[PATCH 00/13 -next] [For linux-next] tracing: Review of changes

[PATCH 00/13 -next] [For linux-next] tracing: Review of changes

[Steven Rostedt]

I'm posting these as a generic review of the changes I'll be pushing
into linux-next and will be pushing this for 3.9.

These patches have passed a series of tests I've run on few machines
with several different configs and such.

You can find the patches here. I'll add these to linux-next tomorrow.

-- Steve

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
tip/perf/core

Head SHA1: a701a1b03bf36d4e31c9fd036a96bde5a11cd5ce


Fengguang Wu (1):
      tracing/syscalls: Make local functions static

Hiraku Toyooka (1):
      tracing: Add checks if tr->buffer is NULL in tracing_reset{_online_cpus}

Jovi Zhang (1):
      tracing: Verify target file before registering a uprobe event

Masami Hiramatsu (3):
      ftrace: Move ARCH_SUPPORTS_FTRACE_SAVE_REGS in Kconfig
      kprobes/x86: Move ftrace-based kprobe code into kprobes-ftrace.c
      kprobes/x86: Move kprobes stuff under arch/x86/kernel/kprobes/

Shan Wei (1):
      tracing: Use this_cpu_ptr per-cpu helper

Steven Rostedt (6):
      tracing: Fix sparse warning with is_signed_type() macro
      ring-buffer: Remove unnecessary recusive call in rb_advance_iter()
      tracing: Remove unneeded check of max_tr->buffer before tracing_reset
      tracing/lockdep: Disable lockdep first in entering NMI
      tracing/fgraph: Add max_graph_depth to limit function_graph depth
      tracing: Remove the extra 4 bytes of padding in events

----
 arch/Kconfig                         |   12 +
 arch/x86/Kconfig                     |    2 +
 arch/x86/include/asm/ftrace.h        |    1 -
 arch/x86/kernel/Makefile             |    3 +-
 arch/x86/kernel/kprobes-common.h     |  102 ---
 arch/x86/kernel/kprobes-opt.c        |  512 ---------------
 arch/x86/kernel/kprobes.c            | 1130 ----------------------------------
 arch/x86/kernel/kprobes/Makefile     |    7 +
 arch/x86/kernel/kprobes/common.h     |  113 ++++
 arch/x86/kernel/kprobes/core.c       | 1064 ++++++++++++++++++++++++++++++++
 arch/x86/kernel/kprobes/ftrace.c     |   93 +++
 arch/x86/kernel/kprobes/opt.c        |  512 +++++++++++++++
 include/linux/ftrace.h               |    6 +-
 include/linux/ftrace_event.h         |    3 +-
 include/linux/hardirq.h              |    4 +-
 include/linux/kprobes.h              |   12 +-
 kernel/kprobes.c                     |    8 +-
 kernel/trace/Kconfig                 |    8 +
 kernel/trace/blktrace.c              |    2 +-
 kernel/trace/ftrace.c                |    6 +-
 kernel/trace/ring_buffer.c           |    2 +-
 kernel/trace/trace.c                 |   15 +-
 kernel/trace/trace_events.c          |    1 -
 kernel/trace/trace_functions_graph.c |   60 +-
 kernel/trace/trace_selftest.c        |    2 +-
 kernel/trace/trace_syscalls.c        |   18 +-
 kernel/trace/trace_uprobe.c          |    6 +-
 27 files changed, 1909 insertions(+), 1795 deletions(-)

[PATCH 01/13 -next] tracing: Fix sparse warning with is_signed_type() macro

[Steven Rostedt]

[-- Attachment #1: 0001-tracing-Fix-sparse-warning-with-is_signed_type-macro.patch --]
[-- Type: text/plain, Size: 1406 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Sparse complains when is_signed_type() is used on a pointer.
This macro is needed for the format output used for ftrace
and perf, to know if a binary field is a signed type or not.
The is_signed_type() macro is used against all fields that are
recorded by events to automate the operation.

The problem sparse has is with the current way is_signed_type()
works:

  ((type)-1 < 0)

If "type" is a poiner, than sparse does not like it being compared
to an integer (zero). The simple fix is to just give zero the
same type. The runtime result stays the same.

Reported-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index a3d4895..43ef8b6 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -272,7 +272,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 extern int trace_add_event_call(struct ftrace_event_call *call);
 extern void trace_remove_event_call(struct ftrace_event_call *call);
 
-#define is_signed_type(type)	(((type)(-1)) < 0)
+#define is_signed_type(type)	(((type)(-1)) < (type)0)
 
 int trace_set_clr_event(const char *system, const char *event, int set);
 
-- 
1.7.10.4

[PATCH 02/13 -next] ring-buffer: Remove unnecessary recusive call in rb_advance_iter()

[Steven Rostedt]

[-- Attachment #1: 0002-ring-buffer-Remove-unnecessary-recusive-call-in-rb_a.patch --]
[-- Type: text/plain, Size: 1263 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

The original ring-buffer code had special checks at the start
of rb_advance_iter() and instead of repeating them again at the
end of the function if a certain condition existed, I just did
a recursive call to rb_advance_iter() because the special condition
would cause rb_advance_iter() to return early (after the checks).

But as things have changed, the special checks no longer exist
and the only thing done for the special_condition is to call
rb_inc_iter() and return. Instead of doing a confusing recursive call,
just call rb_inc_iter instead.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ce8514f..6ff9cc4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3425,7 +3425,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	/* check for end of page padding */
 	if ((iter->head >= rb_page_size(iter->head_page)) &&
 	    (iter->head_page != cpu_buffer->commit_page))
-		rb_advance_iter(iter);
+		rb_inc_iter(iter);
 }
 
 static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
-- 
1.7.10.4

[PATCH 03/13 -next] tracing: Use this_cpu_ptr per-cpu helper

[Steven Rostedt]

[-- Attachment #1: 0003-tracing-Use-this_cpu_ptr-per-cpu-helper.patch --]
[-- Type: text/plain, Size: 1833 bytes --]

From: Shan Wei <davidshan@tencent.com>

typeof(&buffer) is a pointer to array of 1024 char, or char (*)[1024].
But, typeof(&buffer[0]) is a pointer to char which match the return type of get_trace_buf().
As well-known, the value of &buffer is equal to &buffer[0].
so return this_cpu_ptr(&percpu_buffer->buffer[0]) can avoid type cast.

Link: http://lkml.kernel.org/r/50A1A800.3020102@gmail.com

Reviewed-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Shan Wei <davidshan@tencent.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/blktrace.c |    2 +-
 kernel/trace/trace.c    |    5 +----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c0bd030..71259e2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -147,7 +147,7 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 		return;
 
 	local_irq_save(flags);
-	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+	buf = this_cpu_ptr(bt->msg_data);
 	va_start(args, fmt);
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3c13e46..f8b7c62 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1517,7 +1517,6 @@ static struct trace_buffer_struct *trace_percpu_nmi_buffer;
 static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *percpu_buffer;
-	struct trace_buffer_struct *buffer;
 
 	/*
 	 * If we have allocated per cpu buffers, then we do not
@@ -1535,9 +1534,7 @@ static char *get_trace_buf(void)
 	if (!percpu_buffer)
 		return NULL;
 
-	buffer = per_cpu_ptr(percpu_buffer, smp_processor_id());
-
-	return buffer->buffer;
+	return this_cpu_ptr(&percpu_buffer->buffer[0]);
 }
 
 static int alloc_percpu_trace_buffer(void)
-- 
1.7.10.4

[PATCH 04/13 -next] tracing: Verify target file before registering a uprobe event

[Steven Rostedt]

[-- Attachment #1: 0004-tracing-Verify-target-file-before-registering-a-upro.patch --]
[-- Type: text/plain, Size: 1406 bytes --]

From: Jovi Zhang <bookjovi@gmail.com>

Without this patch, we can register a uprobe event for a directory.
Enabling such a uprobe event would anyway fail.

Example:
$ echo 'p /bin:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events

However dirctories cannot be valid targets for uprobe.
Hence verify if the target is a regular file during the probe
registration.

Link: http://lkml.kernel.org/r/20130103004212.690763002@goodmis.org

Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jovi Zhang <bookjovi@gmail.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
[ cleaned up whitespace and removed redundant IS_DIR() check ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_uprobe.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c86e6d4..87b6db4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -258,6 +258,10 @@ static int create_trace_uprobe(int argc, char **argv)
 		goto fail_address_parse;
 
 	inode = igrab(path.dentry->d_inode);
+	if (!S_ISREG(inode->i_mode)) {
+		ret = -EINVAL;
+		goto fail_address_parse;
+	}
 
 	argc -= 2;
 	argv += 2;
@@ -356,7 +360,7 @@ fail_address_parse:
 	if (inode)
 		iput(inode);
 
-	pr_info("Failed to parse address.\n");
+	pr_info("Failed to parse address or file.\n");
 
 	return ret;
 }
-- 
1.7.10.4

[PATCH 05/13 -next] tracing/syscalls: Make local functions static

[Steven Rostedt]

[-- Attachment #1: 0005-tracing-syscalls-Make-local-functions-static.patch --]
[-- Type: text/plain, Size: 3125 bytes --]

From: Fengguang Wu <fengguang.wu@intel.com>

Some functions in the syscall tracing is used only locally to
the file, but they are labeled global. Convert them to static functions.

Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_syscalls.c |   18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7609dd6..5329e13e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -77,7 +77,7 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
 	return syscalls_metadata[nr];
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags,
 		    struct trace_event *event)
 {
@@ -130,7 +130,7 @@ end:
 	return TRACE_TYPE_HANDLED;
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_exit(struct trace_iterator *iter, int flags,
 		   struct trace_event *event)
 {
@@ -270,7 +270,7 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
@@ -305,7 +305,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
@@ -337,7 +337,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -356,7 +356,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
 	return ret;
 }
 
-void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -371,7 +371,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -390,7 +390,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
 	return ret;
 }
 
-void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -459,7 +459,7 @@ unsigned long __init __weak arch_syscall_addr(int nr)
 	return (unsigned long)sys_call_table[nr];
 }
 
-int __init init_ftrace_syscalls(void)
+static int __init init_ftrace_syscalls(void)
 {
 	struct syscall_metadata *meta;
 	unsigned long addr;
-- 
1.7.10.4

[PATCH 06/13 -next] tracing: Add checks if tr->buffer is NULL in tracing_reset{_online_cpus}

[Steven Rostedt]

[-- Attachment #1: 0006-tracing-Add-checks-if-tr-buffer-is-NULL-in-tracing_r.patch --]
[-- Type: text/plain, Size: 1294 bytes --]

From: Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>

max_tr->buffer could be NULL in the tracing_reset{_online_cpus}. In this
case, a NULL pointer dereference happens, so we should return immediately
from these functions.

Note, the current code does not call tracing_reset*() with max_tr when
its buffer is NULL, but future code will. This patch is needed to prevent
the future code from crashing.

Link: http://lkml.kernel.org/r/20121219070234.31200.93863.stgit@liselsia

Signed-off-by: Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |    6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f8b7c62..72b171b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -922,6 +922,9 @@ void tracing_reset(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer *buffer = tr->buffer;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
@@ -936,6 +939,9 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
-- 
1.7.10.4

[PATCH 07/13 -next] tracing: Remove unneeded check of max_tr->buffer before tracing_reset

[Steven Rostedt]

[-- Attachment #1: 0007-tracing-Remove-unneeded-check-of-max_tr-buffer-befor.patch --]
[-- Type: text/plain, Size: 838 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

There's now a check in tracing_reset_online_cpus() if the buffer is
allocated or NULL. No need to do a check before calling it with max_tr.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 72b171b..d62248d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4040,8 +4040,7 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 	 * Reset the buffer so that it doesn't have incomparable timestamps.
 	 */
 	tracing_reset_online_cpus(&global_trace);
-	if (max_tr.buffer)
-		tracing_reset_online_cpus(&max_tr);
+	tracing_reset_online_cpus(&max_tr);
 
 	mutex_unlock(&trace_types_lock);
 
-- 
1.7.10.4

[PATCH 08/13 -next] tracing/lockdep: Disable lockdep first in entering NMI

[Steven Rostedt]

[-- Attachment #1: 0008-tracing-lockdep-Disable-lockdep-first-in-entering-NM.patch --]
[-- Type: text/plain, Size: 2070 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

When function tracing with either debug locks enabled or tracing
preempt disabled, the add_preempt_count() is traced. This is an
issue with lockdep and function tracing. As function tracing
can disable interrupts, and lockdep records that change,
lockdep may not be able to handle this recursion if it happens from
an NMI context.

The first thing that an NMI does is:

 #define nmi_enter()					\
	do {							\
		ftrace_nmi_enter();				\
		BUG_ON(in_nmi());				\
		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
		lockdep_off();					\
		rcu_nmi_enter();				\
		trace_hardirq_enter();				\
	} while (0)

When the add_preempt_count() is traced, and the tracing callback
disables interrupts, it will jump into the lockdep code. There's
some places in lockdep that can't handle this re-entrance, and
causes lockdep to fail.

As the lockdep_off() (and lockdep_on) is a simple:

void lockdep_off(void)
{
	current->lockdep_recursion++;
}

and is never traced, it can be called first in nmi_enter()
and lockdep_on() last in nmi_exit().

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/hardirq.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 624ef3f..57bfdce 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -180,10 +180,10 @@ extern void irq_exit(void);
 
 #define nmi_enter()						\
 	do {							\
+		lockdep_off();					\
 		ftrace_nmi_enter();				\
 		BUG_ON(in_nmi());				\
 		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
-		lockdep_off();					\
 		rcu_nmi_enter();				\
 		trace_hardirq_enter();				\
 	} while (0)
@@ -192,10 +192,10 @@ extern void irq_exit(void);
 	do {							\
 		trace_hardirq_exit();				\
 		rcu_nmi_exit();					\
-		lockdep_on();					\
 		BUG_ON(!in_nmi());				\
 		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
+		lockdep_on();					\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
-- 
1.7.10.4

[PATCH 09/13 -next] tracing/fgraph: Add max_graph_depth to limit function_graph depth

[Steven Rostedt]

[-- Attachment #1: 0009-tracing-fgraph-Add-max_graph_depth-to-limit-function.patch --]
[-- Type: text/plain, Size: 3121 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Add the file max_graph_depth to the debug tracing directory that lets
the user define the depth of the function graph.

A very useful operation is to set the depth to 1. Then it traces only
the first function that is called when entering the kernel. This can
be used to determine what system operations interrupt a process.

For example, to work on NOHZ processes (single tasks running without
a timer tick), if any interrupt goes off and preempts that task, this
code will show it happening.

  # cd /sys/kernel/debug/tracing
  # echo 1 > max_graph_depth
  # echo function_graph > current_tracer
  # cat per_cpu/cpu/<cpu-of-process>/trace

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c |   60 ++++++++++++++++++++++++++++++++--
 1 file changed, 58 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4edb4b7..7008d2e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -47,6 +47,8 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_ABS_TIME	0x20
 #define TRACE_GRAPH_PRINT_IRQS		0x40
 
+static unsigned int max_depth;
+
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
 	{ TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
@@ -250,8 +252,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
-	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
-	      ftrace_graph_ignore_irqs())
+	if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
+	     ftrace_graph_ignore_irqs()) ||
+	    (max_depth && trace->depth >= max_depth))
 		return 0;
 
 	local_irq_save(flags);
@@ -1457,6 +1460,59 @@ static struct tracer graph_trace __read_mostly = {
 #endif
 };
 
+
+static ssize_t
+graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	max_depth = val;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt,
+		 loff_t *ppos)
+{
+	char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/
+	int n;
+
+	n = sprintf(buf, "%d\n", max_depth);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, n);
+}
+
+static const struct file_operations graph_depth_fops = {
+	.open		= tracing_open_generic,
+	.write		= graph_depth_write,
+	.read		= graph_depth_read,
+	.llseek		= generic_file_llseek,
+};
+
+static __init int init_graph_debugfs(void)
+{
+	struct dentry *d_tracer;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	trace_create_file("max_graph_depth", 0644, d_tracer,
+			  NULL, &graph_depth_fops);
+
+	return 0;
+}
+fs_initcall(init_graph_debugfs);
+
 static __init int init_graph_trace(void)
 {
 	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
-- 
1.7.10.4

[PATCH 10/13 -next] ftrace: Move ARCH_SUPPORTS_FTRACE_SAVE_REGS in Kconfig

[Steven Rostedt]

[-- Attachment #1: 0010-ftrace-Move-ARCH_SUPPORTS_FTRACE_SAVE_REGS-in-Kconfi.patch --]
[-- Type: text/plain, Size: 5573 bytes --]

From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>

Move SAVE_REGS support flag into Kconfig and rename
it to CONFIG_DYNAMIC_FTRACE_WITH_REGS. This also introduces
CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS which indicates
the architecture depending part of ftrace has a code
that saves full registers.
On the other hand, CONFIG_DYNAMIC_FTRACE_WITH_REGS indicates
the code is enabled.

Link: http://lkml.kernel.org/r/20120928081516.3560.72534.stgit@ltc138.sdl.hitachi.co.jp

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/Kconfig              |    1 +
 arch/x86/include/asm/ftrace.h |    1 -
 include/linux/ftrace.h        |    6 +++---
 kernel/trace/Kconfig          |    8 ++++++++
 kernel/trace/ftrace.c         |    6 +++---
 kernel/trace/trace_selftest.c |    2 +-
 6 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 79795af..996ccec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -44,6 +44,7 @@ config X86
 	select HAVE_FENTRY if X86_64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9a25b52..86cb51e 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -44,7 +44,6 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
-#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 92691d8..e5ca8ef 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -74,7 +74,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  * SAVE_REGS - The ftrace_ops wants regs saved at each function called
  *            and passed to the callback. If this flag is set, but the
  *            architecture does not support passing regs
- *            (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the
+ *            (CONFIG_DYNAMIC_FTRACE_WITH_REGS is not defined), then the
  *            ftrace_ops will fail to register, unless the next flag
  *            is set.
  * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the
@@ -418,7 +418,7 @@ void ftrace_modify_all_code(int command);
 #endif
 
 #ifndef FTRACE_REGS_ADDR
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 # define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
 #else
 # define FTRACE_REGS_ADDR FTRACE_ADDR
@@ -480,7 +480,7 @@ extern int ftrace_make_nop(struct module *mod,
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
  * @rec: the mcount call site record
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5d89335..cdc9d28 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -39,6 +39,9 @@ config HAVE_DYNAMIC_FTRACE
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_DYNAMIC_FTRACE_WITH_REGS
+	bool
+
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
 	help
@@ -434,6 +437,11 @@ config DYNAMIC_FTRACE
 	  were made. If so, it runs stop_machine (stops all CPUS)
 	  and modifies the code to jump over the call to ftrace.
 
+config DYNAMIC_FTRACE_WITH_REGS
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
+
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 41473b4..6e34dc1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -337,7 +337,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
 		return -EINVAL;
 
-#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	/*
 	 * If the ftrace_ops specifies SAVE_REGS, then it only can be used
 	 * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set.
@@ -4143,8 +4143,8 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
  * Archs are to support both the regs and ftrace_ops at the same time.
  * If they support ftrace_ops, it is assumed they support regs.
  * If call backs want to use regs, they must either check for regs
- * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS.
- * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved.
+ * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS.
+ * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
  * set the ARCH_SUPPORT_FTARCE_OPS.
  */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 4762316..6c62d58 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -568,7 +568,7 @@ trace_selftest_function_regs(void)
 	int ret;
 	int supported = 0;
 
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	supported = 1;
 #endif
 
-- 
1.7.10.4

[PATCH 11/13 -next] kprobes/x86: Move ftrace-based kprobe code into kprobes-ftrace.c

[Steven Rostedt]

[-- Attachment #1: 0011-kprobes-x86-Move-ftrace-based-kprobe-code-into-kprob.patch --]
[-- Type: text/plain, Size: 11708 bytes --]

From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>

Split ftrace-based kprobes code from kprobes, and introduce
CONFIG_(HAVE_)KPROBES_ON_FTRACE Kconfig flags.
For the cleanup reason, this also moves kprobe_ftrace check
into skip_singlestep.

Link: http://lkml.kernel.org/r/20120928081520.3560.25624.stgit@ltc138.sdl.hitachi.co.jp

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/Kconfig                     |   12 +++++
 arch/x86/Kconfig                 |    1 +
 arch/x86/kernel/Makefile         |    1 +
 arch/x86/kernel/kprobes-common.h |   11 +++++
 arch/x86/kernel/kprobes-ftrace.c |   93 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/kprobes.c        |   70 +---------------------------
 include/linux/kprobes.h          |   12 +----
 kernel/kprobes.c                 |    8 ++--
 8 files changed, 125 insertions(+), 83 deletions(-)
 create mode 100644 arch/x86/kernel/kprobes-ftrace.c

diff --git a/arch/Kconfig b/arch/Kconfig
index 7f8f281..97fb7d0 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -76,6 +76,15 @@ config OPTPROBES
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
 
+config KPROBES_ON_FTRACE
+	def_bool y
+	depends on KPROBES && HAVE_KPROBES_ON_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	help
+	 If function tracer is enabled and the arch supports full
+	 passing of pt_regs to function tracing, then kprobes can
+	 optimize on top of function tracing.
+
 config UPROBES
 	bool "Transparent user-space probes (EXPERIMENTAL)"
 	depends on UPROBE_EVENT && PERF_EVENTS
@@ -158,6 +167,9 @@ config HAVE_KRETPROBES
 config HAVE_OPTPROBES
 	bool
 
+config HAVE_KPROBES_ON_FTRACE
+	bool
+
 config HAVE_NMI_WATCHDOG
 	bool
 #
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 996ccec..be8b2b3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -40,6 +40,7 @@ config X86
 	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
+	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FENTRY if X86_64
 	select HAVE_C_RECORDMCOUNT
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 34e923a..cc5d31f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= kprobes-ftrace.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h
index 3230b68..2e9d4b5 100644
--- a/arch/x86/kernel/kprobes-common.h
+++ b/arch/x86/kernel/kprobes-common.h
@@ -99,4 +99,15 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 	return addr;
 }
 #endif
+
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			   struct kprobe_ctlblk *kcb);
+#else
+static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				  struct kprobe_ctlblk *kcb)
+{
+	return 0;
+}
+#endif
 #endif
diff --git a/arch/x86/kernel/kprobes-ftrace.c b/arch/x86/kernel/kprobes-ftrace.c
new file mode 100644
index 0000000..70a81c7
--- /dev/null
+++ b/arch/x86/kernel/kprobes-ftrace.c
@@ -0,0 +1,93 @@
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+#include "kprobes-common.h"
+
+static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
+{
+	/*
+	 * Emulate singlestep (and also recover regs->ip)
+	 * as if there is a 5byte nop
+	 */
+	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+	if (unlikely(p->post_handler)) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+	__this_cpu_write(current_kprobe, NULL);
+	return 1;
+}
+
+int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			      struct kprobe_ctlblk *kcb)
+{
+	if (kprobe_ftrace(p))
+		return __skip_singlestep(p, regs, kcb);
+	else
+		return 0;
+}
+
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+				     struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+	unsigned long flags;
+
+	/* Disable irq for emulating a breakpoint and avoiding preempt */
+	local_irq_save(flags);
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		goto end;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+		regs->ip = ip + sizeof(kprobe_opcode_t);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			__skip_singlestep(p, regs, kcb);
+		/*
+		 * If pre_handler returns !0, it sets regs->ip and
+		 * resets current kprobe.
+		 */
+	}
+end:
+	local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.insn = NULL;
+	p->ainsn.boostable = -1;
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 57916c0..18114bf 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -541,23 +541,6 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
 	return 1;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				      struct kprobe_ctlblk *kcb)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-}
-#endif
-
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled throughout this function.
@@ -616,13 +599,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	} else if (kprobe_running()) {
 		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
-#ifdef KPROBES_CAN_USE_FTRACE
-			if (kprobe_ftrace(p)) {
-				skip_singlestep(p, regs, kcb);
-				return 1;
-			}
-#endif
-			setup_singlestep(p, regs, kcb, 0);
+			if (!skip_singlestep(p, regs, kcb))
+				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
 	} /* else: not a kprobe fault; let the kernel handle it */
@@ -1075,50 +1053,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-/* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
-{
-	struct kprobe *p;
-	struct kprobe_ctlblk *kcb;
-	unsigned long flags;
-
-	/* Disable irq for emulating a breakpoint and avoiding preempt */
-	local_irq_save(flags);
-
-	p = get_kprobe((kprobe_opcode_t *)ip);
-	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
-
-	kcb = get_kprobe_ctlblk();
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(p);
-	} else {
-		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
-		regs->ip = ip + sizeof(kprobe_opcode_t);
-
-		__this_cpu_write(current_kprobe, p);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			skip_singlestep(p, regs, kcb);
-		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe.
-		 */
-	}
-end:
-	local_irq_restore(flags);
-}
-
-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
-{
-	p->ainsn.insn = NULL;
-	p->ainsn.boostable = -1;
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
 	return arch_init_optprobes();
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 23755ba..4b6ef4d 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -49,16 +49,6 @@
 #define KPROBE_REENTER		0x00000004
 #define KPROBE_HIT_SSDONE	0x00000008
 
-/*
- * If function tracer is enabled and the arch supports full
- * passing of pt_regs to function tracing, then kprobes can
- * optimize on top of function tracing.
- */
-#if defined(CONFIG_FUNCTION_TRACER) && defined(ARCH_SUPPORTS_FTRACE_SAVE_REGS) \
-	&& defined(ARCH_SUPPORTS_KPROBES_ON_FTRACE)
-# define KPROBES_CAN_USE_FTRACE
-#endif
-
 /* Attach to insert probes on any functions which should be ignored*/
 #define __kprobes	__attribute__((__section__(".kprobes.text")))
 
@@ -316,7 +306,7 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table,
 #endif
 
 #endif /* CONFIG_OPTPROBES */
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct pt_regs *regs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 098f396..f423c3e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -919,7 +919,7 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 }
 #endif /* CONFIG_OPTPROBES */
 
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
 	.func = kprobe_ftrace_handler,
 	.flags = FTRACE_OPS_FL_SAVE_REGS,
@@ -964,7 +964,7 @@ static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
 			   (unsigned long)p->addr, 1, 0);
 	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
 }
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 #define prepare_kprobe(p)	arch_prepare_kprobe(p)
 #define arm_kprobe_ftrace(p)	do {} while (0)
 #define disarm_kprobe_ftrace(p)	do {} while (0)
@@ -1414,12 +1414,12 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p,
 	 */
 	ftrace_addr = ftrace_location((unsigned long)p->addr);
 	if (ftrace_addr) {
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 		/* Given address is not on the instruction boundary */
 		if ((unsigned long)p->addr != ftrace_addr)
 			return -EILSEQ;
 		p->flags |= KPROBE_FLAG_FTRACE;
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 		return -EINVAL;
 #endif
 	}
-- 
1.7.10.4

[PATCH 12/13 -next] kprobes/x86: Move kprobes stuff under arch/x86/kernel/kprobes/

[Steven Rostedt]

[-- Attachment #1: 0012-kprobes-x86-Move-kprobes-stuff-under-arch-x86-kernel.patch --]
[-- Type: text/plain, Size: 110167 bytes --]

From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>

Move arch-dep kprobes stuff under arch/x86/kernel/kprobes.

Link: http://lkml.kernel.org/r/20120928081522.3560.75469.stgit@ltc138.sdl.hitachi.co.jp

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
[ fixed whitespace and s/__attribute__((packed))/__packed/ ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kernel/Makefile         |    4 +-
 arch/x86/kernel/kprobes-common.h |  113 ----
 arch/x86/kernel/kprobes-ftrace.c |   93 ----
 arch/x86/kernel/kprobes-opt.c    |  512 ------------------
 arch/x86/kernel/kprobes.c        | 1064 --------------------------------------
 arch/x86/kernel/kprobes/Makefile |    7 +
 arch/x86/kernel/kprobes/common.h |  113 ++++
 arch/x86/kernel/kprobes/core.c   | 1064 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/kprobes/ftrace.c |   93 ++++
 arch/x86/kernel/kprobes/opt.c    |  512 ++++++++++++++++++
 10 files changed, 1790 insertions(+), 1785 deletions(-)
 delete mode 100644 arch/x86/kernel/kprobes-common.h
 delete mode 100644 arch/x86/kernel/kprobes-ftrace.c
 delete mode 100644 arch/x86/kernel/kprobes-opt.c
 delete mode 100644 arch/x86/kernel/kprobes.c
 create mode 100644 arch/x86/kernel/kprobes/Makefile
 create mode 100644 arch/x86/kernel/kprobes/common.h
 create mode 100644 arch/x86/kernel/kprobes/core.c
 create mode 100644 arch/x86/kernel/kprobes/ftrace.c
 create mode 100644 arch/x86/kernel/kprobes/opt.c

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cc5d31f..ac3b3d0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -65,9 +65,7 @@ obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
-obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
-obj-$(CONFIG_KPROBES_ON_FTRACE)	+= kprobes-ftrace.o
+obj-y				+= kprobes/
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h
deleted file mode 100644
index 2e9d4b5..0000000
--- a/arch/x86/kernel/kprobes-common.h
+++ /dev/null
@@ -1,113 +0,0 @@
-#ifndef __X86_KERNEL_KPROBES_COMMON_H
-#define __X86_KERNEL_KPROBES_COMMON_H
-
-/* Kprobes and Optprobes common header */
-
-#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
-
-/* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
-/* Recover instruction if given address is probed */
-extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
-					 unsigned long addr);
-/*
- * Copy an instruction and adjust the displacement if the instruction
- * uses the %rip-relative addressing mode.
- */
-extern int __copy_instruction(u8 *dest, u8 *src);
-
-/* Generate a relative-jump/call instruction */
-extern void synthesize_reljump(void *from, void *to);
-extern void synthesize_relcall(void *from, void *to);
-
-#ifdef	CONFIG_OPTPROBES
-extern int arch_init_optprobes(void);
-extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
-extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
-#else	/* !CONFIG_OPTPROBES */
-static inline int arch_init_optprobes(void)
-{
-	return 0;
-}
-static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
-{
-	return 0;
-}
-static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
-{
-	return addr;
-}
-#endif
-
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
-#endif
diff --git a/arch/x86/kernel/kprobes-ftrace.c b/arch/x86/kernel/kprobes-ftrace.c
deleted file mode 100644
index 70a81c7..0000000
--- a/arch/x86/kernel/kprobes-ftrace.c
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Dynamic Ftrace based Kprobes Optimization
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Hitachi Ltd., 2012
- */
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-#include <linux/hardirq.h>
-#include <linux/preempt.h>
-#include <linux/ftrace.h>
-
-#include "kprobes-common.h"
-
-static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			     struct kprobe_ctlblk *kcb)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	return 1;
-}
-
-int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			      struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb);
-	else
-		return 0;
-}
-
-/* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
-{
-	struct kprobe *p;
-	struct kprobe_ctlblk *kcb;
-	unsigned long flags;
-
-	/* Disable irq for emulating a breakpoint and avoiding preempt */
-	local_irq_save(flags);
-
-	p = get_kprobe((kprobe_opcode_t *)ip);
-	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
-
-	kcb = get_kprobe_ctlblk();
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(p);
-	} else {
-		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
-		regs->ip = ip + sizeof(kprobe_opcode_t);
-
-		__this_cpu_write(current_kprobe, p);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			__skip_singlestep(p, regs, kcb);
-		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe.
-		 */
-	}
-end:
-	local_irq_restore(flags);
-}
-
-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
-{
-	p->ainsn.insn = NULL;
-	p->ainsn.boostable = -1;
-	return 0;
-}
diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c
deleted file mode 100644
index c5e410e..0000000
--- a/arch/x86/kernel/kprobes-opt.c
+++ /dev/null
@@ -1,512 +0,0 @@
-/*
- *  Kernel Probes Jump Optimization (Optprobes)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2002, 2004
- * Copyright (C) Hitachi Ltd., 2012
- */
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/hardirq.h>
-#include <linux/preempt.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/kallsyms.h>
-#include <linux/ftrace.h>
-
-#include <asm/cacheflush.h>
-#include <asm/desc.h>
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/alternative.h>
-#include <asm/insn.h>
-#include <asm/debugreg.h>
-
-#include "kprobes-common.h"
-
-unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
-{
-	struct optimized_kprobe *op;
-	struct kprobe *kp;
-	long offs;
-	int i;
-
-	for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
-		kp = get_kprobe((void *)addr - i);
-		/* This function only handles jump-optimized kprobe */
-		if (kp && kprobe_optimized(kp)) {
-			op = container_of(kp, struct optimized_kprobe, kp);
-			/* If op->list is not empty, op is under optimizing */
-			if (list_empty(&op->list))
-				goto found;
-		}
-	}
-
-	return addr;
-found:
-	/*
-	 * If the kprobe can be optimized, original bytes which can be
-	 * overwritten by jump destination address. In this case, original
-	 * bytes must be recovered from op->optinsn.copied_insn buffer.
-	 */
-	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	if (addr == (unsigned long)kp->addr) {
-		buf[0] = kp->opcode;
-		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	} else {
-		offs = addr - (unsigned long)kp->addr - 1;
-		memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
-	}
-
-	return (unsigned long)buf;
-}
-
-/* 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);
-		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)
-{
-	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 *)recover_probed_instruction(buf, addr));
-		insn_get_length(&insn);
-		/* Another subsystem puts a breakpoint */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
-			return 0;
-		/* 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)
- * This is called when new aggr(opt)probe is allocated or reused.
- */
-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);
-}
-
-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;
-}
-
-int __kprobes arch_init_optprobes(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;
-}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
deleted file mode 100644
index 18114bf..0000000
--- a/arch/x86/kernel/kprobes.c
+++ /dev/null
@@ -1,1064 +0,0 @@
-/*
- *  Kernel Probes (KProbes)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2002, 2004
- *
- * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
- *		Probes initial implementation ( includes contributions from
- *		Rusty Russell).
- * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
- *		interface to access function arguments.
- * 2004-Oct	Jim Keniston <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
- *		<prasanna@in.ibm.com> adapted for x86_64 from i386.
- * 2005-Mar	Roland McGrath <roland@redhat.com>
- *		Fixed to handle %rip-relative addressing mode correctly.
- * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
- *		<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
- * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
- *		kprobe-booster and kretprobe-booster for i386.
- * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
- *		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.
- */
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/hardirq.h>
-#include <linux/preempt.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/kallsyms.h>
-#include <linux/ftrace.h>
-
-#include <asm/cacheflush.h>
-#include <asm/desc.h>
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/alternative.h>
-#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;
-DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
-
-#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs))
-
-#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
-	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
-	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
-	  (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) |   \
-	  (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf))    \
-	 << (row % 32))
-	/*
-	 * Undefined/reserved opcodes, conditional jump, Opcode Extension
-	 * Groups, and some special opcodes can not boost.
-	 * This is non-const and volatile to keep gcc from statically
-	 * optimizing it out, as variable_test_bit makes gcc think only
-	 * *(unsigned long*) is used. 
-	 */
-static volatile u32 twobyte_is_boostable[256 / 32] = {
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-	/*      ----------------------------------------------          */
-	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
-	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
-	W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
-	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
-	W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */
-	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */
-	W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
-	W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */
-	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
-	W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */
-	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */
-	W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
-	W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */
-	W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */
-	W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0)   /* f0 */
-	/*      -----------------------------------------------         */
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-};
-#undef W
-
-struct kretprobe_blackpoint kretprobe_blacklist[] = {
-	{"__switch_to", }, /* This function switches only current task, but
-			      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)
-{
-	struct __arch_relative_insn {
-		u8 op;
-		s32 raddr;
-	} __attribute__((packed)) *insn;
-
-	insn = (struct __arch_relative_insn *)from;
-	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
-	insn->op = op;
-}
-
-/* Insert a jump instruction at address 'from', which jumps to address '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.
- */
-static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
-{
-	insn_attr_t attr;
-
-	attr = inat_get_opcode_attribute((insn_byte_t)*insn);
-	while (inat_is_legacy_prefix(attr)) {
-		insn++;
-		attr = inat_get_opcode_attribute((insn_byte_t)*insn);
-	}
-#ifdef CONFIG_X86_64
-	if (inat_is_rex_prefix(attr))
-		insn++;
-#endif
-	return insn;
-}
-
-/*
- * Returns non-zero if opcode is boostable.
- * RIP relative instructions are adjusted at copying time in 64 bits mode
- */
-int __kprobes can_boost(kprobe_opcode_t *opcodes)
-{
-	kprobe_opcode_t opcode;
-	kprobe_opcode_t *orig_opcodes = opcodes;
-
-	if (search_exception_tables((unsigned long)opcodes))
-		return 0;	/* Page fault may occur on this address. */
-
-retry:
-	if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
-		return 0;
-	opcode = *(opcodes++);
-
-	/* 2nd-byte opcode */
-	if (opcode == 0x0f) {
-		if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
-			return 0;
-		return test_bit(*opcodes,
-				(unsigned long *)twobyte_is_boostable);
-	}
-
-	switch (opcode & 0xf0) {
-#ifdef CONFIG_X86_64
-	case 0x40:
-		goto retry; /* REX prefix is boostable */
-#endif
-	case 0x60:
-		if (0x63 < opcode && opcode < 0x67)
-			goto retry; /* prefixes */
-		/* can't boost Address-size override and bound */
-		return (opcode != 0x62 && opcode != 0x67);
-	case 0x70:
-		return 0; /* can't boost conditional jump */
-	case 0xc0:
-		/* can't boost software-interruptions */
-		return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
-	case 0xd0:
-		/* can boost AA* and XLAT */
-		return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
-	case 0xe0:
-		/* can boost in/out and absolute jmps */
-		return ((opcode & 0x04) || opcode == 0xea);
-	case 0xf0:
-		if ((opcode & 0x0c) == 0 && opcode != 0xf1)
-			goto retry; /* lock/rep(ne) prefix */
-		/* clear and set flags are boostable */
-		return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
-	default:
-		/* segment override prefixes are boostable */
-		if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e)
-			goto retry; /* prefixes */
-		/* CS override prefix and call are not boostable */
-		return (opcode != 0x2e && opcode != 0x9a);
-	}
-}
-
-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 addr;
-
-	/*
-	 *  Basically, kp->ainsn.insn has an original instruction.
-	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, __copy_instruction() tweaks the displacement of
-	 *  that instruction. In that case, we can't recover the instruction
-	 *  from the kp->ainsn.insn.
-	 *
-	 *  On the other hand, kp->opcode has a copy of the first byte of
-	 *  the probed instruction, which is overwritten by int3. And
-	 *  the instruction at kp->addr is not modified by kprobes except
-	 *  for the first byte, we can recover the original instruction
-	 *  from it and kp->opcode.
-	 */
-	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	buf[0] = kp->opcode;
-	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)
-{
-	unsigned long addr, __addr, offset = 0;
-	struct insn insn;
-	kprobe_opcode_t buf[MAX_INSN_SIZE];
-
-	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
-		return 0;
-
-	/* Decode instructions */
-	addr = paddr - offset;
-	while (addr < paddr) {
-		/*
-		 * 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.
-		 */
-		__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;
-	}
-
-	return (addr == paddr);
-}
-
-/*
- * Returns non-zero if opcode modifies the interrupt flag.
- */
-static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
-{
-	/* Skip prefixes */
-	insn = skip_prefixes(insn);
-
-	switch (*insn) {
-	case 0xfa:		/* cli */
-	case 0xfb:		/* sti */
-	case 0xcf:		/* iret/iretd */
-	case 0x9d:		/* popf/popfd */
-		return 1;
-	}
-
-	return 0;
-}
-
-/*
- * Copy an instruction and adjust the displacement if the instruction
- * uses the %rip-relative addressing mode.
- * If it does, Return the address of the 32-bit displacement word.
- * If not, return null.
- * Only applicable to 64-bit x86.
- */
-int __kprobes __copy_instruction(u8 *dest, u8 *src)
-{
-	struct insn insn;
-	kprobe_opcode_t buf[MAX_INSN_SIZE];
-
-	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
-	if (insn_rip_relative(&insn)) {
-		s64 newdisp;
-		u8 *disp;
-		kernel_insn_init(&insn, dest);
-		insn_get_displacement(&insn);
-		/*
-		 * The copied instruction uses the %rip-relative addressing
-		 * mode.  Adjust the displacement for the difference between
-		 * the original location of this instruction and the location
-		 * of the copy that will actually be run.  The tricky bit here
-		 * is making sure that the sign extension happens correctly in
-		 * this calculation, since we need a signed 32-bit result to
-		 * be sign-extended to 64 bits when it's added to the %rip
-		 * value and yield the same 64-bit result that the sign-
-		 * extension of the original signed 32-bit displacement would
-		 * have given.
-		 */
-		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;
-	}
-#endif
-	return insn.length;
-}
-
-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_instruction can modify the displacement of the instruction,
-	 * but it doesn't affect boostable check.
-	 */
-	if (can_boost(p->ainsn.insn))
-		p->ainsn.boostable = 0;
-	else
-		p->ainsn.boostable = -1;
-
-	/* Also, displacement change doesn't affect the first byte */
-	p->opcode = p->ainsn.insn[0];
-}
-
-int __kprobes arch_prepare_kprobe(struct kprobe *p)
-{
-	if (alternatives_text_reserved(p->addr, p->addr))
-		return -EINVAL;
-
-	if (!can_probe((unsigned long)p->addr))
-		return -EILSEQ;
-	/* insn: must be on special executable page on x86. */
-	p->ainsn.insn = get_insn_slot();
-	if (!p->ainsn.insn)
-		return -ENOMEM;
-	arch_copy_kprobe(p);
-	return 0;
-}
-
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
-}
-
-void __kprobes arch_disarm_kprobe(struct kprobe *p)
-{
-	text_poke(p->addr, &p->opcode, 1);
-}
-
-void __kprobes arch_remove_kprobe(struct kprobe *p)
-{
-	if (p->ainsn.insn) {
-		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
-		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;
-	kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags;
-	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
-}
-
-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;
-	kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags;
-	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
-}
-
-static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
-				struct kprobe_ctlblk *kcb)
-{
-	__this_cpu_write(current_kprobe, p);
-	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
-		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	if (is_IF_modifier(p->ainsn.insn))
-		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
-}
-
-static void __kprobes clear_btf(void)
-{
-	if (test_thread_flag(TIF_BLOCKSTEP)) {
-		unsigned long debugctl = get_debugctlmsr();
-
-		debugctl &= ~DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
-	}
-}
-
-static void __kprobes restore_btf(void)
-{
-	if (test_thread_flag(TIF_BLOCKSTEP)) {
-		unsigned long debugctl = get_debugctlmsr();
-
-		debugctl |= DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
-	}
-}
-
-void __kprobes
-arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
-{
-	unsigned long *sara = stack_addr(regs);
-
-	ri->ret_addr = (kprobe_opcode_t *) *sara;
-
-	/* Replace the return addr with trampoline addr */
-	*sara = (unsigned long) &kretprobe_trampoline;
-}
-
-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;
-
-#if !defined(CONFIG_PREEMPT)
-	if (p->ainsn.boostable == 1 && !p->post_handler) {
-		/* Boost up -- we can execute copied instructions directly */
-		if (!reenter)
-			reset_current_kprobe();
-		/*
-		 * Reentering boosted probe doesn't reset current_kprobe,
-		 * nor set current_kprobe, because it doesn't use single
-		 * stepping.
-		 */
-		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
-		return;
-	}
-#endif
-	if (reenter) {
-		save_previous_kprobe(kcb);
-		set_current_kprobe(p, regs, kcb);
-		kcb->kprobe_status = KPROBE_REENTER;
-	} else
-		kcb->kprobe_status = KPROBE_HIT_SS;
-	/* Prepare real single stepping */
-	clear_btf();
-	regs->flags |= X86_EFLAGS_TF;
-	regs->flags &= ~X86_EFLAGS_IF;
-	/* single step inline if the instruction is an int3 */
-	if (p->opcode == BREAKPOINT_INSTRUCTION)
-		regs->ip = (unsigned long)p->addr;
-	else
-		regs->ip = (unsigned long)p->ainsn.insn;
-}
-
-/*
- * We have reentered the kprobe_handler(), since another probe was hit while
- * 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)
-{
-	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:
-		/* A probe has been hit in the codepath leading up to, or just
-		 * after, single-stepping of a probed instruction. This entire
-		 * codepath should strictly reside in .kprobes.text section.
-		 * Raise a BUG or we'll continue in an endless reentering loop
-		 * and eventually a stack overflow.
-		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
-		dump_kprobe(p);
-		BUG();
-	default:
-		/* impossible cases */
-		WARN_ON(1);
-		return 0;
-	}
-
-	return 1;
-}
-
-/*
- * Interrupts are disabled on entry as trap3 is an interrupt gate and they
- * remain disabled throughout this function.
- */
-static int __kprobes kprobe_handler(struct pt_regs *regs)
-{
-	kprobe_opcode_t *addr;
-	struct kprobe *p;
-	struct kprobe_ctlblk *kcb;
-
-	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
-	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing. We conditionally
-	 * re-enable preemption at the end of this function,
-	 * and also in reenter_kprobe() and setup_singlestep().
-	 */
-	preempt_disable();
-
-	kcb = get_kprobe_ctlblk();
-	p = get_kprobe(addr);
-
-	if (p) {
-		if (kprobe_running()) {
-			if (reenter_kprobe(p, regs, kcb))
-				return 1;
-		} else {
-			set_current_kprobe(p, regs, kcb);
-			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
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
-			 */
-			if (!p->pre_handler || !p->pre_handler(p, regs))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
-	} else if (*addr != BREAKPOINT_INSTRUCTION) {
-		/*
-		 * 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.
-		 * Back up over the (now missing) int3 and run
-		 * the original instruction.
-		 */
-		regs->ip = (unsigned long)addr;
-		preempt_enable_no_resched();
-		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			if (!skip_singlestep(p, regs, kcb))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
-	} /* else: not a kprobe fault; let the kernel handle it */
-
-	preempt_enable_no_resched();
-	return 0;
-}
-
-/*
- * When a retprobed function returns, this code saves registers and
- * calls trampoline_handler() runs, which calls the kretprobe's handler.
- */
-static void __used __kprobes kretprobe_trampoline_holder(void)
-{
-	asm volatile (
-			".global kretprobe_trampoline\n"
-			"kretprobe_trampoline: \n"
-#ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rdi\n"
-			"	call trampoline_handler\n"
-			/* Replace saved sp with true return address. */
-			"	movq %rax, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			"	popfq\n"
-#else
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %eax\n"
-			"	call trampoline_handler\n"
-			/* Move flags to cs */
-			"	movl 56(%esp), %edx\n"
-			"	movl %edx, 52(%esp)\n"
-			/* Replace saved flags with true return address. */
-			"	movl %eax, 56(%esp)\n"
-			RESTORE_REGS_STRING
-			"	popf\n"
-#endif
-			"	ret\n");
-}
-
-/*
- * Called from kretprobe_trampoline
- */
-static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
-{
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *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);
-	/* fixup registers */
-#ifdef CONFIG_X86_64
-	regs->cs = __KERNEL_CS;
-#else
-	regs->cs = __KERNEL_CS | get_kernel_rpl();
-	regs->gs = 0;
-#endif
-	regs->ip = trampoline_address;
-	regs->orig_ax = ~0UL;
-
-	/*
-	 * 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, node, 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, node, 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, node, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-	return (void *)orig_ret_address;
-}
-
-/*
- * Called after single-stepping.  p->addr is the address of the
- * instruction whose first byte has been replaced by the "int 3"
- * instruction.  To avoid the SMP problems that can occur when we
- * temporarily put back the original opcode to single-step, we
- * single-stepped a copy of the instruction.  The address of this
- * copy is p->ainsn.insn.
- *
- * This function prepares to return from the post-single-step
- * interrupt.  We have to fix up the stack as follows:
- *
- * 0) Except in the case of absolute or indirect jump or call instructions,
- * the new ip is relative to the copied instruction.  We need to make
- * it relative to the original instruction.
- *
- * 1) If the single-stepped instruction was pushfl, then the TF and IF
- * flags are set in the just-pushed flags, and may need to be cleared.
- *
- * 2) If the single-stepped instruction was a call, the return address
- * that is atop the stack is the address following the copied instruction.
- * We need to make it the address following the original instruction.
- *
- * If this is the first time we've single-stepped the instruction at
- * this probepoint, and the instruction is boostable, boost it: add a
- * 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)
-{
-	unsigned long *tos = stack_addr(regs);
-	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
-	unsigned long orig_ip = (unsigned long)p->addr;
-	kprobe_opcode_t *insn = p->ainsn.insn;
-
-	/* Skip prefixes */
-	insn = skip_prefixes(insn);
-
-	regs->flags &= ~X86_EFLAGS_TF;
-	switch (*insn) {
-	case 0x9c:	/* pushfl */
-		*tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF);
-		*tos |= kcb->kprobe_old_flags;
-		break;
-	case 0xc2:	/* iret/ret/lret */
-	case 0xc3:
-	case 0xca:
-	case 0xcb:
-	case 0xcf:
-	case 0xea:	/* jmp absolute -- ip is correct */
-		/* ip is already adjusted, no more changes required */
-		p->ainsn.boostable = 1;
-		goto no_change;
-	case 0xe8:	/* call relative - Fix return addr */
-		*tos = orig_ip + (*tos - copy_ip);
-		break;
-#ifdef CONFIG_X86_32
-	case 0x9a:	/* call absolute -- same as call absolute, indirect */
-		*tos = orig_ip + (*tos - copy_ip);
-		goto no_change;
-#endif
-	case 0xff:
-		if ((insn[1] & 0x30) == 0x10) {
-			/*
-			 * call absolute, indirect
-			 * Fix return addr; ip is correct.
-			 * But this is not boostable
-			 */
-			*tos = orig_ip + (*tos - copy_ip);
-			goto no_change;
-		} else if (((insn[1] & 0x31) == 0x20) ||
-			   ((insn[1] & 0x31) == 0x21)) {
-			/*
-			 * jmp near and far, absolute indirect
-			 * ip is correct. And this is boostable
-			 */
-			p->ainsn.boostable = 1;
-			goto no_change;
-		}
-	default:
-		break;
-	}
-
-	if (p->ainsn.boostable == 0) {
-		if ((regs->ip > copy_ip) &&
-		    (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) {
-			/*
-			 * These instructions can be executed directly if it
-			 * jumps back to correct address.
-			 */
-			synthesize_reljump((void *)regs->ip,
-				(void *)orig_ip + (regs->ip - copy_ip));
-			p->ainsn.boostable = 1;
-		} else {
-			p->ainsn.boostable = -1;
-		}
-	}
-
-	regs->ip += orig_ip - copy_ip;
-
-no_change:
-	restore_btf();
-}
-
-/*
- * Interrupts are disabled on entry as trap1 is an interrupt gate and they
- * remain disabled throughout this function.
- */
-static int __kprobes post_kprobe_handler(struct pt_regs *regs)
-{
-	struct kprobe *cur = kprobe_running();
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (!cur)
-		return 0;
-
-	resume_execution(cur, regs, kcb);
-	regs->flags |= kcb->kprobe_saved_flags;
-
-	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		cur->post_handler(cur, regs, 0);
-	}
-
-	/* Restore back the original saved kprobes variables and continue. */
-	if (kcb->kprobe_status == KPROBE_REENTER) {
-		restore_previous_kprobe(kcb);
-		goto out;
-	}
-	reset_current_kprobe();
-out:
-	preempt_enable_no_resched();
-
-	/*
-	 * if somebody else is singlestepping across a probe point, flags
-	 * will have TF set, in which case, continue the remaining processing
-	 * of do_debug, as if this is not a probe hit.
-	 */
-	if (regs->flags & X86_EFLAGS_TF)
-		return 0;
-
-	return 1;
-}
-
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
-{
-	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.
-		 */
-		regs->ip = (unsigned long)cur->addr;
-		regs->flags |= kcb->kprobe_old_flags;
-		if (kcb->kprobe_status == KPROBE_REENTER)
-			restore_previous_kprobe(kcb);
-		else
-			reset_current_kprobe();
-		preempt_enable_no_resched();
-		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, trapnr))
-			return 1;
-
-		/*
-		 * In case the user-specified fault handler returned
-		 * zero, try to fix up.
-		 */
-		if (fixup_exception(regs))
-			return 1;
-
-		/*
-		 * fixup routine could not handle it,
-		 * Let do_page_fault() fix it.
-		 */
-		break;
-	default:
-		break;
-	}
-	return 0;
-}
-
-/*
- * Wrapper routine for handling exceptions.
- */
-int __kprobes
-kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
-{
-	struct die_args *args = data;
-	int ret = NOTIFY_DONE;
-
-	if (args->regs && user_mode_vm(args->regs))
-		return ret;
-
-	switch (val) {
-	case DIE_INT3:
-		if (kprobe_handler(args->regs))
-			ret = NOTIFY_STOP;
-		break;
-	case DIE_DEBUG:
-		if (post_kprobe_handler(args->regs)) {
-			/*
-			 * Reset the BS bit in dr6 (pointed by args->err) to
-			 * denote completion of processing
-			 */
-			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
-			ret = NOTIFY_STOP;
-		}
-		break;
-	case DIE_GPF:
-		/*
-		 * To be potentially processing a kprobe fault and to
-		 * trust the result from kprobe_running(), we have
-		 * be non-preemptible.
-		 */
-		if (!preemptible() && kprobe_running() &&
-		    kprobe_fault_handler(args->regs, args->trapnr))
-			ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
-	}
-	return ret;
-}
-
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = stack_addr(regs);
-	addr = (unsigned long)(kcb->jprobe_saved_sp);
-
-	/*
-	 * 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, (kprobe_opcode_t *)addr,
-	       MIN_STACK_SIZE(addr));
-	regs->flags &= ~X86_EFLAGS_IF;
-	trace_hardirqs_off();
-	regs->ip = (unsigned long)(jp->entry);
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	asm volatile (
-#ifdef CONFIG_X86_64
-			"       xchg   %%rbx,%%rsp	\n"
-#else
-			"       xchgl   %%ebx,%%esp	\n"
-#endif
-			"       int3			\n"
-			"       .globl jprobe_return_end\n"
-			"       jprobe_return_end:	\n"
-			"       nop			\n"::"b"
-			(kcb->jprobe_saved_sp):"memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	u8 *addr = (u8 *) (regs->ip - 1);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if ((addr > (u8 *) jprobe_return) &&
-	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
-			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
-			printk(KERN_ERR
-			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), kcb->jprobe_saved_sp);
-			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk(KERN_ERR "Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
-		       kcb->jprobes_stack,
-		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
-int __init arch_init_kprobes(void)
-{
-	return arch_init_optprobes();
-}
-
-int __kprobes arch_trampoline_kprobe(struct kprobe *p)
-{
-	return 0;
-}
diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile
new file mode 100644
index 0000000..0d33169
--- /dev/null
+++ b/arch/x86/kernel/kprobes/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for kernel probes
+#
+
+obj-$(CONFIG_KPROBES)		+= core.o
+obj-$(CONFIG_OPTPROBES)		+= opt.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
new file mode 100644
index 0000000..2e9d4b5
--- /dev/null
+++ b/arch/x86/kernel/kprobes/common.h
@@ -0,0 +1,113 @@
+#ifndef __X86_KERNEL_KPROBES_COMMON_H
+#define __X86_KERNEL_KPROBES_COMMON_H
+
+/* Kprobes and Optprobes common header */
+
+#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
+
+/* Ensure if the instruction can be boostable */
+extern int can_boost(kprobe_opcode_t *instruction);
+/* Recover instruction if given address is probed */
+extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
+					 unsigned long addr);
+/*
+ * Copy an instruction and adjust the displacement if the instruction
+ * uses the %rip-relative addressing mode.
+ */
+extern int __copy_instruction(u8 *dest, u8 *src);
+
+/* Generate a relative-jump/call instruction */
+extern void synthesize_reljump(void *from, void *to);
+extern void synthesize_relcall(void *from, void *to);
+
+#ifdef	CONFIG_OPTPROBES
+extern int arch_init_optprobes(void);
+extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
+extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
+#else	/* !CONFIG_OPTPROBES */
+static inline int arch_init_optprobes(void)
+{
+	return 0;
+}
+static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+{
+	return 0;
+}
+static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	return addr;
+}
+#endif
+
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			   struct kprobe_ctlblk *kcb);
+#else
+static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				  struct kprobe_ctlblk *kcb)
+{
+	return 0;
+}
+#endif
+#endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
new file mode 100644
index 0000000..e124554
--- /dev/null
+++ b/arch/x86/kernel/kprobes/core.c
@@ -0,0 +1,1064 @@
+/*
+ *  Kernel Probes (KProbes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
+ *		Probes initial implementation ( includes contributions from
+ *		Rusty Russell).
+ * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
+ *		interface to access function arguments.
+ * 2004-Oct	Jim Keniston <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
+ *		<prasanna@in.ibm.com> adapted for x86_64 from i386.
+ * 2005-Mar	Roland McGrath <roland@redhat.com>
+ *		Fixed to handle %rip-relative addressing mode correctly.
+ * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
+ *		<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
+ * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
+ *		kprobe-booster and kretprobe-booster for i386.
+ * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
+ *		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.
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/module.h>
+#include <linux/kdebug.h>
+#include <linux/kallsyms.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/insn.h>
+#include <asm/debugreg.h>
+
+#include "common.h"
+
+void jprobe_return_end(void);
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs))
+
+#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
+	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
+	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
+	  (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) |   \
+	  (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf))    \
+	 << (row % 32))
+	/*
+	 * Undefined/reserved opcodes, conditional jump, Opcode Extension
+	 * Groups, and some special opcodes can not boost.
+	 * This is non-const and volatile to keep gcc from statically
+	 * optimizing it out, as variable_test_bit makes gcc think only
+	 * *(unsigned long*) is used.
+	 */
+static volatile u32 twobyte_is_boostable[256 / 32] = {
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
+	/*      ----------------------------------------------          */
+	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
+	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
+	W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
+	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
+	W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */
+	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */
+	W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
+	W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
+	W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */
+	W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */
+	W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0)   /* f0 */
+	/*      -----------------------------------------------         */
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
+};
+#undef W
+
+struct kretprobe_blackpoint kretprobe_blacklist[] = {
+	{"__switch_to", }, /* This function switches only current task, but
+			      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)
+{
+	struct __arch_relative_insn {
+		u8 op;
+		s32 raddr;
+	} __packed *insn;
+
+	insn = (struct __arch_relative_insn *)from;
+	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
+	insn->op = op;
+}
+
+/* Insert a jump instruction at address 'from', which jumps to address '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.
+ */
+static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
+{
+	insn_attr_t attr;
+
+	attr = inat_get_opcode_attribute((insn_byte_t)*insn);
+	while (inat_is_legacy_prefix(attr)) {
+		insn++;
+		attr = inat_get_opcode_attribute((insn_byte_t)*insn);
+	}
+#ifdef CONFIG_X86_64
+	if (inat_is_rex_prefix(attr))
+		insn++;
+#endif
+	return insn;
+}
+
+/*
+ * Returns non-zero if opcode is boostable.
+ * RIP relative instructions are adjusted at copying time in 64 bits mode
+ */
+int __kprobes can_boost(kprobe_opcode_t *opcodes)
+{
+	kprobe_opcode_t opcode;
+	kprobe_opcode_t *orig_opcodes = opcodes;
+
+	if (search_exception_tables((unsigned long)opcodes))
+		return 0;	/* Page fault may occur on this address. */
+
+retry:
+	if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
+		return 0;
+	opcode = *(opcodes++);
+
+	/* 2nd-byte opcode */
+	if (opcode == 0x0f) {
+		if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
+			return 0;
+		return test_bit(*opcodes,
+				(unsigned long *)twobyte_is_boostable);
+	}
+
+	switch (opcode & 0xf0) {
+#ifdef CONFIG_X86_64
+	case 0x40:
+		goto retry; /* REX prefix is boostable */
+#endif
+	case 0x60:
+		if (0x63 < opcode && opcode < 0x67)
+			goto retry; /* prefixes */
+		/* can't boost Address-size override and bound */
+		return (opcode != 0x62 && opcode != 0x67);
+	case 0x70:
+		return 0; /* can't boost conditional jump */
+	case 0xc0:
+		/* can't boost software-interruptions */
+		return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
+	case 0xd0:
+		/* can boost AA* and XLAT */
+		return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
+	case 0xe0:
+		/* can boost in/out and absolute jmps */
+		return ((opcode & 0x04) || opcode == 0xea);
+	case 0xf0:
+		if ((opcode & 0x0c) == 0 && opcode != 0xf1)
+			goto retry; /* lock/rep(ne) prefix */
+		/* clear and set flags are boostable */
+		return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
+	default:
+		/* segment override prefixes are boostable */
+		if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e)
+			goto retry; /* prefixes */
+		/* CS override prefix and call are not boostable */
+		return (opcode != 0x2e && opcode != 0x9a);
+	}
+}
+
+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 addr;
+
+	/*
+	 *  Basically, kp->ainsn.insn has an original instruction.
+	 *  However, RIP-relative instruction can not do single-stepping
+	 *  at different place, __copy_instruction() tweaks the displacement of
+	 *  that instruction. In that case, we can't recover the instruction
+	 *  from the kp->ainsn.insn.
+	 *
+	 *  On the other hand, kp->opcode has a copy of the first byte of
+	 *  the probed instruction, which is overwritten by int3. And
+	 *  the instruction at kp->addr is not modified by kprobes except
+	 *  for the first byte, we can recover the original instruction
+	 *  from it and kp->opcode.
+	 */
+	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	buf[0] = kp->opcode;
+	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)
+{
+	unsigned long addr, __addr, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr) {
+		/*
+		 * 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.
+		 */
+		__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;
+	}
+
+	return (addr == paddr);
+}
+
+/*
+ * Returns non-zero if opcode modifies the interrupt flag.
+ */
+static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
+{
+	/* Skip prefixes */
+	insn = skip_prefixes(insn);
+
+	switch (*insn) {
+	case 0xfa:		/* cli */
+	case 0xfb:		/* sti */
+	case 0xcf:		/* iret/iretd */
+	case 0x9d:		/* popf/popfd */
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy an instruction and adjust the displacement if the instruction
+ * uses the %rip-relative addressing mode.
+ * If it does, Return the address of the 32-bit displacement word.
+ * If not, return null.
+ * Only applicable to 64-bit x86.
+ */
+int __kprobes __copy_instruction(u8 *dest, u8 *src)
+{
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	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
+	if (insn_rip_relative(&insn)) {
+		s64 newdisp;
+		u8 *disp;
+		kernel_insn_init(&insn, dest);
+		insn_get_displacement(&insn);
+		/*
+		 * The copied instruction uses the %rip-relative addressing
+		 * mode.  Adjust the displacement for the difference between
+		 * the original location of this instruction and the location
+		 * of the copy that will actually be run.  The tricky bit here
+		 * is making sure that the sign extension happens correctly in
+		 * this calculation, since we need a signed 32-bit result to
+		 * be sign-extended to 64 bits when it's added to the %rip
+		 * value and yield the same 64-bit result that the sign-
+		 * extension of the original signed 32-bit displacement would
+		 * have given.
+		 */
+		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;
+	}
+#endif
+	return insn.length;
+}
+
+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_instruction can modify the displacement of the instruction,
+	 * but it doesn't affect boostable check.
+	 */
+	if (can_boost(p->ainsn.insn))
+		p->ainsn.boostable = 0;
+	else
+		p->ainsn.boostable = -1;
+
+	/* Also, displacement change doesn't affect the first byte */
+	p->opcode = p->ainsn.insn[0];
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	if (alternatives_text_reserved(p->addr, p->addr))
+		return -EINVAL;
+
+	if (!can_probe((unsigned long)p->addr))
+		return -EILSEQ;
+	/* insn: must be on special executable page on x86. */
+	p->ainsn.insn = get_insn_slot();
+	if (!p->ainsn.insn)
+		return -ENOMEM;
+	arch_copy_kprobe(p);
+	return 0;
+}
+
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
+}
+
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+	text_poke(p->addr, &p->opcode, 1);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
+		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;
+	kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags;
+	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
+}
+
+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;
+	kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags;
+	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+				struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, p);
+	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
+		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
+	if (is_IF_modifier(p->ainsn.insn))
+		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
+}
+
+static void __kprobes clear_btf(void)
+{
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
+}
+
+static void __kprobes restore_btf(void)
+{
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		unsigned long debugctl = get_debugctlmsr();
+
+		debugctl |= DEBUGCTLMSR_BTF;
+		update_debugctlmsr(debugctl);
+	}
+}
+
+void __kprobes
+arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	unsigned long *sara = stack_addr(regs);
+
+	ri->ret_addr = (kprobe_opcode_t *) *sara;
+
+	/* Replace the return addr with trampoline addr */
+	*sara = (unsigned long) &kretprobe_trampoline;
+}
+
+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;
+
+#if !defined(CONFIG_PREEMPT)
+	if (p->ainsn.boostable == 1 && !p->post_handler) {
+		/* Boost up -- we can execute copied instructions directly */
+		if (!reenter)
+			reset_current_kprobe();
+		/*
+		 * Reentering boosted probe doesn't reset current_kprobe,
+		 * nor set current_kprobe, because it doesn't use single
+		 * stepping.
+		 */
+		regs->ip = (unsigned long)p->ainsn.insn;
+		preempt_enable_no_resched();
+		return;
+	}
+#endif
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p, regs, kcb);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	/* Prepare real single stepping */
+	clear_btf();
+	regs->flags |= X86_EFLAGS_TF;
+	regs->flags &= ~X86_EFLAGS_IF;
+	/* single step inline if the instruction is an int3 */
+	if (p->opcode == BREAKPOINT_INSTRUCTION)
+		regs->ip = (unsigned long)p->addr;
+	else
+		regs->ip = (unsigned long)p->ainsn.insn;
+}
+
+/*
+ * We have reentered the kprobe_handler(), since another probe was hit while
+ * 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)
+{
+	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:
+		/* A probe has been hit in the codepath leading up to, or just
+		 * after, single-stepping of a probed instruction. This entire
+		 * codepath should strictly reside in .kprobes.text section.
+		 * Raise a BUG or we'll continue in an endless reentering loop
+		 * and eventually a stack overflow.
+		 */
+		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
+		       p->addr);
+		dump_kprobe(p);
+		BUG();
+	default:
+		/* impossible cases */
+		WARN_ON(1);
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * Interrupts are disabled on entry as trap3 is an interrupt gate and they
+ * remain disabled throughout this function.
+ */
+static int __kprobes kprobe_handler(struct pt_regs *regs)
+{
+	kprobe_opcode_t *addr;
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+
+	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
+	/*
+	 * We don't want to be preempted for the entire
+	 * duration of kprobe processing. We conditionally
+	 * re-enable preemption at the end of this function,
+	 * and also in reenter_kprobe() and setup_singlestep().
+	 */
+	preempt_disable();
+
+	kcb = get_kprobe_ctlblk();
+	p = get_kprobe(addr);
+
+	if (p) {
+		if (kprobe_running()) {
+			if (reenter_kprobe(p, regs, kcb))
+				return 1;
+		} else {
+			set_current_kprobe(p, regs, kcb);
+			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
+			 * for jprobe processing, so get out doing nothing
+			 * more here.
+			 */
+			if (!p->pre_handler || !p->pre_handler(p, regs))
+				setup_singlestep(p, regs, kcb, 0);
+			return 1;
+		}
+	} else if (*addr != BREAKPOINT_INSTRUCTION) {
+		/*
+		 * 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.
+		 * Back up over the (now missing) int3 and run
+		 * the original instruction.
+		 */
+		regs->ip = (unsigned long)addr;
+		preempt_enable_no_resched();
+		return 1;
+	} else if (kprobe_running()) {
+		p = __this_cpu_read(current_kprobe);
+		if (p->break_handler && p->break_handler(p, regs)) {
+			if (!skip_singlestep(p, regs, kcb))
+				setup_singlestep(p, regs, kcb, 0);
+			return 1;
+		}
+	} /* else: not a kprobe fault; let the kernel handle it */
+
+	preempt_enable_no_resched();
+	return 0;
+}
+
+/*
+ * When a retprobed function returns, this code saves registers and
+ * calls trampoline_handler() runs, which calls the kretprobe's handler.
+ */
+static void __used __kprobes kretprobe_trampoline_holder(void)
+{
+	asm volatile (
+			".global kretprobe_trampoline\n"
+			"kretprobe_trampoline: \n"
+#ifdef CONFIG_X86_64
+			/* We don't bother saving the ss register */
+			"	pushq %rsp\n"
+			"	pushfq\n"
+			SAVE_REGS_STRING
+			"	movq %rsp, %rdi\n"
+			"	call trampoline_handler\n"
+			/* Replace saved sp with true return address. */
+			"	movq %rax, 152(%rsp)\n"
+			RESTORE_REGS_STRING
+			"	popfq\n"
+#else
+			"	pushf\n"
+			SAVE_REGS_STRING
+			"	movl %esp, %eax\n"
+			"	call trampoline_handler\n"
+			/* Move flags to cs */
+			"	movl 56(%esp), %edx\n"
+			"	movl %edx, 52(%esp)\n"
+			/* Replace saved flags with true return address. */
+			"	movl %eax, 56(%esp)\n"
+			RESTORE_REGS_STRING
+			"	popf\n"
+#endif
+			"	ret\n");
+}
+
+/*
+ * Called from kretprobe_trampoline
+ */
+static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *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);
+	/* fixup registers */
+#ifdef CONFIG_X86_64
+	regs->cs = __KERNEL_CS;
+#else
+	regs->cs = __KERNEL_CS | get_kernel_rpl();
+	regs->gs = 0;
+#endif
+	regs->ip = trampoline_address;
+	regs->orig_ax = ~0UL;
+
+	/*
+	 * 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, node, 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, node, 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, node, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+	return (void *)orig_ret_address;
+}
+
+/*
+ * Called after single-stepping.  p->addr is the address of the
+ * instruction whose first byte has been replaced by the "int 3"
+ * instruction.  To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction.  The address of this
+ * copy is p->ainsn.insn.
+ *
+ * This function prepares to return from the post-single-step
+ * interrupt.  We have to fix up the stack as follows:
+ *
+ * 0) Except in the case of absolute or indirect jump or call instructions,
+ * the new ip is relative to the copied instruction.  We need to make
+ * it relative to the original instruction.
+ *
+ * 1) If the single-stepped instruction was pushfl, then the TF and IF
+ * flags are set in the just-pushed flags, and may need to be cleared.
+ *
+ * 2) If the single-stepped instruction was a call, the return address
+ * that is atop the stack is the address following the copied instruction.
+ * We need to make it the address following the original instruction.
+ *
+ * If this is the first time we've single-stepped the instruction at
+ * this probepoint, and the instruction is boostable, boost it: add a
+ * 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)
+{
+	unsigned long *tos = stack_addr(regs);
+	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
+	unsigned long orig_ip = (unsigned long)p->addr;
+	kprobe_opcode_t *insn = p->ainsn.insn;
+
+	/* Skip prefixes */
+	insn = skip_prefixes(insn);
+
+	regs->flags &= ~X86_EFLAGS_TF;
+	switch (*insn) {
+	case 0x9c:	/* pushfl */
+		*tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF);
+		*tos |= kcb->kprobe_old_flags;
+		break;
+	case 0xc2:	/* iret/ret/lret */
+	case 0xc3:
+	case 0xca:
+	case 0xcb:
+	case 0xcf:
+	case 0xea:	/* jmp absolute -- ip is correct */
+		/* ip is already adjusted, no more changes required */
+		p->ainsn.boostable = 1;
+		goto no_change;
+	case 0xe8:	/* call relative - Fix return addr */
+		*tos = orig_ip + (*tos - copy_ip);
+		break;
+#ifdef CONFIG_X86_32
+	case 0x9a:	/* call absolute -- same as call absolute, indirect */
+		*tos = orig_ip + (*tos - copy_ip);
+		goto no_change;
+#endif
+	case 0xff:
+		if ((insn[1] & 0x30) == 0x10) {
+			/*
+			 * call absolute, indirect
+			 * Fix return addr; ip is correct.
+			 * But this is not boostable
+			 */
+			*tos = orig_ip + (*tos - copy_ip);
+			goto no_change;
+		} else if (((insn[1] & 0x31) == 0x20) ||
+			   ((insn[1] & 0x31) == 0x21)) {
+			/*
+			 * jmp near and far, absolute indirect
+			 * ip is correct. And this is boostable
+			 */
+			p->ainsn.boostable = 1;
+			goto no_change;
+		}
+	default:
+		break;
+	}
+
+	if (p->ainsn.boostable == 0) {
+		if ((regs->ip > copy_ip) &&
+		    (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) {
+			/*
+			 * These instructions can be executed directly if it
+			 * jumps back to correct address.
+			 */
+			synthesize_reljump((void *)regs->ip,
+				(void *)orig_ip + (regs->ip - copy_ip));
+			p->ainsn.boostable = 1;
+		} else {
+			p->ainsn.boostable = -1;
+		}
+	}
+
+	regs->ip += orig_ip - copy_ip;
+
+no_change:
+	restore_btf();
+}
+
+/*
+ * Interrupts are disabled on entry as trap1 is an interrupt gate and they
+ * remain disabled throughout this function.
+ */
+static int __kprobes post_kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (!cur)
+		return 0;
+
+	resume_execution(cur, regs, kcb);
+	regs->flags |= kcb->kprobe_saved_flags;
+
+	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		cur->post_handler(cur, regs, 0);
+	}
+
+	/* Restore back the original saved kprobes variables and continue. */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		goto out;
+	}
+	reset_current_kprobe();
+out:
+	preempt_enable_no_resched();
+
+	/*
+	 * if somebody else is singlestepping across a probe point, flags
+	 * will have TF set, in which case, continue the remaining processing
+	 * of do_debug, as if this is not a probe hit.
+	 */
+	if (regs->flags & X86_EFLAGS_TF)
+		return 0;
+
+	return 1;
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+	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.
+		 */
+		regs->ip = (unsigned long)cur->addr;
+		regs->flags |= kcb->kprobe_old_flags;
+		if (kcb->kprobe_status == KPROBE_REENTER)
+			restore_previous_kprobe(kcb);
+		else
+			reset_current_kprobe();
+		preempt_enable_no_resched();
+		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, trapnr))
+			return 1;
+
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		if (fixup_exception(regs))
+			return 1;
+
+		/*
+		 * fixup routine could not handle it,
+		 * Let do_page_fault() fix it.
+		 */
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Wrapper routine for handling exceptions.
+ */
+int __kprobes
+kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
+{
+	struct die_args *args = data;
+	int ret = NOTIFY_DONE;
+
+	if (args->regs && user_mode_vm(args->regs))
+		return ret;
+
+	switch (val) {
+	case DIE_INT3:
+		if (kprobe_handler(args->regs))
+			ret = NOTIFY_STOP;
+		break;
+	case DIE_DEBUG:
+		if (post_kprobe_handler(args->regs)) {
+			/*
+			 * Reset the BS bit in dr6 (pointed by args->err) to
+			 * denote completion of processing
+			 */
+			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
+			ret = NOTIFY_STOP;
+		}
+		break;
+	case DIE_GPF:
+		/*
+		 * To be potentially processing a kprobe fault and to
+		 * trust the result from kprobe_running(), we have
+		 * be non-preemptible.
+		 */
+		if (!preemptible() && kprobe_running() &&
+		    kprobe_fault_handler(args->regs, args->trapnr))
+			ret = NOTIFY_STOP;
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	unsigned long addr;
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	kcb->jprobe_saved_regs = *regs;
+	kcb->jprobe_saved_sp = stack_addr(regs);
+	addr = (unsigned long)(kcb->jprobe_saved_sp);
+
+	/*
+	 * 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, (kprobe_opcode_t *)addr,
+	       MIN_STACK_SIZE(addr));
+	regs->flags &= ~X86_EFLAGS_IF;
+	trace_hardirqs_off();
+	regs->ip = (unsigned long)(jp->entry);
+	return 1;
+}
+
+void __kprobes jprobe_return(void)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	asm volatile (
+#ifdef CONFIG_X86_64
+			"       xchg   %%rbx,%%rsp	\n"
+#else
+			"       xchgl   %%ebx,%%esp	\n"
+#endif
+			"       int3			\n"
+			"       .globl jprobe_return_end\n"
+			"       jprobe_return_end:	\n"
+			"       nop			\n"::"b"
+			(kcb->jprobe_saved_sp):"memory");
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	u8 *addr = (u8 *) (regs->ip - 1);
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+
+	if ((addr > (u8 *) jprobe_return) &&
+	    (addr < (u8 *) jprobe_return_end)) {
+		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
+			printk(KERN_ERR
+			       "current sp %p does not match saved sp %p\n",
+			       stack_addr(regs), kcb->jprobe_saved_sp);
+			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
+			show_regs(saved_regs);
+			printk(KERN_ERR "Current registers\n");
+			show_regs(regs);
+			BUG();
+		}
+		*regs = kcb->jprobe_saved_regs;
+		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
+		       kcb->jprobes_stack,
+		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+		preempt_enable_no_resched();
+		return 1;
+	}
+	return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+	return arch_init_optprobes();
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
new file mode 100644
index 0000000..23ef5c5
--- /dev/null
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -0,0 +1,93 @@
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+#include "common.h"
+
+static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
+{
+	/*
+	 * Emulate singlestep (and also recover regs->ip)
+	 * as if there is a 5byte nop
+	 */
+	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+	if (unlikely(p->post_handler)) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+	__this_cpu_write(current_kprobe, NULL);
+	return 1;
+}
+
+int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			      struct kprobe_ctlblk *kcb)
+{
+	if (kprobe_ftrace(p))
+		return __skip_singlestep(p, regs, kcb);
+	else
+		return 0;
+}
+
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+				     struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+	unsigned long flags;
+
+	/* Disable irq for emulating a breakpoint and avoiding preempt */
+	local_irq_save(flags);
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		goto end;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+		regs->ip = ip + sizeof(kprobe_opcode_t);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			__skip_singlestep(p, regs, kcb);
+		/*
+		 * If pre_handler returns !0, it sets regs->ip and
+		 * resets current kprobe.
+		 */
+	}
+end:
+	local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.insn = NULL;
+	p->ainsn.boostable = -1;
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
new file mode 100644
index 0000000..76dc6f0
--- /dev/null
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -0,0 +1,512 @@
+/*
+ *  Kernel Probes Jump Optimization (Optprobes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/module.h>
+#include <linux/kdebug.h>
+#include <linux/kallsyms.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/insn.h>
+#include <asm/debugreg.h>
+
+#include "common.h"
+
+unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
+{
+	struct optimized_kprobe *op;
+	struct kprobe *kp;
+	long offs;
+	int i;
+
+	for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
+		kp = get_kprobe((void *)addr - i);
+		/* This function only handles jump-optimized kprobe */
+		if (kp && kprobe_optimized(kp)) {
+			op = container_of(kp, struct optimized_kprobe, kp);
+			/* If op->list is not empty, op is under optimizing */
+			if (list_empty(&op->list))
+				goto found;
+		}
+	}
+
+	return addr;
+found:
+	/*
+	 * If the kprobe can be optimized, original bytes which can be
+	 * overwritten by jump destination address. In this case, original
+	 * bytes must be recovered from op->optinsn.copied_insn buffer.
+	 */
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (addr == (unsigned long)kp->addr) {
+		buf[0] = kp->opcode;
+		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	} else {
+		offs = addr - (unsigned long)kp->addr - 1;
+		memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
+	}
+
+	return (unsigned long)buf;
+}
+
+/* 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);
+		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)
+{
+	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 *)recover_probed_instruction(buf, addr));
+		insn_get_length(&insn);
+		/* Another subsystem puts a breakpoint */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+			return 0;
+		/* 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)
+ * This is called when new aggr(opt)probe is allocated or reused.
+ */
+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);
+}
+
+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;
+}
+
+int __kprobes arch_init_optprobes(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;
+}
-- 
1.7.10.4

[PATCH 13/13 -next] tracing: Remove the extra 4 bytes of padding in events

[Steven Rostedt]

[-- Attachment #1: 0013-tracing-Remove-the-extra-4-bytes-of-padding-in-event.patch --]
[-- Type: text/plain, Size: 2973 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Due to a userspace issue with PowerTop v1, which hardcoded
the offset of event fields that it was using, it broke when
we removed the Big Kernel Lock counter from the event header.

 (commit e6e1e2593 "tracing: Remove lock_depth from event entry")

Because this broke userspace, it was determined that we must
keep those 4 bytes around.

 (commit a3a4a5acd "Regression: partial revert "tracing: Remove lock_depth from event entry"")

This unfortunately wastes space in the ring buffer. 4 bytes per
event, where a lot of events are just 24 bytes. That's 16% of the
buffer wasted. A million events will add 4 megs of white space
into the buffer.

It was later noticed that PowerTop v1 could not work on systems
where the kernel was 64 bit but the userspace was 32 bits.
The reason was because the offsets are different between the
two and the hard coded offset of one would not work with the other.

With PowerTop v2, it implemented the same interface that both
perf and trace-cmd use. That is, it reads the format file of
the event to find the offsets of the fields it needs. This fixes
the problem with running powertop on a 32 bit userspace running
on a 64 bit kernel. It also no longer requires the 4 byte padding.

As PowerTop v2 has been out for a while, and is included in all
major distributions, it is time that we can safely remove the
4 bytes of padding. Users of PowerTop v1 should upgrade to
PowerTop v2.

Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |    1 -
 kernel/trace/trace.c         |    1 -
 kernel/trace/trace_events.c  |    1 -
 3 files changed, 3 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 43ef8b6..6f8d0b7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -49,7 +49,6 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			padding;
 };
 
 #define FTRACE_MAX_EVENT						\
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d62248d..a387bd2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1173,7 +1173,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->padding			= 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 880073d..57e9b28 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, padding);
 
 	return ret;
 }
-- 
1.7.10.4

Re: [PATCH 13/13 -next] tracing: Remove the extra 4 bytes of padding in events

[Arjan van de Ven]

On 1/21/2013 1:14 PM, Steven Rostedt wrote:
> From: Steven Rostedt <srostedt@redhat.com>
>
> Due to a userspace issue with PowerTop v1, which hardcoded
> the offset of event fields that it was using, it broke when
> we removed the Big Kernel Lock counter from the event header.
>
>   (commit e6e1e2593 "tracing: Remove lock_depth from event entry")
>
> Because this broke userspace, it was determined that we must
> keep those 4 bytes around.
>
>   (commit a3a4a5acd "Regression: partial revert "tracing: Remove lock_depth from event entry"")
>
> This unfortunately wastes space in the ring buffer. 4 bytes per
> event, where a lot of events are just 24 bytes. That's 16% of the
> buffer wasted. A million events will add 4 megs of white space
> into the buffer.
>
> It was later noticed that PowerTop v1 could not work on systems
> where the kernel was 64 bit but the userspace was 32 bits.
> The reason was because the offsets are different between the
> two and the hard coded offset of one would not work with the other.
>
> With PowerTop v2, it implemented the same interface that both
> perf and trace-cmd use. That is, it reads the format file of
> the event to find the offsets of the fields it needs. This fixes
> the problem with running powertop on a 32 bit userspace running
> on a 64 bit kernel. It also no longer requires the 4 byte padding.
>
> As PowerTop v2 has been out for a while, and is included in all
> major distributions, it is time that we can safely remove the
> 4 bytes of padding. Users of PowerTop v1 should upgrade to
> PowerTop v2.
>
> Cc: Arjan van de Ven <arjan@linux.intel.com>

this only impacts the users of the 2.0beta series (which, while arguably staying around for too long, is now very very obsolete and
replaced by the final in all distros that I'm aware of)


Acked-By: Arjan van de Ven <arjan@linux.intel.com>