[PATCH v6 14/15] arm64: implement Shadow Call Stack

[Sami Tolvanen <samitolvanen@google.com>]

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>
---
 arch/arm64/Kconfig                   |  5 ++++
 arch/arm64/include/asm/scs.h         | 37 +++++++++++++++++++++++++
 arch/arm64/include/asm/thread_info.h |  3 +++
 arch/arm64/kernel/Makefile           |  1 +
 arch/arm64/kernel/asm-offsets.c      |  3 +++
 arch/arm64/kernel/entry.S            | 31 +++++++++++++++++++--
 arch/arm64/kernel/head.S             |  9 +++++++
 arch/arm64/kernel/irq.c              |  2 ++
 arch/arm64/kernel/process.c          |  2 ++
 arch/arm64/kernel/scs.c              | 40 ++++++++++++++++++++++++++++
 arch/arm64/kernel/smp.c              |  4 +++
 11 files changed, 135 insertions(+), 2 deletions(-)
 create mode 100644 arch/arm64/include/asm/scs.h
 create mode 100644 arch/arm64/kernel/scs.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 49e5f94ff4af..073b19db23f2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -65,6 +65,7 @@ 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
@@ -994,6 +995,10 @@ 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/include/asm/scs.h b/arch/arm64/include/asm/scs.h
new file mode 100644
index 000000000000..c50d2b0c6c5f
--- /dev/null
+++ b/arch/arm64/include/asm/scs.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/scs.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+extern void scs_init_irq(void);
+
+static __always_inline void scs_save(struct task_struct *tsk)
+{
+	void *s;
+
+	asm volatile("mov %0, x18" : "=r" (s));
+	task_set_scs(tsk, s);
+}
+
+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_init_irq(void) {}
+static inline void scs_save(struct task_struct *tsk) {}
+static inline void scs_overflow_check(struct task_struct *tsk) {}
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#endif /* __ASSEMBLY __ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index f0cec4160136..8c73764b9ed2 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -41,6 +41,9 @@ struct thread_info {
 #endif
 		} preempt;
 	};
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*shadow_call_stack;
+#endif
 };
 
 #define thread_saved_pc(tsk)	\
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index fc6488660f64..08fafc4da2cf 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 a5bdce8af65b..d485dc5cd196 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -33,6 +33,9 @@ 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,		offsetof(struct task_struct, thread_info.shadow_call_stack));
 #endif
   DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 583f71abbe98..7aa2d366b2df 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -172,6 +172,10 @@ alternative_cb_end
 
 	apply_ssbd 1, x22, x23
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+	ldr	x18, [tsk, #TSK_TI_SCS]		// Restore shadow call stack
+	str	xzr, [tsk, #TSK_TI_SCS]		// Limit visibility of saved SCS
+#endif
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_current_task tsk
@@ -280,6 +284,12 @@ alternative_else_nop_endif
 	ct_user_enter
 	.endif
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+	.if	\el == 0
+	str	x18, [tsk, #TSK_TI_SCS]		// Save shadow call stack
+	.endif
+#endif
+
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
@@ -385,6 +395,9 @@ 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	x20, x18		// preserve the original shadow stack
+#endif
 
 	/*
 	 * Compare sp with the base of the task stack.
@@ -402,15 +415,24 @@ 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 */
+	ldr_this_cpu x18, irq_shadow_call_stack_ptr, 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.
 	 */
 	.macro	irq_stack_exit
 	mov	sp, x19
+#ifdef CONFIG_SHADOW_CALL_STACK
+	mov	x18, x20
+#endif
 	.endm
 
 /* GPRs used by entry code */
@@ -894,6 +916,11 @@ ENTRY(cpu_switch_to)
 	ldr	lr, [x8]
 	mov	sp, x9
 	msr	sp_el0, x1
+#ifdef CONFIG_SHADOW_CALL_STACK
+	str	x18, [x0, #TSK_TI_SCS]
+	ldr	x18, [x1, #TSK_TI_SCS]
+	str	xzr, [x1, #TSK_TI_SCS]		// limit visibility of saved SCS
+#endif
 	ret
 ENDPROC(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 989b1944cb71..ca561de903d4 100644
--- a/arch/arm64/kernel/head.S
+++ b/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 @@ __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
@@ -731,6 +736,10 @@ __secondary_switched:
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
+#ifdef CONFIG_SHADOW_CALL_STACK
+	ldr	x18, [x2, #TSK_TI_SCS]		// set shadow call stack
+	str	xzr, [x2, #TSK_TI_SCS]		// limit visibility of saved SCS
+#endif
 	mov	x29, #0
 	mov	x30, #0
 	b	secondary_start_kernel
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 04a327ccf84d..fe0ca522ff60 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -21,6 +21,7 @@
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/vmap_stack.h>
+#include <asm/scs.h>
 
 unsigned long irq_err_count;
 
@@ -63,6 +64,7 @@ static void init_irq_stacks(void)
 void __init init_IRQ(void)
 {
 	init_irq_stacks();
+	scs_init_irq();
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 71f788cd2b18..5f0aec285848 100644
--- a/arch/arm64/kernel/process.c
+++ b/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)
@@ -507,6 +508,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	uao_thread_switch(next);
 	ptrauth_thread_switch(next);
 	ssbs_thread_switch(next);
+	scs_overflow_check(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
diff --git a/arch/arm64/kernel/scs.c b/arch/arm64/kernel/scs.c
new file mode 100644
index 000000000000..eaadf5430baa
--- /dev/null
+++ b/arch/arm64/kernel/scs.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#include <linux/percpu.h>
+#include <linux/vmalloc.h>
+#include <asm/pgtable.h>
+#include <asm/scs.h>
+
+DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr);
+
+#ifndef CONFIG_SHADOW_CALL_STACK_VMAP
+DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], irq_shadow_call_stack)
+	__aligned(SCS_SIZE);
+#endif
+
+void scs_init_irq(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+#ifdef CONFIG_SHADOW_CALL_STACK_VMAP
+		unsigned long *p;
+
+		p = __vmalloc_node_range(PAGE_SIZE, SCS_SIZE,
+					 VMALLOC_START, VMALLOC_END,
+					 GFP_SCS, PAGE_KERNEL,
+					 0, cpu_to_node(cpu),
+					 __builtin_return_address(0));
+
+		per_cpu(irq_shadow_call_stack_ptr, cpu) = p;
+#else
+		per_cpu(irq_shadow_call_stack_ptr, cpu) =
+			per_cpu(irq_shadow_call_stack, cpu);
+#endif /* CONFIG_SHADOW_CALL_STACK_VMAP */
+	}
+}
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ab149bcc3dc7..416cf4da6f0c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -44,6 +44,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
+#include <asm/scs.h>
 #include <asm/smp_plat.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -356,6 +357,9 @@ void cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
 
+	/* Save the shadow stack pointer before exiting the idle task */
+	scs_save(current);
+
 	idle_task_exit();
 
 	local_daif_mask();
-- 
2.24.0.393.g34dc348eaf-goog