From c34fa06f4bbba9e26fe50e5f6cde53c61560a794 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 31 Jan 2022 12:36:42 -0800 Subject: [PATCH] FROMLIST: rcu: Don't deboost before reporting expedited quiescent state Currently rcu_preempt_deferred_qs_irqrestore() releases rnp->boost_mtx before reporting the expedited quiescent state. Under heavy real-time load, this can result in this function being preempted before the quiescent state is reported, which can in turn prevent the expedited grace period from completing. Tim Murray reports that the resulting expedited grace periods can take hundreds of milliseconds and even more than one second, when they should normally complete in less than a millisecond. This patch follows Neeraj's suggestion (seconded by Tim and by Uladzislau Rezki) of simply reversing the two operations. Reported-by: Tim Murray Reported-by: Joel Fernandes Reported-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney Bug: 217236054 Link: https://lore.kernel.org/lkml/20220204232406.814-9-paulmck@kernel.org/ Signed-off-by: Tim Murray Change-Id: Ic0f0330b65a0c776a563e03e4b59bf4ab4fbccf6 --- kernel/rcu/tree_plugin.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6ed153f226b3..33a725a03024 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -531,16 +531,16 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - /* Unboost if we were boosted. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx); - /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) rcu_report_exp_rnp(rnp, true); + + /* Unboost if we were boosted. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) + rt_mutex_futex_unlock(&rnp->boost_mtx); } else { local_irq_restore(flags); }