tick/sched: Consolidate idle time fetching APIs

Fetching the idle cputime is available through a variety of accessors all
over the place depending on the different accounting flavours and needs:

  - idle vtime generic accounting can be accessed by kcpustat_field(),
    kcpustat_cpu_fetch(), get_idle/iowait_time() and
    get_cpu_idle/iowait_time_us()

  - dynticks-idle accounting can only be accessed by get_idle/iowait_time()
    or get_cpu_idle/iowait_time_us()

  - CONFIG_NO_HZ_COMMON=n idle accounting can be accessed by kcpustat_field()
    kcpustat_cpu_fetch(), or get_idle/iowait_time() but not by
    get_cpu_idle/iowait_time_us()

Moreover get_idle/iowait_time() relies on get_cpu_idle/iowait_time_us()
with a non-sensical conversion to microseconds and back to nanoseconds on
the way.

Start consolidating the APIs with removing get_idle/iowait_time() and make
kcpustat_field() and kcpustat_cpu_fetch() work for all cases.

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/20260508131647.43868-13-frederic@kernel.org

Author: Frederic Weisbecker

fs/proc/stat.c

@@ -22,38 +22,6 @@
 #define arch_irq_stat() 0
 #endif
 
-u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
-{
-	u64 idle, idle_usecs = -1ULL;
-
-	if (cpu_online(cpu))
-		idle_usecs = get_cpu_idle_time_us(cpu, NULL);
-
-	if (idle_usecs == -1ULL)
-		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
-		idle = kcs->cpustat[CPUTIME_IDLE];
-	else
-		idle = idle_usecs * NSEC_PER_USEC;
-
-	return idle;
-}
-
-static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
-{
-	u64 iowait, iowait_usecs = -1ULL;
-
-	if (cpu_online(cpu))
-		iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
-
-	if (iowait_usecs == -1ULL)
-		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
-		iowait = kcs->cpustat[CPUTIME_IOWAIT];
-	else
-		iowait = iowait_usecs * NSEC_PER_USEC;
-
-	return iowait;
-}
-
 static void show_irq_gap(struct seq_file *p, unsigned int gap)
 {
 	static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
@@ -105,8 +73,8 @@ static int show_stat(struct seq_file *p, void *v)
 		user		+= cpustat[CPUTIME_USER];
 		nice		+= cpustat[CPUTIME_NICE];
 		system		+= cpustat[CPUTIME_SYSTEM];
-		idle		+= get_idle_time(&kcpustat, i);
-		iowait		+= get_iowait_time(&kcpustat, i);
+		idle		+= cpustat[CPUTIME_IDLE];
+		iowait		+= cpustat[CPUTIME_IOWAIT];
 		irq		+= cpustat[CPUTIME_IRQ];
 		softirq		+= cpustat[CPUTIME_SOFTIRQ];
 		steal		+= cpustat[CPUTIME_STEAL];
@@ -146,8 +114,8 @@ static int show_stat(struct seq_file *p, void *v)
 		user		= cpustat[CPUTIME_USER];
 		nice		= cpustat[CPUTIME_NICE];
 		system		= cpustat[CPUTIME_SYSTEM];
-		idle		= get_idle_time(&kcpustat, i);
-		iowait		= get_iowait_time(&kcpustat, i);
+		idle		= cpustat[CPUTIME_IDLE];
+		iowait		= cpustat[CPUTIME_IOWAIT];
 		irq		= cpustat[CPUTIME_IRQ];
 		softirq		= cpustat[CPUTIME_SOFTIRQ];
 		steal		= cpustat[CPUTIME_STEAL];

fs/proc/uptime.c

@@ -18,12 +18,8 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 	int i;
 
 	idle_nsec = 0;
-	for_each_possible_cpu(i) {
-		struct kernel_cpustat kcs;
-
-		kcpustat_cpu_fetch(&kcs, i);
-		idle_nsec += get_idle_time(&kcs, i);
-	}
+	for_each_possible_cpu(i)
+		idle_nsec += kcpustat_field(CPUTIME_IDLE, i);
 
 	ktime_get_boottime_ts64(&uptime);
 	timens_add_boottime(&uptime);

include/linux/kernel_stat.h

@@ -110,32 +110,59 @@ extern void kcpustat_dyntick_start(u64 now);
 extern void kcpustat_dyntick_stop(u64 now);
 extern void kcpustat_irq_enter(u64 now);
 extern void kcpustat_irq_exit(u64 now);
+extern u64 kcpustat_field_idle(int cpu);
+extern u64 kcpustat_field_iowait(int cpu);
 
 static inline bool kcpustat_idle_dyntick(void)
 {
 	return __this_cpu_read(kernel_cpustat.idle_dyntick);
 }
 #else
+static inline u64 kcpustat_field_idle(int cpu)
+{
+	return kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
+}
+static inline u64 kcpustat_field_iowait(int cpu)
+{
+	return kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+}
+
 static inline bool kcpustat_idle_dyntick(void)
 {
 	return false;
 }
 #endif /* CONFIG_NO_HZ_COMMON */
 
+/* Fetch cputime values when vtime is disabled on a CPU */
+static inline u64 kcpustat_field_default(enum cpu_usage_stat usage, int cpu)
+{
+	if (usage == CPUTIME_IDLE)
+		return kcpustat_field_idle(cpu);
+	if (usage == CPUTIME_IOWAIT)
+		return kcpustat_field_iowait(cpu);
+	return kcpustat_cpu(cpu).cpustat[usage];
+}
+
+static inline void kcpustat_cpu_fetch_default(struct kernel_cpustat *dst, int cpu)
+{
+	*dst = kcpustat_cpu(cpu);
+	dst->cpustat[CPUTIME_IDLE] = kcpustat_field_idle(cpu);
+	dst->cpustat[CPUTIME_IOWAIT] = kcpustat_field_iowait(cpu);
+}
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern u64 kcpustat_field(enum cpu_usage_stat usage, int cpu);
 extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu);
 #else
 static inline u64 kcpustat_field(enum cpu_usage_stat usage, int cpu)
 {
-	return kcpustat_cpu(cpu).cpustat[usage];
+	return kcpustat_field_default(usage, cpu);
 }
 
 static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 {
-	*dst = kcpustat_cpu(cpu);
+	kcpustat_cpu_fetch_default(dst, cpu);
 }
-
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
 extern void account_user_time(struct task_struct *, u64);
@@ -145,7 +172,6 @@ extern void account_system_index_time(struct task_struct *, u64,
 				      enum cpu_usage_stat);
 extern void account_steal_time(u64);
 extern void account_idle_time(u64);
-extern u64 get_idle_time(struct kernel_cpustat *kcs, int cpu);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)

kernel/sched/cputime.c

@@ -490,24 +490,14 @@ void kcpustat_irq_exit(u64 now)
 		kcpustat_idle_start(kc, now);
 }
 
-static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx,
-				 bool compute_delta, u64 *last_update_time)
+static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx,
+				  bool compute_delta, u64 now)
 {
 	struct kernel_cpustat *kc = &kcpustat_cpu(cpu);
 	u64 *cpustat = kc->cpustat;
 	unsigned int seq;
-	ktime_t now;
 	u64 idle;
 
-	now = ktime_get();
-	if (last_update_time)
-		*last_update_time = ktime_to_us(now);
-
-	if (vtime_generic_enabled_cpu(cpu)) {
-		idle = kcpustat_field(idx, cpu);
-		goto to_us;
-	}
-
 	do {
 		seq = read_seqcount_begin(&kc->idle_sleeptime_seq);
 
@@ -516,12 +506,42 @@ static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx,
 			idle += (now - kc->idle_entrytime);
 	} while (read_seqcount_retry(&kc->idle_sleeptime_seq, seq));
 
-to_us:
-	do_div(idle, NSEC_PER_USEC);
-
 	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);
+
+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
@@ -569,7 +589,6 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 				     nr_iowait_cpu(cpu), last_update_time);
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
-
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
@@ -1123,8 +1142,8 @@ u64 kcpustat_field(enum cpu_usage_stat usage, int cpu)
 	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);
 
@@ -1219,8 +1238,8 @@ 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;
 	}
 
@@ -1233,7 +1252,7 @@ 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;
 		}