Use rcu_user_{enter,exit}() calls to provide SMP ordering on context
tracking state stores:

__context_tracking_exit()
  __this_cpu_write(context_tracking.state, CONTEXT_KERNEL)
  rcu_user_exit()
    rcu_eqs_exit()
      rcu_dynticks_eqs_eit()
        rcu_dynticks_inc()
          atomic_add_return() /* smp_mb */

__context_tracking_enter()
  rcu_user_enter()
    rcu_eqs_enter()
      rcu_dynticks_eqs_enter()
        rcu_dynticks_inc()
	  atomic_add_return() /* smp_mb */
  __this_cpu_write(context_tracking.state, state)

This separates USER/KERNEL state with an smp_mb() on each side,
therefore, a user of context_tracking_state_cpu() can say the CPU must
pass through an smp_mb() before changing.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/context_tracking_state.h |   12 ++++++++++++
 kernel/context_tracking.c              |    7 ++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h

@@ -45,11 +45,23 @@ static __always_inline bool context_trac
 {
 	return __this_cpu_read(context_tracking.state) == CONTEXT_USER;
 }
+
+static __always_inline bool context_tracking_state_cpu(int cpu)
+{
+	struct context_tracking *ct = per_cpu_ptr(&context_tracking);