rcu-tasks: Permit use of debug-objects with RCU Tasks flavors

Currently, cblist_init_generic() holds a raw spinlock when invoking
INIT_WORK().  This fails in kernels built with CONFIG_DEBUG_OBJECTS=y
due to memory allocation being forbidden while holding a raw spinlock.
But the only reason for holding the raw spinlock is to synchronize
with early boot calls to call_rcu_tasks(), call_rcu_tasks_rude, and,
last but not least, call_rcu_tasks_trace().  These calls also invoke
cblist_init_generic() in order to support early boot queueing of
callbacks.

Except that there are no early boot calls to either of these three
functions, and the BPF guys confirm that they have no plans to add any
such calls.

This commit therefore removes the synchronization and adds a
WARN_ON_ONCE() to catch the case of now-prohibited early boot RCU Tasks
callback queueing.

If early boot queueing is needed, an "initialized" flag may be added to
the rcu_tasks structure.  Then queueing a callback before this flag is set
would initialize the callback list (if needed) and queue the callback.
The decision as to where to queue the callback given the possibility of
non-zero boot CPUs is left as an exercise for the reader.
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tasks.h

@@ -236,7 +236,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 #endif /* #ifndef CONFIG_TINY_RCU */
 
 // Initialize per-CPU callback lists for the specified flavor of
-// Tasks RCU.
+// Tasks RCU.  Do not enqueue callbacks before this function is invoked.
 static void cblist_init_generic(struct rcu_tasks *rtp)
 {
 	int cpu;
@@ -244,7 +244,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 	int lim;
 	int shift;
 
-	raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
 	if (rcu_task_enqueue_lim < 0) {
 		rcu_task_enqueue_lim = 1;
 		rcu_task_cb_adjust = true;
@@ -267,17 +266,16 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 		WARN_ON_ONCE(!rtpcp);
 		if (cpu)
 			raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
-		raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+		local_irq_save(flags);  // serialize initialization
 		if (rcu_segcblist_empty(&rtpcp->cblist))
 			rcu_segcblist_init(&rtpcp->cblist);
+		local_irq_restore(flags);
 		INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
 		rtpcp->cpu = cpu;
 		rtpcp->rtpp = rtp;
 		if (!rtpcp->rtp_blkd_tasks.next)
 			INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
-		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 rcu_task_cb_adjust=%d.\n", rtp->name,
 			data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust);
@@ -351,11 +349,9 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 		    READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids)
 			needadjust = true;  // Defer adjustment to avoid deadlock.
 	}
-	if (!rcu_segcblist_is_enabled(&rtpcp->cblist)) {
-		raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
-		cblist_init_generic(rtp);
-		raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
-	}
+	// Queuing callbacks before initialization not yet supported.
+	if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist)))
+		rcu_segcblist_init(&rtpcp->cblist);
 	needwake = (func == wakeme_after_rcu) ||
 		   (rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim);
 	if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) {