Merge branches 'pm-cpufreq', 'pm-cpuidle', 'pm-devfreq', 'pm-opp' and…

… 'pm-tools'

* pm-cpufreq:
  cpufreq: speedstep-smi: enable interrupts when waiting

* pm-cpuidle:
  intel_idle: support additional Broadwell model

* pm-devfreq:
  PM / devfreq: event: testing the wrong variable

* pm-opp:
  PM / OPP / clk: Remove unnecessary OOM message

* pm-tools:
  tools/power turbostat: support additional Broadwell model
  tools/power turbostat: update parameters, documentation
  tools/power turbostat: Skip printing disabled package C-states

drivers/base/firmware_class.c

@@ -855,7 +855,6 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
 
 	fw_priv = kzalloc(sizeof(*fw_priv), GFP_KERNEL);
 	if (!fw_priv) {
-		dev_err(device, "%s: kmalloc failed\n", __func__);
 		fw_priv = ERR_PTR(-ENOMEM);
 		goto exit;
 	}

drivers/base/power/clock_ops.c

@@ -81,10 +81,8 @@ static int __pm_clk_add(struct device *dev, const char *con_id,
 		return -EINVAL;
 
 	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
-	if (!ce) {
-		dev_err(dev, "Not enough memory for clock entry.\n");
+	if (!ce)
 		return -ENOMEM;
-	}
 
 	if (con_id) {
 		ce->con_id = kstrdup(con_id, GFP_KERNEL);

drivers/base/power/opp.c

@@ -474,10 +474,8 @@ static int _opp_add_dynamic(struct device *dev, unsigned long freq,
 
 	/* allocate new OPP node */
 	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp) {
-		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+	if (!new_opp)
 		return -ENOMEM;
-	}
 
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
@@ -695,10 +693,8 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 
 	/* keep the node allocated */
 	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp) {
-		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+	if (!new_opp)
 		return -ENOMEM;
-	}
 
 	mutex_lock(&dev_opp_list_lock);
 

drivers/cpufreq/speedstep-lib.c

@@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 	pr_debug("previous speed is %u\n", prev_speed);
 
+	preempt_disable();
 	local_irq_save(flags);
 
 	/* switch to low state */
@@ -464,6 +465,8 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 out:
 	local_irq_restore(flags);
+	preempt_enable();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(speedstep_get_freqs);

drivers/cpufreq/speedstep-smi.c

@@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned int state)
 		return;
 
 	/* Disable IRQs */
+	preempt_disable();
 	local_irq_save(flags);
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
@@ -166,9 +167,19 @@ static void speedstep_set_state(unsigned int state)
 
 	do {
 		if (retry) {
+			/*
+			 * We need to enable interrupts, otherwise the blockage
+			 * won't resolve.
+			 *
+			 * We disable preemption so that other processes don't
+			 * run. If other processes were running, they could
+			 * submit more DMA requests, making the blockage worse.
+			 */
 			pr_debug("retry %u, previous result %u, waiting...\n",
 					retry, result);
+			local_irq_enable();
 			mdelay(retry * 50);
+			local_irq_disable();
 		}
 		retry++;
 		__asm__ __volatile__(
@@ -185,6 +196,7 @@ static void speedstep_set_state(unsigned int state)
 
 	/* enable IRQs */
 	local_irq_restore(flags);
+	preempt_enable();
 
 	if (new_state == state)
 		pr_debug("change to %u MHz succeeded after %u tries "

drivers/devfreq/event/exynos-ppmu.c

@@ -327,8 +327,8 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	for (i = 0; i < info->num_events; i++) {
 		edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]);
-		if (IS_ERR(edev)) {
-			ret = PTR_ERR(edev);
+		if (IS_ERR(edev[i])) {
+			ret = PTR_ERR(edev[i]);
 			dev_err(&pdev->dev,
 				"failed to add devfreq-event device\n");
 			goto err;

drivers/idle/intel_idle.c

@@ -727,6 +727,7 @@ static const struct x86_cpu_id intel_idle_ids[] = {
 	ICPU(0x46, idle_cpu_hsw),
 	ICPU(0x4d, idle_cpu_avn),
 	ICPU(0x3d, idle_cpu_bdw),
+	ICPU(0x47, idle_cpu_bdw),
 	ICPU(0x4f, idle_cpu_bdw),
 	ICPU(0x56, idle_cpu_bdw),
 	{}

tools/power/x86/turbostat/turbostat.8

@@ -9,7 +9,7 @@ turbostat \- Report processor frequency and idle statistics
 .br
 .B turbostat
 .RB [ Options ]
-.RB [ "\-i interval_sec" ]
+.RB [ "\--interval seconds" ]
 .SH DESCRIPTION
 \fBturbostat \fP reports processor topology, frequency,
 idle power-state statistics, temperature and power on X86 processors.
@@ -18,31 +18,41 @@ The first method is to supply a
 \fBcommand\fP, which is forked and statistics are printed
 upon its completion.
 The second method is to omit the command,
-and turbodstat will print statistics every 5 seconds.
-The 5-second interval can changed using the -i option.
+and turbostat displays statistics every 5 seconds.
+The 5-second interval can be changed using the --interval option.
 
-Some information is not availalbe on older processors.
+Some information is not available on older processors.
 .SS Options
-The \fB-p\fP option limits output to the 1st thread in 1st core of each package.
+\fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter.
 .PP
-The \fB-P\fP option limits output to the 1st thread in each Package.
+\fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter.
 .PP
-The \fB-S\fP option limits output to a 1-line System Summary for each interval.
+\fB--Dump\fP displays the raw counter values.
 .PP
-The \fB-v\fP option increases verbosity.
+\fB--debug\fP displays additional system configuration information.  Invoking this parameter
+more than once may also enable internal turbostat debug information.
 .PP
-The \fB-c MSR#\fP option includes the delta of the specified 32-bit MSR counter.
+\fB--interval seconds\fP overrides the default 5-second measurement interval.
 .PP
-The \fB-C MSR#\fP option includes the delta of the specified 64-bit MSR counter.
+\fB--help\fP displays usage for the most common parameters.
 .PP
-The \fB-m MSR#\fP option includes the the specified 32-bit MSR value.
+\fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-The \fB-M MSR#\fP option includes the the specified 64-bit MSR value.
+\fB--MSR MSR#\fP shows the specified 64-bit MSR value.
 .PP
-The \fB-i interval_sec\fP option prints statistics every \fiinterval_sec\fP seconds.
-The default is 5 seconds.
+\fB--msr MSR#\fP shows the specified 32-bit MSR value.
 .PP
-The \fBcommand\fP parameter forks \fBcommand\fP and upon its exit,
+\fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
+.PP
+\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
+.PP
+\fB--Summary\fP limits output to a 1-line System Summary for each interval.
+.PP
+\fB--TCC temperature\fP sets the Thermal Control Circuit temperature for systems which do not export that value.  This is used for making sense of the Digital Thermal Sensor outputs, as they return degrees Celsius below the TCC activation temperature.
+.PP
+\fB--version\fP displays the version.
+.PP
+The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit,
 displays the statistics gathered since it was forked.
 .PP
 .SH FIELD DESCRIPTIONS
@@ -52,7 +62,7 @@ displays the statistics gathered since it was forked.
 \fBCPU\fP Linux CPU (logical processor) number.
 Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
 \fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fB%Buzy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
+\fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
 \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
@@ -68,7 +78,7 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 .fi
 .PP
 .SH EXAMPLE
-Without any parameters, turbostat prints out counters ever 5 seconds.
+Without any parameters, turbostat displays statistics ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
 
@@ -91,19 +101,19 @@ Subsequent rows show per-CPU statistics.
        3       3       3    0.20    1596    3492       0    0.44    0.00   99.37    0.00      23
        3       7       5    0.31    1596    3492       0    0.33
 .fi
-.SH VERBOSE EXAMPLE
-The "-v" option adds verbosity to the output:
+.SH DEBUG EXAMPLE
+The "--debug" option prints additional system information before measurements:
 
 .nf
-[root@ivy]# turbostat -v
-turbostat v3.0 November 23, 2012 - Len Brown <[email protected]>
+turbostat version 4.0 10-Feb, 2015 - Len Brown <[email protected]>
 CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3a:9 (6:58:9)
 CPUID(6): APERF, DTS, PTM, EPB
-RAPL: 851 sec. Joule Counter Range
+RAPL: 851 sec. Joule Counter Range, at 77 Watts
 cpu0: MSR_NHM_PLATFORM_INFO: 0x81010f0012300
 16 * 100 = 1600 MHz max efficiency
 35 * 100 = 3500 MHz TSC frequency
-cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6-noret)
+cpu0: MSR_IA32_POWER_CTL: 0x0014005d (C1E auto-promotion: DISabled)
+cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6n)
 cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
 37 * 100 = 3700 MHz max turbo 4 active cores
 38 * 100 = 3800 MHz max turbo 3 active cores
@@ -112,9 +122,9 @@ cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
 cpu0: MSR_RAPL_POWER_UNIT: 0x000a1003 (0.125000 Watts, 0.000015 Joules, 0.000977 sec.)
 cpu0: MSR_PKG_POWER_INFO: 0x01e00268 (77 W TDP, RAPL 60 - 0 W, 0.000000 sec.)
-cpu0: MSR_PKG_POWER_LIMIT: 0x830000148268 (UNlocked)
+cpu0: MSR_PKG_POWER_LIMIT: 0x30000148268 (UNlocked)
 cpu0: PKG Limit #1: ENabled (77.000000 Watts, 1.000000 sec, clamp DISabled)
-cpu0: PKG Limit #2: ENabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
+cpu0: PKG Limit #2: DISabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
 cpu0: MSR_PP0_POLICY: 0
 cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: Cores Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
@@ -123,9 +133,9 @@ cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
 cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00691400 (105 C)
 cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884e0000 (27 C)
-cpu0: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
-cpu1: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
-cpu2: MSR_IA32_THERM_STATUS: 0x88540000 (21 C +/- 1)
+cpu0: MSR_IA32_THERM_STATUS: 0x88580000 (17 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x885a0000 (15 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x88570000 (18 C +/- 1)
 cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1)
  ...
 .fi
@@ -195,7 +205,7 @@ in those kernels.
 
 AVG_MHz = APERF_delta/measurement_interval.  This is the actual
 number of elapsed cycles divided by the entire sample interval --
-including idle time.  Note that this calculation is resiliant
+including idle time.  Note that this calculation is resilient
 to systems lacking a non-stop TSC.
 
 TSC_MHz = TSC_delta/measurement_interval.