1 files changed, 198 insertions, 35 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 5c356a57b892..f703fe8c8346 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -733,6 +733,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 				pte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(*src_pte))
 					pte = pte_swp_mksoft_dirty(pte);
+				if (pte_swp_uffd_wp(*src_pte))
+					pte = pte_swp_mkuffd_wp(pte);
 				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		} else if (is_device_private_entry(entry)) {
@@ -762,6 +764,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			    is_cow_mapping(vm_flags)) {
 				make_device_private_entry_read(&entry);
 				pte = swp_entry_to_pte(entry);
+				if (pte_swp_uffd_wp(*src_pte))
+					pte = pte_swp_mkuffd_wp(pte);
 				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		}
@@ -785,6 +789,14 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pte = pte_mkclean(pte);
 	pte = pte_mkold(pte);
 
+	/*
+	 * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA
+	 * does not have the VM_UFFD_WP, which means that the uffd
+	 * fork event is not enabled.
+	 */
+	if (!(vm_flags & VM_UFFD_WP))
+		pte = pte_clear_uffd_wp(pte);
+
 	page = vm_normal_page(vma, addr, pte);
 	if (page) {
 		get_page(page);
@@ -1407,8 +1419,7 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(zap_vma_ptes);
 
-pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
-			spinlock_t **ptl)
+static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -1427,9 +1438,40 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 		return NULL;
 
 	VM_BUG_ON(pmd_trans_huge(*pmd));
+	return pmd;
+}
+
+pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
+			spinlock_t **ptl)
+{
+	pmd_t *pmd = walk_to_pmd(mm, addr);
+
+	if (!pmd)
+		return NULL;
 	return pte_alloc_map_lock(mm, pmd, addr, ptl);
 }
 
+static int validate_page_before_insert(struct page *page)
+{
+	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+		return -EINVAL;
+	flush_dcache_page(page);
+	return 0;
+}
+
+static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte,
+			unsigned long addr, struct page *page, pgprot_t prot)
+{
+	if (!pte_none(*pte))
+		return -EBUSY;
+	/* Ok, finally just insert the thing.. */
+	get_page(page);
+	inc_mm_counter_fast(mm, mm_counter_file(page));
+	page_add_file_rmap(page, false);
+	set_pte_at(mm, addr, pte, mk_pte(page, prot));
+	return 0;
+}
+
 /*
  * This is the old fallback for page remapping.
  *
@@ -1445,31 +1487,135 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	retval = -EINVAL;
-	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+	retval = validate_page_before_insert(page);
+	if (retval)
 		goto out;
 	retval = -ENOMEM;
-	flush_dcache_page(page);
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
 		goto out;
-	retval = -EBUSY;
-	if (!pte_none(*pte))
-		goto out_unlock;
-
-	/* Ok, finally just insert the thing.. */
-	get_page(page);
-	inc_mm_counter_fast(mm, mm_counter_file(page));
-	page_add_file_rmap(page, false);
-	set_pte_at(mm, addr, pte, mk_pte(page, prot));
-
-	retval = 0;
-out_unlock:
+	retval = insert_page_into_pte_locked(mm, pte, addr, page, prot);
 	pte_unmap_unlock(pte, ptl);
 out:
 	return retval;
 }
 
+#ifdef pte_index
+static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, struct page *page, pgprot_t prot)
+{
+	int err;
+
+	if (!page_count(page))
+		return -EINVAL;
+	err = validate_page_before_insert(page);
+	return err ? err : insert_page_into_pte_locked(
+		mm, pte_offset_map(pmd, addr), addr, page, prot);
+}
+
+/* insert_pages() amortizes the cost of spinlock operations
+ * when inserting pages in a loop. Arch *must* define pte_index.
+ */
+static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
+			struct page **pages, unsigned long *num, pgprot_t prot)
+{
+	pmd_t *pmd = NULL;
+	spinlock_t *pte_lock = NULL;
+	struct mm_struct *const mm = vma->vm_mm;
+	unsigned long curr_page_idx = 0;
+	unsigned long remaining_pages_total = *num;
+	unsigned long pages_to_write_in_pmd;
+	int ret;
+more:
+	ret = -EFAULT;
+	pmd = walk_to_pmd(mm, addr);
+	if (!pmd)
+		goto out;
+
+	pages_to_write_in_pmd = min_t(unsigned long,
+		remaining_pages_total, PTRS_PER_PTE - pte_index(addr));
+
+	/* Allocate the PTE if necessary; takes PMD lock once only. */
+	ret = -ENOMEM;
+	if (pte_alloc(mm, pmd))
+		goto out;
+	pte_lock = pte_lockptr(mm, pmd);
+
+	while (pages_to_write_in_pmd) {
+		int pte_idx = 0;
+		const int batch_size = min_t(int, pages_to_write_in_pmd, 8);
+
+		spin_lock(pte_lock);
+		for (; pte_idx < batch_size; ++pte_idx) {
+			int err = insert_page_in_batch_locked(mm, pmd,
+				addr, pages[curr_page_idx], prot);
+			if (unlikely(err)) {
+				spin_unlock(pte_lock);
+				ret = err;
+				remaining_pages_total -= pte_idx;
+				goto out;
+			}
+			addr += PAGE_SIZE;
+			++curr_page_idx;
+		}
+		spin_unlock(pte_lock);
+		pages_to_write_in_pmd -= batch_size;
+		remaining_pages_total -= batch_size;
+	}
+	if (remaining_pages_total)
+		goto more;
+	ret = 0;
+out:
+	*num = remaining_pages_total;
+	return ret;
+}
+#endif  /* ifdef pte_index */
+
+/**
+ * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
+ * @vma: user vma to map to
+ * @addr: target start user address of these pages
+ * @pages: source kernel pages
+ * @num: in: number of pages to map. out: number of pages that were *not*
+ * mapped. (0 means all pages were successfully mapped).
+ *
+ * Preferred over vm_insert_page() when inserting multiple pages.
+ *
+ * In case of error, we may have mapped a subset of the provided
+ * pages. It is the caller's responsibility to account for this case.
+ *
+ * The same restrictions apply as in vm_insert_page().
+ */
+int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
+			struct page **pages, unsigned long *num)
+{
+#ifdef pte_index
+	const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
+
+	if (addr < vma->vm_start || end_addr >= vma->vm_end)
+		return -EFAULT;
+	if (!(vma->vm_flags & VM_MIXEDMAP)) {
+		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
+		BUG_ON(vma->vm_flags & VM_PFNMAP);
+		vma->vm_flags |= VM_MIXEDMAP;
+	}
+	/* Defer page refcount checking till we're about to map that page. */
+	return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
+#else
+	unsigned long idx = 0, pgcount = *num;
+	int err;
+
+	for (; idx < pgcount; ++idx) {
+		err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]);
+		if (err)
+			break;
+	}
+	*num = pgcount - idx;
+	return err;
+#endif  /* ifdef pte_index */
+}
+EXPORT_SYMBOL(vm_insert_pages);
+
 /**
  * vm_insert_page - insert single page into user vma
  * @vma: user vma to map to
@@ -1940,7 +2086,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
  * @vma: user vma to map to
  * @addr: target user address to start at
  * @pfn: page frame number of kernel physical memory address
- * @size: size of map area
+ * @size: size of mapping area
  * @prot: page protection flags for this mapping
  *
  * Note: this is only safe if the mm semaphore is held when called.
@@ -2752,6 +2898,11 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
+	if (userfaultfd_pte_wp(vma, *vmf->pte)) {
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return handle_userfault(vmf, VM_UFFD_WP);
+	}
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*
@@ -3085,6 +3236,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	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)) {
+		pte = pte_mkuffd_wp(pte);
+		pte = pte_wrprotect(pte);
+	}
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;
@@ -3373,7 +3528,7 @@ map_pte:
 	return 0;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3475,8 +3630,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 	pte_t entry;
 	vm_fault_t ret;
 
-	if (pmd_none(*vmf->pmd) && PageTransCompound(page) &&
-			IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
+	if (pmd_none(*vmf->pmd) && PageTransCompound(page)) {
 		/* THP on COW? */
 		VM_BUG_ON_PAGE(memcg, page);
 
@@ -3949,31 +4103,40 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 /* `inline' is required to avoid gcc 4.1.2 build error */
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
-	if (vma_is_anonymous(vmf->vma))
+	if (vma_is_anonymous(vmf->vma)) {
+		if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd))
+			return handle_userfault(vmf, VM_UFFD_WP);
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+	}
+	if (vmf->vma->vm_ops->huge_fault) {
+		vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	}
 
-	/* COW handled on pte level: split pmd */
-	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
+	/* COW or write-notify handled on pte level: split pmd. */
 	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
 }
 
-static inline bool vma_is_accessible(struct vm_area_struct *vma)
-{
-	return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE);
-}
-
 static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vmf->vma))
-		return VM_FAULT_FALLBACK;
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+		goto split;
+	if (vmf->vma->vm_ops->huge_fault) {
+		vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	}
+split:
+	/* COW or write-notify not handled on PUD level: split pud.*/
+	__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 	return VM_FAULT_FALLBACK;
 }