linux/arch/x86/mm/mmap.c
Craig Bergstrom ce56a86e2a x86/mm: Limit mmap() of /dev/mem to valid physical addresses
Currently, it is possible to mmap() any offset from /dev/mem.  If a
program mmaps() /dev/mem offsets outside of the addressable limits
of a system, the page table can be corrupted by setting reserved bits.

For example if you mmap() offset 0x0001000000000000 of /dev/mem on an
x86_64 system with a 48-bit bus, the page fault handler will be called
with error_code set to RSVD.  The kernel then crashes with a page table
corruption error.

This change prevents this page table corruption on x86 by refusing
to mmap offsets higher than the highest valid address in the system.

Signed-off-by: Craig Bergstrom <craigb@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: dsafonov@virtuozzo.com
Cc: kirill.shutemov@linux.intel.com
Cc: mhocko@suse.com
Cc: oleg@redhat.com
Link: http://lkml.kernel.org/r/20171019192856.39672-1-craigb@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-20 09:48:00 +02:00

189 lines
4.9 KiB
C

/*
* Flexible mmap layout support
*
* Based on code by Ingo Molnar and Andi Kleen, copyrighted
* as follows:
*
* Copyright 2003-2009 Red Hat Inc.
* All Rights Reserved.
* Copyright 2005 Andi Kleen, SUSE Labs.
* Copyright 2007 Jiri Kosina, SUSE Labs.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/personality.h>
#include <linux/mm.h>
#include <linux/random.h>
#include <linux/limits.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/compat.h>
#include <asm/elf.h>
struct va_alignment __read_mostly va_align = {
.flags = -1,
};
unsigned long task_size_32bit(void)
{
return IA32_PAGE_OFFSET;
}
unsigned long task_size_64bit(int full_addr_space)
{
return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW;
}
static unsigned long stack_maxrandom_size(unsigned long task_size)
{
unsigned long max = 0;
if (current->flags & PF_RANDOMIZE) {
max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit());
max <<= PAGE_SHIFT;
}
return max;
}
#ifdef CONFIG_COMPAT
# define mmap32_rnd_bits mmap_rnd_compat_bits
# define mmap64_rnd_bits mmap_rnd_bits
#else
# define mmap32_rnd_bits mmap_rnd_bits
# define mmap64_rnd_bits mmap_rnd_bits
#endif
#define SIZE_128M (128 * 1024 * 1024UL)
static int mmap_is_legacy(void)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
return sysctl_legacy_va_layout;
}
static unsigned long arch_rnd(unsigned int rndbits)
{
if (!(current->flags & PF_RANDOMIZE))
return 0;
return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
}
unsigned long arch_mmap_rnd(void)
{
return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
}
static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
{
unsigned long gap = rlimit(RLIMIT_STACK);
unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
unsigned long gap_min, gap_max;
/* Values close to RLIM_INFINITY can overflow. */
if (gap + pad > gap)
gap += pad;
/*
* Top of mmap area (just below the process stack).
* Leave an at least ~128 MB hole with possible stack randomization.
*/
gap_min = SIZE_128M;
gap_max = (task_size / 6) * 5;
if (gap < gap_min)
gap = gap_min;
else if (gap > gap_max)
gap = gap_max;
return PAGE_ALIGN(task_size - gap - rnd);
}
static unsigned long mmap_legacy_base(unsigned long rnd,
unsigned long task_size)
{
return __TASK_UNMAPPED_BASE(task_size) + rnd;
}
/*
* This function, called very early during the creation of a new
* process VM image, sets up which VM layout function to use:
*/
static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
unsigned long random_factor, unsigned long task_size)
{
*legacy_base = mmap_legacy_base(random_factor, task_size);
if (mmap_is_legacy())
*base = *legacy_base;
else
*base = mmap_base(random_factor, task_size);
}
void arch_pick_mmap_layout(struct mm_struct *mm)
{
if (mmap_is_legacy())
mm->get_unmapped_area = arch_get_unmapped_area;
else
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
arch_rnd(mmap64_rnd_bits), task_size_64bit(0));
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
/*
* The mmap syscall mapping base decision depends solely on the
* syscall type (64-bit or compat). This applies for 64bit
* applications and 32bit applications. The 64bit syscall uses
* mmap_base, the compat syscall uses mmap_compat_base.
*/
arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base,
arch_rnd(mmap32_rnd_bits), task_size_32bit());
#endif
}
unsigned long get_mmap_base(int is_legacy)
{
struct mm_struct *mm = current->mm;
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
if (in_compat_syscall()) {
return is_legacy ? mm->mmap_compat_legacy_base
: mm->mmap_compat_base;
}
#endif
return is_legacy ? mm->mmap_legacy_base : mm->mmap_base;
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_flags & VM_MPX)
return "[mpx]";
return NULL;
}
int valid_phys_addr_range(phys_addr_t addr, size_t count)
{
return addr + count <= __pa(high_memory);
}
int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
{
phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT;
return valid_phys_addr_range(addr, count);
}