Merge tag 'rcu.2023.06.22a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:
 "Documentation updates

  Miscellaneous fixes, perhaps most notably:

   - Remove RCU_NONIDLE(). The new visibility of most of the idle loop
     to RCU has obsoleted this API.

   - Make the RCU_SOFTIRQ callback-invocation time limit also apply to
     the rcuc kthreads that invoke callbacks for CONFIG_PREEMPT_RT.

   - Add a jiffies-based callback-invocation time limit to handle
     long-running callbacks. (The local_clock() function is only invoked
     once per 32 callbacks due to its high overhead.)

   - Stop rcu_tasks_invoke_cbs() from using never-onlined CPUs, which
     fixes a bug that can occur on systems with non-contiguous CPU
     numbering.

  kvfree_rcu updates:

   - Eliminate the single-argument variant of k[v]free_rcu() now that
     all uses have been converted to k[v]free_rcu_mightsleep().

   - Add WARN_ON_ONCE() checks for k[v]free_rcu*() freeing callbacks too
     soon. Yes, this is closing the barn door after the horse has
     escaped, but Murphy says that there will be more horses.

  Callback-offloading updates:

   - Fix a number of bugs involving the shrinker and lazy callbacks.

  Tasks RCU updates

  Torture-test updates"

* tag 'rcu.2023.06.22a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (32 commits)
  torture: Remove duplicated argument -enable-kvm for ppc64
  doc/rcutorture: Add description of rcutorture.stall_cpu_block
  rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale
  rcu/rcuscale: Move rcu_scale_*() after kfree_scale_cleanup()
  rcutorture: Correct name of use_softirq module parameter
  locktorture: Add long_hold to adjust lock-hold delays
  rcu/nocb: Make shrinker iterate only over NOCB CPUs
  rcu-tasks: Stop rcu_tasks_invoke_cbs() from using never-onlined CPUs
  rcu: Make rcu_cpu_starting() rely on interrupts being disabled
  rcu: Mark rcu_cpu_kthread() accesses to ->rcu_cpu_has_work
  rcu: Mark additional concurrent load from ->cpu_no_qs.b.exp
  rcu: Employ jiffies-based backstop to callback time limit
  rcu: Check callback-invocation time limit for rcuc kthreads
  rcu: Remove RCU_NONIDLE()
  rcu: Add more RCU files to kernel-api.rst
  rcu-tasks: Clarify the cblist_init_generic() function's pr_info() output
  rcu-tasks: Avoid pr_info() with spin lock in cblist_init_generic()
  rcu/nocb: Recheck lazy callbacks under the ->nocb_lock from shrinker
  rcu/nocb: Fix shrinker race against callback enqueuer
  rcu/nocb: Protect lazy shrinker against concurrent (de-)offloading
  ...

1 files changed, 8 insertions, 4 deletions

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 5f4fc8184dd0..b770add3f843 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -241,7 +241,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 	if (rcu_task_enqueue_lim < 0) {
 		rcu_task_enqueue_lim = 1;
 		rcu_task_cb_adjust = true;
-		pr_info("%s: Setting adjustable number of callback queues.\n", __func__);
 	} else if (rcu_task_enqueue_lim == 0) {
 		rcu_task_enqueue_lim = 1;
 	}
@@ -272,7 +271,9 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 		raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
 	}
 	raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
-	pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim));
+
+	pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
+			data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust);
 }
 
 // IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
@@ -463,6 +464,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
 {
 	int cpu;
 	int cpunext;
+	int cpuwq;
 	unsigned long flags;
 	int len;
 	struct rcu_head *rhp;
@@ -473,11 +475,13 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
 	cpunext = cpu * 2 + 1;
 	if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
 		rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext);
-		queue_work_on(cpunext, system_wq, &rtpcp_next->rtp_work);
+		cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND;
+		queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work);
 		cpunext++;
 		if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
 			rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext);
-			queue_work_on(cpunext, system_wq, &rtpcp_next->rtp_work);
+			cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND;
+			queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work);
 		}
 	}