From 4788e5b4b2338f85fa42a712a182d8afd65d7c58 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 12 Nov 2013 17:58:50 +0100 Subject: [PATCH] perf/x86: Add Intel RAPL PMU support This patch adds a new uncore PMU to expose the Intel RAPL energy consumption counters. Up to 3 counters, each counting a particular RAPL event are exposed. The RAPL counters are available on Intel SandyBridge, IvyBridge, Haswell. The server skus add a 3rd counter. The following events are available and exposed in sysfs: - power/energy-cores: power consumption of all cores on socket - power/energy-pkg: power consumption of all cores + LLc cache - power/energy-dram: power consumption of DRAM (servers only) For each event both the unit (Joules) and scale (2^-32 J) is exposed in sysfs for use by perf stat and other tools. The files are: /sys/devices/power/events/energy-*.unit /sys/devices/power/events/energy-*.scale The RAPL PMU is uncore by nature and is implemented such that it only works in system-wide mode. Measuring only one CPU per socket is sufficient. The /sys/devices/power/cpumask file can be used by tools to figure out which CPUs to monitor by default. For instance, on a 2-socket system, 2 CPUs (one on each socket) will be shown. All the counters measure in the same unit (exposed via sysfs). The perf_events API exposes all RAPL counters as 64-bit integers counting in unit of 1/2^32 Joules (about 0.23 nJ). User level tools must convert the counts by multiplying them by 2^-32 to obtain Joules. The reason for this is that the kernel avoids doing floating point math whenever possible because it is expensive (user floating-point state must be saved). The method used avoids kernel floating-point usage. There is no loss of precision. Thanks to PeterZ for suggesting this approach. To convert the raw count in Watt: W = C * 2.3 / (1e10 * time) or ldexp(C, -32). RAPL PMU is a new standalone PMU which registers with the perf_event core subsystem. The PMU type (attr->type) is dynamically allocated and is available from /sys/device/power/type. Sampling is not supported by the RAPL PMU. There is no privilege level filtering either. Signed-off-by: Stephane Eranian Reviewed-by: Maria Dimakopoulou Reviewed-by: Andi Kleen Signed-off-by: Peter Zijlstra Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Link: http://lkml.kernel.org/r/1384275531-10892-4-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/perf_event_intel_rapl.c | 591 ++++++++++++++++++++ 2 files changed, 592 insertions(+), 1 deletion(-) create mode 100644 arch/x86/kernel/cpu/perf_event_intel_rapl.c diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 47b56a7e99cb..6359506a19ee 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -36,7 +36,7 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o endif diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c new file mode 100644 index 000000000000..cfcd386b5d89 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -0,0 +1,591 @@ +/* + * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters + * Copyright (C) 2013 Google, Inc., Stephane Eranian + * + * Intel RAPL interface is specified in the IA-32 Manual Vol3b + * section 14.7.1 (September 2013) + * + * RAPL provides more controls than just reporting energy consumption + * however here we only expose the 3 energy consumption free running + * counters (pp0, pkg, dram). + * + * Each of those counters increments in a power unit defined by the + * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules + * but it can vary. + * + * Counter to rapl events mappings: + * + * pp0 counter: consumption of all physical cores (power plane 0) + * event: rapl_energy_cores + * perf code: 0x1 + * + * pkg counter: consumption of the whole processor package + * event: rapl_energy_pkg + * perf code: 0x2 + * + * dram counter: consumption of the dram domain (servers only) + * event: rapl_energy_dram + * perf code: 0x3 + * + * We manage those counters as free running (read-only). They may be + * use simultaneously by other tools, such as turbostat. + * + * The events only support system-wide mode counting. There is no + * sampling support because it does not make sense and is not + * supported by the RAPL hardware. + * + * Because we want to avoid floating-point operations in the kernel, + * the events are all reported in fixed point arithmetic (32.32). + * Tools must adjust the counts to convert them to Watts using + * the duration of the measurement. Tools may use a function such as + * ldexp(raw_count, -32); + */ +#include +#include +#include +#include +#include "perf_event.h" + +/* + * RAPL energy status counters + */ +#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */ +#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */ +#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */ +#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */ +#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */ +#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */ + +/* Clients have PP0, PKG */ +#define RAPL_IDX_CLN (1<config + * any other bit is reserved + */ +#define RAPL_EVENT_MASK 0xFFULL + +#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __rapl_##_var##_show, NULL) + +#define RAPL_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \ + .config = _config, \ +} + +#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ + +struct rapl_pmu { + spinlock_t lock; + int hw_unit; /* 1/2^hw_unit Joule */ + int n_active; /* number of active events */ + struct list_head active_list; + struct pmu *pmu; /* pointer to rapl_pmu_class */ +}; + +static struct pmu rapl_pmu_class; +static cpumask_t rapl_cpu_mask; +static int rapl_cntr_mask; + +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); + +static inline u64 rapl_read_counter(struct perf_event *event) +{ + u64 raw; + rdmsrl(event->hw.event_base, raw); + return raw; +} + +static inline u64 rapl_scale(u64 v) +{ + /* + * scale delta to smallest unit (1/2^32) + * users must then scale back: count * 1/(1e9*2^32) to get Joules + * or use ldexp(count, -32). + * Watts = Joules/Time delta + */ + return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit); +} + +static u64 rapl_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev_raw_count, new_raw_count; + s64 delta, sdelta; + int shift = RAPL_CNTR_WIDTH; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + rdmsrl(event->hw.event_base, new_raw_count); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) { + cpu_relax(); + goto again; + } + + /* + * Now we have the new raw value and have updated the prev + * timestamp already. We can now calculate the elapsed delta + * (event-)time and add that to the generic event. + * + * Careful, not all hw sign-extends above the physical width + * of the count. + */ + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + sdelta = rapl_scale(delta); + + local64_add(sdelta, &event->count); + + return new_raw_count; +} + +static void __rapl_pmu_event_start(struct rapl_pmu *pmu, + struct perf_event *event) +{ + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + + list_add_tail(&event->active_entry, &pmu->active_list); + + local64_set(&event->hw.prev_count, rapl_read_counter(event)); + + pmu->n_active++; +} + +static void rapl_pmu_event_start(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + __rapl_pmu_event_start(pmu, event); + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static void rapl_pmu_event_stop(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + /* mark event as deactivated and stopped */ + if (!(hwc->state & PERF_HES_STOPPED)) { + WARN_ON_ONCE(pmu->n_active <= 0); + pmu->n_active--; + + list_del(&event->active_entry); + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + } + + /* check if update of sw counter is necessary */ + if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + rapl_event_update(event); + hwc->state |= PERF_HES_UPTODATE; + } + + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static int rapl_pmu_event_add(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (mode & PERF_EF_START) + __rapl_pmu_event_start(pmu, event); + + spin_unlock_irqrestore(&pmu->lock, flags); + + return 0; +} + +static void rapl_pmu_event_del(struct perf_event *event, int flags) +{ + rapl_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int rapl_pmu_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config & RAPL_EVENT_MASK; + int bit, msr, ret = 0; + + /* only look at RAPL events */ + if (event->attr.type != rapl_pmu_class.type) + return -ENOENT; + + /* check only supported bits are set */ + if (event->attr.config & ~RAPL_EVENT_MASK) + return -EINVAL; + + /* + * check event is known (determines counter) + */ + switch (cfg) { + case INTEL_RAPL_PP0: + bit = RAPL_IDX_PP0_NRG_STAT; + msr = MSR_PP0_ENERGY_STATUS; + break; + case INTEL_RAPL_PKG: + bit = RAPL_IDX_PKG_NRG_STAT; + msr = MSR_PKG_ENERGY_STATUS; + break; + case INTEL_RAPL_RAM: + bit = RAPL_IDX_RAM_NRG_STAT; + msr = MSR_DRAM_ENERGY_STATUS; + break; + default: + return -EINVAL; + } + /* check event supported */ + if (!(rapl_cntr_mask & (1 << bit))) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* must be done before validate_group */ + event->hw.event_base = msr; + event->hw.config = cfg; + event->hw.idx = bit; + + return ret; +} + +static void rapl_pmu_event_read(struct perf_event *event) +{ + rapl_event_update(event); +} + +static ssize_t rapl_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); + +static struct attribute *rapl_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_attr_group = { + .attrs = rapl_pmu_attrs, +}; + +EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); +EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); +EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); + +EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); +EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); +EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); + +/* + * we compute in 0.23 nJ increments regardless of MSR + */ +EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); + +static struct attribute *rapl_events_srv_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_ram), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_ram_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_ram_scale), + NULL, +}; + +static struct attribute *rapl_events_cln_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + NULL, +}; + +static struct attribute_group rapl_pmu_events_group = { + .name = "events", + .attrs = NULL, /* patched at runtime */ +}; + +DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +static struct attribute *rapl_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_format_group = { + .name = "format", + .attrs = rapl_formats_attr, +}; + +const struct attribute_group *rapl_attr_groups[] = { + &rapl_pmu_attr_group, + &rapl_pmu_format_group, + &rapl_pmu_events_group, + NULL, +}; + +static struct pmu rapl_pmu_class = { + .attr_groups = rapl_attr_groups, + .task_ctx_nr = perf_invalid_context, /* system-wide only */ + .event_init = rapl_pmu_event_init, + .add = rapl_pmu_event_add, /* must have */ + .del = rapl_pmu_event_del, /* must have */ + .start = rapl_pmu_event_start, + .stop = rapl_pmu_event_stop, + .read = rapl_pmu_event_read, +}; + +static void rapl_cpu_exit(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int i, phys_id = topology_physical_package_id(cpu); + int target = -1; + + /* find a new cpu on same package */ + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (phys_id == topology_physical_package_id(i)) { + target = i; + break; + } + } + /* + * clear cpu from cpumask + * if was set in cpumask and still some cpu on package, + * then move to new cpu + */ + if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &rapl_cpu_mask); + + WARN_ON(cpumask_empty(&rapl_cpu_mask)); + /* + * migrate events and context to new cpu + */ + if (target >= 0) + perf_pmu_migrate_context(pmu->pmu, cpu, target); +} + +static void rapl_cpu_init(int cpu) +{ + int i, phys_id = topology_physical_package_id(cpu); + + /* check if phys_is is already covered */ + for_each_cpu(i, &rapl_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) + return; + } + /* was not found, so add it */ + cpumask_set_cpu(cpu, &rapl_cpu_mask); +} + +static int rapl_cpu_prepare(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int phys_id = topology_physical_package_id(cpu); + + if (pmu) + return 0; + + if (phys_id < 0) + return -1; + + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -1; + + spin_lock_init(&pmu->lock); + + INIT_LIST_HEAD(&pmu->active_list); + + /* + * grab power unit as: 1/2^unit Joules + * + * we cache in local PMU instance + */ + rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); + pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->pmu = &rapl_pmu_class; + + /* set RAPL pmu for this cpu for now */ + per_cpu(rapl_pmu, cpu) = pmu; + per_cpu(rapl_pmu_to_free, cpu) = NULL; + + return 0; +} + +static void rapl_cpu_kfree(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu); + + kfree(pmu); + + per_cpu(rapl_pmu_to_free, cpu) = NULL; +} + +static int rapl_cpu_dying(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + + if (!pmu) + return 0; + + per_cpu(rapl_pmu, cpu) = NULL; + + per_cpu(rapl_pmu_to_free, cpu) = pmu; + + return 0; +} + +static int rapl_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + rapl_cpu_prepare(cpu); + break; + case CPU_STARTING: + rapl_cpu_init(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + rapl_cpu_dying(cpu); + break; + case CPU_ONLINE: + case CPU_DEAD: + rapl_cpu_kfree(cpu); + break; + case CPU_DOWN_PREPARE: + rapl_cpu_exit(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static const struct x86_cpu_id rapl_cpu_match[] = { + [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, + [1] = {}, +}; + +static int __init rapl_pmu_init(void) +{ + struct rapl_pmu *pmu; + int cpu, ret; + + /* + * check for Intel processor family 6 + */ + if (!x86_match_cpu(rapl_cpu_match)) + return 0; + + /* check supported CPU */ + switch (boot_cpu_data.x86_model) { + case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ + case 60: /* Haswell */ + rapl_cntr_mask = RAPL_IDX_CLN; + rapl_pmu_events_group.attrs = rapl_events_cln_attr; + break; + case 45: /* Sandy Bridge-EP */ + case 62: /* IvyTown */ + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; + + default: + /* unsupported */ + return 0; + } + get_online_cpus(); + + for_each_online_cpu(cpu) { + rapl_cpu_prepare(cpu); + rapl_cpu_init(cpu); + } + + perf_cpu_notifier(rapl_cpu_notifier); + + ret = perf_pmu_register(&rapl_pmu_class, "power", -1); + if (WARN_ON(ret)) { + pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret); + put_online_cpus(); + return -1; + } + + pmu = __get_cpu_var(rapl_pmu); + + pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + " API unit is 2^-32 Joules," + " %d fixed counters\n", + pmu->hw_unit, + hweight32(rapl_cntr_mask)); + + put_online_cpus(); + + return 0; +} +device_initcall(rapl_pmu_init); -- 2.30.2