rcu: Add a TINY_PREEMPT_RCU

Implement a small-memory-footprint uniprocessor-only implementation of
preemptible RCU.  This implementation uses but a single blocked-tasks
list rather than the combinatorial number used per leaf rcu_node by
TREE_PREEMPT_RCU, which reduces memory consumption and greatly simplifies
processing.  This version also takes advantage of uniprocessor execution
to accelerate grace periods in the case where there are no readers.

The general design is otherwise broadly similar to that of TREE_PREEMPT_RCU.

This implementation is a step towards having RCU implementation driven
off of the SMP and PREEMPT kernel configuration variables, which can
happen once this implementation has accumulated sufficient experience.

Removed ACCESS_ONCE() from __rcu_read_unlock() and added barrier() as
suggested by Steve Rostedt in order to avoid the compiler-reordering
issue noted by Mathieu Desnoyers (http://lkml.org/lkml/2010/8/16/183).

As can be seen below, CONFIG_TINY_PREEMPT_RCU represents almost 5Kbyte
savings compared to CONFIG_TREE_PREEMPT_RCU.  Of course, for non-real-time
workloads, CONFIG_TINY_RCU is even better.

	CONFIG_TREE_PREEMPT_RCU

	   text	   data	    bss	    dec	   filename
	     13	      0	      0	     13	   kernel/rcupdate.o
	   6170	    825	     28	   7023	   kernel/rcutree.o
				   ----
				   7026    Total

	CONFIG_TINY_PREEMPT_RCU

	   text	   data	    bss	    dec	   filename
	     13	      0	      0	     13	   kernel/rcupdate.o
	   2081	     81	      8	   2170	   kernel/rcutiny.o
				   ----
				   2183    Total

	CONFIG_TINY_RCU (non-preemptible)

	   text	   data	    bss	    dec	   filename
	     13	      0	      0	     13	   kernel/rcupdate.o
	    719	     25	      0	    744	   kernel/rcutiny.o
				    ---
				    757    Total

Requested-by: Loïc Minier <loic.minier@canonical.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

1 files changed, 7 insertions, 3 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c756666c111..e18473f0eb78 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1202,11 +1202,13 @@ struct task_struct {
         unsigned int policy;
         cpumask_t cpus_allowed;
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
         int rcu_read_lock_nesting;
         char rcu_read_unlock_special;
-        struct rcu_node *rcu_blocked_node;
         struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+        struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -1740,7 +1742,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
 #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
@@ -1749,7 +1751,9 @@ static inline void rcu_copy_process(struct task_struct *p)
 {
         p->rcu_read_lock_nesting = 0;
         p->rcu_read_unlock_special = 0;
+#ifdef CONFIG_TREE_PREEMPT_RCU
         p->rcu_blocked_node = NULL;
+#endif
         INIT_LIST_HEAD(&p->rcu_node_entry);
 }