diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index a0fe51e0c00f..f53ae1fd986f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -755,7 +755,7 @@ void x86_pmu_enable_all(int added) } } -static inline int is_x86_event(struct perf_event *event) +int is_x86_event(struct perf_event *event) { int i; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 876678aa3895..3152a018c502 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2603,7 +2603,8 @@ static void intel_pmu_del_event(struct perf_event *event) intel_pmu_lbr_del(event); if (event->attr.precise_ip) intel_pmu_pebs_del(event); - if (is_pebs_counter_event_group(event)) + if (is_pebs_counter_event_group(event) || + is_acr_event_group(event)) this_cpu_ptr(&cpu_hw_events)->n_late_setup--; } @@ -2882,6 +2883,52 @@ static void intel_pmu_enable_fixed(struct perf_event *event) cpuc->fixed_ctrl_val |= bits; } +static void intel_pmu_config_acr(int idx, u64 mask, u32 reload) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int msr_b, msr_c; + + if (!mask && !cpuc->acr_cfg_b[idx]) + return; + + if (idx < INTEL_PMC_IDX_FIXED) { + msr_b = MSR_IA32_PMC_V6_GP0_CFG_B; + msr_c = MSR_IA32_PMC_V6_GP0_CFG_C; + } else { + msr_b = MSR_IA32_PMC_V6_FX0_CFG_B; + msr_c = MSR_IA32_PMC_V6_FX0_CFG_C; + idx -= INTEL_PMC_IDX_FIXED; + } + + if (cpuc->acr_cfg_b[idx] != mask) { + wrmsrl(msr_b + x86_pmu.addr_offset(idx, false), mask); + cpuc->acr_cfg_b[idx] = mask; + } + /* Only need to update the reload value when there is a valid config value. */ + if (mask && cpuc->acr_cfg_c[idx] != reload) { + wrmsrl(msr_c + x86_pmu.addr_offset(idx, false), reload); + cpuc->acr_cfg_c[idx] = reload; + } +} + +static void intel_pmu_enable_acr(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!is_acr_event_group(event) || !event->attr.config2) { + /* + * The disable doesn't clear the ACR CFG register. + * Check and clear the ACR CFG register. + */ + intel_pmu_config_acr(hwc->idx, 0, 0); + return; + } + + intel_pmu_config_acr(hwc->idx, hwc->config1, -hwc->sample_period); +} + +DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr); + static void intel_pmu_enable_event(struct perf_event *event) { u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE; @@ -2896,9 +2943,12 @@ static void intel_pmu_enable_event(struct perf_event *event) if (branch_sample_counters(event)) enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR; intel_set_masks(event, idx); + static_call_cond(intel_pmu_enable_acr_event)(event); __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: + static_call_cond(intel_pmu_enable_acr_event)(event); + fallthrough; case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: intel_pmu_enable_fixed(event); break; @@ -2916,6 +2966,31 @@ static void intel_pmu_enable_event(struct perf_event *event) } } +static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc) +{ + struct perf_event *event, *leader; + int i, j, idx; + + for (i = 0; i < cpuc->n_events; i++) { + leader = cpuc->event_list[i]; + if (!is_acr_event_group(leader)) + continue; + + /* The ACR events must be contiguous. */ + for (j = i; j < cpuc->n_events; j++) { + event = cpuc->event_list[j]; + if (event->group_leader != leader->group_leader) + break; + for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) { + if (WARN_ON_ONCE(i + idx > cpuc->n_events)) + return; + __set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1); + } + } + i = j - 1; + } +} + void intel_pmu_late_setup(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -2924,6 +2999,7 @@ void intel_pmu_late_setup(void) return; intel_pmu_pebs_late_setup(cpuc); + intel_pmu_acr_late_setup(cpuc); } static void intel_pmu_add_event(struct perf_event *event) @@ -2932,7 +3008,8 @@ static void intel_pmu_add_event(struct perf_event *event) intel_pmu_pebs_add(event); if (intel_pmu_needs_branch_stack(event)) intel_pmu_lbr_add(event); - if (is_pebs_counter_event_group(event)) + if (is_pebs_counter_event_group(event) || + is_acr_event_group(event)) this_cpu_ptr(&cpu_hw_events)->n_late_setup++; } @@ -4087,6 +4164,39 @@ static u64 intel_pmu_freq_start_period(struct perf_event *event) return start; } +static inline bool intel_pmu_has_acr(struct pmu *pmu) +{ + return !!hybrid(pmu, acr_cause_mask64); +} + +static bool intel_pmu_is_acr_group(struct perf_event *event) +{ + /* The group leader has the ACR flag set */ + if (is_acr_event_group(event)) + return true; + + /* The acr_mask is set */ + if (event->attr.config2) + return true; + + return false; +} + +static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event, + u64 *cause_mask, int *num) +{ + event->hw.dyn_constraint &= hybrid(event->pmu, acr_cntr_mask64); + *cause_mask |= event->attr.config2; + *num += 1; +} + +static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event, + int idx, u64 cause_mask) +{ + if (test_bit(idx, (unsigned long *)&cause_mask)) + event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64); +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -4215,6 +4325,94 @@ static int intel_pmu_hw_config(struct perf_event *event) event->attr.precise_ip) event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR; + if (intel_pmu_has_acr(event->pmu) && intel_pmu_is_acr_group(event)) { + struct perf_event *sibling, *leader = event->group_leader; + struct pmu *pmu = event->pmu; + bool has_sw_event = false; + int num = 0, idx = 0; + u64 cause_mask = 0; + + /* Not support perf metrics */ + if (is_metric_event(event)) + return -EINVAL; + + /* Not support freq mode */ + if (event->attr.freq) + return -EINVAL; + + /* PDist is not supported */ + if (event->attr.config2 && event->attr.precise_ip > 2) + return -EINVAL; + + /* The reload value cannot exceeds the max period */ + if (event->attr.sample_period > x86_pmu.max_period) + return -EINVAL; + /* + * The counter-constraints of each event cannot be finalized + * unless the whole group is scanned. However, it's hard + * to know whether the event is the last one of the group. + * Recalculate the counter-constraints for each event when + * adding a new event. + * + * The group is traversed twice, which may be optimized later. + * In the first round, + * - Find all events which do reload when other events + * overflow and set the corresponding counter-constraints + * - Add all events, which can cause other events reload, + * in the cause_mask + * - Error out if the number of events exceeds the HW limit + * - The ACR events must be contiguous. + * Error out if there are non-X86 events between ACR events. + * This is not a HW limit, but a SW limit. + * With the assumption, the intel_pmu_acr_late_setup() can + * easily convert the event idx to counter idx without + * traversing the whole event list. + */ + if (!is_x86_event(leader)) + return -EINVAL; + + if (leader->attr.config2) + intel_pmu_set_acr_cntr_constr(leader, &cause_mask, &num); + + if (leader->nr_siblings) { + for_each_sibling_event(sibling, leader) { + if (!is_x86_event(sibling)) { + has_sw_event = true; + continue; + } + if (!sibling->attr.config2) + continue; + if (has_sw_event) + return -EINVAL; + intel_pmu_set_acr_cntr_constr(sibling, &cause_mask, &num); + } + } + if (leader != event && event->attr.config2) { + if (has_sw_event) + return -EINVAL; + intel_pmu_set_acr_cntr_constr(event, &cause_mask, &num); + } + + if (hweight64(cause_mask) > hweight64(hybrid(pmu, acr_cause_mask64)) || + num > hweight64(hybrid(event->pmu, acr_cntr_mask64))) + return -EINVAL; + /* + * In the second round, apply the counter-constraints for + * the events which can cause other events reload. + */ + intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask); + + if (leader->nr_siblings) { + for_each_sibling_event(sibling, leader) + intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask); + } + + if (leader != event) + intel_pmu_set_acr_caused_constr(event, idx, cause_mask); + + leader->hw.flags |= PERF_X86_EVENT_ACR; + } + if ((event->attr.type == PERF_TYPE_HARDWARE) || (event->attr.type == PERF_TYPE_HW_CACHE)) return 0; @@ -6061,6 +6259,21 @@ td_is_visible(struct kobject *kobj, struct attribute *attr, int i) return attr->mode; } +PMU_FORMAT_ATTR(acr_mask, "config2:0-63"); + +static struct attribute *format_acr_attrs[] = { + &format_attr_acr_mask.attr, + NULL +}; + +static umode_t +acr_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + struct device *dev = kobj_to_dev(kobj); + + return intel_pmu_has_acr(dev_get_drvdata(dev)) ? attr->mode : 0; +} + static struct attribute_group group_events_td = { .name = "events", .is_visible = td_is_visible, @@ -6103,6 +6316,12 @@ static struct attribute_group group_format_evtsel_ext = { .is_visible = evtsel_ext_is_visible, }; +static struct attribute_group group_format_acr = { + .name = "format", + .attrs = format_acr_attrs, + .is_visible = acr_is_visible, +}; + static struct attribute_group group_default = { .attrs = intel_pmu_attrs, .is_visible = default_is_visible, @@ -6117,6 +6336,7 @@ static const struct attribute_group *attr_update[] = { &group_format_extra, &group_format_extra_skl, &group_format_evtsel_ext, + &group_format_acr, &group_default, NULL, }; @@ -6401,6 +6621,7 @@ static const struct attribute_group *hybrid_attr_update[] = { &group_caps_lbr, &hybrid_group_format_extra, &group_format_evtsel_ext, + &group_format_acr, &group_default, &hybrid_group_cpus, NULL, @@ -6593,6 +6814,7 @@ static __always_inline void intel_pmu_init_skt(struct pmu *pmu) intel_pmu_init_grt(pmu); hybrid(pmu, event_constraints) = intel_skt_event_constraints; hybrid(pmu, extra_regs) = intel_cmt_extra_regs; + static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr); } __init int intel_pmu_init(void) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ab9af2e4da1b..46bbb503aca1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -120,6 +120,11 @@ static inline bool is_pebs_counter_event_group(struct perf_event *event) return event->group_leader->hw.flags & PERF_X86_EVENT_PEBS_CNTR; } +static inline bool is_acr_event_group(struct perf_event *event) +{ + return event->group_leader->hw.flags & PERF_X86_EVENT_ACR; +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ @@ -287,6 +292,10 @@ struct cpu_hw_events { u64 fixed_ctrl_val; u64 active_fixed_ctrl_val; + /* Intel ACR configuration */ + u64 acr_cfg_b[X86_PMC_IDX_MAX]; + u64 acr_cfg_c[X86_PMC_IDX_MAX]; + /* * Intel LBR bits */ @@ -1103,6 +1112,7 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\ .pmu_type = _pmu, \ } +int is_x86_event(struct perf_event *event); struct pmu *x86_get_pmu(unsigned int cpu); extern struct x86_pmu x86_pmu __read_mostly; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e6134ef2263d..53da787b9326 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -594,7 +594,11 @@ /* V6 PMON MSR range */ #define MSR_IA32_PMC_V6_GP0_CTR 0x1900 #define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_GP0_CFG_B 0x1902 +#define MSR_IA32_PMC_V6_GP0_CFG_C 0x1903 #define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_FX0_CFG_B 0x1982 +#define MSR_IA32_PMC_V6_FX0_CFG_C 0x1983 #define MSR_IA32_PMC_V6_STEP 4 /* KeyID partitioning between MKTME and TDX */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5c547329cf02..947ad12dfdbe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -157,6 +157,7 @@ struct hw_perf_event { union { struct { /* hardware */ u64 config; + u64 config1; u64 last_tag; u64 dyn_constraint; unsigned long config_base;