1 files changed, 19 insertions, 1 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 40269a2bf6f9..4b75d591eb5e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -130,7 +130,25 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
                               unsigned long start, unsigned long end)
 {
-        mpx_notify_unmap(mm, vma, start, end);
+        /*
+         * mpx_notify_unmap() goes and reads a rarely-hot
+         * cacheline in the mm_struct.  That can be expensive
+         * enough to be seen in profiles.
+         *
+         * The mpx_notify_unmap() call and its contents have been
+         * observed to affect munmap() performance on hardware
+         * where MPX is not present.
+         *
+         * The unlikely() optimizes for the fast case: no MPX
+         * in the CPU, or no MPX use in the process.  Even if
+         * we get this wrong (in the unlikely event that MPX
+         * is widely enabled on some system) the overhead of
+         * MPX itself (reading bounds tables) is expected to
+         * overwhelm the overhead of getting this unlikely()
+         * consistently wrong.
+         */
+        if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
+                mpx_notify_unmap(mm, vma, start, end);
 }
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */