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

* master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreq:
  [CPUFREQ] Fix sysfs_create_file return value handling
  [CPUFREQ] ondemand: fix tickless accounting and software coordination bug
  [CPUFREQ] ondemand: add a check to avoid negative load calculation
  [CPUFREQ] Keep userspace governor quiet when it is not being used
  [CPUFREQ] Longhaul - Proper register access
  [CPUFREQ] Kconfig powernow-k8 driver should depend on ACPI P-States driver
  [CPUFREQ] Longhaul - Replace ACPI functions with direct I/O
  [CPUFREQ] Longhaul - Remove duplicate multipliers
  [CPUFREQ] Longhaul - Embedded "conservative"
  [CPUFREQ] acpi-cpufreq: Proper ReadModifyWrite of PERF_CTL MSR
  [CPUFREQ] check return value of sysfs_create_file
  [CPUFREQ] Longhaul - Check ACPI "BM DMA in progress" bit
  [CPUFREQ] Longhaul - Move old_ratio to correct place
  [CPUFREQ] Longhaul - VT8237 support
  [CPUFREQ] Longhaul - Use all kinds of support
  [CPUFREQ] powernow-k8: clarify number of cores.

arch/i386/kernel/cpu/cpufreq/Kconfig

@@ -90,10 +90,17 @@ config X86_POWERNOW_K8
 	  If in doubt, say N.
 
 config X86_POWERNOW_K8_ACPI
-	bool
-	depends on X86_POWERNOW_K8 && ACPI_PROCESSOR
-	depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m)
+	bool "ACPI Support"
+	select ACPI_PROCESSOR
+	depends on X86_POWERNOW_K8
 	default y
+	help
+	  This provides access to the K8s Processor Performance States via ACPI.
+	  This driver is probably required for CPUFreq to work with multi-socket and
+	  SMP systems.  It is not required on at least some single-socket yet
+	  multi-core systems, even if SMP is enabled.
+
+	  It is safe to say Y here.
 
 config X86_GX_SUSPMOD
 	tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation"

arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -167,11 +167,13 @@ static void do_drv_read(struct drv_cmd *cmd)
 
 static void do_drv_write(struct drv_cmd *cmd)
 {
-	u32 h = 0;
+	u32 lo, hi;
 
 	switch (cmd->type) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
-		wrmsr(cmd->addr.msr.reg, cmd->val, h);
+		rdmsr(cmd->addr.msr.reg, lo, hi);
+		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
+		wrmsr(cmd->addr.msr.reg, lo, hi);
 		break;
 	case SYSTEM_IO_CAPABLE:
 		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
@@ -372,7 +374,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	struct cpufreq_freqs freqs;
 	cpumask_t online_policy_cpus;
 	struct drv_cmd cmd;
-	unsigned int msr;
 	unsigned int next_state = 0; /* Index into freq_table */
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	unsigned int i;
@@ -417,11 +418,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
-		msr =
-		    (u32) perf->states[next_perf_state].
-		    control & INTEL_MSR_RANGE;
-		cmd.val = get_cur_val(online_policy_cpus);
-		cmd.val = (cmd.val & ~INTEL_MSR_RANGE) | msr;
+		cmd.val = (u32) perf->states[next_perf_state].control;
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;

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

@@ -180,7 +180,7 @@ static const int __initdata ezrat_clock_ratio[32] = {
 
 	-1,  /* 0000 -> RESERVED (10.0x) */
 	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
+	-1, /* 0010 -> 12.0x */
 	-1,  /* 0011 -> RESERVED (9.0x)*/
 	105, /* 0100 -> 10.5x */
 	115, /* 0101 -> 11.5x */
@@ -237,7 +237,7 @@ static const int __initdata ezrat_eblcr[32] = {
 
 static const int __initdata  nehemiah_clock_ratio[32] = {
 	100, /* 0000 -> 10.0x */
-	160, /* 0001 -> 16.0x */
+	-1, /* 0001 -> 16.0x */
 	40,  /* 0010 ->  4.0x */
 	90,  /* 0011 ->  9.0x */
 	95,  /* 0100 ->  9.5x */
@@ -252,10 +252,10 @@ static const int __initdata  nehemiah_clock_ratio[32] = {
 	75,  /* 1101 ->  7.5x */
 	85,  /* 1110 ->  8.5x */
 	120, /* 1111 -> 12.0x */
-	100, /* 0000 -> 10.0x */
+	-1, /* 0000 -> 10.0x */
 	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
-	90,  /* 0011 ->  9.0x */
+	-1, /* 0010 -> 12.0x */
+	-1,  /* 0011 ->  9.0x */
 	105, /* 0100 -> 10.5x */
 	115, /* 0101 -> 11.5x */
 	125, /* 0110 -> 12.5x */
@@ -267,7 +267,7 @@ static const int __initdata  nehemiah_clock_ratio[32] = {
 	145, /* 1100 -> 14.5x */
 	155, /* 1101 -> 15.5x */
 	-1,  /* 1110 -> RESERVED (13.0x) */
-	120, /* 1111 -> 12.0x */
+	-1, /* 1111 -> 12.0x */
 };
 
 static const int __initdata nehemiah_eblcr[32] = {

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

@@ -1330,8 +1330,9 @@ static int __cpuinit powernowk8_init(void)
 
 	if (supported_cpus == num_online_cpus()) {
 		printk(KERN_INFO PFX "Found %d %s "
-			"processors (" VERSION ")\n", supported_cpus,
-			boot_cpu_data.x86_model_id);
+			"processors (%d cpu cores) (" VERSION ")\n",
+			supported_cpus/cpu_data[0].booted_cores,
+			boot_cpu_data.x86_model_id, supported_cpus);
 		return cpufreq_register_driver(&cpufreq_amd64_driver);
 	}
 

drivers/cpufreq/cpufreq.c

@@ -826,13 +826,21 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 	/* set up files for this cpu device */
 	drv_attr = cpufreq_driver->attr;
 	while ((drv_attr) && (*drv_attr)) {
-		sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
+		ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
+		if (ret)
+			goto err_out_driver_exit;
 		drv_attr++;
 	}
-	if (cpufreq_driver->get)
-		sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
-	if (cpufreq_driver->target)
-		sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
+	if (cpufreq_driver->get){
+		ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
+		if (ret)
+			goto err_out_driver_exit;
+	}
+	if (cpufreq_driver->target){
+		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
+		if (ret)
+			goto err_out_driver_exit;
+	}
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu_mask(j, policy->cpus) {

drivers/cpufreq/cpufreq_ondemand.c

@@ -96,15 +96,25 @@ static struct dbs_tuners {
 
 static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
 {
-	cputime64_t retval;
+	cputime64_t idle_time;
+	cputime64_t cur_jiffies;
+	cputime64_t busy_time;
 
-	retval = cputime64_add(kstat_cpu(cpu).cpustat.idle,
-			kstat_cpu(cpu).cpustat.iowait);
+	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
+	busy_time = cputime64_add(kstat_cpu(cpu).cpustat.user,
+			kstat_cpu(cpu).cpustat.system);
 
-	if (dbs_tuners_ins.ignore_nice)
-		retval = cputime64_add(retval, kstat_cpu(cpu).cpustat.nice);
+	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq);
+	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq);
+	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal);
 
-	return retval;
+	if (!dbs_tuners_ins.ignore_nice) {
+		busy_time = cputime64_add(busy_time,
+				kstat_cpu(cpu).cpustat.nice);
+	}
+
+	idle_time = cputime64_sub(cur_jiffies, busy_time);
+	return idle_time;
 }
 
 /*
@@ -325,7 +335,7 @@ static struct attribute_group dbs_attr_group = {
 static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 {
 	unsigned int idle_ticks, total_ticks;
-	unsigned int load;
+	unsigned int load = 0;
 	cputime64_t cur_jiffies;
 
 	struct cpufreq_policy *policy;
@@ -339,7 +349,8 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
 	total_ticks = (unsigned int) cputime64_sub(cur_jiffies,
 			this_dbs_info->prev_cpu_wall);
-	this_dbs_info->prev_cpu_wall = cur_jiffies;
+	this_dbs_info->prev_cpu_wall = get_jiffies_64();
+
 	if (!total_ticks)
 		return;
 	/*
@@ -370,7 +381,8 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 		if (tmp_idle_ticks < idle_ticks)
 			idle_ticks = tmp_idle_ticks;
 	}
-	load = (100 * (total_ticks - idle_ticks)) / total_ticks;
+	if (likely(total_ticks > idle_ticks))
+		load = (100 * (total_ticks - idle_ticks)) / total_ticks;
 
 	/* Check for frequency increase */
 	if (load > dbs_tuners_ins.up_threshold) {

drivers/cpufreq/cpufreq_userspace.c

@@ -37,6 +37,7 @@ static unsigned int	cpu_set_freq[NR_CPUS]; /* CPU freq desired by userspace */
 static unsigned int	cpu_is_managed[NR_CPUS];
 
 static DEFINE_MUTEX	(userspace_mutex);
+static int cpus_using_userspace_governor;
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "userspace", msg)
 
@@ -47,7 +48,11 @@ userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 {
         struct cpufreq_freqs *freq = data;
 
-	dprintk("saving cpu_cur_freq of cpu %u to be %u kHz\n", freq->cpu, freq->new);
+	if (!cpu_is_managed[freq->cpu])
+		return 0;
+
+	dprintk("saving cpu_cur_freq of cpu %u to be %u kHz\n",
+			freq->cpu, freq->new);
 	cpu_cur_freq[freq->cpu] = freq->new;
 
         return 0;
@@ -142,6 +147,13 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 		if (rc)
 			goto start_out;
 
+		if (cpus_using_userspace_governor == 0) {
+			cpufreq_register_notifier(
+					&userspace_cpufreq_notifier_block,
+					CPUFREQ_TRANSITION_NOTIFIER);
+		}
+		cpus_using_userspace_governor++;
+
 		cpu_is_managed[cpu] = 1;
 		cpu_min_freq[cpu] = policy->min;
 		cpu_max_freq[cpu] = policy->max;
@@ -153,6 +165,13 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 		break;
 	case CPUFREQ_GOV_STOP:
 		mutex_lock(&userspace_mutex);
+		cpus_using_userspace_governor--;
+		if (cpus_using_userspace_governor == 0) {
+			cpufreq_unregister_notifier(
+					&userspace_cpufreq_notifier_block,
+					CPUFREQ_TRANSITION_NOTIFIER);
+		}
+
 		cpu_is_managed[cpu] = 0;
 		cpu_min_freq[cpu] = 0;
 		cpu_max_freq[cpu] = 0;
@@ -198,7 +217,6 @@ EXPORT_SYMBOL(cpufreq_gov_userspace);
 
 static int __init cpufreq_gov_userspace_init(void)
 {
-	cpufreq_register_notifier(&userspace_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER);
 	return cpufreq_register_governor(&cpufreq_gov_userspace);
 }
 
@@ -206,7 +224,6 @@ static int __init cpufreq_gov_userspace_init(void)
 static void __exit cpufreq_gov_userspace_exit(void)
 {
 	cpufreq_unregister_governor(&cpufreq_gov_userspace);
-        cpufreq_unregister_notifier(&userspace_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER);
 }