linux/arch/x86/kernel/sys_x86_64.c
Hugh Dickins 1be7107fbe mm: larger stack guard gap, between vmas
Stack guard page is a useful feature to reduce a risk of stack smashing
into a different mapping. We have been using a single page gap which
is sufficient to prevent having stack adjacent to a different mapping.
But this seems to be insufficient in the light of the stack usage in
userspace. E.g. glibc uses as large as 64kB alloca() in many commonly
used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX]
which is 256kB or stack strings with MAX_ARG_STRLEN.

This will become especially dangerous for suid binaries and the default
no limit for the stack size limit because those applications can be
tricked to consume a large portion of the stack and a single glibc call
could jump over the guard page. These attacks are not theoretical,
unfortunatelly.

Make those attacks less probable by increasing the stack guard gap
to 1MB (on systems with 4k pages; but make it depend on the page size
because systems with larger base pages might cap stack allocations in
the PAGE_SIZE units) which should cover larger alloca() and VLA stack
allocations. It is obviously not a full fix because the problem is
somehow inherent, but it should reduce attack space a lot.

One could argue that the gap size should be configurable from userspace,
but that can be done later when somebody finds that the new 1MB is wrong
for some special case applications.  For now, add a kernel command line
option (stack_guard_gap) to specify the stack gap size (in page units).

Implementation wise, first delete all the old code for stack guard page:
because although we could get away with accounting one extra page in a
stack vma, accounting a larger gap can break userspace - case in point,
a program run with "ulimit -S -v 20000" failed when the 1MB gap was
counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK
and strict non-overcommit mode.

Instead of keeping gap inside the stack vma, maintain the stack guard
gap as a gap between vmas: using vm_start_gap() in place of vm_start
(or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few
places which need to respect the gap - mainly arch_get_unmapped_area(),
and and the vma tree's subtree_gap support for that.

Original-patch-by: Oleg Nesterov <oleg@redhat.com>
Original-patch-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Tested-by: Helge Deller <deller@gmx.de> # parisc
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 21:50:20 +08:00

218 lines
5.3 KiB
C

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/msg.h>
#include <linux/shm.h>
#include <linux/stat.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/uaccess.h>
#include <linux/elf.h>
#include <asm/elf.h>
#include <asm/compat.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
/*
* Align a virtual address to avoid aliasing in the I$ on AMD F15h.
*/
static unsigned long get_align_mask(void)
{
/* handle 32- and 64-bit case with a single conditional */
if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
return 0;
if (!(current->flags & PF_RANDOMIZE))
return 0;
return va_align.mask;
}
/*
* To avoid aliasing in the I$ on AMD F15h, the bits defined by the
* va_align.bits, [12:upper_bit), are set to a random value instead of
* zeroing them. This random value is computed once per boot. This form
* of ASLR is known as "per-boot ASLR".
*
* To achieve this, the random value is added to the info.align_offset
* value before calling vm_unmapped_area() or ORed directly to the
* address.
*/
static unsigned long get_align_bits(void)
{
return va_align.bits & get_align_mask();
}
unsigned long align_vdso_addr(unsigned long addr)
{
unsigned long align_mask = get_align_mask();
addr = (addr + align_mask) & ~align_mask;
return addr | get_align_bits();
}
static int __init control_va_addr_alignment(char *str)
{
/* guard against enabling this on other CPU families */
if (va_align.flags < 0)
return 1;
if (*str == 0)
return 1;
if (*str == '=')
str++;
if (!strcmp(str, "32"))
va_align.flags = ALIGN_VA_32;
else if (!strcmp(str, "64"))
va_align.flags = ALIGN_VA_64;
else if (!strcmp(str, "off"))
va_align.flags = 0;
else if (!strcmp(str, "on"))
va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
else
return 0;
return 1;
}
__setup("align_va_addr", control_va_addr_alignment);
SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, off)
{
long error;
error = -EINVAL;
if (off & ~PAGE_MASK)
goto out;
error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
out:
return error;
}
static void find_start_end(unsigned long flags, unsigned long *begin,
unsigned long *end)
{
if (!in_compat_syscall() && (flags & MAP_32BIT)) {
/* This is usually used needed to map code in small
model, so it needs to be in the first 31bit. Limit
it to that. This means we need to move the
unmapped base down for this case. This can give
conflicts with the heap, but we assume that glibc
malloc knows how to fall back to mmap. Give it 1GB
of playground for now. -AK */
*begin = 0x40000000;
*end = 0x80000000;
if (current->flags & PF_RANDOMIZE) {
*begin = randomize_page(*begin, 0x02000000);
}
return;
}
*begin = get_mmap_base(1);
*end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit();
}
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
unsigned long begin, end;
if (flags & MAP_FIXED)
return addr;
find_start_end(flags, &begin, &end);
if (len > end)
return -ENOMEM;
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (end - len >= addr &&
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = 0;
info.length = len;
info.low_limit = begin;
info.high_limit = end;
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
}
return vm_unmapped_area(&info);
}
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
const unsigned long len, const unsigned long pgoff,
const unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
return -ENOMEM;
if (flags & MAP_FIXED)
return addr;
/* for MAP_32BIT mappings we force the legacy mmap base */
if (!in_compat_syscall() && (flags & MAP_32BIT))
goto bottomup;
/* requesting a specific address */
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
}
addr = vm_unmapped_area(&info);
if (!(addr & ~PAGE_MASK))
return addr;
VM_BUG_ON(addr != -ENOMEM);
bottomup:
/*
* A failed mmap() very likely causes application failure,
* so fall back to the bottom-up function here. This scenario
* can happen with large stack limits and large mmap()
* allocations.
*/
return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}