[PATCH rcu 15/18] rcu-tasks: Avoid raw-spinlocked wakeups from call_rcu_tasks_generic()

["Paul E. McKenney" <paulmck@kernel.org>]

If the caller of of call_rcu_tasks(), call_rcu_tasks_rude(),
or call_rcu_tasks_trace() holds a raw spinlock, and then if
call_rcu_tasks_generic() determines that the grace-period kthread must
be awakened, then the wakeup might acquire a normal spinlock while a
raw spinlock is held.  This results in lockdep splats when the
kernel is built with CONFIG_PROVE_RAW_LOCK_NESTING=y.

This commit therefore defers the wakeup using irq_work_queue().

It would be nice to directly invoke wakeup when a raw spinlock is not
held, but there is currently no way to check for this in all kernels.

Reported-by: Martin Lau <kafai@fb.com>
Cc: Neeraj Upadhyay <neeraj.iitr10@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tasks.h | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 3f25022a0db9a..652f51eec5f34 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -27,6 +27,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @rtp_jiffies: Jiffies counter value for statistics.
  * @rtp_n_lock_retries: Rough lock-contention statistic.
  * @rtp_work: Work queue for invoking callbacks.
+ * @rtp_irq_work: IRQ work queue for deferred wakeups.
  * @barrier_q_head: RCU callback for barrier operation.
  * @cpu: CPU number corresponding to this entry.
  * @rtpp: Pointer to the rcu_tasks structure.
@@ -37,6 +38,7 @@ struct rcu_tasks_percpu {
 	unsigned long rtp_jiffies;
 	unsigned long rtp_n_lock_retries;
 	struct work_struct rtp_work;
+	struct irq_work rtp_irq_work;
 	struct rcu_head barrier_q_head;
 	int cpu;
 	struct rcu_tasks *rtpp;
@@ -102,9 +104,12 @@ struct rcu_tasks {
 	char *kname;
 };
 
+static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp);
+
 #define DEFINE_RCU_TASKS(rt_name, gp, call, n)						\
 static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = {			\
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ## __percpu.cbs_pcpu_lock),		\
+	.rtp_irq_work = IRQ_WORK_INIT(call_rcu_tasks_iw_wakeup),			\
 };											\
 static struct rcu_tasks rt_name =							\
 {											\
@@ -230,6 +235,16 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 	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));
 }
 
+// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
+static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
+{
+	struct rcu_tasks *rtp;
+	struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct rcu_tasks_percpu, rtp_irq_work);
+
+	rtp = rtpcp->rtpp;
+	wake_up(&rtp->cbs_wq);
+}
+
 // Enqueue a callback for the specified flavor of Tasks RCU.
 static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 				   struct rcu_tasks *rtp)
@@ -262,8 +277,9 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 	rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 	/* We can't create the thread unless interrupts are enabled. */
-	if (needwake && READ_ONCE(rtp->kthread_ptr))
-		wake_up(&rtp->cbs_wq);
+	if (needwake && READ_ONCE(rtp->kthread_ptr)) {
+		irq_work_queue(&rtpcp->rtp_irq_work);
+	}
 }
 
 // Wait for a grace period for the specified flavor of Tasks RCU.
-- 
2.31.1.189.g2e36527f23