linux/arch/arm64/mm/mmap.c
Ard Biesheuvel 1151f838cb arm64: kernel: restrict /dev/mem read() calls to linear region
When running lscpu on an AArch64 system that has SMBIOS version 2.0
tables, it will segfault in the following way:

  Unable to handle kernel paging request at virtual address ffff8000bfff0000
  pgd = ffff8000f9615000
  [ffff8000bfff0000] *pgd=0000000000000000
  Internal error: Oops: 96000007 [#1] PREEMPT SMP
  Modules linked in:
  CPU: 0 PID: 1284 Comm: lscpu Not tainted 4.11.0-rc3+ #103
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  task: ffff8000fa78e800 task.stack: ffff8000f9780000
  PC is at __arch_copy_to_user+0x90/0x220
  LR is at read_mem+0xcc/0x140

This is caused by the fact that lspci issues a read() on /dev/mem at the
offset where it expects to find the SMBIOS structure array. However, this
region is classified as EFI_RUNTIME_SERVICE_DATA (as per the UEFI spec),
and so it is omitted from the linear mapping.

So let's restrict /dev/mem read/write access to those areas that are
covered by the linear region.

Reported-by: Alexander Graf <agraf@suse.de>
Fixes: 4dffbfc48d ("arm64/efi: mark UEFI reserved regions as MEMBLOCK_NOMAP")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-06-01 18:26:26 +01:00

149 lines
3.9 KiB
C

/*
* Based on arch/arm/mm/mmap.c
*
* Copyright (C) 2012 ARM Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* 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, see <http://www.gnu.org/licenses/>.
*/
#include <linux/elf.h>
#include <linux/fs.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/export.h>
#include <linux/shm.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/io.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <asm/cputype.h>
/*
* Leave enough space between the mmap area and the stack to honour ulimit in
* the face of randomisation.
*/
#define MIN_GAP (SZ_128M + ((STACK_RND_MASK << PAGE_SHIFT) + 1))
#define MAX_GAP (STACK_TOP/6*5)
static int mmap_is_legacy(void)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
return 1;
return sysctl_legacy_va_layout;
}
unsigned long arch_mmap_rnd(void)
{
unsigned long rnd;
#ifdef CONFIG_COMPAT
if (test_thread_flag(TIF_32BIT))
rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
else
#endif
rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
return rnd << PAGE_SHIFT;
}
static unsigned long mmap_base(unsigned long rnd)
{
unsigned long gap = rlimit(RLIMIT_STACK);
if (gap < MIN_GAP)
gap = MIN_GAP;
else if (gap > MAX_GAP)
gap = MAX_GAP;
return PAGE_ALIGN(STACK_TOP - gap - rnd);
}
/*
* This function, called very early during the creation of a new process VM
* image, sets up which VM layout function to use:
*/
void arch_pick_mmap_layout(struct mm_struct *mm)
{
unsigned long random_factor = 0UL;
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
/*
* Fall back to the standard layout if the personality bit is set, or
* if the expected stack growth is unlimited:
*/
if (mmap_is_legacy()) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
mm->get_unmapped_area = arch_get_unmapped_area;
} else {
mm->mmap_base = mmap_base(random_factor);
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
}
}
/*
* You really shouldn't be using read() or write() on /dev/mem. This might go
* away in the future.
*/
int valid_phys_addr_range(phys_addr_t addr, size_t size)
{
/*
* Check whether addr is covered by a memory region without the
* MEMBLOCK_NOMAP attribute, and whether that region covers the
* entire range. In theory, this could lead to false negatives
* if the range is covered by distinct but adjacent memory regions
* that only differ in other attributes. However, few of such
* attributes have been defined, and it is debatable whether it
* follows that /dev/mem read() calls should be able traverse
* such boundaries.
*/
return memblock_is_region_memory(addr, size) &&
memblock_is_map_memory(addr);
}
/*
* Do not allow /dev/mem mappings beyond the supported physical range.
*/
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK);
}
#ifdef CONFIG_STRICT_DEVMEM
#include <linux/ioport.h>
/*
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number. We mimic x86 here by
* disallowing access to system RAM as well as device-exclusive MMIO regions.
* This effectively disable read()/write() on /dev/mem.
*/
int devmem_is_allowed(unsigned long pfn)
{
if (iomem_is_exclusive(pfn << PAGE_SHIFT))
return 0;
if (!page_is_ram(pfn))
return 1;
return 0;
}
#endif