sched/cputime: Correctly support generic vtime idle time

Currently whether generic vtime is running or not, the idle cputime is
fetched from the nohz accounting.

However generic vtime already does its own idle cputime accounting. Only
the kernel stat accessors are not plugged to support it.

Read the idle generic vtime cputime when it's running, this will allow to
later more clearly split nohz and vtime cputime accounting.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Link: https://patch.msgid.link/20260508131647.43868-5-frederic@kernel.org

2 files changed, 38 insertions, 12 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index caaaf0a04ced..815d0f772cae 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -773,9 +773,9 @@ 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)
@@ -784,7 +784,7 @@ 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;
@@ -926,6 +926,7 @@ 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 {
@@ -967,6 +968,14 @@ 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;
 		}
@@ -1029,8 +1038,8 @@ 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);
@@ -1039,15 +1048,17 @@ 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;
@@ -1055,6 +1066,15 @@ 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));
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 171393367b5c..597c3a0682e7 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -783,9 +783,10 @@ static void tick_nohz_start_idle(struct tick_sched *ts)
 	sched_clock_idle_sleep_event();
 }
 
-static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
+static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx, ktime_t *sleeptime,
 				 bool compute_delta, u64 *last_update_time)
 {
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t now, idle;
 	unsigned int seq;
 
@@ -796,6 +797,11 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
 	if (last_update_time)
 		*last_update_time = ktime_to_us(now);
 
+	if (vtime_generic_enabled_cpu(cpu)) {
+		idle = kcpustat_field(idx, cpu);
+		return ktime_to_us(idle);
+	}
+
 	do {
 		ktime_t delta = 0;
 
@@ -834,7 +840,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
-	return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime,
+	return get_cpu_sleep_time_us(cpu, CPUTIME_IDLE, &ts->idle_sleeptime,
 				     !nr_iowait_cpu(cpu), last_update_time);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
@@ -860,7 +866,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
-	return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime,
+	return get_cpu_sleep_time_us(cpu, CPUTIME_IOWAIT, &ts->iowait_sleeptime,
 				     nr_iowait_cpu(cpu), last_update_time);
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);