efa90c11f6
All supported versions of Clang perform auto-init of __builtin_alloca()
when stack auto-init is on (CONFIG_INIT_STACK_ALL_{ZERO,PATTERN}).
add_random_kstack_offset() uses __builtin_alloca() to add a stack
offset. This means, when CONFIG_INIT_STACK_ALL_{ZERO,PATTERN} is
enabled, add_random_kstack_offset() will auto-init that unused portion
of the stack used to add an offset.
There are several problems with this:
1. These offsets can be as large as 1023 bytes. Performing
memset() on them isn't exactly cheap, and this is done on
every syscall entry.
2. Architectures adding add_random_kstack_offset() to syscall
entry implemented in C require them to be 'noinstr' (e.g. see
x86 and s390). The potential problem here is that a call to
memset may occur, which is not noinstr.
A x86_64 defconfig kernel with Clang 11 and CONFIG_VMLINUX_VALIDATION shows:
| vmlinux.o: warning: objtool: do_syscall_64()+0x9d: call to memset() leaves .noinstr.text section
| vmlinux.o: warning: objtool: do_int80_syscall_32()+0xab: call to memset() leaves .noinstr.text section
| vmlinux.o: warning: objtool: __do_fast_syscall_32()+0xe2: call to memset() leaves .noinstr.text section
| vmlinux.o: warning: objtool: fixup_bad_iret()+0x2f: call to memset() leaves .noinstr.text section
Clang 14 (unreleased) will introduce a way to skip alloca initialization
via __builtin_alloca_uninitialized() (https://reviews.llvm.org/D115440).
Constrain RANDOMIZE_KSTACK_OFFSET to only be enabled if no stack
auto-init is enabled, the compiler is GCC, or Clang is version 14+. Use
__builtin_alloca_uninitialized() if the compiler provides it, as is done
by Clang 14.
Link: https://lkml.kernel.org/r/YbHTKUjEejZCLyhX@elver.google.com
Fixes: 39218ff4c625 ("stack: Optionally randomize kernel stack offset each syscall")
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220131090521.1947110-2-elver@google.com
72 lines
2.7 KiB
C
72 lines
2.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
#ifndef _LINUX_RANDOMIZE_KSTACK_H
|
|
#define _LINUX_RANDOMIZE_KSTACK_H
|
|
|
|
#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
|
|
#include <linux/kernel.h>
|
|
#include <linux/jump_label.h>
|
|
#include <linux/percpu-defs.h>
|
|
|
|
DECLARE_STATIC_KEY_MAYBE(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
|
|
randomize_kstack_offset);
|
|
DECLARE_PER_CPU(u32, kstack_offset);
|
|
|
|
/*
|
|
* Do not use this anywhere else in the kernel. This is used here because
|
|
* it provides an arch-agnostic way to grow the stack with correct
|
|
* alignment. Also, since this use is being explicitly masked to a max of
|
|
* 10 bits, stack-clash style attacks are unlikely. For more details see
|
|
* "VLAs" in Documentation/process/deprecated.rst
|
|
*
|
|
* The normal __builtin_alloca() is initialized with INIT_STACK_ALL (currently
|
|
* only with Clang and not GCC). Initializing the unused area on each syscall
|
|
* entry is expensive, and generating an implicit call to memset() may also be
|
|
* problematic (such as in noinstr functions). Therefore, if the compiler
|
|
* supports it (which it should if it initializes allocas), always use the
|
|
* "uninitialized" variant of the builtin.
|
|
*/
|
|
#if __has_builtin(__builtin_alloca_uninitialized)
|
|
#define __kstack_alloca __builtin_alloca_uninitialized
|
|
#else
|
|
#define __kstack_alloca __builtin_alloca
|
|
#endif
|
|
|
|
/*
|
|
* Use, at most, 10 bits of entropy. We explicitly cap this to keep the
|
|
* "VLA" from being unbounded (see above). 10 bits leaves enough room for
|
|
* per-arch offset masks to reduce entropy (by removing higher bits, since
|
|
* high entropy may overly constrain usable stack space), and for
|
|
* compiler/arch-specific stack alignment to remove the lower bits.
|
|
*/
|
|
#define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF)
|
|
|
|
/*
|
|
* These macros must be used during syscall entry when interrupts and
|
|
* preempt are disabled, and after user registers have been stored to
|
|
* the stack.
|
|
*/
|
|
#define add_random_kstack_offset() do { \
|
|
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
|
|
&randomize_kstack_offset)) { \
|
|
u32 offset = raw_cpu_read(kstack_offset); \
|
|
u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \
|
|
/* Keep allocation even after "ptr" loses scope. */ \
|
|
asm volatile("" :: "r"(ptr) : "memory"); \
|
|
} \
|
|
} while (0)
|
|
|
|
#define choose_random_kstack_offset(rand) do { \
|
|
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
|
|
&randomize_kstack_offset)) { \
|
|
u32 offset = raw_cpu_read(kstack_offset); \
|
|
offset ^= (rand); \
|
|
raw_cpu_write(kstack_offset, offset); \
|
|
} \
|
|
} while (0)
|
|
#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
|
|
#define add_random_kstack_offset() do { } while (0)
|
|
#define choose_random_kstack_offset(rand) do { } while (0)
|
|
#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
|
|
|
|
#endif
|