Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "This tree contains various perf fixes on the kernel side, plus three
  hw/event-enablement late additions:

   - Intel Memory Bandwidth Monitoring events and handling
   - the AMD Accumulated Power Mechanism reporting facility
   - more IOMMU events

  ... and a final round of perf tooling updates/fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  perf llvm: Use strerror_r instead of the thread unsafe strerror one
  perf llvm: Use realpath to canonicalize paths
  perf tools: Unexport some methods unused outside strbuf.c
  perf probe: No need to use formatting strbuf method
  perf help: Use asprintf instead of adhoc equivalents
  perf tools: Remove unused perf_pathdup, xstrdup functions
  perf tools: Do not include stringify.h from the kernel sources
  tools include: Copy linux/stringify.h from the kernel
  tools lib traceevent: Remove redundant CPU output
  perf tools: Remove needless 'extern' from function prototypes
  perf tools: Simplify die() mechanism
  perf tools: Remove unused DIE_IF macro
  perf script: Remove lots of unused arguments
  perf thread: Rename perf_event__preprocess_sample_addr to thread__resolve
  perf machine: Rename perf_event__preprocess_sample to machine__resolve
  perf tools: Add cpumode to struct perf_sample
  perf tests: Forward the perf_sample in the dwarf unwind test
  perf tools: Remove misplaced __maybe_unused
  perf list: Fix documentation of :ppp
  perf bench numa: Fix assertion for nodes bitfield
  ...

3 files changed, 391 insertions, 4 deletions

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 51087c29b2c2..3ea25c3917c0 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -376,7 +376,13 @@ static void perf_ibs_start(struct perf_event *event, int flags)
 	hwc->state = 0;
 
 	perf_ibs_set_period(perf_ibs, hwc, &period);
+	/*
+	 * Set STARTED before enabling the hardware, such that
+	 * a subsequent NMI must observe it. Then clear STOPPING
+	 * such that we don't consume NMIs by accident.
+	 */
 	set_bit(IBS_STARTED, pcpu->state);
+	clear_bit(IBS_STOPPING, pcpu->state);
 	perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
 
 	perf_event_update_userpage(event);
@@ -390,7 +396,7 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
 	u64 config;
 	int stopping;
 
-	stopping = test_and_clear_bit(IBS_STARTED, pcpu->state);
+	stopping = test_bit(IBS_STARTED, pcpu->state);
 
 	if (!stopping && (hwc->state & PERF_HES_UPTODATE))
 		return;
@@ -398,8 +404,24 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
 	rdmsrl(hwc->config_base, config);
 
 	if (stopping) {
+		/*
+		 * Set STOPPING before disabling the hardware, such that it
+		 * must be visible to NMIs the moment we clear the EN bit,
+		 * at which point we can generate an !VALID sample which
+		 * we need to consume.
+		 */
 		set_bit(IBS_STOPPING, pcpu->state);
 		perf_ibs_disable_event(perf_ibs, hwc, config);
+		/*
+		 * Clear STARTED after disabling the hardware; if it were
+		 * cleared before an NMI hitting after the clear but before
+		 * clearing the EN bit might think it a spurious NMI and not
+		 * handle it.
+		 *
+		 * Clearing it after, however, creates the problem of the NMI
+		 * handler seeing STARTED but not having a valid sample.
+		 */
+		clear_bit(IBS_STARTED, pcpu->state);
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
 	}
@@ -527,20 +549,24 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	u64 *buf, *config, period;
 
 	if (!test_bit(IBS_STARTED, pcpu->state)) {
+fail:
 		/*
 		 * Catch spurious interrupts after stopping IBS: After
 		 * disabling IBS there could be still incoming NMIs
 		 * with samples that even have the valid bit cleared.
 		 * Mark all this NMIs as handled.
 		 */
-		return test_and_clear_bit(IBS_STOPPING, pcpu->state) ? 1 : 0;
+		if (test_and_clear_bit(IBS_STOPPING, pcpu->state))
+			return 1;
+
+		return 0;
 	}
 
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
 	if (!(*buf++ & perf_ibs->valid_mask))
-		return 0;
+		goto fail;
 
 	config = &ibs_data.regs[0];
 	perf_ibs_event_update(perf_ibs, event, config);
@@ -599,7 +625,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
 	if (throttle)
-		perf_ibs_disable_event(perf_ibs, hwc, *config);
+		perf_ibs_stop(event, 0);
 	else
 		perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
 
@@ -611,6 +637,7 @@ out:
 static int
 perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
+	u64 stamp = sched_clock();
 	int handled = 0;
 
 	handled += perf_ibs_handle_irq(&perf_ibs_fetch, regs);
@@ -619,6 +646,8 @@ perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 	if (handled)
 		inc_irq_stat(apic_perf_irqs);
 
+	perf_sample_event_took(sched_clock() - stamp);
+
 	return handled;
 }
 NOKPROBE_SYMBOL(perf_ibs_nmi_handler);
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 635e5eba0caf..40625ca7a190 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -118,6 +118,11 @@ static struct amd_iommu_event_desc amd_iommu_v2_event_descs[] = {
 	AMD_IOMMU_EVENT_DESC(cmd_processed,           "csource=0x11"),
 	AMD_IOMMU_EVENT_DESC(cmd_processed_inv,       "csource=0x12"),
 	AMD_IOMMU_EVENT_DESC(tlb_inv,                 "csource=0x13"),
+	AMD_IOMMU_EVENT_DESC(ign_rd_wr_mmio_1ff8h,    "csource=0x14"),
+	AMD_IOMMU_EVENT_DESC(vapic_int_non_guest,     "csource=0x15"),
+	AMD_IOMMU_EVENT_DESC(vapic_int_guest,         "csource=0x16"),
+	AMD_IOMMU_EVENT_DESC(smi_recv,                "csource=0x17"),
+	AMD_IOMMU_EVENT_DESC(smi_blk,                 "csource=0x18"),
 	{ /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
new file mode 100644
index 000000000000..55a3529dbf12
--- /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@amd.com>
+ *
+ * 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@amd.com>");
+MODULE_DESCRIPTION("AMD Processor Power Reporting Mechanism");
+MODULE_LICENSE("GPL v2");