#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
+#include <linux/oom.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
struct mem_cgroup *memcg;
pgtable_t pgtable;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+ int ret = 0;
VM_BUG_ON_PAGE(!PageCompound(page), page);
pgtable = pte_alloc_one(vma->vm_mm, haddr);
if (unlikely(!pgtable)) {
- mem_cgroup_cancel_charge(page, memcg, true);
- put_page(page);
- return VM_FAULT_OOM;
+ ret = VM_FAULT_OOM;
+ goto release;
}
clear_huge_page(page, haddr, HPAGE_PMD_NR);
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_none(*vmf->pmd))) {
- spin_unlock(vmf->ptl);
- mem_cgroup_cancel_charge(page, memcg, true);
- put_page(page);
- pte_free(vma->vm_mm, pgtable);
+ goto unlock_release;
} else {
pmd_t entry;
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret)
+ goto unlock_release;
+
/* Deliver the page fault to userland */
if (userfaultfd_missing(vma)) {
int ret;
}
return 0;
+unlock_release:
+ spin_unlock(vmf->ptl);
+release:
+ if (pgtable)
+ pte_free(vma->vm_mm, pgtable);
+ mem_cgroup_cancel_charge(page, memcg, true);
+ put_page(page);
+ return ret;
+
}
/*
ret = 0;
set = false;
if (pmd_none(*vmf->pmd)) {
- if (userfaultfd_missing(vma)) {
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret) {
+ spin_unlock(vmf->ptl);
+ } else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
goto clear_pmdnuma;
}
+ /*
+ * The page_table_lock above provides a memory barrier
+ * with change_protection_range.
+ */
+ if (mm_tlb_flush_pending(vma->vm_mm))
+ flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
/*
* Migrate the THP to the requested node, returns with page unlocked
* and access rights restored.
get_page(page);
spin_unlock(ptl);
split_huge_page(page);
- put_page(page);
unlock_page(page);
+ put_page(page);
goto out_unlocked;
}
* atomic_set() here would be safe on all archs (and not only on x86),
* it's safer to use atomic_inc()/atomic_add().
*/
- if (PageAnon(head)) {
+ if (PageAnon(head) && !PageSwapCache(head)) {
page_ref_inc(page_tail);
} else {
/* Additional pin to radix tree */
page_tail->flags |= (head->flags &
((1L << PG_referenced) |
(1L << PG_swapbacked) |
+ (1L << PG_swapcache) |
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
ClearPageCompound(head);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
- page_ref_inc(head);
+ /* Additional pin to radix tree of swap cache */
+ if (PageSwapCache(head))
+ page_ref_add(head, 2);
+ else
+ page_ref_inc(head);
} else {
/* Additional pin to radix tree */
page_ref_add(head, 2);
return ret;
}
+/* Racy check whether the huge page can be split */
+bool can_split_huge_page(struct page *page, int *pextra_pins)
+{
+ int extra_pins;
+
+ /* Additional pins from radix tree */
+ if (PageAnon(page))
+ extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
+ else
+ extra_pins = HPAGE_PMD_NR;
+ if (pextra_pins)
+ *pextra_pins = extra_pins;
+ return total_mapcount(page) == page_count(page) - extra_pins - 1;
+}
+
/*
* This function splits huge page into normal pages. @page can point to any
* subpage of huge page to split. Split doesn't change the position of @page.
ret = -EBUSY;
goto out;
}
- extra_pins = 0;
mapping = NULL;
anon_vma_lock_write(anon_vma);
} else {
goto out;
}
- /* Addidional pins from radix tree */
- extra_pins = HPAGE_PMD_NR;
anon_vma = NULL;
i_mmap_lock_read(mapping);
}
* Racy check if we can split the page, before freeze_page() will
* split PMDs
*/
- if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
+ if (!can_split_huge_page(head, &extra_pins)) {
ret = -EBUSY;
goto out_unlock;
}