Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

 - Updates to the handling of expedited grace periods, perhaps most
   notably parallelizing their initialization.  Other changes
   include fixes from Boqun Feng.

 - Miscellaneous fixes.  These include an nvme fix from Nitzan Carmi
   that I am carrying because it depends on a new SRCU function
   cleanup_srcu_struct_quiesced().  This branch also includes fixes
   from Byungchul Park and Yury Norov.

 - Updates to reduce lock contention in the rcu_node combining tree.
   These are in preparation for the consolidation of RCU-bh,
   RCU-preempt, and RCU-sched into a single flavor, which was
   requested by Linus Torvalds in response to a security flaw
   whose root cause included confusion between the multiple flavors
   of RCU.

 - Torture-test updates that save their users some time and effort.

Conflicts:
	drivers/nvme/host/core.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 45 insertions, 17 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 36360d07f25b..19d235fefdb9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -188,13 +188,13 @@ static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
- * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
  *
  * This macro resembles cond_resched(), except that it is defined to
  * report potential quiescent states to RCU-tasks even if the cond_resched()
  * machinery were to be shut off, as some advocate for PREEMPT kernels.
  */
-#define cond_resched_rcu_qs() \
+#define cond_resched_tasks_rcu_qs() \
 do { \
 	if (!cond_resched()) \
 		rcu_note_voluntary_context_switch_lite(current); \
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index fd996cdf1833..448f20f27396 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -74,6 +74,7 @@ static inline void synchronize_rcu_bh_expedited(void)
 void rcu_barrier(void);
 void rcu_barrier_bh(void);
 void rcu_barrier_sched(void);
+bool rcu_eqs_special_set(int cpu);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
 unsigned long get_state_synchronize_sched(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c2413703f45d..8e2a84615bb6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1653,7 +1653,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
  * explicit rescheduling in places that are safe. The return
  * value indicates whether a reschedule was done in fact.
  * cond_resched_lock() will drop the spinlock before scheduling,
- * cond_resched_softirq() will enable bhs before scheduling.
  */
 #ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
@@ -1673,13 +1672,6 @@ extern int __cond_resched_lock(spinlock_t *lock);
 	__cond_resched_lock(lock);				\
 })
 
-extern int __cond_resched_softirq(void);
-
-#define cond_resched_softirq() ({					\
-	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
-	__cond_resched_softirq();					\
-})
-
 static inline void cond_resched_rcu(void)
 {
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 33c1c698df09..91494d7e8e41 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -69,11 +69,45 @@ struct srcu_struct { };
 
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head));
-void cleanup_srcu_struct(struct srcu_struct *sp);
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced);
 int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+static inline void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+	_cleanup_srcu_struct(sp, false);
+}
+
+/**
+ * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.  Also,
+ * all grace-period processing must have completed.
+ *
+ * "Completed" means that the last synchronize_srcu() and
+ * synchronize_srcu_expedited() calls must have returned before the call
+ * to cleanup_srcu_struct_quiesced().  It also means that the callback
+ * from the last call_srcu() must have been invoked before the call to
+ * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
+ * with this last.  Violating these rules will get you a WARN_ON() splat
+ * (with high probability, anyway), and will also cause the srcu_struct
+ * to be leaked.
+ */
+static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp)
+{
+	_cleanup_srcu_struct(sp, true);
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 /**
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d8c33298c153..5936aac357ab 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -84,20 +84,21 @@ TRACE_EVENT(rcu_grace_period,
 );
 
 /*
- * Tracepoint for future grace-period events, including those for no-callbacks
- * CPUs.  The caller should pull the data from the rcu_node structure,
- * other than rcuname, which comes from the rcu_state structure, and event,
- * which is one of the following:
+ * Tracepoint for future grace-period events.  The caller should pull
+ * the data from the rcu_node structure, other than rcuname, which comes
+ * from the rcu_state structure, and event, which is one of the following:
  *
- * "Startleaf": Request a nocb grace period based on leaf-node data.
+ * "Startleaf": Request a grace period based on leaf-node data.
+ * "Prestarted": Someone beat us to the request
  * "Startedleaf": Leaf-node start proved sufficient.
  * "Startedleafroot": Leaf-node start proved sufficient after checking root.
  * "Startedroot": Requested a nocb grace period based on root-node data.
+ * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "StartWait": Start waiting for the requested grace period.
  * "ResumeWait": Resume waiting after signal.
  * "EndWait": Complete wait.
  * "Cleanup": Clean up rcu_node structure after previous GP.
- * "CleanupMore": Clean up, and another no-CB GP is needed.
+ * "CleanupMore": Clean up, and another GP is needed.
  */
 TRACE_EVENT(rcu_future_grace_period,