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>

arch/arm/Kconfig

@@ -60,6 +60,7 @@ config ARM
 	select HAVE_MEMBLOCK
 	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
+	select HAVE_OPTPROBES if !THUMB2_KERNEL
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP

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 */

arch/arm/kernel/Makefile

@@ -52,7 +52,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 # Main staffs in KPROBES are in arch/arm/probes/ .
-obj-$(CONFIG_KPROBES)		+= patch.o
+obj-$(CONFIG_KPROBES)		+= patch.o insn.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o patch.o

arch/arm/kernel/ftrace.c

@@ -20,8 +20,7 @@
 #include <asm/cacheflush.h>
 #include <asm/opcodes.h>
 #include <asm/ftrace.h>
-
-#include "insn.h"
+#include <asm/insn.h>
 
 #ifdef CONFIG_THUMB2_KERNEL
 #define	NOP		0xf85deb04	/* pop.w {lr} */

arch/arm/kernel/jump_label.c

@@ -1,8 +1,7 @@
 #include <linux/kernel.h>
 #include <linux/jump_label.h>
 #include <asm/patch.h>
-
-#include "insn.h"
+#include <asm/insn.h>
 
 #ifdef HAVE_JUMP_LABEL
 

arch/arm/probes/kprobes/Makefile

@@ -7,5 +7,6 @@ obj-$(CONFIG_KPROBES)		+= actions-thumb.o checkers-thumb.o
 test-kprobes-objs		+= test-thumb.o
 else
 obj-$(CONFIG_KPROBES)		+= actions-arm.o checkers-arm.o
+obj-$(CONFIG_OPTPROBES)		+= opt-arm.o
 test-kprobes-objs		+= test-arm.o
 endif

arch/arm/probes/kprobes/core.c

@@ -163,19 +163,31 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
  * memory. It is also needed to atomically set the two half-words of a 32-bit
  * Thumb breakpoint.
  */
-int __kprobes __arch_disarm_kprobe(void *p)
-{
-	struct kprobe *kp = p;
-	void *addr = (void *)((uintptr_t)kp->addr & ~1);
-
-	__patch_text(addr, kp->opcode);
+struct patch {
+	void *addr;
+	unsigned int insn;
+};
 
+static int __kprobes_remove_breakpoint(void *data)
+{
+	struct patch *p = data;
+	__patch_text(p->addr, p->insn);
 	return 0;
 }
 
+void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn)
+{
+	struct patch p = {
+		.addr = addr,
+		.insn = insn,
+	};
+	stop_machine(__kprobes_remove_breakpoint, &p, cpu_online_mask);
+}
+
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	stop_machine(__arch_disarm_kprobe, p, cpu_online_mask);
+	kprobes_remove_breakpoint((void *)((uintptr_t)p->addr & ~1),
+			p->opcode);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)

arch/arm/probes/kprobes/core.h

@@ -30,6 +30,8 @@
 #define KPROBE_THUMB16_BREAKPOINT_INSTRUCTION	0xde18
 #define KPROBE_THUMB32_BREAKPOINT_INSTRUCTION	0xf7f0a018
 
+extern void kprobes_remove_breakpoint(void *addr, unsigned int insn);
+
 enum probes_insn __kprobes
 kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_probes_insn *asi,
 		const struct decode_header *h);