1 files changed, 258 insertions, 30 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 46ed4e1383e2..d43318a489f2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -405,27 +405,25 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
 /*
  * Use precise platform statistics if available:
  */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+
 # ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_common_task_switch(struct task_struct *prev)
+void vtime_task_switch(struct task_struct *prev)
 {
 	if (is_idle_task(prev))
 		vtime_account_idle(prev);
 	else
-		vtime_account_system(prev);
+		vtime_account_kernel(prev);
 
 	vtime_flush(prev);
 	arch_vtime_task_switch(prev);
 }
 # endif
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * vtime_account_kernel() and vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -436,7 +434,7 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	if (!in_interrupt() && is_idle_task(tsk))
 		vtime_account_idle(tsk);
 	else
-		vtime_account_system(tsk);
+		vtime_account_kernel(tsk);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -477,7 +475,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	u64 cputime, steal;
 	struct rq *rq = this_rq();
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		return;
 
 	if (sched_clock_irqtime) {
@@ -711,8 +709,8 @@ static u64 get_vtime_delta(struct vtime *vtime)
 	return delta - other;
 }
 
-static void __vtime_account_system(struct task_struct *tsk,
-				   struct vtime *vtime)
+static void vtime_account_system(struct task_struct *tsk,
+				 struct vtime *vtime)
 {
 	vtime->stime += get_vtime_delta(vtime);
 	if (vtime->stime >= TICK_NSEC) {
@@ -731,7 +729,17 @@ static void vtime_account_guest(struct task_struct *tsk,
 	}
 }
 
-void vtime_account_system(struct task_struct *tsk)
+static void __vtime_account_kernel(struct task_struct *tsk,
+				   struct vtime *vtime)
+{
+	/* We might have scheduled out from guest path */
+	if (vtime->state == VTIME_GUEST)
+		vtime_account_guest(tsk, vtime);
+	else
+		vtime_account_system(tsk, vtime);
+}
+
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct vtime *vtime = &tsk->vtime;
 
@@ -739,11 +747,7 @@ void vtime_account_system(struct task_struct *tsk)
 		return;
 
 	write_seqcount_begin(&vtime->seqcount);
-	/* We might have scheduled out from guest path */
-	if (tsk->flags & PF_VCPU)
-		vtime_account_guest(tsk, vtime);
-	else
-		__vtime_account_system(tsk, vtime);
+	__vtime_account_kernel(tsk, vtime);
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -752,7 +756,7 @@ void vtime_user_enter(struct task_struct *tsk)
 	struct vtime *vtime = &tsk->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	vtime->state = VTIME_USER;
 	write_seqcount_end(&vtime->seqcount);
 }
@@ -782,8 +786,9 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 * that can thus safely catch up with a tickless delta.
 	 */
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	tsk->flags |= PF_VCPU;
+	vtime->state = VTIME_GUEST;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -795,6 +800,7 @@ void vtime_guest_exit(struct task_struct *tsk)
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
 	tsk->flags &= ~PF_VCPU;
+	vtime->state = VTIME_SYS;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
@@ -804,19 +810,30 @@ void vtime_account_idle(struct task_struct *tsk)
 	account_idle_time(get_vtime_delta(&tsk->vtime));
 }
 
-void arch_vtime_task_switch(struct task_struct *prev)
+void vtime_task_switch_generic(struct task_struct *prev)
 {
 	struct vtime *vtime = &prev->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
+	if (vtime->state == VTIME_IDLE)
+		vtime_account_idle(prev);
+	else
+		__vtime_account_kernel(prev, vtime);
 	vtime->state = VTIME_INACTIVE;
+	vtime->cpu = -1;
 	write_seqcount_end(&vtime->seqcount);
 
 	vtime = &current->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	if (is_idle_task(current))
+		vtime->state = VTIME_IDLE;
+	else if (current->flags & PF_VCPU)
+		vtime->state = VTIME_GUEST;
+	else
+		vtime->state = VTIME_SYS;
 	vtime->starttime = sched_clock();
+	vtime->cpu = smp_processor_id();
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -827,8 +844,9 @@ void vtime_init_idle(struct task_struct *t, int cpu)
 
 	local_irq_save(flags);
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	vtime->state = VTIME_IDLE;
 	vtime->starttime = sched_clock();
+	vtime->cpu = cpu;
 	write_seqcount_end(&vtime->seqcount);
 	local_irq_restore(flags);
 }
@@ -846,7 +864,7 @@ u64 task_gtime(struct task_struct *t)
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		gtime = t->gtime;
-		if (vtime->state == VTIME_SYS && t->flags & PF_VCPU)
+		if (vtime->state == VTIME_GUEST)
 			gtime += vtime->gtime + vtime_delta(vtime);
 
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
@@ -877,20 +895,230 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		*utime = t->utime;
 		*stime = t->stime;
 
-		/* Task is sleeping, nothing to add */
-		if (vtime->state == VTIME_INACTIVE || is_idle_task(t))
+		/* Task is sleeping or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
 			continue;
 
 		delta = vtime_delta(vtime);
 
 		/*
-		 * Task runs either in user or kernel space, add pending nohz time to
-		 * the right place.
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
 		 */
-		if (vtime->state == VTIME_USER || t->flags & PF_VCPU)
-			*utime += vtime->utime + delta;
-		else if (vtime->state == VTIME_SYS)
+		if (vtime->state == VTIME_SYS)
 			*stime += vtime->stime + delta;
+		else
+			*utime += vtime->utime + delta;
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+}
+
+static int vtime_state_check(struct vtime *vtime, int cpu)
+{
+	/*
+	 * We raced against a context switch, fetch the
+	 * kcpustat task again.
+	 */
+	if (vtime->cpu != cpu && vtime->cpu != -1)
+		return -EAGAIN;
+
+	/*
+	 * Two possible things here:
+	 * 1) We are seeing the scheduling out task (prev) or any past one.
+	 * 2) We are seeing the scheduling in task (next) but it hasn't
+	 *    passed though vtime_task_switch() yet so the pending
+	 *    cputime of the prev task may not be flushed yet.
+	 *
+	 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
+	 */
+	if (vtime->state == VTIME_INACTIVE)
+		return -EAGAIN;
+
+	return 0;
+}
+
+static u64 kcpustat_user_vtime(struct vtime *vtime)
+{
+	if (vtime->state == VTIME_USER)
+		return vtime->utime + vtime_delta(vtime);
+	else if (vtime->state == VTIME_GUEST)
+		return vtime->gtime + vtime_delta(vtime);
+	return 0;
+}
+
+static int kcpustat_field_vtime(u64 *cpustat,
+				struct task_struct *tsk,
+				enum cpu_usage_stat usage,
+				int cpu, u64 *val)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+	int err;
+
+	do {
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
+
+		*val = cpustat[usage];
+
+		/*
+		 * Nice VS unnice cputime accounting may be inaccurate if
+		 * the nice value has changed since the last vtime update.
+		 * But proper fix would involve interrupting target on nice
+		 * updates which is a no go on nohz_full (although the scheduler
+		 * may still interrupt the target if rescheduling is needed...)
+		 */
+		switch (usage) {
+		case CPUTIME_SYSTEM:
+			if (vtime->state == VTIME_SYS)
+				*val += vtime->stime + vtime_delta(vtime);
+			break;
+		case CPUTIME_USER:
+			if (task_nice(tsk) <= 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_NICE:
+			if (task_nice(tsk) > 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_GUEST:
+			if (vtime->state == VTIME_GUEST && task_nice(tsk) <= 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		case CPUTIME_GUEST_NICE:
+			if (vtime->state == VTIME_GUEST && task_nice(tsk) > 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		default:
+			break;
+		}
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return 0;
+}
+
+u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+		   enum cpu_usage_stat usage, int cpu)
+{
+	u64 *cpustat = kcpustat->cpustat;
+	struct rq *rq;
+	u64 val;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu))
+		return cpustat[usage];
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			return cpustat[usage];
+		}
+
+		err = kcpustat_field_vtime(cpustat, curr, usage, cpu, &val);
+		rcu_read_unlock();
+
+		if (!err)
+			return val;
+
+		cpu_relax();
+	}
+}
+EXPORT_SYMBOL_GPL(kcpustat_field);
+
+static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
+				    const struct kernel_cpustat *src,
+				    struct task_struct *tsk, int cpu)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+	int err;
+
+	do {
+		u64 *cpustat;
+		u64 delta;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
+
+		*dst = *src;
+		cpustat = dst->cpustat;
+
+		/* Task is sleeping, dead or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
+			continue;
+
+		delta = vtime_delta(vtime);
+
+		/*
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
+		 */
+		if (vtime->state == VTIME_SYS) {
+			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
+		} else if (vtime->state == VTIME_USER) {
+			if (task_nice(tsk) > 0)
+				cpustat[CPUTIME_NICE] += vtime->utime + delta;
+			else
+				cpustat[CPUTIME_USER] += vtime->utime + delta;
+		} else {
+			WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+			if (task_nice(tsk) > 0) {
+				cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
+				cpustat[CPUTIME_NICE] += vtime->gtime + delta;
+			} else {
+				cpustat[CPUTIME_GUEST] += vtime->gtime + delta;
+				cpustat[CPUTIME_USER] += vtime->gtime + delta;
+			}
+		}
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return err;
+}
+
+void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
+{
+	const struct kernel_cpustat *src = &kcpustat_cpu(cpu);
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu)) {
+		*dst = *src;
+		return;
+	}
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			*dst = *src;
+			return;
+		}
+
+		err = kcpustat_cpu_fetch_vtime(dst, src, curr, cpu);
+		rcu_read_unlock();
+
+		if (!err)
+			return;
+
+		cpu_relax();
+	}
 }
+EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */