Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - another round of rq-clock handling debugging, robustization and
     fixes

   - PELT accounting improvements

   - CPU hotplug related ->cpus_allowed affinity handling fixes all
     around the tree

   - ... plus misc fixes, cleanups and updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
  sched/x86: Update reschedule warning text
  crypto: N2 - Replace racy task affinity logic
  cpufreq/sparc-us2e: Replace racy task affinity logic
  cpufreq/sparc-us3: Replace racy task affinity logic
  cpufreq/sh: Replace racy task affinity logic
  cpufreq/ia64: Replace racy task affinity logic
  ACPI/processor: Replace racy task affinity logic
  ACPI/processor: Fix error handling in __acpi_processor_start()
  sparc/sysfs: Replace racy task affinity logic
  powerpc/smp: Replace open coded task affinity logic
  ia64/sn/hwperf: Replace racy task affinity logic
  ia64/salinfo: Replace racy task affinity logic
  workqueue: Provide work_on_cpu_safe()
  ia64/topology: Remove cpus_allowed manipulation
  sched/fair: Move the PELT constants into a generated header
  sched/fair: Increase PELT accuracy for small tasks
  sched/fair: Fix comments
  sched/Documentation: Add 'sched-pelt' tool
  sched/fair: Fix corner case in __accumulate_sum()
  sched/core: Remove 'task' parameter and rename tsk_restore_flags() to current_restore_flags()
  ...

29 files changed, 847 insertions, 544 deletions

diff --git a/Documentation/scheduler/sched-pelt.c b/Documentation/scheduler/sched-pelt.c
new file mode 100644
index 000000000000..e4219139386a
--- /dev/null
+++ b/Documentation/scheduler/sched-pelt.c
@@ -0,0 +1,108 @@
+/*
+ * The following program is used to generate the constants for
+ * computing sched averages.
+ *
+ * ==============================================================
+ *		C program (compile with -lm)
+ * ==============================================================
+ */
+
+#include <math.h>
+#include <stdio.h>
+
+#define HALFLIFE 32
+#define SHIFT 32
+
+double y;
+
+void calc_runnable_avg_yN_inv(void)
+{
+	int i;
+	unsigned int x;
+
+	printf("static const u32 runnable_avg_yN_inv[] = {");
+	for (i = 0; i < HALFLIFE; i++) {
+		x = ((1UL<<32)-1)*pow(y, i);
+
+		if (i % 6 == 0) printf("\n\t");
+		printf("0x%8x, ", x);
+	}
+	printf("\n};\n\n");
+}
+
+int sum = 1024;
+
+void calc_runnable_avg_yN_sum(void)
+{
+	int i;
+
+	printf("static const u32 runnable_avg_yN_sum[] = {\n\t    0,");
+	for (i = 1; i <= HALFLIFE; i++) {
+		if (i == 1)
+			sum *= y;
+		else
+			sum = sum*y + 1024*y;
+
+		if (i % 11 == 0)
+			printf("\n\t");
+
+		printf("%5d,", sum);
+	}
+	printf("\n};\n\n");
+}
+
+int n = -1;
+/* first period */
+long max = 1024;
+
+void calc_converged_max(void)
+{
+	long last = 0, y_inv = ((1UL<<32)-1)*y;
+
+	for (; ; n++) {
+		if (n > -1)
+			max = ((max*y_inv)>>SHIFT) + 1024;
+			/*
+			 * This is the same as:
+			 * max = max*y + 1024;
+			 */
+
+		if (last == max)
+			break;
+
+		last = max;
+	}
+	n--;
+	printf("#define LOAD_AVG_PERIOD %d\n", HALFLIFE);
+	printf("#define LOAD_AVG_MAX %ld\n", max);
+//	printf("#define LOAD_AVG_MAX_N %d\n\n", n);
+}
+
+void calc_accumulated_sum_32(void)
+{
+	int i, x = sum;
+
+	printf("static const u32 __accumulated_sum_N32[] = {\n\t     0,");
+	for (i = 1; i <= n/HALFLIFE+1; i++) {
+		if (i > 1)
+			x = x/2 + sum;
+
+		if (i % 6 == 0)
+			printf("\n\t");
+
+		printf("%6d,", x);
+	}
+	printf("\n};\n\n");
+}
+
+void main(void)
+{
+	printf("/* Generated by Documentation/scheduler/sched-pelt; do not modify. */\n\n");
+
+	y = pow(0.5, 1/(double)HALFLIFE);
+
+	calc_runnable_avg_yN_inv();
+//	calc_runnable_avg_yN_sum();
+	calc_converged_max();
+//	calc_accumulated_sum_32();
+}
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index d194d5c83d32..63dc9cdc95c5 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -179,14 +179,14 @@ struct salinfo_platform_oemdata_parms {
 	const u8 *efi_guid;
 	u8 **oemdata;
 	u64 *oemdata_size;
-	int ret;
 };
 
-static void
+static long
 salinfo_platform_oemdata_cpu(void *context)
 {
 	struct salinfo_platform_oemdata_parms *parms = context;
-	parms->ret = salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
+
+	return salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
 }
 
 static void
@@ -380,16 +380,7 @@ salinfo_log_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void
-call_on_cpu(int cpu, void (*fn)(void *), void *arg)
-{
-	cpumask_t save_cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-	(*fn)(arg);
-	set_cpus_allowed_ptr(current, &save_cpus_allowed);
-}
-
-static void
+static long
 salinfo_log_read_cpu(void *context)
 {
 	struct salinfo_data *data = context;
@@ -399,6 +390,7 @@ salinfo_log_read_cpu(void *context)
 	/* Clear corrected errors as they are read from SAL */
 	if (rh->severity == sal_log_severity_corrected)
 		ia64_sal_clear_state_info(data->type);
+	return 0;
 }
 
 static void
@@ -430,7 +422,7 @@ retry:
 	spin_unlock_irqrestore(&data_saved_lock, flags);
 
 	if (!data->saved_num)
-		call_on_cpu(cpu, salinfo_log_read_cpu, data);
+		work_on_cpu_safe(cpu, salinfo_log_read_cpu, data);
 	if (!data->log_size) {
 		data->state = STATE_NO_DATA;
 		cpumask_clear_cpu(cpu, &data->cpu_event);
@@ -459,11 +451,13 @@ salinfo_log_read(struct file *file, char __user *buffer, size_t count, loff_t *p
 	return simple_read_from_buffer(buffer, count, ppos, buf, bufsize);
 }
 
-static void
+static long
 salinfo_log_clear_cpu(void *context)
 {
 	struct salinfo_data *data = context;
+
 	ia64_sal_clear_state_info(data->type);
+	return 0;
 }
 
 static int
@@ -486,7 +480,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu)
 	rh = (sal_log_record_header_t *)(data->log_buffer);
 	/* Corrected errors have already been cleared from SAL */
 	if (rh->severity != sal_log_severity_corrected)
-		call_on_cpu(cpu, salinfo_log_clear_cpu, data);
+		work_on_cpu_safe(cpu, salinfo_log_clear_cpu, data);
 	/* clearing a record may make a new record visible */
 	salinfo_log_new_read(cpu, data);
 	if (data->state == STATE_LOG_RECORD) {
@@ -531,9 +525,8 @@ salinfo_log_write(struct file *file, const char __user *buffer, size_t count, lo
 				.oemdata = &data->oemdata,
 				.oemdata_size = &data->oemdata_size
 			};
-			call_on_cpu(cpu, salinfo_platform_oemdata_cpu, &parms);
-			if (parms.ret)
-				count = parms.ret;
+			count = work_on_cpu_safe(cpu, salinfo_platform_oemdata_cpu,
+						 &parms);
 		} else
 			data->oemdata_size = 0;
 	} else
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 1a68f012a6dc..d76529cbff20 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -355,18 +355,12 @@ static int cache_add_dev(unsigned int cpu)
 	unsigned long i, j;
 	struct cache_info *this_object;
 	int retval = 0;
-	cpumask_t oldmask;
 
 	if (all_cpu_cache_info[cpu].kobj.parent)
 		return 0;
 
-	oldmask = current->cpus_allowed;
-	retval = set_cpus_allowed_ptr(current, cpumask_of(cpu));
-	if (unlikely(retval))
-		return retval;
 
 	retval = cpu_cache_sysfs_init(cpu);
-	set_cpus_allowed_ptr(current, &oldmask);
 	if (unlikely(retval < 0))
 		return retval;
 
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 52704f199dd6..55febd65911a 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -598,12 +598,17 @@ static void sn_hwperf_call_sal(void *info)
 	op_info->ret = r;
 }
 
+static long sn_hwperf_call_sal_work(void *info)
+{
+	sn_hwperf_call_sal(info);
+	return 0;
+}
+
 static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 {
 	u32 cpu;
 	u32 use_ipi;
 	int r = 0;
-	cpumask_t save_allowed;
 	
 	cpu = (op_info->a->arg & SN_HWPERF_ARG_CPU_MASK) >> 32;
 	use_ipi = op_info->a->arg & SN_HWPERF_ARG_USE_IPI_MASK;
@@ -629,13 +634,9 @@ static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 			/* use an interprocessor interrupt to call SAL */
 			smp_call_function_single(cpu, sn_hwperf_call_sal,
 				op_info, 1);
-		}
-		else {
-			/* migrate the task before calling SAL */ 
-			save_allowed = current->cpus_allowed;
-			set_cpus_allowed_ptr(current, cpumask_of(cpu));
-			sn_hwperf_call_sal(op_info);
-			set_cpus_allowed_ptr(current, &save_allowed);
+		} else {
+			/* Call on the target CPU */
+			work_on_cpu_safe(cpu, sn_hwperf_call_sal_work, op_info);
 		}
 	}
 	r = op_info->ret;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 46f89e66a273..d68ed1f004a3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -787,24 +787,21 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-void __init smp_cpus_done(unsigned int max_cpus)
+static __init long smp_setup_cpu_workfn(void *data __always_unused)
 {
-	cpumask_var_t old_mask;
+	smp_ops->setup_cpu(boot_cpuid);
+	return 0;
+}
 
-	/* We want the setup_cpu() here to be called from CPU 0, but our
-	 * init thread may have been "borrowed" by another CPU in the meantime
-	 * se we pin us down to CPU 0 for a short while
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+	/*
+	 * We want the setup_cpu() here to be called on the boot CPU, but
+	 * init might run on any CPU, so make sure it's invoked on the boot
+	 * CPU.
 	 */
-	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
-	cpumask_copy(old_mask, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
-	
 	if (smp_ops && smp_ops->setup_cpu)
-		smp_ops->setup_cpu(boot_cpuid);
-
-	set_cpus_allowed_ptr(current, old_mask);
-
-	free_cpumask_var(old_mask);
+		work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
 
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
@@ -812,7 +809,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	dump_numa_cpu_topology();
 
 	set_sched_topology(powerpc_topology);
-
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index d63fc613e7a9..5fd352b759af 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -98,27 +98,7 @@ static struct attribute_group mmu_stat_group = {
 	.name = "mmu_stats",
 };
 
-/* XXX convert to rusty's on_one_cpu */
-static unsigned long run_on_cpu(unsigned long cpu,
-			        unsigned long (*func)(unsigned long),
-				unsigned long arg)
-{
-	cpumask_t old_affinity;
-	unsigned long ret;
-
-	cpumask_copy(&old_affinity, &current->cpus_allowed);
-	/* should return -EINVAL to userspace */
-	if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
-		return 0;
-
-	ret = func(arg);
-
-	set_cpus_allowed_ptr(current, &old_affinity);
-
-	return ret;
-}
-
-static unsigned long read_mmustat_enable(unsigned long junk)
+static long read_mmustat_enable(void *data __maybe_unused)
 {
 	unsigned long ra = 0;
 
@@ -127,11 +107,11 @@ static unsigned long read_mmustat_enable(unsigned long junk)
 	return ra != 0;
 }
 
-static unsigned long write_mmustat_enable(unsigned long val)
+static long write_mmustat_enable(void *data)
 {
-	unsigned long ra, orig_ra;
+	unsigned long ra, orig_ra, *val = data;
 
-	if (val)
+	if (*val)
 		ra = __pa(&per_cpu(mmu_stats, smp_processor_id()));
 	else
 		ra = 0UL;
@@ -142,7 +122,8 @@ static unsigned long write_mmustat_enable(unsigned long val)
 static ssize_t show_mmustat_enable(struct device *s,
 				struct device_attribute *attr, char *buf)
 {
-	unsigned long val = run_on_cpu(s->id, read_mmustat_enable, 0);
+	long val = work_on_cpu(s->id, read_mmustat_enable, NULL);
+
 	return sprintf(buf, "%lx\n", val);
 }
 
@@ -150,13 +131,15 @@ static ssize_t store_mmustat_enable(struct device *s,
 			struct device_attribute *attr, const char *buf,
 			size_t count)
 {
-	unsigned long val, err;
-	int ret = sscanf(buf, "%lu", &val);
+	unsigned long val;
+	long err;
+	int ret;
 
+	ret = sscanf(buf, "%lu", &val);
 	if (ret != 1)
 		return -EINVAL;
 
-	err = run_on_cpu(s->id, write_mmustat_enable, val);
+	err = work_on_cpu(s->id, write_mmustat_enable, &val);
 	if (err)
 		return -EIO;
 
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d3c66a15bbde..3cab8415389a 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -124,7 +124,7 @@ static bool smp_no_nmi_ipi = false;
 static void native_smp_send_reschedule(int cpu)
 {
 	if (unlikely(cpu_is_offline(cpu))) {
-		WARN_ON(1);
+		WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
 		return;
 	}
 	apic->send_IPI(cpu, RESCHEDULE_VECTOR);
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 9d5f0c7ed3f7..8697a82bd465 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -251,6 +251,9 @@ static int __acpi_processor_start(struct acpi_device *device)
 	if (ACPI_SUCCESS(status))
 		return 0;
 
+	result = -ENODEV;
+	acpi_pss_perf_exit(pr, device);
+
 err_power_exit:
 	acpi_processor_power_exit(pr);
 	return result;
@@ -259,11 +262,16 @@ err_power_exit:
 static int acpi_processor_start(struct device *dev)
 {
 	struct acpi_device *device = ACPI_COMPANION(dev);
+	int ret;
 
 	if (!device)
 		return -ENODEV;
 
-	return __acpi_processor_start(device);
+	/* Protect against concurrent CPU hotplug operations */
+	get_online_cpus();
+	ret = __acpi_processor_start(device);
+	put_online_cpus();
+	return ret;
 }
 
 static int acpi_processor_stop(struct device *dev)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index a12f96cc93ff..3de34633f7f9 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -62,8 +62,8 @@ struct acpi_processor_throttling_arg {
 #define THROTTLING_POSTCHANGE      (2)
 
 static int acpi_processor_get_throttling(struct acpi_processor *pr);
-int acpi_processor_set_throttling(struct acpi_processor *pr,
-						int state, bool force);
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+					   int state, bool force, bool direct);
 
 static int acpi_processor_update_tsd_coord(void)
 {
@@ -891,7 +891,8 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				"Invalid throttling state, reset\n"));
 			state = 0;
-			ret = acpi_processor_set_throttling(pr, state, true);
+			ret = __acpi_processor_set_throttling(pr, state, true,
+							      true);
 			if (ret)
 				return ret;
 		}
@@ -901,36 +902,31 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 	return 0;
 }
 
-static int acpi_processor_get_throttling(struct acpi_processor *pr)
+static long __acpi_processor_get_throttling(void *data)
 {
-	cpumask_var_t saved_mask;
-	int ret;
+	struct acpi_processor *pr = data;
+
+	return pr->throttling.acpi_processor_get_throttling(pr);
+}
 
+static int acpi_processor_get_throttling(struct acpi_processor *pr)
+{
 	if (!pr)
 		return -EINVAL;
 
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
-	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	/*
-	 * Migrate task to the cpu pointed by pr.
+	 * This is either called from the CPU hotplug callback of
+	 * processor_driver or via the ACPI probe function. In the latter
+	 * case the CPU is not guaranteed to be online. Both call sites are
+	 * protected against CPU hotplug.
 	 */
-	cpumask_copy(saved_mask, &current->cpus_allowed);
-	/* FIXME: use work_on_cpu() */
-	if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
-		/* Can't migrate to the target pr->id CPU. Exit */
-		free_cpumask_var(saved_mask);
+	if (!cpu_online(pr->id))
 		return -ENODEV;
-	}
-	ret = pr->throttling.acpi_processor_get_throttling(pr);
-	/* restore the previous state */
-	set_cpus_allowed_ptr(current, saved_mask);
-	free_cpumask_var(saved_mask);
 
-	return ret;
+	return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr);
 }
 
 static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
@@ -1080,8 +1076,15 @@ static long acpi_processor_throttling_fn(void *data)
 			arg->target_state, arg->force);
 }
 
-int acpi_processor_set_throttling(struct acpi_processor *pr,
-						int state, bool force)
+static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
+{
+	if (direct)
+		return fn(arg);
+	return work_on_cpu(cpu, fn, arg);
+}
+
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+					   int state, bool force, bool direct)
 {
 	int ret = 0;
 	unsigned int i;
@@ -1130,7 +1133,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 		arg.pr = pr;
 		arg.target_state = state;
 		arg.force = force;
-		ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
+		ret = call_on_cpu(pr->id, acpi_processor_throttling_fn, &arg,
+				  direct);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
@@ -1163,8 +1167,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 			arg.pr = match_pr;
 			arg.target_state = state;
 			arg.force = force;
-			ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
-				&arg);
+			ret = call_on_cpu(pr->id, acpi_processor_throttling_fn,
+					  &arg, direct);
 		}
 	}
 	/*
@@ -1182,6 +1186,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 	return ret;
 }
 
+int acpi_processor_set_throttling(struct acpi_processor *pr, int state,
+				  bool force)
+{
+	return __acpi_processor_set_throttling(pr, state, force, false);
+}
+
 int acpi_processor_get_throttling_info(struct acpi_processor *pr)
 {
 	int result = 0;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ac376b9b852d..56efb0444b4d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -381,7 +381,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 			*sent += result;
 	} while (msg_data_left(&msg));
 
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+	current_restore_flags(pflags, PF_MEMALLOC);
 
 	return result;
 }
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index e28a31a40829..a757c0a1e7b5 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -34,6 +34,11 @@ struct cpufreq_acpi_io {
 	unsigned int				resume;
 };
 
+struct cpufreq_acpi_req {
+	unsigned int		cpu;
+	unsigned int		state;
+};
+
 static struct cpufreq_acpi_io	*acpi_io_data[NR_CPUS];
 
 static struct cpufreq_driver acpi_cpufreq_driver;
@@ -83,8 +88,7 @@ processor_get_pstate (
 static unsigned
 extract_clock (
 	struct cpufreq_acpi_io *data,
-	unsigned value,
-	unsigned int cpu)
+	unsigned value)
 {
 	unsigned long i;
 
@@ -98,60 +102,43 @@ extract_clock (
 }
 
 
-static unsigned int
+static long
 processor_get_freq (
-	struct cpufreq_acpi_io	*data,
-	unsigned int		cpu)
+	void *arg)
 {
-	int			ret = 0;
-	u32			value = 0;
-	cpumask_t		saved_mask;
-	unsigned long 		clock_freq;
+	struct cpufreq_acpi_req *req = arg;
+	unsigned int		cpu = req->cpu;
+	struct cpufreq_acpi_io	*data = acpi_io_data[cpu];
+	u32			value;
+	int			ret;
 
 	pr_debug("processor_get_freq\n");
-
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 	if (smp_processor_id() != cpu)
-		goto migrate_end;
+		return -EAGAIN;
 
 	/* processor_get_pstate gets the instantaneous frequency */
 	ret = processor_get_pstate(&value);
-
 	if (ret) {
-		set_cpus_allowed_ptr(current, &saved_mask);
 		pr_warn("get performance failed with error %d\n", ret);
-		ret = 0;
-		goto migrate_end;
+		return ret;
 	}
-	clock_freq = extract_clock(data, value, cpu);
-	ret = (clock_freq*1000);
-
-migrate_end:
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return ret;
+	return 1000 * extract_clock(data, value);
 }
 
 
-static int
+static long
 processor_set_freq (
-	struct cpufreq_acpi_io	*data,
-	struct cpufreq_policy   *policy,
-	int			state)
+	void *arg)
 {
-	int			ret = 0;
-	u32			value = 0;
-	cpumask_t		saved_mask;
-	int			retval;
+	struct cpufreq_acpi_req *req = arg;
+	unsigned int		cpu = req->cpu;
+	struct cpufreq_acpi_io	*data = acpi_io_data[cpu];
+	int			ret, state = req->state;
+	u32			value;
 
 	pr_debug("processor_set_freq\n");
-
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(policy->cpu));
-	if (smp_processor_id() != policy->cpu) {
-		retval = -EAGAIN;
-		goto migrate_end;
-	}
+	if (smp_processor_id() != cpu)
+		return -EAGAIN;
 
 	if (state == data->acpi_data.state) {
 		if (unlikely(data->resume)) {
@@ -159,8 +146,7 @@ processor_set_freq (
 			data->resume = 0;
 		} else {
 			pr_debug("Already at target state (P%d)\n", state);
-			retval = 0;
-			goto migrate_end;
+			return 0;
 		}
 	}
 
@@ -171,7 +157,6 @@ processor_set_freq (
 	 * First we write the target state's 'control' value to the
 	 * control_register.
 	 */
-
 	value = (u32) data->acpi_data.states[state].control;
 
 	pr_debug("Transitioning to state: 0x%08x\n", value);
@@ -179,17 +164,11 @@ processor_set_freq (
 	ret = processor_set_pstate(value);
 	if (ret) {
 		pr_warn("Transition failed with error %d\n", ret);
-		retval = -ENODEV;
-		goto migrate_end;
+		return -ENODEV;
 	}
 
 	data->acpi_data.state = state;
-
-	retval = 0;
-
-migrate_end:
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return (retval);
+	return 0;
 }
 
 
@@ -197,11 +176,13 @@ static unsigned int
 acpi_cpufreq_get (
 	unsigned int		cpu)
 {
-	struct cpufreq_acpi_io *data = acpi_io_data[cpu];
+	struct cpufreq_acpi_req req;
+	long ret;
 
-	pr_debug("acpi_cpufreq_get\n");
+	req.cpu = cpu;
+	ret = work_on_cpu(cpu, processor_get_freq, &req);
 
-	return processor_get_freq(data, cpu);
+	return ret > 0 ? (unsigned int) ret : 0;
 }
 
 
@@ -210,7 +191,12 @@ acpi_cpufreq_target (
 	struct cpufreq_policy   *policy,
 	unsigned int index)
 {
-	return processor_set_freq(acpi_io_data[policy->cpu], policy, index);
+	struct cpufreq_acpi_req req;
+
+	req.cpu = policy->cpu;
+	req.state = index;
+
+	return work_on_cpu(req.cpu, processor_set_freq, &req);
 }
 
 static int
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 86628e22b2a3..719c3d9f07fb 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -30,54 +30,63 @@
 
 static DEFINE_PER_CPU(struct clk, sh_cpuclk);
 
+struct cpufreq_target {
+	struct cpufreq_policy	*policy;
+	unsigned int		freq;
+};
+
 static unsigned int sh_cpufreq_get(unsigned int cpu)
 {
 	return (clk_get_rate(&per_cpu(sh_cpuclk, cpu)) + 500) / 1000;
 }
 
-/*
- * Here we notify other drivers of the proposed change and the final change.
- */
-static int sh_cpufreq_target(struct cpufreq_policy *policy,
-			     unsigned int target_freq,
-			     unsigned int relation)
+static long __sh_cpufreq_target(void *arg)
 {
-	unsigned int cpu = policy->cpu;
+	struct cpufreq_target *target = arg;
+	struct cpufreq_policy *policy = target->policy;
+	int cpu = policy->cpu;
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
-	cpumask_t cpus_allowed;
 	struct cpufreq_freqs freqs;
 	struct device *dev;
 	long freq;
 
-	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
-	BUG_ON(smp_processor_id() != cpu);
+	if (smp_processor_id() != cpu)
+		return -ENODEV;
 
 	dev = get_cpu_device(cpu);
 
 	/* Convert target_freq from kHz to Hz */
-	freq = clk_round_rate(cpuclk, target_freq * 1000);
+	freq = clk_round_rate(cpuclk, target->freq * 1000);
 
 	if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
 		return -EINVAL;
 
-	dev_dbg(dev, "requested frequency %u Hz\n", target_freq * 1000);
+	dev_dbg(dev, "requested frequency %u Hz\n", target->freq * 1000);
 
 	freqs.old	= sh_cpufreq_get(cpu);
 	freqs.new	= (freq + 500) / 1000;
 	freqs.flags	= 0;
 
-	cpufreq_freq_transition_begin(policy, &freqs);
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	cpufreq_freq_transition_begin(target->policy, &freqs);
 	clk_set_rate(cpuclk, freq);
-	cpufreq_freq_transition_end(policy, &freqs, 0);
+	cpufreq_freq_transition_end(target->policy, &freqs, 0);
 
 	dev_dbg(dev, "set frequency %lu Hz\n", freq);
-
 	return 0;
 }
 
+/*
+ * Here we notify other drivers of the proposed change and the final change.
+ */
+static int sh_cpufreq_target(struct cpufreq_policy *policy,
+			     unsigned int target_freq,
+			     unsigned int relation)
+{
+	struct cpufreq_target data = { .policy = policy, .freq = target_freq };
+
+	return work_on_cpu(policy->cpu, __sh_cpufreq_target, &data);
+}
+
 static int sh_cpufreq_verify(struct cpufreq_policy *policy)
 {
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index 35ddb6da93aa..90f33efee5fc 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -118,10 +118,6 @@ static void us2e_transition(unsigned long estar, unsigned long new_bits,
 			    unsigned long clock_tick,
 			    unsigned long old_divisor, unsigned long divisor)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-
 	estar &= ~ESTAR_MODE_DIV_MASK;
 
 	/* This is based upon the state transition diagram in the IIe manual.  */
@@ -152,8 +148,6 @@ static void us2e_transition(unsigned long estar, unsigned long new_bits,
 	} else {
 		BUG();
 	}
-
-	local_irq_restore(flags);
 }
 
 static unsigned long index_to_estar_mode(unsigned int index)
@@ -229,48 +223,51 @@ static unsigned long estar_to_divisor(unsigned long estar)
 	return ret;
 }
 
+static void __us2e_freq_get(void *arg)
+{
+	unsigned long *estar = arg;
+
+	*estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
+}
+
 static unsigned int us2e_freq_get(unsigned int cpu)
 {
-	cpumask_t cpus_allowed;
 	unsigned long clock_tick, estar;
 
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
 	clock_tick = sparc64_get_clock_tick(cpu) / 1000;
-	estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	if (smp_call_function_single(cpu, __us2e_freq_get, &estar, 1))
+		return 0;
 
 	return clock_tick / estar_to_divisor(estar);
 }