Thread (37 messages) 37 messages, 4 authors, 2021-02-18
STALE1962d REVIEWED: 3 (3M)
Revisions (22)
  1. v2 [diff vs current]
  2. v3 [diff vs current]
  3. v4 [diff vs current]
  4. v5 [diff vs current]
  5. v6 [diff vs current]
  6. v7 [diff vs current]
  7. v8 [diff vs current]
  8. v9 [diff vs current]
  9. v10 [diff vs current]
  10. v11 [diff vs current]
  11. v12 [diff vs current]
  12. v13 [diff vs current]
  13. v14 [diff vs current]
  14. v15 current
  15. v16 [diff vs current]
  16. v17 [diff vs current]
  17. v18 [diff vs current]
  18. v19 [diff vs current]
  19. v20 [diff vs current]
  20. v21 [diff vs current]
  21. v22 [diff vs current]
  22. v23 [diff vs current]

[PATCH v15 8/8] mm: hugetlb: optimize the code with the help of the compiler

From: Muchun Song <hidden>
Date: 2021-02-08 08:58:37
Also in: linux-fsdevel, linux-mm, lkml
Subsystem: hugetlb subsystem, memory management, the rest · Maintainers: Muchun Song, Oscar Salvador, Andrew Morton, Linus Torvalds

When the "struct page size" crosses page boundaries we cannot
make use of this feature. Let free_vmemmap_pages_per_hpage()
return zero if that is the case, most of the functions can be
optimized away.

Signed-off-by: Muchun Song <redacted>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 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 a67301a9d19a..2e7e1d6ee458 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
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help