diff options
Diffstat (limited to 'tools/perf/arch/x86/util')
| -rw-r--r-- | tools/perf/arch/x86/util/archinsn.c | 4 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/auxtrace.c | 25 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/dwarf-regs.c | 16 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/event.c | 9 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/header.c | 4 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/intel-bts.c | 74 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/intel-pt.c | 231 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/kvm-stat.c | 17 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/machine.c | 4 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/perf_regs.c | 50 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/tsc.c | 10 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/unwind-libunwind.c | 2 |
12 files changed, 289 insertions, 157 deletions
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c index 4237bb2e7fa2..3e6791531ca5 100644 --- a/tools/perf/arch/x86/util/archinsn.c +++ b/tools/perf/arch/x86/util/archinsn.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include "perf.h" +#include "../../../../arch/x86/include/asm/insn.h" #include "archinsn.h" -#include "util/intel-pt-decoder/insn.h" +#include "event.h" #include "machine.h" #include "thread.h" #include "symbol.h" diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index b135af62011c..7abc9fd4cbec 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * auxtrace.c: AUX area tracing support * Copyright (c) 2013-2014, 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 <errno.h> @@ -25,22 +16,26 @@ #include "../../util/evlist.h" static -struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, int *err) { struct perf_pmu *intel_pt_pmu; struct perf_pmu *intel_bts_pmu; - struct perf_evsel *evsel; + struct evsel *evsel; bool found_pt = false; bool found_bts = false; intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); + if (intel_pt_pmu) + intel_pt_pmu->auxtrace = true; intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + if (intel_bts_pmu) + intel_bts_pmu->auxtrace = true; evlist__for_each_entry(evlist, evsel) { - if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type) + if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) found_pt = true; - if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type) + if (intel_bts_pmu && evsel->core.attr.type == intel_bts_pmu->type) found_bts = true; } @@ -59,7 +54,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, return NULL; } -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { char buffer[64]; diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index 1f86ee8fb831..530934805710 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. * Extracted from probe-finder.c * * Written by Masami Hiramatsu <mhiramat@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #include <stddef.h> diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 675a0213044d..ac45015cc6ba 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/string.h> +#include <linux/zalloc.h> +#include "../../util/event.h" +#include "../../util/synthetic-events.h" #include "../../util/machine.h" #include "../../util/tool.h" #include "../../util/map.h" -#include "../../util/util.h" #include "../../util/debug.h" #if defined(__x86_64__) @@ -16,8 +18,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, { int rc = 0; struct map *pos; - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps; + struct maps *kmaps = &machine->kmaps; union perf_event *event = zalloc(sizeof(event->mmap) + machine->id_hdr_size); @@ -27,7 +28,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, return -1; } - for (pos = maps__first(maps); pos; pos = map__next(pos)) { + maps__for_each_entry(kmaps, pos) { struct kmap *kmap; size_t size; diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index af9a9f2600be..aa6deb463bf3 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include <sys/types.h> +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <regex.h> +#include "../../util/debug.h" #include "../../util/header.h" static inline void @@ -57,7 +59,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt) buffer[nb-1] = '\0'; return 0; } - return -1; + return ENOBUFS; } int diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 781df40b2966..27d9e214d068 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * intel-bts.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 <errno.h> @@ -18,17 +9,21 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include "../../util/cpumap.h" +#include "../../util/event.h" #include "../../util/evsel.h" #include "../../util/evlist.h" +#include "../../util/mmap.h" #include "../../util/session.h" -#include "../../util/util.h" #include "../../util/pmu.h" #include "../../util/debug.h" +#include "../../util/record.h" #include "../../util/tsc.h" #include "../../util/auxtrace.h" #include "../../util/intel-bts.h" +#include <internal/lib.h> // page_size #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -44,7 +39,7 @@ struct intel_bts_snapshot_ref { struct intel_bts_recording { struct auxtrace_record itr; struct perf_pmu *intel_bts_pmu; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; size_t snapshot_size; int snapshot_ref_cnt; @@ -59,14 +54,14 @@ struct branch { static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return INTEL_BTS_AUXTRACE_PRIV_SIZE; } static int intel_bts_info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size) { struct intel_bts_recording *btsr = @@ -80,10 +75,10 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE) return -EINVAL; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -108,27 +103,32 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, } static int intel_bts_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu; - struct perf_evsel *evsel, *intel_bts_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; - bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + struct evsel *evsel, *intel_bts_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; + bool privileged = perf_event_paranoid_check(-1); + + if (opts->auxtrace_sample_mode) { + pr_err("Intel BTS does not support AUX area sampling\n"); + return -EINVAL; + } btsr->evlist = evlist; btsr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_bts_pmu->type) { + if (evsel->core.attr.type == intel_bts_pmu->type) { if (intel_bts_evsel) { pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_bts_evsel = evsel; opts->full_auxtrace = true; } @@ -142,7 +142,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; - if (opts->full_auxtrace && !cpu_map__empty(cpus)) { + if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) { pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n"); return -EINVAL; } @@ -223,25 +223,25 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(intel_bts_evsel, CPU); } /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; int err; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; } return 0; @@ -322,11 +322,11 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -335,11 +335,11 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -417,10 +417,10 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) return perf_evlist__enable_event_idx(btsr->evlist, evsel, idx); } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index ba8ecaf52200..20df442fdf36 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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 <errno.h> @@ -19,20 +10,25 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include <cpuid.h> -#include "../../perf.h" #include "../../util/session.h" #include "../../util/event.h" #include "../../util/evlist.h" #include "../../util/evsel.h" +#include "../../util/evsel_config.h" #include "../../util/cpumap.h" +#include "../../util/mmap.h" #include <subcmd/parse-options.h> #include "../../util/parse-events.h" #include "../../util/pmu.h" #include "../../util/debug.h" #include "../../util/auxtrace.h" +#include "../../util/record.h" +#include "../../util/target.h" #include "../../util/tsc.h" +#include <internal/lib.h> // page_size #include "../../util/intel-pt.h" #define KiB(x) ((x) * 1024) @@ -52,7 +48,7 @@ struct intel_pt_recording { struct auxtrace_record itr; struct perf_pmu *intel_pt_pmu; int have_sched_switch; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; bool snapshot_init_done; size_t snapshot_size; @@ -118,9 +114,9 @@ static u64 intel_pt_masked_bits(u64 mask, u64 bits) } static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, - struct perf_evlist *evlist, u64 *res) + struct evlist *evlist, u64 *res) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 mask; *res = 0; @@ -130,8 +126,8 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, return -EINVAL; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { - *res = intel_pt_masked_bits(mask, evsel->attr.config); + if (evsel->core.attr.type == intel_pt_pmu->type) { + *res = intel_pt_masked_bits(mask, evsel->core.attr.config); return 0; } } @@ -140,7 +136,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, } static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu, - struct perf_evlist *evlist) + struct evlist *evlist) { u64 val; int err, topa_multiple_entries; @@ -276,13 +272,13 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) return attr; } -static const char *intel_pt_find_filter(struct perf_evlist *evlist, +static const char *intel_pt_find_filter(struct evlist *evlist, struct perf_pmu *intel_pt_pmu) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) + if (evsel->core.attr.type == intel_pt_pmu->type) return evsel->filter; } @@ -297,7 +293,7 @@ static size_t intel_pt_filter_bytes(const char *filter) } static size_t -intel_pt_info_priv_size(struct auxtrace_record *itr, struct perf_evlist *evlist) +intel_pt_info_priv_size(struct auxtrace_record *itr, struct evlist *evlist) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); @@ -320,7 +316,7 @@ static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d) static int intel_pt_info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size) { struct intel_pt_recording *ptr = @@ -334,7 +330,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, unsigned long max_non_turbo_ratio; size_t filter_str_len; const char *filter; - u64 *info; + __u64 *info; int err; if (priv_size != ptr->priv_size) @@ -357,10 +353,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu); filter_str_len = filter ? strlen(filter) : 0; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -373,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus); + per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -406,10 +402,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, return 0; } -static int intel_pt_track_switches(struct perf_evlist *evlist) +static int intel_pt_track_switches(struct evlist *evlist) { const char *sched_switch = "sched:sched_switch"; - struct perf_evsel *evsel; + struct evsel *evsel; int err; if (!perf_evlist__can_select_event(evlist, sched_switch)) @@ -422,12 +418,12 @@ static int intel_pt_track_switches(struct perf_evlist *evlist) return err; } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TIME); - evsel->system_wide = true; + evsel->core.system_wide = true; evsel->no_aux_samples = true; evsel->immediate = true; @@ -521,7 +517,7 @@ out_err: } static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, - struct perf_evsel *evsel) + struct evsel *evsel) { int err; char c; @@ -534,39 +530,96 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, * sets pt=0, which avoids senseless kernel errors. */ if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && - !(evsel->attr.config & 1)) { + !(evsel->core.attr.config & 1)) { pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); - evsel->attr.config |= 1; + evsel->core.attr.config |= 1; } err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; err = intel_pt_val_config_term(intel_pt_pmu, "caps/mtc_periods", "mtc_period", "caps/mtc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; return intel_pt_val_config_term(intel_pt_pmu, "caps/psb_periods", "psb_period", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); +} + +static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu, + struct evsel *evsel) +{ + struct perf_evsel_config_term *term; + u64 user_bits = 0, bits; + + term = perf_evsel__get_config_term(evsel, CFG_CHG); + if (term) + user_bits = term->val.cfg_chg; + + bits = perf_pmu__format_bits(&intel_pt_pmu->format, "psb_period"); + + /* Did user change psb_period */ + if (bits & user_bits) + return; + + /* Set psb_period to 0 */ + evsel->core.attr.config &= ~bits; +} + +static void intel_pt_min_max_sample_sz(struct evlist *evlist, + size_t *min_sz, size_t *max_sz) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + size_t sz = evsel->core.attr.aux_sample_size; + + if (!sz) + continue; + if (min_sz && (sz < *min_sz || !*min_sz)) + *min_sz = sz; + if (max_sz && sz > *max_sz) + *max_sz = sz; + } +} + +/* + * Currently, there is not enough information to disambiguate different PEBS + * events, so only allow one. + */ +static bool intel_pt_too_many_aux_output(struct evlist *evlist) +{ + struct evsel *evsel; + int aux_output_cnt = 0; + + evlist__for_each_entry(evlist, evsel) + aux_output_cnt += !!evsel->core.attr.aux_output; + + if (aux_output_cnt > 1) { + pr_err(INTEL_PT_PMU_NAME " supports at most one event with aux-output\n"); + return true; + } + + return false; } static int intel_pt_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct 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, need_immediate = false; - struct perf_evsel *evsel, *intel_pt_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; - bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + struct evsel *evsel, *intel_pt_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; + bool privileged = perf_event_paranoid_check(-1); u64 tsc_bit; int err; @@ -574,13 +627,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { + if (evsel->core.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; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_pt_evsel = evsel; opts->full_auxtrace = true; } @@ -591,14 +644,25 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, return -EINVAL; } + if (opts->auxtrace_snapshot_mode && opts->auxtrace_sample_mode) { + pr_err("Snapshot mode (" INTEL_PT_PMU_NAME " PMU) and sample trace cannot be used together\n"); + return -EINVAL; + } + if (opts->use_clockid) { pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n"); return -EINVAL; } + if (intel_pt_too_many_aux_output(evlist)) + return -EINVAL; + if (!opts->full_auxtrace) return 0; + if (opts->auxtrace_sample_mode) + intel_pt_config_sample_mode(intel_pt_pmu, intel_pt_evsel); + err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel); if (err) return err; @@ -648,6 +712,34 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, opts->auxtrace_snapshot_size, psb_period); } + /* Set default sizes for sample mode */ + if (opts->auxtrace_sample_mode) { + size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist); + size_t min_sz = 0, max_sz = 0; + + intel_pt_min_max_sample_sz(evlist, &min_sz, &max_sz); + if (!opts->auxtrace_mmap_pages && !privileged && + opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + if (!opts->auxtrace_mmap_pages) { + size_t sz = round_up(max_sz, page_size) / page_size; + + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } + if (max_sz > opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Sample size %zu must not be greater than AUX area tracing mmap size %zu\n", + max_sz, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + pr_debug2("Intel PT min. sample size: %zu max. sample size: %zu\n", + min_sz, max_sz); + if (psb_period && + min_sz <= psb_period + INTEL_PT_PSB_PERIOD_NEAR) + ui__warning("Intel PT sample size (%zu) may be too small for PSB period (%zu)\n", + min_sz, psb_period); + } + /* Set default sizes for full trace mode */ if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { if (privileged) { @@ -664,7 +756,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; size_t min_sz; - if (opts->auxtrace_snapshot_mode) + if (opts->auxtrace_snapshot_mode || opts->auxtrace_sample_mode) min_sz = KiB(4); else min_sz = KiB(8); @@ -678,7 +770,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); - if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit)) + if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit)) have_timing_info = true; else have_timing_info = false; @@ -687,25 +779,25 @@ 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 && !cpu_map__empty(cpus)) { + if (have_timing_info && !perf_cpu_map__empty(cpus)) { 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()) { - struct perf_evsel *switch_evsel; + struct evsel *switch_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - switch_evsel = perf_evlist__last(evlist); + switch_evsel = evlist__last(evlist); - switch_evsel->attr.freq = 0; - switch_evsel->attr.sample_period = 1; - switch_evsel->attr.context_switch = 1; + switch_evsel->core.attr.freq = 0; + switch_evsel->core.attr.sample_period = 1; + switch_evsel->core.attr.context_switch = 1; - switch_evsel->system_wide = true; + switch_evsel->core.system_wide = true; switch_evsel->no_aux_samples = true; switch_evsel->immediate = true; @@ -745,31 +837,31 @@ 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 (!cpu_map__empty(cpus)) + if (!perf_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; + struct evsel *tracking_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; tracking_evsel->no_aux_samples = true; if (need_immediate) tracking_evsel->immediate = true; /* In per-cpu case, always need the time of mmap events etc */ - if (!cpu_map__empty(cpus)) { + if (!perf_cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); /* And the CPU for switch events */ perf_evsel__set_sample_bit(tracking_evsel, CPU); @@ -781,7 +873,7 @@ 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 && !cpu_map__empty(cpus) && + if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) && !target__none(&opts->target)) ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); @@ -792,11 +884,11 @@ 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; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -805,11 +897,11 @@ 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; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -1078,10 +1170,10 @@ 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; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) return perf_evlist__enable_event_idx(ptr->evlist, evsel, idx); } @@ -1118,5 +1210,10 @@ struct auxtrace_record *intel_pt_recording_init(int *err) ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options; ptr->itr.reference = intel_pt_reference; ptr->itr.read_finish = intel_pt_read_finish; + /* + * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K + * should give at least 1 PSB per sample. + */ + ptr->itr.default_aux_sample_size = 4096; return &ptr->itr; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index 865a9762f22e..c0775c39227f 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> -#include "../../util/kvm-stat.h" -#include "../../util/evsel.h" +#include <string.h> +#include "../../../util/kvm-stat.h" +#include "../../../util/evsel.h" #include <asm/svm.h> #include <asm/vmx.h> #include <asm/kvm.h> @@ -27,7 +28,7 @@ const char *kvm_exit_trace = "kvm:kvm_exit"; * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). */ -static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, +static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { key->key = perf_evsel__intval(evsel, sample, "gpa"); @@ -38,7 +39,7 @@ static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sam #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 -static bool mmio_event_begin(struct perf_evsel *evsel, +static bool mmio_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO read begin event in kernel. */ @@ -55,7 +56,7 @@ static bool mmio_event_begin(struct perf_evsel *evsel, return false; } -static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, +static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO write end event in kernel. */ @@ -89,7 +90,7 @@ static struct kvm_events_ops mmio_events = { }; /* The time of emulation pio access is from kvm_pio to kvm_entry. */ -static void ioport_event_get_key(struct perf_evsel *evsel, +static void ioport_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -97,7 +98,7 @@ static void ioport_event_get_key(struct perf_evsel *evsel, key->info = perf_evsel__intval(evsel, sample, "rw"); } -static bool ioport_event_begin(struct perf_evsel *evsel, +static bool ioport_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -109,7 +110,7 @@ static bool ioport_event_begin(struct perf_evsel *evsel, return false; } -static bool ioport_event_end(struct perf_evsel *evsel, +static bool ioport_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index 4520ac53caa9..e17e080e76f4 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/string.h> +#include <limits.h> #include <stdlib.h> +#include <internal/lib.h> // page_size #include "../../util/machine.h" #include "../../util/map.h" #include "../../util/symbol.h" -#include "../../util/sane_ctype.h" +#include <linux/ctype.h> #include <symbol/kallsyms.h> diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index fead6b3b4206..c218b83e063b 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -2,11 +2,13 @@ #include <errno.h> #include <string.h> #include <regex.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> -#include "../../perf.h" -#include "../../util/util.h" +#include "../../perf-sys.h" #include "../../util/perf_regs.h" #include "../../util/debug.h" +#include "../../util/event.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -31,6 +33,22 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(R14, PERF_REG_X86_R14), SMPL_REG(R15, PERF_REG_X86_R15), #endif + SMPL_REG2(XMM0, PERF_REG_X86_XMM0), + SMPL_REG2(XMM1, PERF_REG_X86_XMM1), + SMPL_REG2(XMM2, PERF_REG_X86_XMM2), + SMPL_REG2(XMM3, PERF_REG_X86_XMM3), + SMPL_REG2(XMM4, PERF_REG_X86_XMM4), + SMPL_REG2(XMM5, PERF_REG_X86_XMM5), + SMPL_REG2(XMM6, PERF_REG_X86_XMM6), + SMPL_REG2(XMM7, PERF_REG_X86_XMM7), + SMPL_REG2(XMM8, PERF_REG_X86_XMM8), + SMPL_REG2(XMM9, PERF_REG_X86_XMM9), + SMPL_REG2(XMM10, PERF_REG_X86_XMM10), + SMPL_REG2(XMM11, PERF_REG_X86_XMM11), + SMPL_REG2(XMM12, PERF_REG_X86_XMM12), + SMPL_REG2(XMM13, PERF_REG_X86_XMM13), + SMPL_REG2(XMM14, PERF_REG_X86_XMM14), + SMPL_REG2(XMM15, PERF_REG_X86_XMM15), SMPL_REG_END }; @@ -254,3 +272,31 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) return SDT_ARG_VALID; } + +uint64_t arch__intr_reg_mask(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .sample_regs_intr = PERF_REG_EXTENDED_MASK, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + int fd; + /* + * In an unnamed union, init it here to build on older gcc versions + */ + attr.sample_period = 1; + + event_attr_init(&attr); + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd != -1) { + close(fd); + return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK); + } + + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 950539f9a4f7..2f55afb14e1f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -5,10 +5,12 @@ #include <linux/stddef.h> #include <linux/perf_event.h> -#include "../../perf.h" #include <linux/types.h> -#include "../../util/debug.h" -#include "../../util/tsc.h" +#include <asm/barrier.h> +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/synthetic-events.h" +#include "../../../util/tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) @@ -57,7 +59,7 @@ int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, .time_conv = { .header = { .type = PERF_RECORD_TIME_CONV, - .size = sizeof(struct time_conv_event), + .size = sizeof(struct perf_record_time_conv), }, }, }; diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 05920e3edf7a..47357973b55b 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include "../../util/debug.h" #ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" -#include "../../util/debug.h" #endif #ifdef HAVE_ARCH_X86_64_SUPPORT |
