return pfn_to_page(pfn);
}
+struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte)
+{
+ struct page *page = vm_normal_page(vma, addr, pte);
+
+ if (page)
+ return page_folio(page);
+ return NULL;
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd)
return -EBUSY;
return -ENOENT;
} else if (is_pte_marker_entry(entry)) {
- /*
- * We're copying the pgtable should only because dst_vma has
- * uffd-wp enabled, do sanity check.
- */
- WARN_ON_ONCE(!userfaultfd_wp(dst_vma));
- set_pte_at(dst_mm, addr, dst_pte, pte);
+ if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma))
+ set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
if (!userfaultfd_wp(dst_vma))
pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
if (userfaultfd_pte_wp(dst_vma, *src_pte))
/* Uffd-wp needs to be delivered to dest pte as well */
- pte = pte_wrprotect(pte_mkuffd_wp(pte));
+ pte = pte_mkuffd_wp(pte);
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
return 0;
}
if (is_cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
- 0, src_vma, src_mm, addr, end);
+ 0, src_mm, addr, end);
mmu_notifier_invalidate_range_start(&range);
/*
* Disabling preemption is not needed for the write side, as
force_flush = 1;
}
}
- if (pte_young(ptent) &&
- likely(!(vma->vm_flags & VM_SEQ_READ)))
+ if (pte_young(ptent) && likely(vma_has_recency(vma)))
mark_page_accessed(page);
}
rss[mm_counter(page)]--;
};
MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
- mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
do {
mmu_notifier_invalidate_range_end(&range);
}
-/**
- * zap_page_range - remove user pages in a given range
- * @vma: vm_area_struct holding the applicable pages
- * @start: starting address of pages to zap
- * @size: number of bytes to zap
- *
- * Caller must protect the VMA list
- */
-void zap_page_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long size)
-{
- struct maple_tree *mt = &vma->vm_mm->mm_mt;
- unsigned long end = start + size;
- struct mmu_notifier_range range;
- struct mmu_gather tlb;
- MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
- lru_add_drain();
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- start, start + size);
- tlb_gather_mmu(&tlb, vma->vm_mm);
- update_hiwater_rss(vma->vm_mm);
- mmu_notifier_invalidate_range_start(&range);
- do {
- unmap_single_vma(&tlb, vma, start, range.end, NULL);
- } while ((vma = mas_find(&mas, end - 1)) != NULL);
- mmu_notifier_invalidate_range_end(&range);
- tlb_finish_mmu(&tlb);
-}
-
/**
* zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
struct mmu_gather tlb;
lru_add_drain();
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, end);
if (is_vm_hugetlb_page(vma))
adjust_range_if_pmd_sharing_possible(vma, &range.start,
__SetPageUptodate(new_page);
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags))
return VM_FAULT_RETRY;
- mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
+ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
vma->vm_mm, vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
mmu_notifier_invalidate_range_start(&range);
/*
* Be careful so that we will only recover a special uffd-wp pte into a
* none pte. Otherwise it means the pte could have changed, so retry.
+ *
+ * This should also cover the case where e.g. the pte changed
+ * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR.
+ * So is_pte_marker() check is not enough to safely drop the pte.
*/
- if (is_pte_marker(*vmf->pte))
+ if (pte_same(vmf->orig_pte, *vmf->pte))
pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
flush_icache_page(vma, page);
if (pte_swp_soft_dirty(vmf->orig_pte))
pte = pte_mksoft_dirty(pte);
- if (pte_swp_uffd_wp(vmf->orig_pte)) {
+ if (pte_swp_uffd_wp(vmf->orig_pte))
pte = pte_mkuffd_wp(pte);
- pte = pte_wrprotect(pte);
- }
vmf->orig_pte = pte;
/* ksm created a completely new copy */
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (unlikely(uffd_wp))
- entry = pte_mkuffd_wp(pte_wrprotect(entry));
+ entry = pte_mkuffd_wp(entry);
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) {
inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
#ifdef CONFIG_LRU_GEN
static void lru_gen_enter_fault(struct vm_area_struct *vma)
{
- /* the LRU algorithm doesn't apply to sequential or random reads */
- current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ));
+ /* the LRU algorithm only applies to accesses with recency */
+ current->in_lru_fault = vma_has_recency(vma);
}
static void lru_gen_exit_fault(void)
projects / linux.git / blobdiff