rcu: Stop disabling interrupts in scheduler fastpaths

We need the scheduler's fastpaths to be, well, fast, and unnecessarily
disabling and re-enabling interrupts is not necessarily consistent with
this goal.  Especially given that there are regions of the scheduler that
already have interrupts disabled.

This commit therefore moves the call to rcu_note_context_switch()
to one of the interrupts-disabled regions of the scheduler, and
removes the now-redundant disabling and re-enabling of interrupts from
rcu_note_context_switch() and the functions it calls.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Shift rcu_note_context_switch() to avoid deadlock, as suggested
  by Peter Zijlstra. ]

include/linux/rcutree.h

@@ -37,7 +37,7 @@ void rcu_cpu_stall_reset(void);
 /*
  * Note a virtualization-based context switch.  This is simply a
  * wrapper around rcu_note_context_switch(), which allows TINY_RCU
- * to save a few bytes.
+ * to save a few bytes. The caller must have disabled interrupts.
  */
 static inline void rcu_virt_note_context_switch(int cpu)
 {

kernel/rcu/tree.c

@@ -242,8 +242,6 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(void)
 {
-	unsigned long flags;
-
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
 		return;
 	trace_rcu_grace_period(TPS("rcu_sched"),
@@ -252,13 +250,9 @@ void rcu_sched_qs(void)
 	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
 		return;
-	local_irq_save(flags);
-	if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) {
-		__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
-		rcu_report_exp_rdp(&rcu_sched_state,
-				   this_cpu_ptr(&rcu_sched_data), true);
-	}
-	local_irq_restore(flags);
+	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
+	rcu_report_exp_rdp(&rcu_sched_state,
+			   this_cpu_ptr(&rcu_sched_data), true);
 }
 
 void rcu_bh_qs(void)
@@ -295,17 +289,16 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
  * We inform the RCU core by emulating a zero-duration dyntick-idle
  * period, which we in turn do by incrementing the ->dynticks counter
  * by two.
+ *
+ * The caller must have disabled interrupts.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp;
 	int resched_mask;
 	struct rcu_state *rsp;
 
-	local_irq_save(flags);
-
 	/*
 	 * Yes, we can lose flag-setting operations.  This is OK, because
 	 * the flag will be set again after some delay.
@@ -335,13 +328,12 @@ static void rcu_momentary_dyntick_idle(void)
 		smp_mb__after_atomic(); /* Later stuff after QS. */
 		break;
 	}
-	local_irq_restore(flags);
 }
 
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
- * The caller must have disabled preemption.
+ * The caller must have disabled interrupts.
  */
 void rcu_note_context_switch(void)
 {
@@ -371,9 +363,14 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
  */
 void rcu_all_qs(void)
 {
+	unsigned long flags;
+
 	barrier(); /* Avoid RCU read-side critical sections leaking down. */
-	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+		local_irq_save(flags);
 		rcu_momentary_dyntick_idle();
+		local_irq_restore(flags);
+	}
 	this_cpu_inc(rcu_qs_ctr);
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
 }

kernel/rcu/tree_plugin.h

@@ -146,8 +146,8 @@ static void __init rcu_bootup_announce(void)
  * the corresponding expedited grace period will also be the end of the
  * normal grace period.
  */
-static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
-				   unsigned long flags) __releases(rnp->lock)
+static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
+	__releases(rnp->lock) /* But leaves rrupts disabled. */
 {
 	int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) +
 			 (rnp->exp_tasks ? RCU_EXP_TASKS : 0) +
@@ -235,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
 		rnp->gp_tasks = &t->rcu_node_entry;
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
-	raw_spin_unlock(&rnp->lock);
+	raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */
 
 	/*
 	 * Report the quiescent state for the expedited GP.  This expedited
@@ -250,7 +250,6 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
 	} else {
 		WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs);
 	}
-	local_irq_restore(flags);
 }
 
 /*
@@ -285,12 +284,11 @@ static void rcu_preempt_qs(void)
  * predating the current grace period drain, in other words, until
  * rnp->gp_tasks becomes NULL.
  *
- * Caller must disable preemption.
+ * Caller must disable interrupts.
  */
 static void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
@@ -300,7 +298,7 @@ static void rcu_preempt_note_context_switch(void)
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		raw_spin_lock_rcu_node(rnp);
 		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
@@ -316,7 +314,7 @@ static void rcu_preempt_note_context_switch(void)
 				       (rnp->qsmask & rdp->grpmask)
 				       ? rnp->gpnum
 				       : rnp->gpnum + 1);
-		rcu_preempt_ctxt_queue(rnp, rdp, flags);
+		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
 

kernel/sched/core.c

@@ -3085,7 +3085,6 @@ static void __sched notrace __schedule(bool preempt)
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_note_context_switch();
 	prev = rq->curr;
 
 	/*
@@ -3104,13 +3103,16 @@ static void __sched notrace __schedule(bool preempt)
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	local_irq_disable();
+	rcu_note_context_switch();
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_lock(&rq->lock);
 	lockdep_pin_lock(&rq->lock);
 
 	rq->clock_skip_update <<= 1; /* promote REQ to ACT */