diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 04545725f187..bee8644a192e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4061,6 +4061,17 @@ fully seed the kernel's CRNG. Default is controlled by CONFIG_RANDOM_TRUST_CPU. + randomize_kstack_offset= + [KNL] Enable or disable kernel stack offset + randomization, which provides roughly 5 bits of + entropy, frustrating memory corruption attacks + that depend on stack address determinism or + cross-syscall address exposures. This is only + available on architectures that have defined + CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. + Format: (1/Y/y=enable, 0/N/n=disable) + Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. + ras=option[,option,...] [KNL] RAS-specific options cec_disable [X86] diff --git a/Makefile b/Makefile index cc77fd45ca64..d3bf50326d69 100644 --- a/Makefile +++ b/Makefile @@ -813,6 +813,10 @@ KBUILD_CFLAGS += -ftrivial-auto-var-init=zero KBUILD_CFLAGS += -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang endif +# While VLAs have been removed, GCC produces unreachable stack probes +# for the randomize_kstack_offset feature. Disable it for all compilers. +KBUILD_CFLAGS += $(call cc-option, -fno-stack-clash-protection) + DEBUG_CFLAGS := # Workaround for GCC versions < 5.0 diff --git a/arch/Kconfig b/arch/Kconfig index ecfd3520b676..6b11c825fc36 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1054,6 +1054,29 @@ config VMAP_STACK backing virtual mappings with real shadow memory, and KASAN_VMALLOC must be enabled. +config HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET + def_bool n + help + An arch should select this symbol if it can support kernel stack + offset randomization with calls to add_random_kstack_offset() + during syscall entry and choose_random_kstack_offset() during + syscall exit. Careful removal of -fstack-protector-strong and + -fstack-protector should also be applied to the entry code and + closely examined, as the artificial stack bump looks like an array + to the compiler, so it will attempt to add canary checks regardless + of the static branch state. + +config RANDOMIZE_KSTACK_OFFSET_DEFAULT + bool "Randomize kernel stack offset on syscall entry" + depends on HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET + help + The kernel stack offset can be randomized (after pt_regs) by + roughly 5 bits of entropy, frustrating memory corruption + attacks that depend on stack address determinism or + cross-syscall address exposures. This feature is controlled + by kernel boot param "randomize_kstack_offset=on/off", and this + config chooses the default boot state. + config ARCH_OPTIONAL_KERNEL_RWX def_bool n diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h new file mode 100644 index 000000000000..fd80fab663a9 --- /dev/null +++ b/include/linux/randomize_kstack.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_RANDOMIZE_KSTACK_H +#define _LINUX_RANDOMIZE_KSTACK_H + +#include +#include +#include + +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 + */ +void *__builtin_alloca(size_t size); +/* + * 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 = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ + /* Keep allocation even after "ptr" loses scope. */ \ + asm volatile("" : "=o"(*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) + +#endif diff --git a/init/main.c b/init/main.c index 53b278845b88..f498aac26e8c 100644 --- a/init/main.c +++ b/init/main.c @@ -844,6 +844,29 @@ static void __init mm_init(void) pti_init(); } +#ifdef CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET +DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, + randomize_kstack_offset); +DEFINE_PER_CPU(u32, kstack_offset); + +static int __init early_randomize_kstack_offset(char *buf) +{ + int ret; + bool bool_result; + + ret = kstrtobool(buf, &bool_result); + if (ret) + return ret; + + if (bool_result) + static_branch_enable(&randomize_kstack_offset); + else + static_branch_disable(&randomize_kstack_offset); + return 0; +} +early_param("randomize_kstack_offset", early_randomize_kstack_offset); +#endif + void __init __weak arch_call_rest_init(void) { rest_init();