Merge tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Documentation updates, perhaps most notably Neil Brown's writeup of
   the reference-counting analogy to RCU.

 - Expedited grace-period cleanups.

 - Remove CONFIG_RCU_FAST_NO_HZ due to lack of valid users. I have asked
   around, posted a blog entry, and sent this series to LKML without
   result.

 - Miscellaneous fixes.

 - RCU callback offloading updates, perhaps most notably Frederic
   Weisbecker's updates allowing CPUs booted in the de-offloaded state
   to be offloaded at runtime.

 - nolibc fixes from Willy Tarreau and Anmar Faizi, but also including
   Mark Brown's addition of gettid().

 - RCU Tasks Trace fixes, including changes that increase the
   scalability of call_rcu_tasks_trace() for the BPF folks (Martin Lau
   and KP Singh).

 - Various fixes including those from Wander Lairson Costa and Li
   Zhijian.

 - Fixes plus addition of tests for the increased call_rcu_tasks_trace()
   scalability.

* tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (87 commits)
  rcu/nocb: Merge rcu_spawn_cpu_nocb_kthread() and rcu_spawn_one_nocb_kthread()
  rcu/nocb: Allow empty "rcu_nocbs" kernel parameter
  rcu/nocb: Create kthreads on all CPUs if "rcu_nocbs=" or "nohz_full=" are passed
  rcu/nocb: Optimize kthreads and rdp initialization
  rcu/nocb: Prepare nocb_cb_wait() to start with a non-offloaded rdp
  rcu/nocb: Remove rcu_node structure from nocb list when de-offloaded
  rcu-tasks: Use fewer callbacks queues if callback flood ends
  rcu-tasks: Use separate ->percpu_dequeue_lim for callback dequeueing
  rcu-tasks: Use more callback queues if contention encountered
  rcu-tasks: Avoid raw-spinlocked wakeups from call_rcu_tasks_generic()
  rcu-tasks: Count trylocks to estimate call_rcu_tasks() contention
  rcu-tasks: Add rcupdate.rcu_task_enqueue_lim to set initial queueing
  rcu-tasks: Make rcu_barrier_tasks*() handle multiple callback queues
  rcu-tasks: Use workqueues for multiple rcu_tasks_invoke_cbs() invocations
  rcu-tasks: Abstract invocations of callbacks
  rcu-tasks: Abstract checking of callback lists
  rcu-tasks: Add a ->percpu_enqueue_lim to the rcu_tasks structure
  rcu-tasks: Inspect stalled task's trc state in locked state
  rcu-tasks: Use spin_lock_rcu_node() and friends
  rcutorture: Combine n_max_cbs from all kthreads in a callback flood
  ...

1 files changed, 86 insertions, 45 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ef8d36f580fc..a4c25a6283b0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -79,7 +79,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_RCU_NOCB_CPU
-	.cblist.flags = SEGCBLIST_SOFTIRQ_ONLY,
+	.cblist.flags = SEGCBLIST_RCU_CORE,
 #endif
 };
 static struct rcu_state rcu_state = {
@@ -624,7 +624,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
@@ -768,9 +767,6 @@ noinstr void rcu_nmi_exit(void)
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
-	if (!in_nmi())
-		rcu_prepare_for_idle();
-
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
@@ -872,7 +868,6 @@ static void noinstr rcu_eqs_exit(bool user)
 	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 
-	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
@@ -1014,12 +1009,6 @@ noinstr void rcu_nmi_enter(void)
 		rcu_dynticks_eqs_exit();
 		// ... but is watching here.
 
-		if (!in_nmi()) {
-			instrumentation_begin();
-			rcu_cleanup_after_idle();
-			instrumentation_end();
-		}
-
 		instrumentation_begin();
 		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
 		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
@@ -1087,6 +1076,24 @@ void rcu_irq_enter_irqson(void)
 }
 
 /*
+ * Check to see if any future non-offloaded RCU-related work will need
+ * to be done by the current CPU, even if none need be done immediately,
+ * returning 1 if so.  This function is part of the RCU implementation;
+ * it is -not- an exported member of the RCU API.  This is used by
+ * the idle-entry code to figure out whether it is safe to disable the
+ * scheduler-clock interrupt.
+ *
+ * Just check whether or not this CPU has non-offloaded RCU callbacks
+ * queued.
+ */
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+{
+	*nextevt = KTIME_MAX;
+	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
+}
+
+/*
  * If any sort of urgency was applied to the current CPU (for example,
  * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
  * to get to a quiescent state, disable it.
@@ -1467,7 +1474,7 @@ static void rcu_gp_kthread_wake(void)
 {
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
-	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	if ((current == t && !in_hardirq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
@@ -1590,10 +1597,11 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
-	    !raw_spin_trylock_rcu_node(rnp))
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
 		return;
-	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	// The grace period cannot end while we hold the rcu_node lock.
+	if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+		WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
 	raw_spin_unlock_rcu_node(rnp);
 }
 
@@ -2277,7 +2285,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
+	bool needacc = false;
 	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2304,15 +2312,30 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 		/*
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
+		 *
+		 * NOCB kthreads have their own way to deal with that...
 		 */
-		if (!offloaded)
+		if (!rcu_rdp_is_offloaded(rdp)) {
 			needwake = rcu_accelerate_cbs(rnp, rdp);
+		} else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
+			/*
+			 * ...but NOCB kthreads may miss or delay callbacks acceleration
+			 * if in the middle of a (de-)offloading process.
+			 */
+			needacc = true;
+		}
 
 		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake();
+
+		if (needacc) {
+			rcu_nocb_lock_irqsave(rdp, flags);
+			rcu_accelerate_cbs_unlocked(rnp, rdp);
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+		}
 	}
 }
 
@@ -2444,7 +2467,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	int div;
 	bool __maybe_unused empty;
 	unsigned long flags;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count = 0;
@@ -2462,18 +2484,17 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	}
 
 	/*
-	 * Extract the list of ready callbacks, disabling to prevent
+	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
 	 */
-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	pending = rcu_segcblist_n_cbs(&rdp->cblist);
 	div = READ_ONCE(rcu_divisor);
 	div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
 	bl = max(rdp->blimit, pending >> div);
-	if (unlikely(bl > 100)) {
+	if (in_serving_softirq() && unlikely(bl > 100)) {
 		long rrn = READ_ONCE(rcu_resched_ns);
 
 		rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
@@ -2482,7 +2503,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	trace_rcu_batch_start(rcu_state.name,
 			      rcu_segcblist_n_cbs(&rdp->cblist), bl);
 	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
-	if (offloaded)
+	if (rcu_rdp_is_offloaded(rdp))
 		rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
 
 	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued"));
@@ -2510,18 +2531,21 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		/*
 		 * Stop only if limit reached and CPU has something to do.
 		 */
-		if (count >= bl && !offloaded &&
-		    (need_resched() ||
-		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
-			break;
-		if (unlikely(tlimit)) {
-			/* only call local_clock() every 32 callbacks */
-			if (likely((count & 31) || local_clock() < tlimit))
-				continue;
-			/* Exceeded the time limit, so leave. */
-			break;
-		}
-		if (!in_serving_softirq()) {
+		if (in_serving_softirq()) {
+			if (count >= bl && (need_resched() || !is_idle_task(current)))
+				break;
+			/*
+			 * Make sure we don't spend too much time here and deprive other
+			 * softirq vectors of CPU cycles.
+			 */
+			if (unlikely(tlimit)) {
+				/* only call local_clock() every 32 callbacks */
+				if (likely((count & 31) || local_clock() < tlimit))
+					continue;
+				/* Exceeded the time limit, so leave. */
+				break;
+			}
+		} else {
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
@@ -2530,8 +2554,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		}
 	}
 
-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
@@ -2565,9 +2588,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
-	/* Re-invoke RCU core processing if there are callbacks remaining. */
-	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
-		invoke_rcu_core();
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 }
 
@@ -2706,6 +2726,23 @@ static __latent_entropy void rcu_core(void)
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	/*
+	 * On RT rcu_core() can be preempted when IRQs aren't disabled.
+	 * Therefore this function can race with concurrent NOCB (de-)offloading
+	 * on this CPU and the below condition must be considered volatile.
+	 * However if we race with:
+	 *
+	 * _ Offloading:   In the worst case we accelerate or process callbacks
+	 *                 concurrently with NOCB kthreads. We are guaranteed to
+	 *                 call rcu_nocb_lock() if that happens.
+	 *
+	 * _ Deoffloading: In the worst case we miss callbacks acceleration or
+	 *                 processing. This is fine because the early stage
+	 *                 of deoffloading invokes rcu_core() after setting
+	 *                 SEGCBLIST_RCU_CORE. So we guarantee that we'll process
+	 *                 what could have been dismissed without the need to wait
+	 *                 for the next rcu_pending() check in the next jiffy.
+	 */
 	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
 
 	if (cpu_is_offline(smp_processor_id()))
@@ -2714,7 +2751,7 @@ static __latent_entropy void rcu_core(void)
 	WARN_ON_ONCE(!rdp->beenonline);
 
 	/* Report any deferred quiescent states if preemption enabled. */
-	if (!(preempt_count() & PREEMPT_MASK)) {
+	if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
 		set_tsk_need_resched(current);
@@ -2737,8 +2774,12 @@ static __latent_entropy void rcu_core(void)
 
 	/* If there are callbacks ready, invoke them. */
 	if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
-	    likely(READ_ONCE(rcu_scheduler_fully_active)))
+	    likely(READ_ONCE(rcu_scheduler_fully_active))) {
 		rcu_do_batch(rdp);
+		/* Re-invoke RCU core processing if there are callbacks remaining. */
+		if (rcu_segcblist_ready_cbs(&rdp->cblist))
+			invoke_rcu_core();
+	}
 
 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
@@ -2982,7 +3023,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
-	kasan_record_aux_stack(head);
+	kasan_record_aux_stack_noalloc(head);
 	rdp = this_cpu_ptr(&rcu_data);
 
 	/* Add the callback to our list. */
@@ -3547,7 +3588,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return;
 	}
 
-	kasan_record_aux_stack(ptr);
+	kasan_record_aux_stack_noalloc(ptr);
 	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);