[tip:perf/urgent] perf/x86/amd/power: Add AMD accumulated power reporting mechanism

[tip-bot for Huang Rui]

Commit-ID:  c7ab62bfbe0e27ef452d19d88b083f01e99f13a7
Gitweb:     http://git.kernel.org/tip/c7ab62bfbe0e27ef452d19d88b083f01e99f13a7
Author:     Huang Rui <ray.huang@xxxxxxx>
AuthorDate: Wed, 9 Mar 2016 13:45:06 +0800
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 21 Mar 2016 09:37:15 +0100

perf/x86/amd/power: Add AMD accumulated power reporting mechanism

Introduce an AMD accumlated power reporting mechanism for the Family
15h, Model 60h processor that can be used to calculate the average
power consumed by a processor during a measurement interval. The
feature support is indicated by CPUID Fn8000_0007_EDX[12].

This feature will be implemented both in hwmon and perf. The current
design provides one event to report per package/processor power
consumption by counting each compute unit power value.

Here the gory details of how the computation is done:

* Tsample: compute unit power accumulator sample period
* Tref: the PTSC counter period (PTSC: performance timestamp counter)
* N: the ratio of compute unit power accumulator sample period to the
  PTSC period

* Jmax: max compute unit accumulated power which is indicated by
  MSR_C001007b[MaxCpuSwPwrAcc]

* Jx/Jy: compute unit accumulated power which is indicated by
  MSR_C001007a[CpuSwPwrAcc]

* Tx/Ty: the value of performance timestamp counter which is indicated
  by CU_PTSC MSR_C0010280[PTSC]
* PwrCPUave: CPU average power

i. Determine the ratio of Tsample to Tref by executing CPUID Fn8000_0007.
	N = value of CPUID Fn8000_0007_ECX[CpuPwrSampleTimeRatio[15:0]].

ii. Read the full range of the cumulative energy value from the new
    MSR MaxCpuSwPwrAcc.
	Jmax = value returned.

iii. At time x, software reads CpuSwPwrAcc and samples the PTSC.
	Jx = value read from CpuSwPwrAcc and Tx = value read from PTSC.

iv. At time y, software reads CpuSwPwrAcc and samples the PTSC.
	Jy = value read from CpuSwPwrAcc and Ty = value read from PTSC.

v. Calculate the average power consumption for a compute unit over
time period (y-x). Unit of result is uWatt:

	if (Jy < Jx) // Rollover has occurred
		Jdelta = (Jy + Jmax) - Jx
	else
		Jdelta = Jy - Jx
	PwrCPUave = N * Jdelta * 1000 / (Ty - Tx)

Simple example:

  root@hr-zp:/home/ray/tip# ./tools/perf/perf stat -a -e 'power/power-pkg/' make -j4
    CHK     include/config/kernel.release
    CHK     include/generated/uapi/linux/version.h
    CHK     include/generated/utsrelease.h
    CHK     include/generated/timeconst.h
    CHK     include/generated/bounds.h
    CHK     include/generated/asm-offsets.h
    CALL    scripts/checksyscalls.sh
    CHK     include/generated/compile.h
    SKIPPED include/generated/compile.h
    Building modules, stage 2.
  Kernel: arch/x86/boot/bzImage is ready  (#40)
    MODPOST 4225 modules

   Performance counter stats for 'system wide':

              183.44 mWatts power/power-pkg/

       341.837270111 seconds time elapsed

  root@hr-zp:/home/ray/tip# ./tools/perf/perf stat -a -e 'power/power-pkg/' sleep 10

   Performance counter stats for 'system wide':

                0.18 mWatts power/power-pkg/

        10.012551815 seconds time elapsed

Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Suggested-by: Ingo Molnar <mingo@xxxxxxxxxx>
Suggested-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: Huang Rui <ray.huang@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Robert Richter <rric@xxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Vince Weaver <vincent.weaver@xxxxxxxxx>
Cc: jacob.w.shin@xxxxxxxxx
Link: http://lkml.kernel.org/r/1457502306-2559-1-git-send-email-ray.huang@xxxxxxx
[ Fixed the modular build. ]
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/Kconfig            |   9 ++
 arch/x86/events/Makefile    |   1 +
 arch/x86/events/amd/power.c | 353 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/events/core.c      |   4 +-
 include/linux/perf_event.h  |   4 +
 5 files changed, 369 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8f2e665..a313c0e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1206,6 +1206,15 @@ config MICROCODE_OLD_INTERFACE
 	def_bool y
 	depends on MICROCODE
 
+config PERF_EVENTS_AMD_POWER
+	depends on PERF_EVENTS && CPU_SUP_AMD
+	tristate "AMD Processor Power Reporting Mechanism"
+	---help---
+	  Provide power reporting mechanism support for AMD processors.
+	  Currently, it leverages X86_FEATURE_ACC_POWER
+	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
+	  average power consumption on Family 15h processors.
+
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
 	---help---
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index fdfea15..f59618a 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,6 +1,7 @@
 obj-y			+= core.o
 
 obj-$(CONFIG_CPU_SUP_AMD)               += amd/core.o amd/uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_POWER)	+= amd/power.o
 obj-$(CONFIG_X86_LOCAL_APIC)            += amd/ibs.o msr.o
 ifdef CONFIG_AMD_IOMMU
 obj-$(CONFIG_CPU_SUP_AMD)               += amd/iommu.o
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
new file mode 100644
index 0000000..55a3529
--- /dev/null
+++ b/arch/x86/events/amd/power.c
@@ -0,0 +1,353 @@
+/*
+ * Performance events - AMD Processor Power Reporting Mechanism
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Huang Rui <ray.huang@xxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <asm/cpu_device_id.h>
+#include "../perf_event.h"
+
+#define MSR_F15H_CU_PWR_ACCUMULATOR     0xc001007a
+#define MSR_F15H_CU_MAX_PWR_ACCUMULATOR 0xc001007b
+#define MSR_F15H_PTSC			0xc0010280
+
+/* Event code: LSB 8 bits, passed in attr->config any other bit is reserved. */
+#define AMD_POWER_EVENT_MASK		0xFFULL
+
+/*
+ * Accumulated power status counters.
+ */
+#define AMD_POWER_EVENTSEL_PKG		1
+
+/*
+ * The ratio of compute unit power accumulator sample period to the
+ * PTSC period.
+ */
+static unsigned int cpu_pwr_sample_ratio;
+
+/* Maximum accumulated power of a compute unit. */
+static u64 max_cu_acc_power;
+
+static struct pmu pmu_class;
+
+/*
+ * Accumulated power represents the sum of each compute unit's (CU) power
+ * consumption. On any core of each CU we read the total accumulated power from
+ * MSR_F15H_CU_PWR_ACCUMULATOR. cpu_mask represents CPU bit map of all cores
+ * which are picked to measure the power for the CUs they belong to.
+ */
+static cpumask_t cpu_mask;
+
+static void event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev_pwr_acc, new_pwr_acc, prev_ptsc, new_ptsc;
+	u64 delta, tdelta;
+
+	prev_pwr_acc = hwc->pwr_acc;
+	prev_ptsc = hwc->ptsc;
+	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
+	rdmsrl(MSR_F15H_PTSC, new_ptsc);
+
+	/*
+	 * Calculate the CU power consumption over a time period, the unit of
+	 * final value (delta) is micro-Watts. Then add it to the event count.
+	 */
+	if (new_pwr_acc < prev_pwr_acc) {
+		delta = max_cu_acc_power + new_pwr_acc;
+		delta -= prev_pwr_acc;
+	} else
+		delta = new_pwr_acc - prev_pwr_acc;
+
+	delta *= cpu_pwr_sample_ratio * 1000;
+	tdelta = new_ptsc - prev_ptsc;
+
+	do_div(delta, tdelta);
+	local64_add(delta, &event->count);
+}
+
+static void __pmu_event_start(struct perf_event *event)
+{
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+
+	rdmsrl(MSR_F15H_PTSC, event->hw.ptsc);
+	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
+}
+
+static void pmu_event_start(struct perf_event *event, int mode)
+{
+	__pmu_event_start(event);
+}
+
+static void pmu_event_stop(struct perf_event *event, int mode)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* Mark event as deactivated and stopped. */
+	if (!(hwc->state & PERF_HES_STOPPED))
+		hwc->state |= PERF_HES_STOPPED;
+
+	/* Check if software counter update is necessary. */
+	if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of an event
+		 * that we are disabling:
+		 */
+		event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int pmu_event_add(struct perf_event *event, int mode)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (mode & PERF_EF_START)
+		__pmu_event_start(event);
+
+	return 0;
+}
+
+static void pmu_event_del(struct perf_event *event, int flags)
+{
+	pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int pmu_event_init(struct perf_event *event)
+{
+	u64 cfg = event->attr.config & AMD_POWER_EVENT_MASK;
+
+	/* Only look at AMD power events. */
+	if (event->attr.type != pmu_class.type)
+		return -ENOENT;
+
+	/* 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  ||
+	    /* no sampling */
+	    event->attr.sample_period)
+		return -EINVAL;
+
+	if (cfg != AMD_POWER_EVENTSEL_PKG)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void pmu_event_read(struct perf_event *event)
+{
+	event_update(event);
+}
+
+static ssize_t
+get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpumap_print_to_pagebuf(true, buf, &cpu_mask);
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, get_attr_cpumask, NULL);
+
+static struct attribute *pmu_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group pmu_attr_group = {
+	.attrs = pmu_attrs,
+};
+
+/*
+ * Currently it only supports to report the power of each
+ * processor/package.
+ */
+EVENT_ATTR_STR(power-pkg, power_pkg, "event=0x01");
+
+EVENT_ATTR_STR(power-pkg.unit, power_pkg_unit, "mWatts");
+
+/* Convert the count from micro-Watts to milli-Watts. */
+EVENT_ATTR_STR(power-pkg.scale, power_pkg_scale, "1.000000e-3");
+
+static struct attribute *events_attr[] = {
+	EVENT_PTR(power_pkg),
+	EVENT_PTR(power_pkg_unit),
+	EVENT_PTR(power_pkg_scale),
+	NULL,
+};
+
+static struct attribute_group pmu_events_group = {
+	.name	= "events",
+	.attrs	= events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+
+static struct attribute *formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group pmu_format_group = {
+	.name	= "format",
+	.attrs	= formats_attr,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&pmu_attr_group,
+	&pmu_format_group,
+	&pmu_events_group,
+	NULL,
+};
+
+static struct pmu pmu_class = {
+	.attr_groups	= attr_groups,
+	/* system-wide only */
+	.task_ctx_nr	= perf_invalid_context,
+	.event_init	= pmu_event_init,
+	.add		= pmu_event_add,
+	.del		= pmu_event_del,
+	.start		= pmu_event_start,
+	.stop		= pmu_event_stop,
+	.read		= pmu_event_read,
+};
+
+static void power_cpu_exit(int cpu)
+{
+	int target;
+
+	if (!cpumask_test_and_clear_cpu(cpu, &cpu_mask))
+		return;
+
+	/*
+	 * Find a new CPU on the same compute unit, if was set in cpumask
+	 * and still some CPUs on compute unit. Then migrate event and
+	 * context to new CPU.
+	 */
+	target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
+	if (target < nr_cpumask_bits) {
+		cpumask_set_cpu(target, &cpu_mask);
+		perf_pmu_migrate_context(&pmu_class, cpu, target);
+	}
+}
+
+static void power_cpu_init(int cpu)
+{
+	int target;
+
+	/*
+	 * 1) If any CPU is set at cpu_mask in the same compute unit, do
+	 * nothing.
+	 * 2) If no CPU is set at cpu_mask in the same compute unit,
+	 * set current STARTING CPU.
+	 *
+	 * Note: if there is a CPU aside of the new one already in the
+	 * sibling mask, then it is also in cpu_mask.
+	 */
+	target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
+	if (target >= nr_cpumask_bits)
+		cpumask_set_cpu(cpu, &cpu_mask);
+}
+
+static int
+power_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_FAILED:
+	case CPU_STARTING:
+		power_cpu_init(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		power_cpu_exit(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block power_cpu_notifier_nb = {
+	.notifier_call = power_cpu_notifier,
+	.priority = CPU_PRI_PERF,
+};
+
+static const struct x86_cpu_id cpu_match[] = {
+	{ .vendor = X86_VENDOR_AMD, .family = 0x15 },
+	{},
+};
+
+static int __init amd_power_pmu_init(void)
+{
+	int cpu, target, ret;
+
+	if (!x86_match_cpu(cpu_match))
+		return 0;
+
+	if (!boot_cpu_has(X86_FEATURE_ACC_POWER))
+		return -ENODEV;
+
+	cpu_pwr_sample_ratio = cpuid_ecx(0x80000007);
+
+	if (rdmsrl_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
+		pr_err("Failed to read max compute unit power accumulator MSR\n");
+		return -ENODEV;
+	}
+
+	cpu_notifier_register_begin();
+
+	/* Choose one online core of each compute unit. */
+	for_each_online_cpu(cpu) {
+		target = cpumask_first(topology_sibling_cpumask(cpu));
+		if (!cpumask_test_cpu(target, &cpu_mask))
+			cpumask_set_cpu(target, &cpu_mask);
+	}
+
+	ret = perf_pmu_register(&pmu_class, "power", -1);
+	if (WARN_ON(ret)) {
+		pr_warn("AMD Power PMU registration failed\n");
+		goto out;
+	}
+
+	__register_cpu_notifier(&power_cpu_notifier_nb);
+
+	pr_info("AMD Power PMU detected\n");
+
+out:
+	cpu_notifier_register_done();
+
+	return ret;
+}
+module_init(amd_power_pmu_init);
+
+static void __exit amd_power_pmu_exit(void)
+{
+	cpu_notifier_register_begin();
+	__unregister_cpu_notifier(&power_cpu_notifier_nb);
+	cpu_notifier_register_done();
+
+	perf_pmu_unregister(&pmu_class);
+}
+module_exit(amd_power_pmu_exit);
+
+MODULE_AUTHOR("Huang Rui <ray.huang@xxxxxxx>");
+MODULE_DESCRIPTION("AMD Processor Power Reporting Mechanism");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5e830d0..002b2ea 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1602,8 +1602,7 @@ __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
 	return new;
 }
 
-ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
-			  char *page)
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
 {
 	struct perf_pmu_events_attr *pmu_attr = \
 		container_of(attr, struct perf_pmu_events_attr, attr);
@@ -1615,6 +1614,7 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 
 	return x86_pmu.events_sysfs_show(page, config);
 }
+EXPORT_SYMBOL_GPL(events_sysfs_show);
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7bb315b..15588d4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -129,6 +129,10 @@ struct hw_perf_event {
 		struct { /* itrace */
 			int			itrace_started;
 		};
+		struct { /* amd_power */
+			u64	pwr_acc;
+			u64	ptsc;
+		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		struct { /* breakpoint */
 			/*