mm/hugetlb: handle uffd-wp during fork()

Firstly, we'll need to pass in dst_vma into copy_hugetlb_page_range()
because for uffd-wp it's the dst vma that matters on deciding how we
should treat uffd-wp protected ptes.

We should recognize pte markers during fork and do the pte copy if needed.

[lkp@intel.com: vma_needs_copy can be static]
  Link: https://lkml.kernel.org/r/Ylb0CGeFJlc4EzLk@7ec4ff11d4ae
Link: https://lkml.kernel.org/r/20220405014918.14932-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 30 insertions, 16 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 99281aecbd28..01f0e2e5ab48 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4719,23 +4719,24 @@ hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr
 }
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-			    struct vm_area_struct *vma)
+			    struct vm_area_struct *dst_vma,
+			    struct vm_area_struct *src_vma)
 {
 	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
-	bool cow = is_cow_mapping(vma->vm_flags);
-	struct hstate *h = hstate_vma(vma);
+	bool cow = is_cow_mapping(src_vma->vm_flags);
+	struct hstate *h = hstate_vma(src_vma);
 	unsigned long sz = huge_page_size(h);
 	unsigned long npages = pages_per_huge_page(h);
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = src_vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
 	if (cow) {
-		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
-					vma->vm_start,
-					vma->vm_end);
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src,
+					src_vma->vm_start,
+					src_vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
 		mmap_assert_write_locked(src);
 		raw_write_seqcount_begin(&src->write_protect_seq);
@@ -4749,12 +4750,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		i_mmap_lock_read(mapping);
 	}
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
+		dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4789,6 +4790,7 @@ again:
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+			bool uffd_wp = huge_pte_uffd_wp(entry);
 
 			if (!is_readable_migration_entry(swp_entry) && cow) {
 				/*
@@ -4798,10 +4800,21 @@ again:
 				swp_entry = make_readable_migration_entry(
 							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
+				if (userfaultfd_wp(src_vma) && uffd_wp)
+					entry = huge_pte_mkuffd_wp(entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);
 			}
+			if (!userfaultfd_wp(dst_vma) && uffd_wp)
+				entry = huge_pte_clear_uffd_wp(entry);
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+		} else if (unlikely(is_pte_marker(entry))) {
+			/*
+			 * We copy the pte marker only if the dst vma has
+			 * uffd-wp enabled.
+			 */
+			if (userfaultfd_wp(dst_vma))
+				set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else {
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
@@ -4819,20 +4832,21 @@ again:
 			 */
 			if (!PageAnon(ptepage)) {
 				page_dup_file_rmap(ptepage, true);
-			} else if (page_try_dup_anon_rmap(ptepage, true, vma)) {
+			} else if (page_try_dup_anon_rmap(ptepage, true,
+							  src_vma)) {
 				pte_t src_pte_old = entry;
 				struct page *new;
 
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				/* Do not use reserve as it's private owned */
-				new = alloc_huge_page(vma, addr, 1);
+				new = alloc_huge_page(dst_vma, addr, 1);
 				if (IS_ERR(new)) {
 					put_page(ptepage);
 					ret = PTR_ERR(new);
 					break;
 				}
-				copy_user_huge_page(new, ptepage, addr, vma,
+				copy_user_huge_page(new, ptepage, addr, dst_vma,
 						    npages);
 				put_page(ptepage);
 
@@ -4842,13 +4856,13 @@ again:
 				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 				entry = huge_ptep_get(src_pte);
 				if (!pte_same(src_pte_old, entry)) {
-					restore_reserve_on_error(h, vma, addr,
+					restore_reserve_on_error(h, dst_vma, addr,
 								new);
 					put_page(new);
 					/* dst_entry won't change as in child */
 					goto again;
 				}
-				hugetlb_install_page(vma, dst_pte, addr, new);
+				hugetlb_install_page(dst_vma, dst_pte, addr, new);
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				continue;
diff --git a/mm/memory.c b/mm/memory.c
index 82adda885605..f4161fb07ffa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1234,7 +1234,7 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
  * false when we can speed up fork() by allowing lazy page faults later until
  * when the child accesses the memory range.
  */
-bool
+static bool
 vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	/*
@@ -1278,7 +1278,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		return 0;
 
 	if (is_vm_hugetlb_page(src_vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
+		return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
 
 	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*