || head < ref_end - buf_size) + return true; + } else if (head > ref_offset && head < ref_end) { + return true; + } + + return intel_pt_compare_buffers(ref_buf, ref_size, data, ref_offset, + buf_size); +} + +static void intel_pt_copy_ref(void *ref_buf, size_t ref_size, size_t buf_size, + void *data, size_t head) +{ + if (head >= ref_size) { + memcpy(ref_buf, data + head - ref_size, ref_size); + } else { + memcpy(ref_buf, data, head); + ref_size -= head; + memcpy(ref_buf + head, data + buf_size - ref_size, ref_size); + } +} + +static bool intel_pt_wrapped(struct intel_pt_recording *ptr, int idx, + struct auxtrace_mmap *mm, unsigned char *data, + u64 head) +{ + struct intel_pt_snapshot_ref *ref = &ptr->snapshot_refs[idx]; + bool wrapped; + + wrapped = intel_pt_compare_ref(ref->ref_buf, ref->ref_offset, + ptr->snapshot_ref_buf_size, mm->len, + data, head); + + intel_pt_copy_ref(ref->ref_buf, ptr->snapshot_ref_buf_size, mm->len, + data, head); + + return wrapped; +} + +static bool intel_pt_first_wrap(u64 *data, size_t buf_size) +{ + int i, a, b; + + b = buf_size >> 3; + a = b - 512; + if (a < 0) + a = 0; + + for (i = a; i < b; i++) { + if (data[i]) + return true; + } + + return false; +} + +static int intel_pt_find_snapshot(struct auxtrace_record *itr, int idx, + struct auxtrace_mmap *mm, unsigned char *data, + u64 *head, u64 *old) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + bool wrapped; + int err; + + pr_debug3("%s: mmap index %d old head %zu new head %zu\n", + __func__, idx, (size_t)*old, (size_t)*head); + + err = intel_pt_snapshot_init(ptr, mm->len); + if (err) + goto out_err; + + if (idx >= ptr->snapshot_ref_cnt) { + err = intel_pt_alloc_snapshot_refs(ptr, idx); + if (err) + goto out_err; + } + + if (ptr->snapshot_ref_buf_size) { + if (!ptr->snapshot_refs[idx].ref_buf) { + err = intel_pt_alloc_snapshot_ref(ptr, idx, mm->len); + if (err) + goto out_err; + } + wrapped = intel_pt_wrapped(ptr, idx, mm, data, *head); + } else { + wrapped = ptr->snapshot_refs[idx].wrapped; + if (!wrapped && intel_pt_first_wrap((u64 *)data, mm->len)) { + ptr->snapshot_refs[idx].wrapped = true; + wrapped = true; + } + } + + /* + * In full trace mode 'head' continually increases. However in snapshot + * mode 'head' is an offset within the buffer. Here 'old' and 'head' + * are adjusted to match the full trace case which expects that 'old' is + * always less than 'head'. + */ + if (wrapped) { + *old = *head; + *head += mm->len; + } else { + if (mm->mask) + *old &= mm->mask; + else + *old %= mm->len; + if (*old > *head) + *head += mm->len; + } + + pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n", + __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head); + + return 0; + +out_err: + pr_err("%s: failed, error %d\n", __func__, err); + return err; +} + +static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) +{ + return rdtsc(); +} + +static int intel_pt_read_finish(struct auxtrace_record *itr, int idx) +{ + struct intel_pt_recording *ptr = + container_of(itr, struct intel_pt_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->intel_pt_pmu->type) + return perf_evlist__enable_event_idx(ptr->evlist, evsel, + idx); + } + return -EINVAL; +} + +struct auxtrace_record *intel_pt_recording_init(int *err) +{ + struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); + struct intel_pt_recording *ptr; + + if (!intel_pt_pmu) + return NULL; + + ptr = zalloc(sizeof(struct intel_pt_recording)); + if (!ptr) { + *err = -ENOMEM; + return NULL; + } + + ptr->intel_pt_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; + ptr->itr.free = intel_pt_recording_free; + ptr->itr.snapshot_start = intel_pt_snapshot_start; + ptr->itr.snapshot_finish = intel_pt_snapshot_finish; + ptr->itr.find_snapshot = intel_pt_find_snapshot; + ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options; + ptr->itr.reference = intel_pt_reference; + ptr->itr.read_finish = intel_pt_read_finish; + return &ptr->itr; +} diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 615ca12c2e44..c20473d1369e 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -79,6 +79,7 @@ libperf-y += cloexec.o libperf-y += thread-stack.o libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ +libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-y += parse-branch-options.o libperf-$(CONFIG_LIBELF) += symbol-elf.o diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c new file mode 100644 index 000000000000..2a4a4120473b --- /dev/null +++ b/tools/perf/util/intel-pt.c @@ -0,0 +1,1911 @@ +/* + * intel_pt.c: Intel Processor Trace support + * Copyright (c) 2013-2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <stdio.h> +#include <stdbool.h> +#include <errno.h> +#include <linux/kernel.h> +#include <linux/types.h> + +#include "../perf.h" +#include "session.h" +#include "machine.h" +#include "tool.h" +#include "event.h" +#include "evlist.h" +#include "evsel.h" +#include "map.h" +#include "color.h" +#include "util.h" +#include "thread.h" +#include "thread-stack.h" +#include "symbol.h" +#include "callchain.h" +#include "dso.h" +#include "debug.h" +#include "auxtrace.h" +#include "tsc.h" +#include "intel-pt.h" + +#include "intel-pt-decoder/intel-pt-log.h" +#include "intel-pt-decoder/intel-pt-decoder.h" +#include "intel-pt-decoder/intel-pt-insn-decoder.h" +#include "intel-pt-decoder/intel-pt-pkt-decoder.h" + +#define MAX_TIMESTAMP (~0ULL) + +struct intel_pt { + struct auxtrace auxtrace; + struct auxtrace_queues queues; + struct auxtrace_heap heap; + u32 auxtrace_type; + struct perf_session *session; + struct machine *machine; + struct perf_evsel *switch_evsel; + struct thread *unknown_thread; + bool timeless_decoding; + bool sampling_mode; + bool snapshot_mode; + bool per_cpu_mmaps; + bool have_tsc; + bool data_queued; + bool est_tsc; + bool sync_switch; + int have_sched_switch; + u32 pmu_type; + u64 kernel_start; + u64 switch_ip; + u64 ptss_ip; + + struct perf_tsc_conversion tc; + bool cap_user_time_zero; + + struct itrace_synth_opts synth_opts; + + bool sample_instructions; + u64 instructions_sample_type; + u64 instructions_sample_period; + u64 instructions_id; + + bool sample_branches; + u32 branches_filter; + u64 branches_sample_type; + u64 branches_id; + + bool sample_transactions; + u64 transactions_sample_type; + u64 transactions_id; + + bool synth_needs_swap; + + u64 tsc_bit; + u64 noretcomp_bit; + unsigned max_non_turbo_ratio; +}; + +enum switch_state { + INTEL_PT_SS_NOT_TRACING, + INTEL_PT_SS_UNKNOWN, + INTEL_PT_SS_TRACING, + INTEL_PT_SS_EXPECTING_SWITCH_EVENT, + INTEL_PT_SS_EXPECTING_SWITCH_IP, +}; + +struct intel_pt_queue { + struct intel_pt *pt; + unsigned int queue_nr; + struct auxtrace_buffer *buffer; + void *decoder; + const struct intel_pt_state *state; + struct ip_callchain *chain; + union perf_event *event_buf; + bool on_heap; + bool stop; + bool step_through_buffers; + bool use_buffer_pid_tid; + pid_t pid, tid; + int cpu; + int switch_state; + pid_t next_tid; + struct thread *thread; + bool exclude_kernel; + bool have_sample; + u64 time; + u64 timestamp; + u32 flags; + u16 insn_len; +}; + +static void intel_pt_dump(struct intel_pt *pt __maybe_unused, + unsigned char *buf, size_t len) +{ + struct intel_pt_pkt packet; + size_t pos = 0; + int ret, pkt_len, i; + char desc[INTEL_PT_PKT_DESC_MAX]; + const char *color = PERF_COLOR_BLUE; + + color_fprintf(stdout, color, + ". ... Intel Processor Trace data: size %zu bytes\n", + len); + + while (len) { + ret = intel_pt_get_packet(buf, len, &packet); + if (ret > 0) + pkt_len = ret; + else + pkt_len = 1; + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + for (i = 0; i < pkt_len; i++) + color_fprintf(stdout, color, " %02x", buf[i]); + for (; i < 16; i++) + color_fprintf(stdout, color, " "); + if (ret > 0) { + ret = intel_pt_pkt_desc(&packet, desc, + INTEL_PT_PKT_DESC_MAX); + if (ret > 0) + color_fprintf(stdout, color, " %s\n", desc); + } else { + color_fprintf(stdout, color, " Bad packet!\n"); + } + pos += pkt_len; + buf += pkt_len; + len -= pkt_len; + } +} + +static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, + size_t len) +{ + printf(".\n"); + intel_pt_dump(pt, buf, len); +} + +static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, + struct auxtrace_buffer *b) +{ + void *start; + + start = intel_pt_find_overlap(a->data, a->size, b->data, b->size, + pt->have_tsc); + if (!start) + return -EINVAL; + b->use_size = b->data + b->size - start; + b->use_data = start; + return 0; +} + +static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq, + struct auxtrace_queue *queue, + struct auxtrace_buffer *buffer) +{ + if (queue->cpu == -1 && buffer->cpu != -1) + ptq->cpu = buffer->cpu; + + ptq->pid = buffer->pid; + ptq->tid = buffer->tid; + + intel_pt_log("queue %u cpu %d pid %d tid %d\n", + ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid); + + thread__zput(ptq->thread); + + if (ptq->tid != -1) { + if (ptq->pid != -1) + ptq->thread = machine__findnew_thread(ptq->pt->machine, + ptq->pid, + ptq->tid); + else + ptq->thread = machine__find_thread(ptq->pt->machine, -1, + ptq->tid); + } +} + +/* This function assumes data is processed sequentially only */ +static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) +{ + struct intel_pt_queue *ptq = data; + struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer; + struct auxtrace_queue *queue; + + if (ptq->stop) { + b->len = 0; + return 0; + } + + queue = &ptq->pt->queues.queue_array[ptq->queue_nr]; + + buffer = auxtrace_buffer__next(queue, buffer); + if (!buffer) { + if (old_buffer) + auxtrace_buffer__drop_data(old_buffer); + b->len = 0; + return 0; + } + + ptq->buffer = buffer; + + if (!buffer->data) { + int fd = perf_data_file__fd(ptq->pt->session->file); + + buffer->data = auxtrace_buffer__get_data(buffer, fd); + if (!buffer->data) + return -ENOMEM; + } + + if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer && + intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer)) + return -ENOMEM; + + if (old_buffer) + auxtrace_buffer__drop_data(old_buffer); + + if (buffer->use_data) { + b->len = buffer->use_size; + b->buf = buffer->use_data; + } else { + b->len = buffer->size; + b->buf = buffer->data; + } + b->ref_timestamp = buffer->reference; + + if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode && + !buffer->consecutive)) { + b->consecutive = false; + b->trace_nr = buffer->buffer_nr + 1; + } else { + b->consecutive = true; + } + + if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid || + ptq->tid != buffer->tid)) + intel_pt_use_buffer_pid_tid(ptq, queue, buffer); + + if (ptq->step_through_buffers) + ptq->stop = true; + + if (!b->len) + return intel_pt_get_trace(b, data); + + return 0; +} + +struct intel_pt_cache_entry { + struct auxtrace_cache_entry entry; + u64 insn_cnt; + u64 byte_cnt; + enum intel_pt_insn_op op; + enum intel_pt_insn_branch branch; + int length; + int32_t rel; +}; + +static int intel_pt_config_div(const char *var, const char *value, void *data) +{ + int *d = data; + long val; + + if (!strcmp(var, "intel-pt.cache-divisor")) { + val = strtol(value, NULL, 0); + if (val > 0 && val <= INT_MAX) + *d = val; + } + + return 0; +} + +static int intel_pt_cache_divisor(void) +{ + static int d; + + if (d) + return d; + + perf_config(intel_pt_config_div, &d); + + if (!d) + d = 64; + + return d; +} + +static unsigned int intel_pt_cache_size(struct dso *dso, + struct machine *machine) +{ + off_t size; + + size = dso__data_size(dso, machine); + size /= intel_pt_cache_divisor(); + if (size < 1000) + return 10; + if (size > (1 << 21)) + return 21; + return 32 - __builtin_clz(size); +} + +static struct auxtrace_cache *intel_pt_cache(struct dso *dso, + struct machine *machine) +{ + struct auxtrace_cache *c; + unsigned int bits; + + if (dso->auxtrace_cache) + return dso->auxtrace_cache; + + bits = intel_pt_cache_size(dso, machine); + + /* Ignoring cache creation failure */ + c = auxtrace_cache__new(bits, sizeof(struct intel_pt_cache_entry), 200); + + dso->auxtrace_cache = c; + + return c; +} + +static int intel_pt_cache_add(struct dso *dso, struct machine *machine, + u64 offset, u64 insn_cnt, u64 byte_cnt, + struct intel_pt_insn *intel_pt_insn) +{ + struct auxtrace_cache *c = intel_pt_cache(dso, machine); + struct intel_pt_cache_entry *e; + int err; + + if (!c) + return -ENOMEM; + + e = auxtrace_cache__alloc_entry(c); + if (!e) + return -ENOMEM; + + e->insn_cnt = insn_cnt; + e->byte_cnt = byte_cnt; + e->op = intel_pt_insn->op; + e- |