1 files changed, 377 insertions, 185 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 14d2dbf97c53..4f97896887ec 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1,12 +1,15 @@
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/tsacct_kern.h>
-#include <linux/kernel_stat.h>
-#include <linux/static_key.h>
-#include <linux/context_tracking.h>
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Simple CPU accounting cgroup controller
+ */
 #include <linux/sched/cputime.h>
+#include <linux/tsacct_kern.h>
 #include "sched.h"
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ #include <asm/cputime.h>
+#endif
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
 /*
@@ -14,15 +17,15 @@
  * They are only modified in vtime_account, on corresponding CPU
  * with interrupts disabled. So, writes are safe.
  * They are read and saved off onto struct rq in update_rq_clock().
- * This may result in other CPU reading this CPU's irq time and can
+ * This may result in other CPU reading this CPU's IRQ time and can
  * race with irq/vtime_account on this CPU. We would either get old
- * or new value with a side effect of accounting a slice of irq time to wrong
- * task when irq is in progress while we read rq->clock. That is a worthy
- * compromise in place of having locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of IRQ time to wrong
+ * task when IRQ is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each IRQ in account_system_time.
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
-static int sched_clock_irqtime;
+int sched_clock_irqtime;
 
 void enable_sched_clock_irqtime(void)
 {
@@ -47,21 +50,23 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
 }
 
 /*
- * Called before incrementing preempt_count on {soft,}irq_enter
+ * Called after incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void irqtime_account_irq(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
 {
 	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+	unsigned int pc;
 	s64 delta;
 	int cpu;
 
-	if (!sched_clock_irqtime)
+	if (!irqtime_enabled())
 		return;
 
 	cpu = smp_processor_id();
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
+	pc = irq_count() - offset;
 
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
@@ -69,12 +74,11 @@ void irqtime_account_irq(struct task_struct *curr)
 	 * in that case, so as not to confuse scheduler with a special task
 	 * that do not consume any time, but still wants to run.
 	 */
-	if (hardirq_count())
+	if (pc & HARDIRQ_MASK)
 		irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
-	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+	else if ((pc & SOFTIRQ_OFFSET) && curr != this_cpu_ksoftirqd())
 		irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
 }
-EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
 static u64 irqtime_tick_accounted(u64 maxtime)
 {
@@ -87,9 +91,7 @@ static u64 irqtime_tick_accounted(u64 maxtime)
 	return delta;
 }
 
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#define sched_clock_irqtime	(0)
+#else /* !CONFIG_IRQ_TIME_ACCOUNTING: */
 
 static u64 irqtime_tick_accounted(u64 dummy)
 {
@@ -109,13 +111,13 @@ static inline void task_group_account_field(struct task_struct *p, int index,
 	 */
 	__this_cpu_add(kernel_cpustat.cpustat[index], tmp);
 
-	cpuacct_account_field(p, index, tmp);
+	cgroup_account_cputime_field(p, index, tmp);
 }
 
 /*
- * Account user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
+ * Account user CPU time to a process.
+ * @p: the process that the CPU time gets accounted to
+ * @cputime: the CPU time spent in user space since the last update
  */
 void account_user_time(struct task_struct *p, u64 cputime)
 {
@@ -135,9 +137,9 @@ void account_user_time(struct task_struct *p, u64 cputime)
 }
 
 /*
- * Account guest cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in virtual machine since the last update
+ * Account guest CPU time to a process.
+ * @p: the process that the CPU time gets accounted to
+ * @cputime: the CPU time spent in virtual machine since the last update
  */
 void account_guest_time(struct task_struct *p, u64 cputime)
 {
@@ -150,18 +152,18 @@ void account_guest_time(struct task_struct *p, u64 cputime)
 
 	/* Add guest time to cpustat. */
 	if (task_nice(p) > 0) {
-		cpustat[CPUTIME_NICE] += cputime;
+		task_group_account_field(p, CPUTIME_NICE, cputime);
 		cpustat[CPUTIME_GUEST_NICE] += cputime;
 	} else {
-		cpustat[CPUTIME_USER] += cputime;
+		task_group_account_field(p, CPUTIME_USER, cputime);
 		cpustat[CPUTIME_GUEST] += cputime;
 	}
 }
 
 /*
- * Account system cpu time to a process and desired cpustat field
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in kernel space since the last update
+ * Account system CPU time to a process and desired cpustat field
+ * @p: the process that the CPU time gets accounted to
+ * @cputime: the CPU time spent in kernel space since the last update
  * @index: pointer to cpustat field that has to be updated
  */
 void account_system_index_time(struct task_struct *p,
@@ -179,10 +181,10 @@ void account_system_index_time(struct task_struct *p,
 }
 
 /*
- * Account system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
+ * Account system CPU time to a process.
+ * @p: the process that the CPU time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime: the CPU time spent in kernel space since the last update
  */
 void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime)
 {
@@ -205,7 +207,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime)
 
 /*
  * Account for involuntary wait time.
- * @cputime: the cpu time spent in involuntary wait
+ * @cputime: the CPU time spent in involuntary wait
  */
 void account_steal_time(u64 cputime)
 {
@@ -216,7 +218,7 @@ void account_steal_time(u64 cputime)
 
 /*
  * Account for idle time.
- * @cputime: the cpu time spent in idle wait
+ * @cputime: the CPU time spent in idle wait
  */
 void account_idle_time(u64 cputime)
 {
@@ -229,6 +231,21 @@ void account_idle_time(u64 cputime)
 		cpustat[CPUTIME_IDLE] += cputime;
 }
 
+
+#ifdef CONFIG_SCHED_CORE
+/*
+ * Account for forceidle time due to core scheduling.
+ *
+ * REQUIRES: schedstat is enabled.
+ */
+void __account_forceidle_time(struct task_struct *p, u64 delta)
+{
+	__schedstat_add(p->stats.core_forceidle_sum, delta);
+
+	task_group_account_field(p, CPUTIME_FORCEIDLE, delta);
+}
+#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
@@ -248,19 +265,18 @@ static __always_inline u64 steal_account_process_time(u64 maxtime)
 
 		return steal;
 	}
-#endif
+#endif /* CONFIG_PARAVIRT */
 	return 0;
 }
 
 /*
- * Account how much elapsed time was spent in steal, irq, or softirq time.
+ * Account how much elapsed time was spent in steal, IRQ, or softirq time.
  */
 static inline u64 account_other_time(u64 max)
 {
 	u64 accounted;
 
-	/* Shall be converted to a lockdep-enabled lightweight check */
-	WARN_ON_ONCE(!irqs_disabled());
+	lockdep_assert_irqs_disabled();
 
 	accounted = steal_account_process_time(max);
 
@@ -275,7 +291,7 @@ 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;
@@ -288,7 +304,7 @@ 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
@@ -297,10 +313,8 @@ 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
@@ -313,33 +327,25 @@ 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
 /*
  * Account a tick to a process and cpustat
- * @p: the process that the cpu time gets accounted to
+ * @p: the process that the CPU time gets accounted to
  * @user_tick: is the tick from userspace
  * @rq: the pointer to rq
  *
@@ -355,17 +361,17 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
  * Check for hardirq is done both for system and user time as there is
  * no timer going off while we are on hardirq and hence we may never get an
  * opportunity to update it solely in system time.
- * p->stime and friends are only updated on system time and not on irq
+ * p->stime and friends are only updated on system time and not on IRQ
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-					 struct rq *rq, int ticks)
+					 int ticks)
 {
 	u64 other, cputime = TICK_NSEC * ticks;
 
 	/*
 	 * When returning from idle, many ticks can get accounted at
-	 * once, including some ticks of steal, irq, and softirq time.
+	 * once, including some ticks of steal, IRQ, and softirq time.
 	 * Subtract those ticks from the amount of time accounted to
 	 * idle, or potentially user or system time. Due to rounding,
 	 * other time can exceed ticks occasionally.
@@ -385,7 +391,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
 		account_user_time(p, cputime);
-	} else if (p == rq->idle) {
+	} else if (p == this_rq()->idle) {
 		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
 		account_guest_time(p, cputime);
@@ -396,56 +402,41 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	struct rq *rq = this_rq();
-
-	irqtime_account_process_tick(current, 0, rq, 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_idle_ticks(int ticks) { }
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq, int nr_ticks) {}
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+						int nr_ticks) { }
+#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
  * 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_account_irq(struct task_struct *tsk, unsigned int offset)
 {
-	if (is_idle_task(prev))
-		vtime_account_idle(prev);
-	else
-		vtime_account_system(prev);
-
-	vtime_flush(prev);
-	arch_vtime_task_switch(prev);
+	unsigned int pc = irq_count() - offset;
+
+	if (pc & HARDIRQ_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 {
+		vtime_account_kernel(tsk);
+	}
 }
-#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
- * 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().
- */
-#ifndef __ARCH_HAS_VTIME_ACCOUNT
-void vtime_account_irq_enter(struct task_struct *tsk)
+void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
+		    u64 *ut, u64 *st)
 {
-	if (!in_interrupt() && is_idle_task(tsk))
-		vtime_account_idle(tsk);
-	else
-		vtime_account_system(tsk);
+	*ut = curr->utime;
+	*st = curr->stime;
 }
-EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
-#endif /* __ARCH_HAS_VTIME_ACCOUNT */
 
 void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
@@ -463,22 +454,23 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 	*ut = cputime.utime;
 	*st = cputime.stime;
 }
-#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE: */
+
 /*
- * Account a single tick of cpu time.
- * @p: the process that the cpu time gets accounted to
+ * Account a single tick of CPU time.
+ * @p: the process that the CPU time gets accounted to
  * @user_tick: indicates if the tick is a user or a system tick
  */
 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) {
-		irqtime_account_process_tick(p, user_tick, rq, 1);
+	if (irqtime_enabled()) {
+		irqtime_account_process_tick(p, user_tick, 1);
 		return;
 	}
 
@@ -492,7 +484,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (user_tick)
 		account_user_time(p, cputime);
-	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+	else if ((p != this_rq()->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, cputime);
 	else
 		account_idle_time(cputime);
@@ -506,7 +498,7 @@ void account_idle_ticks(unsigned long ticks)
 {
 	u64 cputime, steal;
 
-	if (sched_clock_irqtime) {
+	if (irqtime_enabled()) {
 		irqtime_account_idle_ticks(ticks);
 		return;
 	}
@@ -522,50 +514,6 @@ void account_idle_ticks(unsigned long ticks)
 }
 
 /*
- * Perform (stime * rtime) / total, but avoid multiplication overflow by
- * loosing precision when the numbers are big.
- */
-static u64 scale_stime(u64 stime, u64 rtime, u64 total)
-{
-	u64 scaled;
-
-	for (;;) {
-		/* Make sure "rtime" is the bigger of stime/rtime */
-		if (stime > rtime)
-			swap(rtime, stime);
-
-		/* Make sure 'total' fits in 32 bits */
-		if (total >> 32)
-			goto drop_precision;
-
-		/* Does rtime (and thus stime) fit in 32 bits? */
-		if (!(rtime >> 32))
-			break;
-
-		/* Can we just balance rtime/stime rather than dropping bits? */
-		if (stime >> 31)
-			goto drop_precision;
-
-		/* We can grow stime and shrink rtime and try to make them both fit */
-		stime <<= 1;
-		rtime >>= 1;
-		continue;
-
-drop_precision:
-		/* We drop from rtime, it has more bits than stime */
-		rtime >>= 1;
-		total >>= 1;
-	}
-
-	/*
-	 * Make sure gcc understands that this is a 32x32->64 multiply,
-	 * followed by a 64/32->64 divide.
-	 */
-	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
-	return scaled;
-}
-
-/*
  * Adjust tick based cputime random precision against scheduler runtime
  * accounting.
  *
@@ -585,9 +533,8 @@ drop_precision:
  *
  * Assuming that rtime_i+1 >= rtime_i.
  */
-static void cputime_adjust(struct task_cputime *curr,
-			   struct prev_cputime *prev,
-			   u64 *ut, u64 *st)
+void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
+		    u64 *ut, u64 *st)
 {
 	u64 rtime, stime, utime;
 	unsigned long flags;
@@ -612,7 +559,7 @@ static void cputime_adjust(struct task_cputime *curr,
 
 	/*
 	 * If either stime or utime are 0, assume all runtime is userspace.
-	 * Once a task gets some ticks, the monotonicy code at 'update:'
+	 * Once a task gets some ticks, the monotonicity code at 'update:'
 	 * will ensure things converge to the observed ratio.
 	 */
 	if (stime == 0) {
@@ -625,7 +572,13 @@ static void cputime_adjust(struct task_cputime *curr,
 		goto update;
 	}
 
-	stime = scale_stime(stime, rtime, stime + utime);
+	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:
 	/*
@@ -664,7 +617,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
-	task_cputime(p, &cputime.utime, &cputime.stime);
+	if (task_cputime(p, &cputime.utime, &cputime.stime))
+		cputime.sum_exec_runtime = task_sched_runtime(p);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -709,8 +663,8 @@ 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) {
@@ -729,7 +683,17 @@ 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;
 
@@ -737,11 +701,7 @@ void vtime_account_system(struct task_struct *tsk)
 		return;
 
 	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);
+	__vtime_account_kernel(tsk, vtime);
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -750,7 +710,7 @@ 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);
 }
@@ -780,8 +740,9 @@ 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);
-	current->flags |= PF_VCPU;
+	vtime_account_system(tsk, vtime);
+	tsk->flags |= PF_VCPU;
+	vtime->state = VTIME_GUEST;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -792,7 +753,8 @@ void vtime_guest_exit(struct task_struct *tsk)
 
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
-	current->flags &= ~PF_VCPU;
+	tsk->flags &= ~PF_VCPU;
+	vtime->state = VTIME_SYS;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
@@ -802,19 +764,30 @@ 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);
 }
 
@@ -825,8 +798,9 @@ 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);
 }
@@ -844,7 +818,7 @@ 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));
@@ -857,38 +831,256 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
 	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 delta;
+	int ret;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
 		*stime = t->stime;
-		return;
+		return false;
 	}
 
 	do {
+		ret = false;
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*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;
 
+		ret = true;
 		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));
+
+	return ret;
+}
+
+static int vtime_state_fetch(struct vtime *vtime, int cpu)
+{
+	int state = READ_ONCE(vtime->state);
+
+	/*
+	 * 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 (state == VTIME_INACTIVE)
+		return -EAGAIN;
+
+	return state;
+}
+
+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;
+
+	do {
+		int state;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
+
+		*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 (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 (state == VTIME_GUEST && task_nice(tsk) <= 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		case CPUTIME_GUEST_NICE:
+			if (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;
+	u64 val = cpustat[usage];
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu))
+		return val;
+
+	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;
+
+	do {
+		u64 *cpustat;
+		u64 delta;
+		int state;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
+
+		*dst = *src;
+		cpustat = dst->cpustat;
+
+		/* Task is sleeping, dead or idle, nothing to add */
+		if (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 (state == VTIME_SYS) {
+			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
+		} else if (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(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 0;
+}
+
+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 */