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>

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -83,6 +83,9 @@ typedef struct {
 	mm_context_id_t id;
 	u16 user_psize;		/* page size index */
 
+	/* Number of bits in the mm_cpumask */
+	atomic_t active_cpus;
+
 	/* NPU NMMU context */
 	struct npu_context *npu_context;
 

arch/powerpc/include/asm/mmu_context.h

@@ -96,6 +96,14 @@ static inline void switch_mm_pgdir(struct task_struct *tsk,
 				   struct mm_struct *mm) { }
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void inc_mm_active_cpus(struct mm_struct *mm)
+{
+	atomic_inc(&mm->context.active_cpus);
+}
+#else
+static inline void inc_mm_active_cpus(struct mm_struct *mm) { }
+#endif
 
 /*
  * switch_mm is the entry point called from the architecture independent
@@ -110,6 +118,7 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 	/* Mark this context has been used on the new CPU */
 	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+		inc_mm_active_cpus(next);
 
 		/*
 		 * This full barrier orders the store to the cpumask above vs

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;

arch/powerpc/mm/mmu_context_book3s64.c

@@ -170,6 +170,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	mm_iommu_init(mm);
 #endif
+	atomic_set(&mm->context.active_cpus, 0);
+
 	return 0;
 }