linux_dsm_epyc7002/arch/arm/mm/mmap.c
Kees Cook 8f2af155b5 exec: pass stack rlimit into mm layout functions
Patch series "exec: Pin stack limit during exec".

Attempts to solve problems with the stack limit changing during exec
continue to be frustrated[1][2].  In addition to the specific issues
around the Stack Clash family of flaws, Andy Lutomirski pointed out[3]
other places during exec where the stack limit is used and is assumed to
be unchanging.  Given the many places it gets used and the fact that it
can be manipulated/raced via setrlimit() and prlimit(), I think the only
way to handle this is to move away from the "current" view of the stack
limit and instead attach it to the bprm, and plumb this down into the
functions that need to know the stack limits.  This series implements
the approach.

[1] 04e35f4495 ("exec: avoid RLIMIT_STACK races with prlimit()")
[2] 779f4e1c6c ("Revert "exec: avoid RLIMIT_STACK races with prlimit()"")
[3] to security@kernel.org, "Subject: existing rlimit races?"

This patch (of 3):

Since it is possible that the stack rlimit can change externally during
exec (either via another thread calling setrlimit() or another process
calling prlimit()), provide a way to pass the rlimit down into the
per-architecture mm layout functions so that the rlimit can stay in the
bprm structure instead of sitting in the signal structure until exec is
finalized.

Link: http://lkml.kernel.org/r/1518638796-20819-2-git-send-email-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hugh Dickins <hughd@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Greg KH <greg@kroah.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Cc: Brad Spengler <spender@grsecurity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-11 10:28:37 -07:00

242 lines
5.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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(struct rlimit *rlim_stack)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
if (rlim_stack->rlim_cur == RLIM_INFINITY)
return 1;
return sysctl_legacy_va_layout;
}
static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
unsigned long gap = rlim_stack->rlim_cur;
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, struct rlimit *rlim_stack)
{
unsigned long random_factor = 0UL;
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
mm->get_unmapped_area = arch_get_unmapped_area;
} else {
mm->mmap_base = mmap_base(random_factor, rlim_stack);
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