@@ -1381,6 +1381,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
{
int i;
+ alloc_huge_page_vmemmap(h, page);
+
for (i = 0; i < pages_per_huge_page(h); i++) {
page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
1 << PG_referenced | 1 << PG_dirty |
@@ -95,6 +95,7 @@
#define pr_fmt(fmt) "HugeTLB vmemmap: " fmt
#include <linux/bootmem_info.h>
+#include <linux/delay.h>
#include "hugetlb_vmemmap.h"
/*
@@ -108,6 +109,8 @@
#define RESERVE_VMEMMAP_NR 2U
#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
#define VMEMMAP_TAIL_PAGE_REUSE -1
+#define GFP_VMEMMAP_PAGE \
+ (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_HIGH)
#ifndef VMEMMAP_HPAGE_SHIFT
#define VMEMMAP_HPAGE_SHIFT HPAGE_SHIFT
@@ -124,6 +127,11 @@
(__boundary - 1 < (end) - 1) ? __boundary : (end); \
})
+typedef void (*vmemmap_remap_pte_func_t)(struct page *reuse, pte_t *pte,
+ unsigned long start, unsigned long end,
+ void *priv);
+
+
static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
{
return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -163,9 +171,40 @@ static pmd_t *vmemmap_to_pmd(unsigned long addr)
return pmd;
}
+static void vmemmap_restore_pte_range(struct page *reuse, pte_t *pte,
+ unsigned long start, unsigned long end,
+ void *priv)
+{
+ pgprot_t pgprot = PAGE_KERNEL;
+ void *from = page_to_virt(reuse);
+ unsigned long addr;
+ struct list_head *pages = priv;
+
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ void *to;
+ struct page *page;
+
+ VM_BUG_ON(pte_none(*pte) || pte_page(*pte) != reuse);
+
+ page = list_first_entry(pages, struct page, lru);
+ list_del(&page->lru);
+ to = page_to_virt(page);
+ copy_page(to, from);
+
+ /*
+ * Make sure that any data that writes to the @to is made
+ * visible to the physical page.
+ */
+ flush_kernel_vmap_range(to, PAGE_SIZE);
+
+ prepare_vmemmap_page(page);
+ set_pte_at(&init_mm, addr, pte++, mk_pte(page, pgprot));
+ }
+}
+
static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
unsigned long start, unsigned long end,
- struct list_head *vmemmap_pages)
+ void *priv)
{
/*
* Make the tail pages are mapped with read-only to catch
@@ -174,6 +213,7 @@ static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
pgprot_t pgprot = PAGE_KERNEL_RO;
pte_t entry = mk_pte(reuse, pgprot);
unsigned long addr;
+ struct list_head *pages = priv;
for (addr = start; addr < end; addr += PAGE_SIZE, pte++) {
struct page *page;
@@ -181,14 +221,14 @@ static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
VM_BUG_ON(pte_none(*pte));
page = pte_page(*pte);
- list_add(&page->lru, vmemmap_pages);
+ list_add(&page->lru, pages);
set_pte_at(&init_mm, addr, pte, entry);
}
}
static void vmemmap_remap_range(unsigned long start, unsigned long end,
- struct list_head *vmemmap_pages)
+ vmemmap_remap_pte_func_t func, void *priv)
{
pmd_t *pmd;
unsigned long next, addr = start;
@@ -208,12 +248,52 @@ static void vmemmap_remap_range(unsigned long start, unsigned long end,
reuse = pte_page(pte[VMEMMAP_TAIL_PAGE_REUSE]);
next = vmemmap_hpage_addr_end(addr, end);
- vmemmap_reuse_pte_range(reuse, pte, addr, next, vmemmap_pages);
+ func(reuse, pte, addr, next, priv);
} while (pmd++, addr = next, addr != end);
flush_tlb_kernel_range(start, end);
}
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+ unsigned int nr = free_vmemmap_pages_per_hpage(h);
+
+ while (nr--) {
+ struct page *page;
+
+retry:
+ page = alloc_page(GFP_VMEMMAP_PAGE);
+ if (unlikely(!page)) {
+ msleep(100);
+ /*
+ * We should retry infinitely, because we cannot
+ * handle allocation failures. Once we allocate
+ * vmemmap pages successfully, then we can free
+ * a HugeTLB page.
+ */
+ goto retry;
+ }
+ list_add_tail(&page->lru, list);
+ }
+}
+
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+ unsigned long start, end;
+ unsigned long vmemmap_addr = (unsigned long)head;
+ LIST_HEAD(vmemmap_pages);
+
+ if (!free_vmemmap_pages_per_hpage(h))
+ return;
+
+ alloc_vmemmap_pages(h, &vmemmap_pages);
+
+ start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+ end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+ vmemmap_remap_range(start, end, vmemmap_restore_pte_range,
+ &vmemmap_pages);
+}
+
static inline void free_vmemmap_page_list(struct list_head *list)
{
struct page *page, *next;
@@ -235,7 +315,7 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
- vmemmap_remap_range(start, end, &vmemmap_pages);
+ vmemmap_remap_range(start, end, vmemmap_reuse_pte_range, &vmemmap_pages);
free_vmemmap_page_list(&vmemmap_pages);
}
@@ -12,6 +12,7 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
void __init hugetlb_vmemmap_init(struct hstate *h);
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
@@ -23,6 +24,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
{
}
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}
When we free a hugetlb page to the buddy, we should allocate the vmemmap pages associated with it. We can do that in the __free_hugepage(). Signed-off-by: Muchun Song <songmuchun@bytedance.com> --- mm/hugetlb.c | 2 ++ mm/hugetlb_vmemmap.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++--- mm/hugetlb_vmemmap.h | 5 +++ 3 files changed, 92 insertions(+), 5 deletions(-)