x86/mm: Fix VDSO and VVAR placement on 5-level paging machines
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Thu, 3 Aug 2023 15:16:09 +0000 (18:16 +0300)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 16 Aug 2023 16:27:25 +0000 (18:27 +0200)
commit9ad49178c00a5f20cd97a81cfa87dba8dfa9ff0f
tree6a8e03634a035ca61d640acfb9f7953c470561e3
parent25085250a150da4599c3f8dd9db6b76dc864178a
x86/mm: Fix VDSO and VVAR placement on 5-level paging machines

commit 1b8b1aa90c9c0e825b181b98b8d9e249dc395470 upstream.

Yingcong has noticed that on the 5-level paging machine, VDSO and VVAR
VMAs are placed above the 47-bit border:

8000001a9000-8000001ad000 r--p 00000000 00:00 0                          [vvar]
8000001ad000-8000001af000 r-xp 00000000 00:00 0                          [vdso]

This might confuse users who are not aware of 5-level paging and expect
all userspace addresses to be under the 47-bit border.

So far problem has only been triggered with ASLR disabled, although it
may also occur with ASLR enabled if the layout is randomized in a just
right way.

The problem happens due to custom placement for the VMAs in the VDSO
code: vdso_addr() tries to place them above the stack and checks the
result against TASK_SIZE_MAX, which is wrong. TASK_SIZE_MAX is set to
the 56-bit border on 5-level paging machines. Use DEFAULT_MAP_WINDOW
instead.

Fixes: b569bab78d8d ("x86/mm: Prepare to expose larger address space to userspace")
Reported-by: Yingcong Wu <yingcong.wu@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20230803151609.22141-1-kirill.shutemov%40linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
arch/x86/entry/vdso/vma.c