[PATCH 4.9 57/83] mm: prevent get_user_pages() from overflowing page refcount

[Greg Kroah-Hartman]

From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>

commit 8fde12ca79aff9b5ba951fce1a2641901b8d8e64 upstream.

If the page refcount wraps around past zero, it will be freed while
there are still four billion references to it.  One of the possible
avenues for an attacker to try to make this happen is by doing direct IO
on a page multiple times.  This patch makes get_user_pages() refuse to
take a new page reference if there are already more than two billion
references to the page.

Reported-by: Jann Horn <jannh@xxxxxxxxxx>
Acked-by: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 4.9:
 - Add the "err" variable in follow_hugetlb_page()
 - Adjust context]
Signed-off-by: Ben Hutchings <ben.hutchings@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 mm/gup.c     |   45 ++++++++++++++++++++++++++++++++++-----------
 mm/hugetlb.c |   16 +++++++++++++++-
 2 files changed, 49 insertions(+), 12 deletions(-)

--- a/mm/gup.c
+++ b/mm/gup.c
@@ -153,7 +153,10 @@ retry:
 	}
 
 	if (flags & FOLL_GET) {
-		get_page(page);
+		if (unlikely(!try_get_page(page))) {
+			page = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 
 		/* drop the pgmap reference now that we hold the page */
 		if (pgmap) {
@@ -292,7 +295,10 @@ struct page *follow_page_mask(struct vm_
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
 		} else {
-			get_page(page);
+			if (unlikely(!try_get_page(page))) {
+				spin_unlock(ptl);
+				return ERR_PTR(-ENOMEM);
+			}
 			spin_unlock(ptl);
 			lock_page(page);
 			ret = split_huge_page(page);
@@ -348,7 +354,10 @@ static int get_gate_page(struct mm_struc
 			goto unmap;
 		*page = pte_page(*pte);
 	}
-	get_page(*page);
+	if (unlikely(!try_get_page(*page))) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
 out:
 	ret = 0;
 unmap:
@@ -1231,6 +1240,20 @@ struct page *get_dump_page(unsigned long
  */
 #ifdef CONFIG_HAVE_GENERIC_RCU_GUP
 
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+	return head;
+}
+
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
@@ -1263,9 +1286,9 @@ static int gup_pte_range(pmd_t pmd, unsi
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
-		head = compound_head(page);
 
-		if (!page_cache_get_speculative(head))
+		head = try_get_compound_head(page, 1);
+		if (!head)
 			goto pte_unmap;
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1321,8 +1344,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pmd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pmd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1355,8 +1378,8 @@ static int gup_huge_pud(pud_t orig, pud_
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pud_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pud_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1390,8 +1413,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pgd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pgd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3984,6 +3984,7 @@ long follow_hugetlb_page(struct mm_struc
 	unsigned long vaddr = *position;
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
+	int err = -EFAULT;
 
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
@@ -4055,6 +4056,19 @@ long follow_hugetlb_page(struct mm_struc
 
 		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));
+
+		/*
+		 * Instead of doing 'try_get_page()' below in the same_page
+		 * loop, just check the count once here.
+		 */
+		if (unlikely(page_count(page) <= 0)) {
+			if (pages) {
+				spin_unlock(ptl);
+				remainder = 0;
+				err = -ENOMEM;
+				break;
+			}
+		}
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);
@@ -4081,7 +4095,7 @@ same_page:
 	*nr_pages = remainder;
 	*position = vaddr;
 
-	return i ? i : -EFAULT;
+	return i ? i : err;
 }
 
 #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE