Merge branch 'rt/head' into rt/2.6.31

arch/x86/include/asm/cpufeature.h

@@ -95,6 +95,7 @@
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 #define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_APERFMPERF	(3*32+27) /* APERFMPERF */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */

arch/x86/include/asm/processor.h

@@ -27,6 +27,7 @@ struct mm_struct;
 #include <linux/cpumask.h>
 #include <linux/cache.h>
 #include <linux/threads.h>
+#include <linux/math64.h>
 #include <linux/init.h>
 
 /*
@@ -1010,4 +1011,33 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
+struct aperfmperf {
+	u64 aperf, mperf;
+};
+
+static inline void get_aperfmperf(struct aperfmperf *am)
+{
+	WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF));
+
+	rdmsrl(MSR_IA32_APERF, am->aperf);
+	rdmsrl(MSR_IA32_MPERF, am->mperf);
+}
+
+#define APERFMPERF_SHIFT 10
+
+static inline
+unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
+				    struct aperfmperf *new)
+{
+	u64 aperf = new->aperf - old->aperf;
+	u64 mperf = new->mperf - old->mperf;
+	unsigned long ratio = aperf;
+
+	mperf >>= APERFMPERF_SHIFT;
+	if (mperf)
+		ratio = div64_u64(aperf, mperf);
+
+	return ratio;
+}
+
 #endif /* _ASM_X86_PROCESSOR_H */

arch/x86/kernel/cpu/Makefile

@@ -13,7 +13,7 @@ CFLAGS_common.o		:= $(nostackp)
 
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
-obj-y			+= vmware.o hypervisor.o
+obj-y			+= vmware.o hypervisor.o sched.o
 
 obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)	+= bugs_64.o

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -60,7 +60,6 @@ enum {
 };
 
 #define INTEL_MSR_RANGE		(0xffff)
-#define CPUID_6_ECX_APERFMPERF_CAPABILITY	(0x1)
 
 struct acpi_cpufreq_data {
 	struct acpi_processor_performance *acpi_data;
@@ -71,11 +70,7 @@ struct acpi_cpufreq_data {
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
-struct acpi_msr_data {
-	u64 saved_aperf, saved_mperf;
-};
-
-static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+static DEFINE_PER_CPU(struct aperfmperf, old_perf);
 
 DEFINE_TRACE(power_mark);
 
@@ -244,23 +239,12 @@ static u32 get_cur_val(const struct cpumask *mask)
 	return cmd.val;
 }
 
-struct perf_pair {
-	union {
-		struct {
-			u32 lo;
-			u32 hi;
-		} split;
-		u64 whole;
-	} aperf, mperf;
-};
-
 /* Called via smp_call_function_single(), on the target CPU */
 static void read_measured_perf_ctrs(void *_cur)
 {
-	struct perf_pair *cur = _cur;
+	struct aperfmperf *am = _cur;
 
-	rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
-	rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
+	get_aperfmperf(am);
 }
 
 /*
@@ -279,63 +263,17 @@ static void read_measured_perf_ctrs(void *_cur)
 static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 				      unsigned int cpu)
 {
-	struct perf_pair readin, cur;
-	unsigned int perf_percent;
+	struct aperfmperf perf;
+	unsigned long ratio;
 	unsigned int retval;
 
-	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1))
+	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
 		return 0;
 
-	cur.aperf.whole = readin.aperf.whole -
-				per_cpu(msr_data, cpu).saved_aperf;
-	cur.mperf.whole = readin.mperf.whole -
-				per_cpu(msr_data, cpu).saved_mperf;
-	per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole;
-	per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole;
-
-#ifdef __i386__
-	/*
-	 * We dont want to do 64 bit divide with 32 bit kernel
-	 * Get an approximate value. Return failure in case we cannot get
-	 * an approximate value.
-	 */
-	if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) {
-		int shift_count;
-		u32 h;
-
-		h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi);
-		shift_count = fls(h);
-
-		cur.aperf.whole >>= shift_count;
-		cur.mperf.whole >>= shift_count;
-	}
-
-	if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) {
-		int shift_count = 7;
-		cur.aperf.split.lo >>= shift_count;
-		cur.mperf.split.lo >>= shift_count;
-	}
-
-	if (cur.aperf.split.lo && cur.mperf.split.lo)
-		perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo;
-	else
-		perf_percent = 0;
+	ratio = calc_aperfmperf_ratio(&per_cpu(old_perf, cpu), &perf);
+	per_cpu(old_perf, cpu) = perf;
 
-#else
-	if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) {
-		int shift_count = 7;
-		cur.aperf.whole >>= shift_count;
-		cur.mperf.whole >>= shift_count;
-	}
-
-	if (cur.aperf.whole && cur.mperf.whole)
-		perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole;
-	else
-		perf_percent = 0;
-
-#endif
-
-	retval = (policy->cpuinfo.max_freq * perf_percent) / 100;
+	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
 
 	return retval;
 }
@@ -731,12 +669,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	acpi_processor_notify_smm(THIS_MODULE);
 
 	/* Check for APERF/MPERF support in hardware */
-	if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) {
-		unsigned int ecx;
-		ecx = cpuid_ecx(6);
-		if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY)
-			acpi_cpufreq_driver.getavg = get_measured_perf;
-	}
+	if (cpu_has(c, X86_FEATURE_APERFMPERF))
+		acpi_cpufreq_driver.getavg = get_measured_perf;
 
 	dprintk("CPU%u - ACPI performance management activated.\n", cpu);
 	for (i = 0; i < perf->state_count; i++)

arch/x86/kernel/cpu/intel.c

@@ -349,6 +349,12 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
+	if (c->cpuid_level > 6) {
+		unsigned ecx = cpuid_ecx(6);
+		if (ecx & 0x01)
+			set_cpu_cap(c, X86_FEATURE_APERFMPERF);
+	}
+
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 	if (cpu_has_ds) {

arch/x86/kernel/cpu/sched.c

+#include <linux/sched.h>
+#include <linux/math64.h>
+#include <linux/percpu.h>
+#include <linux/irqflags.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+static DEFINE_PER_CPU(struct aperfmperf, old_aperfmperf);
+
+static unsigned long scale_aperfmperf(void)
+{
+	struct aperfmperf cur, val, *old = &__get_cpu_var(old_aperfmperf);
+	unsigned long ratio = SCHED_LOAD_SCALE;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	get_aperfmperf(&val);
+	local_irq_restore(flags);
+
+	cur = val;
+	cur.aperf -= old->aperf;
+	cur.mperf -= old->mperf;
+	*old = val;
+
+	cur.mperf >>= SCHED_LOAD_SHIFT;
+	if (cur.mperf)
+		ratio = div_u64(cur.aperf, cur.mperf);
+
+	return ratio;
+}
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	/*
+	 * do aperf/mperf on the cpu level because it includes things
+	 * like turbo mode, which are relevant to full cores.
+	 */
+	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+		return scale_aperfmperf();
+
+	/*
+	 * maybe have something cpufreq here
+	 */
+
+	return default_scale_freq_power(sd, cpu);
+}
+
+unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	/*
+	 * aperf/mperf already includes the smt gain
+	 */
+	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+		return SCHED_LOAD_SCALE;
+
+	return default_scale_smt_power(sd, cpu);
+}

include/linux/sched.h

@@ -843,18 +843,19 @@ enum cpu_idle_type {
 #define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
 
 #ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		4	/* Balance on exec */
-#define SD_BALANCE_FORK		8	/* Balance on fork, clone */
-#define SD_WAKE_IDLE		16	/* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE		32	/* Wake task to waking CPU */
-#define SD_WAKE_BALANCE		64	/* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER	128	/* Domain members share cpu power */
-#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
-#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
-#define SD_SERIALIZE		1024	/* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
+#define SD_WAKE_IDLE		0x0010	/* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
+#define SD_WAKE_BALANCE		0x0040	/* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
+#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
+#define SD_WAKE_IDLE_FAR	0x0800	/* Gain latency sacrificing cache hit */
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
 	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
@@ -874,7 +875,7 @@ static inline int sd_balance_for_mc_power(void)
 	if (sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 static inline int sd_balance_for_package_power(void)
@@ -882,7 +883,7 @@ static inline int sd_balance_for_package_power(void)
 	if (sched_mc_power_savings | sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 /*
@@ -904,15 +905,9 @@ struct sched_group {
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU. This is read only (except for setup, hotplug CPU).
-	 * Note : Never change cpu_power without recompute its reciprocal
-	 */
-	unsigned int __cpu_power;
-	/*
-	 * reciprocal value of cpu_power to avoid expensive divides
-	 * (see include/linux/reciprocal_div.h)
+	 * single CPU.
 	 */
-	u32 reciprocal_cpu_power;
+	unsigned int cpu_power;
 
 	/*
 	 * The CPUs this group covers.
@@ -965,6 +960,7 @@ struct sched_domain {
 	unsigned int newidle_idx;
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
+	unsigned int smt_gain;
 	int flags;			/* See SD_* */
 	enum sched_domain_level level;
 
@@ -1051,6 +1047,10 @@ partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 }
 #endif	/* !CONFIG_SMP */
 
+
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
 struct io_context;			/* See blkdev.h */
 
 
@@ -1913,6 +1913,7 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,

include/linux/topology.h

@@ -99,6 +99,7 @@ int arch_update_cpu_topology(void);
 				| SD_SHARE_CPUPOWER,	\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
+	.smt_gain		= 1178,	/* 15% */	\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */

kernel/sched_fair.c

@@ -1040,39 +1040,58 @@ static void yield_task_fair(struct rq *rq)
 	se->vruntime = rightmost->vruntime + 1;
 }
 
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+/*
+ * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
+ * are idle and this is not a kernel thread and this task's affinity
+ * allows it to be moved to preferred cpu, then just move!
+ *
+ * XXX - can generate significant overload on perferred_wakeup_cpu
+ *       with plenty of idle cpus, leading to a significant loss in
+ *       throughput.
+ *
+ * Returns: <  0 - no placement decision made
+ *          >= 0 - place on cpu
+ */
+static int wake_idle_power_save(int cpu, struct task_struct *p)
+{
+	int this_cpu = smp_processor_id();
+	int wakeup_cpu;
+
+	if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+		return -1;
+
+	if (!idle_cpu(cpu) || !idle_cpu(this_cpu))
+		return -1;
+
+	if (!p->mm || (p->flags & PF_KTHREAD))
+		return -1;
+
+	wakeup_cpu = cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
+
+	if (!cpu_isset(wakeup_cpu, p->cpus_allowed))
+		return -1;
+
+	return wakeup_cpu;
+}
+
 /*
  * wake_idle() will wake a task on an idle cpu if task->cpu is
  * not idle and an idle cpu is available.  The span of cpus to
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
- * Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_mask)
  *
  * Returns the CPU we should wake onto.
  */
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
 static int wake_idle(int cpu, struct task_struct *p)
 {
-	struct sched_domain *sd;
+	struct rq *task_rq = task_rq(p);
+	struct sched_domain *sd, *child = NULL;
 	int i;
-	unsigned int chosen_wakeup_cpu;
-	int this_cpu;
 
-	/*
-	 * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
-	 * are idle and this is not a kernel thread and this task's affinity
-	 * allows it to be moved to preferred cpu, then just move!
-	 */
-
-	this_cpu = smp_processor_id();
-	chosen_wakeup_cpu =
-		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
-
-	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
-		idle_cpu(cpu) && idle_cpu(this_cpu) &&
-		p->mm && !(p->flags & PF_KTHREAD) &&
-		cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
-		return chosen_wakeup_cpu;
+	i = wake_idle_power_save(cpu, p);
+	if (i >= 0)
+		return i;
 
 	/*
 	 * If it is idle, then it is the best cpu to run this task.
@@ -1081,29 +1100,39 @@ static int wake_idle(int cpu, struct task_struct *p)
 	 * Siblings must be also busy(in most cases) as they didn't already
 	 * pickup the extra load from this cpu and hence we need not check
 	 * sibling runqueue info. This will avoid the checks and cache miss
-	 * penalities associated with that.
+	 * penalties associated with that.
 	 */
 	if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
 		return cpu;
 
-	for_each_domain(cpu, sd) {
-		if ((sd->flags & SD_WAKE_IDLE)
-		    || ((sd->flags & SD_WAKE_IDLE_FAR)
-			&& !task_hot(p, task_rq(p)->clock, sd))) {
-			for_each_cpu_and(i, sched_domain_span(sd),
-					 &p->cpus_allowed) {
-				if (cpu_active(i) && idle_cpu(i)) {
-					if (i != task_cpu(p)) {
-						schedstat_inc(p,
-						       se.nr_wakeups_idle);
-					}
-					return i;
-				}
-			}
-		} else {
+	rcu_read_lock();
+ 	for_each_domain(cpu, sd) {
+		if (!(sd->flags & SD_LOAD_BALANCE))
+ 			break;
+
+		if (!(sd->flags & SD_WAKE_IDLE) &&
+		    (task_hot(p, task_rq->clock, sd) || !(sd->flags & SD_WAKE_IDLE_FAR)))
 			break;
-		}
-	}
+
+		for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+			if (child && cpumask_test_cpu(i, sched_domain_span(child)))
+				continue;
+
+			if (!idle_cpu(i))
+				continue;
+
+			if (task_cpu(p) != i)
+				schedstat_inc(p, se.nr_wakeups_idle);
+
+			cpu = i;
+			goto unlock;
+ 		}
+
+		child = sd;
+ 	}
+unlock:
+	rcu_read_unlock();
+
 	return cpu;
 }
 #else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
@@ -1235,7 +1264,17 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	tg = task_group(p);
 	weight = p->se.load.weight;
 
-	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+	/*
+	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
+	 * due to the sync cause above having dropped tl to 0, we'll always have
+	 * an imbalance, but there's really nothing you can do about that, so
+	 * that's good too.
+	 *
+	 * Otherwise check if either cpus are near enough in load to allow this
+	 * task to be woken on this_cpu.
+	 */
+	balanced = !tl ||
+		100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
 		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
 	/*

kernel/sched_rt.c

@@ -602,6 +602,8 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -926,8 +928,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -942,8 +942,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*

kernel/sysctl.c

@@ -330,6 +330,14 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_time_avg",
+		.data		= &sysctl_sched_time_avg,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "timer_migration",