diff --git a/Documentation/arch/arm64/perf.rst b/Documentation/arch/arm64/perf.rst index 1f87b57c233240965ecbe98698467718fe876dba..997fd716b82f7681f8bd4cc0daee05d81770b5aa 100644 --- a/Documentation/arch/arm64/perf.rst +++ b/Documentation/arch/arm64/perf.rst @@ -164,3 +164,75 @@ and should be used to mask the upper bits as needed. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/arch/arm64/tests/user-events.c .. _tools/lib/perf/tests/test-evsel.c: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/lib/perf/tests/test-evsel.c + +Event Counting Threshold +========================================== + +Overview +-------- + +FEAT_PMUv3_TH (Armv8.8) permits a PMU counter to increment only on +events whose count meets a specified threshold condition. For example if +threshold_compare is set to 2 ('Greater than or equal'), and the +threshold is set to 2, then the PMU counter will now only increment by +when an event would have previously incremented the PMU counter by 2 or +more on a single processor cycle. + +To increment by 1 after passing the threshold condition instead of the +number of events on that cycle, add the 'threshold_count' option to the +commandline. + +How-to +------ + +These are the parameters for controlling the feature: + +.. list-table:: + :header-rows: 1 + + * - Parameter + - Description + * - threshold + - Value to threshold the event by. A value of 0 means that + thresholding is disabled and the other parameters have no effect. + * - threshold_compare + - | Comparison function to use, with the following values supported: + | + | 0: Not-equal + | 1: Equals + | 2: Greater-than-or-equal + | 3: Less-than + * - threshold_count + - If this is set, count by 1 after passing the threshold condition + instead of the value of the event on this cycle. + +The threshold, threshold_compare and threshold_count values can be +provided per event, for example: + +.. code-block:: sh + + perf stat -e stall_slot/threshold=2,threshold_compare=2/ \ + -e dtlb_walk/threshold=10,threshold_compare=3,threshold_count/ + +In this example the stall_slot event will count by 2 or more on every +cycle where 2 or more stalls happen. And dtlb_walk will count by 1 on +every cycle where the number of dtlb walks were less than 10. + +The maximum supported threshold value can be read from the caps of each +PMU, for example: + +.. code-block:: sh + + cat /sys/bus/event_source/devices/armv8_pmuv3/caps/threshold_max + + 0x000000ff + +If a value higher than this is given, then opening the event will result +in an error. The highest possible maximum is 4095, as the config field +for threshold is limited to 12 bits, and the Perf tool will refuse to +parse higher values. + +If the PMU doesn't support FEAT_PMUv3_TH, then threshold_max will read +0, and attempting to set a threshold value will also result in an error. +threshold_max will also read as 0 on aarch32 guests, even if the host +is running on hardware with the feature. diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index eb2190477da10ae8631efee2d647c9fc9c76081d..4e115076d3235d1e956fa1f0dd28cedc37a5c504 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -1072,8 +1072,10 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event, { unsigned long config_base = 0; - if (attr->exclude_idle) - return -EPERM; + if (attr->exclude_idle) { + pr_debug("ARM performance counters do not support mode exclusion\n"); + return -EOPNOTSUPP; + } if (attr->exclude_user) config_base |= ARMV7_EXCLUDE_USER; if (attr->exclude_kernel) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 333c65ced84927e6a50cc1eb600312b773072a19..a84c992126d7ba013c1c64e2672cebb2e96d4fb0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -874,8 +874,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) - kvm_pmu_handle_pmcr(vcpu, - __vcpu_sys_reg(vcpu, PMCR_EL0)); + kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu)) kvm_vcpu_pmu_restore_guest(vcpu); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 6b066e04dc5dfe506572338cc3f1008c5f3263d6..fb3398f9bf0e468e9efb792b582d524e40718b38 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -60,6 +60,23 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm) return __kvm_pmu_event_mask(pmuver); } +u64 kvm_pmu_evtyper_mask(struct kvm *kvm) +{ + u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 | + kvm_pmu_event_mask(kvm); + u64 pfr0 = IDREG(kvm, SYS_ID_AA64PFR0_EL1); + + if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL2, pfr0)) + mask |= ARMV8_PMU_INCLUDE_EL2; + + if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL3, pfr0)) + mask |= ARMV8_PMU_EXCLUDE_NS_EL0 | + ARMV8_PMU_EXCLUDE_NS_EL1 | + ARMV8_PMU_EXCLUDE_EL3; + + return mask; +} + /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context @@ -72,7 +89,7 @@ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { - u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0); + u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc)); return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); @@ -250,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { - u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT; + u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu)); - val &= ARMV8_PMU_PMCR_N_MASK; if (val == 0) return BIT(ARMV8_PMU_CYCLE_IDX); else @@ -272,7 +288,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!kvm_vcpu_has_pmu(vcpu)) return; - if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) + if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -324,7 +340,7 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) { u64 reg = 0; - if ((__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) { + if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) { reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); @@ -426,7 +442,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, { int i; - if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) + if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) return; /* Weed out disabled counters */ @@ -569,7 +585,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); - return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) && + return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) && (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)); } @@ -584,6 +600,7 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) struct perf_event *event; struct perf_event_attr attr; u64 eventsel, reg, data; + bool p, u, nsk, nsu; reg = counter_index_to_evtreg(pmc->idx); data = __vcpu_sys_reg(vcpu, reg); @@ -610,13 +627,18 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; + p = data & ARMV8_PMU_EXCLUDE_EL1; + u = data & ARMV8_PMU_EXCLUDE_EL0; + nsk = data & ARMV8_PMU_EXCLUDE_NS_EL1; + nsu = data & ARMV8_PMU_EXCLUDE_NS_EL0; + memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; attr.disabled = !kvm_pmu_counter_is_enabled(pmc); - attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0; - attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0; + attr.exclude_user = (u != nsu); + attr.exclude_kernel = (p != nsk); attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; @@ -657,18 +679,13 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); - u64 reg, mask; + u64 reg; if (!kvm_vcpu_has_pmu(vcpu)) return; - mask = ARMV8_PMU_EVTYPE_MASK; - mask &= ~ARMV8_PMU_EVTYPE_EVENT; - mask |= kvm_pmu_event_mask(vcpu->kvm); - reg = counter_index_to_evtreg(pmc->idx); - - __vcpu_sys_reg(vcpu, reg) = data & mask; + __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); kvm_pmu_create_perf_event(pmc); } @@ -1072,3 +1089,12 @@ u8 kvm_arm_pmu_get_pmuver_limit(void) ID_AA64DFR0_EL1_PMUVer_V3P5); return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); } + +/** + * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU + * @vcpu: The vcpu pointer + */ +u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) +{ + return __vcpu_sys_reg(vcpu, PMCR_EL0); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index dc8663759b0e1e3c45cd1b401f38f4d4ac31b70e..e4952fe3c5a08e6d9bb4d95d9b1852f280dd82ae 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -742,8 +742,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) if (!kvm_arm_support_pmu_v3()) return 0; - n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT; - n &= ARMV8_PMU_PMCR_N_MASK; + n = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); if (n) mask |= GENMASK(n - 1, 0); @@ -763,8 +762,12 @@ static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { + /* This thing will UNDEF, who cares about the reset value? */ + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + reset_unknown(vcpu, r); - __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK; + __vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm); return __vcpu_sys_reg(vcpu, r->reg); } @@ -786,7 +789,7 @@ static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) return 0; /* Only preserve PMCR_EL0.N, and reset the rest to 0 */ - pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); + pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N; if (!kvm_supports_32bit_el0()) pmcr |= ARMV8_PMU_PMCR_LC; @@ -839,7 +842,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Only update writeable bits of PMCR (continuing into * kvm_pmu_handle_pmcr() as well) */ - val = __vcpu_sys_reg(vcpu, PMCR_EL0); + val = kvm_vcpu_read_pmcr(vcpu); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0()) @@ -847,7 +850,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_handle_pmcr(vcpu, val); } else { /* PMCR.P & PMCR.C are RAZ */ - val = __vcpu_sys_reg(vcpu, PMCR_EL0) + val = kvm_vcpu_read_pmcr(vcpu) & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C); p->regval = val; } @@ -896,8 +899,8 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx) { u64 pmcr, val; - pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); - val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; + pmcr = kvm_vcpu_read_pmcr(vcpu); + val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) { kvm_inject_undefined(vcpu); return false; @@ -1005,7 +1008,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_set_counter_event_type(vcpu, p->regval, idx); kvm_vcpu_pmu_restore_guest(vcpu); } else { - p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK; + p->regval = __vcpu_sys_reg(vcpu, reg); } return true; diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c index cd2de44b61b91fddf172aef24efb602baf1486d5..f322e5ca1114b9be8b7cac6c244c336b27bd72af 100644 --- a/drivers/perf/apple_m1_cpu_pmu.c +++ b/drivers/perf/apple_m1_cpu_pmu.c @@ -524,8 +524,10 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event, { unsigned long config_base = 0; - if (!attr->exclude_guest) - return -EINVAL; + if (!attr->exclude_guest) { + pr_debug("ARM performance counters do not support mode exclusion\n"); + return -EOPNOTSUPP; + } if (!attr->exclude_kernel) config_base |= M1_PMU_CFG_COUNT_KERNEL; if (!attr->exclude_user) diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index d712a19e47ac15087b628fdec0939e85dd57d691..2ce65b440e8565c1fac06e151ab596b744bdabde 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -445,7 +445,7 @@ __hw_perf_event_init(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - int mapping; + int mapping, ret; hwc->flags = 0; mapping = armpmu->map_event(event); @@ -470,11 +470,10 @@ __hw_perf_event_init(struct perf_event *event) /* * Check whether we need to exclude the counter from certain modes. */ - if (armpmu->set_event_filter && - armpmu->set_event_filter(hwc, &event->attr)) { - pr_debug("ARM performance counters do not support " - "mode exclusion\n"); - return -EOPNOTSUPP; + if (armpmu->set_event_filter) { + ret = armpmu->set_event_filter(hwc, &event->attr); + if (ret) + return ret; } /* diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 0e8f54168cb6417904a73907fd4f0b8bbe6f3a53..3fe3ecb5a66b102d99604c12fb23b2caa7e958d3 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include @@ -298,26 +299,66 @@ static const struct attribute_group armv8_pmuv3_events_attr_group = { .is_visible = armv8pmu_event_attr_is_visible, }; -PMU_FORMAT_ATTR(event, "config:0-15"); -PMU_FORMAT_ATTR(long, "config1:0"); -PMU_FORMAT_ATTR(rdpmc, "config1:1"); +/* User ABI */ +#define ATTR_CFG_FLD_event_CFG config +#define ATTR_CFG_FLD_event_LO 0 +#define ATTR_CFG_FLD_event_HI 15 +#define ATTR_CFG_FLD_long_CFG config1 +#define ATTR_CFG_FLD_long_LO 0 +#define ATTR_CFG_FLD_long_HI 0 +#define ATTR_CFG_FLD_rdpmc_CFG config1 +#define ATTR_CFG_FLD_rdpmc_LO 1 +#define ATTR_CFG_FLD_rdpmc_HI 1 +#define ATTR_CFG_FLD_threshold_count_CFG config1 /* PMEVTYPER.TC[0] */ +#define ATTR_CFG_FLD_threshold_count_LO 2 +#define ATTR_CFG_FLD_threshold_count_HI 2 +#define ATTR_CFG_FLD_threshold_compare_CFG config1 /* PMEVTYPER.TC[2:1] */ +#define ATTR_CFG_FLD_threshold_compare_LO 3 +#define ATTR_CFG_FLD_threshold_compare_HI 4 +#define ATTR_CFG_FLD_threshold_CFG config1 /* PMEVTYPER.TH */ +#define ATTR_CFG_FLD_threshold_LO 5 +#define ATTR_CFG_FLD_threshold_HI 16 + +GEN_PMU_FORMAT_ATTR(event); +GEN_PMU_FORMAT_ATTR(long); +GEN_PMU_FORMAT_ATTR(rdpmc); +GEN_PMU_FORMAT_ATTR(threshold_count); +GEN_PMU_FORMAT_ATTR(threshold_compare); +GEN_PMU_FORMAT_ATTR(threshold); static int sysctl_perf_user_access __read_mostly; -static inline bool armv8pmu_event_is_64bit(struct perf_event *event) +static bool armv8pmu_event_is_64bit(struct perf_event *event) { - return event->attr.config1 & 0x1; + return ATTR_CFG_GET_FLD(&event->attr, long); } -static inline bool armv8pmu_event_want_user_access(struct perf_event *event) +static bool armv8pmu_event_want_user_access(struct perf_event *event) { - return event->attr.config1 & 0x2; + return ATTR_CFG_GET_FLD(&event->attr, rdpmc); +} + +static u8 armv8pmu_event_threshold_control(struct perf_event_attr *attr) +{ + u8 th_compare = ATTR_CFG_GET_FLD(attr, threshold_compare); + u8 th_count = ATTR_CFG_GET_FLD(attr, threshold_count); + + /* + * The count bit is always the bottom bit of the full control field, and + * the comparison is the upper two bits, but it's not explicitly + * labelled in the Arm ARM. For the Perf interface we split it into two + * fields, so reconstruct it here. + */ + return (th_compare << 1) | th_count; } static struct attribute *armv8_pmuv3_format_attrs[] = { &format_attr_event.attr, &format_attr_long.attr, &format_attr_rdpmc.attr, + &format_attr_threshold.attr, + &format_attr_threshold_compare.attr, + &format_attr_threshold_count.attr, NULL, }; @@ -331,7 +372,7 @@ static ssize_t slots_show(struct device *dev, struct device_attribute *attr, { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK; + u32 slots = FIELD_GET(ARMV8_PMU_SLOTS, cpu_pmu->reg_pmmir); return sysfs_emit(page, "0x%08x\n", slots); } @@ -343,8 +384,7 @@ static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr, { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT) - & ARMV8_PMU_BUS_SLOTS_MASK; + u32 bus_slots = FIELD_GET(ARMV8_PMU_BUS_SLOTS, cpu_pmu->reg_pmmir); return sysfs_emit(page, "0x%08x\n", bus_slots); } @@ -356,8 +396,7 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr, { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT) - & ARMV8_PMU_BUS_WIDTH_MASK; + u32 bus_width = FIELD_GET(ARMV8_PMU_BUS_WIDTH, cpu_pmu->reg_pmmir); u32 val = 0; /* Encoded as Log2(number of bytes), plus one */ @@ -369,10 +408,38 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(bus_width); +static u32 threshold_max(struct arm_pmu *cpu_pmu) +{ + /* + * PMMIR.THWIDTH is readable and non-zero on aarch32, but it would be + * impossible to write the threshold in the upper 32 bits of PMEVTYPER. + */ + if (IS_ENABLED(CONFIG_ARM)) + return 0; + + /* + * The largest value that can be written to PMEVTYPER_EL0.TH is + * (2 ^ PMMIR.THWIDTH) - 1. + */ + return (1 << FIELD_GET(ARMV8_PMU_THWIDTH, cpu_pmu->reg_pmmir)) - 1; +} + +static ssize_t threshold_max_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct pmu *pmu = dev_get_drvdata(dev); + struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); + + return sysfs_emit(page, "0x%08x\n", threshold_max(cpu_pmu)); +} + +static DEVICE_ATTR_RO(threshold_max); + static struct attribute *armv8_pmuv3_caps_attrs[] = { &dev_attr_slots.attr, &dev_attr_bus_slots.attr, &dev_attr_bus_width.attr, + &dev_attr_threshold_max.attr, NULL, }; @@ -401,7 +468,7 @@ static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu) return (IS_ENABLED(CONFIG_ARM64) && is_pmuv3p5(cpu_pmu->pmuver)); } -static inline bool armv8pmu_event_has_user_read(struct perf_event *event) +static bool armv8pmu_event_has_user_read(struct perf_event *event) { return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT; } @@ -411,7 +478,7 @@ static inline bool armv8pmu_event_has_user_read(struct perf_event *event) * except when we have allocated the 64bit cycle counter (for CPU * cycles event) or when user space counter access is enabled. */ -static inline bool armv8pmu_event_is_chained(struct perf_event *event) +static bool armv8pmu_event_is_chained(struct perf_event *event) { int idx = event->hw.idx; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); @@ -432,36 +499,36 @@ static inline bool armv8pmu_event_is_chained(struct perf_event *event) #define ARMV8_IDX_TO_COUNTER(x) \ (((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK) -static inline u64 armv8pmu_pmcr_read(void) +static u64 armv8pmu_pmcr_read(void) { return read_pmcr(); } -static inline void armv8pmu_pmcr_write(u64 val) +static void armv8pmu_pmcr_write(u64 val) { val &= ARMV8_PMU_PMCR_MASK; isb(); write_pmcr(val); } -static inline int armv8pmu_has_overflowed(u32 pmovsr) +static int armv8pmu_has_overflowed(u32 pmovsr) { return pmovsr & ARMV8_PMU_OVERFLOWED_MASK; } -static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) +static int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) { return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx)); } -static inline u64 armv8pmu_read_evcntr(int idx) +static u64 armv8pmu_read_evcntr(int idx) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); return read_pmevcntrn(counter); } -static inline u64 armv8pmu_read_hw_counter(struct perf_event *event) +static u64 armv8pmu_read_hw_counter(struct perf_event *event) { int idx = event->hw.idx; u64 val = armv8pmu_read_evcntr(idx); @@ -523,14 +590,14 @@ static u64 armv8pmu_read_counter(struct perf_event *event) return armv8pmu_unbias_long_counter(event, value); } -static inline void armv8pmu_write_evcntr(int idx, u64 value) +static void armv8pmu_write_evcntr(int idx, u64 value) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); write_pmevcntrn(counter, value); } -static inline void armv8pmu_write_hw_counter(struct perf_event *event, +static void armv8pmu_write_hw_counter(struct perf_event *event, u64 value) { int idx = event->hw.idx; @@ -556,15 +623,22 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value) armv8pmu_write_hw_counter(event, value); } -static inline void armv8pmu_write_evtype(int idx, u32 val) +static void armv8pmu_write_evtype(int idx, unsigned long val) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); + unsigned long mask = ARMV8_PMU_EVTYPE_EVENT | + ARMV8_PMU_INCLUDE_EL2 | + ARMV8_PMU_EXCLUDE_EL0 | + ARMV8_PMU_EXCLUDE_EL1; - val &= ARMV8_PMU_EVTYPE_MASK; + if (IS_ENABLED(CONFIG_ARM64)) + mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH; + + val &= mask; write_pmevtypern(counter, val); } -static inline void armv8pmu_write_event_type(struct perf_event *event) +static void armv8pmu_write_event_type(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; @@ -598,7 +672,7 @@ static u32 armv8pmu_event_cnten_mask(struct perf_event *event) return mask; } -static inline void armv8pmu_enable_counter(u32 mask) +static void armv8pmu_enable_counter(u32 mask) { /* * Make sure event configuration register writes are visible before we @@ -608,7 +682,7 @@ static inline void armv8pmu_enable_counter(u32 mask) write_pmcntenset(mask); } -static inline void armv8pmu_enable_event_counter(struct perf_event *event) +static void armv8pmu_enable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; u32 mask = armv8pmu_event_cnten_mask(event); @@ -620,7 +694,7 @@ static inline void armv8pmu_enable_event_counter(struct perf_event *event) armv8pmu_enable_counter(mask); } -static inline void armv8pmu_disable_counter(u32 mask) +static void armv8pmu_disable_counter(u32 mask) { write_pmcntenclr(mask); /* @@ -630,7 +704,7 @@ static inline void armv8pmu_disable_counter(u32 mask) isb(); } -static inline void armv8pmu_disable_event_counter(struct perf_event *event) +static void armv8pmu_disable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; u32 mask = armv8pmu_event_cnten_mask(event); @@ -642,18 +716,18 @@ static inline void armv8pmu_disable_event_counter(struct perf_event *event) armv8pmu_disable_counter(mask); } -static inline void armv8pmu_enable_intens(u32 mask) +static void armv8pmu_enable_intens(u32 mask) { write_pmintenset(mask); } -static inline void armv8pmu_enable_event_irq(struct perf_event *event) +static void armv8pmu_enable_event_irq(struct perf_event *event) { u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); armv8pmu_enable_intens(BIT(counter)); } -static inline void armv8pmu_disable_intens(u32 mask) +static void armv8pmu_disable_intens(u32 mask) { write_pmintenclr(mask); isb(); @@ -662,13 +736,13 @@ static inline void armv8pmu_disable_intens(u32 mask) isb(); } -static inline void armv8pmu_disable_event_irq(struct perf_event *event) +static void armv8pmu_disable_event_irq(struct perf_event *event) { u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); armv8pmu_disable_intens(BIT(counter)); } -static inline u32 armv8pmu_getreset_flags(void) +static u32 armv8pmu_getreset_flags(void) { u32 value; @@ -676,7 +750,7 @@ static inline u32 armv8pmu_getreset_flags(void) value = read_pmovsclr(); /* Write to clear flags */ - value &= ARMV8_PMU_OVSR_MASK; + value &= ARMV8_PMU_OVERFLOWED_MASK; write_pmovsclr(value); return value; @@ -918,9 +992,15 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, struct perf_event_attr *attr) { unsigned long config_base = 0; - - if (attr->exclude_idle) - return -EPERM; + struct perf_event *perf_event = container_of(attr, struct perf_event, + attr); + struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); + u32 th; + + if (attr->exclude_idle) { + pr_debug("ARM performance counters do not support mode exclusion\n"); + return -EOPNOTSUPP; + } /* * If we're running in hyp mode, then we *are* the hypervisor. @@ -949,6 +1029,22 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, if (attr->exclude_user) config_base |= ARMV8_PMU_EXCLUDE_EL0; + /* + * If FEAT_PMUv3_TH isn't implemented, then THWIDTH (threshold_max) will + * be 0 and will also trigger this check, preventing it from being used. + */ + th = ATTR_CFG_GET_FLD(attr, threshold); + if (th > threshold_max(cpu_pmu)) { + pr_debug("PMU event threshold exceeds max value\n"); + return -EINVAL; + } + + if (IS_ENABLED(CONFIG_ARM64) && th) { + config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TH, th); + config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TC, + armv8pmu_event_threshold_control(attr)); + } + /* * Install the filter into config_base as this is used to * construct the event type. @@ -1111,8 +1207,7 @@ static void __armv8pmu_probe_pmu(void *info) probe->present = true; /* Read the nb of CNTx counters supported from PMNC */ - cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT) - & ARMV8_PMU_PMCR_N_MASK; + cpu_pmu->num_events = FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read()); /* Add the CPU cycles counter */ cpu_pmu->num_events += 1; @@ -1130,7 +1225,7 @@ static void __armv8pmu_probe_pmu(void *info) pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); /* store PMMIR register for sysfs */ - if (is_pmuv3p4(pmuver) && (pmceid_raw[1] & BIT(31))) + if (is_pmuv3p4(pmuver)) cpu_pmu->reg_pmmir = read_pmmir(); else cpu_pmu->reg_pmmir = 0; @@ -1191,10 +1286,7 @@ static void armv8_pmu_register_sysctl_table(void) } static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event), - const struct attribute_group *events, - const struct attribute_group *format, - const struct attribute_group *caps) + int (*map_event)(struct perf_event *event)) { int ret = armv8pmu_probe_pmu(cpu_pmu); if (ret) @@ -1216,27 +1308,23 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, cpu_pmu->name = name; cpu_pmu->map_event = map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ? - events : &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ? - format : &armv8_pmuv3_format_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ? - caps : &armv8_pmuv3_caps_attr_group; - + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &armv8_pmuv3_format_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = &armv8_pmuv3_caps_attr_group; armv8_pmu_register_sysctl_table(); return 0; } -static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event)) -{ - return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL); +#define PMUV3_INIT_SIMPLE(name) \ +static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ +{ \ + return armv8_pmu_init(cpu_pmu, #name, armv8_pmuv3_map_event); \ } -#define PMUV3_INIT_SIMPLE(name) \ +#define PMUV3_INIT_MAP_EVENT(name, map_event) \ static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ { \ - return armv8_pmu_init_nogroups(cpu_pmu, #name, armv8_pmuv3_map_event);\ + return armv8_pmu_init(cpu_pmu, #name, map_event); \ } PMUV3_INIT_SIMPLE(armv8_pmuv3) @@ -1265,58 +1353,24 @@ PMUV3_INIT_SIMPLE(armv8_neoverse_v1) PMUV3_INIT_SIMPLE(armv8_nvidia_carmel) PMUV3_INIT_SIMPLE(armv8_nvidia_denver) -static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35", - armv8_a53_map_event); -} - -static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53", - armv8_a53_map_event); -} - -static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57", - armv8_a57_map_event); -} - -static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72", - armv8_a57_map_event); -} - -static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73", - armv8_a73_map_event); -} - -static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder", - armv8_thunder_map_event); -} - -static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan", - armv8_vulcan_map_event); -} +PMUV3_INIT_MAP_EVENT(armv8_cortex_a35, armv8_a53_map_event) +PMUV3_INIT_MAP_EVENT(armv8_cortex_a53, armv8_a53_map_event) +PMUV3_INIT_MAP_EVENT(armv8_cortex_a57, armv8_a57_map_event) +PMUV3_INIT_MAP_EVENT(armv8_cortex_a72, armv8_a57_map_event) +PMUV3_INIT_MAP_EVENT(armv8_cortex_a73, armv8_a73_map_event) +PMUV3_INIT_MAP_EVENT(armv8_cavium_thunder, armv8_thunder_map_event) +PMUV3_INIT_MAP_EVENT(armv8_brcm_vulcan, armv8_vulcan_map_event) static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_pmu_init}, {.compatible = "arm,cortex-a34-pmu", .data = armv8_cortex_a34_pmu_init}, - {.compatible = "arm,cortex-a35-pmu", .data = armv8_a35_pmu_init}, - {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init}, + {.compatible = "arm,cortex-a35-pmu", .data = armv8_cortex_a35_pmu_init}, + {.compatible = "arm,cortex-a53-pmu", .data = armv8_cortex_a53_pmu_init}, {.compatible = "arm,cortex-a55-pmu", .data = armv8_cortex_a55_pmu_init}, - {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, + {.compatible = "arm,cortex-a57-pmu", .data = armv8_cortex_a57_pmu_init}, {.compatible = "arm,cortex-a65-pmu", .data = armv8_cortex_a65_pmu_init}, - {.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init}, - {.compatible = "arm,cortex-a73-pmu", .data = armv8_a73_pmu_init}, + {.compatible = "arm,cortex-a72-pmu", .data = armv8_cortex_a72_pmu_init}, + {.compatible = "arm,cortex-a73-pmu", .data = armv8_cortex_a73_pmu_init}, {.compatible = "arm,cortex-a75-pmu", .data = armv8_cortex_a75_pmu_init}, {.compatible = "arm,cortex-a76-pmu", .data = armv8_cortex_a76_pmu_init}, {.compatible = "arm,cortex-a77-pmu", .data = armv8_cortex_a77_pmu_init}, @@ -1334,8 +1388,8 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,neoverse-n1-pmu", .data = armv8_neoverse_n1_pmu_init}, {.compatible = "arm,neoverse-n2-pmu", .data = armv9_neoverse_n2_pmu_init}, {.compatible = "arm,neoverse-v1-pmu", .data = armv8_neoverse_v1_pmu_init}, - {.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init}, - {.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init}, + {.compatible = "cavium,thunder-pmu", .data = armv8_cavium_thunder_pmu_init}, + {.compatible = "brcm,vulcan-pmu", .data = armv8_brcm_vulcan_pmu_init}, {.compatible = "nvidia,carmel-pmu", .data = armv8_nvidia_carmel_pmu_init}, {.compatible = "nvidia,denver-pmu", .data = armv8_nvidia_denver_pmu_init}, {}, diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index d2b0cbf0e0c41e38b187239298ce1a75f4f0384f..b622d75d8c9e43089701a23166fdbcd8d490e34b 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -206,28 +206,6 @@ static const struct attribute_group arm_spe_pmu_cap_group = { #define ATTR_CFG_FLD_inv_event_filter_LO 0 #define ATTR_CFG_FLD_inv_event_filter_HI 63 -/* Why does everything I do descend into this? */ -#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ - (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi - -#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ - __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) - -#define GEN_PMU_FORMAT_ATTR(name) \ - PMU_FORMAT_ATTR(name, \ - _GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG, \ - ATTR_CFG_FLD_##name##_LO, \ - ATTR_CFG_FLD_##name##_HI)) - -#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi) \ - ((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0)) - -#define ATTR_CFG_GET_FLD(attr, name) \ - _ATTR_CFG_GET_FLD(attr, \ - ATTR_CFG_FLD_##name##_CFG, \ - ATTR_CFG_FLD_##name##_LO, \ - ATTR_CFG_FLD_##name##_HI) - GEN_PMU_FORMAT_ATTR(ts_enable); GEN_PMU_FORMAT_ATTR(pa_enable); GEN_PMU_FORMAT_ATTR(pct_enable); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index c4aabbf002f7cf06cd02ec1fa23685490b15695d..467d60c53153e983992341461b38fa423c8d80f6 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -101,7 +101,9 @@ void kvm_vcpu_pmu_resync_el0(void); }) u8 kvm_arm_pmu_get_pmuver_limit(void); +u64 kvm_pmu_evtyper_mask(struct kvm *kvm); +u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu); #else struct kvm_pmu { }; @@ -172,8 +174,17 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void) { return 0; } +static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm) +{ + return 0; +} static inline void kvm_vcpu_pmu_resync_el0(void) {} +static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) +{ + return 0; +} + #endif #endif diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 143fbc10ecfe032e593e040514f7225bf316a2d1..337f01674b38b2a5c3a9a9da8df24f10cd09514f 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -189,4 +189,26 @@ void armpmu_free_irq(int irq, int cpu); #define ARMV8_SPE_PDEV_NAME "arm,spe-v1" #define ARMV8_TRBE_PDEV_NAME "arm,trbe" +/* Why does everything I do descend into this? */ +#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ + (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi + +#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ + __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) + +#define GEN_PMU_FORMAT_ATTR(name) \ + PMU_FORMAT_ATTR(name, \ + _GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG, \ + ATTR_CFG_FLD_##name##_LO, \ + ATTR_CFG_FLD_##name##_HI)) + +#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi) \ + ((((attr)->cfg) >> lo) & GENMASK_ULL(hi - lo, 0)) + +#define ATTR_CFG_GET_FLD(attr, name) \ + _ATTR_CFG_GET_FLD(attr, \ + ATTR_CFG_FLD_##name##_CFG, \ + ATTR_CFG_FLD_##name##_LO, \ + ATTR_CFG_FLD_##name##_HI) + #endif /* __ARM_PMU_H__ */ diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index e3899bd77f5cc5860e8c3182bd3797f1ca0002e7..46377e134d67cba65d7f2aa59dc4127af71381de 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -215,45 +215,54 @@ #define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ #define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ #define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */ -#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ -#define ARMV8_PMU_PMCR_N_MASK 0x1f -#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */ +#define ARMV8_PMU_PMCR_N GENMASK(15, 11) /* Number of counters supported */ +/* Mask for writable bits */ +#define ARMV8_PMU_PMCR_MASK (ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \ + ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \ + ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \ + ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP) /* * PMOVSR: counters overflow flag status reg */ -#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */ -#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK +#define ARMV8_PMU_OVSR_P GENMASK(30, 0) +#define ARMV8_PMU_OVSR_C BIT(31) +/* Mask for writable bits is both P and C fields */ +#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C) /* * PMXEVTYPER: Event selection reg */ -#define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ -#define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ +#define ARMV8_PMU_EVTYPE_EVENT GENMASK(15, 0) /* Mask for EVENT bits */ +#define ARMV8_PMU_EVTYPE_TH GENMASK_ULL(43, 32) /* arm64 only */ +#define ARMV8_PMU_EVTYPE_TC GENMASK_ULL(63, 61) /* arm64 only */ /* * Event filters for PMUv3 */ -#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) -#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) -#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) +#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) +#define ARMV8_PMU_EXCLUDE_NS_EL1 (1U << 29) +#define ARMV8_PMU_EXCLUDE_NS_EL0 (1U << 28) +#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) +#define ARMV8_PMU_EXCLUDE_EL3 (1U << 26) /* * PMUSERENR: user enable reg */ -#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */ #define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */ #define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ #define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ #define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ +/* Mask for writable bits */ +#define ARMV8_PMU_USERENR_MASK (ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \ + ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER) /* PMMIR_EL1.SLOTS mask */ -#define ARMV8_PMU_SLOTS_MASK 0xff - -#define ARMV8_PMU_BUS_SLOTS_SHIFT 8 -#define ARMV8_PMU_BUS_SLOTS_MASK 0xff -#define ARMV8_PMU_BUS_WIDTH_SHIFT 16 -#define ARMV8_PMU_BUS_WIDTH_MASK 0xf +#define ARMV8_PMU_SLOTS GENMASK(7, 0) +#define ARMV8_PMU_BUS_SLOTS GENMASK(15, 8) +#define ARMV8_PMU_BUS_WIDTH GENMASK(19, 16) +#define ARMV8_PMU_THWIDTH GENMASK(23, 20) /* * This code is really good