Use __GFP_COMP for gigantic folios to greatly reduce not only the
amount of code but also the allocation and free time.

LOC (approximately): +60, -240

Allocate and free 500 1GB hugeTLB memory without HVO by:
  time echo 500 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages
  time echo 0 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

       Before  After
Alloc  ~13s    ~10s
Free   ~15s    <1s

The above magnitude generally holds for multiple x86 and arm64 CPU
models.

Signed-off-by: Yu Zhao <redacted>
Reported-by: Frank van der Linden <redacted>
---
 include/linux/hugetlb.h |   9 +-
 mm/hugetlb.c            | 293 ++++++++--------------------------------
 2 files changed, 62 insertions(+), 240 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3100a52ceb73..98c47c394b89 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h

@@ -896,10 +896,11 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 /* Movability of hugepages depends on migration support. */
 static inline gfp_t htlb_alloc_mask(struct hstate *h)
 {
-	if (hugepage_movable_supported(h))
-		return GFP_HIGHUSER_MOVABLE;
-	else
-		return GFP_HIGHUSER;
+	gfp_t gfp = __GFP_COMP | __GFP_NOWARN;
+
+	gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER;
+
+	return gfp;
 }

 static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 71d469c8e711..efa77ce87dcc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c

@@ -56,16 +56,6 @@ struct hstate hstates[HUGE_MAX_HSTATE];
 #ifdef CONFIG_CMA
 static struct cma *hugetlb_cma[MAX_NUMNODES];
 static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata;
-static bool hugetlb_cma_folio(struct folio *folio, unsigned int order)
-{
-	return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page,
-				1 << order);
-}
-#else
-static bool hugetlb_cma_folio(struct folio *folio, unsigned int order)
-{
-	return false;
-}
 #endif
 static unsigned long hugetlb_cma_size __initdata;

@@ -100,6 +90,17 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma);

+static void hugetlb_free_folio(struct folio *folio)
+{
+#ifdef CONFIG_CMA
+	int nid = folio_nid(folio);
+
+	if (cma_free_folio(hugetlb_cma[nid], folio))
+		return;
+#endif
+	folio_put(folio);
+}
+