Merge tag 'rcu.2022.12.02a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Documentation updates. This is the second in a series from an ongoing
   review of the RCU documentation.

 - Miscellaneous fixes.

 - Introduce a default-off Kconfig option that depends on RCU_NOCB_CPU
   that, on CPUs mentioned in the nohz_full or rcu_nocbs boot-argument
   CPU lists, causes call_rcu() to introduce delays.

   These delays result in significant power savings on nearly idle
   Android and ChromeOS systems. These savings range from a few percent
   to more than ten percent.

   This series also includes several commits that change call_rcu() to a
   new call_rcu_hurry() function that avoids these delays in a few
   cases, for example, where timely wakeups are required. Several of
   these are outside of RCU and thus have acks and reviews from the
   relevant maintainers.

 - Create an srcu_read_lock_nmisafe() and an srcu_read_unlock_nmisafe()
   for architectures that support NMIs, but which do not provide
   NMI-safe this_cpu_inc(). These NMI-safe SRCU functions are required
   by the upcoming lockless printk() work by John Ogness et al.

 - Changes providing minor but important increases in torture test
   coverage for the new RCU polled-grace-period APIs.

 - Changes to torturescript that avoid redundant kernel builds, thus
   providing about a 30% speedup for the torture.sh acceptance test.

* tag 'rcu.2022.12.02a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (49 commits)
  net: devinet: Reduce refcount before grace period
  net: Use call_rcu_hurry() for dst_release()
  workqueue: Make queue_rcu_work() use call_rcu_hurry()
  percpu-refcount: Use call_rcu_hurry() for atomic switch
  scsi/scsi_error: Use call_rcu_hurry() instead of call_rcu()
  rcu/rcutorture: Use call_rcu_hurry() where needed
  rcu/rcuscale: Use call_rcu_hurry() for async reader test
  rcu/sync: Use call_rcu_hurry() instead of call_rcu
  rcuscale: Add laziness and kfree tests
  rcu: Shrinker for lazy rcu
  rcu: Refactor code a bit in rcu_nocb_do_flush_bypass()
  rcu: Make call_rcu() lazy to save power
  rcu: Implement lockdep_rcu_enabled for !CONFIG_DEBUG_LOCK_ALLOC
  srcu: Debug NMI safety even on archs that don't require it
  srcu: Explain the reason behind the read side critical section on GP start
  srcu: Warn when NMI-unsafe API is used in NMI
  arch/s390: Add ARCH_HAS_NMI_SAFE_THIS_CPU_OPS Kconfig option
  arch/loongarch: Add ARCH_HAS_NMI_SAFE_THIS_CPU_OPS Kconfig option
  rcu: Fix __this_cpu_read() lockdep warning in rcu_force_quiescent_state()
  rcu-tasks: Make grace-period-age message human-readable
  ...

1 files changed, 96 insertions, 56 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 93416afebd59..d04f2192f02c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -301,12 +301,6 @@ static bool rcu_dynticks_in_eqs(int snap)
 	return !(snap & RCU_DYNTICKS_IDX);
 }
 
-/* Return true if the specified CPU is currently idle from an RCU viewpoint.  */
-bool rcu_is_idle_cpu(int cpu)
-{
-	return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu));
-}
-
 /*
  * Return true if the CPU corresponding to the specified rcu_data
  * structure has spent some time in an extended quiescent state since
@@ -2108,7 +2102,7 @@ int rcutree_dying_cpu(unsigned int cpu)
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
 		return 0;
 
-	blkd = !!(rnp->qsmask & rdp->grpmask);
+	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
 	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
 			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
 	return 0;
@@ -2418,7 +2412,7 @@ void rcu_force_quiescent_state(void)
 	struct rcu_node *rnp_old = NULL;
 
 	/* Funnel through hierarchy to reduce memory contention. */
-	rnp = __this_cpu_read(rcu_data.mynode);
+	rnp = raw_cpu_read(rcu_data.mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
 		       !raw_spin_trylock(&rnp->fqslock);
@@ -2730,47 +2724,8 @@ static void check_cb_ovld(struct rcu_data *rdp)
 	raw_spin_unlock_rcu_node(rnp);
 }
 
-/**
- * call_rcu() - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all pre-existing RCU read-side
- * critical sections have completed.  However, the callback function
- * might well execute concurrently with RCU read-side critical sections
- * that started after call_rcu() was invoked.
- *
- * RCU read-side critical sections are delimited by rcu_read_lock()
- * and rcu_read_unlock(), and may be nested.  In addition, but only in
- * v5.0 and later, regions of code across which interrupts, preemption,
- * or softirqs have been disabled also serve as RCU read-side critical
- * sections.  This includes hardware interrupt handlers, softirq handlers,
- * and NMI handlers.
- *
- * Note that all CPUs must agree that the grace period extended beyond
- * all pre-existing RCU read-side critical section.  On systems with more
- * than one CPU, this means that when "func()" is invoked, each CPU is
- * guaranteed to have executed a full memory barrier since the end of its
- * last RCU read-side critical section whose beginning preceded the call
- * to call_rcu().  It also means that each CPU executing an RCU read-side
- * critical section that continues beyond the start of "func()" must have
- * executed a memory barrier after the call_rcu() but before the beginning
- * of that RCU read-side critical section.  Note that these guarantees
- * include CPUs that are offline, idle, or executing in user mode, as
- * well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
- * resulting RCU callback function "func()", then both CPU A and CPU B are
- * guaranteed to execute a full memory barrier during the time interval
- * between the call to call_rcu() and the invocation of "func()" -- even
- * if CPU A and CPU B are the same CPU (but again only if the system has
- * more than one CPU).
- *
- * Implementation of these memory-ordering guarantees is described here:
- * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
- */
-void call_rcu(struct rcu_head *head, rcu_callback_t func)
+static void
+__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy)
 {
 	static atomic_t doublefrees;
 	unsigned long flags;
@@ -2811,7 +2766,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 	}
 
 	check_cb_ovld(rdp);
-	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
+	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy))
 		return; // Enqueued onto ->nocb_bypass, so just leave.
 	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
@@ -2833,8 +2788,84 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 		local_irq_restore(flags);
 	}
 }
-EXPORT_SYMBOL_GPL(call_rcu);
 
+#ifdef CONFIG_RCU_LAZY
+/**
+ * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and
+ * flush all lazy callbacks (including the new one) to the main ->cblist while
+ * doing so.
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.
+ *
+ * Use this API instead of call_rcu() if you don't want the callback to be
+ * invoked after very long periods of time, which can happen on systems without
+ * memory pressure and on systems which are lightly loaded or mostly idle.
+ * This function will cause callbacks to be invoked sooner than later at the
+ * expense of extra power. Other than that, this function is identical to, and
+ * reuses call_rcu()'s logic. Refer to call_rcu() for more details about memory
+ * ordering and other functionality.
+ */
+void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
+{
+	return __call_rcu_common(head, func, false);
+}
+EXPORT_SYMBOL_GPL(call_rcu_hurry);
+#endif
+
+/**
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
+ * By default the callbacks are 'lazy' and are kept hidden from the main
+ * ->cblist to prevent starting of grace periods too soon.
+ * If you desire grace periods to start very soon, use call_rcu_hurry().
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.  However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.
+ *
+ * RCU read-side critical sections are delimited by rcu_read_lock()
+ * and rcu_read_unlock(), and may be nested.  In addition, but only in
+ * v5.0 and later, regions of code across which interrupts, preemption,
+ * or softirqs have been disabled also serve as RCU read-side critical
+ * sections.  This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section.  On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu().  It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section.  Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
+ *
+ * Implementation of these memory-ordering guarantees is described here:
+ * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
+ */
+void call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+	return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+}
+EXPORT_SYMBOL_GPL(call_rcu);
 
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (5 * HZ)
@@ -3509,7 +3540,7 @@ void synchronize_rcu(void)
 		if (rcu_gp_is_expedited())
 			synchronize_rcu_expedited();
 		else
-			wait_rcu_gp(call_rcu);
+			wait_rcu_gp(call_rcu_hurry);
 		return;
 	}
 
@@ -3896,6 +3927,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 {
 	unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence);
 	unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap);
+	bool wake_nocb = false;
+	bool was_alldone = false;
 
 	lockdep_assert_held(&rcu_state.barrier_lock);
 	if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq))
@@ -3904,7 +3937,14 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 	rdp->barrier_head.func = rcu_barrier_callback;
 	debug_rcu_head_queue(&rdp->barrier_head);
 	rcu_nocb_lock(rdp);
-	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	/*
+	 * Flush bypass and wakeup rcuog if we add callbacks to an empty regular
+	 * queue. This way we don't wait for bypass timer that can reach seconds
+	 * if it's fully lazy.
+	 */
+	was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist);
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
+	wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist);
 	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
 		atomic_inc(&rcu_state.barrier_cpu_count);
 	} else {
@@ -3912,6 +3952,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 		rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
 	}
 	rcu_nocb_unlock(rdp);
+	if (wake_nocb)
+		wake_nocb_gp(rdp, false);
 	smp_store_release(&rdp->barrier_seq_snap, gseq);
 }
 
@@ -4278,8 +4320,6 @@ void rcu_report_dead(unsigned int cpu)
 	// Do any dangling deferred wakeups.
 	do_nocb_deferred_wakeup(rdp);
 
-	/* QS for any half-done expedited grace period. */
-	rcu_report_exp_rdp(rdp);
 	rcu_preempt_deferred_qs(current);
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
@@ -4327,7 +4367,7 @@ void rcutree_migrate_callbacks(int cpu)
 	my_rdp = this_cpu_ptr(&rcu_data);
 	my_rnp = my_rdp->mynode;
 	rcu_nocb_lock(my_rdp); /* irqs already disabled. */
-	WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies));
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies, false));
 	raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */
 	/* Leverage recent GPs and set GP for new callbacks. */
 	needwake = rcu_advance_cbs(my_rnp, rdp) ||