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
*/
#define __irq_enter() \
do { \
- account_irq_enter_time(current); \
preempt_count_add(HARDIRQ_OFFSET); \
lockdep_hardirq_enter(); \
+ account_hardirq_enter(current); \
} while (0)
/*
*/
#define __irq_exit() \
do { \
+ account_hardirq_exit(current); \
lockdep_hardirq_exit(); \
- account_irq_exit_time(current); \
preempt_count_sub(HARDIRQ_OFFSET); \
} while (0)
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-extern void vtime_account_irq(struct task_struct *tsk);
+extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset);
extern void vtime_account_softirq(struct task_struct *tsk);
extern void vtime_account_hardirq(struct task_struct *tsk);
extern void vtime_flush(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-static inline void vtime_account_irq(struct task_struct *tsk) { }
+static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
+static inline void vtime_account_softirq(struct task_struct *tsk) { }
+static inline void vtime_account_hardirq(struct task_struct *tsk) { }
static inline void vtime_flush(struct task_struct *tsk) { }
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-extern void irqtime_account_irq(struct task_struct *tsk);
+extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset);
#else
-static inline void irqtime_account_irq(struct task_struct *tsk) { }
+static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
#endif
-static inline void account_irq_enter_time(struct task_struct *tsk)
+static inline void account_softirq_enter(struct task_struct *tsk)
{
- vtime_account_irq(tsk);
- irqtime_account_irq(tsk);
+ vtime_account_irq(tsk, SOFTIRQ_OFFSET);
+ irqtime_account_irq(tsk, SOFTIRQ_OFFSET);
}
-static inline void account_irq_exit_time(struct task_struct *tsk)
+static inline void account_softirq_exit(struct task_struct *tsk)
{
- vtime_account_irq(tsk);
- irqtime_account_irq(tsk);
+ vtime_account_softirq(tsk);
+ irqtime_account_irq(tsk, 0);
+}
+
+static inline void account_hardirq_enter(struct task_struct *tsk)
+{
+ vtime_account_irq(tsk, HARDIRQ_OFFSET);
+ irqtime_account_irq(tsk, HARDIRQ_OFFSET);
+}
+
+static inline void account_hardirq_exit(struct task_struct *tsk)
+{
+ vtime_account_hardirq(tsk);
+ irqtime_account_irq(tsk, 0);
}
#endif /* _LINUX_KERNEL_VTIME_H */
}
/*
- * 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;
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.
* 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);
}
}
# 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)) {
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 */
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);
#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();