4 files changed, 57 insertions, 23 deletions
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6df7f9fe0d01..2bb4c4f3531a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -102,12 +102,6 @@ extern struct group_info init_groups;
 #define INIT_IDS
 #endif
 
-#ifdef CONFIG_RCU_BOOST
-#define INIT_TASK_RCU_BOOST()						\
-	.rcu_boost_mutex = NULL,
-#else
-#define INIT_TASK_RCU_BOOST()
-#endif
 #ifdef CONFIG_TREE_PREEMPT_RCU
 #define INIT_TASK_RCU_TREE_PREEMPT()					\
 	.rcu_blocked_node = NULL,
@@ -119,8 +113,7 @@ extern struct group_info init_groups;
 	.rcu_read_lock_nesting = 0,					\
 	.rcu_read_unlock_special = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
-	INIT_TASK_RCU_TREE_PREEMPT()					\
-	INIT_TASK_RCU_BOOST()
+	INIT_TASK_RCU_TREE_PREEMPT()
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6a94cc8b1ca0..d231aa17b1d7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -826,15 +826,14 @@ static inline void rcu_preempt_sleep_check(void)
  * read-side critical section that would block in a !PREEMPT kernel.
  * But if you want the full story, read on!
  *
- * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
- * is illegal to block while in an RCU read-side critical section.  In
- * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
- * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
- * be preempted, but explicit blocking is illegal.  Finally, in preemptible
- * RCU implementations in real-time (with -rt patchset) kernel builds,
- * RCU read-side critical sections may be preempted and they may also
- * block, but only when acquiring spinlocks that are subject to priority
- * inheritance.
+ * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU),
+ * it is illegal to block while in an RCU read-side critical section.
+ * In preemptible RCU implementations (TREE_PREEMPT_RCU) in CONFIG_PREEMPT
+ * kernel builds, RCU read-side critical sections may be preempted,
+ * but explicit blocking is illegal.  Finally, in preemptible RCU
+ * implementations in real-time (with -rt patchset) kernel builds, RCU
+ * read-side critical sections may be preempted and they may also block, but
+ * only when acquiring spinlocks that are subject to priority inheritance.
  */
 static inline void rcu_read_lock(void)
 {
@@ -858,6 +857,34 @@ static inline void rcu_read_lock(void)
 /**
  * rcu_read_unlock() - marks the end of an RCU read-side critical section.
  *
+ * In most situations, rcu_read_unlock() is immune from deadlock.
+ * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock()
+ * is responsible for deboosting, which it does via rt_mutex_unlock().
+ * Unfortunately, this function acquires the scheduler's runqueue and
+ * priority-inheritance spinlocks.  This means that deadlock could result
+ * if the caller of rcu_read_unlock() already holds one of these locks or
+ * any lock that is ever acquired while holding them.
+ *
+ * That said, RCU readers are never priority boosted unless they were
+ * preempted.  Therefore, one way to avoid deadlock is to make sure
+ * that preemption never happens within any RCU read-side critical
+ * section whose outermost rcu_read_unlock() is called with one of
+ * rt_mutex_unlock()'s locks held.  Such preemption can be avoided in
+ * a number of ways, for example, by invoking preempt_disable() before
+ * critical section's outermost rcu_read_lock().
+ *
+ * Given that the set of locks acquired by rt_mutex_unlock() might change
+ * at any time, a somewhat more future-proofed approach is to make sure
+ * that that preemption never happens within any RCU read-side critical
+ * section whose outermost rcu_read_unlock() is called with irqs disabled.
+ * This approach relies on the fact that rt_mutex_unlock() currently only
+ * acquires irq-disabled locks.
+ *
+ * The second of these two approaches is best in most situations,
+ * however, the first approach can also be useful, at least to those
+ * developers willing to keep abreast of the set of locks acquired by
+ * rt_mutex_unlock().
+ *
  * See rcu_read_lock() for more information.
  */
 static inline void rcu_read_unlock(void)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0376b054a0d0..b39a671cfd59 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1270,9 +1270,6 @@ struct task_struct {
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
-	struct rt_mutex *rcu_boost_mutex;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -2009,9 +2006,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	p->rcu_blocked_node = NULL;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
-	p->rcu_boost_mutex = NULL;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b84773cb9f4c..06cc093ab7ad 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -12,6 +12,7 @@
 #include <linux/hrtimer.h>
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
@@ -162,6 +163,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
 extern cpumask_var_t tick_nohz_full_mask;
+extern cpumask_var_t housekeeping_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
@@ -194,6 +196,24 @@ static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
 #endif
 
+static inline bool is_housekeeping_cpu(int cpu)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_enabled())
+		return cpumask_test_cpu(cpu, housekeeping_mask);
+#endif
+	return true;
+}
+
+static inline void housekeeping_affine(struct task_struct *t)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_enabled())
+		set_cpus_allowed_ptr(t, housekeeping_mask);
+
+#endif
+}
+
 static inline void tick_nohz_full_check(void)
 {
 	if (tick_nohz_full_enabled())