From 59f792d1ef214592ae9b86238fa8fd00f5929b76 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 19 Jan 2015 21:43:40 -0800
Subject: rcu: Refine diagnostics for lacking kthread for no-CBs callbacks

Some diagnostics under CONFIG_PROVE_RCU in rcu_nocb_cpu_needs_barrier()
assume that there can be no early-boot callbacks.  This commit therefore
qualifies the diagnostic with rcu_scheduler_fully_active to permit
early boot callbacks to avoid this splat.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a571e9a0f1d..75d5f096bcb0 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1945,7 +1945,8 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
 
 	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
-	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+	    rcu_scheduler_fully_active) {
 		/* RCU callback enqueued before CPU first came online??? */
 		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
 		       cpu, rhp->func);
-- 
cgit v1.2.3


From 5afff48bdf7481570c9385a8a674a81ffb8f09ee Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 18 Feb 2015 16:39:09 -0800
Subject: rcu: Update from rcu_expedited variable to rcu_gp_is_expedited()

This commit updates open-coded tests of the rcu_expedited variable
to instead use rcu_gp_is_expedited().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/srcu.c        | 2 +-
 kernel/rcu/tree.c        | 9 +++++----
 kernel/rcu/tree_plugin.h | 2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 445bf8ffe3fb..c871f07eff69 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -507,7 +507,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, rcu_expedited
+	__synchronize_srcu(sp, rcu_gp_is_expedited()
 			   ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
 			   : SYNCHRONIZE_SRCU_TRYCOUNT);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 48d640ca1a05..4325fbe79d84 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2954,7 +2954,7 @@ void synchronize_sched(void)
 			   "Illegal synchronize_sched() in RCU-sched read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_sched_expedited();
 	else
 		wait_rcu_gp(call_rcu_sched);
@@ -2981,7 +2981,7 @@ void synchronize_rcu_bh(void)
 			   "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_rcu_bh_expedited();
 	else
 		wait_rcu_gp(call_rcu_bh);
@@ -3660,11 +3660,12 @@ static int rcu_pm_notify(struct notifier_block *self,
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
 		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_expedited = 1;
+			rcu_expedite_gp();
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
-		rcu_expedited = 0;
+		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
+			rcu_unexpedite_gp();
 		break;
 	default:
 		break;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a571e9a0f1d..63726b734d34 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -585,7 +585,7 @@ void synchronize_rcu(void)
 			   "Illegal synchronize_rcu() in RCU read-side critical section");
 	if (!rcu_scheduler_active)
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_rcu_expedited();
 	else
 		wait_rcu_gp(call_rcu);
-- 
cgit v1.2.3


From 5871968d531f39c23a8e6c69525bb705bca52e04 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 24 Feb 2015 11:05:36 -0800
Subject: rcu: Tighten up affinity and check for sysidle

If the RCU grace-period kthread invoking rcu_sysidle_check_cpu()
happens to be running on the tick_do_timer_cpu initially,
then rcu_bind_gp_kthread() won't bind it.  This kthread might
then migrate before invoking rcu_gp_fqs(), which will trigger the
WARN_ON_ONCE() in rcu_sysidle_check_cpu().  This commit therefore makes
rcu_bind_gp_kthread() do the binding even if the kthread is currently
on the same CPU.  Because this incurs added overhead, this commit also
causes each RCU grace-period kthread to invoke rcu_bind_gp_kthread()
once at boot rather than at the beginning of each grace period.
And as long as rcu_bind_gp_kthread() is being modified, this commit
eliminates its #ifdef.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        |  2 +-
 kernel/rcu/tree_plugin.h | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 735bd7ee749a..a6972c20eaa5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1707,7 +1707,6 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	ACCESS_ONCE(rsp->gp_activity) = jiffies;
-	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
 	if (!ACCESS_ONCE(rsp->gp_flags)) {
@@ -1895,6 +1894,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	struct rcu_state *rsp = arg;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	rcu_bind_gp_kthread();
 	for (;;) {
 
 		/* Handle grace-period start. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a571e9a0f1d..b46c92824db1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2763,7 +2763,8 @@ static void rcu_sysidle_exit(int irq)
 
 /*
  * Check to see if the current CPU is idle.  Note that usermode execution
- * does not count as idle.  The caller must have disabled interrupts.
+ * does not count as idle.  The caller must have disabled interrupts,
+ * and must be running on tick_do_timer_cpu.
  */
 static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 				  unsigned long *maxj)
@@ -2784,8 +2785,8 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	if (!*isidle || rdp->rsp != rcu_state_p ||
 	    cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
 		return;
-	if (rcu_gp_in_progress(rdp->rsp))
-		WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
+	/* Verify affinity of current kthread. */
+	WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
 
 	/* Pick up current idle and NMI-nesting counter and check. */
 	cur = atomic_read(&rdtp->dynticks_idle);
@@ -3068,11 +3069,10 @@ static void rcu_bind_gp_kthread(void)
 		return;
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 	cpu = tick_do_timer_cpu;
-	if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu)
+	if (cpu >= 0 && cpu < nr_cpu_ids)
 		set_cpus_allowed_ptr(current, cpumask_of(cpu));
 #else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-	if (!is_housekeeping_cpu(raw_smp_processor_id()))
-		housekeeping_affine(current);
+	housekeeping_affine(current);
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
 
-- 
cgit v1.2.3


From 34404ca8fb252ccee662c4368c555ccf774acc3b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 19 Jan 2015 20:39:20 -0800
Subject: rcu: Move early-boot callbacks to no-CBs lists for no-CBs CPUs

When a CPU is first determined to be a no-CBs CPUs, this commit causes
any early boot callbacks to be moved to the no-CBs callback list,
allowing them to be invoked.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        |  1 +
 kernel/rcu/tree_plugin.h | 24 ++++++++++++------------
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 92fd3eab5823..0317bf7d997f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2851,6 +2851,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		 * and then drop through to queue the callback.
 		 */
 		BUG_ON(cpu != -1);
+		WARN_ON_ONCE(!rcu_is_watching());
 		if (!likely(rdp->nxtlist))
 			init_default_callback_list(rdp);
 	}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 75d5f096bcb0..afddd5641bea 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2393,18 +2393,8 @@ void __init rcu_init_nohz(void)
 		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
 
 	for_each_rcu_flavor(rsp) {
-		for_each_cpu(cpu, rcu_nocb_mask) {
-			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-
-			/*
-			 * If there are early callbacks, they will need
-			 * to be moved to the nocb lists.
-			 */
-			WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
-				     &rdp->nxtlist &&
-				     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
-			init_nocb_callback_list(rdp);
-		}
+		for_each_cpu(cpu, rcu_nocb_mask)
+			init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu));
 		rcu_organize_nocb_kthreads(rsp);
 	}
 }
@@ -2541,6 +2531,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return false;
 
+	/* If there are early-boot callbacks, move them to nocb lists. */
+	if (rdp->nxtlist) {
+		rdp->nocb_head = rdp->nxtlist;
+		rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
+		atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
+		atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
+		rdp->nxtlist = NULL;
+		rdp->qlen = 0;
+		rdp->qlen_lazy = 0;
+	}
 	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
 	return true;
 }
-- 
cgit v1.2.3


From d24209bb689e2c7f7418faec9b4a948e922d24da Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 21 Jan 2015 15:26:03 -0800
Subject: rcu: Improve diagnostics for blocked critical sections in irq

If an RCU read-side critical section occurs within an interrupt handler
or a softirq handler, it cannot have been preempted.  Therefore, there is
a check in rcu_read_unlock_special() checking for this error.  However,
when this check triggers, it lacks diagnostic information.  This commit
therefore moves rcu_read_unlock()'s lockdep annotation to follow the
call to __rcu_read_unlock() and changes rcu_read_unlock_special()'s
WARN_ON_ONCE() to an lockdep_rcu_suspicious() in order to locate where
the offending RCU read-side critical section began.  In addition, the
value of the ->rcu_read_unlock_special field is printed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/lockdep.h  | 7 ++++++-
 include/linux/rcupdate.h | 2 +-
 kernel/rcu/tree_plugin.h | 8 +++++++-
 3 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 74ab23176e9b..066ba4157541 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -531,8 +531,13 @@ do {									\
 # define might_lock_read(lock) do { } while (0)
 #endif
 
-#ifdef CONFIG_PROVE_RCU
+#ifdef CONFIG_LOCKDEP
 void lockdep_rcu_suspicious(const char *file, const int line, const char *s);
+#else
+static inline void
+lockdep_rcu_suspicious(const char *file, const int line, const char *s)
+{
+}
 #endif
 
 #endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3e6afed51051..70b896e16f19 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -942,9 +942,9 @@ static inline void rcu_read_unlock(void)
 {
 	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_unlock() used illegally while idle");
-	rcu_lock_release(&rcu_lock_map);
 	__release(RCU);
 	__rcu_read_unlock();
+	rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
 }
 
 /**
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a571e9a0f1d..8a33920b8845 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -334,7 +334,13 @@ void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Hardware IRQ handlers cannot block, complain if they get here. */
-	if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
+	if (in_irq() || in_serving_softirq()) {
+		lockdep_rcu_suspicious(__FILE__, __LINE__,
+				       "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
+		pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n",
+			 t->rcu_read_unlock_special.s,
+			 t->rcu_read_unlock_special.b.blocked,
+			 t->rcu_read_unlock_special.b.need_qs);
 		local_irq_restore(flags);
 		return;
 	}
-- 
cgit v1.2.3


From ab6f5bd6741af7b157275de299b7b2b96f2df40e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 21 Jan 2015 16:58:06 -0800
Subject: rcu: Use IS_ENABLED() to simplify rcu_bootup_announce_oddness()

This commit gets rid of some inline #ifdefs by replacing them with
IS_ENABLED.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 48 ++++++++++++++++++++----------------------------
 1 file changed, 20 insertions(+), 28 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 8a33920b8845..81c4d91fa18a 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -58,38 +58,30 @@ static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
  */
 static void __init rcu_bootup_announce_oddness(void)
 {
-#ifdef CONFIG_RCU_TRACE
-	pr_info("\tRCU debugfs-based tracing is enabled.\n");
-#endif
-#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
-	pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-	       CONFIG_RCU_FANOUT);
-#endif
-#ifdef CONFIG_RCU_FANOUT_EXACT
-	pr_info("\tHierarchical RCU autobalancing is disabled.\n");
-#endif
-#ifdef CONFIG_RCU_FAST_NO_HZ
-	pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
-#endif
-#ifdef CONFIG_PROVE_RCU
-	pr_info("\tRCU lockdep checking is enabled.\n");
-#endif
-#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
-	pr_info("\tRCU torture testing starts during boot.\n");
-#endif
-#if defined(CONFIG_RCU_CPU_STALL_INFO)
-	pr_info("\tAdditional per-CPU info printed with stalls.\n");
-#endif
-#if NUM_RCU_LVL_4 != 0
-	pr_info("\tFour-level hierarchy is enabled.\n");
-#endif
+	if (IS_ENABLED(CONFIG_RCU_TRACE))
+		pr_info("\tRCU debugfs-based tracing is enabled.\n");
+	if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
+	    (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+		       CONFIG_RCU_FANOUT);
+	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
+	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
+		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+	if (IS_ENABLED(CONFIG_PROVE_RCU))
+		pr_info("\tRCU lockdep checking is enabled.\n");
+	if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE))
+		pr_info("\tRCU torture testing starts during boot.\n");
+	if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO))
+		pr_info("\tAdditional per-CPU info printed with stalls.\n");
+	if (NUM_RCU_LVL_4 != 0)
+		pr_info("\tFour-level hierarchy is enabled.\n");
 	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
-#ifdef CONFIG_RCU_BOOST
-	pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
-#endif
+	if (IS_ENABLED(CONFIG_RCU_BOOST))
+		pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
 }
 
 #ifdef CONFIG_PREEMPT_RCU
-- 
cgit v1.2.3


From a3bd2c09adcc80946262fd15e63868de1f0f4963 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 21 Jan 2015 20:58:57 -0800
Subject: rcu: Add boot-up check for non-default CONFIG_RCU_FANOUT_LEAF values

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 81c4d91fa18a..c9225350d3ed 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -76,6 +76,9 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tAdditional per-CPU info printed with stalls.\n");
 	if (NUM_RCU_LVL_4 != 0)
 		pr_info("\tFour-level hierarchy is enabled.\n");
+	if (CONFIG_RCU_FANOUT_LEAF != 16)
+		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
+			CONFIG_RCU_FANOUT_LEAF);
 	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
-- 
cgit v1.2.3


From c8aead6a9b27fdd94b7bcb74b587ae012d8145f2 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 19 Jan 2015 16:56:46 -0800
Subject: rcu: Simplify sync_rcu_preempt_exp_init()

This commit eliminates a boolean and associated "if" statement by
rearranging the code.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a571e9a0f1d..d37c9fbdba71 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -677,19 +677,16 @@ static void
 sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	unsigned long flags;
-	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
 	if (!rcu_preempt_has_tasks(rnp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		rcu_report_exp_rnp(rsp, rnp, false); /* No tasks, report. */
 	} else {
 		rnp->exp_tasks = rnp->blkd_tasks.next;
 		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
-		must_wait = 1;
 	}
-	if (!must_wait)
-		rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */
 }
 
 /**
-- 
cgit v1.2.3


From 18c629eaebf1814ca7f0c27327f75aa93aa4a5de Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 19 Jan 2015 18:59:56 -0800
Subject: rcu: Eliminate empty HOTPLUG_CPU ifdef

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d37c9fbdba71..79376e2461c9 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -520,10 +520,6 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Check for a quiescent state from the current CPU.  When a task blocks,
  * the task is recorded in the corresponding CPU's rcu_node structure,
-- 
cgit v1.2.3


From 8eb74b2b291e7bf6aa59fcb4e59f236382f00bf5 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 13 Feb 2015 10:52:28 -0800
Subject: rcu: Rework preemptible expedited bitmask handling

Currently, the rcu_node tree ->expmask bitmasks are initially set to
reflect the online CPUs.  This is pointless, because only the CPUs
preempted within RCU read-side critical sections by the preceding
synchronize_sched_expedited() need to be tracked.  This commit therefore
instead sets up these bitmasks based on the state of the ->blkd_tasks
lists.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 98 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 75 insertions(+), 23 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 79376e2461c9..a22721547442 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -626,9 +626,6 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
  *
- * Most callers will set the "wake" flag, but the task initiating the
- * expedited grace period need not wake itself.
- *
  * Caller must hold sync_rcu_preempt_exp_mutex.
  */
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
@@ -663,26 +660,85 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 
 /*
  * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure.  If there are no such
- * tasks, report it up the rcu_node hierarchy.
+ * grace period for the specified rcu_node structure, phase 1.  If there
+ * are such tasks, set the ->expmask bits up the rcu_node tree and also
+ * set the ->expmask bits on the leaf rcu_node structures to tell phase 2
+ * that work is needed here.
  *
- * Caller must hold sync_rcu_preempt_exp_mutex and must exclude
- * CPU hotplug operations.
+ * Caller must hold sync_rcu_preempt_exp_mutex.
  */
 static void
-sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
+sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp_up;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
+	WARN_ON_ONCE(rnp->expmask);
+	WARN_ON_ONCE(rnp->exp_tasks);
 	if (!rcu_preempt_has_tasks(rnp)) {
+		/* No blocked tasks, nothing to do. */
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		rcu_report_exp_rnp(rsp, rnp, false); /* No tasks, report. */
-	} else {
+		return;
+	}
+	/* Call for Phase 2 and propagate ->expmask bits up the tree. */
+	rnp->expmask = 1;
+	rnp_up = rnp;
+	while (rnp_up->parent) {
+		mask = rnp_up->grpmask;
+		rnp_up = rnp_up->parent;
+		if (rnp_up->expmask & mask)
+			break;
+		raw_spin_lock(&rnp_up->lock); /* irqs already off */
+		smp_mb__after_unlock_lock();
+		rnp_up->expmask |= mask;
+		raw_spin_unlock(&rnp_up->lock); /* irqs still off */
+	}
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Snapshot the tasks blocking the newly started preemptible-RCU expedited
+ * grace period for the specified rcu_node structure, phase 2.  If the
+ * leaf rcu_node structure has its ->expmask field set, check for tasks.
+ * If there are some, clear ->expmask and set ->exp_tasks accordingly,
+ * then initiate RCU priority boosting.  Otherwise, clear ->expmask and
+ * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits,
+ * enabling rcu_read_unlock_special() to do the bit-clearing.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static void
+sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
+	if (!rnp->expmask) {
+		/* Phase 1 didn't do anything, so Phase 2 doesn't either. */
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+
+	/* Phase 1 is over. */
+	rnp->expmask = 0;
+
+	/*
+	 * If there are still blocked tasks, set up ->exp_tasks so that
+	 * rcu_read_unlock_special() will wake us and then boost them.
+	 */
+	if (rcu_preempt_has_tasks(rnp)) {
 		rnp->exp_tasks = rnp->blkd_tasks.next;
 		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
+		return;
 	}
+
+	/* No longer any blocked tasks, so undo bit setting. */
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	rcu_report_exp_rnp(rsp, rnp, false);
 }
 
 /**
@@ -699,7 +755,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	unsigned long flags;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_preempt_state;
 	unsigned long snap;
@@ -750,19 +805,16 @@ void synchronize_rcu_expedited(void)
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
-	/* Initialize ->expmask for all non-leaf rcu_node structures. */
-	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
-		rnp->expmask = rnp->qsmaskinit;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	}
-
-	/* Snapshot current state of ->blkd_tasks lists. */
+	/*
+	 * Snapshot current state of ->blkd_tasks lists into ->expmask.
+	 * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special()
+	 * to start clearing them.  Doing this in one phase leads to
+	 * strange races between setting and clearing bits, so just say "no"!
+	 */
+	rcu_for_each_leaf_node(rsp, rnp)
+		sync_rcu_preempt_exp_init1(rsp, rnp);
 	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init(rsp, rnp);
-	if (NUM_RCU_NODES > 1)
-		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
+		sync_rcu_preempt_exp_init2(rsp, rnp);
 
 	put_online_cpus();
 
-- 
cgit v1.2.3


From cc99a310caf811aebbd0986f433d824e4a5e7ce5 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 23 Feb 2015 08:59:29 -0800
Subject: rcu: Move rcu_report_unblock_qs_rnp() to common code

The rcu_report_unblock_qs_rnp() function is invoked when the
last task blocking the current grace period exits its outermost
RCU read-side critical section.  Previously, this was called only
from rcu_read_unlock_special(), and was therefore defined only when
CONFIG_RCU_PREEMPT=y.  However, this function will be invoked even when
CONFIG_RCU_PREEMPT=n once CPU-hotplug operations are processed only at
the beginnings of RCU grace periods.  The reason for this change is that
the last task on a given leaf rcu_node structure's ->blkd_tasks list
might well exit its RCU read-side critical section between the time that
recent CPU-hotplug operations were applied and when the new grace period
was initialized.  This situation could result in RCU waiting forever on
that leaf rcu_node structure, because if all that structure's CPUs were
already offline, there would be no quiescent-state events to drive that
structure's part of the grace period.

This commit therefore moves rcu_report_unblock_qs_rnp() to common code
that is built unconditionally so that the quiescent-state-forcing code
can clean up after this situation, avoiding the grace-period stall.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/rcu/tree_plugin.h | 40 ++--------------------------------------
 2 files changed, 41 insertions(+), 38 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a7151d26b940..5b5cb1ff73ed 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2126,6 +2126,45 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 	rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
 }
 
+/*
+ * Record a quiescent state for all tasks that were previously queued
+ * on the specified rcu_node structure and that were blocking the current
+ * RCU grace period.  The caller must hold the specified rnp->lock with
+ * irqs disabled, and this lock is released upon return, but irqs remain
+ * disabled.
+ */
+static void __maybe_unused rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+				      struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
+{
+	unsigned long mask;
+	struct rcu_node *rnp_p;
+
+	WARN_ON_ONCE(rsp == &rcu_bh_state || rsp == &rcu_sched_state);
+	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;  /* Still need more quiescent states! */
+	}
+
+	rnp_p = rnp->parent;
+	if (rnp_p == NULL) {
+		/*
+		 * Either there is only one rcu_node in the tree,
+		 * or tasks were kicked up to root rcu_node due to
+		 * CPUs going offline.
+		 */
+		rcu_report_qs_rsp(rsp, flags);
+		return;
+	}
+
+	/* Report up the rest of the hierarchy. */
+	mask = rnp->grpmask;
+	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
+	rcu_report_qs_rnp(mask, rsp, rnp_p, flags);
+}
+
 /*
  * Record a quiescent state for the specified CPU to that CPU's rcu_data
  * structure.  This must be either called from the specified CPU, or
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a22721547442..ec6c2efb28cd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -232,43 +232,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return rnp->gp_tasks != NULL;
 }
 
-/*
- * Record a quiescent state for all tasks that were previously queued
- * on the specified rcu_node structure and that were blocking the current
- * RCU grace period.  The caller must hold the specified rnp->lock with
- * irqs disabled, and this lock is released upon return, but irqs remain
- * disabled.
- */
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
-	__releases(rnp->lock)
-{
-	unsigned long mask;
-	struct rcu_node *rnp_p;
-
-	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;  /* Still need more quiescent states! */
-	}
-
-	rnp_p = rnp->parent;
-	if (rnp_p == NULL) {
-		/*
-		 * Either there is only one rcu_node in the tree,
-		 * or tasks were kicked up to root rcu_node due to
-		 * CPUs going offline.
-		 */
-		rcu_report_qs_rsp(&rcu_preempt_state, flags);
-		return;
-	}
-
-	/* Report up the rest of the hierarchy. */
-	mask = rnp->grpmask;
-	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
-	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
-}
-
 /*
  * Advance a ->blkd_tasks-list pointer to the next entry, instead
  * returning NULL if at the end of the list.
@@ -399,7 +362,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(rnp, flags);
+			rcu_report_unblock_qs_rnp(&rcu_preempt_state,
+						  rnp, flags);
 		} else {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
-- 
cgit v1.2.3


From 0aa04b055e71bd3b8040dd71a126126c66b6f01e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 23 Jan 2015 21:52:37 -0800
Subject: rcu: Process offlining and onlining only at grace-period start

Races between CPU hotplug and grace periods can be difficult to resolve,
so the ->onoff_mutex is used to exclude the two events.  Unfortunately,
this means that it is impossible for an outgoing CPU to perform the
last bits of its offlining from its last pass through the idle loop,
because sleeplocks cannot be acquired in that context.

This commit avoids these problems by buffering online and offline events
in a new ->qsmaskinitnext field in the leaf rcu_node structures.  When a
grace period starts, the events accumulated in this mask are applied to
the ->qsmaskinit field, and, if needed, up the rcu_node tree.  The special
case of all CPUs corresponding to a given leaf rcu_node structure being
offline while there are still elements in that structure's ->blkd_tasks
list is handled using a new ->wait_blkd_tasks field.  In this case,
propagating the offline bits up the tree is deferred until the beginning
of the grace period after all of the tasks have exited their RCU read-side
critical sections and removed themselves from the list, at which point
the ->wait_blkd_tasks flag is cleared.  If one of that leaf rcu_node
structure's CPUs comes back online before the list empties, then the
->wait_blkd_tasks flag is simply cleared.

This of course means that RCU's notion of which CPUs are offline can be
out of date.  This is OK because RCU need only wait on CPUs that were
online at the time that the grace period started.  In addition, RCU's
force-quiescent-state actions will handle the case where a CPU goes
offline after the grace period starts.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 154 +++++++++++++++++++++++++++++++++++++----------
 kernel/rcu/tree.h        |   9 +++
 kernel/rcu/tree_plugin.h |  22 ++-----
 kernel/rcu/tree_trace.c  |   4 +-
 4 files changed, 136 insertions(+), 53 deletions(-)

(limited to 'kernel/rcu/tree_plugin.h')

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5b5cb1ff73ed..f0f4d3510d24 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -152,6 +152,8 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
+static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
+static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
@@ -178,6 +180,17 @@ module_param(gp_init_delay, int, 0644);
 unsigned long rcutorture_testseq;
 unsigned long rcutorture_vernum;
 
+/*
+ * Compute the mask of online CPUs for the specified rcu_node structure.
+ * This will not be stable unless the rcu_node structure's ->lock is
+ * held, but the bit corresponding to the current CPU will be stable
+ * in most contexts.
+ */
+unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
+{
+	return ACCESS_ONCE(rnp->qsmaskinitnext);
+}
+
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -960,7 +973,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	preempt_disable();
 	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
-	ret = (rdp->grpmask & rnp->qsmaskinit) ||
+	ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
 	      !rcu_scheduler_fully_active;
 	preempt_enable();
 	return ret;
@@ -1710,6 +1723,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static int rcu_gp_init(struct rcu_state *rsp)
 {
+	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1744,6 +1758,55 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	mutex_lock(&rsp->onoff_mutex);
 	smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
 
+	/*
+	 * Apply per-leaf buffered online and offline operations to the
+	 * rcu_node tree.  Note that this new grace period need not wait
+	 * for subsequent online CPUs, and that quiescent-state forcing
+	 * will handle subsequent offline CPUs.
+	 */
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
+		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
+		    !rnp->wait_blkd_tasks) {
+			/* Nothing to do on this leaf rcu_node structure. */
+			raw_spin_unlock_irq(&rnp->lock);
+			continue;
+		}
+
+		/* Record old state, apply changes to ->qsmaskinit field. */
+		oldmask = rnp->qsmaskinit;
+		rnp->qsmaskinit = rnp->qsmaskinitnext;
+
+		/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
+		if (!oldmask != !rnp->qsmaskinit) {
+			if (!oldmask) /* First online CPU for this rcu_node. */
+				rcu_init_new_rnp(rnp);
+			else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
+				rnp->wait_blkd_tasks = true;
+			else /* Last offline CPU and can propagate. */
+				rcu_cleanup_dead_rnp(rnp);
+		}
+
+		/*
+		 * If all waited-on tasks from prior grace period are
+		 * done, and if all this rcu_node structure's CPUs are
+		 * still offline, propagate up the rcu_node tree and
+		 * clear ->wait_blkd_tasks.  Otherwise, if one of this
+		 * rcu_node structure's CPUs has since come back online,
+		 * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
+		 * checks for this, so just call it unconditionally).
+		 */
+		if (rnp->wait_blkd_tasks &&
+		    (!rcu_preempt_has_tasks(rnp) ||
+		     rnp->qsmaskinit)) {
+			rnp->wait_blkd_tasks = false;
+			rcu_cleanup_dead_rnp(rnp);
+		}
+
+		raw_spin_unlock_irq(&rnp->lock);
+	}
+
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
 	 * structures for all currently online CPUs in breadth-first order,
@@ -2133,7 +2196,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
  * irqs disabled, and this lock is released upon return, but irqs remain
  * disabled.
  */
-static void __maybe_unused rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 				      struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
@@ -2409,6 +2472,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
 		smp_mb__after_unlock_lock(); /* GP memory ordering. */
 		rnp->qsmaskinit &= ~mask;
+		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			return;
@@ -2427,6 +2491,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
+	unsigned long mask;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
@@ -2443,12 +2508,12 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+	mask = rdp->grpmask;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
-	rnp->qsmaskinit &= ~rdp->grpmask;
-	if (rnp->qsmaskinit == 0 && !rcu_preempt_has_tasks(rnp))
-		rcu_cleanup_dead_rnp(rnp);
-	rcu_report_qs_rnp(rdp->grpmask, rsp, rnp, flags); /* Rlses rnp->lock. */
+	rnp->qsmaskinitnext &= ~mask;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+
 	WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
 		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
 		  cpu, rdp->qlen, rdp->nxtlist);
@@ -2654,12 +2719,21 @@ static void force_qs_rnp(struct rcu_state *rsp,
 			}
 		}
 		if (mask != 0) {
-
-			/* rcu_report_qs_rnp() releases rnp->lock. */
+			/* Idle/offline CPUs, report. */
 			rcu_report_qs_rnp(mask, rsp, rnp, flags);
-			continue;
+		} else if (rnp->parent &&
+			 list_empty(&rnp->blkd_tasks) &&
+			 !rnp->qsmask &&
+			 (rnp->parent->qsmask & rnp->grpmask)) {
+			/*
+			 * Race between grace-period initialization and task
+			 * existing RCU read-side critical section, report.
+			 */
+			rcu_report_unblock_qs_rnp(rsp, rnp, flags);
+		} else {
+			/* Nothing to do here, so just drop the lock. */
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 }
 
@@ -3568,6 +3642,28 @@ void rcu_barrier_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
+/*
+ * Propagate ->qsinitmask bits up the rcu_node tree to account for the
+ * first CPU in a given leaf rcu_node structure coming online.  The caller
+ * must hold the corresponding leaf rcu_node ->lock with interrrupts
+ * disabled.
+ */
+static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
+{
+	long mask;
+	struct rcu_node *rnp = rnp_leaf;
+
+	for (;;) {
+		mask = rnp->grpmask;
+		rnp = rnp->parent;
+		if (rnp == NULL)
+			return;
+		raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */
+		rnp->qsmaskinit |= mask;
+		raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
+	}
+}
+
 /*
  * Do boot-time initialization of a CPU's per-CPU RCU data.
  */
@@ -3620,31 +3716,23 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
-	/* Add CPU to rcu_node bitmasks. */
+	/*
+	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
+	 * propagation up the rcu_node tree will happen at the beginning
+	 * of the next grace period.
+	 */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
-	do {
-		/* Exclude any attempts to start a new GP on small systems. */
-		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
-		rnp->qsmaskinit |= mask;
-		mask = rnp->grpmask;
-		if (rnp == rdp->mynode) {
-			/*
-			 * If there is a grace period in progress, we will
-			 * set up to wait for it next time we run the
-			 * RCU core code.
-			 */
-			rdp->gpnum = rnp->completed;
-			rdp->completed = rnp->completed;
-			rdp->passed_quiesce = 0;
-			rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
-			rdp->qs_pending = 0;
-			trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
-		}
-		raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
-		rnp = rnp->parent;
-	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
-	local_irq_restore(flags);
+	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
+	rnp->qsmaskinitnext |= mask;
+	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
+	rdp->completed = rnp->completed;
+	rdp->passed_quiesce = false;
+	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->qs_pending = false;
+	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	mutex_unlock(&rsp->onoff_mutex);
 }
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 119de399eb2f..aa42562ff5b2 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -141,12 +141,20 @@ struct rcu_node {
 				/*  complete (only for PREEMPT_RCU). */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
+				/*  Initialized from ->qsmaskinitnext at the */
+				/*  beginning of each grace period. */
+	unsigned long qsmaskinitnext;
+				/* Online CPUs for next grace period. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
 	int	grplo;		/* lowest-numbered CPU or group here. */
 	int	grphi;		/* highest-numbered CPU or group here. */
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
+	bool	wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
+				/*  exit RCU read-side critical sections */
+				/*  before propagating offline up the */
+				/*  rcu_node tree? */
 	struct rcu_node *parent;
 	struct list_head blkd_tasks;
 				/* Tasks blocked in RCU read-side critical */
@@ -559,6 +567,7 @@ static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(void);
 static void rcu_prepare_for_idle(void);
 static void rcu_idle_count_callbacks_posted(void);
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void print_cpu_stall_info_begin(void);
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index ec6c2efb28cd..d45e961515c1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -180,7 +180,7 @@ static void rcu_preempt_note_context_switch(void)
 		 * But first, note that the current CPU must still be
 		 * on line!
 		 */
-		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
+		WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0);
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
 		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
 			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
@@ -263,7 +263,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  */
 void rcu_read_unlock_special(struct task_struct *t)
 {
-	bool empty;
 	bool empty_exp;
 	bool empty_norm;
 	bool empty_exp_now;
@@ -319,7 +318,6 @@ void rcu_read_unlock_special(struct task_struct *t)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
-		empty = !rcu_preempt_has_tasks(rnp);
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -339,14 +337,6 @@ void rcu_read_unlock_special(struct task_struct *t)
 		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
-		/*
-		 * If this was the last task on the list, go see if we
-		 * need to propagate ->qsmaskinit bit clearing up the
-		 * rcu_node tree.
-		 */
-		if (!empty && !rcu_preempt_has_tasks(rnp))
-			rcu_cleanup_dead_rnp(rnp);
-
 		/*
 		 * If this was the last task on the current list, and if
 		 * we aren't waiting on any CPUs, report the quiescent state.
@@ -868,8 +858,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return 0;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Because there is no preemptible RCU, there can be no readers blocked.
  */
@@ -878,8 +866,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
 	return false;
 }
 
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
@@ -1179,7 +1165,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
  * Returns zero if all is well, a negated errno otherwise.
  */
 static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
-						 struct rcu_node *rnp)
+				       struct rcu_node *rnp)
 {
 	int rnp_index = rnp - &rsp->node[0];
 	unsigned long flags;
@@ -1189,7 +1175,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (&rcu_preempt_state != rsp)
 		return 0;
 
-	if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0)
+	if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
 		return 0;
 
 	rsp->boost = 1;
@@ -1282,7 +1268,7 @@ static void rcu_cpu_kthread(unsigned int cpu)
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 	struct task_struct *t = rnp->boost_kthread_task;
-	unsigned long mask = rnp->qsmaskinit;
+	unsigned long mask = rcu_rnp_online_cpus(rnp);
 	cpumask_var_t cm;
 	int cpu;
 
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index fbb6240509ea..f92361efd0f5 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -283,8 +283,8 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d    ",
-			   rnp->qsmask, rnp->qsmaskinit,
+		seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d    ",
+			   rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext,
 			   ".G"[rnp->gp_tasks != NULL],
 			   ".E"[rnp->exp_tasks != NULL],
 			   ".T"[!list_empty(&rnp->blkd_tasks)],
-- 
cgit v1.2.3