sh: Use local TLB flush for get_mmu_context() ASID exhaustion.

When get_mmu_context() runs out of new ASIDs it flushes the TLB and
wraps around. Despite the fact the ASIDs are tracked per-CPU, a global
TLB flush was being used. Switch this over to a local one, as matches
the intent.
Signed-off-by: NPaul Mundt <lethal@linux-sh.org>

arch/sh/include/asm/mmu_context.h

@@ -69,7 +69,7 @@ static inline void get_mmu_context(struct mm_struct *mm, unsigned int cpu)
 		 * We exhaust ASID of this version.
 		 * Flush all TLB and start new cycle.
 		 */
-		flush_tlb_all();
+		local_flush_tlb_all();
 
 #ifdef CONFIG_SUPERH64
 		/*