rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks

This commit makes the calls to rcu_tasks_qs() detect and report
quiescent states for RCU tasks trace.  If the task is in a quiescent
state and if ->trc_reader_checked is not yet set, the task sets its own
->trc_reader_checked.  This will cause the grace-period kthread to
remove it from the holdout list if it still remains there.

[ paulmck: Fix conditional compilation per kbuild test robot feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

4 files changed, 43 insertions, 14 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2be97a83f266..659cbfa7581a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -131,20 +131,50 @@ static inline void rcu_init_nohz(void) { }
  * This is a macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU_GENERIC
-#define rcu_tasks_qs(t) \
-	do { \
-		if (READ_ONCE((t)->rcu_tasks_holdout)) \
-			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
+
+# ifdef CONFIG_TASKS_RCU
+# define rcu_tasks_classic_qs(t, preempt)				\
+	do {								\
+		if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout))	\
+			WRITE_ONCE((t)->rcu_tasks_holdout, false);	\
 	} while (0)
-#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
+# else
+# define rcu_tasks_classic_qs(t, preempt) do { } while (0)
+# define call_rcu_tasks call_rcu
+# define synchronize_rcu_tasks synchronize_rcu
+# endif
+
+# ifdef CONFIG_TASKS_RCU_TRACE
+# define rcu_tasks_trace_qs(t)						\
+	do {								\
+		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
+		    !unlikely(READ_ONCE((t)->trc_reader_nesting))) {	\
+			smp_store_release(&(t)->trc_reader_checked, true); \
+			smp_mb(); /* Readers partitioned by store. */	\
+		}							\
+	} while (0)
+# else
+# define rcu_tasks_trace_qs(t) do { } while (0)
+# endif
+
+#define rcu_tasks_qs(t, preempt)					\
+do {									\
+	rcu_tasks_classic_qs((t), (preempt));				\
+	rcu_tasks_trace_qs((t));					\
+} while (0)
+
+# ifdef CONFIG_TASKS_RUDE_RCU
 void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks_rude(void);
+# endif
+
+#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
-#define rcu_tasks_qs(t)	do { } while (0)
+#define rcu_tasks_qs(t, preempt) do { } while (0)
 #define rcu_note_voluntary_context_switch(t) do { } while (0)
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
@@ -161,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	rcu_tasks_qs(current); \
+	rcu_tasks_qs(current, false); \
 	cond_resched(); \
 } while (0)
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 045c28b71f4f..d77e11186afd 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void)
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_qs(); \
-		rcu_tasks_qs(current); \
+		rcu_tasks_qs(current, (preempt)); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index c93fb29b460c..6f8a4040fbdd 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -180,7 +180,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 
 		/* Pick up any new callbacks. */
 		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
-		smp_mb__after_unlock_lock(); // Order updates vs. GP.
+		smp_mb__after_spinlock(); // Order updates vs. GP.
 		list = rtp->cbs_head;
 		rtp->cbs_head = NULL;
 		rtp->cbs_tail = &rtp->cbs_head;
@@ -874,7 +874,7 @@ static void rcu_tasks_trace_pertask(struct task_struct *t,
 				    struct list_head *hop)
 {
 	WRITE_ONCE(t->trc_reader_need_end, false);
-	t->trc_reader_checked = false;
+	WRITE_ONCE(t->trc_reader_checked, false);
 	t->trc_ipi_to_cpu = -1;
 	trc_wait_for_one_reader(t, hop);
 }
@@ -983,6 +983,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 		pr_err("\t%d holdouts\n", atomic_read(&trc_n_readers_need_end));
 	}
 	smp_mb(); // Caller's code must be ordered after wakeup.
+		  // Pairs with pretty much every ordering primitive.
 }
 
 /* Report any needed quiescent state for this exiting task. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 4f34c325dd90..37e02812d18f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -331,8 +331,7 @@ void rcu_note_context_switch(bool preempt)
 	rcu_qs();
 	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
-	if (!preempt)
-		rcu_tasks_qs(current);
+	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -841,8 +840,7 @@ void rcu_note_context_switch(bool preempt)
 	this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
 		rcu_momentary_dyntick_idle();
-	if (!preempt)
-		rcu_tasks_qs(current);
+	rcu_tasks_qs(current, preempt);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 }