#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
#include <asm/page.h>
#include <asm/pgtable.h>
(vma->vm_pgoff >> huge_page_order(h));
}
+pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
+ unsigned long address)
+{
+ return vma_hugecache_offset(hstate_vma(vma), vma, address);
+}
+
/*
* Return the size of the pages allocated when backing a VMA. In the majority
* cases this will be same size as used by the page table entries.
}
}
-static void copy_gigantic_page(struct page *dst, struct page *src,
+static void copy_user_gigantic_page(struct page *dst, struct page *src,
unsigned long addr, struct vm_area_struct *vma)
{
int i;
struct hstate *h = hstate_vma(vma);
struct page *dst_base = dst;
struct page *src_base = src;
- might_sleep();
+
for (i = 0; i < pages_per_huge_page(h); ) {
cond_resched();
copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
src = mem_map_next(src, src_base, i);
}
}
-static void copy_huge_page(struct page *dst, struct page *src,
+
+static void copy_user_huge_page(struct page *dst, struct page *src,
unsigned long addr, struct vm_area_struct *vma)
{
int i;
struct hstate *h = hstate_vma(vma);
if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
- copy_gigantic_page(dst, src, addr, vma);
+ copy_user_gigantic_page(dst, src, addr, vma);
return;
}
}
}
+static void copy_gigantic_page(struct page *dst, struct page *src)
+{
+ int i;
+ struct hstate *h = page_hstate(src);
+ struct page *dst_base = dst;
+ struct page *src_base = src;
+
+ for (i = 0; i < pages_per_huge_page(h); ) {
+ cond_resched();
+ copy_highpage(dst, src);
+
+ i++;
+ dst = mem_map_next(dst, dst_base, i);
+ src = mem_map_next(src, src_base, i);
+ }
+}
+
+void copy_huge_page(struct page *dst, struct page *src)
+{
+ int i;
+ struct hstate *h = page_hstate(src);
+
+ if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
+ copy_gigantic_page(dst, src);
+ return;
+ }
+
+ might_sleep();
+ for (i = 0; i < pages_per_huge_page(h); i++) {
+ cond_resched();
+ copy_highpage(dst + i, src + i);
+ }
+}
+
static void enqueue_huge_page(struct hstate *h, struct page *page)
{
int nid = page_to_nid(page);
h->free_huge_pages_node[nid]++;
}
+static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+
+ if (list_empty(&h->hugepage_freelists[nid]))
+ return NULL;
+ page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
+ list_del(&page->lru);
+ h->free_huge_pages--;
+ h->free_huge_pages_node[nid]--;
+ return page;
+}
+
static struct page *dequeue_huge_page_vma(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address, int avoid_reserve)
{
- int nid;
struct page *page = NULL;
struct mempolicy *mpol;
nodemask_t *nodemask;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
MAX_NR_ZONES - 1, nodemask) {
- nid = zone_to_nid(zone);
- if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
- !list_empty(&h->hugepage_freelists[nid])) {
- page = list_entry(h->hugepage_freelists[nid].next,
- struct page, lru);
- list_del(&page->lru);
- h->free_huge_pages--;
- h->free_huge_pages_node[nid]--;
-
- if (!avoid_reserve)
- decrement_hugepage_resv_vma(h, vma);
-
- break;
+ if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+ page = dequeue_huge_page_node(h, zone_to_nid(zone));
+ if (page) {
+ if (!avoid_reserve)
+ decrement_hugepage_resv_vma(h, vma);
+ break;
+ }
}
}
err:
set_page_private(page, 0);
page->mapping = NULL;
BUG_ON(page_count(page));
+ BUG_ON(page_mapcount(page));
INIT_LIST_HEAD(&page->lru);
spin_lock(&hugetlb_lock);
return dtor == free_huge_page;
}
+EXPORT_SYMBOL_GPL(PageHuge);
+
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
return ret;
}
-static struct page *alloc_buddy_huge_page(struct hstate *h,
- struct vm_area_struct *vma, unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
struct page *page;
- unsigned int nid;
+ unsigned int r_nid;
if (h->order >= MAX_ORDER)
return NULL;
}
spin_unlock(&hugetlb_lock);
- page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
- __GFP_REPEAT|__GFP_NOWARN,
- huge_page_order(h));
+ if (nid == NUMA_NO_NODE)
+ page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+ __GFP_REPEAT|__GFP_NOWARN,
+ huge_page_order(h));
+ else
+ page = alloc_pages_exact_node(nid,
+ htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
if (page && arch_prepare_hugepage(page)) {
__free_pages(page, huge_page_order(h));
*/
put_page_testzero(page);
VM_BUG_ON(page_count(page));
- nid = page_to_nid(page);
+ r_nid = page_to_nid(page);
set_compound_page_dtor(page, free_huge_page);
/*
* We incremented the global counters already
*/
- h->nr_huge_pages_node[nid]++;
- h->surplus_huge_pages_node[nid]++;
+ h->nr_huge_pages_node[r_nid]++;
+ h->surplus_huge_pages_node[r_nid]++;
__count_vm_event(HTLB_BUDDY_PGALLOC);
} else {
h->nr_huge_pages--;
}
/*
+ * This allocation function is useful in the context where vma is irrelevant.
+ * E.g. soft-offlining uses this function because it only cares physical
+ * address of error page.
+ */
+struct page *alloc_huge_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+
+ spin_lock(&hugetlb_lock);
+ page = dequeue_huge_page_node(h, nid);
+ spin_unlock(&hugetlb_lock);
+
+ if (!page)
+ page = alloc_buddy_huge_page(h, nid);
+
+ return page;
+}
+
+/*
* Increase the hugetlb pool such that it can accomodate a reservation
* of size 'delta'.
*/
retry:
spin_unlock(&hugetlb_lock);
for (i = 0; i < needed; i++) {
- page = alloc_buddy_huge_page(h, NULL, 0);
+ page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
/*
* We were not able to allocate enough pages to
spin_unlock(&hugetlb_lock);
if (!page) {
- page = alloc_buddy_huge_page(h, vma, addr);
+ page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
hugetlb_put_quota(inode->i_mapping, chg);
return ERR_PTR(-VM_FAULT_SIGBUS);
entry = huge_ptep_get(src_pte);
ptepage = pte_page(entry);
get_page(ptepage);
+ page_dup_rmap(ptepage);
set_huge_pte_at(dst, addr, dst_pte, entry);
}
spin_unlock(&src->page_table_lock);
return -ENOMEM;
}
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+ swp_entry_t swp;
+
+ if (huge_pte_none(pte) || pte_present(pte))
+ return 0;
+ swp = pte_to_swp_entry(pte);
+ if (non_swap_entry(swp) && is_migration_entry(swp)) {
+ return 1;
+ } else
+ return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+ swp_entry_t swp;
+
+ if (huge_pte_none(pte) || pte_present(pte))
+ return 0;
+ swp = pte_to_swp_entry(pte);
+ if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+ return 1;
+ } else
+ return 0;
+}
+
void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
if (huge_pte_none(pte))
continue;
+ /*
+ * HWPoisoned hugepage is already unmapped and dropped reference
+ */
+ if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+ continue;
+
page = pte_page(pte);
if (pte_dirty(pte))
set_page_dirty(page);
flush_tlb_range(vma, start, end);
mmu_notifier_invalidate_range_end(mm, start, end);
list_for_each_entry_safe(page, tmp, &page_list, lru) {
+ page_remove_rmap(page);
list_del(&page->lru);
put_page(page);
}
return 1;
}
+/*
+ * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ */
static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, pte_t pte,
struct page *pagecache_page)
retry_avoidcopy:
/* If no-one else is actually using this page, avoid the copy
* and just make the page writable */
- avoidcopy = (page_count(old_page) == 1);
+ avoidcopy = (page_mapcount(old_page) == 1);
if (avoidcopy) {
+ if (PageAnon(old_page))
+ page_move_anon_rmap(old_page, vma, address);
set_huge_ptep_writable(vma, address, ptep);
return 0;
}
return -PTR_ERR(new_page);
}
- copy_huge_page(new_page, old_page, address, vma);
+ /*
+ * When the original hugepage is shared one, it does not have
+ * anon_vma prepared.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return VM_FAULT_OOM;
+
+ copy_user_huge_page(new_page, old_page, address, vma);
__SetPageUptodate(new_page);
/*
huge_ptep_clear_flush(vma, address, ptep);
set_huge_pte_at(mm, address, ptep,
make_huge_pte(vma, new_page, 1));
+ page_remove_rmap(old_page);
+ hugepage_add_new_anon_rmap(new_page, vma, address);
/* Make the old page be freed below */
new_page = old_page;
mmu_notifier_invalidate_range_end(mm,
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
spin_unlock(&inode->i_lock);
+ page_dup_rmap(page);
} else {
lock_page(page);
- page->mapping = HUGETLB_POISON;
+ if (unlikely(anon_vma_prepare(vma))) {
+ ret = VM_FAULT_OOM;
+ goto backout_unlocked;
+ }
+ hugepage_add_new_anon_rmap(page, vma, address);
}
+ } else {
+ /*
+ * If memory error occurs between mmap() and fault, some process
+ * don't have hwpoisoned swap entry for errored virtual address.
+ * So we need to block hugepage fault by PG_hwpoison bit check.
+ */
+ if (unlikely(PageHWPoison(page))) {
+ ret = VM_FAULT_HWPOISON;
+ goto backout_unlocked;
+ }
+ page_dup_rmap(page);
}
/*
pte_t *ptep;
pte_t entry;
int ret;
+ struct page *page = NULL;
struct page *pagecache_page = NULL;
static DEFINE_MUTEX(hugetlb_instantiation_mutex);
struct hstate *h = hstate_vma(vma);
+ ptep = huge_pte_offset(mm, address);
+ if (ptep) {
+ entry = huge_ptep_get(ptep);
+ if (unlikely(is_hugetlb_entry_migration(entry))) {
+ migration_entry_wait(mm, (pmd_t *)ptep, address);
+ return 0;
+ } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+ return VM_FAULT_HWPOISON;
+ }
+
ptep = huge_pte_alloc(mm, address, huge_page_size(h));
if (!ptep)
return VM_FAULT_OOM;
vma, address);
}
+ /*
+ * hugetlb_cow() requires page locks of pte_page(entry) and
+ * pagecache_page, so here we need take the former one
+ * when page != pagecache_page or !pagecache_page.
+ * Note that locking order is always pagecache_page -> page,
+ * so no worry about deadlock.
+ */
+ page = pte_page(entry);
+ if (page != pagecache_page)
+ lock_page(page);
+
spin_lock(&mm->page_table_lock);
/* Check for a racing update before calling hugetlb_cow */
if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
unlock_page(pagecache_page);
put_page(pagecache_page);
}
+ unlock_page(page);
out_mutex:
mutex_unlock(&hugetlb_instantiation_mutex);
hugetlb_put_quota(inode->i_mapping, (chg - freed));
hugetlb_acct_memory(h, -(chg - freed));
}
+
+/*
+ * This function is called from memory failure code.
+ * Assume the caller holds page lock of the head page.
+ */
+void __isolate_hwpoisoned_huge_page(struct page *hpage)
+{
+ struct hstate *h = page_hstate(hpage);
+ int nid = page_to_nid(hpage);
+
+ spin_lock(&hugetlb_lock);
+ list_del(&hpage->lru);
+ h->free_huge_pages--;
+ h->free_huge_pages_node[nid]--;
+ spin_unlock(&hugetlb_lock);
+}