If we want to split the huge PMD of vmemmap pages associated with each
gigantic page allocated from bootmem allocator, we should pre-allocate
the page tables from bootmem allocator. In this patch, we introduce
some helpers to preallocate page tables for gigantic pages.
Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 3 +++
mm/hugetlb_vmemmap.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++
mm/hugetlb_vmemmap.h | 13 ++++++++++
3 files changed, 79 insertions(+)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 03ca83db0a3e..c27a299c4211 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -622,6 +622,9 @@ struct hstate {
struct huge_bootmem_page {
struct list_head list;
struct hstate *hstate;
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+ pte_t *vmemmap_pte;
+#endif
};
int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 628e2752714f..6f3a47b4ebd3 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -171,6 +171,7 @@
#define pr_fmt(fmt) "HugeTLB: " fmt
#include <linux/list.h>
+#include <linux/memblock.h>
#include <asm/pgalloc.h>
#include "hugetlb_vmemmap.h"
@@ -263,6 +264,68 @@ int vmemmap_pgtable_prealloc(struct hstate *h, struct list_head *pgtables)
return -ENOMEM;
}
+unsigned long __init gigantic_vmemmap_pgtable_prealloc(void)
+{
+ struct huge_bootmem_page *m, *tmp;
+ unsigned long nr_free = 0;
+
+ list_for_each_entry_safe(m, tmp, &huge_boot_pages, list) {
+ struct hstate *h = m->hstate;
+ unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+ unsigned long size;
+
+ if (!nr)
+ continue;
+
+ size = nr << PAGE_SHIFT;
+ m->vmemmap_pte = memblock_alloc_try_nid(size, PAGE_SIZE, 0,
+ MEMBLOCK_ALLOC_ACCESSIBLE,
+ NUMA_NO_NODE);
+ if (!m->vmemmap_pte) {
+ nr_free++;
+ list_del(&m->list);
+ memblock_free_early(__pa(m), huge_page_size(h));
+ }
+ }
+
+ return nr_free;
+}
+
+void __init gigantic_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+ struct page *head)
+{
+ struct hstate *h = m->hstate;
+ unsigned long pte = (unsigned long)m->vmemmap_pte;
+ unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+
+ if (!nr)
+ return;
+
+ /*
+ * If we had gigantic hugepages allocated at boot time, we need
+ * to restore the 'stolen' pages to totalram_pages in order to
+ * fix confusing memory reports from free(1) and another
+ * side-effects, like CommitLimit going negative.
+ */
+ adjust_managed_page_count(head, nr);
+
+ /*
+ * Use the huge page lru list to temporarily store the preallocated
+ * pages. The preallocated pages are used and the list is emptied
+ * before the huge page is put into use. When the huge page is put
+ * into use by prep_new_huge_page() the list will be reinitialized.
+ */
+ INIT_LIST_HEAD(&head->lru);
+
+ while (nr--) {
+ struct page *pte_page = virt_to_page(pte);
+
+ __ClearPageReserved(pte_page);
+ list_add(&pte_page->lru, &head->lru);
+ pte += PAGE_SIZE;
+ }
+}
+
/*
* Previously discarded vmemmap pages will be allocated and remapping
* after this function returns zero.
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 306e15519da1..f6170720f183 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -16,6 +16,9 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head);
void hugetlb_vmemmap_init(struct hstate *h);
int vmemmap_pgtable_prealloc(struct hstate *h, struct list_head *pgtables);
void vmemmap_pgtable_free(struct list_head *pgtables);
+unsigned long gigantic_vmemmap_pgtable_prealloc(void);
+void gigantic_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+ struct page *head);
/*
* How many vmemmap pages associated with a HugeTLB page that can be freed
@@ -45,6 +48,16 @@ static inline void vmemmap_pgtable_free(struct list_head *pgtables)
{
}
+static inline unsigned long gigantic_vmemmap_pgtable_prealloc(void)
+{
+ return 0;
+}
+
+static inline void gigantic_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+ struct page *head)
+{
+}
+
static inline void hugetlb_vmemmap_init(struct hstate *h)
{
}
--
2.11.0
