rcu/nocb: Perform deferred wake up before last idle's need_resched() check

Entering RCU idle mode may cause a deferred wake up of an RCU NOCB_GP
kthread (rcuog) to be serviced.

Usually a local wake up happening while running the idle task is handled
in one of the need_resched() checks carefully placed within the idle
loop that can break to the scheduler.

Unfortunately the call to rcu_idle_enter() is already beyond the last
generic need_resched() check and we may halt the CPU with a resched
request unhandled, leaving the task hanging.

Fix this with splitting the rcuog wakeup handling from rcu_idle_enter()
and place it before the last generic need_resched() check in the idle
loop. It is then assumed that no call to call_rcu() will be performed
after that in the idle loop until the CPU is put in low power mode.

Fixes: 96d3fd0d315a (rcu: Break call_rcu() deadlock involving scheduler and perf)
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210131230548.32970-3-frederic@kernel.org

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index fd02c5f..36c2119 100644 (file)
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -110,8 +110,10 @@ static inline void rcu_user_exit(void) { }
 
 #ifdef CONFIG_RCU_NOCB_CPU
 void rcu_init_nohz(void);
+void rcu_nocb_flush_deferred_wakeup(void);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 static inline void rcu_init_nohz(void) { }
+static inline void rcu_nocb_flush_deferred_wakeup(void) { }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /**

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 63032e5..82838e9 100644 (file)
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -671,10 +671,7 @@ static noinstr void rcu_eqs_enter(bool user)
  */
 void rcu_idle_enter(void)
 {
-       struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
        lockdep_assert_irqs_disabled();
-       do_nocb_deferred_wakeup(rdp);
        rcu_eqs_enter(false);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7e291ce..d5b38c2 100644 (file)
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2187,6 +2187,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
                do_nocb_deferred_wakeup_common(rdp);
 }
 
+void rcu_nocb_flush_deferred_wakeup(void)
+{
+       do_nocb_deferred_wakeup(this_cpu_ptr(&rcu_data));
+}
+
 void __init rcu_init_nohz(void)
 {
        int cpu;

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 305727e..7199e6f 100644 (file)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -285,6 +285,7 @@ static void do_idle(void)
                }
 
                arch_cpu_idle_enter();
+               rcu_nocb_flush_deferred_wakeup();
 
                /*
                 * In poll mode we reenable interrupts and spin. Also if we