[linux-block.git] / include / linux / randomize_kstack.h

/* 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
Commit	Line	Data
39218ff4 KC	1	/* SPDX-License-Identifier: GPL-2.0-only */
	2	#ifndef _LINUX_RANDOMIZE_KSTACK_H
	3	#define _LINUX_RANDOMIZE_KSTACK_H
	4
8cb37a59	5	#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
39218ff4 KC	6	#include <linux/kernel.h>
	7	#include <linux/jump_label.h>
	8	#include <linux/percpu-defs.h>
	9
	10	DECLARE_STATIC_KEY_MAYBE(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
	11	randomize_kstack_offset);
	12	DECLARE_PER_CPU(u32, kstack_offset);
	13
	14	/*
	15	* Do not use this anywhere else in the kernel. This is used here because
	16	* it provides an arch-agnostic way to grow the stack with correct
	17	* alignment. Also, since this use is being explicitly masked to a max of
	18	* 10 bits, stack-clash style attacks are unlikely. For more details see
	19	* "VLAs" in Documentation/process/deprecated.rst
efa90c11 ME	20	*
	21	* The normal __builtin_alloca() is initialized with INIT_STACK_ALL (currently
	22	* only with Clang and not GCC). Initializing the unused area on each syscall
	23	* entry is expensive, and generating an implicit call to memset() may also be
	24	* problematic (such as in noinstr functions). Therefore, if the compiler
	25	* supports it (which it should if it initializes allocas), always use the
	26	* "uninitialized" variant of the builtin.
39218ff4	27	*/
efa90c11 ME	28	#if __has_builtin(__builtin_alloca_uninitialized)
	29	#define __kstack_alloca __builtin_alloca_uninitialized
	30	#else
	31	#define __kstack_alloca __builtin_alloca
	32	#endif
	33
39218ff4 KC	34	/*
	35	* Use, at most, 10 bits of entropy. We explicitly cap this to keep the
	36	* "VLA" from being unbounded (see above). 10 bits leaves enough room for
	37	* per-arch offset masks to reduce entropy (by removing higher bits, since
	38	* high entropy may overly constrain usable stack space), and for
	39	* compiler/arch-specific stack alignment to remove the lower bits.
	40	*/
	41	#define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF)
	42
	43	/*
	44	* These macros must be used during syscall entry when interrupts and
	45	* preempt are disabled, and after user registers have been stored to
	46	* the stack.
	47	*/
	48	#define add_random_kstack_offset() do { \
	49	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
	50	&randomize_kstack_offset)) { \
	51	u32 offset = raw_cpu_read(kstack_offset); \
efa90c11	52	u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \
39218ff4	53	/* Keep allocation even after "ptr" loses scope. */ \
2515dd6c	54	asm volatile("" :: "r"(ptr) : "memory"); \
39218ff4 KC	55	} \
	56	} while (0)
	57
	58	#define choose_random_kstack_offset(rand) do { \
	59	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
	60	&randomize_kstack_offset)) { \
	61	u32 offset = raw_cpu_read(kstack_offset); \
	62	offset ^= (rand); \
	63	raw_cpu_write(kstack_offset, offset); \
	64	} \
	65	} while (0)
8cb37a59 ME	66	#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
	67	#define add_random_kstack_offset() do { } while (0)
	68	#define choose_random_kstack_offset(rand) do { } while (0)
	69	#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
39218ff4 KC	70
39218ff4 KC	71	#endif