Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

1 files changed, 76 insertions, 588 deletions

diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 7da647d8b64..e213fc8408d 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -30,16 +30,15 @@
  *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  * 2005-May	Rusty Lynch <rusty.lynch@intel.com>
- * 		Added function return probes functionality
+ *		Added function return probes functionality
  * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
- * 		kprobe-booster and kretprobe-booster for i386.
+ *		kprobe-booster and kretprobe-booster for i386.
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
- * 		and kretprobe-booster for x86-64
+ *		and kretprobe-booster for x86-64
  * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
- * 		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
- * 		unified x86 kprobes code.
+ *		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
+ *		unified x86 kprobes code.
  */
-
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
@@ -59,6 +58,8 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
+#include "kprobes-common.h"
+
 void jprobe_return_end(void);
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -108,6 +109,7 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
 			      doesn't switch kernel stack.*/
 	{NULL, NULL}	/* Terminator */
 };
+
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
 static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
@@ -123,11 +125,17 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 }
 
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-static void __kprobes synthesize_reljump(void *from, void *to)
+void __kprobes synthesize_reljump(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
 
+/* Insert a call instruction at address 'from', which calls address 'to'.*/
+void __kprobes synthesize_relcall(void *from, void *to)
+{
+	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
+}
+
 /*
  * Skip the prefixes of the instruction.
  */
@@ -151,7 +159,7 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-static int __kprobes can_boost(kprobe_opcode_t *opcodes)
+int __kprobes can_boost(kprobe_opcode_t *opcodes)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
@@ -207,13 +215,15 @@ retry:
 	}
 }
 
-/* Recover the probed instruction at addr for further analysis. */
-static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+static unsigned long
+__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+
 	kp = get_kprobe((void *)addr);
+	/* There is no probe, return original address */
 	if (!kp)
-		return -EINVAL;
+		return addr;
 
 	/*
 	 *  Basically, kp->ainsn.insn has an original instruction.
@@ -230,14 +240,29 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 	 */
 	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
 	buf[0] = kp->opcode;
-	return 0;
+	return (unsigned long)buf;
+}
+
+/*
+ * Recover the probed instruction at addr for further analysis.
+ * Caller must lock kprobes by kprobe_mutex, or disable preemption
+ * for preventing to release referencing kprobes.
+ */
+unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+{
+	unsigned long __addr;
+
+	__addr = __recover_optprobed_insn(buf, addr);
+	if (__addr != addr)
+		return __addr;
+
+	return __recover_probed_insn(buf, addr);
 }
 
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
-	int ret;
-	unsigned long addr, offset = 0;
+	unsigned long addr, __addr, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
@@ -247,26 +272,24 @@ static int __kprobes can_probe(unsigned long paddr)
 	/* Decode instructions */
 	addr = paddr - offset;
 	while (addr < paddr) {
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-
 		/*
 		 * Check if the instruction has been modified by another
 		 * kprobe, in which case we replace the breakpoint by the
 		 * original instruction in our buffer.
+		 * Also, jump optimization will change the breakpoint to
+		 * relative-jump. Since the relative-jump itself is
+		 * normally used, we just go through if there is no kprobe.
 		 */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				/*
-				 * Another debugging subsystem might insert
-				 * this breakpoint. In that case, we can't
-				 * recover it.
-				 */
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
+		__addr = recover_probed_instruction(buf, addr);
+		kernel_insn_init(&insn, (void *)__addr);
 		insn_get_length(&insn);
+
+		/*
+		 * Another debugging subsystem might insert this breakpoint.
+		 * In that case, we can't recover it.
+		 */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
 		addr += insn.length;
 	}
 
@@ -299,24 +322,16 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
  * If not, return null.
  * Only applicable to 64-bit x86.
  */
-static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
+int __kprobes __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
-	int ret;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	kernel_insn_init(&insn, src);
-	if (recover) {
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf,
-							 (unsigned long)src);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-	}
+	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	/* Another subsystem puts a breakpoint, failed to recover */
+	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+		return 0;
 	memcpy(dest, insn.kaddr, insn.length);
 
 #ifdef CONFIG_X86_64
@@ -337,8 +352,7 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
 		 * extension of the original signed 32-bit displacement would
 		 * have given.
 		 */
-		newdisp = (u8 *) src + (s64) insn.displacement.value -
-			  (u8 *) dest;
+		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
 		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
 		disp = (u8 *) dest + insn_offset_displacement(&insn);
 		*(s32 *) disp = (s32) newdisp;
@@ -349,18 +363,20 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
 
 static void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
+	/* Copy an instruction with recovering if other optprobe modifies it.*/
+	__copy_instruction(p->ainsn.insn, p->addr);
+
 	/*
-	 * Copy an instruction without recovering int3, because it will be
-	 * put by another subsystem.
+	 * __copy_instruction can modify the displacement of the instruction,
+	 * but it doesn't affect boostable check.
 	 */
-	__copy_instruction(p->ainsn.insn, p->addr, 0);
-
-	if (can_boost(p->addr))
+	if (can_boost(p->ainsn.insn))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
 
-	p->opcode = *p->addr;
+	/* Also, displacement change doesn't affect the first byte */
+	p->opcode = p->ainsn.insn[0];
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -442,8 +458,8 @@ static void __kprobes restore_btf(void)
 	}
 }
 
-void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
-				      struct pt_regs *regs)
+void __kprobes
+arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long *sara = stack_addr(regs);
 
@@ -453,16 +469,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
 
-#ifdef CONFIG_OPTPROBES
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter);
-#else
-#define setup_detour_execution(p, regs, reenter) (0)
-#endif
-
-static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
-				       struct kprobe_ctlblk *kcb, int reenter)
+static void __kprobes
+setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
 {
 	if (setup_detour_execution(p, regs, reenter))
 		return;
@@ -504,8 +512,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
  * within the handler. We save the original kprobes variables and just single
  * step on the instruction of the new probe without calling any user handlers.
  */
-static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
-				    struct kprobe_ctlblk *kcb)
+static int __kprobes
+reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
@@ -600,69 +608,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax. */	\
-	"	subq $24, %rsp\n"	\
-	"	pushq %rdi\n"		\
-	"	pushq %rsi\n"		\
-	"	pushq %rdx\n"		\
-	"	pushq %rcx\n"		\
-	"	pushq %rax\n"		\
-	"	pushq %r8\n"		\
-	"	pushq %r9\n"		\
-	"	pushq %r10\n"		\
-	"	pushq %r11\n"		\
-	"	pushq %rbx\n"		\
-	"	pushq %rbp\n"		\
-	"	pushq %r12\n"		\
-	"	pushq %r13\n"		\
-	"	pushq %r14\n"		\
-	"	pushq %r15\n"
-#define RESTORE_REGS_STRING		\
-	"	popq %r15\n"		\
-	"	popq %r14\n"		\
-	"	popq %r13\n"		\
-	"	popq %r12\n"		\
-	"	popq %rbp\n"		\
-	"	popq %rbx\n"		\
-	"	popq %r11\n"		\
-	"	popq %r10\n"		\
-	"	popq %r9\n"		\
-	"	popq %r8\n"		\
-	"	popq %rax\n"		\
-	"	popq %rcx\n"		\
-	"	popq %rdx\n"		\
-	"	popq %rsi\n"		\
-	"	popq %rdi\n"		\
-	/* Skip orig_ax, ip, cs */	\
-	"	addq $24, %rsp\n"
-#else
-#define SAVE_REGS_STRING		\
-	/* Skip cs, ip, orig_ax and gs. */	\
-	"	subl $16, %esp\n"	\
-	"	pushl %fs\n"		\
-	"	pushl %es\n"		\
-	"	pushl %ds\n"		\
-	"	pushl %eax\n"		\
-	"	pushl %ebp\n"		\
-	"	pushl %edi\n"		\
-	"	pushl %esi\n"		\
-	"	pushl %edx\n"		\
-	"	pushl %ecx\n"		\
-	"	pushl %ebx\n"
-#define RESTORE_REGS_STRING		\
-	"	popl %ebx\n"		\
-	"	popl %ecx\n"		\
-	"	popl %edx\n"		\
-	"	popl %esi\n"		\
-	"	popl %edi\n"		\
-	"	popl %ebp\n"		\
-	"	popl %eax\n"		\
-	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
-	"	addl $24, %esp\n"
-#endif
-
 /*
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
@@ -816,8 +761,8 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
  * jump instruction after the copied instruction, that jumps to the next
  * instruction after the probepoint.
  */
-static void __kprobes resume_execution(struct kprobe *p,
-		struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static void __kprobes
+resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
 	unsigned long *tos = stack_addr(regs);
 	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@@ -996,8 +941,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 /*
  * Wrapper routine for handling exceptions.
  */
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-				       unsigned long val, void *data)
+int __kprobes
+kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct die_args *args = data;
 	int ret = NOTIFY_DONE;
@@ -1107,466 +1052,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-
-#ifdef CONFIG_OPTPROBES
-
-/* Insert a call instruction at address 'from', which calls address 'to'.*/
-static void __kprobes synthesize_relcall(void *from, void *to)
-{
-	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
-}
-
-/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
-static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
-					  unsigned long val)
-{
-#ifdef CONFIG_X86_64
-	*addr++ = 0x48;
-	*addr++ = 0xbf;
-#else
-	*addr++ = 0xb8;
-#endif
-	*(unsigned long *)addr = val;
-}
-
-static void __used __kprobes kprobes_optinsn_template_holder(void)
-{
-	asm volatile (
-			".global optprobe_template_entry\n"
-			"optprobe_template_entry: \n"
-#ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rsi\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			/* Move flags to rsp */
-			"	movq 144(%rsp), %rdx\n"
-			"	movq %rdx, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			/* Skip flags entry */
-			"	addq $8, %rsp\n"
-			"	popfq\n"
-#else /* CONFIG_X86_32 */
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %edx\n"
-			".global optprobe_template_val\n"
-			"optprobe_template_val: \n"
-			ASM_NOP5
-			".global optprobe_template_call\n"
-			"optprobe_template_call: \n"
-			ASM_NOP5
-			RESTORE_REGS_STRING
-			"	addl $4, %esp\n"	/* skip cs */
-			"	popf\n"
-#endif
-			".global optprobe_template_end\n"
-			"optprobe_template_end: \n");
-}
-
-#define TMPL_MOVE_IDX \
-	((long)&optprobe_template_val - (long)&optprobe_template_entry)
-#define TMPL_CALL_IDX \
-	((long)&optprobe_template_call - (long)&optprobe_template_entry)
-#define TMPL_END_IDX \
-	((long)&optprobe_template_end - (long)&optprobe_template_entry)
-
-#define INT3_SIZE sizeof(kprobe_opcode_t)
-
-/* Optimized kprobe call back function: called from optinsn */
-static void __kprobes optimized_callback(struct optimized_kprobe *op,
-					 struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long flags;
-
-	/* This is possible if op is under delayed unoptimizing */
-	if (kprobe_disabled(&op->kp))
-		return;
-
-	local_irq_save(flags);
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(&op->kp);
-	} else {
-		/* Save skipped registers */
-#ifdef CONFIG_X86_64
-		regs->cs = __KERNEL_CS;
-#else
-		regs->cs = __KERNEL_CS | get_kernel_rpl();
-		regs->gs = 0;
-#endif
-		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
-		regs->orig_ax = ~0UL;
-
-		__this_cpu_write(current_kprobe, &op->kp);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		opt_pre_handler(&op->kp, regs);
-		__this_cpu_write(current_kprobe, NULL);
-	}
-	local_irq_restore(flags);
-}
-
-static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
-{
-	int len = 0, ret;
-
-	while (len < RELATIVEJUMP_SIZE) {
-		ret = __copy_instruction(dest + len, src + len, 1);
-		if (!ret || !can_boost(dest + len))
-			return -EINVAL;
-		len += ret;
-	}
-	/* Check whether the address range is reserved */
-	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1) ||
-	    jump_label_text_reserved(src, src + len - 1))
-		return -EBUSY;
-
-	return len;
-}
-
-/* Check whether insn is indirect jump */
-static int __kprobes insn_is_indirect_jump(struct insn *insn)
-{
-	return ((insn->opcode.bytes[0] == 0xff &&
-		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
-		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
-}
-
-/* Check whether insn jumps into specified address range */
-static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
-{
-	unsigned long target = 0;
-
-	switch (insn->opcode.bytes[0]) {
-	case 0xe0:	/* loopne */
-	case 0xe1:	/* loope */
-	case 0xe2:	/* loop */
-	case 0xe3:	/* jcxz */
-	case 0xe9:	/* near relative jump */
-	case 0xeb:	/* short relative jump */
-		break;
-	case 0x0f:
-		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
-			break;
-		return 0;
-	default:
-		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
-			break;
-		return 0;
-	}
-	target = (unsigned long)insn->next_byte + insn->immediate.value;
-
-	return (start <= target && target <= start + len);
-}
-
-/* Decode whole function to ensure any instructions don't jump into target */
-static int __kprobes can_optimize(unsigned long paddr)
-{
-	int ret;
-	unsigned long addr, size = 0, offset = 0;
-	struct insn insn;
-	kprobe_opcode_t buf[MAX_INSN_SIZE];
-
-	/* Lookup symbol including addr */
-	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
-		return 0;
-
-	/*
-	 * Do not optimize in the entry code due to the unstable
-	 * stack handling.
-	 */
-	if ((paddr >= (unsigned long )__entry_text_start) &&
-	    (paddr <  (unsigned long )__entry_text_end))
-		return 0;
-
-	/* Check there is enough space for a relative jump. */
-	if (size - offset < RELATIVEJUMP_SIZE)
-		return 0;
-
-	/* Decode instructions */
-	addr = paddr - offset;
-	while (addr < paddr - offset + size) { /* Decode until function end */
-		if (search_exception_tables(addr))
-			/*
-			 * Since some fixup code will jumps into this function,
-			 * we can't optimize kprobe in this function.
-			 */
-			return 0;
-		kernel_insn_init(&insn, (void *)addr);
-		insn_get_opcode(&insn);
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
-			ret = recover_probed_instruction(buf, addr);
-			if (ret)
-				return 0;
-			kernel_insn_init(&insn, buf);
-		}
-		insn_get_length(&insn);
-		/* Recover address */
-		insn.kaddr = (void *)addr;
-		insn.next_byte = (void *)(addr + insn.length);
-		/* Check any instructions don't jump into target */
-		if (insn_is_indirect_jump(&insn) ||
-		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
-					 RELATIVE_ADDR_SIZE))
-			return 0;
-		addr += insn.length;
-	}
-
-	return 1;
-}
-
-/* Check optimized_kprobe can actually be optimized. */
-int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
-{
-	int i;
-	struct kprobe *p;
-
-	for (i = 1; i < op->optinsn.size; i++) {
-		p = get_kprobe(op->kp.addr + i);
-		if (p && !kprobe_disabled(p))
-			return -EEXIST;
-	}
-
-	return 0;
-}
-
-/* Check the addr is within the optimized instructions. */
-int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op,
-					   unsigned long addr)
-{
-	return ((unsigned long)op->kp.addr <= addr &&
-		(unsigned long)op->kp.addr + op->optinsn.size > addr);
-}
-
-/* Free optimized instruction slot */
-static __kprobes
-void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
-{
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
-		op->optinsn.insn = NULL;
-		op->optinsn.size = 0;
-	}
-}
-
-void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
-{
-	__arch_remove_optimized_kprobe(op, 1);
-}
-
-/*
- * Copy replacing target instructions
- * Target instructions MUST be relocatable (checked inside)
- */
-int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
-{
-	u8 *buf;
-	int ret;
-	long rel;
-
-	if (!can_optimize((unsigned long)op->kp.addr))
-		return -EILSEQ;
-
-	op->optinsn.insn = get_optinsn_slot();
-	if (!op->optinsn.insn)
-		return -ENOMEM;
-
-	/*
-	 * Verify if the address gap is in 2GB range, because this uses
-	 * a relative jump.
-	 */
-	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
-	if (abs(rel) > 0x7fffffff)
-		return -ERANGE;
-
-	buf = (u8 *)op->optinsn.insn;
-
-	/* Copy instructions into the out-of-line buffer */
-	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
-	if (ret < 0) {
-		__arch_remove_optimized_kprobe(op, 0);
-		return ret;
-	}
-	op->optinsn.size = ret;
-
-	/* Copy arch-dep-instance from template */
-	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
-
-	/* Set probe information */
-	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
-
-	/* Set probe function call */
-	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
-
-	/* Set returning jmp instruction at the tail of out-of-line buffer */
-	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
-			   (u8 *)op->kp.addr + op->optinsn.size);
-
-	flush_icache_range((unsigned long) buf,
-			   (unsigned long) buf + TMPL_END_IDX +
-			   op->optinsn.size + RELATIVEJUMP_SIZE);
-	return 0;
-}
-
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-	u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-					    u8 *insn_buf,
-					    struct optimized_kprobe *op)
-{
-	s32 rel = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-	/* Backup instructions which will be replaced by jump address */
-	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-	       RELATIVE_ADDR_SIZE);
-
-	insn_buf[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&insn_buf[1]) = rel;
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Replace breakpoints (int3) with relative jumps.
- * Caller must call with locking kprobe_mutex and text_mutex.
- */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		WARN_ON(kprobe_disabled(&op->kp));
-		/* Setup param */
-		setup_optimize_kprobe(&jump_poke_params[c],
-				      jump_poke_bufs[c].buf, op);
-		list_del_init(&op->list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-					      u8 *insn_buf,
-					      struct optimized_kprobe *op)
-{
-	/* Set int3 to first byte for kprobes */
-	insn_buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
-/*
- * Recover original instructions and breakpoints from relative jumps.
- * Caller must call with locking kprobe_mutex.
- */
-extern void arch_unoptimize_kprobes(struct list_head *oplist,
-				    struct list_head *done_list)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		/* Setup param */
-		setup_unoptimize_kprobe(&jump_poke_params[c],
-					jump_poke_bufs[c].buf, op);
-		list_move(&op->list, done_list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
-	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-	u8 buf[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
-}
-
-static int  __kprobes setup_detour_execution(struct kprobe *p,
-					     struct pt_regs *regs,
-					     int reenter)
-{
-	struct optimized_kprobe *op;
-
-	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
-		/* This kprobe is really able to run optimized path. */
-		op = container_of(p, struct optimized_kprobe, kp);
-		/* Detour through copied instructions */
-		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
-		if (!reenter)
-			reset_current_kprobe();
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
-static int __kprobes init_poke_params(void)
-{
-	/* Allocate code buffer and parameter array */
-	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_bufs)
-		return -ENOMEM;
-
-	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_params) {
-		kfree(jump_poke_bufs);
-		jump_poke_bufs = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-#else	/* !CONFIG_OPTPROBES */
-static int __kprobes init_poke_params(void)
-{
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
-	return init_poke_params();
+	return arch_init_optprobes();
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)