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.c

@@ -8,12 +8,11 @@
  *  VIA have currently 3 different versions of Longhaul.
  *  Version 1 (Longhaul) uses the BCR2 MSR at 0x1147.
  *   It is present only in Samuel 1 (C5A), Samuel 2 (C5B) stepping 0.
- *  Version 2 of longhaul is the same as v1, but adds voltage scaling.
- *   Present in Samuel 2 (steppings 1-7 only) (C5B), and Ezra (C5C)
- *   voltage scaling support has currently been disabled in this driver
- *   until we have code that gets it right.
+ *  Version 2 of longhaul is backward compatible with v1, but adds
+ *   LONGHAUL MSR for purpose of both frequency and voltage scaling.
+ *   Present in Samuel 2 (steppings 1-7 only) (C5B), and Ezra (C5C).
  *  Version 3 of longhaul got renamed to Powersaver and redesigned
- *   to use the POWERSAVER MSR at 0x110a.
+ *   to use only the POWERSAVER MSR at 0x110a.
  *   It is present in Ezra-T (C5M), Nehemiah (C5X) and above.
  *   It's pretty much the same feature wise to longhaul v2, though
  *   there is provision for scaling FSB too, but this doesn't work
@@ -51,10 +50,12 @@
 #define	CPU_EZRA	3
 #define	CPU_EZRA_T	4
 #define	CPU_NEHEMIAH	5
+#define	CPU_NEHEMIAH_C	6
 
 /* Flags */
 #define USE_ACPI_C3		(1 << 1)
 #define USE_NORTHBRIDGE		(1 << 2)
+#define USE_VT8235		(1 << 3)
 
 static int cpu_model;
 static unsigned int numscales=16;
@@ -63,7 +64,8 @@ static unsigned int fsb;
 static struct mV_pos *vrm_mV_table;
 static unsigned char *mV_vrm_table;
 struct f_msr {
-	unsigned char vrm;
+	u8 vrm;
+	u8 pos;
 };
 static struct f_msr f_msr_table[32];
 
@@ -73,10 +75,10 @@ static int can_scale_voltage;
 static struct acpi_processor *pr = NULL;
 static struct acpi_processor_cx *cx = NULL;
 static u8 longhaul_flags;
+static u8 longhaul_pos;
 
 /* Module parameters */
 static int scale_voltage;
-static int ignore_latency;
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg)
 
@@ -164,26 +166,47 @@ static void do_longhaul1(unsigned int clock_ratio_index)
 static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
 {
 	union msr_longhaul longhaul;
+	u8 dest_pos;
 	u32 t;
 
+	dest_pos = f_msr_table[clock_ratio_index].pos;
+
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+	/* Setup new frequency */
 	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
 	longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf;
 	longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
-	longhaul.bits.EnableSoftBusRatio = 1;
-
-	if (can_scale_voltage) {
+	/* Setup new voltage */
+	if (can_scale_voltage)
 		longhaul.bits.SoftVID = f_msr_table[clock_ratio_index].vrm;
+	/* Sync to timer tick */
+	safe_halt();
+	/* Raise voltage if necessary */
+	if (can_scale_voltage && longhaul_pos < dest_pos) {
 		longhaul.bits.EnableSoftVID = 1;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		/* Change voltage */
+		if (!cx_address) {
+			ACPI_FLUSH_CPU_CACHE();
+			halt();
+		} else {
+			ACPI_FLUSH_CPU_CACHE();
+			/* Invoke C3 */
+			inb(cx_address);
+			/* Dummy op - must do something useless after P_LVL3
+			 * read */
+			t = inl(acpi_gbl_FADT.xpm_timer_block.address);
+		}
+		longhaul.bits.EnableSoftVID = 0;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		longhaul_pos = dest_pos;
 	}
 
-	/* Sync to timer tick */
-	safe_halt();
 	/* Change frequency on next halt or sleep */
+	longhaul.bits.EnableSoftBusRatio = 1;
 	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	if (!cx_address) {
 		ACPI_FLUSH_CPU_CACHE();
-		/* Invoke C1 */
 		halt();
 	} else {
 		ACPI_FLUSH_CPU_CACHE();
@@ -193,12 +216,29 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
 		t = inl(acpi_gbl_FADT.xpm_timer_block.address);
 	}
 	/* Disable bus ratio bit */
-	local_irq_disable();
-	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
 	longhaul.bits.EnableSoftBusRatio = 0;
-	longhaul.bits.EnableSoftBSEL = 0;
-	longhaul.bits.EnableSoftVID = 0;
 	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+
+	/* Reduce voltage if necessary */
+	if (can_scale_voltage && longhaul_pos > dest_pos) {
+		longhaul.bits.EnableSoftVID = 1;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		/* Change voltage */
+		if (!cx_address) {
+			ACPI_FLUSH_CPU_CACHE();
+			halt();
+		} else {
+			ACPI_FLUSH_CPU_CACHE();
+			/* Invoke C3 */
+			inb(cx_address);
+			/* Dummy op - must do something useless after P_LVL3
+			 * read */
+			t = inl(acpi_gbl_FADT.xpm_timer_block.address);
+		}
+		longhaul.bits.EnableSoftVID = 0;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		longhaul_pos = dest_pos;
+	}
 }
 
 /**
@@ -257,26 +297,19 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	/*
 	 * Longhaul v1. (Samuel[C5A] and Samuel2 stepping 0[C5B])
 	 * Software controlled multipliers only.
-	 *
-	 * *NB* Until we get voltage scaling working v1 & v2 are the same code.
-	 * Longhaul v2 appears in Samuel2 Steppings 1->7 [C5b] and Ezra [C5C]
 	 */
 	case TYPE_LONGHAUL_V1:
-	case TYPE_LONGHAUL_V2:
 		do_longhaul1(clock_ratio_index);
 		break;
 
 	/*
+	 * Longhaul v2 appears in Samuel2 Steppings 1->7 [C5B] and Ezra [C5C]
+	 *
 	 * Longhaul v3 (aka Powersaver). (Ezra-T [C5M] & Nehemiah [C5N])
-	 * We can scale voltage with this too, but that's currently
-	 * disabled until we come up with a decent 'match freq to voltage'
-	 * algorithm.
-	 * When we add voltage scaling, we will also need to do the
-	 * voltage/freq setting in order depending on the direction
-	 * of scaling (like we do in powernow-k7.c)
 	 * Nehemiah can do FSB scaling too, but this has never been proven
 	 * to work in practice.
 	 */
+	case TYPE_LONGHAUL_V2:
 	case TYPE_POWERSAVER:
 		if (longhaul_flags & USE_ACPI_C3) {
 			/* Don't allow wakeup */
@@ -301,6 +334,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	local_irq_restore(flags);
 	preempt_enable();
 
+	freqs.new = calc_speed(longhaul_get_cpu_mult());
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 }
 
@@ -315,31 +349,19 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 
 #define ROUNDING	0xf
 
-static int _guess(int guess, int mult)
-{
-	int target;
-
-	target = ((mult/10)*guess);
-	if (mult%10 != 0)
-		target += (guess/2);
-	target += ROUNDING/2;
-	target &= ~ROUNDING;
-	return target;
-}
-
-
 static int guess_fsb(int mult)
 {
-	int speed = (cpu_khz/1000);
+	int speed = cpu_khz / 1000;
 	int i;
-	int speeds[] = { 66, 100, 133, 200 };
-
-	speed += ROUNDING/2;
-	speed &= ~ROUNDING;
-
-	for (i=0; i<4; i++) {
-		if (_guess(speeds[i], mult) == speed)
-			return speeds[i];
+	int speeds[] = { 666, 1000, 1333, 2000 };
+	int f_max, f_min;
+
+	for (i = 0; i < 4; i++) {
+		f_max = ((speeds[i] * mult) + 50) / 100;
+		f_max += (ROUNDING / 2);
+		f_min = f_max - ROUNDING;
+		if ((speed <= f_max) && (speed >= f_min))
+			return speeds[i] / 10;
 	}
 	return 0;
 }
@@ -347,67 +369,40 @@ static int guess_fsb(int mult)
 
 static int __init longhaul_get_ranges(void)
 {
-	unsigned long invalue;
-	unsigned int ezra_t_multipliers[32]= {
-			90,  30,  40, 100,  55,  35,  45,  95,
-			50,  70,  80,  60, 120,  75,  85,  65,
-			-1, 110, 120,  -1, 135, 115, 125, 105,
-			130, 150, 160, 140,  -1, 155,  -1, 145 };
 	unsigned int j, k = 0;
-	union msr_longhaul longhaul;
-	int mult = 0;
+	int mult;
 
-	switch (longhaul_version) {
-	case TYPE_LONGHAUL_V1:
-	case TYPE_LONGHAUL_V2:
-		/* Ugh, Longhaul v1 didn't have the min/max MSRs.
-		   Assume min=3.0x & max = whatever we booted at. */
+	/* Get current frequency */
+	mult = longhaul_get_cpu_mult();
+	if (mult == -1) {
+		printk(KERN_INFO PFX "Invalid (reserved) multiplier!\n");
+		return -EINVAL;
+	}
+	fsb = guess_fsb(mult);
+	if (fsb == 0) {
+		printk(KERN_INFO PFX "Invalid (reserved) FSB!\n");
+		return -EINVAL;
+	}
+	/* Get max multiplier - as we always did.
+	 * Longhaul MSR is usefull only when voltage scaling is enabled.
+	 * C3 is booting at max anyway. */
+	maxmult = mult;
+	/* Get min multiplier */
+	switch (cpu_model) {
+	case CPU_NEHEMIAH:
+		minmult = 50;
+		break;
+	case CPU_NEHEMIAH_C:
+		minmult = 40;
+		break;
+	default:
 		minmult = 30;
-		maxmult = mult = longhaul_get_cpu_mult();
 		break;
-
-	case TYPE_POWERSAVER:
-		/* Ezra-T */
-		if (cpu_model==CPU_EZRA_T) {
-			minmult = 30;
-			rdmsrl (MSR_VIA_LONGHAUL, longhaul.val);
-			invalue = longhaul.bits.MaxMHzBR;
-			if (longhaul.bits.MaxMHzBR4)
-				invalue += 16;
-			maxmult = mult = ezra_t_multipliers[invalue];
-			break;
-		}
-
-		/* Nehemiah */
-		if (cpu_model==CPU_NEHEMIAH) {
-			rdmsrl (MSR_VIA_LONGHAUL, longhaul.val);
-
-			/*
-			 * TODO: This code works, but raises a lot of questions.
-			 * - Some Nehemiah's seem to have broken Min/MaxMHzBR's.
-			 *   We get around this by using a hardcoded multiplier of 4.0x
-			 *   for the minimimum speed, and the speed we booted up at for the max.
-			 *   This is done in longhaul_get_cpu_mult() by reading the EBLCR register.
-			 * - According to some VIA documentation EBLCR is only
-			 *   in pre-Nehemiah C3s. How this still works is a mystery.
-			 *   We're possibly using something undocumented and unsupported,
-			 *   But it works, so we don't grumble.
-			 */
-			minmult=40;
-			maxmult = mult = longhaul_get_cpu_mult();
-			break;
-		}
 	}
-	fsb = guess_fsb(mult);
 
 	dprintk ("MinMult:%d.%dx MaxMult:%d.%dx\n",
 		 minmult/10, minmult%10, maxmult/10, maxmult%10);
 
-	if (fsb == 0) {
-		printk (KERN_INFO PFX "Invalid (reserved) FSB!\n");
-		return -EINVAL;
-	}
-
 	highest_speed = calc_speed(maxmult);
 	lowest_speed = calc_speed(minmult);
 	dprintk ("FSB:%dMHz  Lowest speed: %s   Highest speed:%s\n", fsb,
@@ -455,6 +450,7 @@ static void __init longhaul_setup_voltagescaling(void)
 	union msr_longhaul longhaul;
 	struct mV_pos minvid, maxvid;
 	unsigned int j, speed, pos, kHz_step, numvscales;
+	int min_vid_speed;
 
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	if (!(longhaul.bits.RevisionID & 1)) {
@@ -468,14 +464,14 @@ static void __init longhaul_setup_voltagescaling(void)
 		mV_vrm_table = &mV_vrm85[0];
 	} else {
 		printk (KERN_INFO PFX "Mobile VRM\n");
+		if (cpu_model < CPU_NEHEMIAH)
+			return;
 		vrm_mV_table = &mobilevrm_mV[0];
 		mV_vrm_table = &mV_mobilevrm[0];
 	}
 
 	minvid = vrm_mV_table[longhaul.bits.MinimumVID];
 	maxvid = vrm_mV_table[longhaul.bits.MaximumVID];
-	numvscales = maxvid.pos - minvid.pos + 1;
-	kHz_step = (highest_speed - lowest_speed) / numvscales;
 
 	if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) {
 		printk (KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. "
@@ -491,20 +487,59 @@ static void __init longhaul_setup_voltagescaling(void)
 		return;
 	}
 
-	printk(KERN_INFO PFX "Max VID=%d.%03d  Min VID=%d.%03d, %d possible voltage scales\n",
+	/* How many voltage steps */
+	numvscales = maxvid.pos - minvid.pos + 1;
+	printk(KERN_INFO PFX
+		"Max VID=%d.%03d  "
+		"Min VID=%d.%03d, "
+		"%d possible voltage scales\n",
 		maxvid.mV/1000, maxvid.mV%1000,
 		minvid.mV/1000, minvid.mV%1000,
 		numvscales);
 
+	/* Calculate max frequency at min voltage */
+	j = longhaul.bits.MinMHzBR;
+	if (longhaul.bits.MinMHzBR4)
+		j += 16;
+	min_vid_speed = eblcr_table[j];
+	if (min_vid_speed == -1)
+		return;
+	switch (longhaul.bits.MinMHzFSB) {
+	case 0:
+		min_vid_speed *= 13333;
+		break;
+	case 1:
+		min_vid_speed *= 10000;
+		break;
+	case 3:
+		min_vid_speed *= 6666;
+		break;
+	default:
+		return;
+		break;
+	}
+	if (min_vid_speed >= highest_speed)
+		return;
+	/* Calculate kHz for one voltage step */
+	kHz_step = (highest_speed - min_vid_speed) / numvscales;
+
+
 	j = 0;
 	while (longhaul_table[j].frequency != CPUFREQ_TABLE_END) {
 		speed = longhaul_table[j].frequency;
-		pos = (speed - lowest_speed) / kHz_step + minvid.pos;
+		if (speed > min_vid_speed)
+			pos = (speed - min_vid_speed) / kHz_step + minvid.pos;
+		else
+			pos = minvid.pos;
 		f_msr_table[longhaul_table[j].index].vrm = mV_vrm_table[pos];
+		f_msr_table[longhaul_table[j].index].pos = pos;
 		j++;
 	}
 
+	longhaul_pos = maxvid.pos;
 	can_scale_voltage = 1;
+	printk(KERN_INFO PFX "Voltage scaling enabled. "
+		"Use of \"conservative\" governor is highly recommended.\n");
 }
 
 
@@ -573,20 +608,51 @@ static int enable_arbiter_disable(void)
 	if (dev != NULL) {
 		/* Enable access to port 0x22 */
 		pci_read_config_byte(dev, reg, &pci_cmd);
-		if ( !(pci_cmd & 1<<7) ) {
+		if (!(pci_cmd & 1<<7)) {
 			pci_cmd |= 1<<7;
 			pci_write_config_byte(dev, reg, pci_cmd);
+			pci_read_config_byte(dev, reg, &pci_cmd);
+			if (!(pci_cmd & 1<<7)) {
+				printk(KERN_ERR PFX
+					"Can't enable access to port 0x22.\n");
+				return 0;
+			}
 		}
 		return 1;
 	}
 	return 0;
 }
 
+static int longhaul_setup_vt8235(void)
+{
+	struct pci_dev *dev;
+	u8 pci_cmd;
+
+	/* Find VT8235 southbridge */
+	dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL);
+	if (dev != NULL) {
+		/* Set transition time to max */
+		pci_read_config_byte(dev, 0xec, &pci_cmd);
+		pci_cmd &= ~(1 << 2);
+		pci_write_config_byte(dev, 0xec, pci_cmd);
+		pci_read_config_byte(dev, 0xe4, &pci_cmd);
+		pci_cmd &= ~(1 << 7);
+		pci_write_config_byte(dev, 0xe4, pci_cmd);
+		pci_read_config_byte(dev, 0xe5, &pci_cmd);
+		pci_cmd |= 1 << 7;
+		pci_write_config_byte(dev, 0xe5, pci_cmd);
+		return 1;
+	}
+	return 0;
+}
+
 static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpuinfo_x86 *c = cpu_data;
 	char *cpuname=NULL;
 	int ret;
+	u32 lo, hi;
+	int vt8235_present;
 
 	/* Check what we have on this motherboard */
 	switch (c->x86_model) {
@@ -599,16 +665,20 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 
 	case 7:
-		longhaul_version = TYPE_LONGHAUL_V1;
 		switch (c->x86_mask) {
 		case 0:
+			longhaul_version = TYPE_LONGHAUL_V1;
 			cpu_model = CPU_SAMUEL2;
 			cpuname = "C3 'Samuel 2' [C5B]";
-			/* Note, this is not a typo, early Samuel2's had Samuel1 ratios. */
-			memcpy (clock_ratio, samuel1_clock_ratio, sizeof(samuel1_clock_ratio));
-			memcpy (eblcr_table, samuel2_eblcr, sizeof(samuel2_eblcr));
+			/* Note, this is not a typo, early Samuel2's had
+			 * Samuel1 ratios. */
+			memcpy(clock_ratio, samuel1_clock_ratio,
+				sizeof(samuel1_clock_ratio));
+			memcpy(eblcr_table, samuel2_eblcr,
+				sizeof(samuel2_eblcr));
 			break;
 		case 1 ... 15:
+			longhaul_version = TYPE_LONGHAUL_V2;
 			if (c->x86_mask < 8) {
 				cpu_model = CPU_SAMUEL2;
 				cpuname = "C3 'Samuel 2' [C5B]";
@@ -616,8 +686,10 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 				cpu_model = CPU_EZRA;
 				cpuname = "C3 'Ezra' [C5C]";
 			}
-			memcpy (clock_ratio, ezra_clock_ratio, sizeof(ezra_clock_ratio));
-			memcpy (eblcr_table, ezra_eblcr, sizeof(ezra_eblcr));
+			memcpy(clock_ratio, ezra_clock_ratio,
+				sizeof(ezra_clock_ratio));
+			memcpy(eblcr_table, ezra_eblcr,
+				sizeof(ezra_eblcr));
 			break;
 		}
 		break;
@@ -632,24 +704,24 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 
 	case 9:
-		cpu_model = CPU_NEHEMIAH;
 		longhaul_version = TYPE_POWERSAVER;
-		numscales=32;
+		numscales = 32;
+		memcpy(clock_ratio,
+		       nehemiah_clock_ratio,
+		       sizeof(nehemiah_clock_ratio));
+		memcpy(eblcr_table, nehemiah_eblcr, sizeof(nehemiah_eblcr));
 		switch (c->x86_mask) {
 		case 0 ... 1:
-			cpuname = "C3 'Nehemiah A' [C5N]";
-			memcpy (clock_ratio, nehemiah_a_clock_ratio, sizeof(nehemiah_a_clock_ratio));
-			memcpy (eblcr_table, nehemiah_a_eblcr, sizeof(nehemiah_a_eblcr));
+			cpu_model = CPU_NEHEMIAH;
+			cpuname = "C3 'Nehemiah A' [C5XLOE]";
 			break;
 		case 2 ... 4:
-			cpuname = "C3 'Nehemiah B' [C5N]";
-			memcpy (clock_ratio, nehemiah_b_clock_ratio, sizeof(nehemiah_b_clock_ratio));
-			memcpy (eblcr_table, nehemiah_b_eblcr, sizeof(nehemiah_b_eblcr));
+			cpu_model = CPU_NEHEMIAH;
+			cpuname = "C3 'Nehemiah B' [C5XLOH]";
 			break;
 		case 5 ... 15:
-			cpuname = "C3 'Nehemiah C' [C5N]";
-			memcpy (clock_ratio, nehemiah_c_clock_ratio, sizeof(nehemiah_c_clock_ratio));
-			memcpy (eblcr_table, nehemiah_c_eblcr, sizeof(nehemiah_c_eblcr));
+			cpu_model = CPU_NEHEMIAH_C;
+			cpuname = "C3 'Nehemiah C' [C5P]";
 			break;
 		}
 		break;
@@ -658,6 +730,13 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		cpuname = "Unknown";
 		break;
 	}
+	/* Check Longhaul ver. 2 */
+	if (longhaul_version == TYPE_LONGHAUL_V2) {
+		rdmsr(MSR_VIA_LONGHAUL, lo, hi);
+		if (lo == 0 && hi == 0)
+			/* Looks like MSR isn't present */
+			longhaul_version = TYPE_LONGHAUL_V1;
+	}
 
 	printk (KERN_INFO PFX "VIA %s CPU detected.  ", cpuname);
 	switch (longhaul_version) {
@@ -670,15 +749,18 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 	};
 
+	/* Doesn't hurt */
+	vt8235_present = longhaul_setup_vt8235();
+
 	/* Find ACPI data for processor */
-	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
-			    &longhaul_walk_callback, NULL, (void *)&pr);
+	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
+				ACPI_UINT32_MAX, &longhaul_walk_callback,
+				NULL, (void *)&pr);
 
 	/* Check ACPI support for C3 state */
-	if ((pr != NULL) && (longhaul_version == TYPE_POWERSAVER)) {
+	if (pr != NULL && longhaul_version != TYPE_LONGHAUL_V1) {
 		cx = &pr->power.states[ACPI_STATE_C3];
-		if (cx->address > 0 &&
-		   (cx->latency <= 1000 || ignore_latency != 0) ) {
+		if (cx->address > 0 && cx->latency <= 1000) {
 			longhaul_flags |= USE_ACPI_C3;
 			goto print_support_type;
 		}
@@ -688,8 +770,11 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		longhaul_flags |= USE_NORTHBRIDGE;
 		goto print_support_type;
 	}
-
-	/* No ACPI C3 or we can't use it */
+	/* Use VT8235 southbridge if present */
+	if (longhaul_version == TYPE_POWERSAVER && vt8235_present) {
+		longhaul_flags |= USE_VT8235;
+		goto print_support_type;
+	}
 	/* Check ACPI support for bus master arbiter disable */
 	if ((pr == NULL) || !(pr->flags.bm_control)) {
 		printk(KERN_ERR PFX
@@ -698,18 +783,18 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	}
 
 print_support_type:
-	if (!(longhaul_flags & USE_NORTHBRIDGE)) {
-		printk (KERN_INFO PFX "Using ACPI support.\n");
-	} else {
+	if (longhaul_flags & USE_NORTHBRIDGE)
 		printk (KERN_INFO PFX "Using northbridge support.\n");
-	}
+	else if (longhaul_flags & USE_VT8235)
+		printk (KERN_INFO PFX "Using VT8235 support.\n");
+	else
+		printk (KERN_INFO PFX "Using ACPI support.\n");
 
 	ret = longhaul_get_ranges();
 	if (ret != 0)
 		return ret;
 
-	if ((longhaul_version==TYPE_LONGHAUL_V2 || longhaul_version==TYPE_POWERSAVER) &&
-		 (scale_voltage != 0))
+	if ((longhaul_version != TYPE_LONGHAUL_V1) && (scale_voltage != 0))
 		longhaul_setup_voltagescaling();
 
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
@@ -797,8 +882,6 @@ static void __exit longhaul_exit(void)
 
 module_param (scale_voltage, int, 0644);
 MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
-module_param(ignore_latency, int, 0644);
-MODULE_PARM_DESC(ignore_latency, "Skip ACPI C3 latency test");
 
 MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>");
 MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors.");

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

@@ -1289,7 +1289,11 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (query_current_values_with_pending_wait(data))
 		goto out;
 
-	khz = find_khz_freq_from_fid(data->currfid);
+	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);

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.c

@@ -41,8 +41,67 @@ static struct cpufreq_driver *cpufreq_driver;
 static struct cpufreq_policy *cpufreq_cpu_data[NR_CPUS];
 static DEFINE_SPINLOCK(cpufreq_driver_lock);
 
+/*
+ * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
+ * all cpufreq/hotplug/workqueue/etc related lock issues.
+ *
+ * The rules for this semaphore:
+ * - Any routine that wants to read from the policy structure will
+ *   do a down_read on this semaphore.
+ * - Any routine that will write to the policy structure and/or may take away
+ *   the policy altogether (eg. CPU hotplug), will hold this lock in write
+ *   mode before doing so.
+ *
+ * Additional rules:
+ * - All holders of the lock should check to make sure that the CPU they
+ *   are concerned with are online after they get the lock.
+ * - Governor routines that can be called in cpufreq hotplug path should not
+ *   take this sem as top level hotplug notifier handler takes this.
+ */
+static DEFINE_PER_CPU(int, policy_cpu);
+static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
+
+#define lock_policy_rwsem(mode, cpu)					\
+int lock_policy_rwsem_##mode						\
+(int cpu)								\
+{									\
+	int policy_cpu = per_cpu(policy_cpu, cpu);			\
+	BUG_ON(policy_cpu == -1);					\
+	down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
+	if (unlikely(!cpu_online(cpu))) {				\
+		up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));	\
+		return -1;						\
+	}								\
+									\
+	return 0;							\
+}
+
+lock_policy_rwsem(read, cpu);
+EXPORT_SYMBOL_GPL(lock_policy_rwsem_read);
+
+lock_policy_rwsem(write, cpu);
+EXPORT_SYMBOL_GPL(lock_policy_rwsem_write);
+
+void unlock_policy_rwsem_read(int cpu)
+{
+	int policy_cpu = per_cpu(policy_cpu, cpu);
+	BUG_ON(policy_cpu == -1);
+	up_read(&per_cpu(cpu_policy_rwsem, policy_cpu));
+}
+EXPORT_SYMBOL_GPL(unlock_policy_rwsem_read);
+
+void unlock_policy_rwsem_write(int cpu)
+{
+	int policy_cpu = per_cpu(policy_cpu, cpu);
+	BUG_ON(policy_cpu == -1);
+	up_write(&per_cpu(cpu_policy_rwsem, policy_cpu));
+}
+EXPORT_SYMBOL_GPL(unlock_policy_rwsem_write);
+
+
 /* internal prototypes */
 static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
+static unsigned int __cpufreq_get(unsigned int cpu);
 static void handle_update(struct work_struct *work);
 
 /**
@@ -415,12 +474,8 @@ static ssize_t store_##file_name					\
 	if (ret != 1)							\
 		return -EINVAL;						\
 									\
-	lock_cpu_hotplug();						\
-	mutex_lock(&policy->lock);					\
 	ret = __cpufreq_set_policy(policy, &new_policy);		\
 	policy->user_policy.object = policy->object;			\
-	mutex_unlock(&policy->lock);					\
-	unlock_cpu_hotplug();						\
 									\
 	return ret ? ret : count;					\
 }
@@ -434,7 +489,7 @@ store_one(scaling_max_freq,max);
 static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy,
 							char *buf)
 {
-	unsigned int cur_freq = cpufreq_get(policy->cpu);
+	unsigned int cur_freq = __cpufreq_get(policy->cpu);
 	if (!cur_freq)
 		return sprintf(buf, "<unknown>");
 	return sprintf(buf, "%u\n", cur_freq);
@@ -479,18 +534,12 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy,
 						&new_policy.governor))
 		return -EINVAL;
 
-	lock_cpu_hotplug();
-
 	/* Do not use cpufreq_set_policy here or the user_policy.max
 	   will be wrongly overridden */
-	mutex_lock(&policy->lock);
 	ret = __cpufreq_set_policy(policy, &new_policy);
 
 	policy->user_policy.policy = policy->policy;
 	policy->user_policy.governor = policy->governor;
-	mutex_unlock(&policy->lock);
-
-	unlock_cpu_hotplug();
 
 	if (ret)
 		return ret;
@@ -595,11 +644,17 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf)
 	policy = cpufreq_cpu_get(policy->cpu);
 	if (!policy)
 		return -EINVAL;
+
+	if (lock_policy_rwsem_read(policy->cpu) < 0)
+		return -EINVAL;
+
 	if (fattr->show)
 		ret = fattr->show(policy, buf);
 	else
 		ret = -EIO;
 
+	unlock_policy_rwsem_read(policy->cpu);
+
 	cpufreq_cpu_put(policy);
 	return ret;
 }
@@ -613,11 +668,17 @@ static ssize_t store(struct kobject * kobj, struct attribute * attr,
 	policy = cpufreq_cpu_get(policy->cpu);
 	if (!policy)
 		return -EINVAL;
+
+	if (lock_policy_rwsem_write(policy->cpu) < 0)
+		return -EINVAL;
+
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
 	else
 		ret = -EIO;
 
+	unlock_policy_rwsem_write(policy->cpu);
+
 	cpufreq_cpu_put(policy);
 	return ret;
 }
@@ -691,8 +752,10 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 	policy->cpu = cpu;
 	policy->cpus = cpumask_of_cpu(cpu);
 
-	mutex_init(&policy->lock);
-	mutex_lock(&policy->lock);
+	/* Initially set CPU itself as the policy_cpu */
+	per_cpu(policy_cpu, cpu) = cpu;
+	lock_policy_rwsem_write(cpu);
+
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
@@ -702,7 +765,7 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
 		dprintk("initialization failed\n");
-		mutex_unlock(&policy->lock);
+		unlock_policy_rwsem_write(cpu);
 		goto err_out;
 	}
 
@@ -716,6 +779,14 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		 */
 		managed_policy = cpufreq_cpu_get(j);
 		if (unlikely(managed_policy)) {
+
+			/* Set proper policy_cpu */
+			unlock_policy_rwsem_write(cpu);
+			per_cpu(policy_cpu, cpu) = managed_policy->cpu;
+
+			if (lock_policy_rwsem_write(cpu) < 0)
+				goto err_out_driver_exit;
+
 			spin_lock_irqsave(&cpufreq_driver_lock, flags);
 			managed_policy->cpus = policy->cpus;
 			cpufreq_cpu_data[cpu] = managed_policy;
@@ -726,13 +797,13 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 						&managed_policy->kobj,
 						"cpufreq");
 			if (ret) {
-				mutex_unlock(&policy->lock);
+				unlock_policy_rwsem_write(cpu);
 				goto err_out_driver_exit;
 			}
 
 			cpufreq_debug_enable_ratelimit();
-			mutex_unlock(&policy->lock);
 			ret = 0;
+			unlock_policy_rwsem_write(cpu);
 			goto err_out_driver_exit; /* call driver->exit() */
 		}
 	}
@@ -746,7 +817,7 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 
 	ret = kobject_register(&policy->kobj);
 	if (ret) {
-		mutex_unlock(&policy->lock);
+		unlock_policy_rwsem_write(cpu);
 		goto err_out_driver_exit;
 	}
 	/* set up files for this cpu device */
@@ -761,8 +832,10 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu_mask(j, policy->cpus)
+	for_each_cpu_mask(j, policy->cpus) {
 		cpufreq_cpu_data[j] = policy;
+		per_cpu(policy_cpu, j) = policy->cpu;
+	}
 	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	/* symlink affected CPUs */
@@ -778,14 +851,14 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		ret = sysfs_create_link(&cpu_sys_dev->kobj, &policy->kobj,
 					"cpufreq");
 		if (ret) {
-			mutex_unlock(&policy->lock);
+			unlock_policy_rwsem_write(cpu);
 			goto err_out_unregister;
 		}
 	}
 
 	policy->governor = NULL; /* to assure that the starting sequence is
 				  * run in cpufreq_set_policy */
-	mutex_unlock(&policy->lock);
+	unlock_policy_rwsem_write(cpu);
 
 	/* set default policy */
 	ret = cpufreq_set_policy(&new_policy);
@@ -826,11 +899,13 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 
 
 /**
- * cpufreq_remove_dev - remove a CPU device
+ * __cpufreq_remove_dev - remove a CPU device
  *
  * Removes the cpufreq interface for a CPU device.
+ * Caller should already have policy_rwsem in write mode for this CPU.
+ * This routine frees the rwsem before returning.
  */
-static int cpufreq_remove_dev (struct sys_device * sys_dev)
+static int __cpufreq_remove_dev (struct sys_device * sys_dev)
 {
 	unsigned int cpu = sys_dev->id;
 	unsigned long flags;
@@ -849,6 +924,7 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
 	if (!data) {
 		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 		cpufreq_debug_enable_ratelimit();
+		unlock_policy_rwsem_write(cpu);
 		return -EINVAL;
 	}
 	cpufreq_cpu_data[cpu] = NULL;
@@ -865,6 +941,7 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
 		sysfs_remove_link(&sys_dev->kobj, "cpufreq");
 		cpufreq_cpu_put(data);
 		cpufreq_debug_enable_ratelimit();
+		unlock_policy_rwsem_write(cpu);
 		return 0;
 	}
 #endif
@@ -873,6 +950,7 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
 	if (!kobject_get(&data->kobj)) {
 		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 		cpufreq_debug_enable_ratelimit();
+		unlock_policy_rwsem_write(cpu);
 		return -EFAULT;
 	}
 
@@ -906,10 +984,10 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
 	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 #endif
 
-	mutex_lock(&data->lock);
 	if (cpufreq_driver->target)
 		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
-	mutex_unlock(&data->lock);
+
+	unlock_policy_rwsem_write(cpu);
 
 	kobject_unregister(&data->kobj);
 
@@ -933,6 +1011,18 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
 }
 
 
+static int cpufreq_remove_dev (struct sys_device * sys_dev)
+{
+	unsigned int cpu = sys_dev->id;
+	int retval;
+	if (unlikely(lock_policy_rwsem_write(cpu)))
+		BUG();
+
+	retval = __cpufreq_remove_dev(sys_dev);
+	return retval;
+}
+
+
 static void handle_update(struct work_struct *work)
 {
 	struct cpufreq_policy *policy =
@@ -980,9 +1070,12 @@ unsigned int cpufreq_quick_get(unsigned int cpu)
 	unsigned int ret_freq = 0;
 
 	if (policy) {
-		mutex_lock(&policy->lock);
+		if (unlikely(lock_policy_rwsem_read(cpu)))
+			return ret_freq;
+
 		ret_freq = policy->cur;
-		mutex_unlock(&policy->lock);
+
+		unlock_policy_rwsem_read(cpu);
 		cpufreq_cpu_put(policy);
 	}
 
@@ -991,24 +1084,13 @@ unsigned int cpufreq_quick_get(unsigned int cpu)
 EXPORT_SYMBOL(cpufreq_quick_get);
 
 
-/**
- * cpufreq_get - get the current CPU frequency (in kHz)
- * @cpu: CPU number
- *
- * Get the CPU current (static) CPU frequency
- */
-unsigned int cpufreq_get(unsigned int cpu)
+static unsigned int __cpufreq_get(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_data[cpu];
 	unsigned int ret_freq = 0;
 
-	if (!policy)
-		return 0;
-
 	if (!cpufreq_driver->get)
-		goto out;
-
-	mutex_lock(&policy->lock);
+		return (ret_freq);
 
 	ret_freq = cpufreq_driver->get(cpu);
 
@@ -1022,11 +1104,33 @@ unsigned int cpufreq_get(unsigned int cpu)
 		}
 	}
 
-	mutex_unlock(&policy->lock);
+	return (ret_freq);
+}
 
-out:
-	cpufreq_cpu_put(policy);
+/**
+ * cpufreq_get - get the current CPU frequency (in kHz)
+ * @cpu: CPU number
+ *
+ * Get the CPU current (static) CPU frequency
+ */
+unsigned int cpufreq_get(unsigned int cpu)
+{
+	unsigned int ret_freq = 0;
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+	if (!policy)
+		goto out;
+
+	if (unlikely(lock_policy_rwsem_read(cpu)))
+		goto out_policy;
+
+	ret_freq = __cpufreq_get(cpu);
 
+	unlock_policy_rwsem_read(cpu);
+
+out_policy:
+	cpufreq_cpu_put(policy);
+out:
 	return (ret_freq);
 }
 EXPORT_SYMBOL(cpufreq_get);
@@ -1278,7 +1382,6 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
  *********************************************************************/
 
 
-/* Must be called with lock_cpu_hotplug held */
 int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int target_freq,
 			    unsigned int relation)
@@ -1304,20 +1407,19 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (!policy)
 		return -EINVAL;
 
-	lock_cpu_hotplug();
-	mutex_lock(&policy->lock);
+	if (unlikely(lock_policy_rwsem_write(policy->cpu)))
+		return -EINVAL;
 
 	ret = __cpufreq_driver_target(policy, target_freq, relation);
 
-	mutex_unlock(&policy->lock);
-	unlock_cpu_hotplug();
+	unlock_policy_rwsem_write(policy->cpu);
 
 	cpufreq_cpu_put(policy);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_target);
 
-int cpufreq_driver_getavg(struct cpufreq_policy *policy)
+int __cpufreq_driver_getavg(struct cpufreq_policy *policy)
 {
 	int ret = 0;
 
@@ -1325,20 +1427,15 @@ int cpufreq_driver_getavg(struct cpufreq_policy *policy)
 	if (!policy)
 		return -EINVAL;
 
-	mutex_lock(&policy->lock);
-
 	if (cpu_online(policy->cpu) && cpufreq_driver->getavg)
 		ret = cpufreq_driver->getavg(policy->cpu);
 
-	mutex_unlock(&policy->lock);
-
 	cpufreq_cpu_put(policy);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpufreq_driver_getavg);
+EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg);
 
 /*
- * Locking: Must be called with the lock_cpu_hotplug() lock held
  * when "event" is CPUFREQ_GOV_LIMITS
  */
 
@@ -1420,9 +1517,7 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
 	if (!cpu_policy)
 		return -EINVAL;
 
-	mutex_lock(&cpu_policy->lock);
 	memcpy(policy, cpu_policy, sizeof(struct cpufreq_policy));
-	mutex_unlock(&cpu_policy->lock);
 
 	cpufreq_cpu_put(cpu_policy);
 	return 0;
@@ -1433,7 +1528,6 @@ EXPORT_SYMBOL(cpufreq_get_policy);
 /*
  * data   : current policy.
  * policy : policy to be set.
- * Locking: Must be called with the lock_cpu_hotplug() lock held
  */
 static int __cpufreq_set_policy(struct cpufreq_policy *data,
 				struct cpufreq_policy *policy)
@@ -1539,10 +1633,9 @@ int cpufreq_set_policy(struct cpufreq_policy *policy)
 	if (!data)
 		return -EINVAL;
 
-	lock_cpu_hotplug();
+	if (unlikely(lock_policy_rwsem_write(policy->cpu)))
+		return -EINVAL;
 
-	/* lock this CPU */
-	mutex_lock(&data->lock);
 
 	ret = __cpufreq_set_policy(data, policy);
 	data->user_policy.min = data->min;
@@ -1550,9 +1643,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy)
 	data->user_policy.policy = data->policy;
 	data->user_policy.governor = data->governor;
 
-	mutex_unlock(&data->lock);
+	unlock_policy_rwsem_write(policy->cpu);
 
-	unlock_cpu_hotplug();
 	cpufreq_cpu_put(data);
 
 	return ret;
@@ -1576,8 +1668,8 @@ int cpufreq_update_policy(unsigned int cpu)
 	if (!data)
 		return -ENODEV;
 
-	lock_cpu_hotplug();
-	mutex_lock(&data->lock);
+	if (unlikely(lock_policy_rwsem_write(cpu)))
+		return -EINVAL;
 
 	dprintk("updating policy for CPU %u\n", cpu);
 	memcpy(&policy, data, sizeof(struct cpufreq_policy));
@@ -1602,8 +1694,8 @@ int cpufreq_update_policy(unsigned int cpu)
 
 	ret = __cpufreq_set_policy(data, &policy);
 
-	mutex_unlock(&data->lock);
-	unlock_cpu_hotplug();
+	unlock_policy_rwsem_write(cpu);
+
 	cpufreq_cpu_put(data);
 	return ret;
 }
@@ -1613,31 +1705,28 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct cpufreq_policy *policy;
 	struct sys_device *sys_dev;
+	struct cpufreq_policy *policy;
 
 	sys_dev = get_cpu_sysdev(cpu);
-
 	if (sys_dev) {
 		switch (action) {
 		case CPU_ONLINE:
 			cpufreq_add_dev(sys_dev);
 			break;
 		case CPU_DOWN_PREPARE:
-			/*
-			 * We attempt to put this cpu in lowest frequency
-			 * possible before going down. This will permit
-			 * hardware-managed P-State to switch other related
-			 * threads to min or higher speeds if possible.
-			 */
+			if (unlikely(lock_policy_rwsem_write(cpu)))
+				BUG();
+
 			policy = cpufreq_cpu_data[cpu];
 			if (policy) {
-				cpufreq_driver_target(policy, policy->min,
+				__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_H);
 			}
+			__cpufreq_remove_dev(sys_dev);
 			break;
-		case CPU_DEAD:
-			cpufreq_remove_dev(sys_dev);
+		case CPU_DOWN_FAILED:
+			cpufreq_add_dev(sys_dev);
 			break;
 		}
 	}
@@ -1751,3 +1840,16 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
+
+static int __init cpufreq_core_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		per_cpu(policy_cpu, cpu) = -1;
+		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
+	}
+	return 0;
+}
+
+core_initcall(cpufreq_core_init);

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                     *