mm: prevent get_user_pages() from overflowing page refcount

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

diff --git a/mm/gup.c b/mm/gup.c
index 0a5374e6e82daa5e257229148c2c35e7b1548562..caadd31714a544411a915babd954867453576f2b 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -153,7 +153,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
        }
 
        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) {
@@ -296,7 +299,10 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
                        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);
@@ -480,7 +486,10 @@ 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:
@@ -1368,6 +1377,20 @@ 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)
@@ -1402,9 +1425,9 @@ 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))) {
@@ -1543,8 +1566,8 @@ 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;
        }
@@ -1581,8 +1604,8 @@ 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;
        }
@@ -1618,8 +1641,8 @@ 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 9e5f66cbf711c032c9db3eadb3c428b90c742c72..5fb779cda972cc781d3f222016dc6e42c8e89dbe 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4299,6 +4299,19 @@ 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);