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()
  ...

6 files changed, 44 insertions, 77 deletions

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);