Sync to v4.15-rc3 for security subsystem developers to work against.

1 files changed, 54 insertions, 6 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 424b0ef08a60..9a334f5fb730 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3125,6 +3125,13 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 	}
 }
 
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	if (addr & ~(huge_page_mask(hstate_vma(vma))))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3141,6 +3148,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
+	.split = hugetlb_vm_op_split,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
@@ -3256,9 +3264,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
 		} else {
 			if (cow) {
+				/*
+				 * No need to notify as we are downgrading page
+				 * table protection not changing it to point
+				 * to a new page.
+				 *
+				 * See Documentation/vm/mmu_notifier.txt
+				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
-				mmu_notifier_invalidate_range(src, mmun_start,
-								   mmun_end);
 			}
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
@@ -3984,6 +3997,9 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    unsigned long src_addr,
 			    struct page **pagep)
 {
+	struct address_space *mapping;
+	pgoff_t idx;
+	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
 	struct hstate *h = hstate_vma(dst_vma);
 	pte_t _dst_pte;
@@ -4021,13 +4037,24 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageUptodate(page);
 	set_page_huge_active(page);
 
+	mapping = dst_vma->vm_file->f_mapping;
+	idx = vma_hugecache_offset(h, dst_vma, dst_addr);
+
 	/*
 	 * If shared, add to page cache
 	 */
 	if (vm_shared) {
-		struct address_space *mapping = dst_vma->vm_file->f_mapping;
-		pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
+		size = i_size_read(mapping->host) >> huge_page_shift(h);
+		ret = -EFAULT;
+		if (idx >= size)
+			goto out_release_nounlock;
 
+		/*
+		 * Serialization between remove_inode_hugepages() and
+		 * huge_add_to_page_cache() below happens through the
+		 * hugetlb_fault_mutex_table that here must be hold by
+		 * the caller.
+		 */
 		ret = huge_add_to_page_cache(page, mapping, idx);
 		if (ret)
 			goto out_release_nounlock;
@@ -4036,6 +4063,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
 	spin_lock(ptl);
 
+	/*
+	 * Recheck the i_size after holding PT lock to make sure not
+	 * to leave any page mapped (as page_mapped()) beyond the end
+	 * of the i_size (remove_inode_hugepages() is strict about
+	 * enforcing that). If we bail out here, we'll also leave a
+	 * page in the radix tree in the vm_shared case beyond the end
+	 * of the i_size, but remove_inode_hugepages() will take care
+	 * of it as soon as we drop the hugetlb_fault_mutex_table.
+	 */
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
+	ret = -EFAULT;
+	if (idx >= size)
+		goto out_release_unlock;
+
 	ret = -EEXIST;
 	if (!huge_pte_none(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
@@ -4290,7 +4331,12 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * and that page table be reused and filled with junk.
 	 */
 	flush_hugetlb_tlb_range(vma, start, end);
-	mmu_notifier_invalidate_range(mm, start, end);
+	/*
+	 * No need to call mmu_notifier_invalidate_range() we are downgrading
+	 * page table protection not changing it to point to a new page.
+	 *
+	 * See Documentation/vm/mmu_notifier.txt
+	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 
@@ -4589,7 +4635,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	p4d = p4d_offset(pgd, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
 	pud = pud_alloc(mm, p4d, addr);
 	if (pud) {
 		if (sz == PUD_SIZE) {