srcu: Use irq_work to start GP in tiny SRCU

Tiny SRCU's srcu_gp_start_if_needed() directly calls schedule_work(),
which acquires the workqueue pool->lock.

This causes a lockdep splat when call_srcu() is called with a scheduler
lock held, due to:

  call_srcu() [holding pi_lock]
    srcu_gp_start_if_needed()
      schedule_work() -> pool->lock

  workqueue_init() / create_worker() [holding pool->lock]
    wake_up_process() -> try_to_wake_up() -> pi_lock

Also add irq_work_sync() to cleanup_srcu_struct() to prevent a
use-after-free if a queued irq_work fires after cleanup begins.

Tested with rcutorture SRCU-T and no lockdep warnings.

[ Thanks to Boqun for similar fix in patch "rcu: Use an intermediate irq_work
to start process_srcu()" ]

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>

2 files changed, 22 insertions, 1 deletions

diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index dec7cbe015aa..905b629e8fa3 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -11,6 +11,7 @@
 #ifndef _LINUX_SRCU_TINY_H
 #define _LINUX_SRCU_TINY_H
 
+#include <linux/irq_work_types.h>
 #include <linux/swait.h>
 
 struct srcu_struct {
@@ -24,18 +25,21 @@ struct srcu_struct {
 	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
 	struct rcu_head **srcu_cb_tail;	/* Pending callbacks: Tail. */
 	struct work_struct srcu_work;	/* For driving grace periods. */
+	struct irq_work srcu_irq_work;	/* Defer schedule_work() to irq work. */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
 void srcu_drive_gp(struct work_struct *wp);
+void srcu_tiny_irq_work(struct irq_work *irq_work);
 
 #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored)	\
 {									\
 	.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),	\
 	.srcu_cb_tail = &name.srcu_cb_head,				\
 	.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp),	\
+	.srcu_irq_work = { .func = srcu_tiny_irq_work },		\
 	__SRCU_DEP_MAP_INIT(name)					\
 }
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 3450c3751ef7..a2e2d516e51b 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/irq_work.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate_wait.h>
@@ -41,6 +42,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp)
 	ssp->srcu_idx_max = 0;
 	INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
 	INIT_LIST_HEAD(&ssp->srcu_work.entry);
+	init_irq_work(&ssp->srcu_irq_work, srcu_tiny_irq_work);
 	return 0;
 }
 
@@ -84,6 +86,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
+	irq_work_sync(&ssp->srcu_irq_work);
 	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
 	WARN_ON(ssp->srcu_gp_waiting);
@@ -177,6 +180,20 @@ void srcu_drive_gp(struct work_struct *wp)
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
+/*
+ * Use an irq_work to defer schedule_work() to avoid acquiring the workqueue
+ * pool->lock while the caller might hold scheduler locks, causing lockdep
+ * splats due to workqueue_init() doing a wakeup.
+ */
+void srcu_tiny_irq_work(struct irq_work *irq_work)
+{
+	struct srcu_struct *ssp;
+
+	ssp = container_of(irq_work, struct srcu_struct, srcu_irq_work);
+	schedule_work(&ssp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_tiny_irq_work);
+
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
 	unsigned long cookie;
@@ -189,7 +206,7 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
 		if (likely(srcu_init_done))
-			schedule_work(&ssp->srcu_work);
+			irq_work_queue(&ssp->srcu_irq_work);
 		else if (list_empty(&ssp->srcu_work.entry))
 			list_add(&ssp->srcu_work.entry, &srcu_boot_list);
 	}