powerpc/mm: Optimize detection of thread local mm's

Instead of comparing the whole CPU mask every time, let's
keep a counter of how many bits are set in the mask. Thus
testing for a local mm only requires testing if that counter
is 1 and the current CPU bit is set in the mask.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 10 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 609557569f652..a7eabff27a0fa 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -69,13 +69,22 @@ static inline int mm_is_core_local(struct mm_struct *mm)
 			      topology_sibling_cpumask(smp_processor_id()));
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	if (atomic_read(&mm->context.active_cpus) > 1)
+		return false;
+	return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm));
+}
+#else /* CONFIG_PPC_BOOK3S_64 */
 static inline int mm_is_thread_local(struct mm_struct *mm)
 {
 	return cpumask_equal(mm_cpumask(mm),
 			      cpumask_of(smp_processor_id()));
 }
+#endif /* !CONFIG_PPC_BOOK3S_64 */
 
-#else
+#else /* CONFIG_SMP */
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
 	return 1;