hugetlbfs: check for pgoff value overflow

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.

[[email protected]: v3]
  Link: http://lkml.kernel.org/r/[email protected]
[[email protected]: include mmdebug.h]
[[email protected]: fix -ve left shift count on sh]
Link: http://lkml.kernel.org/r/[email protected]
Fixes: 045c7a3 ("hugetlbfs: fix offset overflow in hugetlbfs mmap")
Signed-off-by: Mike Kravetz <[email protected]>
Reported-by: Nic Losby <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: "Kirill A . Shutemov" <[email protected]>
Cc: Yisheng Xie <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

fs/hugetlbfs/inode.c

@@ -108,6 +108,16 @@ static void huge_pagevec_release(struct pagevec *pvec)
 	pagevec_reinit(pvec);
 }
 
+/*
+ * Mask used when checking the page offset value passed in via system
+ * calls.  This value will be converted to a loff_t which is signed.
+ * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the
+ * value.  The extra bit (- 1 in the shift value) is to take the sign
+ * bit into account.
+ */
+#define PGOFF_LOFFT_MAX \
+	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
@@ -127,12 +137,13 @@ 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)
+	if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
 		return -EINVAL;
 
+	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 

mm/hugetlb.c

@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
 #include <linux/string_helpers.h>
@@ -4374,6 +4375,12 @@ 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