Merge branch 'sched-core-for-linus' of...

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (35 commits)
  sched, cputime: Introduce thread_group_times()
  sched, cputime: Cleanups related to task_times()
  Revert "sched, x86: Optimize branch hint in __switch_to()"
  sched: Fix isolcpus boot option
  sched: Revert 498657a4
  sched, time: Define nsecs_to_jiffies()
  sched: Remove task_{u,s,g}time()
  sched: Introduce task_times() to replace task_{u,s}time() pair
  sched: Limit the number of scheduler debug messages
  sched.c: Call debug_show_all_locks() when dumping all tasks
  sched, x86: Optimize branch hint in __switch_to()
  sched: Optimize branch hint in context_switch()
  sched: Optimize branch hint in pick_next_task_fair()
  sched_feat_write(): Update ppos instead of file->f_pos
  sched: Sched_rt_periodic_timer vs cpu hotplug
  sched, kvm: Fix race condition involving sched_in_preempt_notifers
  sched: More generic WAKE_AFFINE vs select_idle_sibling()
  sched: Cleanup select_task_rq_fair()
  sched: Fix granularity of task_u/stime()
  sched: Fix/add missing update_rq_clock() calls
  ...

Documentation/feature-removal-schedule.txt

@@ -6,6 +6,21 @@ be removed from this file.
 
 ---------------------------
 
+What:	USER_SCHED
+When:	2.6.34
+
+Why:	USER_SCHED was implemented as a proof of concept for group scheduling.
+	The effect of USER_SCHED can already be achieved from userspace with
+	the help of libcgroup. The removal of USER_SCHED will also simplify
+	the scheduler code with the removal of one major ifdef. There are also
+	issues USER_SCHED has with USER_NS. A decision was taken not to fix
+	those and instead remove USER_SCHED. Also new group scheduling
+	features will not be implemented for USER_SCHED.
+
+Who:	Dhaval Giani <dhaval@linux.vnet.ibm.com>
+
+---------------------------
+
 What:	PRISM54
 When:	2.6.34
 

Documentation/filesystems/proc.txt

@@ -1072,7 +1072,8 @@ second).  The meanings of the columns are as follows, from left to right:
 - irq: servicing interrupts
 - softirq: servicing softirqs
 - steal: involuntary wait
-- guest: running a guest
+- guest: running a normal guest
+- guest_nice: running a niced guest
 
 The "intr" line gives counts of interrupts  serviced since boot time, for each
 of the  possible system interrupts.   The first  column  is the  total of  all

Documentation/kernel-parameters.txt

@@ -2186,6 +2186,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	sbni=		[NET] Granch SBNI12 leased line adapter
 
+	sched_debug	[KNL] Enables verbose scheduler debug messages.
+
 	sc1200wdt=	[HW,WDT] SC1200 WDT (watchdog) driver
 			Format: <io>[,<timeout>[,<isapnp>]]
 

fs/proc/array.c

@@ -410,6 +410,16 @@ static void task_show_stack_usage(struct seq_file *m, struct task_struct *task)
 }
 #endif		/* CONFIG_MMU */
 
+static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_allowed:\t");
+	seq_cpumask(m, &task->cpus_allowed);
+	seq_printf(m, "\n");
+	seq_printf(m, "Cpus_allowed_list:\t");
+	seq_cpumask_list(m, &task->cpus_allowed);
+	seq_printf(m, "\n");
+}
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task)
 {
@@ -424,6 +434,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 	}
 	task_sig(m, task);
 	task_cap(m, task);
+	task_cpus_allowed(m, task);
 	cpuset_task_status_allowed(m, task);
 #if defined(CONFIG_S390)
 	task_show_regs(m, task);
@@ -495,20 +506,17 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_cputime cputime;
 			struct task_struct *t = task;
 			do {
 				min_flt += t->min_flt;
 				maj_flt += t->maj_flt;
-				gtime = cputime_add(gtime, task_gtime(t));
+				gtime = cputime_add(gtime, t->gtime);
 				t = next_thread(t);
 			} while (t != task);
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			thread_group_cputime(task, &cputime);
-			utime = cputime.utime;
-			stime = cputime.stime;
+			thread_group_times(task, &utime, &stime);
 			gtime = cputime_add(gtime, sig->gtime);
 		}
 
@@ -524,9 +532,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (!whole) {
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		utime = task_utime(task);
-		stime = task_stime(task);
-		gtime = task_gtime(task);
+		task_times(task, &utime, &stime);
+		gtime = task->gtime;
 	}
 
 	/* scale priority and nice values from timeslices to -20..20 */

fs/proc/stat.c

@@ -27,7 +27,7 @@ static int show_stat(struct seq_file *p, void *v)
 	int i, j;
 	unsigned long jif;
 	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
-	cputime64_t guest;
+	cputime64_t guest, guest_nice;
 	u64 sum = 0;
 	u64 sum_softirq = 0;
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
@@ -36,7 +36,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
-	guest = cputime64_zero;
+	guest = guest_nice = cputime64_zero;
 	getboottime(&boottime);
 	jif = boottime.tv_sec;
 
@@ -51,6 +51,8 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
+		guest_nice = cputime64_add(guest_nice,
+			kstat_cpu(i).cpustat.guest_nice);
 		for_each_irq_nr(j) {
 			sum += kstat_irqs_cpu(j, i);
 		}
@@ -65,7 +67,8 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+		"%llu\n",
 		(unsigned long long)cputime64_to_clock_t(user),
 		(unsigned long long)cputime64_to_clock_t(nice),
 		(unsigned long long)cputime64_to_clock_t(system),
@@ -74,7 +77,8 @@ static int show_stat(struct seq_file *p, void *v)
 		(unsigned long long)cputime64_to_clock_t(irq),
 		(unsigned long long)cputime64_to_clock_t(softirq),
 		(unsigned long long)cputime64_to_clock_t(steal),
-		(unsigned long long)cputime64_to_clock_t(guest));
+		(unsigned long long)cputime64_to_clock_t(guest),
+		(unsigned long long)cputime64_to_clock_t(guest_nice));
 	for_each_online_cpu(i) {
 
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
@@ -88,8 +92,10 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = kstat_cpu(i).cpustat.softirq;
 		steal = kstat_cpu(i).cpustat.steal;
 		guest = kstat_cpu(i).cpustat.guest;
+		guest_nice = kstat_cpu(i).cpustat.guest_nice;
 		seq_printf(p,
-			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+			"%llu\n",
 			i,
 			(unsigned long long)cputime64_to_clock_t(user),
 			(unsigned long long)cputime64_to_clock_t(nice),
@@ -99,7 +105,8 @@ static int show_stat(struct seq_file *p, void *v)
 			(unsigned long long)cputime64_to_clock_t(irq),
 			(unsigned long long)cputime64_to_clock_t(softirq),
 			(unsigned long long)cputime64_to_clock_t(steal),
-			(unsigned long long)cputime64_to_clock_t(guest));
+			(unsigned long long)cputime64_to_clock_t(guest),
+			(unsigned long long)cputime64_to_clock_t(guest_nice));
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 

include/linux/jiffies.h

@@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x);
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);
+extern unsigned long nsecs_to_jiffies(u64 n);
 
 #define TIMESTAMP_SIZE	30
 

include/linux/kernel_stat.h

@@ -25,6 +25,7 @@ struct cpu_usage_stat {
 	cputime64_t iowait;
 	cputime64_t steal;
 	cputime64_t guest;
+	cputime64_t guest_nice;
 };
 
 struct kernel_stat {

include/linux/preempt.h

@@ -105,6 +105,11 @@ struct preempt_notifier;
  * @sched_out: we've just been preempted
  *    notifier: struct preempt_notifier for the task being preempted
  *    next: the task that's kicking us out
+ *
+ * Please note that sched_in and out are called under different
+ * contexts.  sched_out is called with rq lock held and irq disabled
+ * while sched_in is called without rq lock and irq enabled.  This
+ * difference is intentional and depended upon by its users.
  */
 struct preempt_ops {
 	void (*sched_in)(struct preempt_notifier *notifier, int cpu);

include/linux/sched.h

@@ -145,7 +145,6 @@ extern unsigned long this_cpu_load(void);
 
 
 extern void calc_global_load(void);
-extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -171,8 +170,6 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 }
 #endif
 
-extern unsigned long long time_sync_thresh;
-
 /*
  * Task state bitmask. NOTE! These bits are also
  * encoded in fs/proc/array.c: get_task_state().
@@ -349,7 +346,6 @@ extern signed long schedule_timeout(signed long timeout);
 extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
-asmlinkage void __schedule(void);
 asmlinkage void schedule(void);
 extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 
@@ -628,6 +624,9 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	cputime_t prev_utime, prev_stime;
+#endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	unsigned long inblock, oublock, cinblock, coublock;
@@ -1013,9 +1012,13 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
-extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
 /* Test a flag in parent sched domain */
 static inline int test_sd_parent(struct sched_domain *sd, int flag)
 {
@@ -1033,7 +1036,7 @@ unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {
 }
@@ -1331,7 +1334,9 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	cputime_t prev_utime, prev_stime;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
 	struct timespec real_start_time;	/* boot based time */
@@ -1720,9 +1725,8 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
-extern cputime_t task_utime(struct task_struct *p);
-extern cputime_t task_stime(struct task_struct *p);
-extern cputime_t task_gtime(struct task_struct *p);
+extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags

kernel/cpuset.c

@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *	element of the partition (one sched domain) to be passed to
  *	partition_sched_domains().
  */
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	LIST_HEAD(q);		/* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
-	struct cpumask *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
-		doms = kmalloc(cpumask_size(), GFP_KERNEL);
+		ndoms = 1;
+		doms = alloc_sched_domains(ndoms);
 		if (!doms)
 			goto done;
 
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms, top_cpuset.cpus_allowed);
+		cpumask_copy(doms[0], top_cpuset.cpus_allowed);
 
-		ndoms = 1;
 		goto done;
 	}
 
@@ -636,7 +635,7 @@ static int generate_sched_domains(struct cpumask **domains,
 	 * Now we know how many domains to create.
 	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
 	 */
-	doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+	doms = alloc_sched_domains(ndoms);
 	if (!doms)
 		goto done;
 
@@ -656,7 +655,7 @@ static int generate_sched_domains(struct cpumask **domains,
 			continue;
 		}
 
-		dp = doms + nslot;
+		dp = doms[nslot];
 
 		if (nslot == ndoms) {
 			static int warnings = 10;
@@ -718,7 +717,7 @@ static int generate_sched_domains(struct cpumask **domains,
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	get_online_cpus();
@@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	switch (phase) {
@@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = {
 };
 #endif /* CONFIG_PROC_PID_CPUSET */
 
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_printf(m, "Cpus_allowed:\t");
-	seq_cpumask(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
-	seq_printf(m, "Cpus_allowed_list:\t");
-	seq_cpumask_list(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
 	seq_printf(m, "Mems_allowed:\t");
 	seq_nodemask(m, &task->mems_allowed);
 	seq_printf(m, "\n");

kernel/exit.c

@@ -111,9 +111,9 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, task_utime(tsk));
-		sig->stime = cputime_add(sig->stime, task_stime(tsk));
-		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+		sig->utime = cputime_add(sig->utime, tsk->utime);
+		sig->stime = cputime_add(sig->stime, tsk->stime);
+		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;
@@ -1210,6 +1210,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		struct signal_struct *psig;
 		struct signal_struct *sig;
 		unsigned long maxrss;
+		cputime_t tgutime, tgstime;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1225,20 +1226,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * need to protect the access to parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_times() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
 		 */
+		thread_group_times(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(p->utime,
-			cputime_add(sig->utime,
-				    sig->cutime)));
+			cputime_add(tgutime,
+				    sig->cutime));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(p->stime,
-			cputime_add(sig->stime,
-				    sig->cstime)));
+			cputime_add(tgstime,
+				    sig->cstime));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,

kernel/fork.c

@@ -884,6 +884,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	sig->prev_utime = sig->prev_stime = cputime_zero;
+#endif
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
@@ -1066,8 +1069,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->gtime = cputime_zero;
 	p->utimescaled = cputime_zero;
 	p->stimescaled = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
+#endif
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 

kernel/kgdb.c

@@ -870,7 +870,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
 
 	/*
 	 * All threads that don't have debuggerinfo should be
-	 * in __schedule() sleeping, since all other CPUs
+	 * in schedule() sleeping, since all other CPUs
 	 * are in kgdb_wait, and thus have debuggerinfo.
 	 */
 	if (local_debuggerinfo) {

kernel/sched_debug.c

@@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu)
 
 #ifdef CONFIG_SCHEDSTATS
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
 	P(yld_count);
 
 	P(sched_switch);
 	P(sched_count);
 	P(sched_goidle);
+#ifdef CONFIG_SMP
+	P64(avg_idle);
+#endif
 
 	P(ttwu_count);
 	P(ttwu_local);

kernel/sched_fair.c

@@ -1344,6 +1344,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return idlest;
 }
 
+/*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	int cpu = smp_processor_id();
+	int prev_cpu = task_cpu(p);
+	int i;
+
+	/*
+	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
+	 * always a better target than the current cpu.
+	 */
+	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+		return prev_cpu;
+
+	/*
+	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 */
+	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+		if (!cpu_rq(i)->cfs.nr_running) {
+			target = i;
+			break;
+		}
+	}
+
+	return target;
+}
+
 /*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
@@ -1398,12 +1429,36 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				want_sd = 0;
 		}
 
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+		/*
+		 * While iterating the domains looking for a spanning
+		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+		 * in cache sharing domains along the way.
+		 */
+		if (want_affine) {
+			int target = -1;
+
+			/*
+			 * If both cpu and prev_cpu are part of this domain,
+			 * cpu is a valid SD_WAKE_AFFINE target.
+			 */
+			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+				target = cpu;
 
+			/*
+			 * If there's an idle sibling in this domain, make that
+			 * the wake_affine target instead of the current cpu.
+			 */
+			if (tmp->flags & SD_PREFER_SIBLING)
+				target = select_idle_sibling(p, tmp, target);
+
+			if (target >= 0) {
+				if (tmp->flags & SD_WAKE_AFFINE) {
 					affine_sd = tmp;
 					want_affine = 0;
 				}
+				cpu = target;
+			}
+		}
 
 		if (!want_sd && !want_affine)
 			break;
@@ -1679,7 +1734,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 
-	if (unlikely(!cfs_rq->nr_running))
+	if (!cfs_rq->nr_running)
 		return NULL;
 
 	do {

kernel/sched_rt.c

@@ -1153,29 +1153,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu,
-				   const struct cpumask *mask)
-{
-	int first;
-
-	/* "this_cpu" is cheaper to preempt than a remote processor */
-	if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
-		return this_cpu;
-
-	first = cpumask_first(mask);
-	if (first < nr_cpu_ids)
-		return first;
-
-	return -1;
-}
-
 static int find_lowest_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
 	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
-	cpumask_var_t domain_mask;
 
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
@@ -1198,36 +1181,40 @@ static int find_lowest_rq(struct task_struct *task)
 	 * Otherwise, we consult the sched_domains span maps to figure
 	 * out which cpu is logically closest to our hot cache data.
 	 */
-	if (this_cpu == cpu)
-		this_cpu = -1; /* Skip this_cpu opt if the same */
+	if (!cpumask_test_cpu(this_cpu, lowest_mask))
+		this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
-	if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
 	for_each_domain(cpu, sd) {
 		if (sd->flags & SD_WAKE_AFFINE) {
 			int best_cpu;
 
-				cpumask_and(domain_mask,
-					    sched_domain_span(sd),
-					    lowest_mask);
-
-				best_cpu = pick_optimal_cpu(this_cpu,
-							    domain_mask);
+			/*
+			 * "this_cpu" is cheaper to preempt than a
+			 * remote processor.
+			 */
+			if (this_cpu != -1 &&
+			    cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+				return this_cpu;
 
-				if (best_cpu != -1) {
-					free_cpumask_var(domain_mask);
+			best_cpu = cpumask_first_and(lowest_mask,
+						     sched_domain_span(sd));
+			if (best_cpu < nr_cpu_ids)
 				return best_cpu;
 		}
 	}
-		}
-		free_cpumask_var(domain_mask);
-	}
 
 	/*
 	 * And finally, if there were no matches within the domains
 	 * just give the caller *something* to work with from the compatible
 	 * locations.
 	 */
-	return pick_optimal_cpu(this_cpu, lowest_mask);
+	if (this_cpu != -1)
+		return this_cpu;
+
+	cpu = cpumask_any(lowest_mask);
+	if (cpu < nr_cpu_ids)
+		return cpu;
+	return -1;
 }
 
 /* Will lock the rq it finds */

kernel/sys.c

@@ -911,16 +911,15 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 
 void do_sys_times(struct tms *tms)
 {
-	struct task_cputime cputime;
-	cputime_t cutime, cstime;
+	cputime_t tgutime, tgstime, cutime, cstime;
 
-	thread_group_cputime(current, &cputime);
 	spin_lock_irq(&current->sighand->siglock);
+	thread_group_times(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);
-	tms->tms_utime = cputime_to_clock_t(cputime.utime);
-	tms->tms_stime = cputime_to_clock_t(cputime.stime);
+	tms->tms_utime = cputime_to_clock_t(tgutime);
+	tms->tms_stime = cputime_to_clock_t(tgstime);
 	tms->tms_cutime = cputime_to_clock_t(cutime);
 	tms->tms_cstime = cputime_to_clock_t(cstime);
 }
@@ -1338,16 +1337,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 {
 	struct task_struct *t;
 	unsigned long flags;
-	cputime_t utime, stime;
-	struct task_cputime cputime;
+	cputime_t tgutime, tgstime, utime, stime;
 	unsigned long maxrss = 0;
 
 	memset((char *) r, 0, sizeof *r);
 	utime = stime = cputime_zero;
 
 	if (who == RUSAGE_THREAD) {
-		utime = task_utime(current);
-		stime = task_stime(current);
+		task_times(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = p->signal->maxrss;
 		goto out;
@@ -1373,9 +1370,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			thread_group_cputime(p, &cputime);
-			utime = cputime_add(utime, cputime.utime);
-			stime = cputime_add(stime, cputime.stime);
+			thread_group_times(p, &tgutime, &tgstime);
+			utime = cputime_add(utime, tgutime);
+			stime = cputime_add(stime, tgstime);
 			r->ru_nvcsw += p->signal->nvcsw;
 			r->ru_nivcsw += p->signal->nivcsw;
 			r->ru_minflt += p->signal->min_flt;

kernel/time.c

@@ -662,6 +662,36 @@ u64 nsec_to_clock_t(u64 x)
 #endif
 }
 
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n:	nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+#if (NSEC_PER_SEC % HZ) == 0
+	/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
+	return div_u64(n, NSEC_PER_SEC / HZ);
+#elif (HZ % 512) == 0
+	/* overflow after 292 years if HZ = 1024 */
+	return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
+#else
+	/*
+	 * Generic case - optimized for cases where HZ is a multiple of 3.
+	 * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
+	 */
+	return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
+#endif
+}
+
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {