1 files changed, 291 insertions, 82 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 6dab4854c6c0..06bddaa738e5 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -2,6 +2,10 @@
 /*
  * Simple CPU accounting cgroup controller
  */
+#include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
+#include <linux/tsacct_kern.h>
+#include "sched.h"
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
  #include <asm/cputime.h>
@@ -9,6 +13,8 @@
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
+DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
+
 /*
  * There are no locks covering percpu hardirq/softirq time.
  * They are only modified in vtime_account, on corresponding CPU
@@ -22,16 +28,15 @@
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
-int sched_clock_irqtime;
-
 void enable_sched_clock_irqtime(void)
 {
-	sched_clock_irqtime = 1;
+	static_branch_enable(&sched_clock_irqtime);
 }
 
 void disable_sched_clock_irqtime(void)
 {
-	sched_clock_irqtime = 0;
+	if (irqtime_enabled())
+		static_branch_disable(&sched_clock_irqtime);
 }
 
 static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
@@ -42,7 +47,8 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
 	u64_stats_update_begin(&irqtime->sync);
 	cpustat[idx] += delta;
 	irqtime->total += delta;
-	irqtime->tick_delta += delta;
+	if (!kcpustat_idle_dyntick())
+		irqtime->tick_delta += delta;
 	u64_stats_update_end(&irqtime->sync);
 }
 
@@ -88,7 +94,7 @@ static u64 irqtime_tick_accounted(u64 maxtime)
 	return delta;
 }
 
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+#else /* !CONFIG_IRQ_TIME_ACCOUNTING: */
 
 static u64 irqtime_tick_accounted(u64 dummy)
 {
@@ -241,13 +247,26 @@ void __account_forceidle_time(struct task_struct *p, u64 delta)
 
 	task_group_account_field(p, CPUTIME_FORCEIDLE, delta);
 }
-#endif
+#endif /* CONFIG_SCHED_CORE */
 
 /*
  * When a guest is interrupted for a longer amount of time, missed clock
  * ticks are not redelivered later. Due to that, this function may on
  * occasion account more time than the calling functions think elapsed.
  */
+#ifdef CONFIG_PARAVIRT
+struct static_key paravirt_steal_enabled;
+
+#ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+#endif
+#endif
+
 static __always_inline u64 steal_account_process_time(u64 maxtime)
 {
 #ifdef CONFIG_PARAVIRT
@@ -262,7 +281,7 @@ static __always_inline u64 steal_account_process_time(u64 maxtime)
 
 		return steal;
 	}
-#endif
+#endif /* CONFIG_PARAVIRT */
 	return 0;
 }
 
@@ -288,7 +307,7 @@ static inline u64 read_sum_exec_runtime(struct task_struct *t)
 {
 	return t->se.sum_exec_runtime;
 }
-#else
+#else /* !CONFIG_64BIT: */
 static u64 read_sum_exec_runtime(struct task_struct *t)
 {
 	u64 ns;
@@ -301,7 +320,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
 
 	return ns;
 }
-#endif
+#endif /* !CONFIG_64BIT */
 
 /*
  * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
@@ -310,10 +329,8 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct signal_struct *sig = tsk->signal;
-	u64 utime, stime;
 	struct task_struct *t;
-	unsigned int seq, nextseq;
-	unsigned long flags;
+	u64 utime, stime;
 
 	/*
 	 * Update current task runtime to account pending time since last
@@ -326,27 +343,19 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	if (same_thread_group(current, tsk))
 		(void) task_sched_runtime(current);
 
-	rcu_read_lock();
-	/* Attempt a lockless read on the first round. */
-	nextseq = 0;
-	do {
-		seq = nextseq;
-		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+	guard(rcu)();
+	scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) {
 		times->utime = sig->utime;
 		times->stime = sig->stime;
 		times->sum_exec_runtime = sig->sum_sched_runtime;
 
-		for_each_thread(tsk, t) {
+		__for_each_thread(sig, t) {
 			task_cputime(t, &utime, &stime);
 			times->utime += utime;
 			times->stime += stime;
 			times->sum_exec_runtime += read_sum_exec_runtime(t);
 		}
-		/* If lockless access failed, take the lock. */
-		nextseq = 1;
-	} while (need_seqretry(&sig->stats_lock, seq));
-	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
-	rcu_read_unlock();
+	}
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -407,15 +416,218 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	}
 }
 
-static void irqtime_account_idle_ticks(int ticks)
-{
-	irqtime_account_process_tick(current, 0, ticks);
-}
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static inline void irqtime_account_idle_ticks(int ticks) { }
+#else /* !CONFIG_IRQ_TIME_ACCOUNTING: */
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 						int nr_ticks) { }
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
+
+#if defined(CONFIG_NO_HZ_COMMON) && !defined(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE)
+static void kcpustat_idle_stop(struct kernel_cpustat *kc, u64 now)
+{
+	u64 *cpustat = kc->cpustat;
+	u64 delta, steal, steal_delta;
+	int iowait;
+
+	if (!kc->idle_elapse)
+		return;
+
+	iowait = nr_iowait_cpu(smp_processor_id()) > 0;
+	delta = now - kc->idle_entrytime;
+	steal = steal_account_process_time(delta);
+
+	/*
+	 * Record the idle time after substracting the steal time from
+	 * previous update sequence. Don't substract the steal time from
+	 * the current update sequence to avoid readers moving backward.
+	 */
+	write_seqcount_begin(&kc->idle_sleeptime_seq);
+	steal_delta = min_t(u64, kc->idle_stealtime[iowait], delta);
+	delta -= steal_delta;
+	kc->idle_stealtime[iowait] -= steal_delta;
+
+	if (iowait)
+		cpustat[CPUTIME_IOWAIT] += delta;
+	else
+		cpustat[CPUTIME_IDLE] += delta;
+
+	kc->idle_stealtime[iowait] += steal;
+	kc->idle_entrytime = now;
+	kc->idle_elapse = false;
+	write_seqcount_end(&kc->idle_sleeptime_seq);
+}
+
+static void kcpustat_idle_start(struct kernel_cpustat *kc, u64 now)
+{
+	/* Irqtime accounting might have been enabled in the middle of the IRQ */
+	if (kc->idle_elapse)
+		return;
+
+	write_seqcount_begin(&kc->idle_sleeptime_seq);
+	kc->idle_entrytime = now;
+	kc->idle_elapse = true;
+	write_seqcount_end(&kc->idle_sleeptime_seq);
+}
+
+void kcpustat_dyntick_stop(u64 now)
+{
+	struct kernel_cpustat *kc = kcpustat_this_cpu;
+
+	if (!vtime_generic_enabled_this_cpu()) {
+		WARN_ON_ONCE(!kc->idle_dyntick);
+		kcpustat_idle_stop(kc, now);
+		kc->idle_dyntick = false;
+		vtime_dyntick_stop();
+	}
+}
+
+void kcpustat_dyntick_start(u64 now)
+{
+	struct kernel_cpustat *kc = kcpustat_this_cpu;
+
+	if (!vtime_generic_enabled_this_cpu()) {
+		vtime_dyntick_start();
+		kc->idle_dyntick = true;
+		kcpustat_idle_start(kc, now);
+	}
+}
+
+void kcpustat_irq_enter(u64 now)
+{
+	struct kernel_cpustat *kc = kcpustat_this_cpu;
+
+	if (!vtime_generic_enabled_this_cpu() &&
+	    (irqtime_enabled() || vtime_accounting_enabled_this_cpu()))
+		kcpustat_idle_stop(kc, now);
+}
+
+void kcpustat_irq_exit(u64 now)
+{
+	struct kernel_cpustat *kc = kcpustat_this_cpu;
+
+	/*
+	 * Generic vtime already does its own idle accounting.
+	 * But irqtime accounting or arch vtime which also accounts IRQs
+	 * need to pause nohz accounting. Resume nohz accounting as long
+	 * as the irqtime config is enabled to handle case where irqtime
+	 * accounting got runtime disabled in the middle of an IRQ.
+	 */
+	if (!vtime_generic_enabled_this_cpu() &&
+	    (IS_ENABLED(CONFIG_IRQ_TIME_ACCOUNTING) || vtime_accounting_enabled_this_cpu()))
+		kcpustat_idle_start(kc, now);
+}
+
+static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx,
+				  bool compute_delta, u64 now)
+{
+	struct kernel_cpustat *kc = &kcpustat_cpu(cpu);
+	int iowait = idx == CPUTIME_IOWAIT;
+	u64 *cpustat = kc->cpustat;
+	unsigned int seq;
+	u64 idle;
+
+	do {
+		seq = read_seqcount_begin(&kc->idle_sleeptime_seq);
+
+		idle = cpustat[idx];
+
+		if (kc->idle_elapse && compute_delta && now > kc->idle_entrytime) {
+			u64 delta = now - kc->idle_entrytime;
+
+			delta -= min_t(u64, kc->idle_stealtime[iowait], delta);
+			idle += delta;
+		}
+	} while (read_seqcount_retry(&kc->idle_sleeptime_seq, seq));
+
+	return idle;
+}
+
+u64 kcpustat_field_idle(int cpu)
+{
+	return kcpustat_field_dyntick(cpu, CPUTIME_IDLE,
+				      !nr_iowait_cpu(cpu), ktime_get());
+}
+EXPORT_SYMBOL_GPL(kcpustat_field_idle);
+
+u64 kcpustat_field_iowait(int cpu)
+{
+	return kcpustat_field_dyntick(cpu, CPUTIME_IOWAIT,
+				      nr_iowait_cpu(cpu), ktime_get());
+}
+EXPORT_SYMBOL_GPL(kcpustat_field_iowait);
+#else
+static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx,
+				  bool compute_delta, ktime_t now)
+{
+	return kcpustat_cpu(cpu).cpustat[idx];
+}
+#endif /* CONFIG_NO_HZ_COMMON && !CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE */
+
+static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx,
+				 bool compute_delta, u64 *last_update_time)
+{
+	ktime_t now = ktime_get();
+	u64 res;
+
+	if (vtime_generic_enabled_cpu(cpu))
+		res = kcpustat_field(idx, cpu);
+	else
+		res = kcpustat_field_dyntick(cpu, idx, compute_delta, now);
+
+	do_div(res, NSEC_PER_USEC);
+
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
+
+	return res;
+}
+
+/**
+ * get_cpu_idle_time_us - get the total idle time of a CPU
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
+ *
+ * Return the cumulative idle time (since boot) for a given
+ * CPU, in microseconds. Note that this is partially broken due to
+ * the counter of iowait tasks that can be remotely updated without
+ * any synchronization. Therefore it is possible to observe backward
+ * values within two consecutive reads.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * Return: total idle time of the @cpu
+ */
+u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
+{
+	return get_cpu_sleep_time_us(cpu, CPUTIME_IDLE,
+				     !nr_iowait_cpu(cpu), last_update_time);
+}
+EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
+
+/**
+ * get_cpu_iowait_time_us - get the total iowait time of a CPU
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
+ *
+ * Return the cumulative iowait time (since boot) for a given
+ * CPU, in microseconds. Note this is partially broken due to
+ * the counter of iowait tasks that can be remotely updated without
+ * any synchronization. Therefore it is possible to observe backward
+ * values within two consecutive reads.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * Return: total iowait time of @cpu
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+	return get_cpu_sleep_time_us(cpu, CPUTIME_IOWAIT,
+				     nr_iowait_cpu(cpu), last_update_time);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
 /*
  * Use precise platform statistics if available:
@@ -430,11 +642,15 @@ void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 		vtime_account_hardirq(tsk);
 	} else if (pc & SOFTIRQ_OFFSET) {
 		vtime_account_softirq(tsk);
-	} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
-		   is_idle_task(tsk)) {
-		vtime_account_idle(tsk);
+	} else if (!kcpustat_idle_dyntick()) {
+		if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
+		    is_idle_task(tsk)) {
+			vtime_account_idle(tsk);
+		} else {
+			vtime_account_kernel(tsk);
+		}
 	} else {
-		vtime_account_kernel(tsk);
+		vtime_reset();
 	}
 }
 
@@ -476,6 +692,9 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	if (vtime_accounting_enabled_this_cpu())
 		return;
 
+	if (kcpustat_idle_dyntick())
+		return;
+
 	if (irqtime_enabled()) {
 		irqtime_account_process_tick(p, user_tick, 1);
 		return;
@@ -498,29 +717,6 @@ void account_process_tick(struct task_struct *p, int user_tick)
 }
 
 /*
- * Account multiple ticks of idle time.
- * @ticks: number of stolen ticks
- */
-void account_idle_ticks(unsigned long ticks)
-{
-	u64 cputime, steal;
-
-	if (irqtime_enabled()) {
-		irqtime_account_idle_ticks(ticks);
-		return;
-	}
-
-	cputime = ticks * TICK_NSEC;
-	steal = steal_account_process_time(ULONG_MAX);
-
-	if (steal >= cputime)
-		return;
-
-	cputime -= steal;
-	account_idle_time(cputime);
-}
-
-/*
  * Adjust tick based cputime random precision against scheduler runtime
  * accounting.
  *
@@ -580,12 +776,6 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 	}
 
 	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
-	/*
-	 * Because mul_u64_u64_div_u64() can approximate on some
-	 * achitectures; enforce the constraint that: a*b/(b+c) <= a.
-	 */
-	if (unlikely(stime > rtime))
-		stime = rtime;
 
 update:
 	/*
@@ -766,9 +956,9 @@ void vtime_guest_exit(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
-void vtime_account_idle(struct task_struct *tsk)
+static void __vtime_account_idle(struct vtime *vtime)
 {
-	account_idle_time(get_vtime_delta(&tsk->vtime));
+	account_idle_time(get_vtime_delta(vtime));
 }
 
 void vtime_task_switch_generic(struct task_struct *prev)
@@ -777,7 +967,7 @@ void vtime_task_switch_generic(struct task_struct *prev)
 
 	write_seqcount_begin(&vtime->seqcount);
 	if (vtime->state == VTIME_IDLE)
-		vtime_account_idle(prev);
+		__vtime_account_idle(vtime);
 	else
 		__vtime_account_kernel(prev, vtime);
 	vtime->state = VTIME_INACTIVE;
@@ -919,6 +1109,7 @@ static int kcpustat_field_vtime(u64 *cpustat,
 				int cpu, u64 *val)
 {
 	struct vtime *vtime = &tsk->vtime;
+	struct rq *rq = cpu_rq(cpu);
 	unsigned int seq;
 
 	do {
@@ -960,6 +1151,14 @@ static int kcpustat_field_vtime(u64 *cpustat,
 			if (state == VTIME_GUEST && task_nice(tsk) > 0)
 				*val += vtime->gtime + vtime_delta(vtime);
 			break;
+		case CPUTIME_IDLE:
+			if (state == VTIME_IDLE && !atomic_read(&rq->nr_iowait))
+				*val += vtime_delta(vtime);
+			break;
+		case CPUTIME_IOWAIT:
+			if (state == VTIME_IDLE && atomic_read(&rq->nr_iowait) > 0)
+				*val += vtime_delta(vtime);
+			break;
 		default:
 			break;
 		}
@@ -968,16 +1167,15 @@ static int kcpustat_field_vtime(u64 *cpustat,
 	return 0;
 }
 
-u64 kcpustat_field(struct kernel_cpustat *kcpustat,
-		   enum cpu_usage_stat usage, int cpu)
+u64 kcpustat_field(enum cpu_usage_stat usage, int cpu)
 {
-	u64 *cpustat = kcpustat->cpustat;
+	u64 *cpustat = kcpustat_cpu(cpu).cpustat;
 	u64 val = cpustat[usage];
 	struct rq *rq;
 	int err;
 
-	if (!vtime_accounting_enabled_cpu(cpu))
-		return val;
+	if (!vtime_generic_enabled_cpu(cpu))
+		return kcpustat_field_default(usage, cpu);
 
 	rq = cpu_rq(cpu);
 
@@ -1023,8 +1221,8 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 		*dst = *src;
 		cpustat = dst->cpustat;
 
-		/* Task is sleeping, dead or idle, nothing to add */
-		if (state < VTIME_SYS)
+		/* Task is sleeping or dead, nothing to add */
+		if (state < VTIME_IDLE)
 			continue;
 
 		delta = vtime_delta(vtime);
@@ -1033,15 +1231,17 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 		 * Task runs either in user (including guest) or kernel space,
 		 * add pending nohz time to the right place.
 		 */
-		if (state == VTIME_SYS) {
+		switch (state) {
+		case VTIME_SYS:
 			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
-		} else if (state == VTIME_USER) {
+			break;
+		case VTIME_USER:
 			if (task_nice(tsk) > 0)
 				cpustat[CPUTIME_NICE] += vtime->utime + delta;
 			else
 				cpustat[CPUTIME_USER] += vtime->utime + delta;
-		} else {
-			WARN_ON_ONCE(state != VTIME_GUEST);
+			break;
+		case VTIME_GUEST:
 			if (task_nice(tsk) > 0) {
 				cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
 				cpustat[CPUTIME_NICE] += vtime->gtime + delta;
@@ -1049,6 +1249,15 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 				cpustat[CPUTIME_GUEST] += vtime->gtime + delta;
 				cpustat[CPUTIME_USER] += vtime->gtime + delta;
 			}
+			break;
+		case VTIME_IDLE:
+			if (atomic_read(&cpu_rq(cpu)->nr_iowait) > 0)
+				cpustat[CPUTIME_IOWAIT] += delta;
+			else
+				cpustat[CPUTIME_IDLE] += delta;
+			break;
+		default:
+			WARN_ON_ONCE(1);
 		}
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
 
@@ -1061,8 +1270,8 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 	struct rq *rq;
 	int err;
 
-	if (!vtime_accounting_enabled_cpu(cpu)) {
-		*dst = *src;
+	if (!vtime_generic_enabled_cpu(cpu)) {
+		kcpustat_cpu_fetch_default(dst, cpu);
 		return;
 	}
 
@@ -1075,7 +1284,7 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 		curr = rcu_dereference(rq->curr);
 		if (WARN_ON_ONCE(!curr)) {
 			rcu_read_unlock();
-			*dst = *src;
+			kcpustat_cpu_fetch_default(dst, cpu);
 			return;
 		}