diff --git a/Makefile b/Makefile index 679f302a8b8b..33dc0d0cdd08 100644 --- a/Makefile +++ b/Makefile @@ -866,6 +866,12 @@ ifdef CONFIG_LIVEPATCH KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone) endif +ifdef CONFIG_SHADOW_CALL_STACK +CC_FLAGS_SCS := -fsanitize=shadow-call-stack +KBUILD_CFLAGS += $(CC_FLAGS_SCS) +export CC_FLAGS_SCS +endif + # arch Makefile may override CC so keep this after arch Makefile is included NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/Kconfig b/arch/Kconfig index 786a85d4ad40..2e6f843d87c4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -533,6 +533,31 @@ config STACKPROTECTOR_STRONG about 20% of all kernel functions, which increases the kernel code size by about 2%. +config ARCH_SUPPORTS_SHADOW_CALL_STACK + bool + help + An architecture should select this if it supports Clang's Shadow + Call Stack and implements runtime support for shadow stack + switching. + +config SHADOW_CALL_STACK + bool "Clang Shadow Call Stack" + depends on CC_IS_CLANG && ARCH_SUPPORTS_SHADOW_CALL_STACK + depends on DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER + help + This option enables Clang's Shadow Call Stack, which uses a + shadow stack to protect function return addresses from being + overwritten by an attacker. More information can be found in + Clang's documentation: + + https://clang.llvm.org/docs/ShadowCallStack.html + + Note that security guarantees in the kernel differ from the + ones documented for user space. The kernel must store addresses + of shadow stacks in memory, which means an attacker capable of + reading and writing arbitrary memory may be able to locate them + and hijack control flow by modifying the stacks. + config HAVE_ARCH_WITHIN_STACK_FRAMES bool help diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 999ddaefef1e..77c440db9d46 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -68,6 +68,7 @@ config ARM64 select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_SYM_ANNOTATIONS select ARCH_SUPPORTS_MEMORY_FAILURE + select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG) select ARCH_SUPPORTS_NUMA_BALANCING @@ -1026,6 +1027,10 @@ config ARCH_HAS_CACHE_LINE_SIZE config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y if PGTABLE_LEVELS > 2 +# Supported by clang >= 7.0 +config CC_HAVE_SHADOW_CALL_STACK + def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18) + config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" ---help--- diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7dcd38be7dd0..650e1185c190 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -87,6 +87,10 @@ endif KBUILD_CFLAGS += $(branch-prot-flags-y) +ifeq ($(CONFIG_SHADOW_CALL_STACK), y) +KBUILD_CFLAGS += -ffixed-x18 +endif + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index dcb63bf94105..015883671ec3 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -12,7 +12,7 @@ #include #include -#define __hyp_text __section(.hyp.text) notrace +#define __hyp_text __section(.hyp.text) notrace __noscs #define read_sysreg_elx(r,nvh,vh) \ ({ \ diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h new file mode 100644 index 000000000000..eaa2cd92e4c1 --- /dev/null +++ b/arch/arm64/include/asm/scs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_SCS_H +#define _ASM_SCS_H + +#ifdef __ASSEMBLY__ + +#include + +#ifdef CONFIG_SHADOW_CALL_STACK + scs_sp .req x18 + + .macro scs_load tsk, tmp + ldr scs_sp, [\tsk, #TSK_TI_SCS_SP] + .endm + + .macro scs_save tsk, tmp + str scs_sp, [\tsk, #TSK_TI_SCS_SP] + .endm +#else + .macro scs_load tsk, tmp + .endm + + .macro scs_save tsk, tmp + .endm +#endif /* CONFIG_SHADOW_CALL_STACK */ + +#endif /* __ASSEMBLY __ */ + +#endif /* _ASM_SCS_H */ diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index 8939c87c4dce..0cde2f473971 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -2,7 +2,7 @@ #ifndef __ASM_SUSPEND_H #define __ASM_SUSPEND_H -#define NR_CTX_REGS 12 +#define NR_CTX_REGS 13 #define NR_CALLEE_SAVED_REGS 12 /* diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 512174a8e789..6ea8b6a26ae9 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -41,6 +41,10 @@ struct thread_info { #endif } preempt; }; +#ifdef CONFIG_SHADOW_CALL_STACK + void *scs_base; + void *scs_sp; +#endif }; #define thread_saved_pc(tsk) \ @@ -100,11 +104,20 @@ void arch_release_task_struct(struct task_struct *tsk); _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ _TIF_SYSCALL_EMU) +#ifdef CONFIG_SHADOW_CALL_STACK +#define INIT_SCS \ + .scs_base = init_shadow_call_stack, \ + .scs_sp = init_shadow_call_stack, +#else +#define INIT_SCS +#endif + #define INIT_THREAD_INFO(tsk) \ { \ .flags = _TIF_FOREIGN_FPSTATE, \ .preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ + INIT_SCS \ } #endif /* __ASM_THREAD_INFO_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 4e5b8ee31442..151f28521f1e 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o obj-$(CONFIG_ARM64_SSBD) += ssbd.o obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o +obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-y += vdso/ probes/ obj-$(CONFIG_COMPAT_VDSO) += vdso32/ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 890ddd67b8bf..3539d7092612 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -33,6 +33,10 @@ int main(void) DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); #ifdef CONFIG_ARM64_SW_TTBR0_PAN DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); +#endif +#ifdef CONFIG_SHADOW_CALL_STACK + DEFINE(TSK_TI_SCS_BASE, offsetof(struct task_struct, thread_info.scs_base)); + DEFINE(TSK_TI_SCS_SP, offsetof(struct task_struct, thread_info.scs_sp)); #endif DEFINE(TSK_STACK, offsetof(struct task_struct, stack)); #ifdef CONFIG_STACKPROTECTOR diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 1192c4bb48df..75691a2641c1 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -34,5 +34,14 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) ldp x29, x30, [sp], #32 b.ne 0f ret -0: b efi_handle_corrupted_x18 // tail call +0: + /* + * With CONFIG_SHADOW_CALL_STACK, the kernel uses x18 to store a + * shadow stack pointer, which we need to restore before returning to + * potentially instrumented code. This is safe because the wrapper is + * called with preemption disabled and a separate shadow stack is used + * for interrupts. + */ + mov x18, x2 + b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 833d48c9acb5..a338f40e64d3 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -23,8 +23,9 @@ * * ... where is either ftrace_caller or ftrace_regs_caller. * - * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are - * live, and x9-x18 are safe to clobber. + * Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are + * live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to + * clobber. * * We save the callsite's context into a pt_regs before invoking any ftrace * callbacks. So that we can get a sensible backtrace, we create a stack record diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 84cbc513c1e8..5304d193c79d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -179,6 +180,8 @@ alternative_cb_end apply_ssbd 1, x22, x23 ptrauth_keys_install_kernel tsk, x20, x22, x23 + + scs_load tsk, x20 .else add x21, sp, #S_FRAME_SIZE get_current_task tsk @@ -343,6 +346,8 @@ alternative_else_nop_endif msr cntkctl_el1, x1 4: #endif + scs_save tsk, x0 + /* No kernel C function calls after this as user keys are set. */ ptrauth_keys_install_user tsk, x0, x1, x2 @@ -388,6 +393,9 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 .macro irq_stack_entry mov x19, sp // preserve the original sp +#ifdef CONFIG_SHADOW_CALL_STACK + mov x24, scs_sp // preserve the original shadow stack +#endif /* * Compare sp with the base of the task stack. @@ -405,15 +413,25 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 /* switch to the irq stack */ mov sp, x26 + +#ifdef CONFIG_SHADOW_CALL_STACK + /* also switch to the irq shadow stack */ + adr_this_cpu scs_sp, irq_shadow_call_stack, x26 +#endif + 9998: .endm /* - * x19 should be preserved between irq_stack_entry and - * irq_stack_exit. + * The callee-saved regs (x19-x29) should be preserved between + * irq_stack_entry and irq_stack_exit, but note that kernel_entry + * uses x20-x23 to store data for later use. */ .macro irq_stack_exit mov sp, x19 +#ifdef CONFIG_SHADOW_CALL_STACK + mov scs_sp, x24 +#endif .endm /* GPRs used by entry code */ @@ -902,6 +920,8 @@ SYM_FUNC_START(cpu_switch_to) mov sp, x9 msr sp_el0, x1 ptrauth_keys_install_kernel x1, x8, x9, x10 + scs_save x0, x8 + scs_load x1, x8 ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) @@ -1030,13 +1050,16 @@ SYM_CODE_START(__sdei_asm_handler) mov x19, x1 +#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK) + ldrb w4, [x19, #SDEI_EVENT_PRIORITY] +#endif + #ifdef CONFIG_VMAP_STACK /* * entry.S may have been using sp as a scratch register, find whether * this is a normal or critical event and switch to the appropriate * stack for this CPU. */ - ldrb w4, [x19, #SDEI_EVENT_PRIORITY] cbnz w4, 1f ldr_this_cpu dst=x5, sym=sdei_stack_normal_ptr, tmp=x6 b 2f @@ -1046,6 +1069,15 @@ SYM_CODE_START(__sdei_asm_handler) mov sp, x5 #endif +#ifdef CONFIG_SHADOW_CALL_STACK + /* Use a separate shadow call stack for normal and critical events */ + cbnz w4, 3f + adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal, tmp=x6 + b 4f +3: adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical, tmp=x6 +4: +#endif + /* * We may have interrupted userspace, or a guest, or exit-from or * return-to either of these. We can't trust sp_el0, restore it. diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 340d60d2e218..632702146813 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -433,6 +434,10 @@ SYM_FUNC_START_LOCAL(__primary_switched) stp xzr, x30, [sp, #-16]! mov x29, sp +#ifdef CONFIG_SHADOW_CALL_STACK + adr_l scs_sp, init_shadow_call_stack // Set shadow call stack +#endif + str_l x21, __fdt_pointer, x5 // Save FDT pointer ldr_l x4, kimage_vaddr // Save the offset between @@ -745,6 +750,7 @@ SYM_FUNC_START_LOCAL(__secondary_switched) ldr x2, [x0, #CPU_BOOT_TASK] cbz x2, __secondary_too_slow msr sp_el0, x2 + scs_load x2, x3 mov x29, #0 mov x30, #0 diff --git a/arch/arm64/kernel/scs.c b/arch/arm64/kernel/scs.c new file mode 100644 index 000000000000..e8f7ff45dd8f --- /dev/null +++ b/arch/arm64/kernel/scs.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shadow Call Stack support. + * + * Copyright (C) 2019 Google LLC + */ + +#include +#include + +DEFINE_SCS(irq_shadow_call_stack); + +#ifdef CONFIG_ARM_SDE_INTERFACE +DEFINE_SCS(sdei_shadow_call_stack_normal); +DEFINE_SCS(sdei_shadow_call_stack_critical); +#endif diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index fccd67d07c8c..1a83a7162a2d 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -29,7 +29,7 @@ ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 7d3bf1afba0c..b7bebb12a56d 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -58,6 +58,8 @@ * cpu_do_suspend - save CPU registers context * * x0: virtual address of context pointer + * + * This must be kept in sync with struct cpu_suspend_ctx in . */ SYM_FUNC_START(cpu_do_suspend) mrs x2, tpidr_el0 @@ -82,6 +84,11 @@ alternative_endif stp x8, x9, [x0, #48] stp x10, x11, [x0, #64] stp x12, x13, [x0, #80] + /* + * Save x18 as it may be used as a platform register, e.g. by shadow + * call stack. + */ + str x18, [x0, #96] ret SYM_FUNC_END(cpu_do_suspend) @@ -98,6 +105,13 @@ SYM_FUNC_START(cpu_do_resume) ldp x9, x10, [x0, #48] ldp x11, x12, [x0, #64] ldp x13, x14, [x0, #80] + /* + * Restore x18, as it may be used as a platform register, and clear + * the buffer to minimize the risk of exposure when used for shadow + * call stack. + */ + ldr x18, [x0, #96] + str xzr, [x0, #96] msr tpidr_el0, x2 msr tpidrro_el0, x3 msr contextidr_el1, x4 diff --git a/drivers/base/node.c b/drivers/base/node.c index 10d7e818e118..50b8c0d43859 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -415,6 +415,9 @@ static ssize_t node_read_meminfo(struct device *dev, "Node %d AnonPages: %8lu kB\n" "Node %d Shmem: %8lu kB\n" "Node %d KernelStack: %8lu kB\n" +#ifdef CONFIG_SHADOW_CALL_STACK + "Node %d ShadowCallStack:%8lu kB\n" +#endif "Node %d PageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" @@ -438,6 +441,9 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_ANON_MAPPED)), nid, K(i.sharedram), nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB), +#ifdef CONFIG_SHADOW_CALL_STACK + nid, sum_zone_node_page_state(nid, NR_KERNEL_SCS_KB), +#endif nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)), nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)), nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)), diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 094eabdecfe6..b52ae8c29560 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -32,6 +32,9 @@ KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ $(call cc-option,-fno-stack-protector) \ -D__DISABLE_EXPORTS +# remove SCS flags from all objects in this directory +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) + GCOV_PROFILE := n KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 8c1f1bb1a5ce..09cd51c8d23d 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -103,6 +103,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SUnreclaim: ", sunreclaim); seq_printf(m, "KernelStack: %8lu kB\n", global_zone_page_state(NR_KERNEL_STACK_KB)); +#ifdef CONFIG_SHADOW_CALL_STACK + seq_printf(m, "ShadowCallStack:%8lu kB\n", + global_zone_page_state(NR_KERNEL_SCS_KB)); +#endif show_val_kb(m, "PageTables: ", global_zone_page_state(NR_PAGETABLE)); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 333a6695a918..790c0c6b8552 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -42,3 +42,7 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") + +#if __has_feature(shadow_call_stack) +# define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..97b62f47a80d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -193,6 +193,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef __noscs +# define __noscs +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..acffc3bc6178 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -156,6 +156,9 @@ enum zone_stat_item { NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + NR_KERNEL_SCS_KB, /* measured in KiB */ +#endif /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) diff --git a/include/linux/scs.h b/include/linux/scs.h new file mode 100644 index 000000000000..6dec390cf154 --- /dev/null +++ b/include/linux/scs.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shadow Call Stack support. + * + * Copyright (C) 2019 Google LLC + */ + +#ifndef _LINUX_SCS_H +#define _LINUX_SCS_H + +#include +#include +#include +#include + +#ifdef CONFIG_SHADOW_CALL_STACK + +/* + * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit + * architecture) provided ~40% safety margin on stack usage while keeping + * memory allocation overhead reasonable. + */ +#define SCS_SIZE SZ_1K +#define GFP_SCS (GFP_KERNEL | __GFP_ZERO) + +/* An illegal pointer value to mark the end of the shadow stack. */ +#define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) + +/* Allocate a static per-CPU shadow stack */ +#define DEFINE_SCS(name) \ + DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name) \ + +#define task_scs(tsk) (task_thread_info(tsk)->scs_base) +#define task_scs_sp(tsk) (task_thread_info(tsk)->scs_sp) + +void scs_init(void); +int scs_prepare(struct task_struct *tsk, int node); +void scs_release(struct task_struct *tsk); + +static inline void scs_task_reset(struct task_struct *tsk) +{ + /* + * Reset the shadow stack to the base address in case the task + * is reused. + */ + task_scs_sp(tsk) = task_scs(tsk); +} + +static inline unsigned long *__scs_magic(void *s) +{ + return (unsigned long *)(s + SCS_SIZE) - 1; +} + +static inline bool task_scs_end_corrupted(struct task_struct *tsk) +{ + unsigned long *magic = __scs_magic(task_scs(tsk)); + unsigned long sz = task_scs_sp(tsk) - task_scs(tsk); + + return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC; +} + +#else /* CONFIG_SHADOW_CALL_STACK */ + +static inline void scs_init(void) {} +static inline void scs_task_reset(struct task_struct *tsk) {} +static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } +static inline void scs_release(struct task_struct *tsk) {} +static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; } + +#endif /* CONFIG_SHADOW_CALL_STACK */ + +#endif /* _LINUX_SCS_H */ diff --git a/init/init_task.c b/init/init_task.c index bd403ed3e418..169e34066d35 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -50,6 +51,13 @@ static struct sighand_struct init_sighand = { .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), }; +#ifdef CONFIG_SHADOW_CALL_STACK +unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] + __init_task_data = { + [(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC +}; +#endif + /* * Set up the first task table, touch at your own risk!. Base=0, * limit=0x1fffff (=2MB) diff --git a/kernel/Makefile b/kernel/Makefile index 4cb4130ced32..c332eb9d4841 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ +obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/fork.c b/kernel/fork.c index 8c700f881d92..f6339f9d232d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -94,6 +94,7 @@ #include #include #include +#include #include #include @@ -456,6 +457,8 @@ void put_task_stack(struct task_struct *tsk) void free_task(struct task_struct *tsk) { + scs_release(tsk); + #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, @@ -840,6 +843,8 @@ void __init fork_init(void) NULL, free_vm_stack_cache); #endif + scs_init(); + lockdep_init_task(&init_task); uprobes_init(); } @@ -899,6 +904,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (err) goto free_stack; + err = scs_prepare(tsk, node); + if (err) + goto free_stack; + #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9a2fbf98fd6f..a1d815a11b90 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -3877,6 +3878,9 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) #ifdef CONFIG_SCHED_STACK_END_CHECK if (task_stack_end_corrupted(prev)) panic("corrupted stack end detected inside scheduler\n"); + + if (task_scs_end_corrupted(prev)) + panic("corrupted shadow stack detected inside scheduler\n"); #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -6040,6 +6044,7 @@ void init_idle(struct task_struct *idle, int cpu) idle->se.exec_start = sched_clock(); idle->flags |= PF_IDLE; + scs_task_reset(idle); kasan_unpoison_task_stack(idle); #ifdef CONFIG_SMP diff --git a/kernel/scs.c b/kernel/scs.c new file mode 100644 index 000000000000..222a7a9ad543 --- /dev/null +++ b/kernel/scs.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shadow Call Stack support. + * + * Copyright (C) 2019 Google LLC + */ + +#include +#include +#include +#include +#include + +static struct kmem_cache *scs_cache; + +static void __scs_account(void *s, int account) +{ + struct page *scs_page = virt_to_page(s); + + mod_zone_page_state(page_zone(scs_page), NR_KERNEL_SCS_KB, + account * (SCS_SIZE / SZ_1K)); +} + +static void *scs_alloc(int node) +{ + void *s = kmem_cache_alloc_node(scs_cache, GFP_SCS, node); + + if (!s) + return NULL; + + *__scs_magic(s) = SCS_END_MAGIC; + + /* + * Poison the allocation to catch unintentional accesses to + * the shadow stack when KASAN is enabled. + */ + kasan_poison_object_data(scs_cache, s); + __scs_account(s, 1); + return s; +} + +static void scs_free(void *s) +{ + __scs_account(s, -1); + kasan_unpoison_object_data(scs_cache, s); + kmem_cache_free(scs_cache, s); +} + +void __init scs_init(void) +{ + scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, 0, 0, NULL); +} + +int scs_prepare(struct task_struct *tsk, int node) +{ + void *s = scs_alloc(node); + + if (!s) + return -ENOMEM; + + task_scs(tsk) = task_scs_sp(tsk) = s; + return 0; +} + +static void scs_check_usage(struct task_struct *tsk) +{ + static unsigned long highest; + + unsigned long *p, prev, curr = highest, used = 0; + + if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE)) + return; + + for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) { + if (!READ_ONCE_NOCHECK(*p)) + break; + used++; + } + + while (used > curr) { + prev = cmpxchg_relaxed(&highest, curr, used); + + if (prev == curr) { + pr_info("%s (%d): highest shadow stack usage: %lu bytes\n", + tsk->comm, task_pid_nr(tsk), used); + break; + } + + curr = prev; + } +} + +void scs_release(struct task_struct *tsk) +{ + void *s = task_scs(tsk); + + if (!s) + return; + + WARN(task_scs_end_corrupted(tsk), + "corrupted shadow stack detected when freeing task\n"); + scs_check_usage(tsk); + scs_free(s); +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69827d4fa052..83743d7a6177 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5411,6 +5411,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " managed:%lukB" " mlocked:%lukB" " kernel_stack:%lukB" +#ifdef CONFIG_SHADOW_CALL_STACK + " shadow_call_stack:%lukB" +#endif " pagetables:%lukB" " bounce:%lukB" " free_pcp:%lukB" @@ -5433,6 +5436,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone_managed_pages(zone)), K(zone_page_state(zone, NR_MLOCK)), zone_page_state(zone, NR_KERNEL_STACK_KB), +#ifdef CONFIG_SHADOW_CALL_STACK + zone_page_state(zone, NR_KERNEL_SCS_KB), +#endif K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), diff --git a/mm/vmstat.c b/mm/vmstat.c index 96d21a792b57..2435d2c24657 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1119,6 +1119,9 @@ const char * const vmstat_text[] = { "nr_mlock", "nr_page_table_pages", "nr_kernel_stack", +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + "nr_shadow_call_stack", +#endif "nr_bounce", #if IS_ENABLED(CONFIG_ZSMALLOC) "nr_zspages",