Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Kexec support for arm64

 - Kprobes support

 - Expose MIDR_EL1 and REVIDR_EL1 CPU identification registers to sysfs

 - Trapping of user space cache maintenance operations and emulation in
   the kernel (CPU errata workaround)

 - Clean-up of the early page tables creation (kernel linear mapping,
   EFI run-time maps) to avoid splitting larger blocks (e.g.  pmds) into
   smaller ones (e.g.  ptes)

 - VDSO support for CLOCK_MONOTONIC_RAW in clock_gettime()

 - ARCH_HAS_KCOV enabled for arm64

 - Optimise IP checksum helpers

 - SWIOTLB optimisation to only allocate/initialise the buffer if the
   available RAM is beyond the 32-bit mask

 - Properly handle the "nosmp" command line argument

 - Fix for the initialisation of the CPU debug state during early boot

 - vdso-offsets.h build dependency workaround

 - Build fix when RANDOMIZE_BASE is enabled with MODULES off

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (64 commits)
  arm64: arm: Fix-up the removal of the arm64 regs_query_register_name() prototype
  arm64: Only select ARM64_MODULE_PLTS if MODULES=y
  arm64: mm: run pgtable_page_ctor() on non-swapper translation table pages
  arm64: mm: make create_mapping_late() non-allocating
  arm64: Honor nosmp kernel command line option
  arm64: Fix incorrect per-cpu usage for boot CPU
  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
  arm64: debug: remove unused local_dbg_{enable, disable} macros
  arm64: debug: remove redundant spsr manipulation
  arm64: debug: unmask PSTATE.D earlier
  arm64: localise Image objcopy flags
  arm64: ptrace: remove extra define for CPSR's E bit
  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
  ...

7 files changed, 1224 insertions, 0 deletions

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 */