@@ -3056,7 +3056,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
#endif
void vmemmap_remap_free(unsigned long start, unsigned long end,
- unsigned long reuse);
+ unsigned long reuse, struct list_head *pgtables);
int vmemmap_remap_alloc(unsigned long start, unsigned long end,
unsigned long reuse, gfp_t gfp_mask);
@@ -1609,6 +1609,13 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid)
static void __prep_new_huge_page(struct hstate *h, struct page *page)
{
free_huge_page_vmemmap(h, page);
+ /*
+ * Because we store preallocated pages on @page->lru,
+ * vmemmap_pgtable_free() must be called before the
+ * initialization of @page->lru in INIT_LIST_HEAD().
+ */
+ vmemmap_pgtable_free(&page->lru);
+
INIT_LIST_HEAD(&page->lru);
set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
hugetlb_set_page_subpool(page, NULL);
@@ -1775,14 +1782,29 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
nodemask_t *node_alloc_noretry)
{
struct page *page;
+ LIST_HEAD(pgtables);
+
+ if (vmemmap_pgtable_prealloc(h, &pgtables))
+ return NULL;
if (hstate_is_gigantic(h))
page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
else
page = alloc_buddy_huge_page(h, gfp_mask,
nid, nmask, node_alloc_noretry);
- if (!page)
+ if (!page) {
+ vmemmap_pgtable_free(&pgtables);
return NULL;
+ }
+
+ /*
+ * 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(&page->lru);
+ list_splice(&pgtables, &page->lru);
if (hstate_is_gigantic(h))
prep_compound_gigantic_page(page, huge_page_order(h));
@@ -2417,6 +2439,10 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
int nid = page_to_nid(old_page);
struct page *new_page;
int ret = 0;
+ LIST_HEAD(pgtables);
+
+ if (vmemmap_pgtable_prealloc(h, &pgtables))
+ return -ENOMEM;
/*
* Before dissolving the page, we need to allocate a new one for the
@@ -2426,8 +2452,15 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
* under the lock.
*/
new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL);
- if (!new_page)
+ if (!new_page) {
+ vmemmap_pgtable_free(&pgtables);
return -ENOMEM;
+ }
+
+ /* See the comments in alloc_fresh_huge_page(). */
+ INIT_LIST_HEAD(&new_page->lru);
+ list_splice(&pgtables, &new_page->lru);
+
__prep_new_huge_page(h, new_page);
retry:
@@ -2711,6 +2744,7 @@ static void __init gather_bootmem_prealloc(void)
WARN_ON(page_count(page) != 1);
prep_compound_huge_page(page, huge_page_order(h));
WARN_ON(PageReserved(page));
+ gigantic_vmemmap_pgtable_init(m, page);
prep_new_huge_page(h, page, page_to_nid(page));
put_page(page); /* free it into the hugepage allocator */
@@ -2763,6 +2797,10 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
break;
cond_resched();
}
+
+ if (hstate_is_gigantic(h))
+ i -= gigantic_vmemmap_pgtable_prealloc();
+
if (i < h->max_huge_pages) {
char buf[32];
@@ -375,7 +375,8 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
* to the page which @vmemmap_reuse is mapped to, then free the pages
* which the range [@vmemmap_addr, @vmemmap_end] is mapped to.
*/
- vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse);
+ vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse,
+ &head->lru);
SetHPageVmemmapOptimized(head);
}
@@ -42,6 +42,8 @@
* @reuse_addr: the virtual address of the @reuse_page page.
* @vmemmap_pages: the list head of the vmemmap pages that can be freed
* or is mapped from.
+ * @pgtables: the list of page tables which is used for splitting huge
+ * PMD page tables.
*/
struct vmemmap_remap_walk {
void (*remap_pte)(pte_t *pte, unsigned long addr,
@@ -49,8 +51,49 @@ struct vmemmap_remap_walk {
struct page *reuse_page;
unsigned long reuse_addr;
struct list_head *vmemmap_pages;
+ struct list_head *pgtables;
};
+#define VMEMMAP_HPMD_ORDER (PMD_SHIFT - PAGE_SHIFT)
+#define VMEMMAP_HPMD_NR (1 << VMEMMAP_HPMD_ORDER)
+
+static inline pte_t *pte_withdraw(struct vmemmap_remap_walk *walk)
+{
+ pgtable_t pgtable;
+
+ pgtable = list_first_entry(walk->pgtables, struct page, lru);
+ list_del(&pgtable->lru);
+
+ return page_to_virt(pgtable);
+}
+
+static void split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start,
+ struct vmemmap_remap_walk *walk)
+{
+ int i;
+ pmd_t tmp;
+ pte_t *new = pte_withdraw(walk);
+ struct page *page = pmd_page(*pmd);
+ unsigned long addr = start;
+
+ pmd_populate_kernel(&init_mm, &tmp, new);
+
+ for (i = 0; i < VMEMMAP_HPMD_NR; i++, addr += PAGE_SIZE) {
+ pte_t entry, *pte;
+ pgprot_t pgprot = PAGE_KERNEL;
+
+ entry = mk_pte(page + i, pgprot);
+ pte = pte_offset_kernel(&tmp, addr);
+ set_pte_at(&init_mm, addr, pte, entry);
+ }
+
+ /* Make pte visible before pmd. See comment in __pte_alloc(). */
+ smp_wmb();
+ pmd_populate_kernel(&init_mm, pmd, new);
+
+ flush_tlb_kernel_range(start, start + PMD_SIZE);
+}
+
static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end,
struct vmemmap_remap_walk *walk)
@@ -84,8 +127,8 @@ static void vmemmap_pmd_range(pud_t *pud, unsigned long addr,
pmd = pmd_offset(pud, addr);
do {
- BUG_ON(pmd_leaf(*pmd));
-
+ if (pmd_leaf(*pmd))
+ split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk);
next = pmd_addr_end(addr, end);
vmemmap_pte_range(pmd, addr, next, walk);
} while (pmd++, addr = next, addr != end);
@@ -192,18 +235,17 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
* @end: end address of the vmemmap virtual address range that we want to
* remap.
* @reuse: reuse address.
- *
- * Note: This function depends on vmemmap being base page mapped. Please make
- * sure that we disable PMD mapping of vmemmap pages when calling this function.
+ * @pgtables: the list of page tables used for splitting huge PMD.
*/
void vmemmap_remap_free(unsigned long start, unsigned long end,
- unsigned long reuse)
+ unsigned long reuse, struct list_head *pgtables)
{
LIST_HEAD(vmemmap_pages);
struct vmemmap_remap_walk walk = {
.remap_pte = vmemmap_remap_pte,
.reuse_addr = reuse,
.vmemmap_pages = &vmemmap_pages,
+ .pgtables = pgtables,
};
/*
@@ -221,7 +263,10 @@ void vmemmap_remap_free(unsigned long start, unsigned long end,
*/
BUG_ON(start - reuse != PAGE_SIZE);
+ mmap_write_lock(&init_mm);
vmemmap_remap_range(reuse, end, &walk);
+ mmap_write_unlock(&init_mm);
+
free_vmemmap_page_list(&vmemmap_pages);
}
@@ -287,12 +332,12 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end,
/* See the comment in the vmemmap_remap_free(). */
BUG_ON(start - reuse != PAGE_SIZE);
- might_sleep_if(gfpflags_allow_blocking(gfp_mask));
-
if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages))
return -ENOMEM;
+ mmap_read_lock(&init_mm);
vmemmap_remap_range(reuse, end, &walk);
+ mmap_read_unlock(&init_mm);
return 0;
}
If the vmemmap is huge PMD mapped, we should split the huge PMD firstly and then we can change the PTE page table entry. In this patch, we add the ability of splitting the huge PMD mapping of vmemmap pages. Signed-off-by: Muchun Song <songmuchun@bytedance.com> --- include/linux/mm.h | 2 +- mm/hugetlb.c | 42 ++++++++++++++++++++++++++++++++++-- mm/hugetlb_vmemmap.c | 3 ++- mm/sparse-vmemmap.c | 61 +++++++++++++++++++++++++++++++++++++++++++++------- 4 files changed, 96 insertions(+), 12 deletions(-)