Merge master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreq

* master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreq:
  [CPUFREQ] Longhaul - Redo Longhaul ver. 2
  [CPUFREQ] EPS - Correct 2nd brand test
  [CPUFREQ] Longhaul - Separate frequency and voltage transition
  [CPUFREQ] Longhaul - Models of Nehemiah
  [CPUFREQ] Whitespace fixup
  [CPUFREQ] Longhaul - Simplier minmult
  [CPUFREQ] CPU_FREQ_TABLE shouldn't be a def_tristate
  [CPUFREQ] ondemand governor use new cpufreq rwsem locking in work callback
  [CPUFREQ] ondemand governor restructure the work callback
  [CPUFREQ] Rewrite lock in cpufreq to eliminate cpufreq/hotplug related issues
  [CPUFREQ] Remove hotplug cpu crap
  [CPUFREQ] Enhanced PowerSaver driver
  [CPUFREQ] Longhaul - Add VT8235 support
  [CPUFREQ] Longhaul - Fix guess_fsb function
  [CPUFREQ] Longhaul - Remove duplicate tables
  [CPUFREQ] Longhaul - Introduce Nehemiah C
  [CPUFREQ] fix cpuinfo_cur_freq for CPU_HW_PSTATE
  [CPUFREQ] Longhaul - Remove "ignore_latency" option

arch/i386/kernel/cpu/cpufreq/Kconfig

@@ -217,6 +217,15 @@ config X86_LONGHAUL
 
 	  If in doubt, say N.
 
+config X86_E_POWERSAVER
+	tristate "VIA C7 Enhanced PowerSaver (EXPERIMENTAL)"
+	select CPU_FREQ_TABLE
+	depends on EXPERIMENTAL
+	help
+	  This adds the CPUFreq driver for VIA C7 processors.
+
+	  If in doubt, say N.
+
 comment "shared options"
 
 config X86_ACPI_CPUFREQ_PROC_INTF

arch/i386/kernel/cpu/cpufreq/Makefile

@@ -2,6 +2,7 @@ obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
 obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
+obj-$(CONFIG_X86_E_POWERSAVER)		+= e_powersaver.o
 obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
 obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
 obj-$(CONFIG_X86_LONGRUN)		+= longrun.o  

arch/i386/kernel/cpu/cpufreq/e_powersaver.c

+/*
+ *  Based on documentation provided by Dave Jones. Thanks!
+ *
+ *  Licensed under the terms of the GNU GPL License version 2.
+ *
+ *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+
+#include <asm/msr.h>
+#include <asm/tsc.h>
+#include <asm/timex.h>
+#include <asm/io.h>
+#include <asm/delay.h>
+
+#define EPS_BRAND_C7M	0
+#define EPS_BRAND_C7	1
+#define EPS_BRAND_EDEN	2
+#define EPS_BRAND_C3	3
+
+struct eps_cpu_data {
+	u32 fsb;
+	struct cpufreq_frequency_table freq_table[];
+};
+
+static struct eps_cpu_data *eps_cpu[NR_CPUS];
+
+
+static unsigned int eps_get(unsigned int cpu)
+{
+	struct eps_cpu_data *centaur;
+	u32 lo, hi;
+
+	if (cpu)
+		return 0;
+	centaur = eps_cpu[cpu];
+	if (centaur == NULL)
+		return 0;
+
+	/* Return current frequency */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	return centaur->fsb * ((lo >> 8) & 0xff);
+}
+
+static int eps_set_state(struct eps_cpu_data *centaur,
+			 unsigned int cpu,
+			 u32 dest_state)
+{
+	struct cpufreq_freqs freqs;
+	u32 lo, hi;
+	int err = 0;
+	int i;
+
+	freqs.old = eps_get(cpu);
+	freqs.new = centaur->fsb * ((dest_state >> 8) & 0xff);
+	freqs.cpu = cpu;
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	/* Wait while CPU is busy */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	i = 0;
+	while (lo & ((1 << 16) | (1 << 17))) {
+		udelay(16);
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		i++;
+		if (unlikely(i > 64)) {
+			err = -ENODEV;
+			goto postchange;
+		}
+	}
+	/* Set new multiplier and voltage */
+	wrmsr(MSR_IA32_PERF_CTL, dest_state & 0xffff, 0);
+	/* Wait until transition end */
+	i = 0;
+	do {
+		udelay(16);
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		i++;
+		if (unlikely(i > 64)) {
+			err = -ENODEV;
+			goto postchange;
+		}
+	} while (lo & ((1 << 16) | (1 << 17)));
+
+	/* Return current frequency */
+postchange:
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	freqs.new = centaur->fsb * ((lo >> 8) & 0xff);
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	return err;
+}
+
+static int eps_target(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int relation)
+{
+	struct eps_cpu_data *centaur;
+	unsigned int newstate = 0;
+	unsigned int cpu = policy->cpu;
+	unsigned int dest_state;
+	int ret;
+
+	if (unlikely(eps_cpu[cpu] == NULL))
+		return -ENODEV;
+	centaur = eps_cpu[cpu];
+
+	if (unlikely(cpufreq_frequency_table_target(policy,
+			&eps_cpu[cpu]->freq_table[0],
+			target_freq,
+			relation,
+			&newstate))) {
+		return -EINVAL;
+	}
+
+	/* Make frequency transition */
+	dest_state = centaur->freq_table[newstate].index & 0xffff;
+	ret = eps_set_state(centaur, cpu, dest_state);
+	if (ret)
+		printk(KERN_ERR "eps: Timeout!\n");
+	return ret;
+}
+
+static int eps_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy,
+			&eps_cpu[policy->cpu]->freq_table[0]);
+}
+
+static int eps_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int i;
+	u32 lo, hi;
+	u64 val;
+	u8 current_multiplier, current_voltage;
+	u8 max_multiplier, max_voltage;
+	u8 min_multiplier, min_voltage;
+	u8 brand;
+	u32 fsb;
+	struct eps_cpu_data *centaur;
+	struct cpufreq_frequency_table *f_table;
+	int k, step, voltage;
+	int ret;
+	int states;
+
+	if (policy->cpu != 0)
+		return -ENODEV;
+
+	/* Check brand */
+	printk("eps: Detected VIA ");
+	rdmsr(0x1153, lo, hi);
+	brand = (((lo >> 2) ^ lo) >> 18) & 3;
+	switch(brand) {
+	case EPS_BRAND_C7M:
+		printk("C7-M\n");
+		break;
+	case EPS_BRAND_C7:
+		printk("C7\n");
+		break;
+	case EPS_BRAND_EDEN:
+		printk("Eden\n");
+		break;
+	case EPS_BRAND_C3:
+		printk("C3\n");
+		return -ENODEV;
+		break;
+	}
+	/* Enable Enhanced PowerSaver */
+	rdmsrl(MSR_IA32_MISC_ENABLE, val);
+	if (!(val & 1 << 16)) {
+		val |= 1 << 16;
+		wrmsrl(MSR_IA32_MISC_ENABLE, val);
+		/* Can be locked at 0 */
+		rdmsrl(MSR_IA32_MISC_ENABLE, val);
+		if (!(val & 1 << 16)) {
+			printk("eps: Can't enable Enhanced PowerSaver\n");
+			return -ENODEV;
+		}
+	}
+
+	/* Print voltage and multiplier */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	current_voltage = lo & 0xff;
+	printk("eps: Current voltage = %dmV\n", current_voltage * 16 + 700);
+	current_multiplier = (lo >> 8) & 0xff;
+	printk("eps: Current multiplier = %d\n", current_multiplier);
+
+	/* Print limits */
+	max_voltage = hi & 0xff;
+	printk("eps: Highest voltage = %dmV\n", max_voltage * 16 + 700);
+	max_multiplier = (hi >> 8) & 0xff;
+	printk("eps: Highest multiplier = %d\n", max_multiplier);
+	min_voltage = (hi >> 16) & 0xff;
+	printk("eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700);
+	min_multiplier = (hi >> 24) & 0xff;
+	printk("eps: Lowest multiplier = %d\n", min_multiplier);
+
+	/* Sanity checks */
+	if (current_multiplier == 0 || max_multiplier == 0
+	    || min_multiplier == 0)
+		return -EINVAL;
+	if (current_multiplier > max_multiplier
+	    || max_multiplier <= min_multiplier)
+		return -EINVAL;
+	if (current_voltage > 0x1c || max_voltage > 0x1c)
+		return -EINVAL;
+	if (max_voltage < min_voltage)
+		return -EINVAL;
+
+	/* Calc FSB speed */
+	fsb = cpu_khz / current_multiplier;
+	/* Calc number of p-states supported */
+	if (brand == EPS_BRAND_C7M)
+		states = max_multiplier - min_multiplier + 1;
+	else
+		states = 2;
+
+	/* Allocate private data and frequency table for current cpu */
+	centaur = kzalloc(sizeof(struct eps_cpu_data)
+		    + (states + 1) * sizeof(struct cpufreq_frequency_table),
+		    GFP_KERNEL);
+	if (!centaur)
+		return -ENOMEM;
+	eps_cpu[0] = centaur;
+
+	/* Copy basic values */
+	centaur->fsb = fsb;
+
+	/* Fill frequency and MSR value table */
+	f_table = &centaur->freq_table[0];
+	if (brand != EPS_BRAND_C7M) {
+		f_table[0].frequency = fsb * min_multiplier;
+		f_table[0].index = (min_multiplier << 8) | min_voltage;
+		f_table[1].frequency = fsb * max_multiplier;
+		f_table[1].index = (max_multiplier << 8) | max_voltage;
+		f_table[2].frequency = CPUFREQ_TABLE_END;
+	} else {
+		k = 0;
+		step = ((max_voltage - min_voltage) * 256)
+			/ (max_multiplier - min_multiplier);
+		for (i = min_multiplier; i <= max_multiplier; i++) {
+			voltage = (k * step) / 256 + min_voltage;
+			f_table[k].frequency = fsb * i;
+			f_table[k].index = (i << 8) | voltage;
+			k++;
+		}
+		f_table[k].frequency = CPUFREQ_TABLE_END;
+	}
+
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */
+	policy->cur = fsb * current_multiplier;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, &centaur->freq_table[0]);
+	if (ret) {
+		kfree(centaur);
+		return ret;
+	}
+
+	cpufreq_frequency_table_get_attr(&centaur->freq_table[0], policy->cpu);
+	return 0;
+}
+
+static int eps_cpu_exit(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct eps_cpu_data *centaur;
+	u32 lo, hi;
+
+	if (eps_cpu[cpu] == NULL)
+		return -ENODEV;
+	centaur = eps_cpu[cpu];
+
+	/* Get max frequency */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	/* Set max frequency */
+	eps_set_state(centaur, cpu, hi & 0xffff);
+	/* Bye */
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	kfree(eps_cpu[cpu]);
+	eps_cpu[cpu] = NULL;
+	return 0;
+}
+
+static struct freq_attr* eps_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver eps_driver = {
+	.verify		= eps_verify,
+	.target		= eps_target,
+	.init		= eps_cpu_init,
+	.exit		= eps_cpu_exit,
+	.get		= eps_get,
+	.name		= "e_powersaver",
+	.owner		= THIS_MODULE,
+	.attr		= eps_attr,
+};
+
+static int __init eps_init(void)
+{
+	struct cpuinfo_x86 *c = cpu_data;
+
+	/* This driver will work only on Centaur C7 processors with
+	 * Enhanced SpeedStep/PowerSaver registers */
+	if (c->x86_vendor != X86_VENDOR_CENTAUR
+	    || c->x86 != 6 || c->x86_model != 10)
+		return -ENODEV;
+	if (!cpu_has(c, X86_FEATURE_EST))
+		return -ENODEV;
+
+	if (cpufreq_register_driver(&eps_driver))
+		return -EINVAL;
+	return 0;
+}
+
+static void __exit eps_exit(void)
+{
+	cpufreq_unregister_driver(&eps_driver);
+}
+
+MODULE_AUTHOR("Rafa Bilski <rafalbilski@interia.pl>");
+MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's.");
+MODULE_LICENSE("GPL");
+
+module_init(eps_init);
+module_exit(eps_exit);

arch/i386/kernel/cpu/cpufreq/longhaul.h

@@ -235,84 +235,14 @@ static int __initdata ezrat_eblcr[32] = {
 /*
  * VIA C3 Nehemiah */
 
-static int __initdata nehemiah_a_clock_ratio[32] = {
+static int __initdata  nehemiah_clock_ratio[32] = {
 	100, /* 0000 -> 10.0x */
 	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	90,  /* 0011 ->  9.0x */
-	95,  /* 0100 ->  9.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	55,  /* 0111 ->  5.5x */
-	60,  /* 1000 ->  6.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	50,  /* 1011 ->  5.0x */
-	65,  /* 1100 ->  6.5x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	120, /* 1111 -> 12.0x */
-	100, /* 0000 -> 10.0x */
-	-1,  /* 0001 -> RESERVED */
-	120, /* 0010 -> 12.0x */
-	90,  /* 0011 ->  9.0x */
-	105, /* 0100 -> 10.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	135, /* 0111 -> 13.5x */
-	140, /* 1000 -> 14.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	130, /* 1011 -> 13.0x */
-	145, /* 1100 -> 14.5x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	120, /* 1111 -> 12.0x */
-};
-
-static int __initdata  nehemiah_b_clock_ratio[32] = {
-	100, /* 0000 -> 10.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	90,  /* 0011 ->  9.0x */
-	95,  /* 0100 ->  9.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	55,  /* 0111 ->  5.5x */
-	60,  /* 1000 ->  6.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	50,  /* 1011 ->  5.0x */
-	65,  /* 1100 ->  6.5x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	120, /* 1111 -> 12.0x */
-	100, /* 0000 -> 10.0x */
-	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
-	90,  /* 0011 ->  9.0x */
-	105, /* 0100 -> 10.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	135, /* 0111 -> 13.5x */
-	140, /* 1000 -> 14.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	130, /* 1011 -> 13.0x */
-	145, /* 1100 -> 14.5x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	120, /* 1111 -> 12.0x */
-};
-
-static int __initdata  nehemiah_c_clock_ratio[32] = {
-	100, /* 0000 -> 10.0x */
-	160, /* 0001 -> 16.0x */
-	40,  /* 0010 ->  RESERVED */
+	40,  /* 0010 ->  4.0x */
 	90,  /* 0011 ->  9.0x */
 	95,  /* 0100 ->  9.5x */
 	-1,  /* 0101 ->  RESERVED */
-	45,  /* 0110 ->  RESERVED */
+	45,  /* 0110 ->  4.5x */
 	55,  /* 0111 ->  5.5x */
 	60,  /* 1000 ->  6.0x */
 	70,  /* 1001 ->  7.0x */
@@ -340,84 +270,14 @@ static int __initdata  nehemiah_c_clock_ratio[32] = {
 	120, /* 1111 -> 12.0x */
 };
 
-static int __initdata nehemiah_a_eblcr[32] = {
-	50,  /* 0000 ->  5.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	100, /* 0011 -> 10.0x */
-	55,  /* 0100 ->  5.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	95,  /* 0111 ->  9.5x */
-	90,  /* 1000 ->  9.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	60,  /* 1011 ->  6.0x */
-	120, /* 1100 -> 12.0x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	65,  /* 1111 ->  6.5x */
-	90,  /* 0000 ->  9.0x */
-	-1,  /* 0001 -> RESERVED */
-	120, /* 0010 -> 12.0x */
-	100, /* 0011 -> 10.0x */
-	135, /* 0100 -> 13.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	105, /* 0111 -> 10.5x */
-	130, /* 1000 -> 13.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	140, /* 1011 -> 14.0x */
-	120, /* 1100 -> 12.0x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	145 /* 1111 -> 14.5x */
-   /* end of table  */
-};
-static int __initdata nehemiah_b_eblcr[32] = {
-	50,  /* 0000 ->  5.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	100, /* 0011 -> 10.0x */
-	55,  /* 0100 ->  5.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	95,  /* 0111 ->  9.5x */
-	90,  /* 1000 ->  9.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	60,  /* 1011 ->  6.0x */
-	120, /* 1100 -> 12.0x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	65,  /* 1111 ->  6.5x */
-	90,  /* 0000 ->  9.0x */
-	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
-	100, /* 0011 -> 10.0x */
-	135, /* 0100 -> 13.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	105, /* 0111 -> 10.5x */
-	130, /* 1000 -> 13.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	140, /* 1011 -> 14.0x */
-	120, /* 1100 -> 12.0x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	145 /* 1111 -> 14.5x */
-	   /* end of table  */
-};
-static int __initdata nehemiah_c_eblcr[32] = {
+static int __initdata nehemiah_eblcr[32] = {
 	50,  /* 0000 ->  5.0x */
 	160, /* 0001 -> 16.0x */
-	40,  /* 0010 ->  RESERVED */
+	40,  /* 0010 ->  4.0x */
 	100, /* 0011 -> 10.0x */
 	55,  /* 0100 ->  5.5x */
 	-1,  /* 0101 ->  RESERVED */
-	45,  /* 0110 ->  RESERVED */
+	45,  /* 0110 ->  4.5x */
 	95,  /* 0111 ->  9.5x */
 	90,  /* 1000 ->  9.0x */
 	70,  /* 1001 ->  7.0x */
@@ -443,7 +303,6 @@ static int __initdata nehemiah_c_eblcr[32] = {
 	155, /* 1101 -> 15.5x */
 	-1,  /* 1110 -> RESERVED (13.0x) */
 	145 /* 1111 -> 14.5x */
-	  /* end of table  */
 };
 
 /*

arch/i386/kernel/cpu/cpufreq/powernow-k8.c

@@ -1289,8 +1289,12 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (query_current_values_with_pending_wait(data))
 		goto out;
 
+	if (cpu_family == CPU_HW_PSTATE)
+		khz = find_khz_freq_from_fiddid(data->currfid, data->currdid);
+	else
 		khz = find_khz_freq_from_fid(data->currfid);
 
+
 out:
 	set_cpus_allowed(current, oldmask);
 	return khz;

drivers/cpufreq/Kconfig

@@ -16,7 +16,7 @@ config CPU_FREQ
 if CPU_FREQ
 
 config CPU_FREQ_TABLE
-       def_tristate m
+       tristate
 
 config CPU_FREQ_DEBUG
 	bool "Enable CPUfreq debugging"

drivers/cpufreq/cpufreq_conservative.c

@@ -429,14 +429,12 @@ static void dbs_check_cpu(int cpu)
 static void do_dbs_timer(struct work_struct *work)
 { 
 	int i;
-	lock_cpu_hotplug();
 	mutex_lock(&dbs_mutex);
 	for_each_online_cpu(i)
 		dbs_check_cpu(i);
 	schedule_delayed_work(&dbs_work, 
 			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
 	mutex_unlock(&dbs_mutex);
-	unlock_cpu_hotplug();
 } 
 
 static inline void dbs_timer_init(void)

drivers/cpufreq/cpufreq_ondemand.c

@@ -52,19 +52,20 @@ static unsigned int def_sampling_rate;
 static void do_dbs_timer(struct work_struct *work);
 
 /* Sampling types */
-enum dbs_sample {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
+enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
 
 struct cpu_dbs_info_s {
 	cputime64_t prev_cpu_idle;
 	cputime64_t prev_cpu_wall;
 	struct cpufreq_policy *cur_policy;
  	struct delayed_work work;
-	enum dbs_sample sample_type;
-	unsigned int enable;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_jiffies;
 	unsigned int freq_hi_jiffies;
+	int cpu;
+	unsigned int enable:1,
+	             sample_type:1;
 };
 static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
 
@@ -402,7 +403,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 	if (load < (dbs_tuners_ins.up_threshold - 10)) {
 		unsigned int freq_next, freq_cur;
 
-		freq_cur = cpufreq_driver_getavg(policy);
+		freq_cur = __cpufreq_driver_getavg(policy);
 		if (!freq_cur)
 			freq_cur = policy->cur;
 
@@ -423,9 +424,11 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 
 static void do_dbs_timer(struct work_struct *work)
 {
-	unsigned int cpu = smp_processor_id();
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, cpu);
-	enum dbs_sample sample_type = dbs_info->sample_type;
+	struct cpu_dbs_info_s *dbs_info =
+		container_of(work, struct cpu_dbs_info_s, work.work);
+	unsigned int cpu = dbs_info->cpu;
+	int sample_type = dbs_info->sample_type;
+
 	/* We want all CPUs to do sampling nearly on same jiffy */
 	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
 
@@ -434,15 +437,19 @@ static void do_dbs_timer(struct work_struct *work)
 
 	delay -= jiffies % delay;
 
-	if (!dbs_info->enable)
+	if (lock_policy_rwsem_write(cpu) < 0)
+		return;
+
+	if (!dbs_info->enable) {
+		unlock_policy_rwsem_write(cpu);
 		return;
+	}
+
 	/* Common NORMAL_SAMPLE setup */
 	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
 	if (!dbs_tuners_ins.powersave_bias ||
 	    sample_type == DBS_NORMAL_SAMPLE) {
-		lock_cpu_hotplug();
 		dbs_check_cpu(dbs_info);
-		unlock_cpu_hotplug();
 		if (dbs_info->freq_lo) {
 			/* Setup timer for SUB_SAMPLE */
 			dbs_info->sample_type = DBS_SUB_SAMPLE;
@@ -454,26 +461,27 @@ static void do_dbs_timer(struct work_struct *work)
 	                        	CPUFREQ_RELATION_H);
 	}
 	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
+	unlock_policy_rwsem_write(cpu);
 }
 
-static inline void dbs_timer_init(unsigned int cpu)
+static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
 {
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, cpu);
 	/* We want all CPUs to do sampling nearly on same jiffy */
 	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
 	delay -= jiffies % delay;
 
+	dbs_info->enable = 1;
 	ondemand_powersave_bias_init();
-	INIT_DELAYED_WORK_NAR(&dbs_info->work, do_dbs_timer);
 	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
-	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
+	INIT_DELAYED_WORK_NAR(&dbs_info->work, do_dbs_timer);
+	queue_delayed_work_on(dbs_info->cpu, kondemand_wq, &dbs_info->work,
+	                      delay);
 }
 
 static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
 {
 	dbs_info->enable = 0;
 	cancel_delayed_work(&dbs_info->work);
-	flush_workqueue(kondemand_wq);
 }
 
 static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
@@ -502,21 +510,9 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		mutex_lock(&dbs_mutex);
 		dbs_enable++;
-		if (dbs_enable == 1) {
-			kondemand_wq = create_workqueue("kondemand");
-			if (!kondemand_wq) {
-				printk(KERN_ERR
-					 "Creation of kondemand failed\n");
-				dbs_enable--;
-				mutex_unlock(&dbs_mutex);
-				return -ENOSPC;
-			}
-		}
 
 		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group);
 		if (rc) {
-			if (dbs_enable == 1)
-				destroy_workqueue(kondemand_wq);
 			dbs_enable--;
 			mutex_unlock(&dbs_mutex);
 			return rc;
@@ -530,7 +526,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j);
 			j_dbs_info->prev_cpu_wall = get_jiffies_64();
 		}
-		this_dbs_info->enable = 1;
+		this_dbs_info->cpu = cpu;
 		/*
 		 * Start the timerschedule work, when this governor
 		 * is used for first time
@@ -550,7 +546,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 			dbs_tuners_ins.sampling_rate = def_sampling_rate;
 		}
-		dbs_timer_init(policy->cpu);
+		dbs_timer_init(this_dbs_info);
 
 		mutex_unlock(&dbs_mutex);
 		break;
@@ -560,9 +556,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		dbs_timer_exit(this_dbs_info);
 		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
 		dbs_enable--;
-		if (dbs_enable == 0)
-			destroy_workqueue(kondemand_wq);
-
 		mutex_unlock(&dbs_mutex);
 
 		break;
@@ -591,12 +584,18 @@ static struct cpufreq_governor cpufreq_gov_dbs = {
 
 static int __init cpufreq_gov_dbs_init(void)
 {
+	kondemand_wq = create_workqueue("kondemand");
+	if (!kondemand_wq) {
+		printk(KERN_ERR "Creation of kondemand failed\n");
+		return -EFAULT;
+	}
 	return cpufreq_register_governor(&cpufreq_gov_dbs);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
 	cpufreq_unregister_governor(&cpufreq_gov_dbs);
+	destroy_workqueue(kondemand_wq);
 }
 
 
@@ -608,3 +607,4 @@ MODULE_LICENSE("GPL");
 
 module_init(cpufreq_gov_dbs_init);
 module_exit(cpufreq_gov_dbs_exit);
+

drivers/cpufreq/cpufreq_stats.c

@@ -370,12 +370,10 @@ __exit cpufreq_stats_exit(void)
 	cpufreq_unregister_notifier(&notifier_trans_block,
 			CPUFREQ_TRANSITION_NOTIFIER);
 	unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
-	lock_cpu_hotplug();
 	for_each_online_cpu(cpu) {
 		cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier,
 						CPU_DEAD, (void *)(long)cpu);
 	}
-	unlock_cpu_hotplug();
 }
 
 MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>");

drivers/cpufreq/cpufreq_userspace.c

@@ -71,7 +71,6 @@ static int cpufreq_set(unsigned int freq, struct cpufreq_policy *policy)
 
 	dprintk("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
-	lock_cpu_hotplug();
 	mutex_lock(&userspace_mutex);
 	if (!cpu_is_managed[policy->cpu])
 		goto err;
@@ -94,7 +93,6 @@ static int cpufreq_set(unsigned int freq, struct cpufreq_policy *policy)
 
  err:
 	mutex_unlock(&userspace_mutex);
-	unlock_cpu_hotplug();
 	return ret;
 }
 

include/linux/cpufreq.h

@@ -84,9 +84,6 @@ struct cpufreq_policy {
         unsigned int		policy; /* see above */
 	struct cpufreq_governor	*governor; /* see below */
 
- 	struct mutex		lock;   /* CPU ->setpolicy or ->target may
-					   only be called once a time */
-
 	struct work_struct	update; /* if update_policy() needs to be
 					 * called, but you're in IRQ context */
 
@@ -172,11 +169,16 @@ extern int __cpufreq_driver_target(struct cpufreq_policy *policy,
 				   unsigned int relation);
 
 
-extern int cpufreq_driver_getavg(struct cpufreq_policy *policy);
+extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy);
 
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
+int lock_policy_rwsem_read(int cpu);
+int lock_policy_rwsem_write(int cpu);
+void unlock_policy_rwsem_read(int cpu);
+void unlock_policy_rwsem_write(int cpu);
+
 
 /*********************************************************************
  *                      CPUFREQ DRIVER INTERFACE                     *