A vma with vm_pgoff large enough to overflow a loff_t type when
converted to a byte offset can be passed via the remap_file_pages
system call. The hugetlbfs mmap routine uses the byte offset to
calculate reservations and file size.
A sequence such as:
mmap(0x20a00000, 0x600000, 0, 0x66033, -1, 0);
remap_file_pages(0x20a00000, 0x600000, 0, 0x20000000000000, 0);
will result in the following when task exits/file closed,
kernel BUG at mm/hugetlb.c:749!
Call Trace:
hugetlbfs_evict_inode+0x2f/0x40
evict+0xcb/0x190
__dentry_kill+0xcb/0x150
__fput+0x164/0x1e0
task_work_run+0x84/0xa0
exit_to_usermode_loop+0x7d/0x80
do_syscall_64+0x18b/0x190
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
The overflowed pgoff value causes hugetlbfs to try to set up a
mapping with a negative range (end < start) that leaves invalid
state which causes the BUG.
The previous overflow fix to this code was incomplete and did not
take the remap_file_pages system call into account.
Fixes: 045c7a3f53d9 ("hugetlbfs: fix offset overflow in hugetlbfs mmap")
Cc: <stable@xxxxxxxxxxxxxxx>
Reported-by: Nic Losby <blurbdust@xxxxxxxxx>
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
Changes in v2
* Use bitmask for overflow check as suggested by Yisheng Xie
* Add explicit (from > to) check when setting up reservations
* Cc stable
fs/hugetlbfs/inode.c | 11 ++++++++---
mm/hugetlb.c | 6 ++++++
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8fe1b0aa2896..dafffa6affae 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -111,6 +111,7 @@ static void huge_pagevec_release(struct pagevec *pvec)
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
+ unsigned long ovfl_mask;
loff_t len, vma_len;
int ret;
struct hstate *h = hstate_file(file);
@@ -127,12 +128,16 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
vma->vm_ops = &hugetlb_vm_ops;
/*
- * Offset passed to mmap (before page shift) could have been
- * negative when represented as a (l)off_t.
+ * page based offset in vm_pgoff could be sufficiently large to
+ * overflow a (l)off_t when converted to byte offset.
*/
- if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+ ovfl_mask = (1UL << (PAGE_SHIFT + 1)) - 1;
+ ovfl_mask <<= ((sizeof(unsigned long) * BITS_PER_BYTE) -
+ (PAGE_SHIFT + 1));
+ if (vma->vm_pgoff & ovfl_mask)
return -EINVAL;
+ /* must be huge page aligned */
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c204e3d132b..8eeade0a0b7a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4374,6 +4374,12 @@ int hugetlb_reserve_pages(struct inode *inode,
struct resv_map *resv_map;
long gbl_reserve;
+ /* This should never happen */
+ if (from > to) {
+ VM_WARN(1, "%s called with a negative range\n", __func__);
+ return -EINVAL;
+ }
+
/*
* Only apply hugepage reservation if asked. At fault time, an
* attempt will be made for VM_NORESERVE to allocate a page
--
2.13.6