tasklets: Replace spin wait in tasklet_unlock_wait()

tasklet_unlock_wait() spin waits for TASKLET_STATE_RUN to be cleared. This
is wasting CPU cycles in a tight loop which is especially painful in a
guest when the CPU running the tasklet is scheduled out.

tasklet_unlock_wait() is invoked from tasklet_kill() which is used in
teardown paths and not performance critical at all. Replace the spin wait
with wait_var_event().

There are no users of tasklet_unlock_wait() which are invoked from atomic
contexts. The usage in tasklet_disable() has been replaced temporarily with
the spin waiting variant until the atomic users are fixed up and will be
converted to the sleep wait variant later.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210309084241.783936921@linutronix.de

include/linux/interrupt.h

@@ -664,17 +664,8 @@ static inline int tasklet_trylock(struct tasklet_struct *t)
 	return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 
-static inline void tasklet_unlock(struct tasklet_struct *t)
-{
-	smp_mb__before_atomic();
-	clear_bit(TASKLET_STATE_RUN, &(t)->state);
-}
-
-static inline void tasklet_unlock_wait(struct tasklet_struct *t)
-{
-	while (test_bit(TASKLET_STATE_RUN, &t->state))
-		cpu_relax();
-}
+void tasklet_unlock(struct tasklet_struct *t);
+void tasklet_unlock_wait(struct tasklet_struct *t);
 
 /*
  * Do not use in new code. Waiting for tasklets from atomic contexts is

kernel/softirq.c

@@ -25,6 +25,7 @@
 #include <linux/smpboot.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/wait_bit.h>
 
 #include <asm/softirq_stack.h>
 
@@ -632,6 +633,23 @@ void tasklet_kill(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(tasklet_kill);
 
+#ifdef CONFIG_SMP
+void tasklet_unlock(struct tasklet_struct *t)
+{
+	smp_mb__before_atomic();
+	clear_bit(TASKLET_STATE_RUN, &t->state);
+	smp_mb__after_atomic();
+	wake_up_var(&t->state);
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock);
+
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+	wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
 void __init softirq_init(void)
 {
 	int cpu;