diff options
Diffstat (limited to 'tools/perf')
59 files changed, 1499 insertions, 238 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index a653311d9693..fd7a6ff9e7aa 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -4,6 +4,7 @@ PERF-GUI-VARS PERF-VERSION-FILE FEATURE-DUMP perf +!include/perf/ perf-read-vdso32 perf-read-vdsox32 perf-help diff --git a/tools/perf/Documentation/perf-arm-coresight.txt b/tools/perf/Documentation/arm-coresight.txt index c117fc50a2a9..c117fc50a2a9 100644 --- a/tools/perf/Documentation/perf-arm-coresight.txt +++ b/tools/perf/Documentation/arm-coresight.txt diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 6fd4b1384b97..898226ea8cad 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -588,6 +588,10 @@ ifndef NO_LIBELF ifeq ($(feature-libbpf-bpf_object__next_map), 1) CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP endif + $(call feature_check,libbpf-bpf_program__set_insns) + ifeq ($(feature-libbpf-bpf_program__set_insns), 1) + CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS + endif $(call feature_check,libbpf-btf__raw_data) ifeq ($(feature-libbpf-btf__raw_data), 1) CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA @@ -604,6 +608,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP + CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE endif diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 5fc6a2a3dbc5..deeb163999ce 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -4,9 +4,11 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <dirent.h> #include <stdbool.h> #include <linux/coresight-pmu.h> #include <linux/zalloc.h> +#include <api/fs/fs.h> #include "../../../util/auxtrace.h" #include "../../../util/debug.h" @@ -14,6 +16,7 @@ #include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" +#include "hisi-ptt.h" static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) { @@ -50,42 +53,114 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) return arm_spe_pmus; } +static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err) +{ + const char *sysfs = sysfs__mountpoint(); + struct perf_pmu **hisi_ptt_pmus = NULL; + struct dirent *dent; + char path[PATH_MAX]; + DIR *dir = NULL; + int idx = 0; + + snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + dir = opendir(path); + if (!dir) { + pr_err("can't read directory '%s'\n", EVENT_SOURCE_DEVICE_PATH); + *err = -EINVAL; + return NULL; + } + + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME)) + (*nr_ptts)++; + } + + if (!(*nr_ptts)) + goto out; + + hisi_ptt_pmus = zalloc(sizeof(struct perf_pmu *) * (*nr_ptts)); + if (!hisi_ptt_pmus) { + pr_err("hisi_ptt alloc failed\n"); + *err = -ENOMEM; + goto out; + } + + rewinddir(dir); + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) { + hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name); + if (hisi_ptt_pmus[idx]) + idx++; + } + } + +out: + closedir(dir); + return hisi_ptt_pmus; +} + +static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus, + int pmu_nr, struct evsel *evsel) +{ + int i; + + if (!pmus) + return NULL; + + for (i = 0; i < pmu_nr; i++) { + if (evsel->core.attr.type == pmus[i]->type) + return pmus[i]; + } + + return NULL; +} + struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { - struct perf_pmu *cs_etm_pmu; + struct perf_pmu *cs_etm_pmu = NULL; + struct perf_pmu **arm_spe_pmus = NULL; + struct perf_pmu **hisi_ptt_pmus = NULL; struct evsel *evsel; - bool found_etm = false; + struct perf_pmu *found_etm = NULL; struct perf_pmu *found_spe = NULL; - struct perf_pmu **arm_spe_pmus = NULL; + struct perf_pmu *found_ptt = NULL; + int auxtrace_event_cnt = 0; int nr_spes = 0; - int i = 0; + int nr_ptts = 0; if (!evlist) return NULL; cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); + hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err); evlist__for_each_entry(evlist, evsel) { - if (cs_etm_pmu && - evsel->core.attr.type == cs_etm_pmu->type) - found_etm = true; - - if (!nr_spes || found_spe) - continue; - - for (i = 0; i < nr_spes; i++) { - if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = arm_spe_pmus[i]; - break; - } - } + if (cs_etm_pmu && !found_etm) + found_etm = find_pmu_for_event(&cs_etm_pmu, 1, evsel); + + if (arm_spe_pmus && !found_spe) + found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel); + + if (hisi_ptt_pmus && !found_ptt) + found_ptt = find_pmu_for_event(hisi_ptt_pmus, nr_ptts, evsel); } + free(arm_spe_pmus); + free(hisi_ptt_pmus); + + if (found_etm) + auxtrace_event_cnt++; - if (found_etm && found_spe) { - pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n"); + if (found_spe) + auxtrace_event_cnt++; + + if (found_ptt) + auxtrace_event_cnt++; + + if (auxtrace_event_cnt > 1) { + pr_err("Concurrent AUX trace operation not currently supported\n"); *err = -EOPNOTSUPP; return NULL; } @@ -96,6 +171,9 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) return arm_spe_recording_init(err, found_spe); + + if (found_ptt) + return hisi_ptt_recording_init(err, found_ptt); #endif /* diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index b8b23b9dc598..887c8addc491 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,6 +10,7 @@ #include <linux/string.h> #include "arm-spe.h" +#include "hisi-ptt.h" #include "../../../util/pmu.h" struct perf_event_attr @@ -22,6 +23,8 @@ struct perf_event_attr #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { return arm_spe_pmu_default_config(pmu); + } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { + pmu->selectable = true; #endif } diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 037e292ecd8e..4af0c3a0f86e 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -102,7 +102,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) if (err) goto out_free_arm; /* b, b.cond, br, cbz/cbnz, tbz/tbnz */ - err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$", + err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|hs|le|lo|ls|lt|mi|ne|pl|vc|vs)?n?z?$", REG_EXTENDED); if (err) goto out_free_call; diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index 9fcb4e68add9..337aa9bdf905 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -11,4 +11,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ ../../arm/util/cs-etm.o \ - arm-spe.o mem-events.o + arm-spe.o mem-events.o hisi-ptt.o diff --git a/tools/perf/arch/arm64/util/hisi-ptt.c b/tools/perf/arch/arm64/util/hisi-ptt.c new file mode 100644 index 000000000000..ba97c8a562a0 --- /dev/null +++ b/tools/perf/arch/arm64/util/hisi-ptt.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/log2.h> +#include <linux/zalloc.h> +#include <time.h> + +#include <internal/lib.h> // page_size +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/hisi-ptt.h" +#include "../../../util/pmu.h" +#include "../../../util/record.h" +#include "../../../util/session.h" +#include "../../../util/tsc.h" + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) + +struct hisi_ptt_recording { + struct auxtrace_record itr; + struct perf_pmu *hisi_ptt_pmu; + struct evlist *evlist; +}; + +static size_t +hisi_ptt_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + return HISI_PTT_AUXTRACE_PRIV_SIZE; +} + +static int hisi_ptt_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct perf_record_auxtrace_info *auxtrace_info, + size_t priv_size) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu; + + if (priv_size != HISI_PTT_AUXTRACE_PRIV_SIZE) + return -EINVAL; + + if (!session->evlist->core.nr_mmaps) + return -EINVAL; + + auxtrace_info->type = PERF_AUXTRACE_HISI_PTT; + auxtrace_info->priv[0] = hisi_ptt_pmu->type; + + return 0; +} + +static int hisi_ptt_set_auxtrace_mmap_page(struct record_opts *opts) +{ + bool privileged = perf_event_paranoid_check(-1); + + if (!opts->full_auxtrace) + return 0; + + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(16) / 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 = KiB(8); + + if (sz < min_sz || !is_power_of_2(sz)) { + pr_err("Invalid mmap size for HISI PTT: must be at least %zuKiB and a power of 2\n", + min_sz / 1024); + return -EINVAL; + } + } + + return 0; +} + +static int hisi_ptt_recording_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu; + struct evsel *evsel, *hisi_ptt_evsel = NULL; + struct evsel *tracking_evsel; + int err; + + pttr->evlist = evlist; + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type == hisi_ptt_pmu->type) { + if (hisi_ptt_evsel) { + pr_err("There may be only one " HISI_PTT_PMU_NAME "x event\n"); + return -EINVAL; + } + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; + evsel->needs_auxtrace_mmap = true; + hisi_ptt_evsel = evsel; + opts->full_auxtrace = true; + } + } + + err = hisi_ptt_set_auxtrace_mmap_page(opts); + if (err) + return err; + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace event + * must come first. + */ + evlist__to_front(evlist, hisi_ptt_evsel); + evsel__set_sample_bit(hisi_ptt_evsel, TIME); + + /* Add dummy event to keep tracking */ + err = parse_event(evlist, "dummy:u"); + if (err) + return err; + + tracking_evsel = evlist__last(evlist); + evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; + evsel__set_sample_bit(tracking_evsel, TIME); + + return 0; +} + +static u64 hisi_ptt_reference(struct auxtrace_record *itr __maybe_unused) +{ + return rdtsc(); +} + +static void hisi_ptt_recording_free(struct auxtrace_record *itr) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + + free(pttr); +} + +struct auxtrace_record *hisi_ptt_recording_init(int *err, + struct perf_pmu *hisi_ptt_pmu) +{ + struct hisi_ptt_recording *pttr; + + if (!hisi_ptt_pmu) { + *err = -ENODEV; + return NULL; + } + + pttr = zalloc(sizeof(*pttr)); + if (!pttr) { + *err = -ENOMEM; + return NULL; + } + + pttr->hisi_ptt_pmu = hisi_ptt_pmu; + pttr->itr.pmu = hisi_ptt_pmu; + pttr->itr.recording_options = hisi_ptt_recording_options; + pttr->itr.info_priv_size = hisi_ptt_info_priv_size; + pttr->itr.info_fill = hisi_ptt_info_fill; + pttr->itr.free = hisi_ptt_recording_free; + pttr->itr.reference = hisi_ptt_reference; + pttr->itr.read_finish = auxtrace_record__read_finish; + pttr->itr.alignment = 0; + + *err = 0; + return &pttr->itr; +} diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2bca64f96164..e9e0df4f9a61 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_ppc_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_ppc_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 793b35f2221a..af102f471e9f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -866,7 +866,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * User space tasks can migrate between CPUs, so when tracing * selected CPUs, sideband for all CPUs is still needed. */ - need_system_wide_tracking = evlist->core.has_user_cpus && + need_system_wide_tracking = opts->target.cpu_list && !intel_pt_evsel->core.attr.exclude_user; tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking); diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 744dd3520584..58e1ec1654ef 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -60,7 +60,7 @@ int cmd_list(int argc, const char **argv) setup_pager(); if (!raw_dump && pager_in_use()) - printf("\nList of pre-defined events (to be used in -e):\n\n"); + printf("\nList of pre-defined events (to be used in -e or -M):\n\n"); if (hybrid_type) { pmu_name = perf_pmu__hybrid_type_to_pmu(hybrid_type); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index f7dd8216de72..923fb8316fda 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -97,6 +97,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) else rec_argc = argc + 9 * perf_pmu__hybrid_pmu_num(); + if (mem->cpu_list) + rec_argc += 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; @@ -159,6 +162,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (all_kernel) rec_argv[i++] = "--all-kernel"; + if (mem->cpu_list) { + rec_argv[i++] = "-C"; + rec_argv[i++] = mem->cpu_list; + } + for (j = 0; j < argc; j++, i++) rec_argv[i] = argv[j]; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 52d254b1530c..e128b855ddde 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -649,7 +649,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size) static volatile int signr = -1; static volatile int child_finished; #ifdef HAVE_EVENTFD_SUPPORT -static int done_fd = -1; +static volatile int done_fd = -1; #endif static void sig_handler(int sig) @@ -661,19 +661,24 @@ static void sig_handler(int sig) done = 1; #ifdef HAVE_EVENTFD_SUPPORT -{ - u64 tmp = 1; - /* - * It is possible for this signal handler to run after done is checked - * in the main loop, but before the perf counter fds are polled. If this - * happens, the poll() will continue to wait even though done is set, - * and will only break out if either another signal is received, or the - * counters are ready for read. To ensure the poll() doesn't sleep when - * done is set, use an eventfd (done_fd) to wake up the poll(). - */ - if (write(done_fd, &tmp, sizeof(tmp)) < 0) - pr_err("failed to signal wakeup fd, error: %m\n"); -} + if (done_fd >= 0) { + u64 tmp = 1; + int orig_errno = errno; + + /* + * It is possible for this signal handler to run after done is + * checked in the main loop, but before the perf counter fds are + * polled. If this happens, the poll() will continue to wait + * even though done is set, and will only break out if either + * another signal is received, or the counters are ready for + * read. To ensure the poll() doesn't sleep when done is set, + * use an eventfd (done_fd) to wake up the poll(). + */ + if (write(done_fd, &tmp, sizeof(tmp)) < 0) + pr_err("failed to signal wakeup fd, error: %m\n"); + + errno = orig_errno; + } #endif // HAVE_EVENTFD_SUPPORT } @@ -2834,8 +2839,12 @@ out_free_threads: out_delete_session: #ifdef HAVE_EVENTFD_SUPPORT - if (done_fd >= 0) - close(done_fd); + if (done_fd >= 0) { + fd = done_fd; + done_fd = -1; + + close(fd); + } #endif zstd_fini(&session->zstd_data); perf_session__delete(session); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 6ee44b18c6b5..eacca9a874e2 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -143,7 +143,7 @@ for i in $SYNC_CHECK_FILES; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"' +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check arch/x86/include/asm/amd-ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"' check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json index 6970203cb247..6443a061e22a 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json @@ -112,21 +112,21 @@ "MetricName": "indirect_branch" }, { - "MetricExpr": "(armv8_pmuv3_0@event\\=0x1014@ + armv8_pmuv3_0@event\\=0x1018@) / BR_MIS_PRED", + "MetricExpr": "(armv8_pmuv3_0@event\\=0x1013@ + armv8_pmuv3_0@event\\=0x1016@) / BR_MIS_PRED", "PublicDescription": "Push branch L3 topdown metric", "BriefDescription": "Push branch L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "push_branch" }, { - "MetricExpr": "armv8_pmuv3_0@event\\=0x100c@ / BR_MIS_PRED", + "MetricExpr": "armv8_pmuv3_0@event\\=0x100d@ / BR_MIS_PRED", "PublicDescription": "Pop branch L3 topdown metric", "BriefDescription": "Pop branch L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "pop_branch" }, { - "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1014@ - armv8_pmuv3_0@event\\=0x1018@ - armv8_pmuv3_0@event\\=0x100c@) / BR_MIS_PRED", + "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1013@ - armv8_pmuv3_0@event\\=0x1016@ - armv8_pmuv3_0@event\\=0x100d@) / BR_MIS_PRED", "PublicDescription": "Other branch L3 topdown metric", "BriefDescription": "Other branch L3 topdown metric", "MetricGroup": "TopDownL3", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json index 8ba3e81c9808..fe050d44374b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json @@ -1,13 +1,13 @@ [ { "MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P01", - "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P23", - "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, @@ -61,13 +61,13 @@ }, { "MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P01", - "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P23", - "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, @@ -151,193 +151,193 @@ }, { "MetricName": "XLINK0_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK1_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK2_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK3_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK4_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK5_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK6_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK7_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK0_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK1_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK2_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK3_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK4_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK5_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK6_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK7_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK0_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK1_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK2_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK3_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK4_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK5_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK6_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK7_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK0_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK1_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK2_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK3_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK4_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK5_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK6_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK7_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json index cf8563d059b9..cf8563d059b9 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 8c10955eff93..3ef07a12aa14 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -9,7 +9,7 @@ size=128 config=0 sample_period=* sample_type=263 -read_format=0|4 +read_format=0|4|20 disabled=1 inherit=1 pinned=0 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index 86a15dd359d9..8fec06eda5f9 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -11,7 +11,7 @@ size=128 config=9 sample_period=4000 sample_type=455 -read_format=4 +read_format=4|20 # Event will be enabled right away. disabled=0 inherit=1 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index 14ee60fd3f41..6c1cff8aae8b 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -7,14 +7,14 @@ ret = 1 fd=1 group_fd=-1 sample_type=327 -read_format=4 +read_format=4|20 [event-2:base-record] fd=2 group_fd=1 config=1 sample_type=327 -read_format=4 +read_format=4|20 mmap=0 comm=0 task=0 diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 300b9f7e6d69..97e7e64a38f0 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -7,7 +7,7 @@ ret = 1 fd=1 group_fd=-1 sample_type=343 -read_format=12 +read_format=12|28 inherit=0 [event-2:base-record] @@ -21,8 +21,8 @@ config=3 # default | PERF_SAMPLE_READ sample_type=343 -# PERF_FORMAT_ID | PERF_FORMAT_GROUP -read_format=12 +# PERF_FORMAT_ID | PERF_FORMAT_GROUP | PERF_FORMAT_LOST +read_format=12|28 task=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index 3ffe246e0228..eeb1db392bc9 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -7,7 +7,7 @@ ret = 1 fd=1 group_fd=-1 sample_type=327 -read_format=4 +read_format=4|20 [event-2:base-record] fd=2 @@ -15,7 +15,7 @@ group_fd=1 type=0 config=1 sample_type=327 -read_format=4 +read_format=4|20 mmap=0 comm=0 task=0 diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2 index 6b9f8d182ce1..cebdaa8e64e4 100644 --- a/tools/perf/tests/attr/test-record-group2 +++ b/tools/perf/tests/attr/test-record-group2 @@ -9,7 +9,7 @@ group_fd=-1 config=0|1 sample_period=1234000 sample_type=87 -read_format=12 +read_format=12|28 inherit=0 freq=0 @@ -19,7 +19,7 @@ group_fd=1 config=0|1 sample_period=6789000 sample_type=87 -read_format=12 +read_format=12|28 disabled=0 inherit=0 mmap=0 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 6512f5e22045..c598f95aebf3 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -130,12 +130,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO", ctx) == 0); TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", - (void **)&val_ptr)); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", - (void **)&val_ptr)); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", - (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", &val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", &val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", &val_ptr)); expr__ctx_clear(ctx); ctx->sctx.runtime = 3; @@ -143,20 +140,16 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", NULL, ctx) == 0); TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", - (void **)&val_ptr)); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", - (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", &val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", &val_ptr)); expr__ctx_clear(ctx); TEST_ASSERT_VAL("find ids", expr__find_ids("dash\\-event1 - dash\\-event2", NULL, ctx) == 0); TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", - (void **)&val_ptr)); - TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", - (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", &val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", &val_ptr)); /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ { @@ -174,7 +167,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1); TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, smton ? "EVENT1" : "EVENT2", - (void **)&val_ptr)); + &val_ptr)); expr__ctx_clear(ctx); TEST_ASSERT_VAL("find ids", @@ -183,7 +176,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1); TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, corewide ? "EVENT1" : "EVENT2", - (void **)&val_ptr)); + &val_ptr)); } /* The expression is a constant 1.0 without needing to evaluate EVENT1. */ @@ -220,8 +213,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u expr__find_ids("source_count(EVENT1)", NULL, ctx) == 0); TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1); - TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", - (void **)&val_ptr)); + TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr)); expr__ctx_free(ctx); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 097e05c796ab..3c2ee55e75c7 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -986,10 +986,10 @@ static int metric_parse_fake(const char *str) */ i = 1; hashmap__for_each_entry(ctx->ids, cur, bkt) - expr__add_id_val(ctx, strdup(cur->key), i++); + expr__add_id_val(ctx, strdup(cur->pkey), i++); hashmap__for_each_entry(ctx->ids, cur, bkt) { - if (check_parse_fake(cur->key)) { + if (check_parse_fake(cur->pkey)) { pr_err("check_parse_fake failed\n"); goto out; } @@ -1003,7 +1003,7 @@ static int metric_parse_fake(const char *str) */ i = 1024; hashmap__for_each_entry(ctx->ids, cur, bkt) - expr__add_id_val(ctx, strdup(cur->key), i--); + expr__add_id_val(ctx, strdup(cur->pkey), i--); if (expr__parse(&result, ctx, str)) { pr_err("expr__parse failed\n"); ret = -1; diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index eb5196f58190..b7f050aa6210 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -6,6 +6,8 @@ set -e +skip_test=0 + function commachecker() { local -i cnt=0 @@ -156,14 +158,47 @@ check_per_socket() echo "[Success]" } +# The perf stat options for per-socket, per-core, per-die +# and -A ( no_aggr mode ) uses the info fetched from this +# directory: "/sys/devices/system/cpu/cpu*/topology". For +# example, socket value is fetched from "physical_package_id" +# file in topology directory. +# Reference: cpu__get_topology_int in util/cpumap.c +# If the platform doesn't expose topology information, values +# will be set to -1. For example, incase of pSeries platform +# of powerpc, value for "physical_package_id" is restricted +# and set to -1. Check here validates the socket-id read from +# topology file before proceeding further + +FILE_LOC="/sys/devices/system/cpu/cpu*/topology/" +FILE_NAME="physical_package_id" + +check_for_topology() +{ + if ! ParanoidAndNotRoot 0 + then + socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1` + [ -z $socket_file ] && return 0 + socket_id=`cat $socket_file` + [ $socket_id == -1 ] && skip_test=1 + return 0 + fi +} + +check_for_topology check_no_args check_system_wide -check_system_wide_no_aggr check_interval check_event -check_per_core check_per_thread -check_per_die check_per_node -check_per_socket +if [ $skip_test -ne 1 ] +then + check_system_wide_no_aggr + check_per_core + check_per_die + check_per_socket +else + echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" +fi exit 0 diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index ea8714a36051..2c4212c641ed 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -6,6 +6,8 @@ set -e +skip_test=0 + pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py if [ "x$PYTHON" == "x" ] then @@ -134,14 +136,47 @@ check_per_socket() echo "[Success]" } +# The perf stat options for per-socket, per-core, per-die +# and -A ( no_aggr mode ) uses the info fetched from this +# directory: "/sys/devices/system/cpu/cpu*/topology". For +# example, socket value is fetched from "physical_package_id" +# file in topology directory. +# Reference: cpu__get_topology_int in util/cpumap.c +# If the platform doesn't expose topology information, values +# will be set to -1. For example, incase of pSeries platform +# of powerpc, value for "physical_package_id" is restricted +# and set to -1. Check here validates the socket-id read from +# topology file before proceeding further + +FILE_LOC="/sys/devices/system/cpu/cpu*/topology/" +FILE_NAME="physical_package_id" + +check_for_topology() +{ + if ! ParanoidAndNotRoot 0 + then + socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1` + [ -z $socket_file ] && return 0 + socket_id=`cat $socket_file` + [ $socket_id == -1 ] && skip_test=1 + return 0 + fi +} + +check_for_topology check_no_args check_system_wide -check_system_wide_no_aggr check_interval check_event -check_per_core check_per_thread -check_per_die check_per_node -check_per_socket +if [ $skip_test -ne 1 ] +then + check_system_wide_no_aggr + check_per_core + check_per_die + check_per_socket +else + echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" +fi exit 0 diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index e4cb4f1806ff..daad786cf48d 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -70,7 +70,7 @@ perf_report_instruction_samples() { # 68.12% touch libc-2.27.so [.] _dl_addr # 5.80% touch libc-2.27.so [.] getenv # 4.35% touch ld-2.27.so [.] _dl_fixup - perf report --itrace=i1000i --stdio -i ${perfdata} 2>&1 | \ + perf report --itrace=i20i --stdio -i ${perfdata} 2>&1 | \ egrep " +[0-9]+\.[0-9]+% +$1" > /dev/null 2>&1 } diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index ec801cffae6b..d7ff5c4b4da4 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -13,7 +13,10 @@ fi # skip the test if the hardware doesn't support branch stack sampling # and if the architecture doesn't support filter types: any,save_type,u -perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2 +if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then + echo "skip: system doesn't support filter types: any,save_type,u" + exit 2 +fi TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index efaad9566c34..f5ed7b1af419 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -22,6 +22,8 @@ outfile="${temp_dir}/test-out.txt" errfile="${temp_dir}/test-err.txt" workload="${temp_dir}/workload" awkscript="${temp_dir}/awkscript" +jitdump_workload="${temp_dir}/jitdump_workload" +maxbrstack="${temp_dir}/maxbrstack.py" cleanup() { @@ -42,6 +44,21 @@ trap_cleanup() trap trap_cleanup EXIT TERM INT +# perf record for testing without decoding +perf_record_no_decode() +{ + # Options to speed up recording: no post-processing, no build-id cache update, + # and no BPF events. + perf record -B -N --no-bpf-event "$@" +} + +# perf record for testing should not need BPF events +perf_record_no_bpf() +{ + # Options for no BPF events + perf record --no-bpf-event "$@" +} + have_workload=false cat << _end_of_file_ | /usr/bin/cc -o "${workload}" -xc - -pthread && have_workload=true #include <time.h> @@ -76,7 +93,7 @@ _end_of_file_ can_cpu_wide() { echo "Checking for CPU-wide recording on CPU $1" - if ! perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:u -C "$1" true >/dev/null 2>&1 ; then + if ! perf_record_no_decode -o "${tmpfile}" -e dummy:u -C "$1" true >/dev/null 2>&1 ; then echo "No so skipping" return 2 fi @@ -93,7 +110,7 @@ test_system_wide_side_band() can_cpu_wide 1 || return $? # Record on CPU 0 a task running on CPU 1 - perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname # Should get MMAP events from CPU 1 because they can be needed to decode mmap_cnt=$(perf script -i "${perfdatafile}" --no-itrace --show-mmap-events -C 1 2>/dev/null | grep -c MMAP) @@ -109,7 +126,14 @@ test_system_wide_side_band() can_kernel() { - perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:k true >/dev/null 2>&1 || return 2 + if [ -z "${can_kernel_trace}" ] ; then + can_kernel_trace=0 + perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 && can_kernel_trace=1 + fi + if [ ${can_kernel_trace} -eq 0 ] ; then + echo "SKIP: no kernel tracing" + return 2 + fi return 0 } @@ -235,7 +259,7 @@ test_per_thread() wait_for_threads ${w1} 2 wait_for_threads ${w2} 2 - perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" & + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" & ppid=$! echo "perf PID is $ppid" wait_for_perf_to_start ${ppid} "${errfile}" || return 1 @@ -254,6 +278,348 @@ test_per_thread() return 0 } +test_jitdump() +{ + echo "--- Test tracing self-modifying code that uses jitdump ---" + + script_path=$(realpath "$0") + script_dir=$(dirname "$script_path") + jitdump_incl_dir="${script_dir}/../../util" + jitdump_h="${jitdump_incl_dir}/jitdump.h" + + if [ ! -e "${jitdump_h}" ] ; then + echo "SKIP: Include file jitdump.h not found" + return 2 + fi + + if [ -z "${have_jitdump_workload}" ] ; then + have_jitdump_workload=false + # Create a workload that uses self-modifying code and generates its own jitdump file + cat <<- "_end_of_file_" | /usr/bin/cc -o "${jitdump_workload}" -I "${jitdump_incl_dir}" -xc - -pthread && have_jitdump_workload=true + #define _GNU_SOURCE + #include <sys/mman.h> + #include <sys/types.h> + #include <stddef.h> + #include <stdio.h> + #include <stdint.h> + #include <unistd.h> + #include <string.h> + + #include "jitdump.h" + + #define CHK_BYTE 0x5a + + static inline uint64_t rdtsc(void) + { + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((uint64_t)high) << 32; + } + + static FILE *open_jitdump(void) + { + struct jitheader header = { + .magic = JITHEADER_MAGIC, + .version = JITHEADER_VERSION, + .total_size = sizeof(header), + .pid = getpid(), + .timestamp = rdtsc(), + .flags = JITDUMP_FLAGS_ARCH_TIMESTAMP, + }; + char filename[256]; + FILE *f; + void *m; + + snprintf(filename, sizeof(filename), "jit-%d.dump", getpid()); + f = fopen(filename, "w+"); + if (!f) + goto err; + /* Create an MMAP event for the jitdump file. That is how perf tool finds it. */ + m = mmap(0, 4096, PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(f), 0); + if (m == MAP_FAILED) + goto err_close; + munmap(m, 4096); + if (fwrite(&header,sizeof(header),1,f) != 1) + goto err_close; + return f; + + err_close: + fclose(f); + err: + return NULL; + } + + static int write_jitdump(FILE *f, void *addr, const uint8_t *dat, size_t sz, uint64_t *idx) + { + struct jr_code_load rec = { + .p.id = JIT_CODE_LOAD, + .p.total_size = sizeof(rec) + sz, + .p.timestamp = rdtsc(), + .pid = getpid(), + .tid = gettid(), + .vma = (unsigned long)addr, + .code_addr = (unsigned long)addr, + .code_size = sz, + .code_index = ++*idx, + }; + + if (fwrite(&rec,sizeof(rec),1,f) != 1 || + fwrite(dat, sz, 1, f) != 1) + return -1; + return 0; + } + + static void close_jitdump(FILE *f) + { + fclose(f); + } + + int main() + { + /* Get a memory page to store executable code */ + void *addr = mmap(0, 4096, PROT_WRITE | PROT_EXEC, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + /* Code to execute: mov CHK_BYTE, %eax ; ret */ + uint8_t dat[] = {0xb8, CHK_BYTE, 0x00, 0x00, 0x00, 0xc3}; + FILE *f = open_jitdump(); + uint64_t idx = 0; + int ret = 1; + + if (!f) + return 1; + /* Copy executable code to executable memory page */ + memcpy(addr, dat, sizeof(dat)); + /* Record it in the jitdump file */ + if (write_jitdump(f, addr, dat, sizeof(dat), &idx)) + goto out_close; + /* Call it */ + ret = ((int (*)(void))addr)() - CHK_BYTE; + out_close: + close_jitdump(f); + return ret; + } + _end_of_file_ + fi + + if ! $have_jitdump_workload ; then + echo "SKIP: No jitdump workload" + return 2 + fi + + # Change to temp_dir so jitdump collateral files go there + cd "${temp_dir}" + perf_record_no_bpf -o "${tmpfile}" -e intel_pt//u "${jitdump_workload}" + perf inject -i "${tmpfile}" -o "${perfdatafile}" --jit + decode_br_cnt=$(perf script -i "${perfdatafile}" --itrace=b | wc -l) + # Note that overflow and lost errors are suppressed for the error count + decode_err_cnt=$(perf script -i "${perfdatafile}" --itrace=e-o-l | grep -ci error) + cd - + # Should be thousands of branches + if [ "${decode_br_cnt}" -lt 1000 ] ; then + echo "Decode failed, only ${decode_br_cnt} branches" + return 1 + fi + # Should be no errors + if [ "${decode_err_cnt}" -ne 0 ] ; then + echo "Decode failed, ${decode_err_cnt} errors" + perf script -i "${perfdatafile}" --itrace=e-o-l --show-mmap-events | cat + return 1 + fi + + echo OK + return 0 +} + +test_packet_filter() +{ + echo "--- Test with MTC and TSC disabled ---" + # Disable MTC and TSC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/mtc=0,tsc=0/u uname + # Should not get MTC packet + mtc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "MTC 0x") + if [ "${mtc_cnt}" -ne 0 ] ; then + echo "Failed to filter with mtc=0" + return 1 + fi + # Should not get TSC package + tsc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TSC 0x") + if [ "${tsc_cnt}" -ne 0 ] ; then + echo "Failed to filter with tsc=0" + return 1 + fi + echo OK + return 0 +} + +test_disable_branch() +{ + echo "--- Test with branches disabled ---" + # Disable branch + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/branch=0/u uname + # Should not get branch related packets + tnt_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TNT 0x") + tip_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TIP 0x") + fup_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "FUP 0x") + if [ "${tnt_cnt}" -ne 0 ] || [ "${tip_cnt}" -ne 0 ] || [ "${fup_cnt}" -ne 0 ] ; then + echo "Failed to disable branches" + return 1 + fi + echo OK + return 0 +} + +test_time_cyc() +{ + echo "--- Test with/without CYC ---" + # Check if CYC is supported + cyc=$(cat /sys/bus/event_source/devices/intel_pt/caps/psb_cyc) + if [ "${cyc}" != "1" ] ; then + echo "SKIP: CYC is not supported" + return 2 + fi + # Enable CYC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/cyc/u uname + # should get CYC packets + cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x") + if [ "${cyc_cnt}" = "0" ] ; then + echo "Failed to get CYC packet" + return 1 + fi + # Without CYC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u uname + # Should not get CYC packets + cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x") + if [ "${cyc_cnt}" -gt 0 ] ; then + echo "Still get CYC packet without cyc" + return 1 + fi + echo OK + return 0 +} + +test_sample() +{ + echo "--- Test recording with sample mode ---" + # Check if recording with sample mode is working + if ! perf_record_no_decode -o "${perfdatafile}" --aux-sample=8192 -e '{intel_pt//u,branch-misses:u}' uname ; then + echo "perf record failed with --aux-sample" + return 1 + fi + echo OK + return 0 +} + +test_kernel_trace() +{ + echo "--- Test with kernel trace ---" + # Check if recording with kernel trace is working + can_kernel || return 2 + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt//k -m1,128 uname ; then + echo "perf record failed with intel_pt//k" + return 1 + fi + echo OK + return 0 +} + +test_virtual_lbr() +{ + echo "--- Test virtual LBR ---" + # Check if python script is supported + libpython=$(perf version --build-options | grep python | grep -cv OFF) + if [ "${libpython}" != "1" ] ; then + echo "SKIP: python scripting is not supported" + return 2 + fi + + # Python script to determine the maximum size of branch stacks + cat << "_end_of_file_" > "${maxbrstack}" +from __future__ import print_function + +bmax = 0 + +def process_event(param_dict): + if "brstack" in param_dict: + brstack = param_dict["brstack"] + n = len(brstack) + global bmax + if n > bmax: + bmax = n + +def trace_end(): + print("max brstack", bmax) +_end_of_file_ + + # Check if virtual lbr is working + perf_record_no_bpf -o "${perfdatafile}" --aux-sample -e '{intel_pt//,cycles}:u' uname + times_val=$(perf script -i "${perfdatafile}" --itrace=L -s "${maxbrstack}" 2>/dev/null | grep "max brstack " | cut -d " " -f 3) + case "${times_val}" in + [0-9]*) ;; + *) times_val=0;; + esac + if [ "${times_val}" -lt 2 ] ; then + echo "Failed with virtual lbr" + return 1 + fi + echo OK + return 0 +} + +test_power_event() +{ + echo "--- Test power events ---" + # Check if power events are supported + power_event=$(cat /sys/bus/event_source/devices/intel_pt/caps/power_event_trace) + if [ "${power_event}" != "1" ] ; then + echo "SKIP: power_event_trace is not supported" + return 2 + fi + if ! perf_record_no_decode -o "${perfdatafile}" -a -e intel_pt/pwr_evt/u uname ; then + echo "perf record failed with pwr_evt" + return 1 + fi + echo OK + return 0 +} + +test_no_tnt() +{ + echo "--- Test with TNT packets disabled ---" + # Check if TNT disable is supported + notnt=$(cat /sys/bus/event_source/devices/intel_pt/caps/tnt_disable) + if [ "${notnt}" != "1" ] ; then + echo "SKIP: tnt_disable is not supported" + return 2 + fi + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/notnt/u uname + # Should be no TNT packets + tnt_cnt=$(perf script -i "${perfdatafile}" -D | grep -c TNT) + if [ "${tnt_cnt}" -ne 0 ] ; then + echo "TNT packets still there after notnt" + return 1 + fi + echo OK + return 0 +} + +test_event_trace() +{ + echo "--- Test with event_trace ---" + # Check if event_trace is supported + event_trace=$(cat /sys/bus/event_source/devices/intel_pt/caps/event_trace) + if [ "${event_trace}" != 1 ] ; then + echo "SKIP: event_trace is not supported" + return 2 + fi + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/event/u uname ; then + echo "perf record failed with event trace" + return 1 + fi + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -265,13 +631,22 @@ count_result() return fi err_cnt=$((err_cnt + 1)) - ret=0 } ret=0 -test_system_wide_side_band || ret=$? ; count_result $ret -test_per_thread "" "" || ret=$? ; count_result $ret -test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret +test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 +test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 +test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 +test_jitdump || ret=$? ; count_result $ret ; ret=0 +test_packet_filter || ret=$? ; count_result $ret ; ret=0 +test_disable_branch || ret=$? ; count_result $ret ; ret=0 +test_time_cyc || ret=$? ; count_result $ret ; ret=0 +test_sample || ret=$? ; count_result $ret ; ret=0 +test_kernel_trace || ret=$? ; count_result $ret ; ret=0 +test_virtual_lbr || ret=$? ; count_result $ret ; ret=0 +test_power_event || ret=$? ; count_result $ret ; ret=0 +test_no_tnt || ret=$? ; count_result $ret ; ret=0 +test_event_trace || ret=$? ; count_result $ret ; ret=0 cleanup diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c index 110f0c609d84..5f5320f7c6e2 100644 --- a/tools/perf/trace/beauty/statx.c +++ b/tools/perf/trace/beauty/statx.c @@ -66,6 +66,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a P_FLAG(BLOCKS); P_FLAG(BTIME); P_FLAG(MNT_ID); + P_FLAG(DIOALIGN); #undef P_FLAG diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 815d235466d0..e315ecaec323 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -118,6 +118,8 @@ perf-$(CONFIG_AUXTRACE) += intel-pt.o perf-$(CONFIG_AUXTRACE) += intel-bts.o perf-$(CONFIG_AUXTRACE) += arm-spe.o perf-$(CONFIG_AUXTRACE) += arm-spe-decoder/ +perf-$(CONFIG_AUXTRACE) += hisi-ptt.o +perf-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/ perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o ifdef CONFIG_LIBOPENCSD diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index b59c278fe9ed..46ada5ec3f9a 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -52,6 +52,7 @@ #include "intel-pt.h" #include "intel-bts.h" #include "arm-spe.h" +#include "hisi-ptt.h" #include "s390-cpumsf.h" #include "util/mmap.h" @@ -1320,6 +1321,9 @@ int perf_event__process_auxtrace_info(struct perf_session *session, case PERF_AUXTRACE_S390_CPUMSF: err = s390_cpumsf_process_auxtrace_info(event, session); break; + case PERF_AUXTRACE_HISI_PTT: + err = hisi_ptt_process_auxtrace_info(event, session); + break; case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; @@ -2321,11 +2325,19 @@ struct sym_args { bool near; }; +static bool kern_sym_name_match(const char *kname, const char *name) +{ + size_t n = strlen(name); + + return !strcmp(kname, name) || + (!strncmp(kname, name, n) && kname[n] == '\t'); +} + static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ return kallsyms__is_function(type) && - !strcmp(name, args->name) && + kern_sym_name_match(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || (!args->global && !args->selected)); diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index cb8e0a01abb6..6a0f9b98f059 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -48,6 +48,7 @@ enum auxtrace_type { PERF_AUXTRACE_CS_ETM, PERF_AUXTRACE_ARM_SPE, PERF_AUXTRACE_S390_CPUMSF, + PERF_AUXTRACE_HISI_PTT, }; enum itrace_period_type { diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index eee64ddb766d..cc7c1f90cf62 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -36,6 +36,11 @@ struct btf *btf__load_from_kernel_by_id(__u32 id) #endif #ifndef HAVE_LIBBPF_BPF_PROG_LOAD +LIBBPF_API int bpf_load_program(enum bpf_prog_type type, + const struct bpf_insn *insns, size_t insns_cnt, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz); + int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name __maybe_unused, const char *license, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index d657594894cf..a5dbd71cb9ab 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -36,6 +36,24 @@ #include <internal/xyarray.h> +#ifndef HAVE_LIBBPF_BPF_PROGRAM__SET_INSNS +int bpf_program__set_insns(struct bpf_program *prog __maybe_unused, + struct bpf_insn *new_insns __maybe_unused, size_t new_insn_cnt __maybe_unused) +{ + pr_err("%s: not support, update libbpf\n", __func__); + return -ENOTSUP; +} + +int libbpf_register_prog_handler(const char *sec __maybe_unused, + enum bpf_prog_type prog_type __maybe_unused, + enum bpf_attach_type exp_attach_type __maybe_unused, + const struct libbpf_prog_handler_opts *opts __maybe_unused) +{ + pr_err("%s: not support, update libbpf\n", __func__); + return -ENOTSUP; +} +#endif + /* temporarily disable libbpf deprecation warnings */ #pragma GCC diagnostic ignored "-Wdeprecated-declarations" @@ -300,7 +318,7 @@ static void bpf_program_hash_free(void) return; hashmap__for_each_entry(bpf_program_hash, cur, bkt) - clear_prog_priv(cur->key, cur->value); + clear_prog_priv(cur->pkey, cur->pvalue); hashmap__free(bpf_program_hash); bpf_program_hash = NULL; @@ -321,13 +339,12 @@ void bpf__clear(void) bpf_map_hash_free(); } -static size_t ptr_hash(const void *__key, void *ctx __maybe_unused) +static size_t ptr_hash(const long __key, void *ctx __maybe_unused) { - return (size_t) __key; + return __key; } -static bool ptr_equal(const void *key1, const void *key2, - void *ctx __maybe_unused) +static bool ptr_equal(long key1, long key2, void *ctx __maybe_unused) { return key1 == key2; } @@ -1167,7 +1184,7 @@ static void bpf_map_hash_free(void) return; hashmap__for_each_entry(bpf_map_hash, cur, bkt) - bpf_map_priv__clear(cur->key, cur->value); + bpf_map_priv__clear(cur->pkey, cur->pvalue); hashmap__free(bpf_map_hash); bpf_map_hash = NULL; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 435a87556688..6a438e0102c5 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -43,6 +43,18 @@ struct { __uint(value_size, sizeof(struct bpf_perf_event_value)); } cgrp_readings SEC(".maps"); +/* new kernel cgroup definition */ +struct cgroup___new { + int level; + struct cgroup *ancestors[]; +} __attribute__((preserve_access_index)); + +/* old kernel cgroup definition */ +struct cgroup___old { + int level; + u64 ancestor_ids[]; +} __attribute__((preserve_access_index)); + const volatile __u32 num_events = 1; const volatile __u32 num_cpus = 1; @@ -50,6 +62,21 @@ int enabled = 0; int use_cgroup_v2 = 0; int perf_subsys_id = -1; +static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level) +{ + /* recast pointer to capture new type for compiler */ + struct cgroup___new *cgrp_new = (void *)cgrp; + + if (bpf_core_field_exists(cgrp_new->ancestors)) { + return BPF_CORE_READ(cgrp_new, ancestors[level], kn, id); + } else { + /* recast pointer to capture old type for compiler */ + struct cgroup___old *cgrp_old = (void *)cgrp; + + return BPF_CORE_READ(cgrp_old, ancestor_ids[level]); + } +} + static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) { struct task_struct *p = (void *)bpf_get_current_task(); @@ -77,7 +104,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) break; // convert cgroup-id to a map index - cgrp_id = BPF_CORE_READ(cgrp, ancestors[i], kn, id); + cgrp_id = get_cgroup_v1_ancestor_id(cgrp, i); elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id); if (!elem) continue; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 76605fde3507..9e8a1294c981 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -3123,7 +3123,7 @@ void evsel__zero_per_pkg(struct evsel *evsel) if (evsel->per_pkg_mask) { hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt) - free((char *)cur->key); + free((void *)cur->pkey); hashmap__clear(evsel->per_pkg_mask); } diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index aaacf514dc09..2f05ecdcfe9a 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -46,7 +46,7 @@ struct expr_id_data { } kind; }; -static size_t key_hash(const void *key, void *ctx __maybe_unused) +static size_t key_hash(long key, void *ctx __maybe_unused) { const char *str = (const char *)key; size_t hash = 0; @@ -59,8 +59,7 @@ static size_t key_hash(const void *key, void *ctx __maybe_unused) return hash; } -static bool key_equal(const void *key1, const void *key2, - void *ctx __maybe_unused) +static bool key_equal(long key1, long key2, void *ctx __maybe_unused) { return !strcmp((const char *)key1, (const char *)key2); } @@ -84,8 +83,8 @@ void ids__free(struct hashmap *ids) return; hashmap__for_each_entry(ids, cur, bkt) { - free((char *)cur->key); - free(cur->value); + free((void *)cur->pkey); + free((void *)cur->pvalue); } hashmap__free(ids); @@ -97,8 +96,7 @@ int ids__insert(struct hashmap *ids, const char *id) char *old_key = NULL; int ret; - ret = hashmap__set(ids, id, data_ptr, - (const void **)&old_key, (void **)&old_data); + ret = hashmap__set(ids, id, data_ptr, &old_key, &old_data); if (ret) free(data_ptr); free(old_key); @@ -127,8 +125,7 @@ struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2) ids2 = tmp; } hashmap__for_each_entry(ids2, cur, bkt) { - ret = hashmap__set(ids1, cur->key, cur->value, - (const void **)&old_key, (void **)&old_data); + ret = hashmap__set(ids1, cur->key, cur->value, &old_key, &old_data); free(old_key); free(old_data); @@ -169,8 +166,7 @@ int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, data_ptr->val.source_count = source_count; data_ptr->kind = EXPR_ID_DATA__VALUE; - ret = hashmap__set(ctx->ids, id, data_ptr, - (const void **)&old_key, (void **)&old_data); + ret = hashmap__set(ctx->ids, id, data_ptr, &old_key, &old_data); if (ret) free(data_ptr); free(old_key); @@ -205,8 +201,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) data_ptr->ref.metric_expr = ref->metric_expr; data_ptr->kind = EXPR_ID_DATA__REF; - ret = hashmap__set(ctx->ids, name, data_ptr, - (const void **)&old_key, (void **)&old_data); + ret = hashmap__set(ctx->ids, name, data_ptr, &old_key, &old_data); if (ret) free(data_ptr); @@ -221,7 +216,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { - return hashmap__find(ctx->ids, id, (void **)data) ? 0 : -1; + return hashmap__find(ctx->ids, id, data) ? 0 : -1; } bool expr__subset_of_ids(struct expr_parse_ctx *haystack, @@ -232,7 +227,7 @@ bool expr__subset_of_ids(struct expr_parse_ctx *haystack, struct expr_id_data *data; hashmap__for_each_entry(needles->ids, cur, bkt) { - if (expr__get_id(haystack, cur->key, &data)) + if (expr__get_id(haystack, cur->pkey, &data)) return false; } return true; @@ -282,8 +277,7 @@ void expr__del_id(struct expr_parse_ctx *ctx, const char *id) struct expr_id_data *old_val = NULL; char *old_key = NULL; - hashmap__delete(ctx->ids, id, - (const void **)&old_key, (void **)&old_val); + hashmap__delete(ctx->ids, id, &old_key, &old_val); free(old_key); free(old_val); } @@ -314,8 +308,8 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx) size_t bkt; hashmap__for_each_entry(ctx->ids, cur, bkt) { - free((char *)cur->key); - free(cur->value); + free((void *)cur->pkey); + free(cur->pvalue); } hashmap__clear(ctx->ids); } @@ -330,8 +324,8 @@ void expr__ctx_free(struct expr_parse_ctx *ctx) free(ctx->sctx.user_requested_cpu_list); hashmap__for_each_entry(ctx->ids, cur, bkt) { - free((char *)cur->key); - free(cur->value); + free((void *)cur->pkey); + free(cur->pvalue); } hashmap__free(ctx->ids); free(ctx); diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index b5c909546e3f..6af062d1c452 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -2,6 +2,8 @@ #ifndef __GENELF_H__ #define __GENELF_H__ +#include <linux/math.h> + /* genelf.c */ int jit_write_elf(int fd, uint64_t code_addr, const char *sym, const void *code, int csize, void *debug, int nr_debug_entries, @@ -76,6 +78,6 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #endif /* The .text section is directly after the ELF header */ -#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr) +#define GEN_ELF_TEXT_OFFSET round_up(sizeof(Elf_Ehdr) + sizeof(Elf_Phdr), 16) #endif diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c index aeb09c288716..140ee4055676 100644 --- a/tools/perf/util/hashmap.c +++ b/tools/perf/util/hashmap.c @@ -128,7 +128,7 @@ static int hashmap_grow(struct hashmap *map) } static bool hashmap_find_entry(const struct hashmap *map, - const void *key, size_t hash, + const long key, size_t hash, struct hashmap_entry ***pprev, struct hashmap_entry **entry) { @@ -151,18 +151,18 @@ static bool hashmap_find_entry(const struct hashmap *map, return false; } -int hashmap__insert(struct hashmap *map, const void *key, void *value, - enum hashmap_insert_strategy strategy, - const void **old_key, void **old_value) +int hashmap_insert(struct hashmap *map, long key, long value, + enum hashmap_insert_strategy strategy, + long *old_key, long *old_value) { struct hashmap_entry *entry; size_t h; int err; if (old_key) - *old_key = NULL; + *old_key = 0; if (old_value) - *old_value = NULL; + *old_value = 0; h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); if (strategy != HASHMAP_APPEND && @@ -203,7 +203,7 @@ int hashmap__insert(struct hashmap *map, const void *key, void *value, return 0; } -bool hashmap__find(const struct hashmap *map, const void *key, void **value) +bool hashmap_find(const struct hashmap *map, long key, long *value) { struct hashmap_entry *entry; size_t h; @@ -217,8 +217,8 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value) return true; } -bool hashmap__delete(struct hashmap *map, const void *key, - const void **old_key, void **old_value) +bool hashmap_delete(struct hashmap *map, long key, + long *old_key, long *old_value) { struct hashmap_entry **pprev, *entry; size_t h; diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index 10a4c4cd13cf..0a5bf1937a7c 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -40,12 +40,32 @@ static inline size_t str_hash(const char *s) return h; } -typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); -typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); +typedef size_t (*hashmap_hash_fn)(long key, void *ctx); +typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx); +/* + * Hashmap interface is polymorphic, keys and values could be either + * long-sized integers or pointers, this is achieved as follows: + * - interface functions that operate on keys and values are hidden + * behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert; + * - these auxiliary macros cast the key and value parameters as + * long or long *, so the user does not have to specify the casts explicitly; + * - for pointer parameters (e.g. old_key) the size of the pointed + * type is verified by hashmap_cast_ptr using _Static_assert; + * - when iterating using hashmap__for_each_* forms + * hasmap_entry->key should be used for integer keys and + * hasmap_entry->pkey should be used for pointer keys, + * same goes for values. + */ struct hashmap_entry { - const void *key; - void *value; + union { + long key; + const void *pkey; + }; + union { + long value; + void *pvalue; + }; struct hashmap_entry *next; }; @@ -102,6 +122,13 @@ enum hashmap_insert_strategy { HASHMAP_APPEND, }; +#define hashmap_cast_ptr(p) ({ \ + _Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) || \ + sizeof(*(p)) == sizeof(long), \ + #p " pointee should be a long-sized integer or a pointer"); \ + (long *)(p); \ +}) + /* * hashmap__insert() adds key/value entry w/ various semantics, depending on * provided strategy value. If a given key/value pair replaced already @@ -109,42 +136,38 @@ enum hashmap_insert_strategy { * through old_key and old_value to allow calling code do proper memory * management. */ -int hashmap__insert(struct hashmap *map, const void *key, void *value, - enum hashmap_insert_strategy strategy, - const void **old_key, void **old_value); +int hashmap_insert(struct hashmap *map, long key, long value, + enum hashmap_insert_strategy strategy, + long *old_key, long *old_value); -static inline int hashmap__add(struct hashmap *map, - const void *key, void *value) -{ - return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL); -} +#define hashmap__insert(map, key, value, strategy, old_key, old_value) \ + hashmap_insert((map), (long)(key), (long)(value), (strategy), \ + hashmap_cast_ptr(old_key), \ + hashmap_cast_ptr(old_value)) -static inline int hashmap__set(struct hashmap *map, - const void *key, void *value, - const void **old_key, void **old_value) -{ - return hashmap__insert(map, key, value, HASHMAP_SET, - old_key, old_value); -} +#define hashmap__add(map, key, value) \ + hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL) -static inline int hashmap__update(struct hashmap *map, - const void *key, void *value, - const void **old_key, void **old_value) -{ - return hashmap__insert(map, key, value, HASHMAP_UPDATE, - old_key, old_value); -} +#define hashmap__set(map, key, value, old_key, old_value) \ + hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value)) -static inline int hashmap__append(struct hashmap *map, - const void *key, void *value) -{ - return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL); -} +#define hashmap__update(map, key, value, old_key, old_value) \ + hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value)) + +#define hashmap__append(map, key, value) \ + hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL) + +bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value); + +#define hashmap__delete(map, key, old_key, old_value) \ + hashmap_delete((map), (long)(key), \ + hashmap_cast_ptr(old_key), \ + hashmap_cast_ptr(old_value)) -bool hashmap__delete(struct hashmap *map, const void *key, - const void **old_key, void **old_value); +bool hashmap_find(const struct hashmap *map, long key, long *value); -bool hashmap__find(const struct hashmap *map, const void *key, void **value); +#define hashmap__find(map, key, value) \ + hashmap_find((map), (long)(key), hashmap_cast_ptr(value)) /* * hashmap__for_each_entry - iterate over all entries in hashmap diff --git a/tools/perf/util/hisi-ptt-decoder/Build b/tools/perf/util/hisi-ptt-decoder/Build new file mode 100644 index 000000000000..db3db8b75033 --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/Build @@ -0,0 +1 @@ +perf-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c new file mode 100644 index 000000000000..a17c423a526d --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <endian.h> +#include <byteswap.h> +#include <linux/bitops.h> +#include <stdarg.h> + +#include "../color.h" +#include "hisi-ptt-pkt-decoder.h" + +/* + * For 8DW format, the bit[31:11] of DW0 is always 0x1fffff, which can be + * used to distinguish the data format. + * 8DW format is like: + * bits [ 31:11 ][ 10:0 ] + * |---------------------------------------|-------------------| + * DW0 [ 0x1fffff ][ Reserved (0x7ff) ] + * DW1 [ Prefix ] + * DW2 [ Header DW0 ] + * DW3 [ Header DW1 ] + * DW4 [ Header DW2 ] + * DW5 [ Header DW3 ] + * DW6 [ Reserved (0x0) ] + * DW7 [ Time ] + * + * 4DW format is like: + * bits [31:30] [ 29:25 ][24][23][22][21][ 20:11 ][ 10:0 ] + * |-----|---------|---|---|---|---|-------------|-------------| + * DW0 [ Fmt ][ Type ][T9][T8][TH][SO][ Length ][ Time ] + * DW1 [ Header DW1 ] + * DW2 [ Header DW2 ] + * DW3 [ Header DW3 ] + */ + +enum hisi_ptt_8dw_pkt_field_type { + HISI_PTT_8DW_CHK_AND_RSV0, + HISI_PTT_8DW_PREFIX, + HISI_PTT_8DW_HEAD0, + HISI_PTT_8DW_HEAD1, + HISI_PTT_8DW_HEAD2, + HISI_PTT_8DW_HEAD3, + HISI_PTT_8DW_RSV1, + HISI_PTT_8DW_TIME, + HISI_PTT_8DW_TYPE_MAX +}; + +enum hisi_ptt_4dw_pkt_field_type { + HISI_PTT_4DW_HEAD1, + HISI_PTT_4DW_HEAD2, + HISI_PTT_4DW_HEAD3, + HISI_PTT_4DW_TYPE_MAX +}; + +static const char * const hisi_ptt_8dw_pkt_field_name[] = { + [HISI_PTT_8DW_PREFIX] = "Prefix", + [HISI_PTT_8DW_HEAD0] = "Header DW0", + [HISI_PTT_8DW_HEAD1] = "Header DW1", + [HISI_PTT_8DW_HEAD2] = "Header DW2", + [HISI_PTT_8DW_HEAD3] = "Header DW3", + [HISI_PTT_8DW_TIME] = "Time" +}; + +static const char * const hisi_ptt_4dw_pkt_field_name[] = { + [HISI_PTT_4DW_HEAD1] = "Header DW1", + [HISI_PTT_4DW_HEAD2] = "Header DW2", + [HISI_PTT_4DW_HEAD3] = "Header DW3", +}; + +union hisi_ptt_4dw { + struct { + uint32_t format : 2; + uint32_t type : 5; + uint32_t t9 : 1; + uint32_t t8 : 1; + uint32_t th : 1; + uint32_t so : 1; + uint32_t len : 10; + uint32_t time : 11; + }; + uint32_t value; +}; + +static void hisi_ptt_print_pkt(const unsigned char *buf, int pos, const char *desc) +{ + const char *color = PERF_COLOR_BLUE; + int i; + + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + for (i = 0; i < HISI_PTT_FIELD_LENTH; i++) + color_fprintf(stdout, color, "%02x ", buf[pos + i]); + for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++) + color_fprintf(stdout, color, " "); + color_fprintf(stdout, color, " %s\n", desc); +} + +static int hisi_ptt_8dw_kpt_desc(const unsigned char *buf, int pos) +{ + int i; + + for (i = 0; i < HISI_PTT_8DW_TYPE_MAX; i++) { + /* Do not show 8DW check field and reserved fields */ + if (i == HISI_PTT_8DW_CHK_AND_RSV0 || i == HISI_PTT_8DW_RSV1) { + pos += HISI_PTT_FIELD_LENTH; + continue; + } + + hisi_ptt_print_pkt(buf, pos, hisi_ptt_8dw_pkt_field_name[i]); + pos += HISI_PTT_FIELD_LENTH; + } + + return hisi_ptt_pkt_size[HISI_PTT_8DW_PKT]; +} + +static void hisi_ptt_4dw_print_dw0(const unsigned char *buf, int pos) +{ + const char *color = PERF_COLOR_BLUE; + union hisi_ptt_4dw dw0; + int i; + + dw0.value = *(uint32_t *)(buf + pos); + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + for (i = 0; i < HISI_PTT_FIELD_LENTH; i++) + color_fprintf(stdout, color, "%02x ", buf[pos + i]); + for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++) + color_fprintf(stdout, color, " "); + + color_fprintf(stdout, color, + " %s %x %s %x %s %x %s %x %s %x %s %x %s %x %s %x\n", + "Format", dw0.format, "Type", dw0.type, "T9", dw0.t9, + "T8", dw0.t8, "TH", dw0.th, "SO", dw0.so, "Length", + dw0.len, "Time", dw0.time); +} + +static int hisi_ptt_4dw_kpt_desc(const unsigned char *buf, int pos) +{ + int i; + + hisi_ptt_4dw_print_dw0(buf, pos); + pos += HISI_PTT_FIELD_LENTH; + + for (i = 0; i < HISI_PTT_4DW_TYPE_MAX; i++) { + hisi_ptt_print_pkt(buf, pos, hisi_ptt_4dw_pkt_field_name[i]); + pos += HISI_PTT_FIELD_LENTH; + } + + return hisi_ptt_pkt_size[HISI_PTT_4DW_PKT]; +} + +int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type) +{ + if (type == HISI_PTT_8DW_PKT) + return hisi_ptt_8dw_kpt_desc(buf, pos); + + return hisi_ptt_4dw_kpt_desc(buf, pos); +} diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h new file mode 100644 index 000000000000..e78f1b5bc836 --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#ifndef INCLUDE__HISI_PTT_PKT_DECODER_H__ +#define INCLUDE__HISI_PTT_PKT_DECODER_H__ + +#include <stddef.h> +#include <stdint.h> + +#define HISI_PTT_8DW_CHECK_MASK GENMASK(31, 11) +#define HISI_PTT_IS_8DW_PKT GENMASK(31, 11) +#define HISI_PTT_MAX_SPACE_LEN 10 +#define HISI_PTT_FIELD_LENTH 4 + +enum hisi_ptt_pkt_type { + HISI_PTT_4DW_PKT, + HISI_PTT_8DW_PKT, + HISI_PTT_PKT_MAX +}; + +static int hisi_ptt_pkt_size[] = { + [HISI_PTT_4DW_PKT] = 16, + [HISI_PTT_8DW_PKT] = 32, +}; + +int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type); + +#endif diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c new file mode 100644 index 000000000000..45b614bb73bf --- /dev/null +++ b/tools/perf/util/hisi-ptt.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include <byteswap.h> +#include <endian.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/types.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <unistd.h> + +#include "auxtrace.h" +#include "color.h" +#include "debug.h" +#include "evsel.h" +#include "hisi-ptt.h" +#include "hisi-ptt-decoder/hisi-ptt-pkt-decoder.h" +#include "machine.h" +#include "session.h" +#include "tool.h" +#include <internal/lib.h> + +struct hisi_ptt { + struct auxtrace auxtrace; + u32 auxtrace_type; + struct perf_session *session; + struct machine *machine; + u32 pmu_type; +}; + +struct hisi_ptt_queue { + struct hisi_ptt *ptt; + struct auxtrace_buffer *buffer; +}; + +static enum hisi_ptt_pkt_type hisi_ptt_check_packet_type(unsigned char *buf) +{ + uint32_t head = *(uint32_t *)buf; + + if ((HISI_PTT_8DW_CHECK_MASK & head) == HISI_PTT_IS_8DW_PKT) + return HISI_PTT_8DW_PKT; + + return HISI_PTT_4DW_PKT; +} + +static void hisi_ptt_dump(struct hisi_ptt *ptt __maybe_unused, + unsigned char *buf, size_t len) +{ + const char *color = PERF_COLOR_BLUE; + enum hisi_ptt_pkt_type type; + size_t pos = 0; + int pkt_len; + + type = hisi_ptt_check_packet_type(buf); + len = round_down(len, hisi_ptt_pkt_size[type]); + color_fprintf(stdout, color, ". ... HISI PTT data: size %zu bytes\n", + len); + + while (len > 0) { + pkt_len = hisi_ptt_pkt_desc(buf, pos, type); + if (!pkt_len) + color_fprintf(stdout, color, " Bad packet!\n"); + + pos += pkt_len; + len -= pkt_len; + } +} + +static void hisi_ptt_dump_event(struct hisi_ptt *ptt, unsigned char *buf, + size_t len) +{ + printf(".\n"); + + hisi_ptt_dump(ptt, buf, len); +} + +static int hisi_ptt_process_event(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static int hisi_ptt_process_auxtrace_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool __maybe_unused) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, + auxtrace); + int fd = perf_data__fd(session->data); + int size = event->auxtrace.size; + void *data = malloc(size); + off_t data_offset; + int err; + + if (!data) + return -errno; + + if (perf_data__is_pipe(session->data)) { + data_offset = 0; + } else { + data_offset = lseek(fd, 0, SEEK_CUR); + if (data_offset == -1) + return -errno; + } + + err = readn(fd, data, size); + if (err != (ssize_t)size) { + free(data); + return -errno; + } + + if (dump_trace) + hisi_ptt_dump_event(ptt, data, size); + + return 0; +} + +static int hisi_ptt_flush(struct perf_session *session __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static void hisi_ptt_free_events(struct perf_session *session __maybe_unused) +{ +} + +static void hisi_ptt_free(struct perf_session *session) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, + auxtrace); + + session->auxtrace = NULL; + free(ptt); +} + +static bool hisi_ptt_evsel_is_auxtrace(struct perf_session *session, + struct evsel *evsel) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, auxtrace); + + return evsel->core.attr.type == ptt->pmu_type; +} + +static void hisi_ptt_print_info(__u64 type) +{ + if (!dump_trace) + return; + + fprintf(stdout, " PMU Type %" PRId64 "\n", (s64) type); +} + +int hisi_ptt_process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; + struct hisi_ptt *ptt; + + if (auxtrace_info->header.size < HISI_PTT_AUXTRACE_PRIV_SIZE + + sizeof(struct perf_record_auxtrace_info)) + return -EINVAL; + + ptt = zalloc(sizeof(*ptt)); + if (!ptt) + return -ENOMEM; + + ptt->session = session; + ptt->machine = &session->machines.host; /* No kvm support */ + ptt->auxtrace_type = auxtrace_info->type; + ptt->pmu_type = auxtrace_info->priv[0]; + + ptt->auxtrace.process_event = hisi_ptt_process_event; + ptt->auxtrace.process_auxtrace_event = hisi_ptt_process_auxtrace_event; + ptt->auxtrace.flush_events = hisi_ptt_flush; + ptt->auxtrace.free_events = hisi_ptt_free_events; + ptt->auxtrace.free = hisi_ptt_free; + ptt->auxtrace.evsel_is_auxtrace = hisi_ptt_evsel_is_auxtrace; + session->auxtrace = &ptt->auxtrace; + + hisi_ptt_print_info(auxtrace_info->priv[0]); + + return 0; +} diff --git a/tools/perf/util/hisi-ptt.h b/tools/perf/util/hisi-ptt.h new file mode 100644 index 000000000000..2db9b4056214 --- /dev/null +++ b/tools/perf/util/hisi-ptt.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#ifndef INCLUDE__PERF_HISI_PTT_H__ +#define INCLUDE__PERF_HISI_PTT_H__ + +#define HISI_PTT_PMU_NAME "hisi_ptt" +#define HISI_PTT_AUXTRACE_PRIV_SIZE sizeof(u64) + +struct auxtrace_record *hisi_ptt_recording_init(int *err, + struct perf_pmu *hisi_ptt_pmu); + +int hisi_ptt_process_auxtrace_info(union perf_event *event, + struct perf_session *session); + +#endif diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index aa0c5179836d..75e2248416f5 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -115,4 +115,17 @@ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) #endif +// In the kernel sources (include/linux/cfi_types.h), this has a different +// definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang +// definition: +#ifndef SYM_TYPED_START +#define SYM_TYPED_START(name, linkage, align...) \ + SYM_START(name, linkage, align) +#endif + +#ifndef SYM_TYPED_FUNC_START +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index b34cb3dec1aa..e3548ddef254 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -4046,6 +4046,7 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n", [INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n", [INTEL_PT_MTC_BIT] = " MTC bit %#"PRIx64"\n", + [INTEL_PT_MTC_FREQ_BITS] = " MTC freq bits %#"PRIx64"\n", [INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n", [INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n", [INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n", @@ -4060,8 +4061,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish) if (!dump_trace) return; - for (i = start; i <= finish; i++) - fprintf(stdout, intel_pt_info_fmts[i], arr[i]); + for (i = start; i <= finish; i++) { + const char *fmt = intel_pt_info_fmts[i]; + + if (fmt) + fprintf(stdout, fmt, arr[i]); + } } static void intel_pt_print_info_str(const char *name, const char *str) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 4c98ac29ee13..6b3505b1b6ac 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -288,7 +288,7 @@ static int setup_metric_events(struct hashmap *ids, * combined or shared groups, this metric may not care * about this event. */ - if (hashmap__find(ids, metric_id, (void **)&val_ptr)) { + if (hashmap__find(ids, metric_id, &val_ptr)) { metric_events[matched_events++] = ev; if (matched_events >= ids_size) @@ -764,7 +764,7 @@ static int metricgroup__build_event_string(struct strbuf *events, #define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0) hashmap__for_each_entry(ctx->ids, cur, bkt) { - const char *sep, *rsep, *id = cur->key; + const char *sep, *rsep, *id = cur->pkey; enum perf_tool_event ev; pr_debug("found event %s\n", id); @@ -945,14 +945,14 @@ static int resolve_metric(struct list_head *metric_list, hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) { struct pmu_event pe; - if (metricgroup__find_metric(cur->key, table, &pe)) { + if (metricgroup__find_metric(cur->pkey, table, &pe)) { pending = realloc(pending, (pending_cnt + 1) * sizeof(struct to_resolve)); if (!pending) return -ENOMEM; memcpy(&pending[pending_cnt].pe, &pe, sizeof(pe)); - pending[pending_cnt].key = cur->key; + pending[pending_cnt].key = cur->pkey; pending_cnt++; } } @@ -1433,7 +1433,7 @@ static int build_combined_expr_ctx(const struct list_head *metric_list, list_for_each_entry(m, metric_list, nd) { if (m->has_constraint && !m->modifier) { hashmap__for_each_entry(m->pctx->ids, cur, bkt) { - dup = strdup(cur->key); + dup = strdup(cur->pkey); if (!dup) { ret = -ENOMEM; goto err_out; diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 00588b9db474..31faf2bb49ff 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -102,8 +102,10 @@ parse_branch_stack(const struct option *opt, const char *str, int unset) /* * cannot set it twice, -b + --branch-filter for instance */ - if (*mode) + if (*mode) { + pr_err("Error: Can't use --branch-any (-b) with --branch-filter (-j).\n"); return -1; + } return parse_branch_str(str, mode); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 437389dacf48..5973f46c2375 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -246,6 +246,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu) + perf_pmu__warn_invalid_formats(pmu); + if (pmu && attr->type == PERF_TYPE_RAW) perf_pmu__warn_invalid_config(pmu, attr->config, name); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 74a2cafb4e8d..03284059175f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1005,6 +1005,23 @@ err: return NULL; } +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) +{ + struct perf_pmu_format *format; + + /* fake pmu doesn't have format list */ + if (pmu == &perf_pmu__fake) + return; + + list_for_each_entry(format, &pmu->format, list) + if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) { + pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'" + "which is not supported by this version of perf!\n", + pmu->name, format->name, format->value); + return; + } +} + static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a7b0f9507510..68e15c38ae71 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -17,6 +17,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG, PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, + PERF_PMU_FORMAT_VALUE_CONFIG_END, }; #define PERF_PMU_FORMAT_BITS 64 @@ -139,6 +140,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *name); +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); bool perf_pmu__has_hybrid(void); int perf_pmu__match(char *pattern, char *name, char *tok); diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l index a15d9fbd7c0e..58b4926cfaca 100644 --- a/tools/perf/util/pmu.l +++ b/tools/perf/util/pmu.l @@ -27,8 +27,6 @@ num_dec [0-9]+ {num_dec} { return value(10); } config { return PP_CONFIG; } -config1 { return PP_CONFIG1; } -config2 { return PP_CONFIG2; } - { return '-'; } : { return ':'; } , { return ','; } diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index 0dab0ec2eff7..e675d79a0274 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -18,7 +18,7 @@ do { \ %} -%token PP_CONFIG PP_CONFIG1 PP_CONFIG2 +%token PP_CONFIG %token PP_VALUE PP_ERROR %type <num> PP_VALUE %type <bits> bit_term @@ -45,18 +45,11 @@ PP_CONFIG ':' bits $3)); } | -PP_CONFIG1 ':' bits +PP_CONFIG PP_VALUE ':' bits { ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG1, - $3)); -} -| -PP_CONFIG2 ':' bits -{ - ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG2, - $3)); + $2, + $4)); } bits: diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 5c47ee9963a7..ba66bb7fc1ca 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -273,7 +273,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) fputc('\n', os->fh); if (os->prefix) - fprintf(os->fh, "%s%s", os->prefix, config->csv_sep); + fprintf(os->fh, "%s", os->prefix); aggr_printout(config, os->evsel, os->id, os->nr); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); @@ -559,7 +559,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int [AGGR_CORE] = 2, [AGGR_THREAD] = 1, [AGGR_UNSET] = 0, - [AGGR_NODE] = 0, + [AGGR_NODE] = 1, }; pm = config->metric_only ? print_metric_only_csv : print_metric_csv; @@ -1124,6 +1124,7 @@ static int aggr_header_lens[] = { [AGGR_SOCKET] = 12, [AGGR_NONE] = 6, [AGGR_THREAD] = 24, + [AGGR_NODE] = 6, [AGGR_GLOBAL] = 0, }; @@ -1133,6 +1134,7 @@ static const char *aggr_header_csv[] = { [AGGR_SOCKET] = "socket,cpus", [AGGR_NONE] = "cpu,", [AGGR_THREAD] = "comm-pid,", + [AGGR_NODE] = "node,", [AGGR_GLOBAL] = "" }; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 07b29fe272c7..0bf71b02aa06 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -398,7 +398,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) i = 0; hashmap__for_each_entry(ctx->ids, cur, bkt) { - const char *metric_name = (const char *)cur->key; + const char *metric_name = cur->pkey; found = false; if (leader) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 8ec8bb4a9912..c0656f85bfa5 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -278,15 +278,14 @@ void evlist__save_aggr_prev_raw_counts(struct evlist *evlist) } } -static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused) +static size_t pkg_id_hash(long __key, void *ctx __maybe_unused) { uint64_t *key = (uint64_t *) __key; return *key & 0xffffffff; } -static bool pkg_id_equal(const void *__key1, const void *__key2, - void *ctx __maybe_unused) +static bool pkg_id_equal(long __key1, long __key2, void *ctx __maybe_unused) { uint64_t *key1 = (uint64_t *) __key1; uint64_t *key2 = (uint64_t *) __key2; @@ -347,11 +346,11 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, return -ENOMEM; *key = (uint64_t)d << 32 | s; - if (hashmap__find(mask, (void *)key, NULL)) { + if (hashmap__find(mask, key, NULL)) { *skip = true; free(key); } else - ret = hashmap__add(mask, (void *)key, (void *)1); + ret = hashmap__add(mask, key, 1); return ret; } |