mm: prevent get_user_pages() from overflowing page refcount

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@google.com>
Acked-by: Matthew Wilcox <willy@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/gup.c b/mm/gup.c
index 75029649baca4ac834732b931cb9f743cdc58afb..81e0bdefa2ccb936fc2182e59e513dcf2c2076a4 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -157,8 +157,12 @@ retry:
                goto retry;
        }
 
-       if (flags & FOLL_GET)
-               get_page(page);
+       if (flags & FOLL_GET) {
+               if (unlikely(!try_get_page(page))) {
+                       page = ERR_PTR(-ENOMEM);
+                       goto out;
+               }
+       }
        if (flags & FOLL_TOUCH) {
                if ((flags & FOLL_WRITE) &&
                    !pte_dirty(pte) && !PageDirty(page))
@@ -295,7 +299,10 @@ retry_locked:
                        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);
@@ -497,7 +504,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
                if (is_device_public_page(*page))
                        goto unmap;
        }
-       get_page(*page);
+       if (unlikely(!try_get_page(*page))) {
+               ret = -ENOMEM;
+               goto unmap;
+       }
 out:
        ret = 0;
 unmap:
@@ -1393,6 +1403,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
        }
 }
 
+/*
+ * 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 CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
                         int write, struct page **pages, int *nr)
@@ -1427,9 +1451,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
                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))) {
@@ -1568,8 +1592,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
                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;
        }
@@ -1606,8 +1630,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
                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;
        }
@@ -1643,8 +1667,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
                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;
        }

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8dfdffc34a99bcb099742fd9614196fd3e1f685f..c220315dc5331f74817dc1d05c5fc411bec80ae8 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4298,6 +4298,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
                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);