diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index d3ea1f3c06a0..a7d7b7ade42f 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void)
  * are flush_tlb_*() routines, and these run after flush_cache_*()
  * which performs the flushw.
  *
- * The SMP TLB coherency scheme we use works as follows:
- *
- * 1) mm->cpu_vm_mask is a bit mask of which cpus an address
- *    space has (potentially) executed on, this is the heuristic
- *    we use to avoid doing cross calls.
- *
- *    Also, for flushing from kswapd and also for clones, we
- *    use cpu_vm_mask as the list of cpus to make run the TLB.
- *
- * 2) TLB context numbers are shared globally across all processors
- *    in the system, this allows us to play several games to avoid
- *    cross calls.
- *
- *    One invariant is that when a cpu switches to a process, and
- *    that processes tsk->active_mm->cpu_vm_mask does not have the
- *    current cpu's bit set, that tlb context is flushed locally.
- *
- *    If the address space is non-shared (ie. mm->count == 1) we avoid
- *    cross calls when we want to flush the currently running process's
- *    tlb state.  This is done by clearing all cpu bits except the current
- *    processor's in current->mm->cpu_vm_mask and performing the
- *    flush locally only.  This will force any subsequent cpus which run
- *    this task to flush the context from the local tlb if the process
- *    migrates to another cpu (again).
- *
- * 3) For shared address spaces (threads) and swapping we bite the
- *    bullet for most cases and perform the cross call (but only to
- *    the cpus listed in cpu_vm_mask).
- *
- *    The performance gain from "optimizing" away the cross call for threads is
- *    questionable (in theory the big win for threads is the massive sharing of
- *    address space state across processors).
+ * mm->cpu_vm_mask is a bit mask of which cpus an address
+ * space has (potentially) executed on, this is the heuristic
+ * we use to limit cross calls.
  */
 
 /* This currently is only used by the hugetlb arch pre-fault
@@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void)
 void smp_flush_tlb_mm(struct mm_struct *mm)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (atomic_read(&mm->mm_users) == 1) {
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-		goto local_flush_and_out;
-	}
+	get_cpu();
 
 	smp_cross_call_masked(&xcall_flush_tlb_mm,
 			      ctx, 0, 0,
 			      mm_cpumask(mm));
 
-local_flush_and_out:
 	__flush_tlb_mm(ctx, SECONDARY_CONTEXT);
 
 	put_cpu();
@@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 {
 	u32 ctx = CTX_HWBITS(mm->context);
 	struct tlb_pending_info info;
-	int cpu = get_cpu();
+
+	get_cpu();
 
 	info.ctx = ctx;
 	info.nr = nr;
 	info.vaddrs = vaddrs;
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
-				       &info, 1);
+	smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+			       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
@@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	unsigned long context = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_cross_call_masked(&xcall_flush_tlb_page,
-				      context, vaddr, 0,
-				      mm_cpumask(mm));
+	get_cpu();
+
+	smp_cross_call_masked(&xcall_flush_tlb_page,
+			      context, vaddr, 0,
+			      mm_cpumask(mm));
+
 	__flush_tlb_page(context, vaddr);
 
 	put_cpu();