pmd_t *dst_pmd, pmd_t *src_pmd,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end);
-extern int handle_pte_fault(struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long address,
- pte_t *pte, pmd_t *pmd, unsigned int flags);
extern int split_huge_page_to_list(struct page *page, struct list_head *list);
static inline int split_huge_page(struct page *page)
{
#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
+#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
- VM_FAULT_HWPOISON_LARGE)
+ VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
{
struct page *page;
unsigned long haddr = address & HPAGE_PMD_MASK;
- pte_t *pte;
if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
- goto out;
+ return VM_FAULT_FALLBACK;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
if (unlikely(khugepaged_enter(vma)))
if (unlikely(!zero_page)) {
pte_free(mm, pgtable);
count_vm_event(THP_FAULT_FALLBACK);
- goto out;
+ return VM_FAULT_FALLBACK;
}
spin_lock(&mm->page_table_lock);
set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
vma, haddr, numa_node_id(), 0);
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
- goto out;
+ return VM_FAULT_FALLBACK;
}
count_vm_event(THP_FAULT_ALLOC);
if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
put_page(page);
- goto out;
+ return VM_FAULT_FALLBACK;
}
if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
mem_cgroup_uncharge_page(page);
put_page(page);
- goto out;
+ return VM_FAULT_FALLBACK;
}
return 0;
-out:
- /*
- * Use __pte_alloc instead of pte_alloc_map, because we can't
- * run pte_offset_map on the pmd, if an huge pmd could
- * materialize from under us from a different thread.
- */
- if (unlikely(pmd_none(*pmd)) &&
- unlikely(__pte_alloc(mm, vma, pmd, address)))
- return VM_FAULT_OOM;
- /* if an huge pmd materialized from under us just retry later */
- if (unlikely(pmd_trans_huge(*pmd)))
- return 0;
- /*
- * A regular pmd is established and it can't morph into a huge pmd
- * from under us anymore at this point because we hold the mmap_sem
- * read mode and khugepaged takes it in write mode. So now it's
- * safe to run pte_offset_map().
- */
- pte = pte_offset_map(pmd, address);
- return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
-int handle_pte_fault(struct mm_struct *mm,
+static int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pmd_t *pmd, unsigned int flags)
{
if (!pmd)
return VM_FAULT_OOM;
if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+ int ret = VM_FAULT_FALLBACK;
if (!vma->vm_ops)
- return do_huge_pmd_anonymous_page(mm, vma, address,
- pmd, flags);
+ ret = do_huge_pmd_anonymous_page(mm, vma, address,
+ pmd, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
} else {
pmd_t orig_pmd = *pmd;
int ret;