1 files changed, 15 insertions, 4 deletions
diff --git a/mm/gup.c b/mm/gup.c
index a6c20a7b3c49..8651309f8ec3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -420,6 +420,17 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
 }
 EXPORT_SYMBOL(unpin_user_pages);
 
+/*
+ * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
+ * lifecycle.  Avoid setting the bit unless necessary, or it might cause write
+ * cache bouncing on large SMP machines for concurrent pinned gups.
+ */
+static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
+{
+	if (!test_bit(MMF_HAS_PINNED, mm_flags))
+		set_bit(MMF_HAS_PINNED, mm_flags);
+}
+
 #ifdef CONFIG_MMU
 static struct page *no_page_table(struct vm_area_struct *vma,
 		unsigned int flags)
@@ -1320,8 +1331,8 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 		BUG_ON(*locked != 1);
 	}
 
-	if ((flags & FOLL_PIN) && !atomic_read(&mm->has_pinned))
-		atomic_set(&mm->has_pinned, 1);
+	if (flags & FOLL_PIN)
+		mm_set_has_pinned_flag(&mm->flags);
 
 	/*
 	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
@@ -2641,8 +2652,8 @@ static int internal_get_user_pages_fast(unsigned long start,
 				       FOLL_FAST_ONLY)))
 		return -EINVAL;
 
-	if ((gup_flags & FOLL_PIN) && !atomic_read(&current->mm->has_pinned))
-		atomic_set(&current->mm->has_pinned, 1);
+	if (gup_flags & FOLL_PIN)
+		mm_set_has_pinned_flag(&current->mm->flags);
 
 	if (!(gup_flags & FOLL_FAST_ONLY))
 		might_lock_read(&current->mm->mmap_lock);