summaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c79
1 files changed, 34 insertions, 45 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3103099f64fd..3c21775f196b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1479,22 +1479,20 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
/*
* Dissolve a given free hugepage into free buddy pages. This function does
* nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
- * number of free hugepages would be reduced below the number of reserved
- * hugepages.
+ * dissolution fails because a give page is not a free hugepage, or because
+ * free hugepages are fully reserved.
*/
int dissolve_free_huge_page(struct page *page)
{
- int rc = 0;
+ int rc = -EBUSY;
spin_lock(&hugetlb_lock);
if (PageHuge(page) && !page_count(page)) {
struct page *head = compound_head(page);
struct hstate *h = page_hstate(head);
int nid = page_to_nid(head);
- if (h->free_huge_pages - h->resv_huge_pages == 0) {
- rc = -EBUSY;
+ if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
- }
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
@@ -1508,6 +1506,7 @@ int dissolve_free_huge_page(struct page *page)
h->free_huge_pages_node[nid]--;
h->max_huge_pages--;
update_and_free_page(h, head);
+ rc = 0;
}
out:
spin_unlock(&hugetlb_lock);
@@ -2101,7 +2100,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
void *addr;
- addr = memblock_virt_alloc_try_nid_nopanic(
+ addr = memblock_virt_alloc_try_nid_raw(
huge_page_size(h), huge_page_size(h),
0, BOOTMEM_ALLOC_ACCESSIBLE, node);
if (addr) {
@@ -2119,6 +2118,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
found:
BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
/* Put them into a private list first because mem_map is not up yet */
+ INIT_LIST_HEAD(&m->list);
list_add(&m->list, &huge_boot_pages);
m->hstate = h;
return 1;
@@ -2139,16 +2139,9 @@ static void __init gather_bootmem_prealloc(void)
struct huge_bootmem_page *m;
list_for_each_entry(m, &huge_boot_pages, list) {
+ struct page *page = virt_to_page(m);
struct hstate *h = m->hstate;
- struct page *page;
-#ifdef CONFIG_HIGHMEM
- page = pfn_to_page(m->phys >> PAGE_SHIFT);
- memblock_free_late(__pa(m),
- sizeof(struct huge_bootmem_page));
-#else
- page = virt_to_page(m);
-#endif
WARN_ON(page_count(page) != 1);
prep_compound_huge_page(page, h->order);
WARN_ON(PageReserved(page));
@@ -3508,16 +3501,18 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
* cannot race with other handlers or page migration.
* Keep the pte_same checks anyway to make transition from the mutex easier.
*/
-static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
+static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
struct page *pagecache_page, spinlock_t *ptl)
{
pte_t pte;
struct hstate *h = hstate_vma(vma);
struct page *old_page, *new_page;
- int ret = 0, outside_reserve = 0;
+ int outside_reserve = 0;
+ vm_fault_t ret = 0;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
+ unsigned long haddr = address & huge_page_mask(h);
pte = huge_ptep_get(ptep);
old_page = pte_page(pte);
@@ -3527,7 +3522,7 @@ retry_avoidcopy:
* and just make the page writable */
if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
page_move_anon_rmap(old_page, vma);
- set_huge_ptep_writable(vma, address, ptep);
+ set_huge_ptep_writable(vma, haddr, ptep);
return 0;
}
@@ -3551,7 +3546,7 @@ retry_avoidcopy:
* be acquired again before returning to the caller, as expected.
*/
spin_unlock(ptl);
- new_page = alloc_huge_page(vma, address, outside_reserve);
+ new_page = alloc_huge_page(vma, haddr, outside_reserve);
if (IS_ERR(new_page)) {
/*
@@ -3564,11 +3559,10 @@ retry_avoidcopy:
if (outside_reserve) {
put_page(old_page);
BUG_ON(huge_pte_none(pte));
- unmap_ref_private(mm, vma, old_page, address);
+ unmap_ref_private(mm, vma, old_page, haddr);
BUG_ON(huge_pte_none(pte));
spin_lock(ptl);
- ptep = huge_pte_offset(mm, address & huge_page_mask(h),
- huge_page_size(h));
+ ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
if (likely(ptep &&
pte_same(huge_ptep_get(ptep), pte)))
goto retry_avoidcopy;
@@ -3579,8 +3573,7 @@ retry_avoidcopy:
return 0;
}
- ret = (PTR_ERR(new_page) == -ENOMEM) ?
- VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ ret = vmf_error(PTR_ERR(new_page));
goto out_release_old;
}
@@ -3598,7 +3591,7 @@ retry_avoidcopy:
__SetPageUptodate(new_page);
set_page_huge_active(new_page);
- mmun_start = address & huge_page_mask(h);
+ mmun_start = haddr;
mmun_end = mmun_start + huge_page_size(h);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
@@ -3607,25 +3600,24 @@ retry_avoidcopy:
* before the page tables are altered
*/
spin_lock(ptl);
- ptep = huge_pte_offset(mm, address & huge_page_mask(h),
- huge_page_size(h));
+ ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
ClearPagePrivate(new_page);
/* Break COW */
- huge_ptep_clear_flush(vma, address, ptep);
+ huge_ptep_clear_flush(vma, haddr, ptep);
mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
- set_huge_pte_at(mm, address, ptep,
+ set_huge_pte_at(mm, haddr, ptep,
make_huge_pte(vma, new_page, 1));
page_remove_rmap(old_page, true);
- hugepage_add_new_anon_rmap(new_page, vma, address);
+ hugepage_add_new_anon_rmap(new_page, vma, haddr);
/* Make the old page be freed below */
new_page = old_page;
}
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out_release_all:
- restore_reserve_on_error(h, vma, address, new_page);
+ restore_reserve_on_error(h, vma, haddr, new_page);
put_page(new_page);
out_release_old:
put_page(old_page);
@@ -3684,12 +3676,13 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
return 0;
}
-static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
- struct address_space *mapping, pgoff_t idx,
- unsigned long address, pte_t *ptep, unsigned int flags)
+static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ struct address_space *mapping, pgoff_t idx,
+ unsigned long address, pte_t *ptep, unsigned int flags)
{
struct hstate *h = hstate_vma(vma);
- int ret = VM_FAULT_SIGBUS;
+ vm_fault_t ret = VM_FAULT_SIGBUS;
int anon_rmap = 0;
unsigned long size;
struct page *page;
@@ -3752,11 +3745,7 @@ retry:
page = alloc_huge_page(vma, haddr, 0);
if (IS_ERR(page)) {
- ret = PTR_ERR(page);
- if (ret == -ENOMEM)
- ret = VM_FAULT_OOM;
- else
- ret = VM_FAULT_SIGBUS;
+ ret = vmf_error(PTR_ERR(page));
goto out;
}
clear_huge_page(page, address, pages_per_huge_page(h));
@@ -3828,7 +3817,7 @@ retry:
hugetlb_count_add(pages_per_huge_page(h), mm);
if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
/* Optimization, do the COW without a second fault */
- ret = hugetlb_cow(mm, vma, haddr, ptep, page, ptl);
+ ret = hugetlb_cow(mm, vma, address, ptep, page, ptl);
}
spin_unlock(ptl);
@@ -3880,12 +3869,12 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
}
#endif
-int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
pte_t *ptep, entry;
spinlock_t *ptl;
- int ret;
+ vm_fault_t ret;
u32 hash;
pgoff_t idx;
struct page *page = NULL;
@@ -3982,7 +3971,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
if (flags & FAULT_FLAG_WRITE) {
if (!huge_pte_write(entry)) {
- ret = hugetlb_cow(mm, vma, haddr, ptep,
+ ret = hugetlb_cow(mm, vma, address, ptep,
pagecache_page, ptl);
goto out_put_page;
}
@@ -4215,7 +4204,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (absent || is_swap_pte(huge_ptep_get(pte)) ||
((flags & FOLL_WRITE) &&
!huge_pte_write(huge_ptep_get(pte)))) {
- int ret;
+ vm_fault_t ret;
unsigned int fault_flags = 0;
if (pte)