[PATCH tip/core/rcu 0/12]

[PATCH tip/core/rcu 0/12]

[Paul E. McKenney]

Hello!

This series provides yet more cleanups and fixes for the RCU flavor
consolidation effort:

1.	Enable elimination of Tree-RCU softirq processing, courtesy of
	Sebastian Andrzej Siewior.  (More along the lines of real-time
	than consolidation, but placed here to avoid conflicts.)

2.	Check for wakeup-safe conditions in rcu_read_unlock_special().

3.	Only do rcu_read_unlock_special() wakeups if expedited.

4.	Allow rcu_read_unlock_special() to raise_softirq() if in_irq().

5.	Use irq_work to get scheduler's attention in clean context.

6.	Inline invoke_rcu_callbacks() into its sole remaining caller.

7.	Avoid self-IPI in sync_rcu_exp_select_node_cpus().

8.	Avoid self-IPI in sync_sched_exp_online_cleanup().

9.	Add assertion to check if in an interrupt, courtesy of Joel
	Fernandes.

10.	Add checks for dynticks counters in rcu_is_cpu_rrupt_from_idle(),
	courtesy of Joel Fernandes.

11.	Rename rcu_data's ->deferred_qs to ->exp_deferred_qs.

12.	Remove unused rdp local from synchronize_rcu_expedited(),
	courtesy of Jiang Biao.

							Thanx, Paul

------------------------------------------------------------------------

 Documentation/admin-guide/kernel-parameters.txt |    6 
 include/linux/lockdep.h                         |    7 
 include/linux/sched.h                           |    2 
 kernel/rcu/tree.c                               |  179 +++++++++++++++++----
 kernel/rcu/tree.h                               |    6 
 kernel/rcu/tree_exp.h                           |   50 ++++-
 kernel/rcu/tree_plugin.h                        |  201 +++++++-----------------
 7 files changed, 267 insertions(+), 184 deletions(-)

[PATCH tip/core/rcu 01/12] rcu: Enable elimination of Tree-RCU softirq processing

[Paul E. McKenney]

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Some workloads need to change kthread priority for RCU core processing
without affecting other softirq work.  This commit therefore introduces
the rcutree.use_softirq kernel boot parameter, which moves the RCU core
work from softirq to a per-CPU SCHED_OTHER kthread named rcuc.  Use of
SCHED_OTHER approach avoids the scalability problems that appeared
with the earlier attempt to move RCU core processing to from softirq
to kthreads.  That said, kernels built with RCU_BOOST=y will run the
rcuc kthreads at the RCU-boosting priority.

Note that rcutree.use_softirq=0 must be specified to move RCU core
processing to the rcuc kthreads: rcutree.use_softirq=1 is the default.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[ paulmck: Adjust for invoke_rcu_callbacks() only ever being invoked
  from RCU core processing, in contrast to softirq->rcuc transition
  in old mainline RCU priority boosting. ]
[ paulmck: Avoid wakeups when scheduler might have invoked rcu_read_unlock()
  while holding rq or pi locks, also possibly fixing a pre-existing latent
  bug involving raise_softirq()-induced wakeups. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 .../admin-guide/kernel-parameters.txt         |   6 +
 kernel/rcu/tree.c                             | 138 ++++++++++++++++--
 kernel/rcu/tree.h                             |   2 +-
 kernel/rcu/tree_plugin.h                      | 134 ++---------------
 4 files changed, 146 insertions(+), 134 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 138f6664b2e2..b96fd15c7316 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3752,6 +3752,12 @@
 			the propagation of recent CPU-hotplug changes up
 			the rcu_node combining tree.
 
+	rcutree.use_softirq=	[KNL]
+			If set to zero, move all RCU_SOFTIRQ processing to
+			per-CPU rcuc kthreads.  Defaults to a non-zero
+			value, meaning that RCU_SOFTIRQ is used by default.
+			Specify rcutree.use_softirq=0 to use rcuc kthreads.
+
 	rcutree.rcu_fanout_exact= [KNL]
 			Disable autobalancing of the rcu_node combining
 			tree.  This is used by rcutorture, and might
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 980ca3ca643f..8e290163505a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -51,6 +51,12 @@
 #include <linux/tick.h>
 #include <linux/sysrq.h>
 #include <linux/kprobes.h>
+#include <linux/gfp.h>
+#include <linux/oom.h>
+#include <linux/smpboot.h>
+#include <linux/jiffies.h>
+#include <linux/sched/isolation.h>
+#include "../time/tick-internal.h"
 
 #include "tree.h"
 #include "rcu.h"
@@ -92,6 +98,9 @@ struct rcu_state rcu_state = {
 /* Dump rcu_node combining tree at boot to verify correct setup. */
 static bool dump_tree;
 module_param(dump_tree, bool, 0444);
+/* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
+static bool use_softirq = 1;
+module_param(use_softirq, bool, 0444);
 /* Control rcu_node-tree auto-balancing at boot time. */
 static bool rcu_fanout_exact;
 module_param(rcu_fanout_exact, bool, 0444);
@@ -2253,7 +2262,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /* Perform RCU core processing work for the current CPU.  */
-static __latent_entropy void rcu_core(struct softirq_action *unused)
+static __latent_entropy void rcu_core(void)
 {
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
@@ -2295,29 +2304,131 @@ static __latent_entropy void rcu_core(struct softirq_action *unused)
 	trace_rcu_utilization(TPS("End RCU core"));
 }
 
+static void rcu_core_si(struct softirq_action *h)
+{
+	rcu_core();
+}
+
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+	/*
+	 * If the thread is yielding, only wake it when this
+	 * is invoked from idle
+	 */
+	if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
+		wake_up_process(t);
+}
+
+static void invoke_rcu_core_kthread(void)
+{
+	struct task_struct *t;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
+	t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
+	if (t != NULL && t != current)
+		rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
+	local_irq_restore(flags);
+}
+
 /*
- * Schedule RCU callback invocation.  If the running implementation of RCU
- * does not support RCU priority boosting, just do a direct call, otherwise
- * wake up the per-CPU kernel kthread.  Note that because we are running
- * on the current CPU with softirqs disabled, the rcu_cpu_kthread_task
- * cannot disappear out from under us.
+ * Do RCU callback invocation.  Not that if we are running !use_softirq,
+ * we are already in the rcuc kthread.  If callbacks are offloaded, then
+ * ->cblist is always empty, so we don't get here.  Therefore, we only
+ * ever need to check for the scheduler being operational (some callbacks
+ * do wakeups, so we do need the scheduler).
  */
 static void invoke_rcu_callbacks(struct rcu_data *rdp)
 {
 	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
 		return;
-	if (likely(!rcu_state.boost)) {
-		rcu_do_batch(rdp);
-		return;
-	}
-	invoke_rcu_callbacks_kthread();
+	rcu_do_batch(rdp);
 }
 
+/*
+ * Wake up this CPU's rcuc kthread to do RCU core processing.
+ */
 static void invoke_rcu_core(void)
 {
-	if (cpu_online(smp_processor_id()))
+	if (!cpu_online(smp_processor_id()))
+		return;
+	if (use_softirq)
 		raise_softirq(RCU_SOFTIRQ);
+	else
+		invoke_rcu_core_kthread();
+}
+
+static void rcu_cpu_kthread_park(unsigned int cpu)
+{
+	per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+}
+
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
+{
+	return __this_cpu_read(rcu_data.rcu_cpu_has_work);
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces
+ * the RCU softirq used in configurations of RCU that do not support RCU
+ * priority boosting.
+ */
+static void rcu_cpu_kthread(unsigned int cpu)
+{
+	unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
+	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
+	int spincnt;
+
+	for (spincnt = 0; spincnt < 10; spincnt++) {
+		trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
+		local_bh_disable();
+		*statusp = RCU_KTHREAD_RUNNING;
+		local_irq_disable();
+		work = *workp;
+		*workp = 0;
+		local_irq_enable();
+		if (work)
+			rcu_core();
+		local_bh_enable();
+		if (*workp == 0) {
+			trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
+			*statusp = RCU_KTHREAD_WAITING;
+			return;
+		}
+	}
+	*statusp = RCU_KTHREAD_YIELDING;
+	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
+	schedule_timeout_interruptible(2);
+	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
+	*statusp = RCU_KTHREAD_WAITING;
+}
+
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+	.store			= &rcu_data.rcu_cpu_kthread_task,
+	.thread_should_run	= rcu_cpu_kthread_should_run,
+	.thread_fn		= rcu_cpu_kthread,
+	.thread_comm		= "rcuc/%u",
+	.setup			= rcu_cpu_kthread_setup,
+	.park			= rcu_cpu_kthread_park,
+};
+
+/*
+ * Spawn per-CPU RCU core processing kthreads.
+ */
+static int __init rcu_spawn_core_kthreads(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
+	if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq)
+		return 0;
+	WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec),
+		  "%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__);
+	return 0;
 }
+early_initcall(rcu_spawn_core_kthreads);
 
 /*
  * Handle any core-RCU processing required by a call_rcu() invocation.
@@ -3355,7 +3466,8 @@ void __init rcu_init(void)
 	rcu_init_one();
 	if (dump_tree)
 		rcu_dump_rcu_node_tree();
-	open_softirq(RCU_SOFTIRQ, rcu_core);
+	if (use_softirq)
+		open_softirq(RCU_SOFTIRQ, rcu_core_si);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index e253d11af3c4..a1a72a1ecb02 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -407,8 +407,8 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
-static void invoke_rcu_callbacks_kthread(void);
 static bool rcu_is_callbacks_kthread(void);
+static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void __init rcu_spawn_boost_kthreads(void);
 static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1102765f91fd..21611862e083 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -11,29 +11,7 @@
  *	   Paul E. McKenney <paulmck@linux.ibm.com>
  */
 
-#include <linux/delay.h>
-#include <linux/gfp.h>
-#include <linux/oom.h>
-#include <linux/sched/debug.h>
-#include <linux/smpboot.h>
-#include <linux/sched/isolation.h>
-#include <uapi/linux/sched/types.h>
-#include "../time/tick-internal.h"
-
-#ifdef CONFIG_RCU_BOOST
 #include "../locking/rtmutex_common.h"
-#else /* #ifdef CONFIG_RCU_BOOST */
-
-/*
- * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
- * all uses are in dead code.  Provide a definition to keep the compiler
- * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
- * This probably needs to be excluded from -rt builds.
- */
-#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
-#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1)
-
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@@ -94,6 +72,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay);
 	if (gp_cleanup_delay)
 		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay);
+	if (!use_softirq)
+		pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n");
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG))
 		pr_info("\tRCU debug extended QS entry/exit.\n");
 	rcupdate_announce_bootup_oddness();
@@ -627,7 +607,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	if (preempt_bh_were_disabled || irqs_were_disabled) {
 		WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
 		/* Need to defer quiescent state until everything is enabled. */
-		if (irqs_were_disabled) {
+		if (irqs_were_disabled && use_softirq) {
 			/* Enabling irqs does not reschedule, so... */
 			raise_softirq_irqoff(RCU_SOFTIRQ);
 		} else {
@@ -944,18 +924,21 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+/*
+ * If boosting, set rcuc kthreads to realtime priority.
+ */
+static void rcu_cpu_kthread_setup(unsigned int cpu)
+{
 #ifdef CONFIG_RCU_BOOST
+	struct sched_param sp;
 
-static void rcu_wake_cond(struct task_struct *t, int status)
-{
-	/*
-	 * If the thread is yielding, only wake it when this
-	 * is invoked from idle
-	 */
-	if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
-		wake_up_process(t);
+	sp.sched_priority = kthread_prio;
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+#endif /* #ifdef CONFIG_RCU_BOOST */
 }
 
+#ifdef CONFIG_RCU_BOOST
+
 /*
  * Carry out RCU priority boosting on the task indicated by ->exp_tasks
  * or ->boost_tasks, advancing the pointer to the next task in the
@@ -1090,23 +1073,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	}
 }
 
-/*
- * Wake up the per-CPU kthread to invoke RCU callbacks.
- */
-static void invoke_rcu_callbacks_kthread(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
-	if (__this_cpu_read(rcu_data.rcu_cpu_kthread_task) != NULL &&
-	    current != __this_cpu_read(rcu_data.rcu_cpu_kthread_task)) {
-		rcu_wake_cond(__this_cpu_read(rcu_data.rcu_cpu_kthread_task),
-			      __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
-	}
-	local_irq_restore(flags);
-}
-
 /*
  * Is the current CPU running the RCU-callbacks kthread?
  * Caller must have preemption disabled.
@@ -1160,59 +1126,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	return 0;
 }
 
-static void rcu_cpu_kthread_setup(unsigned int cpu)
-{
-	struct sched_param sp;
-
-	sp.sched_priority = kthread_prio;
-	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-}
-
-static void rcu_cpu_kthread_park(unsigned int cpu)
-{
-	per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
-}
-
-static int rcu_cpu_kthread_should_run(unsigned int cpu)
-{
-	return __this_cpu_read(rcu_data.rcu_cpu_has_work);
-}
-
-/*
- * Per-CPU kernel thread that invokes RCU callbacks.  This replaces
- * the RCU softirq used in configurations of RCU that do not support RCU
- * priority boosting.
- */
-static void rcu_cpu_kthread(unsigned int cpu)
-{
-	unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
-	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
-	int spincnt;
-
-	for (spincnt = 0; spincnt < 10; spincnt++) {
-		trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
-		local_bh_disable();
-		*statusp = RCU_KTHREAD_RUNNING;
-		local_irq_disable();
-		work = *workp;
-		*workp = 0;
-		local_irq_enable();
-		if (work)
-			rcu_do_batch(this_cpu_ptr(&rcu_data));
-		local_bh_enable();
-		if (*workp == 0) {
-			trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
-			*statusp = RCU_KTHREAD_WAITING;
-			return;
-		}
-	}
-	*statusp = RCU_KTHREAD_YIELDING;
-	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
-	schedule_timeout_interruptible(2);
-	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
-	*statusp = RCU_KTHREAD_WAITING;
-}
-
 /*
  * Set the per-rcu_node kthread's affinity to cover all CPUs that are
  * served by the rcu_node in question.  The CPU hotplug lock is still
@@ -1243,27 +1156,13 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 	free_cpumask_var(cm);
 }
 
-static struct smp_hotplug_thread rcu_cpu_thread_spec = {
-	.store			= &rcu_data.rcu_cpu_kthread_task,
-	.thread_should_run	= rcu_cpu_kthread_should_run,
-	.thread_fn		= rcu_cpu_kthread,
-	.thread_comm		= "rcuc/%u",
-	.setup			= rcu_cpu_kthread_setup,
-	.park			= rcu_cpu_kthread_park,
-};
-
 /*
  * Spawn boost kthreads -- called as soon as the scheduler is running.
  */
 static void __init rcu_spawn_boost_kthreads(void)
 {
 	struct rcu_node *rnp;
-	int cpu;
 
-	for_each_possible_cpu(cpu)
-		per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
-	if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
-		return;
 	rcu_for_each_leaf_node(rnp)
 		(void)rcu_spawn_one_boost_kthread(rnp);
 }
@@ -1286,11 +1185,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
-static void invoke_rcu_callbacks_kthread(void)
-{
-	WARN_ON_ONCE(1);
-}
-
 static bool rcu_is_callbacks_kthread(void)
 {
 	return false;
-- 
2.17.1

[PATCH tip/core/rcu 02/12] rcu: Check for wakeup-safe conditions in rcu_read_unlock_special()

[Paul E. McKenney]

When RCU core processing is offloaded from RCU_SOFTIRQ to the rcuc
kthreads, a full and unconditional wakeup is required to initiate RCU
core processing.  In contrast, when RCU core processing is carried
out by RCU_SOFTIRQ, a raise_softirq() suffices.  Of course, there are
situations where raise_softirq() does a full wakeup, but these do not
occur with normal usage of rcu_read_unlock().

The reason that full wakeups can be problematic is that the scheduler
sometimes invokes rcu_read_unlock() with its pi or rq locks held,
which can of course result in deadlock in CONFIG_PREEMPT=y kernels when
rcu_read_unlock() invokes the scheduler.  Scheduler invocations can happen
in the following situations: (1) The just-ended reader has been subjected
to RCU priority boosting, in which case rcu_read_unlock() must deboost,
(2) Interrupts were disabled across the call to rcu_read_unlock(), so
the quiescent state must be deferred, requiring a wakeup of the rcuc
kthread corresponding to the current CPU.

Now, the scheduler may hold one of its locks across rcu_read_unlock()
only if preemption has been disabled across the entire RCU read-side
critical section, which in the days prior to RCU flavor consolidation
meant that rcu_read_unlock() never needed to do wakeups.  However, this
is no longer the case for any but the first rcu_read_unlock() following a
condition (e.g., preempted RCU reader) requiring special rcu_read_unlock()
attention.  For example, an RCU read-side critical section might be
preempted, but preemption might be disabled across the rcu_read_unlock().
The rcu_read_unlock() must defer the quiescent state, and therefore
leaves the task queued on its leaf rcu_node structure.  If a scheduler
interrupt occurs, the scheduler might well invoke rcu_read_unlock() with
one of its locks held.  However, the preempted task is still queued, so
rcu_read_unlock() will attempt to defer the quiescent state once more.
When RCU core processing is carried out by RCU_SOFTIRQ, this works just
fine: The raise_softirq() function simply sets a bit in a per-CPU mask
and the RCU core processing will be undertaken upon return from interrupt.

Not so when RCU core processing is carried out by the rcuc kthread: In this
case, the required wakeup can result in deadlock.

The initial solution to this problem was to use set_tsk_need_resched() and
set_preempt_need_resched() to force a future context switch, which allows
rcu_preempt_note_context_switch() to report the deferred quiescent state
to RCU's core processing.  Unfortunately for expedited grace periods,
there can be a significant delay between the call for a context switch
and the actual context switch.

This commit therefore introduces a ->deferred_qs flag to the task_struct
structure's rcu_special structure.  This flag is initially false, and
is set to true by the first call to rcu_read_unlock() requiring special
attention, then finally reset back to false when the quiescent state is
finally reported.  Then rcu_read_unlock() attempts full wakeups only when
->deferred_qs is false, that is, on the first rcu_read_unlock() requiring
special attention.  Note that a chain of RCU readers linked by some other
sort of reader may find that a later rcu_read_unlock() is once again able
to do a full wakeup, courtesy of an intervening preemption:

	rcu_read_lock();
	/* preempted */
	local_irq_disable();
	rcu_read_unlock(); /* Can do full wakeup, sets ->deferred_qs. */
	rcu_read_lock();
	local_irq_enable();
	preempt_disable()
	rcu_read_unlock(); /* Cannot do full wakeup, ->deferred_qs set. */
	rcu_read_lock();
	preempt_enable();
	/* preempted, >deferred_qs reset. */
	local_irq_disable();
	rcu_read_unlock(); /* Can again do full wakeup, sets ->deferred_qs. */

Such linked RCU readers do not yet seem to appear in the Linux kernel, and
it is probably best if they don't.  However, RCU needs to handle them, and
some variations on this theme could make even raise_softirq() unsafe due to
the possibility of its doing a full wakeup.  This commit therefore also
avoids invoking raise_softirq() when the ->deferred_qs set flag is set.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/sched.h    |  2 +-
 kernel/rcu/tree_plugin.h | 19 ++++++++++++++-----
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 11837410690f..942a44c1b8eb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -565,7 +565,7 @@ union rcu_special {
 		u8			blocked;
 		u8			need_qs;
 		u8			exp_hint; /* Hint for performance. */
-		u8			pad; /* No garbage from compiler! */
+		u8			deferred_qs;
 	} b; /* Bits. */
 	u32 s; /* Set of bits. */
 };
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 21611862e083..75110ea75d01 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -455,6 +455,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		local_irq_restore(flags);
 		return;
 	}
+	t->rcu_read_unlock_special.b.deferred_qs = false;
 	if (special.b.need_qs) {
 		rcu_qs();
 		t->rcu_read_unlock_special.b.need_qs = false;
@@ -605,16 +606,24 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	local_irq_save(flags);
 	irqs_were_disabled = irqs_disabled_flags(flags);
 	if (preempt_bh_were_disabled || irqs_were_disabled) {
-		WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
-		/* Need to defer quiescent state until everything is enabled. */
-		if (irqs_were_disabled && use_softirq) {
-			/* Enabling irqs does not reschedule, so... */
+		t->rcu_read_unlock_special.b.exp_hint = false;
+		// Need to defer quiescent state until everything is enabled.
+		if (irqs_were_disabled && use_softirq &&
+		    (in_irq() || !t->rcu_read_unlock_special.b.deferred_qs)) {
+			// Using softirq, safe to awaken, and we get
+			// no help from enabling irqs, unlike bh/preempt.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
+		} else if (irqs_were_disabled && !use_softirq &&
+			   !t->rcu_read_unlock_special.b.deferred_qs) {
+			// Safe to awaken and we get no help from enabling
+			// irqs, unlike bh/preempt.
+			invoke_rcu_core();
 		} else {
-			/* Enabling BH or preempt does reschedule, so... */
+			// Enabling BH or preempt does reschedule, so...
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 		}
+		t->rcu_read_unlock_special.b.deferred_qs = true;
 		local_irq_restore(flags);
 		return;
 	}
-- 
2.17.1

[PATCH tip/core/rcu 03/12] rcu: Only do rcu_read_unlock_special() wakeups if expedited

[Paul E. McKenney]

Currently, rcu_read_unlock_special() will do wakeups whenever it is safe
to do so.  However, wakeups are expensive, and they are only really
needed when the just-ended RCU read-side critical section is blocking
an expedited grace period (in which case speed is of the essence)
or on a nohz_full CPU (where it might be a good long time before an
interrupt arrives).  This commit therefore checks for these conditions,
and does the expensive wakeups only if doing so would be useful.

Note it can be rather expensive to determine whether or not the current
task (as opposed to the current CPU) is blocking the current expedited
grace period.  Doing so requires traversing the ->blkd_tasks list, which
can be quite long.  This commit therefore cheats:  If the current task
is on a given ->blkd_tasks list, and some task on that list is blocking
the current expedited grace period, the code assumes that the current
task is blocking that expedited grace period.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree_plugin.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 75110ea75d01..d15cdab6aeb4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -606,20 +606,28 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	local_irq_save(flags);
 	irqs_were_disabled = irqs_disabled_flags(flags);
 	if (preempt_bh_were_disabled || irqs_were_disabled) {
+		bool exp;
+		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+		struct rcu_node *rnp = rdp->mynode;
+
 		t->rcu_read_unlock_special.b.exp_hint = false;
+		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
+		      (rdp->grpmask & rnp->expmask) ||
+		      tick_nohz_full_cpu(rdp->cpu);
 		// Need to defer quiescent state until everything is enabled.
-		if (irqs_were_disabled && use_softirq &&
+		if (exp && irqs_were_disabled && use_softirq &&
 		    (in_irq() || !t->rcu_read_unlock_special.b.deferred_qs)) {
 			// Using softirq, safe to awaken, and we get
 			// no help from enabling irqs, unlike bh/preempt.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
-		} else if (irqs_were_disabled && !use_softirq &&
+		} else if (exp && irqs_were_disabled && !use_softirq &&
 			   !t->rcu_read_unlock_special.b.deferred_qs) {
 			// Safe to awaken and we get no help from enabling
 			// irqs, unlike bh/preempt.
 			invoke_rcu_core();
 		} else {
 			// Enabling BH or preempt does reschedule, so...
+			// Also if no expediting or NO_HZ_FULL, slow is OK.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 		}
-- 
2.17.1

[PATCH tip/core/rcu 04/12] rcu: Allow rcu_read_unlock_special() to raise_softirq() if in_irq()

[Paul E. McKenney]

When running in an interrupt handler, raise_softirq() and
raise_softirq_irqoff() have extremely low overhead: They simply set a
bit in a per-CPU mask, which is checked upon exit from that interrupt
handler.  Therefore, if rcu_read_unlock_special() is invoked within an
interrupt handler and RCU_SOFTIRQ is in use, this commit make use of
raise_softirq_irqoff() even if there is no expedited grace period in
flight and even if this is not a nohz_full CPU.

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

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d15cdab6aeb4..e1005f5e8094 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -615,7 +615,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		      (rdp->grpmask & rnp->expmask) ||
 		      tick_nohz_full_cpu(rdp->cpu);
 		// Need to defer quiescent state until everything is enabled.
-		if (exp && irqs_were_disabled && use_softirq &&
+		if ((exp || in_irq()) && irqs_were_disabled && use_softirq &&
 		    (in_irq() || !t->rcu_read_unlock_special.b.deferred_qs)) {
 			// Using softirq, safe to awaken, and we get
 			// no help from enabling irqs, unlike bh/preempt.
-- 
2.17.1

[PATCH tip/core/rcu 05/12] rcu: Use irq_work to get scheduler's attention in clean context

[Paul E. McKenney]

When rcu_read_unlock_special() is invoked with interrupts disabled, is
either not in an interrupt handler or is not using RCU_SOFTIRQ, is not
the first RCU read-side critical section in the chain, and either there
is an expedited grace period in flight or this is a NO_HZ_FULL kernel,
the end of the grace period can be unduly delayed.  The reason for this
is that it is not safe to do wakeups in this situation.

This commit fixes this problem by using the irq_work subsystem to
force a later interrupt handler in a clean environment.  Because
set_tsk_need_resched(current) and set_preempt_need_resched() are
invoked prior to this, the scheduler will force a context switch
upon return from this interrupt (though perhaps at the end of any
interrupted preempt-disable or BH-disable region of code), which will
invoke rcu_note_context_switch() (again in a clean environment), which
will in turn give RCU the chance to report the deferred quiescent state.

Of course, by then this task might be within another RCU read-side
critical section.  But that will be detected at that time and reporting
will be further deferred to the outermost rcu_read_unlock().  See
rcu_preempt_need_deferred_qs() and rcu_preempt_deferred_qs() for more
details on the checking.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree.h        |  2 ++
 kernel/rcu/tree_plugin.h | 20 ++++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a1a72a1ecb02..21d740f0b8dc 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -161,6 +161,8 @@ struct rcu_data {
 					/*  ticks this CPU has handled */
 					/*  during and after the last grace */
 					/* period it is aware of. */
+	struct irq_work defer_qs_iw;	/* Obtain later scheduler attention. */
+	bool defer_qs_iw_pending;	/* Scheduler attention pending? */
 
 	/* 2) batch handling */
 	struct rcu_segcblist cblist;	/* Segmented callback list, with */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e1005f5e8094..58c7853f19e7 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -587,6 +587,17 @@ static void rcu_preempt_deferred_qs(struct task_struct *t)
 		t->rcu_read_lock_nesting += RCU_NEST_BIAS;
 }
 
+/*
+ * Minimal handler to give the scheduler a chance to re-evaluate.
+ */
+static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp)
+{
+	struct rcu_data *rdp;
+
+	rdp = container_of(iwp, struct rcu_data, defer_qs_iw);
+	rdp->defer_qs_iw_pending = false;
+}
+
 /*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
@@ -630,6 +641,15 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			// Also if no expediting or NO_HZ_FULL, slow is OK.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
+			if (IS_ENABLED(CONFIG_IRQ_WORK) &&
+			    !rdp->defer_qs_iw_pending && exp) {
+				// Get scheduler to re-evaluate and call hooks.
+				// If !IRQ_WORK, FQS scan will eventually IPI.
+				init_irq_work(&rdp->defer_qs_iw,
+					      rcu_preempt_deferred_qs_handler);
+				rdp->defer_qs_iw_pending = true;
+				irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
+			}
 		}
 		t->rcu_read_unlock_special.b.deferred_qs = true;
 		local_irq_restore(flags);
-- 
2.17.1

[PATCH tip/core/rcu 06/12] rcu: Inline invoke_rcu_callbacks() into its sole remaining caller

[Paul E. McKenney]

This commit saves a few lines of code by inlining invoke_rcu_callbacks()
into its sole remaining caller.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree.c | 20 +++-----------------
 1 file changed, 3 insertions(+), 17 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8e290163505a..7822a2e1370d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -147,7 +147,6 @@ 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_data *rdp);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
 
@@ -2296,8 +2295,9 @@ static __latent_entropy void rcu_core(void)
 	rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
 
 	/* If there are callbacks ready, invoke them. */
-	if (rcu_segcblist_ready_cbs(&rdp->cblist))
-		invoke_rcu_callbacks(rdp);
+	if (rcu_segcblist_ready_cbs(&rdp->cblist) &&
+	    likely(READ_ONCE(rcu_scheduler_fully_active)))
+		rcu_do_batch(rdp);
 
 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
@@ -2332,20 +2332,6 @@ static void invoke_rcu_core_kthread(void)
 	local_irq_restore(flags);
 }
 
-/*
- * Do RCU callback invocation.  Not that if we are running !use_softirq,
- * we are already in the rcuc kthread.  If callbacks are offloaded, then
- * ->cblist is always empty, so we don't get here.  Therefore, we only
- * ever need to check for the scheduler being operational (some callbacks
- * do wakeups, so we do need the scheduler).
- */
-static void invoke_rcu_callbacks(struct rcu_data *rdp)
-{
-	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
-		return;
-	rcu_do_batch(rdp);
-}
-
 /*
  * Wake up this CPU's rcuc kthread to do RCU core processing.
  */
-- 
2.17.1

[PATCH tip/core/rcu 07/12] rcu: Avoid self-IPI in sync_rcu_exp_select_node_cpus()

[Paul E. McKenney]

Although sync_rcu_exp_select_node_cpus() treats the current CPU as being
in a quiescent state, it might well migrate to some other CPU before
reaching the smp_call_function_single(), which could then result in an
unnecessary simulated self-IPI.  This commit therefore instead simply
refuses to invoke smp_call_function_single() on the current CPU, which
causes the later rcu_report_exp_cpu_mult() to report this CPU's quiescent
state with less overhead.

This also reduces the rcu_exp_handler() function's state space by removing
the direct call that this smp_call_function_single() uses to emulate the
requested self-IPI.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
[ paulmck: Use get_cpu() instead of preempt_disable() per Joel Fernandes. ]
---
 kernel/rcu/tree_exp.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 9c990df880d1..5390618787b6 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -384,7 +384,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 			mask_ofl_test |= mask;
 			continue;
 		}
+		if (get_cpu() == cpu) {
+			put_cpu();
+			continue;
+		}
 		ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
+		put_cpu();
 		if (!ret) {
 			mask_ofl_ipi &= ~mask;
 			continue;
-- 
2.17.1

[PATCH tip/core/rcu 08/12] rcu: Avoid self-IPI in sync_sched_exp_online_cleanup()

[Paul E. McKenney]

The sync_sched_exp_online_cleanup() is invoked at online time to handle
the case where the start of an expedited grace period ran concurrently
with a CPU being taken offline and then immediately being placed online.
It checks to see if RCU needs an expedited quiescent state from the
incoming CPU, sending it an IPI if so.  However, it is quite possible
that sync_sched_exp_online_cleanup() is running on that CPU, in which
case it is considerably less overhead to simply request the quiescent
state locally instead of simulating a self-IPI.

This commit therefore places the last few lines of rcu_exp_handler()
into a new rcu_exp_need_qs() function, which is invoked both by
rcu_exp_handler() and by sync_sched_exp_online_cleanup() in the self-IPI
case.

This also reduces the rcu_exp_handler() function's state space by
removing the direct call that this smp_call_function_single() uses to
emulate the requested self-IPI.  This in turn will allow tighter error
checking in rcu_is_cpu_rrupt_from_idle().

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
 kernel/rcu/tree_exp.h | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 5390618787b6..de1b4acf6979 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -699,6 +699,16 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+/* Request an expedited quiescent state. */
+static void rcu_exp_need_qs(void)
+{
+	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
+	/* Store .exp before .rcu_urgent_qs. */
+	smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
+}
+
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
 static void rcu_exp_handler(void *unused)
 {
@@ -714,25 +724,38 @@ static void rcu_exp_handler(void *unused)
 		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
 		return;
 	}
-	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
-	/* Store .exp before .rcu_urgent_qs. */
-	smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
+	rcu_exp_need_qs();
 }
 
 /* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
 static void sync_sched_exp_online_cleanup(int cpu)
 {
+	unsigned long flags;
+	int my_cpu;
 	struct rcu_data *rdp;
 	int ret;
 	struct rcu_node *rnp;
 
 	rdp = per_cpu_ptr(&rcu_data, cpu);
 	rnp = rdp->mynode;
-	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
+	my_cpu = get_cpu();
+	/* Quiescent state either not needed or already requested, leave. */
+	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
+	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) {
+		put_cpu();
 		return;
+	}
+	/* Quiescent state needed on current CPU, so set it up locally. */
+	if (my_cpu == cpu) {
+		local_irq_save(flags);
+		rcu_exp_need_qs();
+		local_irq_restore(flags);
+		put_cpu();
+		return;
+	}
+	/* Quiescent state needed on some other CPU, send IPI. */
 	ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
+	put_cpu();
 	WARN_ON_ONCE(ret);
 }
 
-- 
2.17.1

[PATCH tip/core/rcu 09/12] lockdep: Add assertion to check if in an interrupt

[Paul E. McKenney]

From: "Joel Fernandes (Google)" <joel@joelfernandes.org>

In rcu_rrupt_from_idle, we want to check if it is called from within an
interrupt, but want to do such checking only for debug builds. lockdep
already tracks when we enter an interrupt. Let us expose it as an
assertion macro so it can be used to assert this.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Cc: kernel-team@android.com
Cc: rcu@vger.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 include/linux/lockdep.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 6e2377e6c1d6..e8eef38b2213 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -632,11 +632,18 @@ do {									\
 			  "IRQs not disabled as expected\n");		\
 	} while (0)
 
+#define lockdep_assert_in_irq() do {					\
+		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
+			  !current->hardirq_context,			\
+			  "Not in hardirq as expected\n");		\
+	} while (0)
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
+# define lockdep_assert_in_irq() do { } while (0)
 #endif
 
 #ifdef CONFIG_LOCKDEP
-- 
2.17.1

[PATCH tip/core/rcu 10/12] rcu: Add checks for dynticks counters in rcu_is_cpu_rrupt_from_idle()

[Paul E. McKenney]

From: "Joel Fernandes (Google)" <joel@joelfernandes.org>

It would be good to combine the dynticks and dynticks_nesting counters
in order to simplify the code.  Unfortunately, there are concerns
about usermode upcalls appearing to RCU as half of an interrupt, as
Byungchul learned [1].  The "half" in "half interrupt" is due to an
unpaired rcu_irq_enter(): Normally, each rcu_irq_enter() has a later
call to rcu_irq_exit().

Out of an abundance of caution, Paul added warnings [2] in the RCU
code which if not fired by 2021 will be interpreted as meaning that
this half-interrupt scenario cannot happen any more, thus permitting
simplification of this code.

In the meantime, this commit makes the following changes:

(1) Combining these two counters requires that rcu_rrupt_from_idle()
    is invoked only from hard-interrupt contexts as discussed here [3].
    This commit therefore adds the required lockdep_assert_in_irq()
    to check this constraint.

(2) Furthermore, rcu_rrupt_from_idle() is not explicit about how it
    is using the counters which can lead to weird future bugs. This
    commit therefore adds comments indicating the meaning and use of
    each counter.

(3) Lastly, this commit checks for counter underflows as another check
    that half interrupts don't occur.  (Previously, the function would
    simply return true upon underflow.)

All these checks checks are NOOPs if PROVE_LOCKING (and thus PROVE_RCU)
are disabled.

[1] https://lore.kernel.org/patchwork/patch/952349/
[2] Commit e11ec65cc8d6 ("rcu: Add warning to detect half-interrupts")
[3] https://lore.kernel.org/lkml/20190312150514.GB249405@google.com/

Cc: byungchul.park@lge.com
Cc: kernel-team@android.com
Cc: rcu@vger.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7822a2e1370d..b9629cf08f94 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -376,16 +376,29 @@ static void __maybe_unused rcu_momentary_dyntick_idle(void)
 }
 
 /**
- * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
+ * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
  *
- * If the current CPU is idle or running at a first-level (not nested)
+ * If the current CPU is idle and running at a first-level (not nested)
  * interrupt from idle, return true.  The caller must have at least
  * disabled preemption.
  */
 static int rcu_is_cpu_rrupt_from_idle(void)
 {
-	return __this_cpu_read(rcu_data.dynticks_nesting) <= 0 &&
-	       __this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 1;
+	/* Called only from within the scheduling-clock interrupt */
+	lockdep_assert_in_irq();
+
+	/* Check for counter underflows */
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
+			 "RCU dynticks_nesting counter underflow!");
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 0,
+			 "RCU dynticks_nmi_nesting counter underflow/zero!");
+
+	/* Are we at first interrupt nesting level? */
+	if (__this_cpu_read(rcu_data.dynticks_nmi_nesting) != 1)
+		return false;
+
+	/* Does CPU appear to be idle from an RCU standpoint? */
+	return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
 }
 
 #define DEFAULT_RCU_BLIMIT 10     /* Maximum callbacks per rcu_do_batch. */
-- 
2.17.1

[PATCH tip/core/rcu 11/12] rcu: Rename rcu_data's ->deferred_qs to ->exp_deferred_qs

[Paul E. McKenney]

The rcu_data structure's ->deferred_qs field is used to indicate that the
current CPU is blocking an expedited grace period (perhaps a future one).
Given that it is used only for expedited grace periods, its current name
is misleading, so this commit renames it to ->exp_deferred_qs.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree.h        |  2 +-
 kernel/rcu/tree_exp.h    |  8 ++++----
 kernel/rcu/tree_plugin.h | 14 +++++++-------
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 21d740f0b8dc..7acaf3a62d39 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -154,7 +154,7 @@ struct rcu_data {
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible ->gp_seq wrap. */
-	bool		deferred_qs;	/* This CPU awaiting a deferred QS? */
+	bool		exp_deferred_qs; /* This CPU awaiting a deferred QS? */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index de1b4acf6979..e0c928d04be5 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -250,7 +250,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
  */
 static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	WRITE_ONCE(rdp->deferred_qs, false);
+	WRITE_ONCE(rdp->exp_deferred_qs, false);
 	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }
 
@@ -616,7 +616,7 @@ static void rcu_exp_handler(void *unused)
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
-			rdp->deferred_qs = true;
+			rdp->exp_deferred_qs = true;
 			set_tsk_need_resched(t);
 			set_preempt_need_resched();
 		}
@@ -638,7 +638,7 @@ static void rcu_exp_handler(void *unused)
 	if (t->rcu_read_lock_nesting > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
-			rdp->deferred_qs = true;
+			rdp->exp_deferred_qs = true;
 			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -661,7 +661,7 @@ static void rcu_exp_handler(void *unused)
 	 *
 	 * Otherwise, force a context switch after the CPU enables everything.
 	 */
-	rdp->deferred_qs = true;
+	rdp->exp_deferred_qs = true;
 	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
 	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
 		rcu_preempt_deferred_qs(t);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 58c7853f19e7..1aeb4ae187ce 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -237,10 +237,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * no need to check for a subsequent expedited GP.  (Though we are
 	 * still in a quiescent state in any case.)
 	 */
-	if (blkd_state & RCU_EXP_BLKD && rdp->deferred_qs)
+	if (blkd_state & RCU_EXP_BLKD && rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
 	else
-		WARN_ON_ONCE(rdp->deferred_qs);
+		WARN_ON_ONCE(rdp->exp_deferred_qs);
 }
 
 /*
@@ -337,7 +337,7 @@ void rcu_note_context_switch(bool preempt)
 	 * means that we continue to block the current grace period.
 	 */
 	rcu_qs();
-	if (rdp->deferred_qs)
+	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
 	trace_rcu_utilization(TPS("End context switch"));
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
@@ -451,7 +451,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 */
 	special = t->rcu_read_unlock_special;
 	rdp = this_cpu_ptr(&rcu_data);
-	if (!special.s && !rdp->deferred_qs) {
+	if (!special.s && !rdp->exp_deferred_qs) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -459,7 +459,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	if (special.b.need_qs) {
 		rcu_qs();
 		t->rcu_read_unlock_special.b.need_qs = false;
-		if (!t->rcu_read_unlock_special.s && !rdp->deferred_qs) {
+		if (!t->rcu_read_unlock_special.s && !rdp->exp_deferred_qs) {
 			local_irq_restore(flags);
 			return;
 		}
@@ -471,7 +471,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 * tasks are handled when removing the task from the
 	 * blocked-tasks list below.
 	 */
-	if (rdp->deferred_qs) {
+	if (rdp->exp_deferred_qs) {
 		rcu_report_exp_rdp(rdp);
 		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
@@ -560,7 +560,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
  */
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
-	return (__this_cpu_read(rcu_data.deferred_qs) ||
+	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
 	       t->rcu_read_lock_nesting <= 0;
 }
-- 
2.17.1

[PATCH tip/core/rcu 12/12] rcu: Remove unused rdp local from synchronize_rcu_expedited()

[Paul E. McKenney]

From: Jiang Biao <benbjiang@tencent.com>

Because rdp is initialized but never used in synchronize_rcu_expedited(),
this commit removes it.

Signed-off-by: Jiang Biao <benbjiang@tencent.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 kernel/rcu/tree_exp.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index e0c928d04be5..8e539710721a 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -793,7 +793,6 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	struct rcu_data *rdp;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
 	unsigned long s;
@@ -830,7 +829,6 @@ void synchronize_rcu_expedited(void)
 	}
 
 	/* Wait for expedited grace period to complete. */
-	rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
 	rnp = rcu_get_root();
 	wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
 		   sync_exp_work_done(s));
-- 
2.17.1