In preparation for using insert_page() for DAX, enhance insert_page_into_pte_locked() to handle establishing writable mappings. Recall that DAX returns VM_FAULT_NOPAGE after installing a PTE which bypasses the typical set_pte_range() in finish_fault. Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx> Suggested-by: Dan Williams <dan.j.williams@xxxxxxxxx> --- Changes since v2: - New patch split out from "mm/memory: Add dax_insert_pfn" --- mm/memory.c | 45 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 24a34a4..323662c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2042,19 +2042,47 @@ static int validate_page_before_insert(struct vm_area_struct *vma, } static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, - unsigned long addr, struct page *page, pgprot_t prot) + unsigned long addr, struct page *page, + pgprot_t prot, bool mkwrite) { struct folio *folio = page_folio(page); + pte_t entry = ptep_get(pte); pte_t pteval; - if (!pte_none(ptep_get(pte))) - return -EBUSY; + if (!pte_none(entry)) { + if (!mkwrite) + return -EBUSY; + + /* + * For read faults on private mappings the PFN passed in may not + * match the PFN we have mapped if the mapped PFN is a writeable + * COW page. In the mkwrite case we are creating a writable PTE + * for a shared mapping and we expect the PFNs to match. If they + * don't match, we are likely racing with block allocation and + * mapping invalidation so just skip the update. + */ + if (pte_pfn(entry) != page_to_pfn(page)) { + WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry))); + return -EFAULT; + } + entry = maybe_mkwrite(entry, vma); + entry = pte_mkyoung(entry); + if (ptep_set_access_flags(vma, addr, pte, entry, 1)) + update_mmu_cache(vma, addr, pte); + return 0; + } + /* Ok, finally just insert the thing.. */ pteval = mk_pte(page, prot); if (unlikely(is_zero_folio(folio))) { pteval = pte_mkspecial(pteval); } else { folio_get(folio); + entry = mk_pte(page, prot); + if (mkwrite) { + entry = pte_mkyoung(entry); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } inc_mm_counter(vma->vm_mm, mm_counter_file(folio)); folio_add_file_rmap_pte(folio, page, vma); } @@ -2063,7 +2091,7 @@ static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, } static int insert_page(struct vm_area_struct *vma, unsigned long addr, - struct page *page, pgprot_t prot) + struct page *page, pgprot_t prot, bool mkwrite) { int retval; pte_t *pte; @@ -2076,7 +2104,8 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; - retval = insert_page_into_pte_locked(vma, pte, addr, page, prot); + retval = insert_page_into_pte_locked(vma, pte, addr, page, prot, + mkwrite); pte_unmap_unlock(pte, ptl); out: return retval; @@ -2090,7 +2119,7 @@ static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, err = validate_page_before_insert(vma, page); if (err) return err; - return insert_page_into_pte_locked(vma, pte, addr, page, prot); + return insert_page_into_pte_locked(vma, pte, addr, page, prot, false); } /* insert_pages() amortizes the cost of spinlock operations @@ -2226,7 +2255,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } - return insert_page(vma, addr, page, vma->vm_page_prot); + return insert_page(vma, addr, page, vma->vm_page_prot, false); } EXPORT_SYMBOL(vm_insert_page); @@ -2506,7 +2535,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); - err = insert_page(vma, addr, page, pgprot); + err = insert_page(vma, addr, page, pgprot, mkwrite); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } -- git-series 0.9.1