#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
+#include <linux/page_owner.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
VM_BUG_ON_PAGE(!PageCompound(page), page);
- if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+ if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg,
+ true)) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd)
+ pmd_t *pmd, int flags)
{
pmd_t _pmd;
- /*
- * We should set the dirty bit only for FOLL_WRITE but for now
- * the dirty bit in the pmd is meaningless. And if the dirty
- * bit will become meaningful and we'll only set it with
- * FOLL_WRITE, an atomic set_bit will be required on the pmd to
- * set the young bit, instead of the current set_pmd_at.
- */
- _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+ _pmd = pmd_mkyoung(*pmd);
+ if (flags & FOLL_WRITE)
+ _pmd = pmd_mkdirty(_pmd);
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
- pmd, _pmd, 1))
+ pmd, _pmd, flags & FOLL_WRITE))
update_mmu_cache_pmd(vma, addr, pmd);
}
assert_spin_locked(pmd_lockptr(mm, pmd));
+ /*
+ * When we COW a devmap PMD entry, we split it into PTEs, so we should
+ * not be in this function with `flags & FOLL_COW` set.
+ */
+ WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
+
if (flags & FOLL_WRITE && !pmd_write(*pmd))
return NULL;
return NULL;
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
/*
* device mapped pages can only be returned if the
{
pmd_t entry;
unsigned long haddr;
+ bool write = fe->flags & FAULT_FLAG_WRITE;
fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd);
if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
goto unlock;
entry = pmd_mkyoung(orig_pmd);
+ if (write)
+ entry = pmd_mkdirty(entry);
haddr = fe->address & HPAGE_PMD_MASK;
- if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry,
- fe->flags & FAULT_FLAG_WRITE))
+ if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry, write))
update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd);
unlock:
}
if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
- huge_gfp, &memcg, true))) {
+ huge_gfp | __GFP_NORETRY, &memcg, true))) {
put_page(new_page);
split_huge_pmd(vma, fe->pmd, fe->address);
if (page)
return ret;
}
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+ return pmd_write(pmd) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr,
pmd_t *pmd,
assert_spin_locked(pmd_lockptr(mm, pmd));
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
goto out;
/* Avoid dumping huge zero page */
page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* We don't mlock() pte-mapped THPs. This way we can avoid
*/
if (unlikely(pmd_trans_migrating(*fe->pmd))) {
page = pmd_page(*fe->pmd);
+ if (!get_page_unless_zero(page))
+ goto out_unlock;
spin_unlock(fe->ptl);
wait_on_page_locked(page);
+ put_page(page);
goto out;
}
/* Migration could have started since the pmd_trans_migrating check */
if (!page_locked) {
+ page_nid = -1;
+ if (!get_page_unless_zero(page))
+ goto out_unlock;
spin_unlock(fe->ptl);
wait_on_page_locked(page);
- page_nid = -1;
+ put_page(page);
goto out;
}
get_page(page);
spin_unlock(ptl);
split_huge_page(page);
- put_page(page);
unlock_page(page);
+ put_page(page);
goto out_unlocked;
}
deactivate_page(page);
if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
- orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
- tlb->fullmm);
+ pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
orig_pmd = pmd_mkclean(orig_pmd);
spinlock_t *old_ptl, *new_ptl;
pmd_t pmd;
struct mm_struct *mm = vma->vm_mm;
+ bool force_flush = false;
if ((old_addr & ~HPAGE_PMD_MASK) ||
(new_addr & ~HPAGE_PMD_MASK) ||
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
+ if (pmd_present(pmd))
+ force_flush = true;
VM_BUG_ON(!pmd_none(*new_pmd));
if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
}
set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
+ if (force_flush)
+ flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
- int ret = 0;
+ pmd_t entry;
+ bool preserve_write;
+ int ret;
ptl = __pmd_trans_huge_lock(pmd, vma);
- if (ptl) {
- pmd_t entry;
- bool preserve_write = prot_numa && pmd_write(*pmd);
- ret = 1;
+ if (!ptl)
+ return 0;
- /*
- * Avoid trapping faults against the zero page. The read-only
- * data is likely to be read-cached on the local CPU and
- * local/remote hits to the zero page are not interesting.
- */
- if (prot_numa && is_huge_zero_pmd(*pmd)) {
- spin_unlock(ptl);
- return ret;
- }
+ preserve_write = prot_numa && pmd_write(*pmd);
+ ret = 1;
- if (!prot_numa || !pmd_protnone(*pmd)) {
- entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
- entry = pmd_modify(entry, newprot);
- if (preserve_write)
- entry = pmd_mkwrite(entry);
- ret = HPAGE_PMD_NR;
- set_pmd_at(mm, addr, pmd, entry);
- BUG_ON(vma_is_anonymous(vma) && !preserve_write &&
- pmd_write(entry));
- }
- spin_unlock(ptl);
- }
+ /*
+ * Avoid trapping faults against the zero page. The read-only
+ * data is likely to be read-cached on the local CPU and
+ * local/remote hits to the zero page are not interesting.
+ */
+ if (prot_numa && is_huge_zero_pmd(*pmd))
+ goto unlock;
+
+ if (prot_numa && pmd_protnone(*pmd))
+ goto unlock;
+ /*
+ * In case prot_numa, we are under down_read(mmap_sem). It's critical
+ * to not clear pmd intermittently to avoid race with MADV_DONTNEED
+ * which is also under down_read(mmap_sem):
+ *
+ * CPU0: CPU1:
+ * change_huge_pmd(prot_numa=1)
+ * pmdp_huge_get_and_clear_notify()
+ * madvise_dontneed()
+ * zap_pmd_range()
+ * pmd_trans_huge(*pmd) == 0 (without ptl)
+ * // skip the pmd
+ * set_pmd_at();
+ * // pmd is re-established
+ *
+ * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
+ * which may break userspace.
+ *
+ * pmdp_invalidate() is required to make sure we don't miss
+ * dirty/young flags set by hardware.
+ */
+ entry = *pmd;
+ pmdp_invalidate(vma, addr, pmd);
+
+ /*
+ * Recover dirty/young flags. It relies on pmdp_invalidate to not
+ * corrupt them.
+ */
+ if (pmd_dirty(*pmd))
+ entry = pmd_mkdirty(entry);
+ if (pmd_young(*pmd))
+ entry = pmd_mkyoung(entry);
+
+ entry = pmd_modify(entry, newprot);
+ if (preserve_write)
+ entry = pmd_mkwrite(entry);
+ ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
+ BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
+unlock:
+ spin_unlock(ptl);
return ret;
}
if (vma_is_dax(vma))
return;
page = pmd_page(_pmd);
+ if (!PageDirty(page) && pmd_dirty(_pmd))
+ set_page_dirty(page);
if (!PageReferenced(page) && pmd_young(_pmd))
SetPageReferenced(page);
page_remove_rmap(page, true);
}
}
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
{
enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
TTU_RMAP_LOCKED;
VM_BUG_ON_PAGE(ret, page + i - 1);
}
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
{
int i;
struct page *page_tail = head + tail;
VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
- VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
/*
- * tail_page->_refcount is zero and not changing from under us. But
- * get_page_unless_zero() may be running from under us on the
- * tail_page. If we used atomic_set() below instead of atomic_inc() or
- * atomic_add(), we would then run atomic_set() concurrently with
- * get_page_unless_zero(), and atomic_set() is implemented in C not
- * using locked ops. spin_unlock on x86 sometime uses locked ops
- * because of PPro errata 66, 92, so unless somebody can guarantee
- * atomic_set() here would be safe on all archs (and not only on x86),
- * it's safer to use atomic_inc()/atomic_add().
+ * Clone page flags before unfreezing refcount.
+ *
+ * After successful get_page_unless_zero() might follow flags change,
+ * for exmaple lock_page() which set PG_waiters.
*/
- if (PageAnon(head)) {
- page_ref_inc(page_tail);
- } else {
- /* Additional pin to radix tree */
- page_ref_add(page_tail, 2);
- }
-
page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
page_tail->flags |= (head->flags &
((1L << PG_referenced) |
(1L << PG_unevictable) |
(1L << PG_dirty)));
- /*
- * After clearing PageTail the gup refcount can be released.
- * Page flags also must be visible before we make the page non-compound.
- */
+ /* ->mapping in first tail page is compound_mapcount */
+ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+ page_tail);
+ page_tail->mapping = head->mapping;
+ page_tail->index = head->index + tail;
+
+ /* Page flags must be visible before we make the page non-compound. */
smp_wmb();
+ /*
+ * Clear PageTail before unfreezing page refcount.
+ *
+ * After successful get_page_unless_zero() might follow put_page()
+ * which needs correct compound_head().
+ */
clear_compound_head(page_tail);
+ /* Finally unfreeze refcount. Additional reference from page cache. */
+ page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
+ PageSwapCache(head)));
+
if (page_is_young(head))
set_page_young(page_tail);
if (page_is_idle(head))
set_page_idle(page_tail);
- /* ->mapping in first tail page is compound_mapcount */
- VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
- page_tail);
- page_tail->mapping = head->mapping;
-
- page_tail->index = head->index + tail;
page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
lru_add_page_tail(head, page_tail, lruvec, list);
}
static void __split_huge_page(struct page *page, struct list_head *list,
- unsigned long flags)
+ pgoff_t end, unsigned long flags)
{
struct page *head = compound_head(page);
struct zone *zone = page_zone(head);
struct lruvec *lruvec;
- pgoff_t end = -1;
int i;
lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
- if (!PageAnon(page))
- end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
}
ClearPageCompound(head);
+
+ split_page_owner(head, HPAGE_PMD_ORDER);
+
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
page_ref_inc(head);
spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
- unfreeze_page(head);
+ remap_page(head);
for (i = 0; i < HPAGE_PMD_NR; i++) {
struct page *subpage = head + i;
int count, mapcount, extra_pins, ret;
bool mlocked;
unsigned long flags;
+ pgoff_t end;
VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
goto out;
}
extra_pins = 0;
+ end = -1;
mapping = NULL;
anon_vma_lock_write(anon_vma);
} else {
extra_pins = HPAGE_PMD_NR;
anon_vma = NULL;
i_mmap_lock_read(mapping);
+
+ /*
+ *__split_huge_page() may need to trim off pages beyond EOF:
+ * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+ * which cannot be nested inside the page tree lock. So note
+ * end now: i_size itself may be changed at any moment, but
+ * head page lock is good enough to serialize the trimming.
+ */
+ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
}
/*
- * Racy check if we can split the page, before freeze_page() will
+ * Racy check if we can split the page, before unmap_page() will
* split PMDs
*/
if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
}
mlocked = PageMlocked(page);
- freeze_page(head);
+ unmap_page(head);
VM_BUG_ON_PAGE(compound_mapcount(head), head);
/* Make sure the page is not on per-CPU pagevec as it takes pin */
if (mapping)
__dec_node_page_state(page, NR_SHMEM_THPS);
spin_unlock(&pgdata->split_queue_lock);
- __split_huge_page(page, list, flags);
+ __split_huge_page(page, list, end, flags);
ret = 0;
} else {
if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
fail: if (mapping)
spin_unlock(&mapping->tree_lock);
spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
- unfreeze_page(head);
+ remap_page(head);
ret = -EBUSY;
}
list_for_each_safe(pos, next, &list) {
page = list_entry((void *)pos, struct page, mapping);
- lock_page(page);
+ if (!trylock_page(page))
+ goto next;
/* split_huge_page() removes page from list on success */
if (!split_huge_page(page))
split++;
unlock_page(page);
+next:
put_page(page);
}