mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git
synced 2024-12-28 16:52:18 +00:00
872bb37f68
The codgen for adding architecture-specific stack alignment to the effective alloca() usage is somewhat inefficient and allows a bit to get carried beyond the desired entropy range. This isn't really a problem, but it's unexpected and the codegen is kind of bad. Quoting Mark[1], the disassembly for arm64's invoke_syscall() looks like: // offset = raw_cpu_read(kstack_offset) mov x4, sp adrp x0, kstack_offset mrs x5, tpidr_el1 add x0, x0, #:lo12:kstack_offset ldr w0, [x0, x5] // offset = KSTACK_OFFSET_MAX(offset) and x0, x0, #0x3ff // alloca(offset) add x0, x0, #0xf and x0, x0, #0x7f0 sub sp, x4, x0 ... which in C would be: offset = raw_cpu_read(kstack_offset) offset &= 0x3ff; // [0x0, 0x3ff] offset += 0xf; // [0xf, 0x40e] offset &= 0x7f0; // [0x0, ... so when *all* bits [3:0] are 0, they'll have no impact, and when *any* of bits [3:0] are 1 they'll trigger a carry into bit 4, which could ripple all the way up and spill into bit 10. Switch the masking in KSTACK_OFFSET_MAX() to explicitly clear the bottom bits to avoid the rounding by using 0b1111110000 instead of 0b1111111111: // offset = raw_cpu_read(kstack_offset) mov x4, sp adrp x0, 0 <kstack_offset> mrs x5, tpidr_el1 add x0, x0, #:lo12:kstack_offset ldr w0, [x0, x5] // offset = KSTACK_OFFSET_MAX(offset) and x0, x0, #0x3f0 // alloca(offset) sub sp, x4, x0 Suggested-by: Mark Rutland <mark.rutland@arm.com> Link: https://lore.kernel.org/lkml/ZnVfOnIuFl2kNWkT@J2N7QTR9R3/ [1] Link: https://lore.kernel.org/r/20240702211612.work.576-kees@kernel.org Signed-off-by: Kees Cook <kees@kernel.org>
99 lines
4.0 KiB
C
99 lines
4.0 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, 6 bits of entropy (on 64-bit; 8 on 32-bit). This cap is
|
|
* to keep the "VLA" from being unbounded (see above). Additionally clear
|
|
* the bottom 4 bits (on 64-bit systems, 2 for 32-bit), since stack
|
|
* alignment will always be at least word size. This makes the compiler
|
|
* code gen better when it is applying the actual per-arch alignment to
|
|
* the final offset. The resulting randomness is reasonable without overly
|
|
* constraining usable stack space.
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111110000)
|
|
#else
|
|
#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111111100)
|
|
#endif
|
|
|
|
/**
|
|
* add_random_kstack_offset - Increase stack utilization by previously
|
|
* chosen random offset
|
|
*
|
|
* This should be used in the syscall entry path when interrupts and
|
|
* preempt are disabled, and after user registers have been stored to
|
|
* the stack. For testing the resulting entropy, please see:
|
|
* tools/testing/selftests/lkdtm/stack-entropy.sh
|
|
*/
|
|
#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)
|
|
|
|
/**
|
|
* choose_random_kstack_offset - Choose the random offset for the next
|
|
* add_random_kstack_offset()
|
|
*
|
|
* This should only be used during syscall exit when interrupts and
|
|
* preempt are disabled. This position in the syscall flow is done to
|
|
* frustrate attacks from userspace attempting to learn the next offset:
|
|
* - Maximize the timing uncertainty visible from userspace: if the
|
|
* offset is chosen at syscall entry, userspace has much more control
|
|
* over the timing between choosing offsets. "How long will we be in
|
|
* kernel mode?" tends to be more difficult to predict than "how long
|
|
* will we be in user mode?"
|
|
* - Reduce the lifetime of the new offset sitting in memory during
|
|
* kernel mode execution. Exposure of "thread-local" memory content
|
|
* (e.g. current, percpu, etc) tends to be easier than arbitrary
|
|
* location memory exposure.
|
|
*/
|
|
#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 = ror32(offset, 5) ^ (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
|