tick/sched: Unify idle cputime accounting

The non-vtime dynticks-idle cputime accounting is a big mess that
accumulates within two concurrent statistics, each having their own
shortcomings:

 * The accounting for online CPUs which is based on the delta between
   tick_nohz_start_idle() and tick_nohz_stop_idle().

   Pros:
       - Works when the tick is off

       - Has nsecs granularity

   Cons:
       - Account idle steal time but doesn't substract it from idle
         cputime.

       - Assumes CONFIG_IRQ_TIME_ACCOUNTING by not accounting IRQs but
         the IRQ time is simply ignored when
         CONFIG_IRQ_TIME_ACCOUNTING=n

       - The windows between 1) idle task scheduling and the first call
         to tick_nohz_start_idle() and 2) idle task between the last
         tick_nohz_stop_idle() and the rest of the idle time are
         blindspots wrt. cputime accounting (though mostly insignificant
         amount)

       - Relies on private fields outside of kernel stats, with specific
         accessors.

 * The accounting for offline CPUs which is based on ticks and the
   jiffies delta during which the tick was stopped.

   Pros:
       - Handles steal time correctly

       - Handle CONFIG_IRQ_TIME_ACCOUNTING=y and
         CONFIG_IRQ_TIME_ACCOUNTING=n correctly.

       - Handles the whole idle task

       - Accounts directly to kernel stats, without midlayer accumulator.

    Cons:
       - Doesn't elapse when the tick is off, which doesn't make it
         suitable for online CPUs.

       - Has TICK_NSEC granularity (jiffies)

       - Needs to track the dyntick-idle ticks that were accounted and
         substract them from the total jiffies time spent while the tick
         was stopped. This is an ugly workaround.

Having two different accounting for a single context is not the only
problem: since those accountings are of different natures, it is
possible to observe the global idle time going backward after a CPU goes
offline.

Clean up the situation with introducing a hybrid approach that stays
coherent and works for both online and offline CPUs:

  * Tick based or native vtime accounting operate before the idle loop
    is entered and resume once the idle loop prepares to exit.

  * When the idle loop starts, switch to dynticks-idle accounting as is
    done currently, except that the statistics accumulate directly to the
    relevant kernel stat fields.

  * Private dyntick cputime accounting fields are removed.

  * Works on both online and offline case.

Further improvement will include:

  * Only switch to dynticks-idle cputime accounting when the tick actually
    goes in dynticks mode.

  * Handle CONFIG_IRQ_TIME_ACCOUNTING=n correctly such that the
    dynticks-idle accounting still elapses while on IRQs.

  * Correctly substract idle steal cputime from idle time

Reported-by: Xin Zhao <jackzxcui1989@163.com>
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/20260508131647.43868-8-frederic@kernel.org

1 files changed, 30 insertions, 32 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 815d0f772cae..a5733789e0bd 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -414,16 +414,30 @@ 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) { }
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 						int nr_ticks) { }
 #endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
 
+#ifdef CONFIG_NO_HZ_COMMON
+void kcpustat_dyntick_start(void)
+{
+	if (!vtime_generic_enabled_this_cpu()) {
+		vtime_dyntick_start();
+		__this_cpu_write(kernel_cpustat.idle_dyntick, 1);
+	}
+}
+
+void kcpustat_dyntick_stop(void)
+{
+	if (!vtime_generic_enabled_this_cpu()) {
+		__this_cpu_write(kernel_cpustat.idle_dyntick, 0);
+		vtime_dyntick_stop();
+		steal_account_process_time(ULONG_MAX);
+	}
+}
+#endif /* CONFIG_NO_HZ_COMMON */
+
 /*
  * Use precise platform statistics if available:
  */
@@ -437,11 +451,15 @@ 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();
 	}
 }
 
@@ -483,6 +501,9 @@ 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;
@@ -505,29 +526,6 @@ 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.
  *