arm64: Kprobes with single stepping support

Add support for basic kernel probes(kprobes) and jump probes
(jprobes) for ARM64.

Kprobes utilizes software breakpoint and single step debug
exceptions supported on ARM v8.

A software breakpoint is placed at the probe address to trap the
kernel execution into the kprobe handler.

ARM v8 supports enabling single stepping before the break exception
return (ERET), with next PC in exception return address (ELR_EL1). The
kprobe handler prepares an executable memory slot for out-of-line
execution with a copy of the original instruction being probed, and
enables single stepping. The PC is set to the out-of-line slot address
before the ERET. With this scheme, the instruction is executed with the
exact same register context except for the PC (and DAIF) registers.

Debug mask (PSTATE.D) is enabled only when single stepping a recursive
kprobe, e.g.: during kprobes reenter so that probed instruction can be
single stepped within the kprobe handler -exception- context.
The recursion depth of kprobe is always 2, i.e. upon probe re-entry,
any further re-entry is prevented by not calling handlers and the case
counted as a missed kprobe).

Single stepping from the x-o-l slot has a drawback for PC-relative accesses
like branching and symbolic literals access as the offset from the new PC
(slot address) may not be ensured to fit in the immediate value of
the opcode. Such instructions need simulation, so reject
probing them.

Instructions generating exceptions or cpu mode change are rejected
for probing.

Exclusive load/store instructions are rejected too.  Additionally, the
code is checked to see if it is inside an exclusive load/store sequence
(code from Pratyush).

System instructions are mostly enabled for stepping, except MSR/MRS
accesses to "DAIF" flags in PSTATE, which are not safe for
probing.

This also changes arch/arm64/include/asm/ptrace.h to use
include/asm-generic/ptrace.h.

Thanks to Steve Capper and Pratyush Anand for several suggested
Changes.
Signed-off-by: NSandeepa Prabhu <sandeepa.s.prabhu@gmail.com>
Signed-off-by: NDavid A. Long <dave.long@linaro.org>
Signed-off-by: NPratyush Anand <panand@redhat.com>
Acked-by: NMasami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>

arch/arm64/Kconfig

@@ -88,6 +88,7 @@ config ARM64
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_KPROBES
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING

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

arch/arm64/include/asm/insn.h

@@ -253,6 +253,8 @@ __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)

arch/arm64/include/asm/kprobes.h

+/*
+ * 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);
+
+#endif /* _ARM_KPROBES_H */

arch/arm64/include/asm/probes.h

+/*
+ * 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
+
+struct kprobe;
+struct arch_specific_insn;
+
+typedef u32 kprobe_opcode_t;
+typedef unsigned long (kprobes_pstate_check_t)(unsigned long);
+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;
+	kprobes_pstate_check_t *pstate_cc;
+	kprobes_handler_t *handler;
+	/* restore address after step xol */
+	unsigned long restore;
+};
+
+#endif

arch/arm64/include/asm/ptrace.h

@@ -147,9 +147,12 @@ 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,
@@ -206,8 +209,15 @@ 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__ */

arch/arm64/kernel/Makefile

@@ -46,7 +46,7 @@ arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.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

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>
 
@@ -266,6 +267,10 @@ 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;
 
@@ -322,8 +327,15 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 {
 	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;
 	}
 

arch/arm64/kernel/probes/Makefile

+obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o

arch/arm64/kernel/probes/decode-insn.c

+/*
+ * 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"
+
+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,
+ */
+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;
+	else
+		return INSN_REJECTED;
+}
+
+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;
+}

arch/arm64/kernel/probes/decode-insn.h

+/*
+ * 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,
+};
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi);
+
+#endif /* _ARM_KERNEL_KPROBES_ARM64_H */

arch/arm64/kernel/probes/kprobes.c

+/*
+ * 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/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 "decode-insn.h"
+
+#define MIN_STACK_SIZE(addr)	(on_irq_stack(addr, raw_smp_processor_id()) ? \
+	min((unsigned long)IRQ_STACK_SIZE,	\
+	IRQ_STACK_PTR(raw_smp_processor_id()) - (addr)) : \
+	min((unsigned long)MAX_STACK_SIZE,	\
+	(unsigned long)current_thread_info() + THREAD_START_SP - (addr)))
+
+void jprobe_return_break(void);
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+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);
+}
+
+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:	/* instruction uses slot */
+		p->ainsn.insn = get_insn_slot();
+		if (!p->ainsn.insn)
+			return -ENOMEM;
+		break;
+	};
+
+	/* prepare the instruction */
+	arch_prepare_ss_slot(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;
+	}
+
+	BUG_ON(!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);
+
+	/* IRQs and single stepping do not mix well. */
+	kprobes_save_local_irqflag(kcb, regs);
+	kernel_enable_single_step(regs);
+	instruction_pointer_set(regs, slot);
+}
+
+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.
+	 */
+	memcpy(kcb->jprobes_stack, (void *)stack_ptr,
+	       MIN_STACK_SIZE(stack_ptr));
+
+	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 magic number in x0 to identify from rest of other kprobes.
+	 * -restore stack addr to original saved pt_regs
+	 */
+	asm volatile ("ldr x0, [%0]\n\t"
+		      "mov sp, x0\n\t"
+		      ".globl jprobe_return_break\n\t"
+		      "jprobe_return_break:\n\t"
+		      "brk %1\n\t"
+		      :
+		      : "r"(&kcb->jprobe_saved_regs.sp),
+		      "I"(BRK64_ESR_KPROBES)
+		      : "memory");
+}
+
+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);
+
+	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;
+	memcpy((void *)stack_addr, kcb->jprobes_stack,
+	       MIN_STACK_SIZE(stack_addr));
+	preempt_enable_no_resched();
+	return 1;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return 0;
+}

arch/arm64/kernel/vmlinux.lds.S

@@ -121,6 +121,7 @@ SECTIONS
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
+			KPROBES_TEXT
 			HYPERVISOR_TEXT
 			IDMAP_TEXT
 			HIBERNATE_TEXT

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'.
  */
@@ -259,6 +281,9 @@ 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;
 
@@ -629,6 +654,7 @@ 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)