static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
{
trace_rcu_dyntick("Start", oldval, 0);
if (!is_idle_task(current)) {
struct task_struct *idle = idle_task(smp_processor_id());
trace_rcu_dyntick("Error on entry: not idle task", oldval, 0);
ftrace_dump(DUMP_ALL);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm);
}
rcu_prepare_for_idle(smp_processor_id());
smp_mb__before_atomic_inc();
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic_inc();
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
"Illegal idle entry in RCU read-side critical section.");
rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
"Illegal idle entry in RCU-bh read-side critical section.");
rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
"Illegal idle entry in RCU-sched read-side critical section.");
}
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_sched() from within an RCU read-side critical section.
* Therefore, any legal call to synchronize_sched() is a quiescent
* state, and so on a UP system, synchronize_sched() need do nothing.
* Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the
* benefits of doing might_sleep() to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
*
* But we want to make this a static inline later. The cond_resched()
* currently makes this problematic.
*/
void synchronize_sched(void)
{
rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
!lock_is_held(&rcu_lock_map) &&
!lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_sched() in RCU read-side critical section");
cond_resched();
}
/*
* Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
{
int idx;
rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
!lock_is_held(&rcu_bh_lock_map) &&
!lock_is_held(&rcu_lock_map) &&
!lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
idx = sp->completed;
mutex_lock(&sp->mutex);
/*
* Check to see if someone else did the work for us while we were
* waiting to acquire the lock. We need -two- advances of
* the counter, not just one. If there was but one, we might have
* shown up -after- our helper's first synchronize_sched(), thus
* having failed to prevent CPU-reordering races with concurrent
* srcu_read_unlock()s on other CPUs (see comment below). So we
* either (1) wait for two or (2) supply the second ourselves.
*/
if ((sp->completed - idx) >= 2) {
mutex_unlock(&sp->mutex);
return;
}
sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() ensures that any CPU that
* sees the new value of sp->completed will also see any preceding
* changes to data structures made by this CPU. This prevents
* some other CPU from reordering the accesses in its SRCU
* read-side critical section to precede the corresponding
* srcu_read_lock() -- ensuring that such references will in
* fact be protected.
*
* So it is now safe to do the flip.
*/
idx = sp->completed & 0x1;
sp->completed++;
sync_func(); /* Force memory barrier on all CPUs. */
/*
* At this point, because of the preceding synchronize_sched(),
* all srcu_read_lock() calls using the old counters have completed.
* Their corresponding critical sections might well be still
* executing, but the srcu_read_lock() primitives themselves
* will have finished executing. We initially give readers
* an arbitrarily chosen 10 microseconds to get out of their
* SRCU read-side critical sections, then loop waiting 1/HZ
* seconds per iteration. The 10-microsecond value has done
* very well in testing.
*/
if (srcu_readers_active_idx(sp, idx))
udelay(SYNCHRONIZE_SRCU_READER_DELAY);
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() forces all srcu_read_unlock()
* primitives that were executing concurrently with the preceding
* for_each_possible_cpu() loop to have completed by this point.
* More importantly, it also forces the corresponding SRCU read-side
* critical sections to have also completed, and the corresponding
* references to SRCU-protected data items to be dropped.
*
* Note:
*
* Despite what you might think at first glance, the
* preceding synchronize_sched() -must- be within the
* critical section ended by the following mutex_unlock().
* Otherwise, a task taking the early exit can race
* with a srcu_read_unlock(), which might have executed
* just before the preceding srcu_readers_active() check,
* and whose CPU might have reordered the srcu_read_unlock()
* with the preceding critical section. In this case, there
* is nothing preventing the synchronize_sched() task that is
* taking the early exit from freeing a data structure that
* is still being referenced (out of order) by the task
* doing the srcu_read_unlock().
*
* Alternatively, the comparison with "2" on the early exit
* could be changed to "3", but this increases synchronize_srcu()
* latency for bulk loads. So the current code is preferred.
*/
mutex_unlock(&sp->mutex);
}
