Merge branch 'for-next/kprobes' into for-next/core

* kprobes:
  arm64: kprobes: Add KASAN instrumentation around stack accesses
  arm64: kprobes: Cleanup jprobe_return
  arm64: kprobes: Fix overflow when saving stack
  arm64: kprobes: WARN if attempting to step with PSTATE.D=1
  kprobes: Add arm64 case in kprobe example module
  arm64: Add kernel return probes support (kretprobes)
  arm64: Add trampoline code for kretprobes
  arm64: kprobes instruction simulation support
  arm64: Treat all entry code as non-kprobe-able
  arm64: Blacklist non-kprobe-able symbol
  arm64: Kprobes with single stepping support
  arm64: add conditional instruction simulation support
  arm64: Add more test functions to insn.c
  arm64: Add HAVE_REGS_AND_STACK_ACCESS_API feature

25 files changed, 1772 insertions, 9 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1b196bf99320..ac4746f454ed 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -86,8 +86,11 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES if HAVE_KPROBES
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 2fcb9b7c876c..4b6b3f72a215 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -66,6 +66,11 @@
 
 #define CACHE_FLUSH_IS_SAFE		1
 
+/* kprobes BRK opcodes with ESR encoding  */
+#define BRK64_ESR_MASK		0xFFFF
+#define BRK64_ESR_KPROBES	0x0004
+#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
 #define DBG_ESR_EVT_VECC	0x5
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 30e50eb54a67..1dbaa901d7e5 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -120,6 +120,29 @@ enum aarch64_insn_register {
 	AARCH64_INSN_REG_SP = 31  /* Stack pointer: as load/store base reg */
 };
 
+enum aarch64_insn_special_register {
+	AARCH64_INSN_SPCLREG_SPSR_EL1	= 0xC200,
+	AARCH64_INSN_SPCLREG_ELR_EL1	= 0xC201,
+	AARCH64_INSN_SPCLREG_SP_EL0	= 0xC208,
+	AARCH64_INSN_SPCLREG_SPSEL	= 0xC210,
+	AARCH64_INSN_SPCLREG_CURRENTEL	= 0xC212,
+	AARCH64_INSN_SPCLREG_DAIF	= 0xDA11,
+	AARCH64_INSN_SPCLREG_NZCV	= 0xDA10,
+	AARCH64_INSN_SPCLREG_FPCR	= 0xDA20,
+	AARCH64_INSN_SPCLREG_DSPSR_EL0	= 0xDA28,
+	AARCH64_INSN_SPCLREG_DLR_EL0	= 0xDA29,
+	AARCH64_INSN_SPCLREG_SPSR_EL2	= 0xE200,
+	AARCH64_INSN_SPCLREG_ELR_EL2	= 0xE201,
+	AARCH64_INSN_SPCLREG_SP_EL1	= 0xE208,
+	AARCH64_INSN_SPCLREG_SPSR_INQ	= 0xE218,
+	AARCH64_INSN_SPCLREG_SPSR_ABT	= 0xE219,
+	AARCH64_INSN_SPCLREG_SPSR_UND	= 0xE21A,
+	AARCH64_INSN_SPCLREG_SPSR_FIQ	= 0xE21B,
+	AARCH64_INSN_SPCLREG_SPSR_EL3	= 0xF200,
+	AARCH64_INSN_SPCLREG_ELR_EL3	= 0xF201,
+	AARCH64_INSN_SPCLREG_SP_EL2	= 0xF210
+};
+
 enum aarch64_insn_variant {
 	AARCH64_INSN_VARIANT_32BIT,
 	AARCH64_INSN_VARIANT_64BIT
@@ -223,8 +246,15 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 { return (val); }
 
+__AARCH64_INSN_FUNCS(adr_adrp,	0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
+__AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
+__AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
 __AARCH64_INSN_FUNCS(stp_post,	0x7FC00000, 0x28800000)
 __AARCH64_INSN_FUNCS(ldp_post,	0x7FC00000, 0x28C00000)
 __AARCH64_INSN_FUNCS(stp_pre,	0x7FC00000, 0x29800000)
@@ -273,10 +303,15 @@ __AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
 __AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
 __AARCH64_INSN_FUNCS(smc,	0xFFE0001F, 0xD4000003)
 __AARCH64_INSN_FUNCS(brk,	0xFFE0001F, 0xD4200000)
+__AARCH64_INSN_FUNCS(exception,	0xFF000000, 0xD4000000)
 __AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
 __AARCH64_INSN_FUNCS(br,	0xFFFFFC1F, 0xD61F0000)
 __AARCH64_INSN_FUNCS(blr,	0xFFFFFC1F, 0xD63F0000)
 __AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
+__AARCH64_INSN_FUNCS(eret,	0xFFFFFFFF, 0xD69F03E0)
+__AARCH64_INSN_FUNCS(mrs,	0xFFF00000, 0xD5300000)
+__AARCH64_INSN_FUNCS(msr_imm,	0xFFF8F01F, 0xD500401F)
+__AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
 
 #undef	__AARCH64_INSN_FUNCS
 
@@ -286,6 +321,8 @@ bool aarch64_insn_is_branch_imm(u32 insn);
 int aarch64_insn_read(void *addr, u32 *insnp);
 int aarch64_insn_write(void *addr, u32 insn);
 enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
+bool aarch64_insn_uses_literal(u32 insn);
+bool aarch64_insn_is_branch(u32 insn);
 u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
 u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 				  u32 insn, u64 imm);
@@ -367,9 +404,13 @@ bool aarch32_insn_is_wide(u32 insn);
 #define A32_RT_OFFSET	12
 #define A32_RT2_OFFSET	 0
 
+u32 aarch64_insn_extract_system_reg(u32 insn);
 u32 aarch32_insn_extract_reg_num(u32 insn, int offset);
 u32 aarch32_insn_mcr_extract_opc2(u32 insn);
 u32 aarch32_insn_mcr_extract_crm(u32 insn);
+
+typedef bool (pstate_check_t)(unsigned long);
+extern pstate_check_t * const aarch32_opcode_cond_checks[16];
 #endif /* __ASSEMBLY__ */
 
 #endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
new file mode 100644
index 000000000000..61b49150dfa3
--- /dev/null
+++ b/arch/arm64/include/asm/kprobes.h
@@ -0,0 +1,62 @@
+/*
+ * arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KPROBES_H
+#define _ARM_KPROBES_H
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			1
+#define MAX_STACK_SIZE			128
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+	unsigned long ss_pending;
+	unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_irqflag;
+	struct prev_kprobe prev_kprobe;
+	struct kprobe_step_ctx ss_ctx;
+	struct pt_regs jprobe_saved_regs;
+	char jprobes_stack[MAX_STACK_SIZE];
+};
+
+void arch_remove_kprobe(struct kprobe *);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
+int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
+void kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* _ARM_KPROBES_H */
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
new file mode 100644
index 000000000000..5af574d632fa
--- /dev/null
+++ b/arch/arm64/include/asm/probes.h
@@ -0,0 +1,35 @@
+/*
+ * arch/arm64/include/asm/probes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef _ARM_PROBES_H
+#define _ARM_PROBES_H
+
+#include <asm/opcodes.h>
+
+struct kprobe;
+struct arch_specific_insn;
+
+typedef u32 kprobe_opcode_t;
+typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_specific_insn {
+	kprobe_opcode_t *insn;
+	pstate_check_t *pstate_cc;
+	kprobes_handler_t *handler;
+	/* restore address after step xol */
+	unsigned long restore;
+};
+
+#endif
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 10e6f1d7269c..3fd15fdf4181 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -73,6 +73,7 @@
 #define COMPAT_PT_DATA_ADDR		0x10004
 #define COMPAT_PT_TEXT_END_ADDR		0x10008
 #ifndef __ASSEMBLY__
+#include <linux/bug.h>
 
 /* sizeof(struct user) for AArch32 */
 #define COMPAT_USER_SZ	296
@@ -118,6 +119,8 @@ struct pt_regs {
 	u64 syscallno;
 };
 
+#define MAX_REG_OFFSET offsetof(struct pt_regs, pstate)
+
 #define arch_has_single_step()	(1)
 
 #ifdef CONFIG_COMPAT
@@ -143,9 +146,59 @@ struct pt_regs {
 #define fast_interrupts_enabled(regs) \
 	(!((regs)->pstate & PSR_F_BIT))
 
-#define user_stack_pointer(regs) \
+#define GET_USP(regs) \
 	(!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
 
+#define SET_USP(ptregs, value) \
+	(!compat_user_mode(regs) ? ((regs)->sp = value) : ((regs)->compat_sp = value))
+
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	pt_regs from which register value is gotten
+ * @offset:	offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	u64 val = 0;
+
+	WARN_ON(offset & 7);
+
+	offset >>= 3;
+	switch (offset) {
+	case 0 ... 30:
+		val = regs->regs[offset];
+		break;
+	case offsetof(struct pt_regs, sp) >> 3:
+		val = regs->sp;
+		break;
+	case offsetof(struct pt_regs, pc) >> 3:
+		val = regs->pc;
+		break;
+	case offsetof(struct pt_regs, pstate) >> 3:
+		val = regs->pstate;
+		break;
+	default:
+		val = 0;
+	}
+
+	return val;
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
 	return regs->regs[0];
@@ -155,8 +208,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 struct task_struct;
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
 
-#define instruction_pointer(regs)	((unsigned long)(regs)->pc)
+#define GET_IP(regs)		((unsigned long)(regs)->pc)
+#define SET_IP(regs, value)	((regs)->pc = ((u64) (value)))
+
+#define GET_FP(ptregs)		((unsigned long)(ptregs)->regs[29])
+#define SET_FP(ptregs, value)	((ptregs)->regs[29] = ((u64) (value)))
+
+#include <asm-generic/ptrace.h>
 
+#undef profile_pc
 extern unsigned long profile_pc(struct pt_regs *regs);
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 9ef8ec681e30..0b9e49a92c47 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -26,8 +26,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o entry32.o		\
-					   ../../arm/kernel/opcodes.o
+					   sys_compat.o entry32.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
@@ -49,7 +48,7 @@ arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
 
-obj-y					+= $(arm64-obj-y) vdso/
+obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
 head-y					:= head.o
 extra-y					+= $(head-y) vmlinux.lds
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 2dc44406a7ad..78f368039c79 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -27,6 +27,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/arm-smccc.h>
+#include <linux/kprobes.h>
 
 #include <asm/checksum.h>
 
@@ -68,6 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
+NOKPROBE_SYMBOL(_mcount);
 #endif
 
 	/* arm-smccc */
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index fab5603f57ea..5f72475e2e3b 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -344,6 +344,21 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	return res;
 }
 
+#define	ARM_OPCODE_CONDITION_UNCOND	0xf
+
+static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)
+{
+	u32 cc_bits  = opcode >> 28;
+
+	if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
+		if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
+			return ARM_OPCODE_CONDTEST_PASS;
+		else
+			return ARM_OPCODE_CONDTEST_FAIL;
+	}
+	return ARM_OPCODE_CONDTEST_UNCOND;
+}
+
 /*
  * swp_handler logs the id of calling process, dissects the instruction, sanity
  * checks the memory location, calls emulate_swpX for the actual operation and
@@ -358,7 +373,7 @@ static int swp_handler(struct pt_regs *regs, u32 instr)
 
 	type = instr & TYPE_SWPB;
 
-	switch (arm_check_condition(instr, regs->pstate)) {
+	switch (aarch32_check_condition(instr, regs->pstate)) {
 	case ARM_OPCODE_CONDTEST_PASS:
 		break;
 	case ARM_OPCODE_CONDTEST_FAIL:
@@ -440,7 +455,7 @@ static int cp15barrier_handler(struct pt_regs *regs, u32 instr)
 {
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
 
-	switch (arm_check_condition(instr, regs->pstate)) {
+	switch (aarch32_check_condition(instr, regs->pstate)) {
 	case ARM_OPCODE_CONDTEST_PASS:
 		break;
 	case ARM_OPCODE_CONDTEST_FAIL:
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 334a1cd7a942..93ff5922debb 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -51,6 +51,17 @@ int main(void)
   DEFINE(S_X5,			offsetof(struct pt_regs, regs[5]));
   DEFINE(S_X6,			offsetof(struct pt_regs, regs[6]));
   DEFINE(S_X7,			offsetof(struct pt_regs, regs[7]));
+  DEFINE(S_X8,			offsetof(struct pt_regs, regs[8]));
+  DEFINE(S_X10,			offsetof(struct pt_regs, regs[10]));
+  DEFINE(S_X12,			offsetof(struct pt_regs, regs[12]));
+  DEFINE(S_X14,			offsetof(struct pt_regs, regs[14]));
+  DEFINE(S_X16,			offsetof(struct pt_regs, regs[16]));
+  DEFINE(S_X18,			offsetof(struct pt_regs, regs[18]));
+  DEFINE(S_X20,			offsetof(struct pt_regs, regs[20]));
+  DEFINE(S_X22,			offsetof(struct pt_regs, regs[22]));
+  DEFINE(S_X24,			offsetof(struct pt_regs, regs[24]));
+  DEFINE(S_X26,			offsetof(struct pt_regs, regs[26]));
+  DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index f17134d39e6b..91fff48d0f57 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -23,6 +23,7 @@
 #include <linux/hardirq.h>
 #include <linux/init.h>
 #include <linux/ptrace.h>
+#include <linux/kprobes.h>
 #include <linux/stat.h>
 #include <linux/uaccess.h>
 
@@ -48,6 +49,7 @@ static void mdscr_write(u32 mdscr)
 	asm volatile("msr mdscr_el1, %0" :: "r" (mdscr));
 	local_dbg_restore(flags);
 }
+NOKPROBE_SYMBOL(mdscr_write);
 
 static u32 mdscr_read(void)
 {
@@ -55,6 +57,7 @@ static u32 mdscr_read(void)
 	asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr));
 	return mdscr;
 }
+NOKPROBE_SYMBOL(mdscr_read);
 
 /*
  * Allow root to disable self-hosted debug from userspace.
@@ -103,6 +106,7 @@ void enable_debug_monitors(enum dbg_active_el el)
 		mdscr_write(mdscr);
 	}
 }
+NOKPROBE_SYMBOL(enable_debug_monitors);
 
 void disable_debug_monitors(enum dbg_active_el el)
 {
@@ -123,6 +127,7 @@ void disable_debug_monitors(enum dbg_active_el el)
 		mdscr_write(mdscr);
 	}
 }
+NOKPROBE_SYMBOL(disable_debug_monitors);
 
 /*
  * OS lock clearing.
@@ -167,11 +172,13 @@ static void set_regs_spsr_ss(struct pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
+NOKPROBE_SYMBOL(set_regs_spsr_ss);
 
 static void clear_regs_spsr_ss(struct pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
+NOKPROBE_SYMBOL(clear_regs_spsr_ss);
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
@@ -215,6 +222,7 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 
 	return retval;
 }
+NOKPROBE_SYMBOL(call_step_hook);
 
 static void send_user_sigtrap(int si_code)
 {
@@ -256,6 +264,10 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		 */
 		user_rewind_single_step(current);
 	} else {
+#ifdef	CONFIG_KPROBES
+		if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
+			return 0;
+#endif
 		if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
 			return 0;
 
@@ -269,6 +281,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 
 	return 0;
 }
+NOKPROBE_SYMBOL(single_step_handler);
 
 /*
  * Breakpoint handler is re-entrant as another breakpoint can
@@ -306,19 +319,28 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
+NOKPROBE_SYMBOL(call_break_hook);
 
 static int brk_handler(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		send_user_sigtrap(TRAP_BRKPT);
-	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
-		pr_warning("Unexpected kernel BRK exception at EL1\n");
+	}
+#ifdef	CONFIG_KPROBES
+	else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
+		if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED)
+			return -EFAULT;
+	}
+#endif
+	else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+		pr_warn("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
 	}
 
 	return 0;
 }
+NOKPROBE_SYMBOL(brk_handler);
 
 int aarch32_break_handler(struct pt_regs *regs)
 {
@@ -355,6 +377,7 @@ int aarch32_break_handler(struct pt_regs *regs)
 	send_user_sigtrap(TRAP_BRKPT);
 	return 0;
 }
+NOKPROBE_SYMBOL(aarch32_break_handler);
 
 static int __init debug_traps_init(void)
 {
@@ -376,6 +399,7 @@ void user_rewind_single_step(struct task_struct *task)
 	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
+NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
@@ -391,6 +415,7 @@ void kernel_enable_single_step(struct pt_regs *regs)
 	mdscr_write(mdscr_read() | DBG_MDSCR_SS);
 	enable_debug_monitors(DBG_ACTIVE_EL1);
 }
+NOKPROBE_SYMBOL(kernel_enable_single_step);
 
 void kernel_disable_single_step(void)
 {
@@ -398,12 +423,14 @@ void kernel_disable_single_step(void)
 	mdscr_write(mdscr_read() & ~DBG_MDSCR_SS);
 	disable_debug_monitors(DBG_ACTIVE_EL1);
 }
+NOKPROBE_SYMBOL(kernel_disable_single_step);
 
 int kernel_active_single_step(void)
 {
 	WARN_ON(!irqs_disabled());
 	return mdscr_read() & DBG_MDSCR_SS;
 }
+NOKPROBE_SYMBOL(kernel_active_single_step);
 
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
@@ -411,8 +438,10 @@ void user_enable_single_step(struct task_struct *task)
 	set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
 	set_regs_spsr_ss(task_pt_regs(task));
 }
+NOKPROBE_SYMBOL(user_enable_single_step);
 
 void user_disable_single_step(struct task_struct *task)
 {
 	clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
 }
+NOKPROBE_SYMBOL(user_disable_single_step);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 3eca5d34f7a6..a03eb49cfeeb 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -242,6 +242,7 @@ tsk	.req	x28		// current thread_info
 /*
  * Exception vectors.
  */
+	.pushsection ".entry.text", "ax"
 
 	.align	11
 ENTRY(vectors)
@@ -784,6 +785,8 @@ __ni_sys_trace:
 	bl	do_ni_syscall
 	b	__sys_trace_return
 
+	.popsection				// .entry.text
+
 /*
  * Special system call wrappers.
  */
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index ce21aa88263f..26a6bf77d272 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -24,6 +24,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/smp.h>
@@ -127,6 +128,7 @@ static u64 read_wb_reg(int reg, int n)
 
 	return val;
 }
+NOKPROBE_SYMBOL(read_wb_reg);
 
 static void write_wb_reg(int reg, int n, u64 val)
 {
@@ -140,6 +142,7 @@ static void write_wb_reg(int reg, int n, u64 val)
 	}
 	isb();
 }
+NOKPROBE_SYMBOL(write_wb_reg);
 
 /*
  * Convert a breakpoint privilege level to the corresponding exception
@@ -157,6 +160,7 @@ static enum dbg_active_el debug_exception_level(int privilege)
 		return -EINVAL;
 	}
 }
+NOKPROBE_SYMBOL(debug_exception_level);
 
 enum hw_breakpoint_ops {
 	HW_BREAKPOINT_INSTALL,
@@ -575,6 +579,7 @@ static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable)
 		write_wb_reg(reg, i, ctrl);
 	}
 }
+NOKPROBE_SYMBOL(toggle_bp_registers);
 
 /*
  * Debug exception handlers.
@@ -654,6 +659,7 @@ unlock:
 
 	return 0;
 }
+NOKPROBE_SYMBOL(breakpoint_handler);
 
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
@@ -756,6 +762,7 @@ unlock:
 
 	return 0;
 }
+NOKPROBE_SYMBOL(watchpoint_handler);
 
 /*
  * Handle single-step exception.
@@ -813,6 +820,7 @@ int reinstall_suspended_bps(struct pt_regs *regs)
 
 	return !handled_exception;
 }
+NOKPROBE_SYMBOL(reinstall_suspended_bps);
 
 /*
  * Context-switcher for restoring suspended breakpoints.
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 368c08290dd8..63f9432d05e8 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -30,6 +30,7 @@
 #include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
 #include <asm/fixmap.h>
+#include <asm/opcodes.h>
 #include <asm/insn.h>
 
 #define AARCH64_INSN_SF_BIT	BIT(31)
@@ -162,6 +163,32 @@ static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
 		aarch64_insn_is_nop(insn);
 }
 
+bool __kprobes aarch64_insn_uses_literal(u32 insn)
+{
+	/* ldr/ldrsw (literal), prfm */
+
+	return aarch64_insn_is_ldr_lit(insn) ||
+		aarch64_insn_is_ldrsw_lit(insn) ||
+		aarch64_insn_is_adr_adrp(insn) ||
+		aarch64_insn_is_prfm_lit(insn);
+}
+
+bool __kprobes aarch64_insn_is_branch(u32 insn)
+{
+	/* b, bl, cb*, tb*, b.cond, br, blr */
+
+	return aarch64_insn_is_b(insn) ||
+		aarch64_insn_is_bl(insn) ||
+		aarch64_insn_is_cbz(insn) ||
+		aarch64_insn_is_cbnz(insn) ||
+		aarch64_insn_is_tbz(insn) ||
+		aarch64_insn_is_tbnz(insn) ||
+		aarch64_insn_is_ret(insn) ||
+		aarch64_insn_is_br(insn) ||
+		aarch64_insn_is_blr(insn) ||
+		aarch64_insn_is_bcond(insn);
+}
+
 /*
  * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
  * Section B2.6.5 "Concurrent modification and execution of instructions":
@@ -1175,6 +1202,14 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset)
 	BUG();
 }
 
+/*
+ * Extract the Op/CR data from a msr/mrs instruction.
+ */
+u32 aarch64_insn_extract_system_reg(u32 insn)
+{
+	return (insn & 0x1FFFE0) >> 5;
+}
+
 bool aarch32_insn_is_wide(u32 insn)
 {
 	return insn >= 0xe800;
@@ -1200,3 +1235,101 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn)
 {
 	return insn & CRM_MASK;
 }
+
+static bool __kprobes __check_eq(unsigned long pstate)
+{
+	return (pstate & PSR_Z_BIT) != 0;
+}
+
+static bool __kprobes __check_ne(unsigned long pstate)
+{
+	return (pstate & PSR_Z_BIT) == 0;
+}
+
+static bool __kprobes __check_cs(unsigned long pstate)
+{
+	return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_cc(unsigned long pstate)
+{
+	return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_mi(unsigned long pstate)
+{
+	return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_pl(unsigned long pstate)
+{
+	return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_vs(unsigned long pstate)
+{
+	return (pstate & PSR_V_BIT) != 0;
+}
+
+static bool __kprobes __check_vc(unsigned long pstate)
+{
+	return (pstate & PSR_V_BIT) == 0;
+}
+
+static bool __kprobes __check_hi(unsigned long pstate)
+{
+	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_ls(unsigned long pstate)
+{
+	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_ge(unsigned long pstate)
+{
+	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
+	return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_lt(unsigned long pstate)
+{
+	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
+	return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_gt(unsigned long pstate)
+{
+	/*PSR_N_BIT ^= PSR_V_BIT */
+	unsigned long temp = pstate ^ (pstate << 3);
+
+	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
+	return (temp & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_le(unsigned long pstate)
+{
+	/*PSR_N_BIT ^= PSR_V_BIT */
+	unsigned long temp = pstate ^ (pstate << 3);
+
+	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
+	return (temp & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_al(unsigned long pstate)
+{
+	return true;
+}
+
+/*
+ * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that
+ * it behaves identically to 0b1110 ("al").
+ */
+pstate_check_t * const aarch32_opcode_cond_checks[16] = {
+	__check_eq, __check_ne, __check_cs, __check_cc,
+	__check_mi, __check_pl, __check_vs, __check_vc,
+	__check_hi, __check_ls, __check_ge, __check_lt,
+	__check_gt, __check_le, __check_al, __check_al
+};
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b5f063e5eff7..8c57f6496e56 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -22,6 +22,7 @@
 #include <linux/irq.h>
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
+#include <linux/kprobes.h>
 #include <asm/traps.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
@@ -230,6 +231,7 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 	return 0;
 }
+NOKPROBE_SYMBOL(kgdb_brk_fn)
 
 static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
@@ -238,12 +240,14 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
 
 	return 0;
 }
+NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
 static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 	return 0;
 }
+NOKPROBE_SYMBOL(kgdb_step_brk_fn);
 
 static struct break_hook kgdb_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
diff --git a/arch/arm64/kernel/probes/Makefile b/arch/arm64/kernel/probes/Makefile
new file mode 100644
index 000000000000..ce06312e3d34
--- /dev/null
+++ b/arch/arm64/kernel/probes/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o	\
+				   kprobes_trampoline.o		\
+				   simulate-insn.o
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
new file mode 100644
index 000000000000..37e47a9d617e
--- /dev/null
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -0,0 +1,174 @@
+/*
+ * arch/arm64/kernel/probes/decode-insn.c
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <asm/kprobes.h>
+#include <asm/insn.h>
+#include <asm/sections.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+static bool __kprobes aarch64_insn_is_steppable(u32 insn)
+{
+	/*
+	 * Branch instructions will write a new value into the PC which is
+	 * likely to be relative to the XOL address and therefore invalid.
+	 * Deliberate generation of an exception during stepping is also not
+	 * currently safe. Lastly, MSR instructions can do any number of nasty
+	 * things we can't handle during single-stepping.
+	 */
+	if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) {
+		if (aarch64_insn_is_branch(insn) ||
+		    aarch64_insn_is_msr_imm(insn) ||
+		    aarch64_insn_is_msr_reg(insn) ||
+		    aarch64_insn_is_exception(insn) ||
+		    aarch64_insn_is_eret(insn))
+			return false;
+
+		/*
+		 * The MRS instruction may not return a correct value when
+		 * executing in the single-stepping environment. We do make one
+		 * exception, for reading the DAIF bits.
+		 */
+		if (aarch64_insn_is_mrs(insn))
+			return aarch64_insn_extract_system_reg(insn)
+			     != AARCH64_INSN_SPCLREG_DAIF;
+
+		/*
+		 * The HINT instruction is is problematic when single-stepping,
+		 * except for the NOP case.
+		 */
+		if (aarch64_insn_is_hint(insn))
+			return aarch64_insn_is_nop(insn);
+
+		return true;
+	}
+
+	/*
+	 * Instructions which load PC relative literals are not going to work
+	 * when executed from an XOL slot. Instructions doing an exclusive
+	 * load/store are not going to complete successfully when single-step
+	 * exception handling happens in the middle of the sequence.
+	 */
+	if (aarch64_insn_uses_literal(insn) ||
+	    aarch64_insn_is_exclusive(insn))
+		return false;
+
+	return true;
+}
+
+/* Return:
+ *   INSN_REJECTED     If instruction is one not allowed to kprobe,
+ *   INSN_GOOD         If instruction is supported and uses instruction slot,
+ *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+static enum kprobe_insn __kprobes
+arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+{
+	/*
+	 * Instructions reading or modifying the PC won't work from the XOL
+	 * slot.
+	 */
+	if (aarch64_insn_is_steppable(insn))
+		return INSN_GOOD;
+
+	if (aarch64_insn_is_bcond(insn)) {
+		asi->handler = simulate_b_cond;
+	} else if (aarch64_insn_is_cbz(insn) ||
+	    aarch64_insn_is_cbnz(insn)) {
+		asi->handler = simulate_cbz_cbnz;
+	} else if (aarch64_insn_is_tbz(insn) ||
+	    aarch64_insn_is_tbnz(insn)) {
+		asi->handler = simulate_tbz_tbnz;
+	} else if (aarch64_insn_is_adr_adrp(insn)) {
+		asi->handler = simulate_adr_adrp;
+	} else if (aarch64_insn_is_b(insn) ||
+	    aarch64_insn_is_bl(insn)) {
+		asi->handler = simulate_b_bl;
+	} else if (aarch64_insn_is_br(insn) ||
+	    aarch64_insn_is_blr(insn) ||
+	    aarch64_insn_is_ret(insn)) {
+		asi->handler = simulate_br_blr_ret;
+	} else if (aarch64_insn_is_ldr_lit(insn)) {
+		asi->handler = simulate_ldr_literal;
+	} else if (aarch64_insn_is_ldrsw_lit(insn)) {
+		asi->handler = simulate_ldrsw_literal;
+	} else {
+		/*
+		 * Instruction cannot be stepped out-of-line and we don't
+		 * (yet) simulate it.
+		 */
+		return INSN_REJECTED;
+	}
+
+	return INSN_GOOD_NO_SLOT;
+}
+
+static bool __kprobes
+is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
+{
+	while (scan_start > scan_end) {
+		/*
+		 * atomic region starts from exclusive load and ends with
+		 * exclusive store.
+		 */
+		if (aarch64_insn_is_store_ex(le32_to_cpu(*scan_start)))
+			return false;
+		else if (aarch64_insn_is_load_ex(le32_to_cpu(*scan_start)))
+			return true;
+		scan_start--;
+	}
+
+	return false;
+}
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
+{
+	enum kprobe_insn decoded;
+	kprobe_opcode_t insn = le32_to_cpu(*addr);
+	kprobe_opcode_t *scan_start = addr - 1;
+	kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+	struct module *mod;
+#endif
+
+	if (addr >= (kprobe_opcode_t *)_text &&
+	    scan_end < (kprobe_opcode_t *)_text)
+		scan_end = (kprobe_opcode_t *)_text;
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+	else {
+		preempt_disable();
+		mod = __module_address((unsigned long)addr);
+		if (mod && within_module_init((unsigned long)addr, mod) &&
+			!within_module_init((unsigned long)scan_end, mod))
+			scan_end = (kprobe_opcode_t *)mod->init_layout.base;
+		else if (mod && within_module_core((unsigned long)addr, mod) &&
+			!within_module_core((unsigned long)scan_end, mod))
+			scan_end = (kprobe_opcode_t *)mod->core_layout.base;
+		preempt_enable();
+	}
+#endif
+	decoded = arm_probe_decode_insn(insn, asi);
+
+	if (decoded == INSN_REJECTED ||
+			is_probed_address_atomic(scan_start, scan_end))
+		return INSN_REJECTED;
+
+	return decoded;
+}
diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h
new file mode 100644
index 000000000000..d438289646a6
--- /dev/null
+++ b/arch/arm64/kernel/probes/decode-insn.h
@@ -0,0 +1,35 @@
+/*
+ * arch/arm64/kernel/probes/decode-insn.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_ARM64_H
+#define _ARM_KERNEL_KPROBES_ARM64_H
+
+/*
+ * ARM strongly recommends a limit of 128 bytes between LoadExcl and
+ * StoreExcl instructions in a single thread of execution. So keep the
+ * max atomic context size as 32.
+ */
+#define MAX_ATOMIC_CONTEXT_SIZE	(128 / sizeof(kprobe_opcode_t))
+
+enum kprobe_insn {
+	INSN_REJECTED,
+	INSN_GOOD_NO_SLOT,
+	INSN_GOOD,
+};
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi);
+
+#endif /* _ARM_KERNEL_KPROBES_ARM64_H */
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
new file mode 100644
index 000000000000..bf9768588288
--- /dev/null
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -0,0 +1,686 @@
+/*
+ * arch/arm64/kernel/probes/kprobes.c
+ *
+ * Kprobes support for ARM64
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/stringify.h>
+#include <asm/traps.h>
+#include <asm/ptrace.h>
+#include <asm/cacheflush.h>
+#include <asm/debug-monitors.h>
+#include <asm/system_misc.h>
+#include <asm/insn.h>
+#include <asm/uaccess.h>
+#include <asm/irq.h>
+#include <asm-generic/sections.h>
+
+#include "decode-insn.h"
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
+
+static inline unsigned long min_stack_size(unsigned long addr)
+{
+	unsigned long size;
+
+	if (on_irq_stack(addr, raw_smp_processor_id()))
+		size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
+	else
+		size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
+
+	return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
+}
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+	/* prepare insn slot */
+	p->ainsn.insn[0] = cpu_to_le32(p->opcode);
+
+	flush_icache_range((uintptr_t) (p->ainsn.insn),
+			   (uintptr_t) (p->ainsn.insn) +
+			   MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+
+	/*
+	 * Needs restoring of return address after stepping xol.
+	 */
+	p->ainsn.restore = (unsigned long) p->addr +
+	  sizeof(kprobe_opcode_t);
+}
+
+static void __kprobes arch_prepare_simulate(struct kprobe *p)
+{
+	/* This instructions is not executed xol. No need to adjust the PC */
+	p->ainsn.restore = 0;
+}
+
+static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (p->ainsn.handler)
+		p->ainsn.handler((u32)p->opcode, (long)p->addr, regs);
+
+	/* single step simulated, now go for post processing */
+	post_kprobe_handler(kcb, regs);
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	unsigned long probe_addr = (unsigned long)p->addr;
+	extern char __start_rodata[];
+	extern char __end_rodata[];
+
+	if (probe_addr & 0x3)
+		return -EINVAL;
+
+	/* copy instruction */
+	p->opcode = le32_to_cpu(*p->addr);
+
+	if (in_exception_text(probe_addr))
+		return -EINVAL;
+	if (probe_addr >= (unsigned long) __start_rodata &&
+	    probe_addr <= (unsigned long) __end_rodata)
+		return -EINVAL;
+
+	/* decode instruction */
+	switch (arm_kprobe_decode_insn(p->addr, &p->ainsn)) {
+	case INSN_REJECTED:	/* insn not supported */
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:	/* insn need simulation */
+		p->ainsn.insn = NULL;
+		break;
+
+	case INSN_GOOD:	/* instruction uses slot */
+		p->ainsn.insn = get_insn_slot();
+		if (!p->ainsn.insn)
+			return -ENOMEM;
+		break;
+	};
+
+	/* prepare the instruction */
+	if (p->ainsn.insn)
+		arch_prepare_ss_slot(p);
+	else
+		arch_prepare_simulate(p);
+
+	return 0;
+}
+
+static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
+{
+	void *addrs[1];
+	u32 insns[1];
+
+	addrs[0] = (void *)addr;
+	insns[0] = (u32)opcode;
+
+	return aarch64_insn_patch_text(addrs, insns, 1);
+}
+
+/* arm kprobe: install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, BRK64_OPCODE_KPROBES);
+}
+
+/* disarm kprobe: remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	patch_text(p->addr, p->opcode);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, 0);
+		p->ainsn.insn = NULL;
+	}
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	kcb->prev_kprobe.kp = kprobe_running();
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p)
+{
+	__this_cpu_write(current_kprobe, p);
+}
+
+/*
+ * The D-flag (Debug mask) is set (masked) upon debug exception entry.
+ * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
+ * probe i.e. when probe hit from kprobe handler context upon
+ * executing the pre/post handlers. In this case we return with
+ * D-flag clear so that single-stepping can be carried-out.
+ *
+ * Leave D-flag set in all other cases.
+ */
+static void __kprobes
+spsr_set_debug_flag(struct pt_regs *regs, int mask)
+{
+	unsigned long spsr = regs->pstate;
+
+	if (mask)
+		spsr |= PSR_D_BIT;
+	else
+		spsr &= ~PSR_D_BIT;
+
+	regs->pstate = spsr;
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and  start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * into the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	kcb->saved_irqflag = regs->pstate;
+	regs->pstate |= PSR_I_BIT;
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+						struct pt_regs *regs)
+{
+	if (kcb->saved_irqflag & PSR_I_BIT)
+		regs->pstate |= PSR_I_BIT;
+	else
+		regs->pstate &= ~PSR_I_BIT;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+	kcb->ss_ctx.ss_pending = true;
+	kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t);
+}
+
+static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
+{
+	kcb->ss_ctx.ss_pending = false;
+	kcb->ss_ctx.match_addr = 0;
+}
+
+static void __kprobes setup_singlestep(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb, int reenter)
+{
+	unsigned long slot;
+
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else {
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	}
+
+
+	if (p->ainsn.insn) {
+		/* prepare for single stepping */
+		slot = (unsigned long)p->ainsn.insn;
+
+		set_ss_context(kcb, slot);	/* mark pending ss */
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			spsr_set_debug_flag(regs, 0);
+		else
+			WARN_ON(regs->pstate & PSR_D_BIT);
+
+		/* IRQs and single stepping do not mix well. */
+		kprobes_save_local_irqflag(kcb, regs);
+		kernel_enable_single_step(regs);
+		instruction_pointer_set(regs, slot);
+	} else {
+		/* insn simulation */
+		arch_simulate_insn(p, regs);
+	}
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+				    struct pt_regs *regs,
+				    struct kprobe_ctlblk *kcb)
+{
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SSDONE:
+	case KPROBE_HIT_ACTIVE:
+		kprobes_inc_nmissed_count(p);
+		setup_singlestep(p, regs, kcb, 1);
+		break;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+		dump_kprobe(p);
+		BUG();
+		break;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+
+	if (!cur)
+		return;
+
+	/* return addr restore if non-branching insn */
+	if (cur->ainsn.restore != 0)
+		instruction_pointer_set(regs, cur->ainsn.restore);
+
+	/* restore back original saved kprobe variables and continue */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		return;
+	}
+	/* call post handler */
+	kcb->kprobe_status = KPROBE_HIT_SSDONE;
+	if (cur->post_handler)	{
+		/* post_handler can hit breakpoint and single step
+		 * again, so we enable D-flag for recursive exception.
+		 */
+		cur->post_handler(cur, regs, 0);
+	}
+
+	reset_current_kprobe();
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		/*
+		 * We are here because the instruction being single
+		 * stepped caused a page fault. We reset the current
+		 * kprobe and the ip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		instruction_pointer_set(regs, (unsigned long) cur->addr);
+		if (!instruction_pointer(regs))
+			BUG();
+
+		kernel_disable_single_step();
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			spsr_set_debug_flag(regs, 1);
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else
+			reset_current_kprobe();
+
+		break;
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * We increment the nmissed count for accounting,
+		 * we can also use npre/npostfault count for accounting
+		 * these specific fault cases.
+		 */
+		kprobes_inc_nmissed_count(cur);
+
+		/*
+		 * We come here because instructions in the pre/post
+		 * handler caused the page_fault, this could happen
+		 * if handler tries to access user space by
+		 * copy_from_user(), get_user() etc. Let the
+		 * user-specified handler try to fix it first.
+		 */
+		if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
+			return 1;
+
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+	}
+	return 0;
+}
+
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+				       unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+static void __kprobes kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe *p, *cur_kprobe;
+	struct kprobe_ctlblk *kcb;
+	unsigned long addr = instruction_pointer(regs);
+
+	kcb = get_kprobe_ctlblk();
+	cur_kprobe = kprobe_running();
+
+	p = get_kprobe((kprobe_opcode_t *) addr);
+
+	if (p) {
+		if (cur_kprobe) {
+			if (reenter_kprobe(p, regs, kcb))
+				return;
+		} else {
+			/* Probe hit */
+			set_current_kprobe(p);
+			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+			/*
+			 * If we have no pre-handler or it returned 0, we
+			 * continue with normal processing.  If we have a
+			 * pre-handler and it returned non-zero, it prepped
+			 * for calling the break_handler below on re-entry,
+			 * so get out doing nothing more here.
+			 *
+			 * pre_handler can hit a breakpoint and can step thru
+			 * before return, keep PSTATE D-flag enabled until
+			 * pre_handler return back.
+			 */
+			if (!p->pre_handler || !p->pre_handler(p, regs)) {
+				setup_singlestep(p, regs, kcb, 0);
+				return;
+			}
+		}
+	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
+	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
+		/* We probably hit a jprobe.  Call its break handler. */
+		if (cur_kprobe->break_handler  &&
+		     cur_kprobe->break_handler(cur_kprobe, regs)) {
+			setup_singlestep(cur_kprobe, regs, kcb, 0);
+			return;
+		}
+	}
+	/*
+	 * The breakpoint instruction was removed right
+	 * after we hit it.  Another cpu has removed
+	 * either a probepoint or a debugger breakpoint
+	 * at this address.  In either case, no further
+	 * handling of this interrupt is appropriate.
+	 * Return back to original instruction, and continue.
+	 */
+}
+
+static int __kprobes
+kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+	if ((kcb->ss_ctx.ss_pending)
+	    && (kcb->ss_ctx.match_addr == addr)) {
+		clear_ss_context(kcb);	/* clear pending ss */
+		return DBG_HOOK_HANDLED;
+	}
+	/* not ours, kprobes should ignore it */
+	return DBG_HOOK_ERROR;
+}
+
+int __kprobes
+kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	int retval;
+
+	/* return error if this is not our step */
+	retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
+
+	if (retval == DBG_HOOK_HANDLED) {
+		kprobes_restore_local_irqflag(kcb, regs);
+		kernel_disable_single_step();
+
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			spsr_set_debug_flag(regs, 1);
+
+		post_kprobe_handler(kcb, regs);
+	}
+
+	return retval;
+}
+
+int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
+{
+	kprobe_handler(regs);
+	return DBG_HOOK_HANDLED;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	long stack_ptr = kernel_stack_pointer(regs);
+
+	kcb->jprobe_saved_regs = *regs;
+	/*
+	 * As Linus pointed out, gcc assumes that the callee
+	 * owns the argument space and could overwrite it, e.g.
+	 * tailcall optimization. So, to be absolutely safe
+	 * we also save and restore enough stack bytes to cover
+	 * the argument area.
+	 */
+	kasan_disable_current();
+	memcpy(kcb->jprobes_stack, (void *)stack_ptr,
+	       min_stack_size(stack_ptr));
+	kasan_enable_current();
+
+	instruction_pointer_set(regs, (unsigned long) jp->entry);
+	preempt_disable();
+	pause_graph_tracing();
+	return 1;
+}
+
+void __kprobes jprobe_return(void)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	/*
+	 * Jprobe handler return by entering break exception,
+	 * encoded same as kprobe, but with following conditions
+	 * -a special PC to identify it from the other kprobes.
+	 * -restore stack addr to original saved pt_regs
+	 */
+	asm volatile("				mov sp, %0	\n"
+		     "jprobe_return_break:	brk %1		\n"
+		     :
+		     : "r" (kcb->jprobe_saved_regs.sp),
+		       "I" (BRK64_ESR_KPROBES)
+		     : "memory");
+
+	unreachable();
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	long stack_addr = kcb->jprobe_saved_regs.sp;
+	long orig_sp = kernel_stack_pointer(regs);
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	extern const char jprobe_return_break[];
+
+	if (instruction_pointer(regs) != (u64) jprobe_return_break)
+		return 0;
+
+	if (orig_sp != stack_addr) {
+		struct pt_regs *saved_regs =
+		    (struct pt_regs *)kcb->jprobe_saved_regs.sp;
+		pr_err("current sp %lx does not match saved sp %lx\n",
+		       orig_sp, stack_addr);
+		pr_err("Saved registers for jprobe %p\n", jp);
+		show_regs(saved_regs);
+		pr_err("Current registers\n");
+		show_regs(regs);
+		BUG();
+	}
+	unpause_graph_tracing();
+	*regs = kcb->jprobe_saved_regs;
+	kasan_disable_current();
+	memcpy((void *)stack_addr, kcb->jprobes_stack,
+	       min_stack_size(stack_addr));
+	kasan_enable_current();
+	preempt_enable_no_resched();
+	return 1;
+}
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+	extern char __idmap_text_start[], __idmap_text_end[];
+	extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+
+	if ((addr >= (unsigned long)__kprobes_text_start &&
+	    addr < (unsigned long)__kprobes_text_end) ||
+	    (addr >= (unsigned long)__entry_text_start &&
+	    addr < (unsigned long)__entry_text_end) ||
+	    (addr >= (unsigned long)__idmap_text_start &&
+	    addr < (unsigned long)__idmap_text_end) ||
+	    !!search_exception_tables(addr))
+		return true;
+
+	if (!is_kernel_in_hyp_mode()) {
+		if ((addr >= (unsigned long)__hyp_text_start &&
+		    addr < (unsigned long)__hyp_text_end) ||
+		    (addr >= (unsigned long)__hyp_idmap_text_start &&
+		    addr < (unsigned long)__hyp_idmap_text_end))
+			return true;
+	}
+
+	return false;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags, orig_ret_address = 0;
+	unsigned long trampoline_address =
+		(unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * return probes installed on them, and/or more than one
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always pushed into the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the (chronologically) first instance's ret_addr
+	 *	 will be the real return address, and all the rest will
+	 *	 point to kretprobe_trampoline.
+	 */
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (ri->rp && ri->rp->handler) {
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__this_cpu_write(current_kprobe, NULL);
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_hash_unlock(current, &flags);
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+	return (void *)orig_ret_address;
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *)regs->regs[30];
+
+	/* replace return addr (x30) with trampoline */
+	regs->regs[30] = (long)&kretprobe_trampoline;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return 0;
+}
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000000..5d6e7f14638c
--- /dev/null
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,81 @@
+/*
+ * trampoline entry and return code for kretprobes.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+	.text
+
+	.macro	save_all_base_regs
+	stp x0, x1, [sp, #S_X0]
+	stp x2, x3, [sp, #S_X2]
+	stp x4, x5, [sp, #S_X4]
+	stp x6, x7, [sp, #S_X6]
+	stp x8, x9, [sp, #S_X8]
+	stp x10, x11, [sp, #S_X10]
+	stp x12, x13, [sp, #S_X12]
+	stp x14, x15, [sp, #S_X14]
+	stp x16, x17, [sp, #S_X16]
+	stp x18, x19, [sp, #S_X18]
+	stp x20, x21, [sp, #S_X20]
+	stp x22, x23, [sp, #S_X22]
+	stp x24, x25, [sp, #S_X24]
+	stp x26, x27, [sp, #S_X26]
+	stp x28, x29, [sp, #S_X28]
+	add x0, sp, #S_FRAME_SIZE
+	stp lr, x0, [sp, #S_LR]
+	/*
+	 * Construct a useful saved PSTATE
+	 */
+	mrs x0, nzcv
+	mrs x1, daif
+	orr x0, x0, x1
+	mrs x1, CurrentEL
+	orr x0, x0, x1
+	mrs x1, SPSel
+	orr x0, x0, x1
+	stp xzr, x0, [sp, #S_PC]
+	.endm
+
+	.macro	restore_all_base_regs
+	ldr x0, [sp, #S_PSTATE]
+	and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT)
+	msr nzcv, x0
+	ldp x0, x1, [sp, #S_X0]
+	ldp x2, x3, [sp, #S_X2]
+	ldp x4, x5, [sp, #S_X4]
+	ldp x6, x7, [sp, #S_X6]
+	ldp x8, x9, [sp, #S_X8]
+	ldp x10, x11, [sp, #S_X10]
+	ldp x12, x13, [sp, #S_X12]
+	ldp x14, x15, [sp, #S_X14]
+	ldp x16, x17, [sp, #S_X16]
+	ldp x18, x19, [sp, #S_X18]
+	ldp x20, x21, [sp, #S_X20]
+	ldp x22, x23, [sp, #S_X22]
+	ldp x24, x25, [sp, #S_X24]
+	ldp x26, x27, [sp, #S_X26]
+	ldp x28, x29, [sp, #S_X28]
+	.endm
+
+ENTRY(kretprobe_trampoline)
+	sub sp, sp, #S_FRAME_SIZE
+
+	save_all_base_regs
+
+	mov x0, sp
+	bl trampoline_probe_handler
+	/*
+	 * Replace trampoline address in lr with actual orig_ret_addr return
+	 * address.
+	 */
+	mov lr, x0
+
+	restore_all_base_regs
+
+	add sp, sp, #S_FRAME_SIZE
+	ret
+
+ENDPROC(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000000..8977ce9d009d
--- /dev/null
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -0,0 +1,217 @@
+/*
+ * arch/arm64/kernel/probes/simulate-insn.c
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+
+#include "simulate-insn.h"
+
+#define sign_extend(x, signbit)		\
+	((x) | (0 - ((x) & (1 << (signbit)))))
+
+#define bbl_displacement(insn)		\
+	sign_extend(((insn) & 0x3ffffff) << 2, 27)
+
+#define bcond_displacement(insn)	\
+	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+#define cbz_displacement(insn)	\
+	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+#define tbz_displacement(insn)	\
+	sign_extend(((insn >> 5) & 0x3fff) << 2, 15)
+
+#define ldr_displacement(insn)	\
+	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val)
+{
+	if (reg < 31)
+		regs->regs[reg] = val;
+}
+
+static inline void set_w_reg(struct pt_regs *regs, int reg, u64 val)
+{
+	if (reg < 31)
+		regs->regs[reg] = lower_32_bits(val);
+}
+
+static inline u64 get_x_reg(struct pt_regs *regs, int reg)
+{
+	if (reg < 31)
+		return regs->regs[reg];
+	else
+		return 0;
+}
+
+static inline u32 get_w_reg(struct pt_regs *regs, int reg)
+{
+	if (reg < 31)
+		return lower_32_bits(regs->regs[reg]);
+	else
+		return 0;
+}
+
+static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs)
+{
+	int xn = opcode & 0x1f;
+
+	return (opcode & (1 << 31)) ?
+	    (get_x_reg(regs, xn) == 0) : (get_w_reg(regs, xn) == 0);
+}
+
+static bool __kprobes check_cbnz(u32 opcode, struct pt_regs *regs)
+{
+	int xn = opcode & 0x1f;
+
+	return (opcode & (1 << 31)) ?
+	    (get_x_reg(regs, xn) != 0) : (get_w_reg(regs, xn) != 0);
+}
+
+static bool __kprobes check_tbz(u32 opcode, struct pt_regs *regs)
+{
+	int xn = opcode & 0x1f;
+	int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f);
+
+	return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) == 0;
+}
+
+static bool __kprobes check_tbnz(u32 opcode, struct pt_regs *regs)
+{
+	int xn = opcode & 0x1f;
+	int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f);
+
+	return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) != 0;
+}
+
+/*
+ * instruction simulation functions
+ */
+void __kprobes
+simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs)
+{
+	long imm, xn, val;
+
+	xn = opcode & 0x1f;
+	imm = ((opcode >> 3) & 0x1ffffc) | ((opcode >> 29) & 0x3);
+	imm = sign_extend(imm, 20);
+	if (opcode & 0x80000000)
+		val = (imm<<12) + (addr & 0xfffffffffffff000);
+	else
+		val = imm + addr;
+
+	set_x_reg(regs, xn, val);
+
+	instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
+
+void __kprobes
+simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs)
+{
+	int disp = bbl_displacement(opcode);
+
+	/* Link register is x30 */
+	if (opcode & (1 << 31))
+		set_x_reg(regs, 30, addr + 4);
+
+	instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs)
+{
+	int disp = 4;
+
+	if (aarch32_opcode_cond_checks[opcode & 0xf](regs->pstate & 0xffffffff))
+		disp = bcond_displacement(opcode);
+
+	instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs)
+{
+	int xn = (opcode >> 5) & 0x1f;
+
+	/* update pc first in case we're doing a "blr lr" */
+	instruction_pointer_set(regs, get_x_reg(regs, xn));
+
+	/* Link register is x30 */
+	if (((opcode >> 21) & 0x3) == 1)
+		set_x_reg(regs, 30, addr + 4);
+}
+
+void __kprobes
+simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs)
+{
+	int disp = 4;
+
+	if (opcode & (1 << 24)) {
+		if (check_cbnz(opcode, regs))
+			disp = cbz_displacement(opcode);
+	} else {
+		if (check_cbz(opcode, regs))
+			disp = cbz_displacement(opcode);
+	}
+	instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs)
+{
+	int disp = 4;
+
+	if (opcode & (1 << 24)) {
+		if (check_tbnz(opcode, regs))
+			disp = tbz_displacement(opcode);
+	} else {
+		if (check_tbz(opcode, regs))
+			disp = tbz_displacement(opcode);
+	}
+	instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
+{
+	u64 *load_addr;
+	int xn = opcode & 0x1f;
+	int disp;
+
+	disp = ldr_displacement(opcode);
+	load_addr = (u64 *) (addr + disp);
+
+	if (opcode & (1 << 30))	/* x0-x30 */
+		set_x_reg(regs, xn, *load_addr);
+	else			/* w0-w30 */
+		set_w_reg(regs, xn, *load_addr);
+
+	instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
+
+void __kprobes
+simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs)
+{
+	s32 *load_addr;
+	int xn = opcode & 0x1f;
+	int disp;
+
+	disp = ldr_displacement(opcode);
+	load_addr = (s32 *) (addr + disp);
+
+	set_x_reg(regs, xn, *load_addr);
+
+	instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000000..050bde683c2d
--- /dev/null
+++ b/arch/arm64/kernel/probes/simulate-insn.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm64/kernel/probes/simulate-insn.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_SIMULATE_INSN_H
+#define _ARM_KERNEL_KPROBES_SIMULATE_INSN_H
+
+void simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs);
+
+#endif /* _ARM_KERNEL_KPROBES_SIMULATE_INSN_H */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 3f6cd5c5234f..030c1d5aa46d 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -48,6 +48,107 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+#define GPR_OFFSET_NAME(r) \
+	{.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	GPR_OFFSET_NAME(0),
+	GPR_OFFSET_NAME(1),
+	GPR_OFFSET_NAME(2),
+	GPR_OFFSET_NAME(3),
+	GPR_OFFSET_NAME(4),
+	GPR_OFFSET_NAME(5),
+	GPR_OFFSET_NAME(6),
+	GPR_OFFSET_NAME(7),
+	GPR_OFFSET_NAME(8),
+	GPR_OFFSET_NAME(9),
+	GPR_OFFSET_NAME(10),
+	GPR_OFFSET_NAME(11),
+	GPR_OFFSET_NAME(12),
+	GPR_OFFSET_NAME(13),
+	GPR_OFFSET_NAME(14),
+	GPR_OFFSET_NAME(15),
+	GPR_OFFSET_NAME(16),
+	GPR_OFFSET_NAME(17),
+	GPR_OFFSET_NAME(18),
+	GPR_OFFSET_NAME(19),
+	GPR_OFFSET_NAME(20),
+	GPR_OFFSET_NAME(21),
+	GPR_OFFSET_NAME(22),
+	GPR_OFFSET_NAME(23),
+	GPR_OFFSET_NAME(24),
+	GPR_OFFSET_NAME(25),
+	GPR_OFFSET_NAME(26),
+	GPR_OFFSET_NAME(27),
+	GPR_OFFSET_NAME(28),
+	GPR_OFFSET_NAME(29),
+	GPR_OFFSET_NAME(30),
+	{.name = "lr", .offset = offsetof(struct pt_regs, regs[30])},
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(pc),
+	REG_OFFSET_NAME(pstate),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:      pt_regs which contains kernel stack pointer.
+ * @addr:      address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
+		on_irq_stack(addr, raw_smp_processor_id());
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
 /*
  * TODO: does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 0de7be4f1a9d..89d6e177ecbd 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
 			__exception_text_end = .;
 			IRQENTRY_TEXT
 			SOFTIRQENTRY_TEXT
+			ENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
+			KPROBES_TEXT
 			HYPERVISOR_TEXT
 			IDMAP_TEXT
 			HIBERNATE_TEXT
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index fc5a34a72c6d..4ebda515a016 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -41,6 +41,28 @@
 
 static const char *fault_name(unsigned int esr);
 
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+	int ret = 0;
+
+	/* kprobe_running() needs smp_processor_id() */
+	if (!user_mode(regs)) {
+		preempt_disable();
+		if (kprobe_running() && kprobe_fault_handler(regs, esr))
+			ret = 1;
+		preempt_enable();
+	}
+
+	return ret;
+}
+#else
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+	return 0;
+}
+#endif
+
 /*
  * Dump out the page tables associated with 'addr' in mm 'mm'.
  */
@@ -262,6 +284,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
+	if (notify_page_fault(regs, esr))
+		return 0;
+
 	tsk = current;
 	mm  = tsk->mm;
 
@@ -632,6 +657,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 
 	return rv;
 }
+NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
 void cpu_enable_pan(void *__unused)