[PATCH v23 9/9] mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate

From: Muchun Song
Date: Sun May 09 2021 - 23:05:11 EST


All the infrastructure is ready, so we introduce nr_free_vmemmap_pages
field in the hstate to indicate how many vmemmap pages associated with
a HugeTLB page that can be freed to buddy allocator. And initialize it
in the hugetlb_vmemmap_init(). This patch is actual enablement of the
feature.

There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Acked-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Tested-by: Chen Huang <chenhuang5@xxxxxxxxxx>
Tested-by: Bodeddula Balasubramaniam <bodeddub@xxxxxxxxxx>
---
include/linux/hugetlb.h | 3 +++
mm/hugetlb.c | 1 +
mm/hugetlb_vmemmap.c | 33 +++++++++++++++++++++++++++++++++
mm/hugetlb_vmemmap.h | 10 ++++++----
4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3258177f6494..e078db25cf3b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -602,6 +602,9 @@ struct hstate {
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+ unsigned int nr_free_vmemmap_pages;
+#endif
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files_dfl[7];
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6e43ee6bca33..d11b41de9e07 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3517,6 +3517,7 @@ void __init hugetlb_add_hstate(unsigned int order)
h->next_nid_to_free = first_memory_node;
snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
huge_page_size(h)/1024);
+ hugetlb_vmemmap_init(h);

parsed_hstate = h;
}
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 3070e1465b1b..f9f9bb212319 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -262,3 +262,36 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)

SetHPageVmemmapOptimized(head);
}
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+ unsigned int nr_pages = pages_per_huge_page(h);
+ unsigned int vmemmap_pages;
+
+ /*
+ * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
+ * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
+ * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
+ */
+ BUILD_BUG_ON(__NR_USED_SUBPAGE >=
+ RESERVE_VMEMMAP_SIZE / sizeof(struct page));
+
+ if (!hugetlb_free_vmemmap_enabled)
+ return;
+
+ vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
+ /*
+ * The head page and the first tail page are not to be freed to buddy
+ * allocator, the other pages will map to the first tail page, so they
+ * can be freed.
+ *
+ * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true
+ * on some architectures (e.g. aarch64). See Documentation/arm64/
+ * hugetlbpage.rst for more details.
+ */
+ if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+ h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+ pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+ h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index a37771b0b82a..cb2bef8f9e73 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,17 +13,15 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
int alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+void hugetlb_vmemmap_init(struct hstate *h);

/*
* How many vmemmap pages associated with a HugeTLB page that can be freed
* to the buddy allocator.
- *
- * Todo: Returns zero for now, which means the feature is disabled. We will
- * enable it once all the infrastructure is there.
*/
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
{
- return 0;
+ return h->nr_free_vmemmap_pages;
}
#else
static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
@@ -35,6 +33,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}

+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
{
return 0;
--
2.11.0