summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2017-11-02 15:59:29 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-03 07:39:19 -0700
commit1e3921471354244f70fe268586ff94a97a6dd4df (patch)
treed103a318db6e2d238365ff0e585dc56fd1962b1d
parent5cb0512c02ecd7e6214e912e4c150f4219ac78e0 (diff)
userfaultfd: hugetlbfs: prevent UFFDIO_COPY to fill beyond the end of i_size
This oops: kernel BUG at fs/hugetlbfs/inode.c:484! RIP: remove_inode_hugepages+0x3d0/0x410 Call Trace: hugetlbfs_setattr+0xd9/0x130 notify_change+0x292/0x410 do_truncate+0x65/0xa0 do_sys_ftruncate.constprop.3+0x11a/0x180 SyS_ftruncate+0xe/0x10 tracesys+0xd9/0xde was caused by the lack of i_size check in hugetlb_mcopy_atomic_pte. mmap() can still succeed beyond the end of the i_size after vmtruncate zapped vmas in those ranges, but the faults must not succeed, and that includes UFFDIO_COPY. We could differentiate the retval to userland to represent a SIGBUS like a page fault would do (vs SIGSEGV), but it doesn't seem very useful and we'd need to pick a random retval as there's no meaningful syscall retval that would differentiate from SIGSEGV and SIGBUS, there's just -EFAULT. Link: http://lkml.kernel.org/r/20171016223914.2421-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/hugetlb.c32
1 files changed, 30 insertions, 2 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 424b0ef08a60..2d2ff5e8bf2b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3984,6 +3984,9 @@ 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 +4024,24 @@ 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 +4050,20 @@ 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;