ARM: kprobes: enable OPTPROBES for ARM 32

This patch introduce kprobeopt for ARM 32.

Limitations:
 - Currently only kernel compiled with ARM ISA is supported.

 - Offset between probe point and optinsn slot must not larger than
   32MiB. Masami Hiramatsu suggests replacing 2 words, it will make
   things complex. Futher patch can make such optimization.

Kprobe opt on ARM is relatively simpler than kprobe opt on x86 because
ARM instruction is always 4 bytes aligned and 4 bytes long. This patch
replace probed instruction by a 'b', branch to trampoline code and then
calls optimized_callback(). optimized_callback() calls opt_pre_handler()
to execute kprobe handler. It also emulate/simulate replaced instruction.

When unregistering kprobe, the deferred manner of unoptimizer may leave
branch instruction before optimizer is called. Different from x86_64,
which only copy the probed insn after optprobe_template_end and
reexecute them, this patch call singlestep to emulate/simulate the insn
directly. Futher patch can optimize this behavior.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Will Deacon <will.deacon@arm.com>
Reviewed-by: Jon Medhurst (Tixy) <tixy@linaro.org>
Signed-off-by: Jon Medhurst <tixy@linaro.org>

2 files changed, 58 insertions, 0 deletions

diff --git a/arch/arm/include/asm/insn.h b/arch/arm/include/asm/insn.h
new file mode 100644
index 000000000000..e96065da4dae
--- /dev/null
+++ b/arch/arm/include/asm/insn.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+        return 0xf3af8000; /* nop.w */
+#else
+        return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+        return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+        return __arm_gen_branch(pc, addr, true);
+}
+
+#endif
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 56f9ac68fbd1..50ff3bc7928e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -50,5 +50,34 @@ int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
                              unsigned long val, void *data);
 
+/* optinsn template addresses */
+extern __visible kprobe_opcode_t optprobe_template_entry;
+extern __visible kprobe_opcode_t optprobe_template_val;
+extern __visible kprobe_opcode_t optprobe_template_call;
+extern __visible kprobe_opcode_t optprobe_template_end;
+extern __visible kprobe_opcode_t optprobe_template_sub_sp;
+extern __visible kprobe_opcode_t optprobe_template_add_sp;
+
+#define MAX_OPTIMIZED_LENGTH    4
+#define MAX_OPTINSN_SIZE                                \
+        ((unsigned long)&optprobe_template_end -        \
+         (unsigned long)&optprobe_template_entry)
+#define RELATIVEJUMP_SIZE       4
+
+struct arch_optimized_insn {
+        /*
+         * copy of the original instructions.
+         * Different from x86, ARM kprobe_opcode_t is u32.
+         */
+#define MAX_COPIED_INSN DIV_ROUND_UP(RELATIVEJUMP_SIZE, sizeof(kprobe_opcode_t))
+        kprobe_opcode_t copied_insn[MAX_COPIED_INSN];
+        /* detour code buffer */
+        kprobe_opcode_t *insn;
+        /*
+         * We always copy one instruction on ARM,
+         * so size will always be 4, and unlike x86, there is no
+         * need for a size field.
+         */
+};
 
 #endif /* _ARM_KPROBES_H */