[PATCH] rcu: Use an intermediate irq_work to start process_srcu()

[Boqun Feng <boqun@kernel.org>]

Since commit c27cea4416a3 ("rcu: Re-implement RCU Tasks Trace in terms
of SRCU-fast") we switched to SRCU in BPF. However as BPF instrument can
happen basically everywhere (including where a scheduler lock is held),
call_srcu() now needs to avoid acquiring scheduler lock because
otherwise it could cause deadlock [1]. Fix this by following what the
previous RCU Tasks Trace did: using an irq_work to delay the queuing of
the work to start process_srcu().

[boqun: Apply Joel's feedback]

Reported-by: Andrea Righi <arighi@nvidia.com>
Closes: https://lore.kernel.org/all/abjzvz_tL_siV17s@gpd4/
Fixes: commit c27cea4416a3 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast")
Link: https://lore.kernel.org/rcu/3c4c5a29-24ea-492d-aeee-e0d9605b4183@nvidia.com/ [1]
Suggested-by: Zqiang <qiang.zhang@linux.dev>
Signed-off-by: Boqun Feng <boqun@kernel.org>
---
@Zqiang, I put your name as Suggested-by because you proposed the same
idea, let me know if you rather not have it.

@Joel, I did two updates (including your test feedback, other one is
call irq_work_sync() when we clean the srcu_struct), please give it a
try.

 include/linux/srcutree.h |  1 +
 kernel/rcu/srcutree.c    | 29 +++++++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index dfb31d11ff05..be76fa4fc170 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -95,6 +95,7 @@ struct srcu_usage {
 	unsigned long reschedule_jiffies;
 	unsigned long reschedule_count;
 	struct delayed_work work;
+	struct irq_work irq_work;
 	struct srcu_struct *srcu_ssp;
 };
 
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 2328827f8775..73aef361a524 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
+#include <linux/irq_work.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
@@ -75,6 +76,7 @@ static bool __read_mostly srcu_init_done;
 static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
+static void srcu_irq_work(struct irq_work *work);
 static void srcu_delay_timer(struct timer_list *t);
 
 /*
@@ -216,6 +218,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
 	INIT_DELAYED_WORK(&ssp->srcu_sup->work, process_srcu);
+	init_irq_work(&ssp->srcu_sup->irq_work, srcu_irq_work);
 	ssp->srcu_sup->sda_is_static = is_static;
 	if (!is_static) {
 		ssp->sda = alloc_percpu(struct srcu_data);
@@ -713,6 +716,8 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
+	/* Wait for irq_work to finish first as it may queue a new work. */
+	irq_work_sync(&sup->irq_work);
 	flush_delayed_work(&sup->work);
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
@@ -1118,9 +1123,13 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		// it isn't.  And it does not have to be.  After all, it
 		// can only be executed during early boot when there is only
 		// the one boot CPU running with interrupts still disabled.
+		//
+		// Use an irq_work here to avoid acquiring runqueue lock with
+		// srcu rcu_node::lock held. BPF instrument could introduce the
+		// opposite dependency, hence we need to break the possible
+		// locking dependency here.
 		if (likely(srcu_init_done))
-			queue_delayed_work(rcu_gp_wq, &sup->work,
-					   !!srcu_get_delay(ssp));
+			irq_work_queue(&sup->irq_work);
 		else if (list_empty(&sup->work.work.entry))
 			list_add(&sup->work.work.entry, &srcu_boot_list);
 	}
@@ -1979,6 +1988,22 @@ static void process_srcu(struct work_struct *work)
 	srcu_reschedule(ssp, curdelay);
 }
 
+static void srcu_irq_work(struct irq_work *work)
+{
+	struct srcu_struct *ssp;
+	struct srcu_usage *sup;
+	unsigned long delay;
+
+	sup = container_of(work, struct srcu_usage, irq_work);
+	ssp = sup->srcu_ssp;
+
+	raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
+	delay = srcu_get_delay(ssp);
+	raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
+
+	queue_delayed_work(rcu_gp_wq, &sup->work, !!delay);
+}
+
 void srcutorture_get_gp_data(struct srcu_struct *ssp, int *flags,
 			     unsigned long *gp_seq)
 {
-- 
2.50.1 (Apple Git-155)