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, 9 insertions, 5 deletions

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index f3947c49eee7..237a79989aba 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -255,7 +255,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
  */
 static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	WRITE_ONCE(rdp->exp_deferred_qs, false);
+	WRITE_ONCE(rdp->cpu_no_qs.b.exp, false);
 	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }
 
@@ -387,6 +387,7 @@ retry_ipi:
 			continue;
 		}
 		if (get_cpu() == cpu) {
+			mask_ofl_test |= mask;
 			put_cpu();
 			continue;
 		}
@@ -506,7 +507,10 @@ static void synchronize_rcu_expedited_wait(void)
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_disable();
+				if (cpu_online(cpu))
+					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_enable();
 			}
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
@@ -655,7 +659,7 @@ static void rcu_exp_handler(void *unused)
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			set_tsk_need_resched(t);
 			set_preempt_need_resched();
 		}
@@ -677,7 +681,7 @@ static void rcu_exp_handler(void *unused)
 	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -759,7 +763,7 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	my_cpu = get_cpu();
 	/* Quiescent state either not needed or already requested, leave. */
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
-	    rdp->cpu_no_qs.b.exp) {
+	    READ_ONCE(rdp->cpu_no_qs.b.exp)) {
 		put_cpu();
 		return;
 	}