OpenCloudOS-Kernel/arch/mips/mm/mmap.c

209 lines
5.0 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2011 Wind River Systems,
* written by Ralf Baechle <ralf@linux-mips.org>
*/
#include <linux/compiler.h>
#include <linux/elf-randomize.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/export.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */
EXPORT_SYMBOL(shm_align_mask);
/* gap between mmap and stack */
#define MIN_GAP (128*1024*1024UL)
#define MAX_GAP ((TASK_SIZE)/6*5)
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
static int mmap_is_legacy(struct rlimit *rlim_stack)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
if (rlim_stack->rlim_cur == RLIM_INFINITY)
return 1;
return sysctl_legacy_va_layout;
}
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
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);
}
#define COLOUR_ALIGN(addr, pgoff) \
((((addr) + shm_align_mask) & ~shm_align_mask) + \
(((pgoff) << PAGE_SHIFT) & shm_align_mask))
enum mmap_allocation_direction {UP, DOWN};
static unsigned long arch_get_unmapped_area_common(struct file *filp,
unsigned long addr0, unsigned long len, unsigned long pgoff,
unsigned long flags, enum mmap_allocation_direction dir)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long addr = addr0;
int do_color_align;
struct vm_unmapped_area_info info;
if (unlikely(len > TASK_SIZE))
return -ENOMEM;
if (flags & MAP_FIXED) {
/* Even MAP_FIXED mappings must reside within TASK_SIZE */
if (TASK_SIZE - len < addr)
return -EINVAL;
/*
* We do not accept a shared mapping if it would violate
* cache aliasing constraints.
*/
if ((flags & MAP_SHARED) &&
((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
return -EINVAL;
return addr;
}
do_color_align = 0;
if (filp || (flags & MAP_SHARED))
do_color_align = 1;
/* requesting a specific address */
if (addr) {
if (do_color_align)
addr = COLOUR_ALIGN(addr, pgoff);
else
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= 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)))
return addr;
}
info.length = len;
info.align_mask = do_color_align ? (PAGE_MASK & shm_align_mask) : 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (dir == DOWN) {
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.low_limit = PAGE_SIZE;
info.high_limit = mm->mmap_base;
addr = vm_unmapped_area(&info);
if (!(addr & ~PAGE_MASK))
return addr;
/*
* 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.
*/
}
info.flags = 0;
info.low_limit = mm->mmap_base;
info.high_limit = TASK_SIZE;
return vm_unmapped_area(&info);
}
unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
return arch_get_unmapped_area_common(filp,
addr0, len, pgoff, flags, UP);
}
/*
* There is no need to export this but sched.h declares the function as
* extern so making it static here results in an error.
*/
unsigned long arch_get_unmapped_area_topdown(struct file *filp,
unsigned long addr0, unsigned long len, unsigned long pgoff,
unsigned long flags)
{
return arch_get_unmapped_area_common(filp,
addr0, len, pgoff, flags, DOWN);
}
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)
{
unsigned long rnd;
#ifdef CONFIG_COMPAT
if (TASK_IS_32BIT_ADDR)
rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
else
#endif /* CONFIG_COMPAT */
rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
return rnd << PAGE_SHIFT;
}
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
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();
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
mm->get_unmapped_area = arch_get_unmapped_area;
} else {
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] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("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 07:34:53 +08:00
mm->mmap_base = mmap_base(random_factor, rlim_stack);
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
}
}
static inline unsigned long brk_rnd(void)
{
unsigned long rnd = get_random_long();
rnd = rnd << PAGE_SHIFT;
/* 8MB for 32bit, 256MB for 64bit */
if (TASK_IS_32BIT_ADDR)
rnd = rnd & 0x7ffffful;
else
rnd = rnd & 0xffffffful;
return rnd;
}
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
unsigned long base = mm->brk;
unsigned long ret;
ret = PAGE_ALIGN(base + brk_rnd());
if (ret < mm->brk)
return mm->brk;
return ret;
}
int __virt_addr_valid(const volatile void *kaddr)
{
return pfn_valid(PFN_DOWN(virt_to_phys(kaddr)));
}
EXPORT_SYMBOL_GPL(__virt_addr_valid);