Two power management fixes for v4.15-rc1

This is the change making /proc/cpuinfo on x86 report current
 CPU frequency in "cpu MHz" again in all cases and an additional
 one dealing with an overzealous check in one of the helper
 routines in the runtime PM framework.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCAAGBQJaDvBIAAoJEILEb/54YlRxZ58QAJP6p53XDcml8Risw9CrpnZV
 6kBdFTYn6JSJiE4cALTER14ScqHQdTP2M6QJPDDLV5LwiQFa5fJYsSNP7F1Dpg4r
 8V3QNZbBjpyc8rSGRUkjY7+WsvUUb2UWzEkLIUjOWIT4mfC969JxV/fBYEL7ZDn9
 Wg7q79qI5Tss9PU2GUmaFtdkR0lqUIdNrrWe+qyLl0XHkrmU8DGL4XkPykdkwX0L
 gn0i/RrK+5DBUVPR1qQTU2CO3751IdIDktpK3RLmWl/yb4TqlM4WKIhIZvvglc2g
 S+OWGg/E4CNU6/EcGllNCPENAH7v0FNvvLMslPs6ao+wGQBcgO4R5d70dzobph/i
 P1ns6iJbd+lgRlGSQBReVo/FWcwi4HrINRxAB4W88dBBxchHdt+G3/Juq6GiGEJi
 mOh3ZHWd0J3mQEIWLKEcm5nHwIeY9yhCFJIpr5azte7JIz1fDuMnnp2gYl1SOVCK
 CHv0uD8Mw7hQFC0Dzje8T0Hr29MBwpEJiXE4Eh+Fp4zWiI7BYd1TNtp5WPDtchhv
 weqFqgDArN5gpkrZuSsxxg8eeRRwPeQR/mCyxofmsQ5lplCVJi8Ieqcf/KZrCy/c
 1vHGJsn9ec2dNeQKTFFT5luznQSSSXoZCXprumFuTp2804E3Hpkf/UnAldc4EYSn
 SwzAOO3gNA76eaFikvTK
 =h6Ux
 -----END PGP SIGNATURE-----

Merge tag 'pm-fixes-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull two power management fixes from Rafael Wysocki:
 "This is the change making /proc/cpuinfo on x86 report current CPU
  frequency in "cpu MHz" again in all cases and an additional one
  dealing with an overzealous check in one of the helper routines in the
  runtime PM framework"

* tag 'pm-fixes-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM / runtime: Drop children check from __pm_runtime_set_status()
  x86 / CPU: Always show current CPU frequency in /proc/cpuinfo

Documentation/power/runtime_pm.txt

@@ -435,8 +435,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       PM status to 'suspended' and update its parent's counter of 'active'
       children as appropriate (it is only valid to use this function if
       'power.runtime_error' is set or 'power.disable_depth' is greater than
-      zero); it will fail and return an error code if the device has a child
-      which is active and the 'power.ignore_children' flag is unset
+      zero)
 
   bool pm_runtime_active(struct device *dev);
     - return true if the device's runtime PM status is 'active' or its

arch/x86/kernel/cpu/Makefile

@@ -22,7 +22,7 @@ obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
-obj-$(CONFIG_CPU_FREQ)	+= aperfmperf.o
+obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o

arch/x86/kernel/cpu/aperfmperf.c

@@ -14,6 +14,8 @@
 #include <linux/percpu.h>
 #include <linux/smp.h>
 
+#include "cpu.h"
+
 struct aperfmperf_sample {
 	unsigned int	khz;
 	ktime_t	time;
@@ -24,7 +26,7 @@ struct aperfmperf_sample {
 static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
 
 #define APERFMPERF_CACHE_THRESHOLD_MS	10
-#define APERFMPERF_REFRESH_DELAY_MS	20
+#define APERFMPERF_REFRESH_DELAY_MS	10
 #define APERFMPERF_STALE_THRESHOLD_MS	1000
 
 /*
@@ -38,8 +40,6 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	u64 aperf, aperf_delta;
 	u64 mperf, mperf_delta;
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
-	ktime_t now = ktime_get();
-	s64 time_delta = ktime_ms_delta(now, s->time);
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -57,38 +57,68 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	if (mperf_delta == 0)
 		return;
 
-	s->time = now;
+	s->time = ktime_get();
 	s->aperf = aperf;
 	s->mperf = mperf;
-
-	/* If the previous iteration was too long ago, discard it. */
-	if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
-		s->khz = 0;
-	else
-		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
+	s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
 }
 
-unsigned int arch_freq_get_on_cpu(int cpu)
+static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
 {
-	s64 time_delta;
-	unsigned int khz;
+	s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu));
 
+	/* Don't bother re-computing within the cache threshold time. */
+	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
+		return true;
+
+	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait);
+
+	/* Return false if the previous iteration was too long ago. */
+	return time_delta <= APERFMPERF_STALE_THRESHOLD_MS;
+}
+
+unsigned int aperfmperf_get_khz(int cpu)
+{
 	if (!cpu_khz)
 		return 0;
 
 	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
-	/* Don't bother re-computing within the cache threshold time. */
-	time_delta = ktime_ms_delta(ktime_get(), per_cpu(samples.time, cpu));
-	khz = per_cpu(samples.khz, cpu);
-	if (khz && time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
-		return khz;
+	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
+	return per_cpu(samples.khz, cpu);
+}
 
-	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
-	khz = per_cpu(samples.khz, cpu);
-	if (khz)
-		return khz;
+void arch_freq_prepare_all(void)
+{
+	ktime_t now = ktime_get();
+	bool wait = false;
+	int cpu;
+
+	if (!cpu_khz)
+		return;
+
+	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+		return;
+
+	for_each_online_cpu(cpu)
+		if (!aperfmperf_snapshot_cpu(cpu, now, false))
+			wait = true;
+
+	if (wait)
+		msleep(APERFMPERF_REFRESH_DELAY_MS);
+}
+
+unsigned int arch_freq_get_on_cpu(int cpu)
+{
+	if (!cpu_khz)
+		return 0;
+
+	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+		return 0;
+
+	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
+		return per_cpu(samples.khz, cpu);
 
 	msleep(APERFMPERF_REFRESH_DELAY_MS);
 	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);

arch/x86/kernel/cpu/cpu.h

@@ -47,4 +47,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+
+unsigned int aperfmperf_get_khz(int cpu);
+
 #endif /* ARCH_X86_CPU_H */

arch/x86/kernel/cpu/proc.c

@@ -5,6 +5,8 @@
 #include <linux/seq_file.h>
 #include <linux/cpufreq.h>
 
+#include "cpu.h"
+
 /*
  *	Get CPU information for use by the procfs.
  */
@@ -78,8 +80,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
 	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = cpufreq_quick_get(cpu);
+		unsigned int freq = aperfmperf_get_khz(cpu);
 
+		if (!freq)
+			freq = cpufreq_quick_get(cpu);
 		if (!freq)
 			freq = cpu_khz;
 		seq_printf(m, "cpu MHz\t\t: %u.%03u\n",

drivers/base/power/runtime.c

@@ -1101,29 +1101,13 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
 		goto out;
 	}
 
-	if (dev->power.runtime_status == status)
+	if (dev->power.runtime_status == status || !parent)
 		goto out_set;
 
 	if (status == RPM_SUSPENDED) {
-		/*
-		 * It is invalid to suspend a device with an active child,
-		 * unless it has been set to ignore its children.
-		 */
-		if (!dev->power.ignore_children &&
-			atomic_read(&dev->power.child_count)) {
-			dev_err(dev, "runtime PM trying to suspend device but active child\n");
-			error = -EBUSY;
-			goto out;
-		}
-
-		if (parent) {
-			atomic_add_unless(&parent->power.child_count, -1, 0);
-			notify_parent = !parent->power.ignore_children;
-		}
-		goto out_set;
-	}
-
-	if (parent) {
+		atomic_add_unless(&parent->power.child_count, -1, 0);
+		notify_parent = !parent->power.ignore_children;
+	} else {
 		spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);
 
 		/*
@@ -1307,6 +1291,13 @@ void pm_runtime_enable(struct device *dev)
 	else
 		dev_warn(dev, "Unbalanced %s!\n", __func__);
 
+	WARN(!dev->power.disable_depth &&
+	     dev->power.runtime_status == RPM_SUSPENDED &&
+	     !dev->power.ignore_children &&
+	     atomic_read(&dev->power.child_count) > 0,
+	     "Enabling runtime PM for inactive device (%s) with active children\n",
+	     dev_name(dev));
+
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 }
 EXPORT_SYMBOL_GPL(pm_runtime_enable);

fs/proc/cpuinfo.c

@@ -1,12 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/cpufreq.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
+__weak void arch_freq_prepare_all(void)
+{
+}
+
 extern const struct seq_operations cpuinfo_op;
 static int cpuinfo_open(struct inode *inode, struct file *file)
 {
+	arch_freq_prepare_all();
 	return seq_open(file, &cpuinfo_op);
 }
 

include/linux/cpufreq.h

@@ -917,6 +917,7 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 }
 #endif
 
+extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
 extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,