linux/arch/s390/mm/mmap.c

206 lines
4.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0+
/*
* flexible mmap layout support
*
* Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
* All Rights Reserved.
*
* Started by Ingo Molnar <mingo@elte.hu>
*/
#include <linux/elf-randomize.h>
#include <linux/personality.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/random.h>
#include <linux/compat.h>
#include <linux/security.h>
#include <asm/pgalloc.h>
#include <asm/elf.h>
static unsigned long stack_maxrandom_size(void)
{
if (!(current->flags & PF_RANDOMIZE))
return 0;
if (current->personality & ADDR_NO_RANDOMIZE)
return 0;
return STACK_RND_MASK << PAGE_SHIFT;
}
/*
* Top of mmap area (just below the process stack).
*
* Leave at least a ~32 MB hole.
*/
#define MIN_GAP (32*1024*1024)
#define MAX_GAP (STACK_TOP/6*5)
static inline 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;
}
mm: expose arch_mmap_rnd when available When an architecture fully supports randomizing the ELF load location, a per-arch mmap_rnd() function is used to find a randomized mmap base. In preparation for randomizing the location of ET_DYN binaries separately from mmap, this renames and exports these functions as arch_mmap_rnd(). Additionally introduces CONFIG_ARCH_HAS_ELF_RANDOMIZE for describing this feature on architectures that support it (which is a superset of ARCH_BINFMT_ELF_RANDOMIZE_PIE, since s390 already supports a separated ET_DYN ASLR from mmap ASLR without the ARCH_BINFMT_ELF_RANDOMIZE_PIE logic). 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 06:48:00 +08:00
unsigned long arch_mmap_rnd(void)
{
return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT;
}
static unsigned long mmap_base_legacy(unsigned long rnd)
{
return TASK_UNMAPPED_BASE + rnd;
}
static inline 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;
gap &= PAGE_MASK;
return STACK_TOP - stack_maxrandom_size() - rnd - gap;
}
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;
struct vm_unmapped_area_info info;
int rc;
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
goto check_asce_limit;
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
mm: larger stack guard gap, between vmas 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>
2017-06-19 19:03:24 +08:00
(!vma || addr + len <= vm_start_gap(vma)))
goto check_asce_limit;
}
info.flags = 0;
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = TASK_SIZE;
if (filp || (flags & MAP_SHARED))
info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
else
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
addr = vm_unmapped_area(&info);
if (addr & ~PAGE_MASK)
return addr;
check_asce_limit:
if (addr + len > current->mm->context.asce_limit &&
addr + len <= TASK_SIZE) {
rc = crst_table_upgrade(mm, addr + len);
if (rc)
return (unsigned long) rc;
}
return addr;
}
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;
struct vm_unmapped_area_info info;
int rc;
/* requested length too big for entire address space */
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
goto check_asce_limit;
/* requesting a specific address */
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
mm: larger stack guard gap, between vmas 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>
2017-06-19 19:03:24 +08:00
(!vma || addr + len <= vm_start_gap(vma)))
goto check_asce_limit;
}
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = max(PAGE_SIZE, mmap_min_addr);
info.high_limit = mm->mmap_base;
if (filp || (flags & MAP_SHARED))
info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
else
info.align_mask = 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 = TASK_UNMAPPED_BASE;
info.high_limit = TASK_SIZE;
addr = vm_unmapped_area(&info);
if (addr & ~PAGE_MASK)
return addr;
}
check_asce_limit:
if (addr + len > current->mm->context.asce_limit &&
addr + len <= TASK_SIZE) {
rc = crst_table_upgrade(mm, addr + len);
if (rc)
return (unsigned long) rc;
}
return addr;
}
/*
* 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)
mm: expose arch_mmap_rnd when available When an architecture fully supports randomizing the ELF load location, a per-arch mmap_rnd() function is used to find a randomized mmap base. In preparation for randomizing the location of ET_DYN binaries separately from mmap, this renames and exports these functions as arch_mmap_rnd(). Additionally introduces CONFIG_ARCH_HAS_ELF_RANDOMIZE for describing this feature on architectures that support it (which is a superset of ARCH_BINFMT_ELF_RANDOMIZE_PIE, since s390 already supports a separated ET_DYN ASLR from mmap ASLR without the ARCH_BINFMT_ELF_RANDOMIZE_PIE logic). 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 06:48:00 +08:00
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 = mmap_base_legacy(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;
}
}