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

Pull scheduler fixes from Thomas Gleixner:
 "This scheduler update provides:

   - The (hopefully) final fix for the vtime accounting issues which
     were around for quite some time

   - Use types known to user space in UAPI headers to unbreak user space
     builds

   - Make load balancing respect the current scheduling domain again
     instead of evaluating unrelated CPUs"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/headers/uapi: Fix linux/sched/types.h userspace compilation errors
  sched/fair: Fix load_balance() affinity redo path
  sched/cputime: Accumulate vtime on top of nsec clocksource
  sched/cputime: Move the vtime task fields to their own struct
  sched/cputime: Rename vtime fields
  sched/cputime: Always set tsk->vtime_snap_whence after accounting vtime
  vtime, sched/cputime: Remove vtime_account_user()
  Revert "sched/cputime: Refactor the cputime_adjust() code"

3 files changed, 134 insertions, 84 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index aa01b810c0bd..0f69a3e5281e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1637,9 +1637,9 @@ static __latent_entropy struct task_struct *copy_process(
 	prev_cputime_init(&p->prev_cputime);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqcount_init(&p->vtime_seqcount);
-	p->vtime_snap = 0;
-	p->vtime_snap_whence = VTIME_INACTIVE;
+	seqcount_init(&p->vtime.seqcount);
+	p->vtime.starttime = 0;
+	p->vtime.state = VTIME_INACTIVE;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 67c70e287647..6e3ea4ac1bda 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -611,17 +611,23 @@ static void cputime_adjust(struct task_cputime *curr,
 	utime = curr->utime;
 
 	/*
-	 * If either stime or both stime and utime are 0, assume all runtime is
-	 * userspace. Once a task gets some ticks, the monotonicy code at
-	 * 'update' will ensure things converge to the observed ratio.
+	 * If either stime or utime are 0, assume all runtime is userspace.
+	 * Once a task gets some ticks, the monotonicy code at 'update:'
+	 * will ensure things converge to the observed ratio.
 	 */
-	if (stime != 0) {
-		if (utime == 0)
-			stime = rtime;
-		else
-			stime = scale_stime(stime, rtime, stime + utime);
+	if (stime == 0) {
+		utime = rtime;
+		goto update;
 	}
 
+	if (utime == 0) {
+		stime = rtime;
+		goto update;
+	}
+
+	stime = scale_stime(stime, rtime, stime + utime);
+
+update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
@@ -673,20 +679,21 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static u64 vtime_delta(struct task_struct *tsk)
+static u64 vtime_delta(struct vtime *vtime)
 {
-	unsigned long now = READ_ONCE(jiffies);
+	unsigned long long clock;
 
-	if (time_before(now, (unsigned long)tsk->vtime_snap))
+	clock = sched_clock_cpu(smp_processor_id());
+	if (clock < vtime->starttime)
 		return 0;
 
-	return jiffies_to_nsecs(now - tsk->vtime_snap);
+	return clock - vtime->starttime;
 }
 
-static u64 get_vtime_delta(struct task_struct *tsk)
+static u64 get_vtime_delta(struct vtime *vtime)
 {
-	unsigned long now = READ_ONCE(jiffies);
-	u64 delta, other;
+	u64 delta = vtime_delta(vtime);
+	u64 other;
 
 	/*
 	 * Unlike tick based timing, vtime based timing never has lost
@@ -695,104 +702,138 @@ static u64 get_vtime_delta(struct task_struct *tsk)
 	 * elapsed time. Limit account_other_time to prevent rounding
 	 * errors from causing elapsed vtime to go negative.
 	 */
-	delta = jiffies_to_nsecs(now - tsk->vtime_snap);
 	other = account_other_time(delta);
-	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
-	tsk->vtime_snap = now;
+	WARN_ON_ONCE(vtime->state == VTIME_INACTIVE);
+	vtime->starttime += delta;
 
 	return delta - other;
 }
 
-static void __vtime_account_system(struct task_struct *tsk)
+static void __vtime_account_system(struct task_struct *tsk,
+				   struct vtime *vtime)
+{
+	vtime->stime += get_vtime_delta(vtime);
+	if (vtime->stime >= TICK_NSEC) {
+		account_system_time(tsk, irq_count(), vtime->stime);
+		vtime->stime = 0;
+	}
+}
+
+static void vtime_account_guest(struct task_struct *tsk,
+				struct vtime *vtime)
 {
-	account_system_time(tsk, irq_count(), get_vtime_delta(tsk));
+	vtime->gtime += get_vtime_delta(vtime);
+	if (vtime->gtime >= TICK_NSEC) {
+		account_guest_time(tsk, vtime->gtime);
+		vtime->gtime = 0;
+	}
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	if (!vtime_delta(tsk))
+	struct vtime *vtime = &tsk->vtime;
+
+	if (!vtime_delta(vtime))
 		return;
 
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	__vtime_account_system(tsk);
-	write_seqcount_end(&tsk->vtime_seqcount);
+	write_seqcount_begin(&vtime->seqcount);
+	/* We might have scheduled out from guest path */
+	if (current->flags & PF_VCPU)
+		vtime_account_guest(tsk, vtime);
+	else
+		__vtime_account_system(tsk, vtime);
+	write_seqcount_end(&vtime->seqcount);
 }
 
-void vtime_account_user(struct task_struct *tsk)
+void vtime_user_enter(struct task_struct *tsk)
 {
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	tsk->vtime_snap_whence = VTIME_SYS;
-	if (vtime_delta(tsk))
-		account_user_time(tsk, get_vtime_delta(tsk));
-	write_seqcount_end(&tsk->vtime_seqcount);
+	struct vtime *vtime = &tsk->vtime;
+
+	write_seqcount_begin(&vtime->seqcount);
+	__vtime_account_system(tsk, vtime);
+	vtime->state = VTIME_USER;
+	write_seqcount_end(&vtime->seqcount);
 }
 
-void vtime_user_enter(struct task_struct *tsk)
+void vtime_user_exit(struct task_struct *tsk)
 {
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	if (vtime_delta(tsk))
-		__vtime_account_system(tsk);
-	tsk->vtime_snap_whence = VTIME_USER;
-	write_seqcount_end(&tsk->vtime_seqcount);
+	struct vtime *vtime = &tsk->vtime;
+
+	write_seqcount_begin(&vtime->seqcount);
+	vtime->utime += get_vtime_delta(vtime);
+	if (vtime->utime >= TICK_NSEC) {
+		account_user_time(tsk, vtime->utime);
+		vtime->utime = 0;
+	}
+	vtime->state = VTIME_SYS;
+	write_seqcount_end(&vtime->seqcount);
 }
 
 void vtime_guest_enter(struct task_struct *tsk)
 {
+	struct vtime *vtime = &tsk->vtime;
 	/*
 	 * The flags must be updated under the lock with
-	 * the vtime_snap flush and update.
+	 * the vtime_starttime flush and update.
 	 * That enforces a right ordering and update sequence
 	 * synchronization against the reader (task_gtime())
 	 * that can thus safely catch up with a tickless delta.
 	 */
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	if (vtime_delta(tsk))
-		__vtime_account_system(tsk);
+	write_seqcount_begin(&vtime->seqcount);
+	__vtime_account_system(tsk, vtime);
 	current->flags |= PF_VCPU;
-	write_seqcount_end(&tsk->vtime_seqcount);
+	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
 
 void vtime_guest_exit(struct task_struct *tsk)
 {
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	__vtime_account_system(tsk);
+	struct vtime *vtime = &tsk->vtime;
+
+	write_seqcount_begin(&vtime->seqcount);
+	vtime_account_guest(tsk, vtime);
 	current->flags &= ~PF_VCPU;
-	write_seqcount_end(&tsk->vtime_seqcount);
+	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	account_idle_time(get_vtime_delta(tsk));
+	account_idle_time(get_vtime_delta(&tsk->vtime));
 }
 
 void arch_vtime_task_switch(struct task_struct *prev)
 {
-	write_seqcount_begin(&prev->vtime_seqcount);
-	prev->vtime_snap_whence = VTIME_INACTIVE;
-	write_seqcount_end(&prev->vtime_seqcount);
+	struct vtime *vtime = &prev->vtime;
+
+	write_seqcount_begin(&vtime->seqcount);
+	vtime->state = VTIME_INACTIVE;
+	write_seqcount_end(&vtime->seqcount);
+
+	vtime = &current->vtime;
 
-	write_seqcount_begin(&current->vtime_seqcount);
-	current->vtime_snap_whence = VTIME_SYS;
-	current->vtime_snap = jiffies;
-	write_seqcount_end(&current->vtime_seqcount);
+	write_seqcount_begin(&vtime->seqcount);
+	vtime->state = VTIME_SYS;
+	vtime->starttime = sched_clock_cpu(smp_processor_id());
+	write_seqcount_end(&vtime->seqcount);
 }
 
 void vtime_init_idle(struct task_struct *t, int cpu)
 {
+	struct vtime *vtime = &t->vtime;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	write_seqcount_begin(&t->vtime_seqcount);
-	t->vtime_snap_whence = VTIME_SYS;
-	t->vtime_snap = jiffies;
-	write_seqcount_end(&t->vtime_seqcount);
+	write_seqcount_begin(&vtime->seqcount);
+	vtime->state = VTIME_SYS;
+	vtime->starttime = sched_clock_cpu(cpu);
+	write_seqcount_end(&vtime->seqcount);
 	local_irq_restore(flags);
 }
 
 u64 task_gtime(struct task_struct *t)
 {
+	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 gtime;
 
@@ -800,13 +841,13 @@ u64 task_gtime(struct task_struct *t)
 		return t->gtime;
 
 	do {
-		seq = read_seqcount_begin(&t->vtime_seqcount);
+		seq = read_seqcount_begin(&vtime->seqcount);
 
 		gtime = t->gtime;
-		if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU)
-			gtime += vtime_delta(t);
+		if (vtime->state == VTIME_SYS && t->flags & PF_VCPU)
+			gtime += vtime->gtime + vtime_delta(vtime);
 
-	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
 
 	return gtime;
 }
@@ -818,8 +859,9 @@ u64 task_gtime(struct task_struct *t)
  */
 void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
-	u64 delta;
+	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
+	u64 delta;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
@@ -828,25 +870,25 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 	}
 
 	do {
-		seq = read_seqcount_begin(&t->vtime_seqcount);
+		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*utime = t->utime;
 		*stime = t->stime;
 
 		/* Task is sleeping, nothing to add */
-		if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t))
+		if (vtime->state == VTIME_INACTIVE || is_idle_task(t))
 			continue;
 
-		delta = vtime_delta(t);
+		delta = vtime_delta(vtime);
 
 		/*
 		 * Task runs either in user or kernel space, add pending nohz time to
 		 * the right place.
 		 */
-		if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU)
-			*utime += delta;
-		else if (t->vtime_snap_whence == VTIME_SYS)
-			*stime += delta;
-	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
+		if (vtime->state == VTIME_USER || t->flags & PF_VCPU)
+			*utime += vtime->utime + delta;
+		else if (vtime->state == VTIME_SYS)
+			*stime += vtime->stime + delta;
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 008c514dc241..c95880e216f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6646,10 +6646,10 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		 * our sched_group. We may want to revisit it if we couldn't
 		 * meet load balance goals by pulling other tasks on src_cpu.
 		 *
-		 * Also avoid computing new_dst_cpu if we have already computed
-		 * one in current iteration.
+		 * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
+		 * already computed one in current iteration.
 		 */
-		if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
+		if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's cpus */
@@ -8022,14 +8022,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.tasks		= LIST_HEAD_INIT(env.tasks),
 	};
 
-	/*
-	 * For NEWLY_IDLE load_balancing, we don't need to consider
-	 * other cpus in our group
-	 */
-	if (idle == CPU_NEWLY_IDLE)
-		env.dst_grpmask = NULL;
-
-	cpumask_copy(cpus, cpu_active_mask);
+	cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
 
 	schedstat_inc(sd->lb_count[idle]);
 
@@ -8151,7 +8144,15 @@ more_balance:
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus)) {
+			/*
+			 * Attempting to continue load balancing at the current
+			 * sched_domain level only makes sense if there are
+			 * active CPUs remaining as possible busiest CPUs to
+			 * pull load from which are not contained within the
+			 * destination group that is receiving any migrated
+			 * load.
+			 */
+			if (!cpumask_subset(cpus, env.dst_grpmask)) {
 				env.loop = 0;
 				env.loop_break = sched_nr_migrate_break;
 				goto redo;
@@ -8447,6 +8448,13 @@ static int active_load_balance_cpu_stop(void *data)
 			.src_cpu	= busiest_rq->cpu,
 			.src_rq		= busiest_rq,
 			.idle		= CPU_IDLE,
+			/*
+			 * can_migrate_task() doesn't need to compute new_dst_cpu
+			 * for active balancing. Since we have CPU_IDLE, but no
+			 * @dst_grpmask we need to make that test go away with lying
+			 * about DST_PINNED.
+			 */
+			.flags		= LBF_DST_PINNED,
 		};
 
 		schedstat_inc(sd->alb_count);