diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index a9f51031d3e8950af557bd9cd38c401357ab5115..d47e03e5792ad70ec0ac45aa6774e27aaa154c12 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -60,7 +60,8 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 		NUM_RCU_LVL_0,  /* root of hierarchy. */ \
 		NUM_RCU_LVL_1, \
 		NUM_RCU_LVL_2, \
-		NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
+		NUM_RCU_LVL_3, \
+		NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \
 	}, \
 	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
@@ -1877,6 +1878,9 @@ void __init rcu_init(void)
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#if NUM_RCU_LVL_4 != 0
+	printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
+#endif /* #if NUM_RCU_LVL_4 != 0 */
 	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
 	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
 	__rcu_init_preempt();
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 8bb03cb07447895539e7a1c03afda920daa47cc7..df2e0b694744204a98ad3434694b55420ffe280c 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -34,10 +34,11 @@
  * In practice, this has not been tested, so there is probably some
  * bug somewhere.
  */
-#define MAX_RCU_LVLS 3
+#define MAX_RCU_LVLS 4
 #define RCU_FANOUT	      (CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_SQ	      (RCU_FANOUT * RCU_FANOUT)
 #define RCU_FANOUT_CUBE	      (RCU_FANOUT_SQ * RCU_FANOUT)
+#define RCU_FANOUT_FOURTH     (RCU_FANOUT_CUBE * RCU_FANOUT)
 
 #if NR_CPUS <= RCU_FANOUT
 #  define NUM_RCU_LVLS	      1
@@ -45,23 +46,33 @@
 #  define NUM_RCU_LVL_1	      (NR_CPUS)
 #  define NUM_RCU_LVL_2	      0
 #  define NUM_RCU_LVL_3	      0
+#  define NUM_RCU_LVL_4	      0
 #elif NR_CPUS <= RCU_FANOUT_SQ
 #  define NUM_RCU_LVLS	      2
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
 #  define NUM_RCU_LVL_2	      (NR_CPUS)
 #  define NUM_RCU_LVL_3	      0
+#  define NUM_RCU_LVL_4	      0
 #elif NR_CPUS <= RCU_FANOUT_CUBE
 #  define NUM_RCU_LVLS	      3
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
 #  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
 #  define NUM_RCU_LVL_3	      NR_CPUS
+#  define NUM_RCU_LVL_4	      0
+#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#  define NUM_RCU_LVLS	      4
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+#  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+#  define NUM_RCU_LVL_4	      NR_CPUS
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
 #endif /* #if (NR_CPUS) <= RCU_FANOUT */
 
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
 #define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
 
 /*