mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 08:14:15 +08:00
1be7107fbe
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>
241 lines
5.6 KiB
C
241 lines
5.6 KiB
C
/*
|
|
* linux/arch/arm/mm/mmap.c
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mman.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/cachetype.h>
|
|
|
|
#define COLOUR_ALIGN(addr,pgoff) \
|
|
((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \
|
|
(((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
|
|
|
|
/* 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);
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
int do_align = 0;
|
|
int aliasing = cache_is_vipt_aliasing();
|
|
struct vm_unmapped_area_info info;
|
|
|
|
/*
|
|
* We only need to do colour alignment if either the I or D
|
|
* caches alias.
|
|
*/
|
|
if (aliasing)
|
|
do_align = filp || (flags & MAP_SHARED);
|
|
|
|
/*
|
|
* We enforce the MAP_FIXED case.
|
|
*/
|
|
if (flags & MAP_FIXED) {
|
|
if (aliasing && flags & MAP_SHARED &&
|
|
(addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
|
|
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 <= vm_start_gap(vma)))
|
|
return addr;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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();
|
|
struct vm_unmapped_area_info info;
|
|
|
|
/*
|
|
* 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 <= vm_start_gap(vma)))
|
|
return addr;
|
|
}
|
|
|
|
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
|
|
info.length = len;
|
|
info.low_limit = FIRST_USER_ADDRESS;
|
|
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);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
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);
|
|
}
|
|
|
|
return addr;
|
|
}
|
|
|
|
unsigned long arch_mmap_rnd(void)
|
|
{
|
|
unsigned long rnd;
|
|
|
|
rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
|
|
|
|
return rnd << PAGE_SHIFT;
|
|
}
|
|
|
|
void arch_pick_mmap_layout(struct mm_struct *mm)
|
|
{
|
|
unsigned long random_factor = 0UL;
|
|
|
|
if (current->flags & PF_RANDOMIZE)
|
|
random_factor = arch_mmap_rnd();
|
|
|
|
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)
|
|
{
|
|
if (addr < PHYS_OFFSET)
|
|
return 0;
|
|
if (addr + size > __pa(high_memory - 1) + 1)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* 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 + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
|
|
}
|
|
|
|
#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
|