diff options
Diffstat (limited to 'tools/perf/arch/x86/util')
| -rw-r--r-- | tools/perf/arch/x86/util/Build | 1 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/auxtrace.c | 5 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/env.c | 19 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/env.h | 7 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/evlist.c | 29 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/evsel.c | 43 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/intel-bts.c | 4 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/intel-pt.c | 4 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/mem-events.c | 36 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/perf_regs.c | 15 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/pmu.c | 12 | ||||
| -rw-r--r-- | tools/perf/arch/x86/util/topdown.c | 5 |
12 files changed, 94 insertions, 86 deletions
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 195ccfdef7aa..005907cb97d8 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -10,6 +10,7 @@ perf-y += evlist.o perf-y += mem-events.o perf-y += evsel.o perf-y += iostat.o +perf-y += env.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 330d03216b0e..354780ff1605 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -10,6 +10,7 @@ #include "../../../util/header.h" #include "../../../util/debug.h" #include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/auxtrace.h" #include "../../../util/intel-pt.h" #include "../../../util/intel-bts.h" @@ -25,8 +26,8 @@ struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, bool found_pt = false; bool found_bts = false; - intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); - intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); + intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME); evlist__for_each_entry(evlist, evsel) { if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c new file mode 100644 index 000000000000..3e537ffb1353 --- /dev/null +++ b/tools/perf/arch/x86/util/env.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "linux/string.h" +#include "util/env.h" +#include "env.h" + +bool x86__is_amd_cpu(void) +{ + struct perf_env env = { .total_mem = 0, }; + static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */ + + if (is_amd) + goto ret; + + perf_env__cpuid(&env); + is_amd = env.cpuid && strstarts(env.cpuid, "AuthenticAMD") ? 1 : -1; + perf_env__exit(&env); +ret: + return is_amd >= 1 ? true : false; +} diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h new file mode 100644 index 000000000000..d78f080b6b3f --- /dev/null +++ b/tools/perf/arch/x86/util/env.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_ENV_H +#define _X86_ENV_H + +bool x86__is_amd_cpu(void); + +#endif /* _X86_ENV_H */ diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index d4193479a364..cbd582182932 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -1,38 +1,42 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include "util/pmu.h" +#include "util/pmus.h" #include "util/evlist.h" #include "util/parse-events.h" #include "util/event.h" -#include "util/pmu-hybrid.h" #include "topdown.h" +#include "evsel.h" static int ___evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { - struct perf_cpu_map *cpus; - struct evsel *evsel, *n; - struct perf_pmu *pmu; LIST_HEAD(head); size_t i = 0; for (i = 0; i < nr_attrs; i++) event_attr_init(attrs + i); - if (!perf_pmu__has_hybrid()) + if (perf_pmus__num_core_pmus() == 1) return evlist__add_attrs(evlist, attrs, nr_attrs); for (i = 0; i < nr_attrs; i++) { + struct perf_pmu *pmu = NULL; + if (attrs[i].type == PERF_TYPE_SOFTWARE) { - evsel = evsel__new(attrs + i); + struct evsel *evsel = evsel__new(attrs + i); + if (evsel == NULL) goto out_delete_partial_list; list_add_tail(&evsel->core.node, &head); continue; } - perf_pmu__for_each_hybrid_pmu(pmu) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + struct perf_cpu_map *cpus; + struct evsel *evsel; + evsel = evsel__new(attrs + i); if (evsel == NULL) goto out_delete_partial_list; @@ -50,8 +54,12 @@ static int ___evlist__add_default_attrs(struct evlist *evlist, return 0; out_delete_partial_list: - __evlist__for_each_entry_safe(&head, n, evsel) - evsel__delete(evsel); + { + struct evsel *evsel, *n; + + __evlist__for_each_entry_safe(&head, n, evsel) + evsel__delete(evsel); + } return -1; } @@ -67,8 +75,7 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) { - if (topdown_sys_has_perf_metrics() && - (!lhs->pmu_name || !strncmp(lhs->pmu_name, "cpu", 3))) { + if (topdown_sys_has_perf_metrics() && evsel__sys_has_perf_metrics(lhs)) { /* Ensure the topdown slots comes first. */ if (strcasestr(lhs->name, "slots")) return -1; diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index ea3972d785d1..512c2d885d24 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -4,9 +4,11 @@ #include "util/evsel.h" #include "util/env.h" #include "util/pmu.h" +#include "util/pmus.h" #include "linux/string.h" #include "evsel.h" #include "util/debug.h" +#include "env.h" #define IBS_FETCH_L3MISSONLY (1ULL << 59) #define IBS_OP_L3MISSONLY (1ULL << 16) @@ -16,26 +18,6 @@ void arch_evsel__set_sample_weight(struct evsel *evsel) evsel__set_sample_bit(evsel, WEIGHT_STRUCT); } -void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr) -{ - struct perf_env env = { .total_mem = 0, } ; - - if (!perf_env__cpuid(&env)) - return; - - /* - * On AMD, precise cycles event sampling internally uses IBS pmu. - * But IBS does not have filtering capabilities and perf by default - * sets exclude_guest = 1. This makes IBS pmu event init fail and - * thus perf ends up doing non-precise sampling. Avoid it by clearing - * exclude_guest. - */ - if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD")) - attr->exclude_guest = 0; - - free(env.cpuid); -} - /* Check whether the evsel's PMU supports the perf metrics */ bool evsel__sys_has_perf_metrics(const struct evsel *evsel) { @@ -50,7 +32,7 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel) * should be good enough to detect the perf metrics feature. */ if ((evsel->core.attr.type == PERF_TYPE_RAW) && - pmu_have_event(pmu_name, "slots")) + perf_pmus__have_event(pmu_name, "slots")) return true; return false; @@ -97,29 +79,16 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr) { struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu; static int warned_once; - /* 0: Uninitialized, 1: Yes, -1: No */ - static int is_amd; - if (warned_once || is_amd == -1) + if (warned_once || !x86__is_amd_cpu()) return; - if (!is_amd) { - struct perf_env *env = evsel__env(evsel); - - if (!perf_env__cpuid(env) || !env->cpuid || - !strstarts(env->cpuid, "AuthenticAMD")) { - is_amd = -1; - return; - } - is_amd = 1; - } - evsel_pmu = evsel__find_pmu(evsel); if (!evsel_pmu) return; - ibs_fetch_pmu = perf_pmu__find("ibs_fetch"); - ibs_op_pmu = perf_pmu__find("ibs_op"); + ibs_fetch_pmu = perf_pmus__find("ibs_fetch"); + ibs_op_pmu = perf_pmus__find("ibs_op"); if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) { if (attr->config & IBS_FETCH_L3MISSONLY) { diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 439c2956f3e7..d2c8cac11470 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -17,7 +17,7 @@ #include "../../../util/evlist.h" #include "../../../util/mmap.h" #include "../../../util/session.h" -#include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/debug.h" #include "../../../util/record.h" #include "../../../util/tsc.h" @@ -416,7 +416,7 @@ out_err: struct auxtrace_record *intel_bts_recording_init(int *err) { - struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + struct perf_pmu *intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME); struct intel_bts_recording *btsr; if (!intel_bts_pmu) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 17336da08b58..74b70fd379df 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -23,7 +23,7 @@ #include "../../../util/mmap.h" #include <subcmd/parse-options.h> #include "../../../util/parse-events.h" -#include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/debug.h" #include "../../../util/auxtrace.h" #include "../../../util/perf_api_probe.h" @@ -1185,7 +1185,7 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) struct auxtrace_record *intel_pt_recording_init(int *err) { - struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); + struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); struct intel_pt_recording *ptr; if (!intel_pt_pmu) diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c index f683ac702247..a8a782bcb121 100644 --- a/tools/perf/arch/x86/util/mem-events.c +++ b/tools/perf/arch/x86/util/mem-events.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/pmu.h" +#include "util/pmus.h" #include "util/env.h" #include "map_symbol.h" #include "mem-events.h" #include "linux/string.h" +#include "env.h" static char mem_loads_name[100]; static bool mem_loads_name__init; @@ -26,28 +28,12 @@ static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = { E("mem-ldst", "ibs_op//", "ibs_op"), }; -static int perf_mem_is_amd_cpu(void) -{ - struct perf_env env = { .total_mem = 0, }; - - perf_env__cpuid(&env); - if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD")) - return 1; - return -1; -} - struct perf_mem_event *perf_mem_events__ptr(int i) { - /* 0: Uninitialized, 1: Yes, -1: No */ - static int is_amd; - if (i >= PERF_MEM_EVENTS__MAX) return NULL; - if (!is_amd) - is_amd = perf_mem_is_amd_cpu(); - - if (is_amd == 1) + if (x86__is_amd_cpu()) return &perf_mem_events_amd[i]; return &perf_mem_events_intel[i]; @@ -55,13 +41,13 @@ struct perf_mem_event *perf_mem_events__ptr(int i) bool is_mem_loads_aux_event(struct evsel *leader) { - if (perf_pmu__find("cpu")) { - if (!pmu_have_event("cpu", "mem-loads-aux")) - return false; - } else if (perf_pmu__find("cpu_core")) { - if (!pmu_have_event("cpu_core", "mem-loads-aux")) - return false; - } + struct perf_pmu *pmu = perf_pmus__find("cpu"); + + if (!pmu) + pmu = perf_pmus__find("cpu_core"); + + if (pmu && !perf_pmu__have_event(pmu, "mem-loads-aux")) + return false; return leader->core.attr.config == MEM_LOADS_AUX; } @@ -82,7 +68,7 @@ char *perf_mem_events__name(int i, char *pmu_name) pmu_name = (char *)"cpu"; } - if (pmu_have_event(pmu_name, "mem-loads-aux")) { + if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) { scnprintf(mem_loads_name, sizeof(mem_loads_name), MEM_LOADS_AUX_NAME, pmu_name, pmu_name, perf_mem_events__loads_ldlat); diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 0ed177991ad0..8ad4112ad10c 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -10,7 +10,7 @@ #include "../../../util/debug.h" #include "../../../util/event.h" #include "../../../util/pmu.h" -#include "../../../util/pmu-hybrid.h" +#include "../../../util/pmus.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -286,20 +286,25 @@ uint64_t arch__intr_reg_mask(void) .disabled = 1, .exclude_kernel = 1, }; - struct perf_pmu *pmu; int fd; /* * In an unnamed union, init it here to build on older gcc versions */ attr.sample_period = 1; - if (perf_pmu__has_hybrid()) { + if (perf_pmus__num_core_pmus() > 1) { + struct perf_pmu *pmu = NULL; + __u64 type = PERF_TYPE_RAW; + /* * The same register set is supported among different hybrid PMUs. * Only check the first available one. */ - pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list); - attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + type = pmu->type; + break; + } + attr.config |= type << PERF_PMU_TYPE_SHIFT; } event_attr_init(&attr); diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 3c0de3370d7e..65d8cdff4d5f 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -14,6 +14,8 @@ #include "../../../util/intel-bts.h" #include "../../../util/pmu.h" #include "../../../util/fncache.h" +#include "../../../util/pmus.h" +#include "env.h" struct pmu_alias { char *name; @@ -168,3 +170,13 @@ char *pmu_find_alias_name(const char *name) return __pmu_find_alias_name(name); } + +int perf_pmus__num_mem_pmus(void) +{ + /* AMD uses IBS OP pmu and not a core PMU for perf mem/c2c */ + if (x86__is_amd_cpu()) + return 1; + + /* Intel uses core pmus for perf mem/c2c */ + return perf_pmus__num_core_pmus(); +} diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index 9ad5e5c7bd27..3f9a267d4501 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -2,6 +2,7 @@ #include "api/fs/fs.h" #include "util/evsel.h" #include "util/pmu.h" +#include "util/pmus.h" #include "util/topdown.h" #include "topdown.h" #include "evsel.h" @@ -22,8 +23,8 @@ bool topdown_sys_has_perf_metrics(void) * The slots event is only available when the core PMU * supports the perf metrics feature. */ - pmu = perf_pmu__find_by_type(PERF_TYPE_RAW); - if (pmu && pmu_have_event(pmu->name, "slots")) + pmu = perf_pmus__find_by_type(PERF_TYPE_RAW); + if (pmu && perf_pmu__have_event(pmu, "slots")) has_perf_metrics = true; cached = true; |