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()
  ...

4 files changed, 103 insertions, 125 deletions

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);
 }
 
-static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+static void __us2e_freq_target(void *arg)
 {
-	unsigned int cpu = policy->cpu;
+	unsigned int cpu = smp_processor_id();
+	unsigned int *index = arg;
 	unsigned long new_bits, new_freq;
 	unsigned long clock_tick, divisor, old_divisor, estar;
-	cpumask_t cpus_allowed;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = clock_tick = sparc64_get_clock_tick(cpu) / 1000;
-	new_bits = index_to_estar_mode(index);
-	divisor = index_to_divisor(index);
+	new_bits = index_to_estar_mode(*index);
+	divisor = index_to_divisor(*index);
 	new_freq /= divisor;
 
 	estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
 
 	old_divisor = estar_to_divisor(estar);
 
-	if (old_divisor != divisor)
+	if (old_divisor != divisor) {
 		us2e_transition(estar, new_bits, clock_tick * 1000,
 				old_divisor, divisor);
+	}
+}
 
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+{
+	unsigned int cpu = policy->cpu;
 
-	return 0;
+	return smp_call_function_single(cpu, __us2e_freq_target, &index, 1);
 }
 
 static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy)
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index a8d86a449ca1..30645b0118f9 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -35,22 +35,28 @@ static struct us3_freq_percpu_info *us3_freq_table;
 #define SAFARI_CFG_DIV_32	0x0000000080000000UL
 #define SAFARI_CFG_DIV_MASK	0x00000000C0000000UL
 
-static unsigned long read_safari_cfg(void)
+static void read_safari_cfg(void *arg)
 {
-	unsigned long ret;
+	unsigned long ret, *val = arg;
 
 	__asm__ __volatile__("ldxa	[%%g0] %1, %0"
 			     : "=&r" (ret)
 			     : "i" (ASI_SAFARI_CONFIG));
-	return ret;
+	*val = ret;
 }
 
-static void write_safari_cfg(unsigned long val)
+static void update_safari_cfg(void *arg)
 {
+	unsigned long reg, *new_bits = arg;
+
+	read_safari_cfg(&reg);
+	reg &= ~SAFARI_CFG_DIV_MASK;
+	reg |= *new_bits;
+
 	__asm__ __volatile__("stxa	%0, [%%g0] %1\n\t"
 			     "membar	#Sync"
 			     : /* no outputs */
-			     : "r" (val), "i" (ASI_SAFARI_CONFIG)
+			     : "r" (reg), "i" (ASI_SAFARI_CONFIG)
 			     : "memory");
 }
 
@@ -78,29 +84,17 @@ static unsigned long get_current_freq(unsigned int cpu, unsigned long safari_cfg
 
 static unsigned int us3_freq_get(unsigned int cpu)
 {
-	cpumask_t cpus_allowed;
 	unsigned long reg;
-	unsigned int ret;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
-	reg = read_safari_cfg();
-	ret = get_current_freq(cpu, reg);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
 
-	return ret;
+	if (smp_call_function_single(cpu, read_safari_cfg, &reg, 1))
+		return 0;
+	return get_current_freq(cpu, reg);
 }
 
 static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned int cpu = policy->cpu;
-	unsigned long new_bits, new_freq, reg;
-	cpumask_t cpus_allowed;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+	unsigned long new_bits, new_freq;
 
 	new_freq = sparc64_get_clock_tick(cpu) / 1000;
 	switch (index) {
@@ -121,15 +115,7 @@ static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 		BUG();
 	}
 
-	reg = read_safari_cfg();
-
-	reg &= ~SAFARI_CFG_DIV_MASK;
-	reg |= new_bits;
-	write_safari_cfg(reg);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
-
-	return 0;
+	return smp_call_function_single(cpu, update_safari_cfg, &new_bits, 1);
 }
 
 static int __init us3_freq_cpu_init(struct cpufreq_policy *policy)