@@ -139,6 +139,14 @@ extern unsigned int ptrs_per_p4d;
# define VMEMMAP_START __VMEMMAP_BASE_L4
#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ * a struct page array.
+ */
+#define VMEMMAP_SIZE (1UL << (__VIRTUAL_MASK_SHIFT - PAGE_SHIFT - \
+ 1 + ilog2(sizeof(struct page))))
+#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
+
#define VMALLOC_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
@@ -1499,6 +1499,8 @@ void free_huge_page(struct page *page)
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
+ free_huge_page_vmemmap(h, page);
+
INIT_LIST_HEAD(&page->lru);
set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
set_hugetlb_cgroup(page, NULL);
@@ -92,8 +92,9 @@
* to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
* pages.
*/
-#define pr_fmt(fmt) "HugeTLB Vmemmap: " fmt
+#define pr_fmt(fmt) "HugeTLB vmemmap: " fmt
+#include <linux/bootmem_info.h>
#include "hugetlb_vmemmap.h"
/*
@@ -105,6 +106,136 @@
* these page frames. Therefore, we need to reserve two pages as vmemmap areas.
*/
#define RESERVE_VMEMMAP_NR 2U
+#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define TAIL_PAGE_REUSE -1
+
+#ifndef VMEMMAP_HPAGE_SHIFT
+#define VMEMMAP_HPAGE_SHIFT HPAGE_SHIFT
+#endif
+#define VMEMMAP_HPAGE_ORDER (VMEMMAP_HPAGE_SHIFT - PAGE_SHIFT)
+#define VMEMMAP_HPAGE_NR (1 << VMEMMAP_HPAGE_ORDER)
+#define VMEMMAP_HPAGE_SIZE ((1UL) << VMEMMAP_HPAGE_SHIFT)
+#define VMEMMAP_HPAGE_MASK (~(VMEMMAP_HPAGE_SIZE - 1))
+
+#define vmemmap_hpage_addr_end(addr, end) \
+({ \
+ unsigned long __boundary; \
+ __boundary = ((addr) + VMEMMAP_HPAGE_SIZE) & VMEMMAP_HPAGE_MASK; \
+ (__boundary - 1 < (end) - 1) ? __boundary : (end); \
+})
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+ return h->nr_free_vmemmap_pages;
+}
+
+static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
+{
+ return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
+}
+
+static inline unsigned long vmemmap_pages_size_per_hpage(struct hstate *h)
+{
+ return (unsigned long)vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
+}
+
+/*
+ * Walk a vmemmap address to the pmd it maps.
+ */
+static pmd_t *vmemmap_to_pmd(unsigned long page)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+
+ if (page < VMEMMAP_START || page >= VMEMMAP_END)
+ return NULL;
+
+ pgd = pgd_offset_k(page);
+ if (pgd_none(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, page);
+ if (p4d_none(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, page);
+ if (pud_none(*pud) || pud_bad(*pud))
+ return NULL;
+
+ return pmd_offset(pud, page);
+}
+
+static inline void free_vmemmap_page_list(struct list_head *list)
+{
+ struct page *page, *next;
+
+ list_for_each_entry_safe(page, next, list, lru) {
+ list_del(&page->lru);
+ free_vmemmap_page(page);
+ }
+}
+
+static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+ unsigned long start,
+ unsigned long end,
+ struct list_head *free_pages)
+{
+ /* Make the tail pages are mapped read-only. */
+ pgprot_t pgprot = PAGE_KERNEL_RO;
+ pte_t entry = mk_pte(reuse, pgprot);
+ unsigned long addr;
+
+ for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
+ struct page *page;
+ pte_t old = *ptep;
+
+ VM_WARN_ON(!pte_present(old));
+ page = pte_page(old);
+ list_add(&page->lru, free_pages);
+
+ set_pte_at(&init_mm, addr, ptep, entry);
+ }
+}
+
+static void __free_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+ unsigned long end,
+ struct list_head *vmemmap_pages)
+{
+ unsigned long next, addr = start;
+ struct page *reuse = NULL;
+
+ do {
+ pte_t *ptep;
+
+ ptep = pte_offset_kernel(pmd, addr);
+ if (!reuse)
+ reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+ next = vmemmap_hpage_addr_end(addr, end);
+ __free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+ vmemmap_pages);
+ } while (pmd++, addr = next, addr != end);
+
+ flush_tlb_kernel_range(start, end);
+}
+
+void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+ pmd_t *pmd;
+ unsigned long start, end;
+ unsigned long vmemmap_addr = (unsigned long)head;
+ LIST_HEAD(free_pages);
+
+ if (!free_vmemmap_pages_per_hpage(h))
+ return;
+
+ pmd = vmemmap_to_pmd(vmemmap_addr);
+ BUG_ON(!pmd);
+
+ start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+ end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+ __free_huge_page_pmd_vmemmap(pmd, start, end, &free_pages);
+ free_vmemmap_page_list(&free_pages);
+}
void __init hugetlb_vmemmap_init(struct hstate *h)
{
@@ -12,9 +12,14 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
void __init hugetlb_vmemmap_init(struct hstate *h);
+void free_huge_page_vmemmap(struct hstate *h, struct page *head);
#else
static inline void hugetlb_vmemmap_init(struct hstate *h)
{
}
+
+static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
#endif /* _LINUX_HUGETLB_VMEMMAP_H */
When we allocate a hugetlb page from the buddy, we should free the unused vmemmap pages associated with it. We can do that in the prep_new_huge_page(). Signed-off-by: Muchun Song <songmuchun@bytedance.com> --- arch/x86/include/asm/pgtable_64_types.h | 8 ++ mm/hugetlb.c | 2 + mm/hugetlb_vmemmap.c | 133 +++++++++++++++++++++++++++++++- mm/hugetlb_vmemmap.h | 5 ++ 4 files changed, 147 insertions(+), 1 deletion(-)