irqtime: Move irqtime entry accounting after irq offset incrementation

IRQ time entry is currently accounted before HARDIRQ_OFFSET or
SOFTIRQ_OFFSET are incremented. This is convenient to decide to which
index the cputime to account is dispatched.

Unfortunately it prevents tick_irq_enter() from being called under
HARDIRQ_OFFSET because tick_irq_enter() has to be called before the IRQ
entry accounting due to the necessary clock catch up. As a result we
don't benefit from appropriate lockdep coverage on tick_irq_enter().

To prepare for fixing this, move the IRQ entry cputime accounting after
the preempt offset is incremented. This requires the cputime dispatch
code to handle the extra offset.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201202115732.27827-5-frederic@kernel.org

2 files changed, 14 insertions, 10 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 02163d4260d7..5f611658eeab 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -44,12 +44,13 @@ 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;
 
@@ -59,6 +60,7 @@ void irqtime_account_irq(struct task_struct *curr)
 	cpu = smp_processor_id();
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
+	pc = preempt_count() - offset;
 
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
@@ -66,9 +68,9 @@ 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);
 }
 
@@ -417,11 +419,13 @@ void vtime_task_switch(struct task_struct *prev)
 }
 # endif
 
-void vtime_account_irq(struct task_struct *tsk)
+void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 {
-	if (hardirq_count()) {
+	unsigned int pc = preempt_count() - offset;
+
+	if (pc & HARDIRQ_OFFSET) {
 		vtime_account_hardirq(tsk);
-	} else if (in_serving_softirq()) {
+	} else if (pc & SOFTIRQ_OFFSET) {
 		vtime_account_softirq(tsk);
 	} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
 		   is_idle_task(tsk)) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 617009ccd82c..b8f42b3ba8ca 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,10 +315,10 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	account_irq_enter_time(current);
 
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	in_hardirq = lockdep_softirq_start();
+	account_softirq_enter(current);
 
 restart:
 	/* Reset the pending bitmask before enabling irqs */
@@ -365,8 +365,8 @@ restart:
 		wakeup_softirqd();
 	}
 
+	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	current_restore_flags(old_flags, PF_MEMALLOC);
@@ -418,7 +418,7 @@ static inline void __irq_exit_rcu(void)
 #else
 	lockdep_assert_irqs_disabled();
 #endif
-	account_irq_exit_time(current);
+	account_hardirq_exit(current);
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();