arm64: Implement Shadow Call Stack

This change implements shadow stack switching, initial SCS set-up,
and interrupt shadow stacks for arm64.
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/Kconfig

@@ -64,6 +64,7 @@ config ARM64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	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
@@ -1025,6 +1026,10 @@ 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---

arch/arm64/include/asm/scs.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+	.macro scs_load tsk, tmp
+	ldp	x18, \tmp, [\tsk, #TSK_TI_SCS_BASE]
+	add	x18, x18, \tmp
+	.endm
+
+	.macro scs_save tsk, tmp
+	ldr	\tmp, [\tsk, #TSK_TI_SCS_BASE]
+	sub	\tmp, x18, \tmp
+	str	\tmp, [\tsk, #TSK_TI_SCS_OFFSET]
+	.endm
+#else
+	.macro scs_load tsk, tmp
+	.endm
+
+	.macro scs_save tsk, tmp
+	.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#else /* __ASSEMBLY__ */
+
+#include <linux/scs.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+static inline void scs_overflow_check(struct task_struct *tsk)
+{
+	if (unlikely(scs_corrupted(tsk)))
+		panic("corrupted shadow stack detected inside scheduler\n");
+}
+
+#else /* CONFIG_SHADOW_CALL_STACK */
+
+static inline void scs_overflow_check(struct task_struct *tsk) {}
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#endif /* __ASSEMBLY __ */
+
+#endif /* _ASM_SCS_H */

arch/arm64/include/asm/thread_info.h

@@ -41,6 +41,10 @@ struct thread_info {
 #endif
 		} preempt;
 	};
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*scs_base;
+	unsigned long		scs_offset;
+#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_offset	= 0,
+#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 */

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/

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_OFFSET,	offsetof(struct task_struct, thread_info.scs_offset));
 #endif
   DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
 #ifdef CONFIG_STACKPROTECTOR

arch/arm64/kernel/entry.S

@@ -23,6 +23,7 @@
 #include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
+#include <asm/scs.h>
 #include <asm/thread_info.h>
 #include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
@@ -179,6 +180,8 @@ alternative_cb_end
 	apply_ssbd 1, x22, x23
 
 	ptrauth_keys_install_kernel tsk, 1, 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, x18		// 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 x18, 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	x18, x24
+#endif
 	.endm
 
 /* GPRs used by entry code */
@@ -901,6 +919,8 @@ SYM_FUNC_START(cpu_switch_to)
 	mov	sp, x9
 	msr	sp_el0, x1
 	ptrauth_keys_install_kernel x1, 1, x8, x9, x10
+	scs_save x0, x8
+	scs_load x1, x8
 	ret
 SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)

arch/arm64/kernel/head.S

@@ -27,6 +27,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/scs.h>
 #include <asm/smp.h>
 #include <asm/sysreg.h>
 #include <asm/thread_info.h>
@@ -424,6 +425,10 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	stp	xzr, x30, [sp, #-16]!
 	mov	x29, sp
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+	adr_l	x18, 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
@@ -737,6 +742,7 @@ 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
 	b	secondary_start_kernel

arch/arm64/kernel/process.c

@@ -52,6 +52,7 @@
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/pointer_auth.h>
+#include <asm/scs.h>
 #include <asm/stacktrace.h>
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
@@ -515,6 +516,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	entry_task_switch(next);
 	uao_thread_switch(next);
 	ssbs_thread_switch(next);
+	scs_overflow_check(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case

arch/arm64/kernel/scs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#include <linux/percpu.h>
+#include <asm/scs.h>
+
+/* Allocate a static per-CPU shadow stack */
+#define DEFINE_SCS(name)						\
+	DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name)	\
+
+DEFINE_SCS(irq_shadow_call_stack);