From 2f5f6ad9390c1ebbf738d130dbfe80b60eaa167e Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Mon, 8 Aug 2011 16:57:47 -0400
Subject: ftrace: Pass ftrace_ops as third parameter to function trace callback

Currently the function trace callback receives only the ip and parent_ip
of the function that it traced. It would be more powerful to also return
the ops that registered the function as well. This allows the same function
to act differently depending on what ftrace_ops registered it.

Link: http://lkml.kernel.org/r/20120612225424.267254552@goodmis.org

Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 101 ++++++++++++++++++++++++++++++++++----------------
 1 file changed, 70 insertions(+), 31 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b4f20fba09f..4f2ab9352a6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -64,12 +64,19 @@
 
 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
 
+static struct ftrace_ops ftrace_list_end __read_mostly = {
+	.func		= ftrace_stub,
+};
+
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
 /* Quick disabling of function tracer. */
-int function_trace_stop;
+int function_trace_stop __read_mostly;
+
+/* Current function tracing op */
+struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
 
 /* List for set_ftrace_pid's pids. */
 LIST_HEAD(ftrace_pids);
@@ -86,10 +93,6 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops ftrace_list_end __read_mostly = {
-	.func		= ftrace_stub,
-};
-
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
@@ -100,8 +103,14 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 static struct ftrace_ops control_ops;
 
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+				 struct ftrace_ops *op);
+#else
+/* See comment below, where ftrace_ops_list_func is defined */
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
+#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
+#endif
 
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
@@ -112,29 +121,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
-static void ftrace_global_list_func(unsigned long ip,
-				    unsigned long parent_ip)
+static void
+ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
+			struct ftrace_ops *op)
 {
-	struct ftrace_ops *op;
-
 	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
 		return;
 
 	trace_recursion_set(TRACE_GLOBAL_BIT);
 	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 	while (op != &ftrace_list_end) {
-		op->func(ip, parent_ip);
+		op->func(ip, parent_ip, op);
 		op = rcu_dereference_raw(op->next); /*see above*/
 	};
 	trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
-static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
+			    struct ftrace_ops *op)
 {
 	if (!test_tsk_trace_trace(current))
 		return;
 
-	ftrace_pid_function(ip, parent_ip);
+	ftrace_pid_function(ip, parent_ip, op);
 }
 
 static void set_ftrace_pid_function(ftrace_func_t func)
@@ -163,12 +172,13 @@ void clear_ftrace_function(void)
  * For those archs that do not test ftrace_trace_stop in their
  * mcount call site, we need to do it from C.
  */
-static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip,
+				  struct ftrace_ops *op)
 {
 	if (function_trace_stop)
 		return;
 
-	__ftrace_trace_function(ip, parent_ip);
+	__ftrace_trace_function(ip, parent_ip, op);
 }
 #endif
 
@@ -230,15 +240,24 @@ static void update_ftrace_function(void)
 
 	/*
 	 * If we are at the end of the list and this ops is
-	 * not dynamic, then have the mcount trampoline call
-	 * the function directly
+	 * not dynamic and the arch supports passing ops, then have the
+	 * mcount trampoline call the function directly.
 	 */
 	if (ftrace_ops_list == &ftrace_list_end ||
 	    (ftrace_ops_list->next == &ftrace_list_end &&
-	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC)))
+	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
+	     ARCH_SUPPORTS_FTRACE_OPS)) {
+		/* Set the ftrace_ops that the arch callback uses */
+		if (ftrace_ops_list == &global_ops)
+			function_trace_op = ftrace_global_list;
+		else
+			function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
-	else
+	} else {
+		/* Just use the default ftrace_ops */
+		function_trace_op = &ftrace_list_end;
 		func = ftrace_ops_list_func;
+	}
 
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
@@ -773,7 +792,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
 }
 
 static void
-function_profile_call(unsigned long ip, unsigned long parent_ip)
+function_profile_call(unsigned long ip, unsigned long parent_ip,
+		      struct ftrace_ops *ops)
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
@@ -803,7 +823,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static int profile_graph_entry(struct ftrace_graph_ent *trace)
 {
-	function_profile_call(trace->func, 0);
+	function_profile_call(trace->func, 0, NULL);
 	return 1;
 }
 
@@ -2790,8 +2810,8 @@ static int __init ftrace_mod_cmd_init(void)
 }
 device_initcall(ftrace_mod_cmd_init);
 
-static void
-function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
+static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
+				      struct ftrace_ops *op)
 {
 	struct ftrace_func_probe *entry;
 	struct hlist_head *hhd;
@@ -3942,10 +3962,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 static void
-ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
+			struct ftrace_ops *op)
 {
-	struct ftrace_ops *op;
-
 	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
 		return;
 
@@ -3959,7 +3978,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
 	while (op != &ftrace_list_end) {
 		if (!ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip);
+			op->func(ip, parent_ip, op);
 
 		op = rcu_dereference_raw(op->next);
 	};
@@ -3971,8 +3990,9 @@ static struct ftrace_ops control_ops = {
 	.func = ftrace_ops_control_func,
 };
 
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
+static inline void
+__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *ignored)
 {
 	struct ftrace_ops *op;
 
@@ -3988,13 +4008,32 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 	op = rcu_dereference_raw(ftrace_ops_list);
 	while (op != &ftrace_list_end) {
 		if (ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip);
+			op->func(ip, parent_ip, op);
 		op = rcu_dereference_raw(op->next);
 	};
 	preempt_enable_notrace();
 	trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
+/*
+ * Some archs only support passing ip and parent_ip. Even though
+ * the list function ignores the op parameter, we do not want any
+ * C side effects, where a function is called without the caller
+ * sending a third parameter.
+ */
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+				 struct ftrace_ops *op)
+{
+	__ftrace_ops_list_func(ip, parent_ip, NULL);
+}
+#else
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+{
+	__ftrace_ops_list_func(ip, parent_ip, NULL);
+}
+#endif
+
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
-- 
cgit v1.2.3-70-g09d2


From ccf3672d530170c98c734dfc5db07d64bcbad2ad Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Tue, 5 Jun 2012 09:44:25 -0400
Subject: ftrace: Consolidate arch dependent functions with 'list' function

As the function tracer starts to get more features, the support for
theses features will spread out throughout the different architectures
over time. These features boil down to what each arch does in the
mcount trampoline (the ftrace_caller).

Currently there's two features that are not the same throughout the
archs.

 1) Support to stop function tracing before the callback
 2) passing of the ftrace ops

Both of these require placing an indirect function to support the
features if the mcount trampoline does not.

On a side note, for all architectures, when more than one callback
is registered to the function tracer, an intermediate 'list' function
is called by the mcount trampoline to iterate through the callbacks
that are registered.

Instead of making a separate function for each of these features,
and requiring several indirect calls, just use the single 'list' function
as the intermediate, to handle all cases. If an arch does not support
the 'stop function tracing' or the passing of ftrace ops, just force
it to use the list function that will handle the features required.

This makes the code cleaner and simpler and removes a lot of
 #ifdefs in the code.

Link: http://lkml.kernel.org/r/20120612225424.495625483@goodmis.org

Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 13 +++++++++++++
 kernel/trace/ftrace.c  | 45 ++++-----------------------------------------
 2 files changed, 17 insertions(+), 41 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 2d596411988..3651fdc3bec 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -27,6 +27,19 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 0
 #endif
 
+/*
+ * If the arch's mcount caller does not support all of ftrace's
+ * features, then it must call an indirect function that
+ * does. Or at least does enough to prevent any unwelcomed side effects.
+ */
+#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \
+	!ARCH_SUPPORTS_FTRACE_OPS
+# define FTRACE_FORCE_LIST_FUNC 1
+#else
+# define FTRACE_FORCE_LIST_FUNC 0
+#endif
+
+
 struct module;
 struct ftrace_hash;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f2ab9352a6..4cbca2e6eb7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -97,8 +97,6 @@ static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
-static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
-ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 static struct ftrace_ops control_ops;
@@ -162,26 +160,9 @@ static void set_ftrace_pid_function(ftrace_func_t func)
 void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
-	__ftrace_trace_function = ftrace_stub;
-	__ftrace_trace_function_delay = ftrace_stub;
 	ftrace_pid_function = ftrace_stub;
 }
 
-#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-/*
- * For those archs that do not test ftrace_trace_stop in their
- * mcount call site, we need to do it from C.
- */
-static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *op)
-{
-	if (function_trace_stop)
-		return;
-
-	__ftrace_trace_function(ip, parent_ip, op);
-}
-#endif
-
 static void control_ops_disable_all(struct ftrace_ops *ops)
 {
 	int cpu;
@@ -246,7 +227,7 @@ static void update_ftrace_function(void)
 	if (ftrace_ops_list == &ftrace_list_end ||
 	    (ftrace_ops_list->next == &ftrace_list_end &&
 	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
-	     ARCH_SUPPORTS_FTRACE_OPS)) {
+	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
 		if (ftrace_ops_list == &global_ops)
 			function_trace_op = ftrace_global_list;
@@ -259,18 +240,7 @@ static void update_ftrace_function(void)
 		func = ftrace_ops_list_func;
 	}
 
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
-#else
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* do not update till all functions have been modified */
-	__ftrace_trace_function_delay = func;
-#else
-	__ftrace_trace_function = func;
-#endif
-	ftrace_trace_function =
-		(func == ftrace_stub) ? func : ftrace_test_stop_func;
-#endif
 }
 
 static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
@@ -1902,16 +1872,6 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	/*
-	 * For archs that call ftrace_test_stop_func(), we must
-	 * wait till after we update all the function callers
-	 * before we update the callback. This keeps different
-	 * ops that record different functions from corrupting
-	 * each other.
-	 */
-	__ftrace_trace_function = __ftrace_trace_function_delay;
-#endif
 	function_trace_stop--;
 
 	ret = ftrace_arch_code_modify_post_process();
@@ -3996,6 +3956,9 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 {
 	struct ftrace_ops *op;
 
+	if (function_trace_stop)
+		return;
+
 	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
 		return;
 
-- 
cgit v1.2.3-70-g09d2


From a1e2e31d175a1349274eba3465d17616c6725f8c Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Tue, 9 Aug 2011 12:50:46 -0400
Subject: ftrace: Return pt_regs to function trace callback

Return as the 4th paramater to the function tracer callback the pt_regs.

Later patches that implement regs passing for the architectures will require
having the ftrace_ops set the SAVE_REGS flag, which will tell the arch
to take the time to pass a full set of pt_regs to the ftrace_ops callback
function. If the arch does not support it then it should pass NULL.

If an arch can pass full regs, then it should define:
 ARCH_SUPPORTS_FTRACE_SAVE_REGS to 1

Link: http://lkml.kernel.org/r/20120702201821.019966811@goodmis.org

Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h            |  6 ++++--
 kernel/trace/ftrace.c             | 37 ++++++++++++++++++++++---------------
 kernel/trace/trace_event_perf.c   |  2 +-
 kernel/trace/trace_events.c       |  2 +-
 kernel/trace/trace_functions.c    |  7 ++++---
 kernel/trace/trace_irqsoff.c      |  2 +-
 kernel/trace/trace_sched_wakeup.c |  3 ++-
 kernel/trace/trace_selftest.c     | 15 ++++++++++-----
 kernel/trace/trace_stack.c        |  3 ++-
 9 files changed, 47 insertions(+), 30 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 3651fdc3bec..e4202881fb0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -10,6 +10,7 @@
 #include <linux/kallsyms.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
+#include <linux/ptrace.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
 #include <linux/types.h>
@@ -54,7 +55,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 struct ftrace_ops;
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
-			      struct ftrace_ops *op);
+			      struct ftrace_ops *op, struct pt_regs *regs);
 
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
@@ -188,7 +189,8 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
 	return *this_cpu_ptr(ops->disabled);
 }
 
-extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op);
+extern void ftrace_stub(unsigned long a0, unsigned long a1,
+			struct ftrace_ops *op, struct pt_regs *regs);
 
 #else /* !CONFIG_FUNCTION_TRACER */
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4cbca2e6eb7..6ff07ad0ede 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -103,7 +103,7 @@ static struct ftrace_ops control_ops;
 
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op);
+				 struct ftrace_ops *op, struct pt_regs *regs);
 #else
 /* See comment below, where ftrace_ops_list_func is defined */
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
@@ -121,7 +121,7 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
  */
 static void
 ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *op)
+			struct ftrace_ops *op, struct pt_regs *regs)
 {
 	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
 		return;
@@ -129,19 +129,19 @@ ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
 	trace_recursion_set(TRACE_GLOBAL_BIT);
 	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 	while (op != &ftrace_list_end) {
-		op->func(ip, parent_ip, op);
+		op->func(ip, parent_ip, op, regs);
 		op = rcu_dereference_raw(op->next); /*see above*/
 	};
 	trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
-			    struct ftrace_ops *op)
+			    struct ftrace_ops *op, struct pt_regs *regs)
 {
 	if (!test_tsk_trace_trace(current))
 		return;
 
-	ftrace_pid_function(ip, parent_ip, op);
+	ftrace_pid_function(ip, parent_ip, op, regs);
 }
 
 static void set_ftrace_pid_function(ftrace_func_t func)
@@ -763,7 +763,7 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
 
 static void
 function_profile_call(unsigned long ip, unsigned long parent_ip,
-		      struct ftrace_ops *ops)
+		      struct ftrace_ops *ops, struct pt_regs *regs)
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
@@ -793,7 +793,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static int profile_graph_entry(struct ftrace_graph_ent *trace)
 {
-	function_profile_call(trace->func, 0, NULL);
+	function_profile_call(trace->func, 0, NULL, NULL);
 	return 1;
 }
 
@@ -2771,7 +2771,7 @@ static int __init ftrace_mod_cmd_init(void)
 device_initcall(ftrace_mod_cmd_init);
 
 static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
-				      struct ftrace_ops *op)
+				      struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct ftrace_func_probe *entry;
 	struct hlist_head *hhd;
@@ -3923,7 +3923,7 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 
 static void
 ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *op)
+			struct ftrace_ops *op, struct pt_regs *regs)
 {
 	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
 		return;
@@ -3938,7 +3938,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	while (op != &ftrace_list_end) {
 		if (!ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip, op);
+			op->func(ip, parent_ip, op, regs);
 
 		op = rcu_dereference_raw(op->next);
 	};
@@ -3952,7 +3952,7 @@ static struct ftrace_ops control_ops = {
 
 static inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-		       struct ftrace_ops *ignored)
+		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
 	struct ftrace_ops *op;
 
@@ -3971,7 +3971,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	op = rcu_dereference_raw(ftrace_ops_list);
 	while (op != &ftrace_list_end) {
 		if (ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip, op);
+			op->func(ip, parent_ip, op, regs);
 		op = rcu_dereference_raw(op->next);
 	};
 	preempt_enable_notrace();
@@ -3983,17 +3983,24 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
  * the list function ignores the op parameter, we do not want any
  * C side effects, where a function is called without the caller
  * sending a third parameter.
+ * 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.
+ * An architecture can pass partial regs with ftrace_ops and still
+ * set the ARCH_SUPPORT_FTARCE_OPS.
  */
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op)
+				 struct ftrace_ops *op, struct pt_regs *regs)
 {
-	__ftrace_ops_list_func(ip, parent_ip, NULL);
+	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
 }
 #else
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 {
-	__ftrace_ops_list_func(ip, parent_ip, NULL);
+	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
 #endif
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a872a9a298a..9824419c840 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -259,7 +259,7 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
 #ifdef CONFIG_FUNCTION_TRACER
 static void
 perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *ops)
+			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
 {
 	struct ftrace_entry *entry;
 	struct hlist_head *head;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 88daa5177bf..8c669683368 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1682,7 +1682,7 @@ static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
 static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *op)
+			  struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index fceb7a9aa06..5675ebd541f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -49,7 +49,7 @@ static void function_trace_start(struct trace_array *tr)
 
 static void
 function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op)
+				 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = func_trace;
 	struct trace_array_cpu *data;
@@ -77,7 +77,8 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
 
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op)
+		    struct ftrace_ops *op, struct pt_regs *pt_regs)
+
 {
 	struct trace_array *tr = func_trace;
 	struct trace_array_cpu *data;
@@ -109,7 +110,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 
 static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *op)
+			  struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = func_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2862c77f95d..c7a9ba936de 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -137,7 +137,7 @@ static int func_prolog_dec(struct trace_array *tr,
  */
 static void
 irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op)
+		    struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0caf4f5da56..7547e36d483 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -108,7 +108,8 @@ out_enable:
  * wakeup uses its own tracer function to keep the overhead down:
  */
 static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op)
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+		   struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 9ae40c823af..add37e019fd 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -104,7 +104,8 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
 static int trace_selftest_test_probe1_cnt;
 static void trace_selftest_test_probe1_func(unsigned long ip,
 					    unsigned long pip,
-					    struct ftrace_ops *op)
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe1_cnt++;
 }
@@ -112,7 +113,8 @@ static void trace_selftest_test_probe1_func(unsigned long ip,
 static int trace_selftest_test_probe2_cnt;
 static void trace_selftest_test_probe2_func(unsigned long ip,
 					    unsigned long pip,
-					    struct ftrace_ops *op)
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe2_cnt++;
 }
@@ -120,7 +122,8 @@ static void trace_selftest_test_probe2_func(unsigned long ip,
 static int trace_selftest_test_probe3_cnt;
 static void trace_selftest_test_probe3_func(unsigned long ip,
 					    unsigned long pip,
-					    struct ftrace_ops *op)
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe3_cnt++;
 }
@@ -128,7 +131,8 @@ static void trace_selftest_test_probe3_func(unsigned long ip,
 static int trace_selftest_test_global_cnt;
 static void trace_selftest_test_global_func(unsigned long ip,
 					    unsigned long pip,
-					    struct ftrace_ops *op)
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_global_cnt++;
 }
@@ -136,7 +140,8 @@ static void trace_selftest_test_global_func(unsigned long ip,
 static int trace_selftest_test_dyn_cnt;
 static void trace_selftest_test_dyn_func(unsigned long ip,
 					 unsigned long pip,
-					 struct ftrace_ops *op)
+					 struct ftrace_ops *op,
+					 struct pt_regs *pt_regs)
 {
 	trace_selftest_test_dyn_cnt++;
 }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index e20006d5fb6..2fa5328e889 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -111,7 +111,8 @@ static inline void check_stack(void)
 }
 
 static void
-stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op)
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+		 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	int cpu;
 
-- 
cgit v1.2.3-70-g09d2


From 08f6fba503111e0336f2b4d6915a4a18f9b60e51 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Mon, 30 Apr 2012 16:20:23 -0400
Subject: ftrace/x86: Add separate function to save regs

Add a way to have different functions calling different trampolines.
If a ftrace_ops wants regs saved on the return, then have only the
functions with ops registered to save regs. Functions registered by
other ops would not be affected, unless the functions overlap.

If one ftrace_ops registered functions A, B and C and another ops
registered fucntions to save regs on A, and D, then only functions
A and D would be saving regs. Function B and C would work as normal.
Although A is registered by both ops: normal and saves regs; this is fine
as saving the regs is needed to satisfy one of the ops that calls it
but the regs are ignored by the other ops function.

x86_64 implements the full regs saving, and i386 just passes a NULL
for regs to satisfy the ftrace_ops passing. Where an arch must supply
both regs and ftrace_ops parameters, even if regs is just NULL.

It is OK for an arch to pass NULL regs. All function trace users that
require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when
registering the ftrace_ops. If the arch does not support saving regs
then the ftrace_ops will fail to register. The flag
FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the
ftrace_ops from failing to register. In this case, the handler may
either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS.
If the arch supports passing regs it will set this macro and pass regs
for ops that request them. All other archs will just pass NULL.

Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org

Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/include/asm/ftrace.h |  47 +++++++++++--------
 arch/x86/kernel/entry_32.S    |   4 +-
 arch/x86/kernel/entry_64.S    |  94 +++++++++++++++++++++++++++++++++----
 arch/x86/kernel/ftrace.c      |  77 ++++++++++++++++++++++++++++--
 include/linux/ftrace.h        | 107 +++++++++++++++++++++++++++++++++++++++---
 kernel/trace/ftrace.c         |  91 +++++++++++++++++++++++++++++++----
 6 files changed, 373 insertions(+), 47 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b3bb1f3f277..a8475014c4a 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,27 +3,33 @@
 
 #ifdef __ASSEMBLY__
 
-	.macro MCOUNT_SAVE_FRAME
-	/* taken from glibc */
-	subq $0x38, %rsp
-	movq %rax, (%rsp)
-	movq %rcx, 8(%rsp)
-	movq %rdx, 16(%rsp)
-	movq %rsi, 24(%rsp)
-	movq %rdi, 32(%rsp)
-	movq %r8, 40(%rsp)
-	movq %r9, 48(%rsp)
+	/* skip is set if the stack was already partially adjusted */
+	.macro MCOUNT_SAVE_FRAME skip=0
+	 /*
+	  * We add enough stack to save all regs.
+	  */
+	subq $(SS+8-\skip), %rsp
+	movq %rax, RAX(%rsp)
+	movq %rcx, RCX(%rsp)
+	movq %rdx, RDX(%rsp)
+	movq %rsi, RSI(%rsp)
+	movq %rdi, RDI(%rsp)
+	movq %r8, R8(%rsp)
+	movq %r9, R9(%rsp)
+	 /* Move RIP to its proper location */
+	movq SS+8(%rsp), %rdx
+	movq %rdx, RIP(%rsp)
 	.endm
 
-	.macro MCOUNT_RESTORE_FRAME
-	movq 48(%rsp), %r9
-	movq 40(%rsp), %r8
-	movq 32(%rsp), %rdi
-	movq 24(%rsp), %rsi
-	movq 16(%rsp), %rdx
-	movq 8(%rsp), %rcx
-	movq (%rsp), %rax
-	addq $0x38, %rsp
+	.macro MCOUNT_RESTORE_FRAME skip=0
+	movq R9(%rsp), %r9
+	movq R8(%rsp), %r8
+	movq RDI(%rsp), %rdi
+	movq RSI(%rsp), %rsi
+	movq RDX(%rsp), %rdx
+	movq RCX(%rsp), %rcx
+	movq RAX(%rsp), %rax
+	addq $(SS+8-\skip), %rsp
 	.endm
 
 #endif
@@ -34,6 +40,9 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
+#ifdef CONFIG_X86_64
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#endif
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e3e17a0b7ff..5da11d1b85a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1109,7 +1109,8 @@ ENTRY(ftrace_caller)
 	pushl %eax
 	pushl %ecx
 	pushl %edx
-	movl 0xc(%esp), %eax
+	pushl $0	/* Pass NULL as regs pointer */
+	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
 	leal function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
@@ -1118,6 +1119,7 @@ ENTRY(ftrace_caller)
 ftrace_call:
 	call ftrace_stub
 
+	addl $4,%esp	/* skip NULL pointer */
 	popl %edx
 	popl %ecx
 	popl %eax
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2b4f94c5dc6..52bda2e8f7a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -73,21 +73,34 @@ ENTRY(mcount)
 	retq
 END(mcount)
 
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+	MCOUNT_SAVE_FRAME \skip
+
+	/* Load the ftrace_ops into the 3rd parameter */
+	leaq function_trace_op, %rdx
+
+	/* Load ip into the first parameter */
+	movq RIP(%rsp), %rdi
+	subq $MCOUNT_INSN_SIZE, %rdi
+	/* Load the parent_ip into the second parameter */
+	movq 8(%rbp), %rsi
+.endm
+
 ENTRY(ftrace_caller)
+	/* Check if tracing was disabled (quick check) */
 	cmpl $0, function_trace_stop
 	jne  ftrace_stub
 
-	MCOUNT_SAVE_FRAME
-
-	leaq function_trace_op, %rdx
-	movq 0x38(%rsp), %rdi
-	movq 8(%rbp), %rsi
-	subq $MCOUNT_INSN_SIZE, %rdi
+	ftrace_caller_setup
+	/* regs go into 4th parameter (but make it NULL) */
+	movq $0, %rcx
 
 GLOBAL(ftrace_call)
 	call ftrace_stub
 
 	MCOUNT_RESTORE_FRAME
+ftrace_return:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -98,6 +111,71 @@ GLOBAL(ftrace_stub)
 	retq
 END(ftrace_caller)
 
+ENTRY(ftrace_regs_caller)
+	/* Save the current flags before compare (in SS location)*/
+	pushfq
+
+	/* Check if tracing was disabled (quick check) */
+	cmpl $0, function_trace_stop
+	jne  ftrace_restore_flags
+
+	/* skip=8 to skip flags saved in SS */
+	ftrace_caller_setup 8
+
+	/* Save the rest of pt_regs */
+	movq %r15, R15(%rsp)
+	movq %r14, R14(%rsp)
+	movq %r13, R13(%rsp)
+	movq %r12, R12(%rsp)
+	movq %r11, R11(%rsp)
+	movq %r10, R10(%rsp)
+	movq %rbp, RBP(%rsp)
+	movq %rbx, RBX(%rsp)
+	/* Copy saved flags */
+	movq SS(%rsp), %rcx
+	movq %rcx, EFLAGS(%rsp)
+	/* Kernel segments */
+	movq $__KERNEL_DS, %rcx
+	movq %rcx, SS(%rsp)
+	movq $__KERNEL_CS, %rcx
+	movq %rcx, CS(%rsp)
+	/* Stack - skipping return address */
+	leaq SS+16(%rsp), %rcx
+	movq %rcx, RSP(%rsp)
+
+	/* regs go into 4th parameter */
+	leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+	call ftrace_stub
+
+	/* Copy flags back to SS, to restore them */
+	movq EFLAGS(%rsp), %rax
+	movq %rax, SS(%rsp)
+
+	/* restore the rest of pt_regs */
+	movq R15(%rsp), %r15
+	movq R14(%rsp), %r14
+	movq R13(%rsp), %r13
+	movq R12(%rsp), %r12
+	movq R10(%rsp), %r10
+	movq RBP(%rsp), %rbp
+	movq RBX(%rsp), %rbx
+
+	/* skip=8 to skip flags saved in SS */
+	MCOUNT_RESTORE_FRAME 8
+
+	/* Restore flags */
+	popfq
+
+	jmp ftrace_return
+ftrace_restore_flags:
+	popfq
+	jmp  ftrace_stub
+
+END(ftrace_regs_caller)
+
+
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
 	cmpl $0, function_trace_stop
@@ -120,7 +198,7 @@ GLOBAL(ftrace_stub)
 trace:
 	MCOUNT_SAVE_FRAME
 
-	movq 0x38(%rsp), %rdi
+	movq RIP(%rsp), %rdi
 	movq 8(%rbp), %rsi
 	subq $MCOUNT_INSN_SIZE, %rdi
 
@@ -141,7 +219,7 @@ ENTRY(ftrace_graph_caller)
 	MCOUNT_SAVE_FRAME
 
 	leaq 8(%rbp), %rdi
-	movq 0x38(%rsp), %rsi
+	movq RIP(%rsp), %rsi
 	movq (%rbp), %rdx
 	subq $MCOUNT_INSN_SIZE, %rsi
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c3a7cb4bf6e..b90eb1a1307 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -206,6 +206,23 @@ static int
 ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 		   unsigned const char *new_code);
 
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+/*
+ * Should never be called:
+ *  As it is only called by __ftrace_replace_code() which is called by
+ *  ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
+ *  which is called to turn mcount into nops or nops into function calls
+ *  but not to convert a function from not using regs to one that uses
+ *  regs, which ftrace_modify_call() is for.
+ */
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+				 unsigned long addr)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
+#endif
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -220,6 +237,16 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 	ret = ftrace_modify_code(ip, old, new);
 
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+	/* Also update the regs callback function */
+	if (!ret) {
+		ip = (unsigned long)(&ftrace_regs_call);
+		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
+		new = ftrace_call_replace(ip, (unsigned long)func);
+		ret = ftrace_modify_code(ip, old, new);
+	}
+#endif
+
 	atomic_dec(&modifying_ftrace_code);
 
 	return ret;
@@ -299,6 +326,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
 	return add_break(rec->ip, old);
 }
 
+/*
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ */
+static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
+/*
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ */
+static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS_EN)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
 static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
@@ -306,7 +359,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_test_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
@@ -316,6 +369,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 		/* converting nop to call */
 		return add_brk_on_nop(rec);
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
+		ftrace_addr = get_ftrace_old_addr(rec);
+		/* fall through */
 	case FTRACE_UPDATE_MAKE_NOP:
 		/* converting a call to a nop */
 		return add_brk_on_call(rec, ftrace_addr);
@@ -360,13 +417,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 		 * If not, don't touch the breakpoint, we make just create
 		 * a disaster.
 		 */
-		ftrace_addr = (unsigned long)FTRACE_ADDR;
+		ftrace_addr = get_ftrace_addr(rec);
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
+			goto update;
+
+		/* Check both ftrace_addr and ftrace_old_addr */
+		ftrace_addr = get_ftrace_old_addr(rec);
 		nop = ftrace_call_replace(ip, ftrace_addr);
 
 		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
 			return -EINVAL;
 	}
 
+ update:
 	return probe_kernel_write((void *)ip, &nop[0], 1);
 }
 
@@ -405,12 +470,14 @@ static int add_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_test_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr  = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
 		return add_update_call(rec, ftrace_addr);
@@ -455,12 +522,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_update_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
 		return finish_update_call(rec, ftrace_addr);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e4202881fb0..ab39990cc43 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -71,12 +71,28 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  *           could be controled by following calls:
  *             ftrace_function_local_enable
  *             ftrace_function_local_disable
+ * 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
+ *            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
+ *            handler can handle an arch that does not save regs
+ *            (the handler tests if regs == NULL), then it can set
+ *            this flag instead. It will not fail registering the ftrace_ops
+ *            but, the regs field will be NULL if the arch does not support
+ *            passing regs to the handler.
+ *            Note, if this flag is set, the SAVE_REGS flag will automatically
+ *            get set upon registering the ftrace_ops, if the arch supports it.
  */
 enum {
-	FTRACE_OPS_FL_ENABLED		= 1 << 0,
-	FTRACE_OPS_FL_GLOBAL		= 1 << 1,
-	FTRACE_OPS_FL_DYNAMIC		= 1 << 2,
-	FTRACE_OPS_FL_CONTROL		= 1 << 3,
+	FTRACE_OPS_FL_ENABLED			= 1 << 0,
+	FTRACE_OPS_FL_GLOBAL			= 1 << 1,
+	FTRACE_OPS_FL_DYNAMIC			= 1 << 2,
+	FTRACE_OPS_FL_CONTROL			= 1 << 3,
+	FTRACE_OPS_FL_SAVE_REGS			= 1 << 4,
+	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 5,
 };
 
 struct ftrace_ops {
@@ -254,12 +270,31 @@ extern void unregister_ftrace_function_probe_all(char *glob);
 
 extern int ftrace_text_reserved(void *start, void *end);
 
+/*
+ * The dyn_ftrace record's flags field is split into two parts.
+ * the first part which is '0-FTRACE_REF_MAX' is a counter of
+ * the number of callbacks that have registered the function that
+ * the dyn_ftrace descriptor represents.
+ *
+ * The second part is a mask:
+ *  ENABLED - the function is being traced
+ *  REGS    - the record wants the function to save regs
+ *  REGS_EN - the function is set up to save regs.
+ *
+ * When a new ftrace_ops is registered and wants a function to save
+ * pt_regs, the rec->flag REGS is set. When the function has been
+ * set up to save regs, the REG_EN flag is set. Once a function
+ * starts saving regs it will do so until all ftrace_ops are removed
+ * from tracing that function.
+ */
 enum {
-	FTRACE_FL_ENABLED	= (1 << 30),
+	FTRACE_FL_ENABLED	= (1UL << 29),
+	FTRACE_FL_REGS		= (1UL << 30),
+	FTRACE_FL_REGS_EN	= (1UL << 31)
 };
 
-#define FTRACE_FL_MASK		(0x3UL << 30)
-#define FTRACE_REF_MAX		((1 << 30) - 1)
+#define FTRACE_FL_MASK		(0x7UL << 29)
+#define FTRACE_REF_MAX		((1UL << 29) - 1)
 
 struct dyn_ftrace {
 	union {
@@ -290,9 +325,23 @@ enum {
 	FTRACE_STOP_FUNC_RET		= (1 << 4),
 };
 
+/*
+ * The FTRACE_UPDATE_* enum is used to pass information back
+ * from the ftrace_update_record() and ftrace_test_record()
+ * functions. These are called by the code update routines
+ * to find out what is to be done for a given function.
+ *
+ *  IGNORE           - The function is already what we want it to be
+ *  MAKE_CALL        - Start tracing the function
+ *  MODIFY_CALL      - Stop saving regs for the function
+ *  MODIFY_CALL_REGS - Start saving regs for the function
+ *  MAKE_NOP         - Stop tracing the function
+ */
 enum {
 	FTRACE_UPDATE_IGNORE,
 	FTRACE_UPDATE_MAKE_CALL,
+	FTRACE_UPDATE_MODIFY_CALL,
+	FTRACE_UPDATE_MODIFY_CALL_REGS,
 	FTRACE_UPDATE_MAKE_NOP,
 };
 
@@ -344,7 +393,9 @@ extern int ftrace_dyn_arch_init(void *data);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
+extern void ftrace_regs_caller(void);
 extern void ftrace_call(void);
+extern void ftrace_regs_call(void);
 extern void mcount_call(void);
 
 void ftrace_modify_all_code(int command);
@@ -352,6 +403,15 @@ void ftrace_modify_all_code(int command);
 #ifndef FTRACE_ADDR
 #define FTRACE_ADDR ((unsigned long)ftrace_caller)
 #endif
+
+#ifndef FTRACE_REGS_ADDR
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
+#else
+# define FTRACE_REGS_ADDR FTRACE_ADDR
+#endif
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
@@ -407,6 +467,39 @@ 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
+/**
+ * ftrace_modify_call - convert from one addr to another (no nop)
+ * @rec: the mcount call site record
+ * @old_addr: the address expected to be currently called to
+ * @addr: the address to change to
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should be a caller to @old_addr
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			      unsigned long addr);
+#else
+/* Should never be called */
+static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+				     unsigned long addr)
+{
+	return -EINVAL;
+}
+#endif
+
 /* May be defined in arch */
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6ff07ad0ede..c55f7e27461 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -314,6 +314,20 @@ 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
+	/*
+	 * 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.
+	 * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant.
+	 */
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS &&
+	    !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED))
+		return -EINVAL;
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)
+		ops->flags |= FTRACE_OPS_FL_SAVE_REGS;
+#endif
+
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
@@ -1515,6 +1529,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			rec->flags++;
 			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX))
 				return;
+			/*
+			 * If any ops wants regs saved for this function
+			 * then all ops will get saved regs.
+			 */
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
 		} else {
 			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0))
 				return;
@@ -1606,18 +1626,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 	if (enable && (rec->flags & ~FTRACE_FL_MASK))
 		flag = FTRACE_FL_ENABLED;
 
+	/*
+	 * If enabling and the REGS flag does not match the REGS_EN, then
+	 * do not ignore this record. Set flags to fail the compare against
+	 * ENABLED.
+	 */
+	if (flag &&
+	    (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)))
+		flag |= FTRACE_FL_REGS;
+
 	/* If the state of this record hasn't changed, then do nothing */
 	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
 		return FTRACE_UPDATE_IGNORE;
 
 	if (flag) {
-		if (update)
+		/* Save off if rec is being enabled (for return value) */
+		flag ^= rec->flags & FTRACE_FL_ENABLED;
+
+		if (update) {
 			rec->flags |= FTRACE_FL_ENABLED;
-		return FTRACE_UPDATE_MAKE_CALL;
+			if (flag & FTRACE_FL_REGS) {
+				if (rec->flags & FTRACE_FL_REGS)
+					rec->flags |= FTRACE_FL_REGS_EN;
+				else
+					rec->flags &= ~FTRACE_FL_REGS_EN;
+			}
+		}
+
+		/*
+		 * If this record is being updated from a nop, then
+		 *   return UPDATE_MAKE_CALL.
+		 * Otherwise, if the EN flag is set, then return
+		 *   UPDATE_MODIFY_CALL_REGS to tell the caller to convert
+		 *   from the non-save regs, to a save regs function.
+		 * Otherwise,
+		 *   return UPDATE_MODIFY_CALL to tell the caller to convert
+		 *   from the save regs, to a non-save regs function.
+		 */
+		if (flag & FTRACE_FL_ENABLED)
+			return FTRACE_UPDATE_MAKE_CALL;
+		else if (rec->flags & FTRACE_FL_REGS_EN)
+			return FTRACE_UPDATE_MODIFY_CALL_REGS;
+		else
+			return FTRACE_UPDATE_MODIFY_CALL;
 	}
 
-	if (update)
-		rec->flags &= ~FTRACE_FL_ENABLED;
+	if (update) {
+		/* If there's no more users, clear all flags */
+		if (!(rec->flags & ~FTRACE_FL_MASK))
+			rec->flags = 0;
+		else
+			/* Just disable the record (keep REGS state) */
+			rec->flags &= ~FTRACE_FL_ENABLED;
+	}
 
 	return FTRACE_UPDATE_MAKE_NOP;
 }
@@ -1652,13 +1713,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable)
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
+	unsigned long ftrace_old_addr;
 	unsigned long ftrace_addr;
 	int ret;
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
-
 	ret = ftrace_update_record(rec, enable);
 
+	if (rec->flags & FTRACE_FL_REGS)
+		ftrace_addr = (unsigned long)FTRACE_REGS_ADDR;
+	else
+		ftrace_addr = (unsigned long)FTRACE_ADDR;
+
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
@@ -1668,6 +1733,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 
 	case FTRACE_UPDATE_MAKE_NOP:
 		return ftrace_make_nop(NULL, rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
+		if (rec->flags & FTRACE_FL_REGS)
+			ftrace_old_addr = (unsigned long)FTRACE_ADDR;
+		else
+			ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR;
+
+		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
 	return -1; /* unknow ftrace bug */
@@ -2421,8 +2495,9 @@ static int t_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "%ps", (void *)rec->ip);
 	if (iter->flags & FTRACE_ITER_ENABLED)
-		seq_printf(m, " (%ld)",
-			   rec->flags & ~FTRACE_FL_MASK);
+		seq_printf(m, " (%ld)%s",
+			   rec->flags & ~FTRACE_FL_MASK,
+			   rec->flags & FTRACE_FL_REGS ? " R" : "");
 	seq_printf(m, "\n");
 
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From 4740974a6844156c14d741b0080b59d275679a23 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 20 Jul 2012 11:04:44 -0400
Subject: ftrace: Add default recursion protection for function tracing

As more users of the function tracer utility are being added, they do
not always add the necessary recursion protection. To protect from
function recursion due to tracing, if the callback ftrace_ops does not
specifically specify that it protects against recursion (by setting
the FTRACE_OPS_FL_RECURSION_SAFE flag), the list operation will be
called by the mcount trampoline which adds recursion protection.

If the flag is set, then the function will be called directly with no
extra protection.

Note, the list operation is called if more than one function callback
is registered, or if the arch does not support all of the function
tracer features.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h            |  5 +++++
 kernel/trace/ftrace.c             | 10 ++++++++--
 kernel/trace/trace_events.c       |  1 +
 kernel/trace/trace_functions.c    |  4 ++--
 kernel/trace/trace_irqsoff.c      |  2 +-
 kernel/trace/trace_sched_wakeup.c |  2 +-
 kernel/trace/trace_selftest.c     |  7 +++++--
 kernel/trace/trace_stack.c        |  1 +
 8 files changed, 24 insertions(+), 8 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ab39990cc43..65a14e47a0d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -85,6 +85,10 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  *            passing regs to the handler.
  *            Note, if this flag is set, the SAVE_REGS flag will automatically
  *            get set upon registering the ftrace_ops, if the arch supports it.
+ * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure
+ *            that the call back has its own recursion protection. If it does
+ *            not set this, then the ftrace infrastructure will add recursion
+ *            protection for the caller.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -93,6 +97,7 @@ enum {
 	FTRACE_OPS_FL_CONTROL			= 1 << 3,
 	FTRACE_OPS_FL_SAVE_REGS			= 1 << 4,
 	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 5,
+	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 6,
 };
 
 struct ftrace_ops {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c55f7e27461..ad765b4ba42 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -66,6 +66,7 @@
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -221,12 +222,13 @@ static void update_ftrace_function(void)
 
 	/*
 	 * If we are at the end of the list and this ops is
-	 * not dynamic and the arch supports passing ops, then have the
-	 * mcount trampoline call the function directly.
+	 * recursion safe and not dynamic and the arch supports passing ops,
+	 * then have the mcount trampoline call the function directly.
 	 */
 	if (ftrace_ops_list == &ftrace_list_end ||
 	    (ftrace_ops_list->next == &ftrace_list_end &&
 	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
+	     (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
 		if (ftrace_ops_list == &global_ops)
@@ -867,6 +869,7 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static int register_ftrace_profiler(void)
@@ -1049,6 +1052,7 @@ static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
 	.notrace_hash		= EMPTY_HASH,
 	.filter_hash		= EMPTY_HASH,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static DEFINE_MUTEX(ftrace_regex_lock);
@@ -3967,6 +3971,7 @@ void __init ftrace_init(void)
 
 static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static int __init ftrace_nodyn_init(void)
@@ -4023,6 +4028,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 
 static struct ftrace_ops control_ops = {
 	.func = ftrace_ops_control_func,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static inline void
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 8c669683368..6825d833a25 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1721,6 +1721,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __initdata  =
 {
 	.func = function_test_events_call,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static __init void event_trace_self_test_with_function(void)
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 5675ebd541f..fdff65dff1b 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -153,13 +153,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = function_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops trace_stack_ops __read_mostly =
 {
 	.func = function_stack_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 /* Our two options */
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index c7a9ba936de..d98ee8283b2 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -154,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = irqsoff_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 7547e36d483..02170c00c41 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -130,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = wakeup_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index add37e019fd..1fb6da85ff8 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -148,19 +148,22 @@ static void trace_selftest_test_dyn_func(unsigned long ip,
 
 static struct ftrace_ops test_probe1 = {
 	.func			= trace_selftest_test_probe1_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe2 = {
 	.func			= trace_selftest_test_probe2_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe3 = {
 	.func			= trace_selftest_test_probe3_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_global = {
-	.func			= trace_selftest_test_global_func,
-	.flags			= FTRACE_OPS_FL_GLOBAL,
+	.func		= trace_selftest_test_global_func,
+	.flags		= FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static void print_counts(void)
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2fa5328e889..0c1b165778e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -137,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = stack_trace_call,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static ssize_t
-- 
cgit v1.2.3-70-g09d2


From ea701f11da44b44907af226fe5a5f57d2f26eeb2 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 20 Jul 2012 13:08:05 -0400
Subject: ftrace: Add selftest to test function trace recursion protection

Add selftests to test the function tracing recursion protection actually
does work. It also tests if a ftrace_ops states it will perform its own
protection. Although, even if the ftrace_ops states it will protect itself,
the ftrace infrastructure may still provide protection if the arch does
not support all features or another ftrace_ops is registered.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h        |   6 ++
 kernel/trace/ftrace.c         |  21 +++++++
 kernel/trace/trace_selftest.c | 136 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 163 insertions(+)

(limited to 'kernel/trace/ftrace.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 65a14e47a0d..9962e954a63 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -220,6 +220,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1,
  */
 #define register_ftrace_function(ops) ({ 0; })
 #define unregister_ftrace_function(ops) ({ 0; })
+static inline int ftrace_nr_registered_ops(void)
+{
+	return 0;
+}
 static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_stop(void) { }
@@ -275,6 +279,8 @@ extern void unregister_ftrace_function_probe_all(char *glob);
 
 extern int ftrace_text_reserved(void *start, void *end);
 
+extern int ftrace_nr_registered_ops(void);
+
 /*
  * The dyn_ftrace record's flags field is split into two parts.
  * the first part which is '0-FTRACE_REF_MAX' is a counter of
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ad765b4ba42..528d997c7f9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -111,6 +111,27 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
 #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
 #endif
 
+/**
+ * ftrace_nr_registered_ops - return number of ops registered
+ *
+ * Returns the number of ftrace_ops registered and tracing functions
+ */
+int ftrace_nr_registered_ops(void)
+{
+	struct ftrace_ops *ops;
+	int cnt = 0;
+
+	mutex_lock(&ftrace_lock);
+
+	for (ops = ftrace_ops_list;
+	     ops != &ftrace_list_end; ops = ops->next)
+		cnt++;
+
+	mutex_unlock(&ftrace_lock);
+
+	return cnt;
+}
+
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
  * can use rcu_dereference_raw() is that elements removed from this list
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 1fb6da85ff8..86422f91dbe 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -406,8 +406,141 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 
 	return ret;
 }
+
+static int trace_selftest_recursion_cnt;
+static void trace_selftest_test_recursion_func(unsigned long ip,
+					       unsigned long pip,
+					       struct ftrace_ops *op,
+					       struct pt_regs *pt_regs)
+{
+	/*
+	 * This function is registered without the recursion safe flag.
+	 * The ftrace infrastructure should provide the recursion
+	 * protection. If not, this will crash the kernel!
+	 */
+	trace_selftest_recursion_cnt++;
+	DYN_FTRACE_TEST_NAME();
+}
+
+static void trace_selftest_test_recursion_safe_func(unsigned long ip,
+						    unsigned long pip,
+						    struct ftrace_ops *op,
+						    struct pt_regs *pt_regs)
+{
+	/*
+	 * We said we would provide our own recursion. By calling
+	 * this function again, we should recurse back into this function
+	 * and count again. But this only happens if the arch supports
+	 * all of ftrace features and nothing else is using the function
+	 * tracing utility.
+	 */
+	if (trace_selftest_recursion_cnt++)
+		return;
+	DYN_FTRACE_TEST_NAME();
+}
+
+static struct ftrace_ops test_rec_probe = {
+	.func			= trace_selftest_test_recursion_func,
+};
+
+static struct ftrace_ops test_recsafe_probe = {
+	.func			= trace_selftest_test_recursion_safe_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int
+trace_selftest_function_recursion(void)
+{
+	int save_ftrace_enabled = ftrace_enabled;
+	int save_tracer_enabled = tracer_enabled;
+	char *func_name;
+	int len;
+	int ret;
+	int cnt;
+
+	/* The previous test PASSED */
+	pr_cont("PASSED\n");
+	pr_info("Testing ftrace recursion: ");
+
+
+	/* enable tracing, and record the filter function */
+	ftrace_enabled = 1;
+	tracer_enabled = 1;
+
+	/* Handle PPC64 '.' name */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	len = strlen(func_name);
+
+	ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1);
+	if (ret) {
+		pr_cont("*Could not set filter* ");
+		goto out;
+	}
+
+	ret = register_ftrace_function(&test_rec_probe);
+	if (ret) {
+		pr_cont("*could not register callback* ");
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	unregister_ftrace_function(&test_rec_probe);
+
+	ret = -1;
+	if (trace_selftest_recursion_cnt != 1) {
+		pr_cont("*callback not called once (%d)* ",
+			trace_selftest_recursion_cnt);
+		goto out;
+	}
+
+	trace_selftest_recursion_cnt = 1;
+
+	pr_cont("PASSED\n");
+	pr_info("Testing ftrace recursion safe: ");
+
+	ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1);
+	if (ret) {
+		pr_cont("*Could not set filter* ");
+		goto out;
+	}
+
+	ret = register_ftrace_function(&test_recsafe_probe);
+	if (ret) {
+		pr_cont("*could not register callback* ");
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	unregister_ftrace_function(&test_recsafe_probe);
+
+	/*
+	 * If arch supports all ftrace features, and no other task
+	 * was on the list, we should be fine.
+	 */
+	if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC)
+		cnt = 2; /* Should have recursed */
+	else
+		cnt = 1;
+
+	ret = -1;
+	if (trace_selftest_recursion_cnt != cnt) {
+		pr_cont("*callback not called expected %d times (%d)* ",
+			cnt, trace_selftest_recursion_cnt);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	ftrace_enabled = save_ftrace_enabled;
+	tracer_enabled = save_tracer_enabled;
+
+	return ret;
+}
 #else
 # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
+# define trace_selftest_function_recursion() ({ 0; })
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /*
@@ -455,7 +588,10 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 
 	ret = trace_selftest_startup_dynamic_tracing(trace, tr,
 						     DYN_FTRACE_TEST_NAME);
+	if (ret)
+		goto out;
 
+	ret = trace_selftest_function_recursion();
  out:
 	ftrace_enabled = save_ftrace_enabled;
 	tracer_enabled = save_tracer_enabled;
-- 
cgit v1.2.3-70-g09d2


From 647664eaf4033501739ac1f42dd52ce8c9266ccc Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Tue, 5 Jun 2012 19:28:08 +0900
Subject: ftrace: add ftrace_set_filter_ip() for address based filter

Add a new filter update interface ftrace_set_filter_ip()
to set ftrace filter by ip address, not only glob pattern.

Link: http://lkml.kernel.org/r/20120605102808.27845.67952.stgit@localhost.localdomain

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  3 +++
 kernel/trace/ftrace.c  | 59 ++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 2 deletions(-)

(limited to 'kernel/trace/ftrace.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9962e954a63..3e711122f66 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -317,6 +317,8 @@ struct dyn_ftrace {
 };
 
 int ftrace_force_update(void);
+int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
+			 int remove, int reset);
 int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
 		       int len, int reset);
 int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
@@ -544,6 +546,7 @@ static inline int ftrace_text_reserved(void *start, void *end)
  */
 #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
 #define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
+#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; })
 #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
 #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
 #define ftrace_free_filter(ops) do { } while (0)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 528d997c7f9..9dcf15d3838 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3242,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf,
 }
 
 static int
-ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
-		 int reset, int enable)
+ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
+{
+	struct ftrace_func_entry *entry;
+
+	if (!ftrace_location(ip))
+		return -EINVAL;
+
+	if (remove) {
+		entry = ftrace_lookup_ip(hash, ip);
+		if (!entry)
+			return -ENOENT;
+		free_hash_entry(hash, entry);
+		return 0;
+	}
+
+	return add_hash_entry(hash, ip);
+}
+
+static int
+ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
+		unsigned long ip, int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *hash;
@@ -3272,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ret = -EINVAL;
 		goto out_regex_unlock;
 	}
+	if (ip) {
+		ret = ftrace_match_addr(hash, ip, remove);
+		if (ret < 0)
+			goto out_regex_unlock;
+	}
 
 	mutex_lock(&ftrace_lock);
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@@ -3288,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 	return ret;
 }
 
+static int
+ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove,
+		int reset, int enable)
+{
+	return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable);
+}
+
+/**
+ * ftrace_set_filter_ip - set a function to filter on in ftrace by address
+ * @ops - the ops to set the filter with
+ * @ip - the address to add to or remove from the filter.
+ * @remove - non zero to remove the ip from the filter
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled
+ * If @ip is NULL, it failes to update filter.
+ */
+int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
+			 int remove, int reset)
+{
+	return ftrace_set_addr(ops, ip, remove, reset, 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
+
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+		 int reset, int enable)
+{
+	return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable);
+}
+
 /**
  * ftrace_set_filter - set a function to filter on in ftrace
  * @ops - the ops to set the filter with
-- 
cgit v1.2.3-70-g09d2