rcu: limit rcu_node leaf-level fanout

Some recent benchmarks have indicated possible lock contention on the
leaf-level rcu_node locks.  This commit therefore limits the number of
CPUs per leaf-level rcu_node structure to 16, in other words, there
can be at most 16 rcu_data structures fanning into a given rcu_node
structure.  Prior to this, the limit was 32 on 32-bit systems and 64 on
64-bit systems.

Note that the fanout of non-leaf rcu_node structures is unchanged.  The
organization of accesses to the rcu_node tree is such that references
to non-leaf rcu_node structures are much less frequent than to the
leaf structures.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcutree.c

@@ -1869,8 +1869,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+	for (i = NUM_RCU_LVLS - 1; i > 0; i--)
 		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+	rsp->levelspread[0] = RCU_FANOUT_LEAF;
 }
 #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)

kernel/rcutree.h

@@ -31,46 +31,51 @@
 /*
  * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
  * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
  */
 #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
+#if CONFIG_RCU_FANOUT > 16
+#define RCU_FANOUT_LEAF       16
+#else /* #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_LEAF       (CONFIG_RCU_FANOUT)
+#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
 #  define NUM_RCU_LVLS	      1
 #  define NUM_RCU_LVL_0	      1
 #  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
+#elif NR_CPUS <= RCU_FANOUT_2
 #  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_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
 #  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
+#elif NR_CPUS <= RCU_FANOUT_3
 #  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_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+#  define NUM_RCU_LVL_3	      (NR_CPUS)
 #  define NUM_RCU_LVL_4	      0
-#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#elif NR_CPUS <= RCU_FANOUT_4
 #  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
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+#  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+#  define NUM_RCU_LVL_4	      (NR_CPUS)
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
 
 #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)