[PATCH v14 8/8] mm: hugetlb: optimize the code with the help of the compiler

[Muchun Song]

We cannot optimize if a "struct page" crosses page boundaries. If
it is true, we can optimize the code with the help of a compiler.
When free_vmemmap_pages_per_hpage() returns zero, most functions are
optimized by the compiler.

Signed-off-by: Muchun Song <songmuc...@bytedance.com>
---
 include/linux/hugetlb.h |  3 ++-
 mm/hugetlb_vmemmap.c    | 13 +++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 822ab2f5542a..7bfb06e16298 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -878,7 +878,8 @@ extern bool hugetlb_free_vmemmap_enabled;
 
 static inline bool is_hugetlb_free_vmemmap_enabled(void)
 {
-       return hugetlb_free_vmemmap_enabled;
+       return hugetlb_free_vmemmap_enabled &&
+              is_power_of_2(sizeof(struct page));
 }
 #else
 static inline bool is_hugetlb_free_vmemmap_enabled(void)
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 8efad9978821..068d0e0cebc8 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -211,6 +211,12 @@ early_param("hugetlb_free_vmemmap", 
early_hugetlb_free_vmemmap_param);
  */
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
+       /*
+        * This check aims to let the compiler help us optimize the code as
+        * much as possible.
+        */
+       if (!is_power_of_2(sizeof(struct page)))
+               return 0;
        return h->nr_free_vmemmap_pages;
 }
 
@@ -280,6 +286,13 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
        BUILD_BUG_ON(NR_USED_SUBPAGE >=
                     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
 
+       /*
+        * The compiler can help us to optimize this function to null
+        * when the size of the struct page is not power of 2.
+        */
+       if (!is_power_of_2(sizeof(struct page)))
+               return;
+
        if (!hugetlb_free_vmemmap_enabled)
                return;
 
-- 
2.11.0