@@ -141,6 +141,13 @@ static void __maybe_unused sync_exp_reset_tree(void)
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WARN_ON_ONCE(rnp->expmask);
WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
+ /*
+ * Need to wait for any blocked tasks as well. Note that
+ * additional blocking tasks will also block the expedited GP
+ * until such time as the ->expmask bits are cleared.
+ */
+ if (rcu_is_leaf_node(rnp) && rcu_preempt_has_tasks(rnp))
+ WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
@@ -393,13 +400,6 @@ static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp)
}
mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
- /*
- * Need to wait for any blocked tasks as well. Note that
- * additional blocking tasks will also block the expedited GP
- * until such time as the ->expmask bits are cleared.
- */
- if (rcu_preempt_has_tasks(rnp))
- WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* IPI the remaining CPUs for expedited quiescent state. */
When a grace period is started, the ->expmask of each node is set up from sync_exp_reset_tree(). Then later on each leaf node also initialize its ->exp_tasks pointer. This means that the initialization of the quiescent state of a node and the initialization of its blocking tasks happen with an unlocked node gap in-between. It happens to be fine because nothing is expected to report an exp quiescent state within this gap, since no IPI have been issued yet and every rdp's ->cpu_no_qs.b.exp should be false. However if it were to happen by accident, the quiescent state could be reported and propagated while ignoring tasks that blocked _before_ the start of the grace period. Prevent such trouble to happen in the future and initialize both the quiescent states mask to report and the blocked tasks head from the same node locked block. If a task blocks within an RCU read side critical section before sync_exp_reset_tree() is called and is then unblocked between sync_exp_reset_tree() and __sync_rcu_exp_select_node_cpus(), the QS won't be reported because no RCU exp IPI had been issued to request it through the setting of srdp->cpu_no_qs.b.exp. Signed-off-by: Frederic Weisbecker <frederic@kernel.org> --- kernel/rcu/tree_exp.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)