2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* linux/arch/arm/mm/mmap.c
|
|
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/shm.h>
|
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-21 05:22:52 +08:00
|
|
|
#include <linux/sched.h>
|
2008-09-05 21:08:44 +08:00
|
|
|
#include <linux/io.h>
|
2011-04-13 11:57:17 +08:00
|
|
|
#include <linux/personality.h>
|
2010-06-15 09:16:19 +08:00
|
|
|
#include <linux/random.h>
|
2011-11-22 11:01:06 +08:00
|
|
|
#include <asm/cachetype.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define COLOUR_ALIGN(addr,pgoff) \
|
|
|
|
((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \
|
|
|
|
(((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
|
|
|
|
|
2011-11-22 11:01:07 +08:00
|
|
|
/* gap between mmap and stack */
|
|
|
|
#define MIN_GAP (128*1024*1024UL)
|
|
|
|
#define MAX_GAP ((TASK_SIZE)/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;
|
|
|
|
}
|
|
|
|
|
|
|
|
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(TASK_SIZE - gap - rnd);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* We need to ensure that shared mappings are correctly aligned to
|
|
|
|
* avoid aliasing issues with VIPT caches. We need to ensure that
|
|
|
|
* a specific page of an object is always mapped at a multiple of
|
|
|
|
* SHMLBA bytes.
|
|
|
|
*
|
|
|
|
* We unconditionally provide this function for all cases, however
|
|
|
|
* in the VIVT case, we optimise out the alignment rules.
|
|
|
|
*/
|
|
|
|
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;
|
2011-11-22 11:01:06 +08:00
|
|
|
int do_align = 0;
|
|
|
|
int aliasing = cache_is_vipt_aliasing();
|
2012-12-12 08:02:10 +08:00
|
|
|
struct vm_unmapped_area_info info;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We only need to do colour alignment if either the I or D
|
2011-11-22 11:01:06 +08:00
|
|
|
* caches alias.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2011-11-22 11:01:06 +08:00
|
|
|
if (aliasing)
|
|
|
|
do_align = filp || (flags & MAP_SHARED);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
2007-05-07 05:50:07 +08:00
|
|
|
* We enforce the MAP_FIXED case.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
if (flags & MAP_FIXED) {
|
2009-12-06 04:10:44 +08:00
|
|
|
if (aliasing && flags & MAP_SHARED &&
|
|
|
|
(addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (len > TASK_SIZE)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (addr) {
|
|
|
|
if (do_align)
|
|
|
|
addr = COLOUR_ALIGN(addr, pgoff);
|
|
|
|
else
|
|
|
|
addr = PAGE_ALIGN(addr);
|
|
|
|
|
|
|
|
vma = find_vma(mm, addr);
|
|
|
|
if (TASK_SIZE - len >= addr &&
|
|
|
|
(!vma || addr + len <= vma->vm_start))
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
2012-12-12 08:02:10 +08:00
|
|
|
info.flags = 0;
|
|
|
|
info.length = len;
|
|
|
|
info.low_limit = mm->mmap_base;
|
|
|
|
info.high_limit = TASK_SIZE;
|
|
|
|
info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
|
|
|
|
info.align_offset = pgoff << PAGE_SHIFT;
|
|
|
|
return vm_unmapped_area(&info);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2011-11-22 11:01:07 +08:00
|
|
|
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;
|
|
|
|
int do_align = 0;
|
|
|
|
int aliasing = cache_is_vipt_aliasing();
|
2012-12-12 08:02:10 +08:00
|
|
|
struct vm_unmapped_area_info info;
|
2011-11-22 11:01:07 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We only need to do colour alignment if either the I or D
|
|
|
|
* caches alias.
|
|
|
|
*/
|
|
|
|
if (aliasing)
|
|
|
|
do_align = filp || (flags & MAP_SHARED);
|
|
|
|
|
|
|
|
/* requested length too big for entire address space */
|
|
|
|
if (len > TASK_SIZE)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (flags & MAP_FIXED) {
|
|
|
|
if (aliasing && flags & MAP_SHARED &&
|
|
|
|
(addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
|
|
|
|
return -EINVAL;
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* requesting a specific address */
|
|
|
|
if (addr) {
|
|
|
|
if (do_align)
|
|
|
|
addr = COLOUR_ALIGN(addr, pgoff);
|
|
|
|
else
|
|
|
|
addr = PAGE_ALIGN(addr);
|
|
|
|
vma = find_vma(mm, addr);
|
|
|
|
if (TASK_SIZE - len >= addr &&
|
|
|
|
(!vma || addr + len <= vma->vm_start))
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
2012-12-12 08:02:10 +08:00
|
|
|
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
|
|
|
|
info.length = len;
|
2013-11-29 05:43:40 +08:00
|
|
|
info.low_limit = FIRST_USER_ADDRESS;
|
2012-12-12 08:02:10 +08:00
|
|
|
info.high_limit = mm->mmap_base;
|
|
|
|
info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
|
|
|
|
info.align_offset = pgoff << PAGE_SHIFT;
|
|
|
|
addr = vm_unmapped_area(&info);
|
2011-11-22 11:01:07 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2012-12-12 08:02:10 +08:00
|
|
|
if (addr & ~PAGE_MASK) {
|
|
|
|
VM_BUG_ON(addr != -ENOMEM);
|
|
|
|
info.flags = 0;
|
|
|
|
info.low_limit = mm->mmap_base;
|
|
|
|
info.high_limit = TASK_SIZE;
|
|
|
|
addr = vm_unmapped_area(&info);
|
|
|
|
}
|
2011-11-22 11:01:07 +08:00
|
|
|
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
2015-04-15 06:48:00 +08:00
|
|
|
unsigned long arch_mmap_rnd(void)
|
arm: factor out mmap ASLR into mmap_rnd
To address the "offset2lib" ASLR weakness[1], this separates ET_DYN ASLR
from mmap ASLR, as already done on s390. The architectures that are
already randomizing mmap (arm, arm64, mips, powerpc, s390, and x86), have
their various forms of arch_mmap_rnd() made available via the new
CONFIG_ARCH_HAS_ELF_RANDOMIZE. For these architectures,
arch_randomize_brk() is collapsed as well.
This is an alternative to the solutions in:
https://lkml.org/lkml/2015/2/23/442
I've been able to test x86 and arm, and the buildbot (so far) seems happy
with building the rest.
[1] http://cybersecurity.upv.es/attacks/offset2lib/offset2lib.html
This patch (of 10):
In preparation for splitting out ET_DYN ASLR, this moves the ASLR
calculations for mmap on ARM into a separate routine, similar to x86.
This also removes the redundant check of personality (PF_RANDOMIZE is
already set before calling arch_pick_mmap_layout).
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Hector Marco-Gisbert <hecmargi@upv.es>
Cc: Russell King <linux@arm.linux.org.uk>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Arun Chandran <achandran@mvista.com>
Cc: Yann Droneaud <ydroneaud@opteya.com>
Cc: Min-Hua Chen <orca.chen@gmail.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Alex Smith <alex@alex-smith.me.uk>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: Vineeth Vijayan <vvijayan@mvista.com>
Cc: Jeff Bailey <jeffbailey@google.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Behan Webster <behanw@converseincode.com>
Cc: Ismael Ripoll <iripoll@upv.es>
Cc: Jan-Simon Mller <dl9pf@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 06:47:41 +08:00
|
|
|
{
|
|
|
|
unsigned long rnd;
|
|
|
|
|
|
|
|
/* 8 bits of randomness in 20 address space bits */
|
|
|
|
rnd = (unsigned long)get_random_int() % (1 << 8);
|
|
|
|
|
|
|
|
return rnd << PAGE_SHIFT;
|
|
|
|
}
|
|
|
|
|
2011-11-22 11:01:07 +08:00
|
|
|
void arch_pick_mmap_layout(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
unsigned long random_factor = 0UL;
|
|
|
|
|
arm: factor out mmap ASLR into mmap_rnd
To address the "offset2lib" ASLR weakness[1], this separates ET_DYN ASLR
from mmap ASLR, as already done on s390. The architectures that are
already randomizing mmap (arm, arm64, mips, powerpc, s390, and x86), have
their various forms of arch_mmap_rnd() made available via the new
CONFIG_ARCH_HAS_ELF_RANDOMIZE. For these architectures,
arch_randomize_brk() is collapsed as well.
This is an alternative to the solutions in:
https://lkml.org/lkml/2015/2/23/442
I've been able to test x86 and arm, and the buildbot (so far) seems happy
with building the rest.
[1] http://cybersecurity.upv.es/attacks/offset2lib/offset2lib.html
This patch (of 10):
In preparation for splitting out ET_DYN ASLR, this moves the ASLR
calculations for mmap on ARM into a separate routine, similar to x86.
This also removes the redundant check of personality (PF_RANDOMIZE is
already set before calling arch_pick_mmap_layout).
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Hector Marco-Gisbert <hecmargi@upv.es>
Cc: Russell King <linux@arm.linux.org.uk>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Arun Chandran <achandran@mvista.com>
Cc: Yann Droneaud <ydroneaud@opteya.com>
Cc: Min-Hua Chen <orca.chen@gmail.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Alex Smith <alex@alex-smith.me.uk>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: Vineeth Vijayan <vvijayan@mvista.com>
Cc: Jeff Bailey <jeffbailey@google.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Behan Webster <behanw@converseincode.com>
Cc: Ismael Ripoll <iripoll@upv.es>
Cc: Jan-Simon Mller <dl9pf@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 06:47:41 +08:00
|
|
|
if (current->flags & PF_RANDOMIZE)
|
2015-04-15 06:48:00 +08:00
|
|
|
random_factor = arch_mmap_rnd();
|
2011-11-22 11:01:07 +08:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
2006-09-16 17:50:22 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* You really shouldn't be using read() or write() on /dev/mem. This
|
|
|
|
* might go away in the future.
|
|
|
|
*/
|
2012-09-13 02:05:58 +08:00
|
|
|
int valid_phys_addr_range(phys_addr_t addr, size_t size)
|
2006-09-16 17:50:22 +08:00
|
|
|
{
|
2008-02-27 01:42:10 +08:00
|
|
|
if (addr < PHYS_OFFSET)
|
|
|
|
return 0;
|
2009-10-02 07:45:28 +08:00
|
|
|
if (addr + size > __pa(high_memory - 1) + 1)
|
2006-09-16 17:50:22 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2013-09-24 23:38:00 +08:00
|
|
|
* Do not allow /dev/mem mappings beyond the supported physical range.
|
2006-09-16 17:50:22 +08:00
|
|
|
*/
|
|
|
|
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
|
|
|
|
{
|
2013-09-24 23:38:00 +08:00
|
|
|
return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
|
2006-09-16 17:50:22 +08:00
|
|
|
}
|
2010-09-23 06:34:36 +08:00
|
|
|
|
|
|
|
#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
|