diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f04b1978899d..153ddc4c47ef 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -51,8 +51,11 @@ torture_param(int, rt_boost, 2,
 torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
 torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
+torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
+/* Going much higher trips "BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!" errors */
+#define MAX_NESTED_LOCKS 8
 
-static char *torture_type = "spin_lock";
+static char *torture_type = IS_ENABLED(CONFIG_PREEMPT_RT) ? "raw_spin_lock" : "spin_lock";
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type,
 		 "Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
@@ -79,10 +82,12 @@ static void lock_torture_cleanup(void);
 struct lock_torture_ops {
 	void (*init)(void);
 	void (*exit)(void);
+	int (*nested_lock)(int tid, u32 lockset);
 	int (*writelock)(int tid);
 	void (*write_delay)(struct torture_random_state *trsp);
 	void (*task_boost)(struct torture_random_state *trsp);
 	void (*writeunlock)(int tid);
+	void (*nested_unlock)(int tid, u32 lockset);
 	int (*readlock)(int tid);
 	void (*read_delay)(struct torture_random_state *trsp);
 	void (*readunlock)(int tid);
@@ -252,6 +257,59 @@ static struct lock_torture_ops spin_lock_irq_ops = {
 	.name		= "spin_lock_irq"
 };
 
+static DEFINE_RAW_SPINLOCK(torture_raw_spinlock);
+
+static int torture_raw_spin_lock_write_lock(int tid __maybe_unused)
+__acquires(torture_raw_spinlock)
+{
+	raw_spin_lock(&torture_raw_spinlock);
+	return 0;
+}
+
+static void torture_raw_spin_lock_write_unlock(int tid __maybe_unused)
+__releases(torture_raw_spinlock)
+{
+	raw_spin_unlock(&torture_raw_spinlock);
+}
+
+static struct lock_torture_ops raw_spin_lock_ops = {
+	.writelock	= torture_raw_spin_lock_write_lock,
+	.write_delay	= torture_spin_lock_write_delay,
+	.task_boost	= torture_rt_boost,
+	.writeunlock	= torture_raw_spin_lock_write_unlock,
+	.readlock	= NULL,
+	.read_delay	= NULL,
+	.readunlock	= NULL,
+	.name		= "raw_spin_lock"
+};
+
+static int torture_raw_spin_lock_write_lock_irq(int tid __maybe_unused)
+__acquires(torture_raw_spinlock)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&torture_raw_spinlock, flags);
+	cxt.cur_ops->flags = flags;
+	return 0;
+}
+
+static void torture_raw_spin_lock_write_unlock_irq(int tid __maybe_unused)
+__releases(torture_raw_spinlock)
+{
+	raw_spin_unlock_irqrestore(&torture_raw_spinlock, cxt.cur_ops->flags);
+}
+
+static struct lock_torture_ops raw_spin_lock_irq_ops = {
+	.writelock	= torture_raw_spin_lock_write_lock_irq,
+	.write_delay	= torture_spin_lock_write_delay,
+	.task_boost	= torture_rt_boost,
+	.writeunlock	= torture_raw_spin_lock_write_unlock_irq,
+	.readlock	= NULL,
+	.read_delay	= NULL,
+	.readunlock	= NULL,
+	.name		= "raw_spin_lock_irq"
+};
+
 static DEFINE_RWLOCK(torture_rwlock);
 
 static int torture_rwlock_write_lock(int tid __maybe_unused)
@@ -365,6 +423,28 @@ static struct lock_torture_ops rw_lock_irq_ops = {
 };
 
 static DEFINE_MUTEX(torture_mutex);
+static struct mutex torture_nested_mutexes[MAX_NESTED_LOCKS];
+static struct lock_class_key nested_mutex_keys[MAX_NESTED_LOCKS];
+
+static void torture_mutex_init(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_NESTED_LOCKS; i++)
+		__mutex_init(&torture_nested_mutexes[i], __func__,
+			     &nested_mutex_keys[i]);
+}
+
+static int torture_mutex_nested_lock(int tid __maybe_unused,
+				     u32 lockset)
+{
+	int i;
+
+	for (i = 0; i < nested_locks; i++)
+		if (lockset & (1 << i))
+			mutex_lock(&torture_nested_mutexes[i]);
+	return 0;
+}
 
 static int torture_mutex_lock(int tid __maybe_unused)
 __acquires(torture_mutex)
@@ -393,11 +473,24 @@ __releases(torture_mutex)
 	mutex_unlock(&torture_mutex);
 }
 
+static void torture_mutex_nested_unlock(int tid __maybe_unused,
+					u32 lockset)
+{
+	int i;
+
+	for (i = nested_locks - 1; i >= 0; i--)
+		if (lockset & (1 << i))
+			mutex_unlock(&torture_nested_mutexes[i]);
+}
+
 static struct lock_torture_ops mutex_lock_ops = {
+	.init		= torture_mutex_init,
+	.nested_lock	= torture_mutex_nested_lock,
 	.writelock	= torture_mutex_lock,
 	.write_delay	= torture_mutex_delay,
 	.task_boost     = torture_rt_boost,
 	.writeunlock	= torture_mutex_unlock,
+	.nested_unlock	= torture_mutex_nested_unlock,
 	.readlock       = NULL,
 	.read_delay     = NULL,
 	.readunlock     = NULL,
@@ -504,6 +597,28 @@ static struct lock_torture_ops ww_mutex_lock_ops = {
 
 #ifdef CONFIG_RT_MUTEXES
 static DEFINE_RT_MUTEX(torture_rtmutex);
+static struct rt_mutex torture_nested_rtmutexes[MAX_NESTED_LOCKS];
+static struct lock_class_key nested_rtmutex_keys[MAX_NESTED_LOCKS];
+
+static void torture_rtmutex_init(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_NESTED_LOCKS; i++)
+		__rt_mutex_init(&torture_nested_rtmutexes[i], __func__,
+				&nested_rtmutex_keys[i]);
+}
+
+static int torture_rtmutex_nested_lock(int tid __maybe_unused,
+				       u32 lockset)
+{
+	int i;
+
+	for (i = 0; i < nested_locks; i++)
+		if (lockset & (1 << i))
+			rt_mutex_lock(&torture_nested_rtmutexes[i]);
+	return 0;
+}
 
 static int torture_rtmutex_lock(int tid __maybe_unused)
 __acquires(torture_rtmutex)
@@ -545,11 +660,24 @@ static void torture_rt_boost_rtmutex(struct torture_random_state *trsp)
 	__torture_rt_boost(trsp);
 }
 
+static void torture_rtmutex_nested_unlock(int tid __maybe_unused,
+					  u32 lockset)
+{
+	int i;
+
+	for (i = nested_locks - 1; i >= 0; i--)
+		if (lockset & (1 << i))
+			rt_mutex_unlock(&torture_nested_rtmutexes[i]);
+}
+
 static struct lock_torture_ops rtmutex_lock_ops = {
+	.init		= torture_rtmutex_init,
+	.nested_lock	= torture_rtmutex_nested_lock,
 	.writelock	= torture_rtmutex_lock,
 	.write_delay	= torture_rtmutex_delay,
 	.task_boost     = torture_rt_boost_rtmutex,
 	.writeunlock	= torture_rtmutex_unlock,
+	.nested_unlock	= torture_rtmutex_nested_unlock,
 	.readlock       = NULL,
 	.read_delay     = NULL,
 	.readunlock     = NULL,
@@ -684,6 +812,8 @@ static int lock_torture_writer(void *arg)
 	struct lock_stress_stats *lwsp = arg;
 	int tid = lwsp - cxt.lwsa;
 	DEFINE_TORTURE_RANDOM(rand);
+	u32 lockset_mask;
+	bool skip_main_lock;
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
 	set_user_nice(current, MAX_NICE);
@@ -692,19 +822,40 @@ static int lock_torture_writer(void *arg)
 		if ((torture_random(&rand) & 0xfffff) == 0)
 			schedule_timeout_uninterruptible(1);
 
-		cxt.cur_ops->task_boost(&rand);
-		cxt.cur_ops->writelock(tid);
-		if (WARN_ON_ONCE(lock_is_write_held))
-			lwsp->n_lock_fail++;
-		lock_is_write_held = true;
-		if (WARN_ON_ONCE(atomic_read(&lock_is_read_held)))
-			lwsp->n_lock_fail++; /* rare, but... */
+		lockset_mask = torture_random(&rand);
+		/*
+		 * When using nested_locks, we want to occasionally
+		 * skip the main lock so we can avoid always serializing
+		 * the lock chains on that central lock. By skipping the
+		 * main lock occasionally, we can create different
+		 * contention patterns (allowing for multiple disjoint
+		 * blocked trees)
+		 */
+		skip_main_lock = (nested_locks &&
+				 !(torture_random(&rand) % 100));
 
-		lwsp->n_lock_acquired++;
+		cxt.cur_ops->task_boost(&rand);
+		if (cxt.cur_ops->nested_lock)
+			cxt.cur_ops->nested_lock(tid, lockset_mask);
+
+		if (!skip_main_lock) {
+			cxt.cur_ops->writelock(tid);
+			if (WARN_ON_ONCE(lock_is_write_held))
+				lwsp->n_lock_fail++;
+			lock_is_write_held = true;
+			if (WARN_ON_ONCE(atomic_read(&lock_is_read_held)))
+				lwsp->n_lock_fail++; /* rare, but... */
+
+			lwsp->n_lock_acquired++;
+		}
 		cxt.cur_ops->write_delay(&rand);
-		lock_is_write_held = false;
-		WRITE_ONCE(last_lock_release, jiffies);
-		cxt.cur_ops->writeunlock(tid);
+		if (!skip_main_lock) {
+			lock_is_write_held = false;
+			WRITE_ONCE(last_lock_release, jiffies);
+			cxt.cur_ops->writeunlock(tid);
+		}
+		if (cxt.cur_ops->nested_unlock)
+			cxt.cur_ops->nested_unlock(tid, lockset_mask);
 
 		stutter_wait("lock_torture_writer");
 	} while (!torture_must_stop());
@@ -845,11 +996,11 @@ lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
 				const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
-		 "--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+		 "--- %s%s: nwriters_stress=%d nreaders_stress=%d nested_locks=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
 		 torture_type, tag, cxt.debug_lock ? " [debug]": "",
-		 cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval,
-		 verbose, shuffle_interval, stutter, shutdown_secs,
-		 onoff_interval, onoff_holdoff);
+		 cxt.nrealwriters_stress, cxt.nrealreaders_stress,
+		 nested_locks, stat_interval, verbose, shuffle_interval,
+		 stutter, shutdown_secs, onoff_interval, onoff_holdoff);
 }
 
 static void lock_torture_cleanup(void)
@@ -919,6 +1070,7 @@ static int __init lock_torture_init(void)
 	static struct lock_torture_ops *torture_ops[] = {
 		&lock_busted_ops,
 		&spin_lock_ops, &spin_lock_irq_ops,
+		&raw_spin_lock_ops, &raw_spin_lock_irq_ops,
 		&rw_lock_ops, &rw_lock_irq_ops,
 		&mutex_lock_ops,
 		&ww_mutex_lock_ops,
@@ -1068,6 +1220,10 @@ static int __init lock_torture_init(void)
 		}
 	}
 
+	/* cap nested_locks to MAX_NESTED_LOCKS */
+	if (nested_locks > MAX_NESTED_LOCKS)
+		nested_locks = MAX_NESTED_LOCKS;
+
 	if (cxt.cur_ops->readlock) {
 		reader_tasks = kcalloc(cxt.nrealreaders_stress,
 				       sizeof(reader_tasks[0]),
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
index 41bae5824339..28e23d05d5a5 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -5,3 +5,5 @@ LOCK04
 LOCK05
 LOCK06
 LOCK07
+LOCK08
+LOCK09
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK08 b/tools/testing/selftests/rcutorture/configs/lock/LOCK08
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK08
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot
new file mode 100644
index 000000000000..b8b6caebb89e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot
@@ -0,0 +1 @@
+locktorture.torture_type=mutex_lock locktorture.nested_locks=8
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK09 b/tools/testing/selftests/rcutorture/configs/lock/LOCK09
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK09
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot
new file mode 100644
index 000000000000..fd5eff148a93
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot
@@ -0,0 +1 @@
+locktorture.torture_type=rtmutex_lock locktorture.nested_locks=8