[PATCH 0/11][GIT PULL] tracing: various updates for 2.6.34

[PATCH 0/11][GIT PULL] tracing: various updates for 2.6.34

[Steven Rostedt]

Ingo,

Please pull the latest tip/tracing/core tree, which can be found at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/tracing/core


Lai Jiangshan (7):
      tracing: Have __dynamic_array() define a field
      tracing: Add print_fmt field
      tracing/syscalls: Init print_fmt for syscall events
      tracing/kprobes: Init print_fmt for kprobe events
      tracing: Use defined fields and print_fmt to print formats
      tracing: Remove show_format and related macros from TRACE_EVENT
      tracing: Consolidate protection of reader access to the ring buffer

Steven Rostedt (2):
      tracing: Have syscall tracing call its own init function
      tracing: Add stack dump to trace_printk if stacktrace option is set

Wolfram Sang (2):
      tracing: optimize recordmcount.pl for offsets-handling
      tracing: Use appropriate perl constructs in recordmcount.pl

----
 include/linux/ftrace_event.h  |    3 +-
 include/linux/syscalls.h      |    6 +-
 include/trace/ftrace.h        |  161 +++++++++--------------------------------
 include/trace/syscall.h       |    4 -
 kernel/trace/trace.c          |  144 ++++++++++++++++++++++++++-----------
 kernel/trace/trace_events.c   |   77 +++++++++++---------
 kernel/trace/trace_export.c   |   87 ++++-------------------
 kernel/trace/trace_kprobe.c   |  104 +++++++++++---------------
 kernel/trace/trace_syscalls.c |  106 ++++++++++++++--------------
 scripts/recordmcount.pl       |   47 +++++-------
 10 files changed, 310 insertions(+), 429 deletions(-)

[PATCH 01/11] tracing: Have __dynamic_array() define a field

[Steven Rostedt]

[-- Attachment #1: 0001-tracing-Have-__dynamic_array-define-a-field.patch --]
[-- Type: text/plain, Size: 1233 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

This is part of a patch set that removes the show_format method
in the ftrace event macros.

This patch set requires that all fields are added to the
ftrace_event_call->fields. This patch changes __dynamic_array()
to call trace_define_field() to include fields that use __dynamic_array().

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D36.8090100@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_export.c |    7 ++++++-
 1 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d4fa5dc..9978a4f 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -175,7 +175,12 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 		return ret;
 
 #undef __dynamic_array
-#define __dynamic_array(type, item)
+#define __dynamic_array(type, item)					\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 0, is_signed_type(type), FILTER_OTHER);\
+	if (ret)							\
+		return ret;
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
-- 
1.6.5

[PATCH 02/11] tracing: Add print_fmt field

[Steven Rostedt]

[-- Attachment #1: 0002-tracing-Add-print_fmt-field.patch --]
[-- Type: text/plain, Size: 4683 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

This is part of a patch set that removes the show_format method
in the ftrace event macros.

The print_fmt field is added to hold the string that shows
the print_fmt in the event format files. This patch only adds
the field but it is currently not used. Later patches will use
this field to enable us to remove the show_format field
and function.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D3E.2000704@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |    1 +
 include/trace/ftrace.h       |   28 +++++++++++++++++++++++++++-
 kernel/trace/trace_export.c  |    7 +++++++
 3 files changed, 35 insertions(+), 1 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 2233c98..bd23d8e 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -121,6 +121,7 @@ struct ftrace_event_call {
 	int			(*regfunc)(struct ftrace_event_call *);
 	void			(*unregfunc)(struct ftrace_event_call *);
 	int			id;
+	const char		*print_fmt;
 	int			(*raw_init)(struct ftrace_event_call *);
 	int			(*show_format)(struct ftrace_event_call *,
 					       struct trace_seq *);
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6fe03e..3351d85 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -722,8 +722,20 @@ static struct trace_event ftrace_event_type_##call = {			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef __entry
+#define __entry REC
+
+#undef __print_flags
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
+
 #undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+static const char print_fmt_##call[] = print;
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
@@ -737,6 +749,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.raw_init		= trace_event_raw_init,			\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.print_fmt		= print_fmt_##template,			\
 	.show_format		= ftrace_format_##template,		\
 	.define_fields		= ftrace_define_fields_##template,	\
 	_TRACE_PROFILE_INIT(call)					\
@@ -745,6 +758,8 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
 									\
+static const char print_fmt_##call[] = print;				\
+									\
 static struct ftrace_event_call __used					\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
@@ -754,6 +769,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.raw_init		= trace_event_raw_init,			\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.print_fmt		= print_fmt_##call,			\
 	.show_format		= ftrace_format_##call,			\
 	.define_fields		= ftrace_define_fields_##template,	\
 	_TRACE_PROFILE_INIT(call)					\
@@ -837,6 +853,16 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #ifdef CONFIG_EVENT_PROFILE
 
+#undef __entry
+#define __entry entry
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
 #undef __perf_addr
 #define __perf_addr(a) __addr = (a)
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 9978a4f..95d14b6 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -203,6 +203,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 	return 0;
 }
 
+#undef __entry
+#define __entry REC
+
 #undef __field
 #define __field(type, item)
 
@@ -218,6 +221,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 #undef __dynamic_array
 #define __dynamic_array(type, item)
 
+#undef F_printk
+#define F_printk(fmt, args...) #fmt ", "  __stringify(args)
+
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
 									\
@@ -228,6 +234,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.id			= type,					\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.raw_init		= ftrace_raw_init_event,		\
+	.print_fmt		= print,				\
 	.show_format		= ftrace_format_##call,			\
 	.define_fields		= ftrace_define_fields_##call,		\
 };									\
-- 
1.6.5

[PATCH 03/11] tracing/syscalls: Init print_fmt for syscall events

[Steven Rostedt]

[-- Attachment #1: 0003-tracing-syscalls-Init-print_fmt-for-syscall-events.patch --]
[-- Type: text/plain, Size: 2823 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

This is part of a patch set that removes the show_format method
in the ftrace event macros.

Add the print_fmt initialization to the syscall events.
The print_fmt is still not used, but will be in the follow up
patches.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D41.609@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_syscalls.c |   68 ++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 67 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 75289f3..1352b0a 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -191,6 +191,67 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 	return trace_seq_putc(s, '\n');
 }
 
+static
+int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
+{
+	int i;
+	int pos = 0;
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+	for (i = 0; i < entry->nb_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+				entry->args[i], sizeof(unsigned long),
+				i == entry->nb_args - 1 ? "" : ", ");
+	}
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	for (i = 0; i < entry->nb_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO,
+				", ((unsigned long)(REC->%s))", entry->args[i]);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
+{
+	char *print_fmt;
+	int len;
+	struct syscall_metadata *entry = call->data;
+
+	if (entry->enter_event != call) {
+		call->print_fmt = "\"0x%lx\", REC->ret";
+		return 0;
+	}
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_enter_print_fmt(entry, NULL, 0);
+
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_enter_print_fmt(entry, print_fmt, len + 1);
+	call->print_fmt = print_fmt;
+
+	return 0;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+	struct syscall_metadata *entry = call->data;
+
+	if (entry->enter_event == call)
+		kfree(call->print_fmt);
+}
+
 int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
 	int ret;
@@ -386,9 +447,14 @@ int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
 
+	if (set_syscall_print_fmt(call) < 0)
+		return -ENOMEM;
+
 	id = register_ftrace_event(call->event);
-	if (!id)
+	if (!id) {
+		free_syscall_print_fmt(call);
 		return -ENODEV;
+	}
 	call->id = id;
 	INIT_LIST_HEAD(&call->fields);
 	return 0;
-- 
1.6.5

[PATCH 04/11] tracing/kprobes: Init print_fmt for kprobe events

[Steven Rostedt]

[-- Attachment #1: 0004-tracing-kprobes-Init-print_fmt-for-kprobe-events.patch --]
[-- Type: text/plain, Size: 3312 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

This is part of a patch set that removes the show_format method
in the ftrace event macros.

Add the print_fmt initialization to the kprobe events.
The print_fmt is still not used, but will be in the follow up
patches.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D45.3080100@cn.fujitsu.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c |   64 ++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 63 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6ea90c0..147491d 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1250,6 +1250,62 @@ static int kretprobe_event_show_format(struct ftrace_event_call *call,
 					 ", REC->" FIELD_STRING_RETIP);
 }
 
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
+{
+	int i;
+	int pos = 0;
+
+	const char *fmt, *arg;
+
+	if (!probe_is_return(tp)) {
+		fmt = "(%lx)";
+		arg = "REC->" FIELD_STRING_IP;
+	} else {
+		fmt = "(%lx <- %lx)";
+		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+	}
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
+				tp->args[i].name);
+	}
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+				tp->args[i].name);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+static int set_print_fmt(struct trace_probe *tp)
+{
+	int len;
+	char *print_fmt;
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_print_fmt(tp, NULL, 0);
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_print_fmt(tp, print_fmt, len + 1);
+	tp->call.print_fmt = print_fmt;
+
+	return 0;
+}
+
 #ifdef CONFIG_EVENT_PROFILE
 
 /* Kprobe profile handler */
@@ -1456,10 +1512,14 @@ static int register_probe_event(struct trace_probe *tp)
 		call->show_format = kprobe_event_show_format;
 		call->define_fields = kprobe_event_define_fields;
 	}
+	if (set_print_fmt(tp) < 0)
+		return -ENOMEM;
 	call->event = &tp->event;
 	call->id = register_ftrace_event(&tp->event);
-	if (!call->id)
+	if (!call->id) {
+		kfree(call->print_fmt);
 		return -ENODEV;
+	}
 	call->enabled = 0;
 	call->regfunc = probe_event_enable;
 	call->unregfunc = probe_event_disable;
@@ -1472,6 +1532,7 @@ static int register_probe_event(struct trace_probe *tp)
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n", call->name);
+		kfree(call->print_fmt);
 		unregister_ftrace_event(&tp->event);
 	}
 	return ret;
@@ -1481,6 +1542,7 @@ static void unregister_probe_event(struct trace_probe *tp)
 {
 	/* tp->event is unregistered in trace_remove_event_call() */
 	trace_remove_event_call(&tp->call);
+	kfree(tp->call.print_fmt);
 }
 
 /* Make a debugfs interface for controling probe points */
-- 
1.6.5

[PATCH 05/11] tracing: Have syscall tracing call its own init function

[Steven Rostedt]

[-- Attachment #1: 0005-tracing-Have-syscall-tracing-call-its-own-init-funct.patch --]
[-- Type: text/plain, Size: 2226 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

In the clean up of having all events call one specific function,
the syscall event init was changed to call this helper function.

With the new print_fmt updates, the syscalls need to do special
initializations. This patch converts the syscall events to call
its own init function again.

Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h      |    4 ++--
 kernel/trace/trace_syscalls.c |   12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 207466a..ed353d2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -143,7 +143,7 @@ struct perf_event_attr;
 		.name                   = "sys_enter"#sname,		\
 		.system                 = "syscalls",			\
 		.event                  = &enter_syscall_print_##sname,	\
-		.raw_init		= trace_event_raw_init,		\
+		.raw_init		= init_syscall_trace,		\
 		.show_format		= syscall_enter_format,		\
 		.define_fields		= syscall_enter_define_fields,	\
 		.regfunc		= reg_event_syscall_enter,	\
@@ -165,7 +165,7 @@ struct perf_event_attr;
 		.name                   = "sys_exit"#sname,		\
 		.system                 = "syscalls",			\
 		.event                  = &exit_syscall_print_##sname,	\
-		.raw_init		= trace_event_raw_init,		\
+		.raw_init		= init_syscall_trace,		\
 		.show_format		= syscall_exit_format,		\
 		.define_fields		= syscall_exit_define_fields,	\
 		.regfunc		= reg_event_syscall_exit,	\
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 1352b0a..a78e863 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -450,14 +450,14 @@ int init_syscall_trace(struct ftrace_event_call *call)
 	if (set_syscall_print_fmt(call) < 0)
 		return -ENOMEM;
 
-	id = register_ftrace_event(call->event);
-	if (!id) {
+	id = trace_event_raw_init(call);
+
+	if (id < 0) {
 		free_syscall_print_fmt(call);
-		return -ENODEV;
+		return id;
 	}
-	call->id = id;
-	INIT_LIST_HEAD(&call->fields);
-	return 0;
+
+	return id;
 }
 
 int __init init_ftrace_syscalls(void)
-- 
1.6.5

[PATCH 06/11] tracing: Use defined fields and print_fmt to print formats

[Steven Rostedt]

[-- Attachment #1: 0006-tracing-Use-defined-fields-and-print_fmt-to-print-fo.patch --]
[-- Type: text/plain, Size: 3706 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

The calls ftrace_format_##call() and ftrace_define_fields_##call()
are almost duplicate in functionality. With the addition of the
print_fmt in previous patches, these two functions can be merged
into one.

The trace_define_field() defines the fields and links them into
the struct ftrace_event_call. The previous patches introduced
the print_fmt field and this can now be used with the trace_define_field()
to create the event format file fields and print_fmt field.

The struct ftrace_event_call->fields are used to print the fields
The struct ftrace_event_call->print_fmt is used to print
the "print fmt: XXXXXXXXXXX" line.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D49.5000006@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c |   65 +++++++++++++++++++++++++++----------------
 1 files changed, 41 insertions(+), 24 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 189b09b..250ec86 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -528,33 +528,16 @@ extern char *__bad_type_size(void);
 	#type, "common_" #name, offsetof(typeof(field), name),		\
 		sizeof(field.name), is_signed_type(type)
 
-static int trace_write_header(struct trace_seq *s)
-{
-	struct trace_entry field;
-
-	/* struct trace_entry */
-	return trace_seq_printf(s,
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\n",
-			FIELD(unsigned short, type),
-			FIELD(unsigned char, flags),
-			FIELD(unsigned char, preempt_count),
-			FIELD(int, pid),
-			FIELD(int, lock_depth));
-}
-
 static ssize_t
 event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
+	struct ftrace_event_field *field;
 	struct trace_seq *s;
+	int common_field_count = 5;
 	char *buf;
-	int r;
+	int r = 0;
 
 	if (*ppos)
 		return 0;
@@ -565,14 +548,48 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	/* If any of the first writes fail, so will the show_format. */
-
 	trace_seq_printf(s, "name: %s\n", call->name);
 	trace_seq_printf(s, "ID: %d\n", call->id);
 	trace_seq_printf(s, "format:\n");
-	trace_write_header(s);
 
-	r = call->show_format(call, s);
+	list_for_each_entry_reverse(field, &call->fields, link) {
+		/*
+		 * Smartly shows the array type(except dynamic array).
+		 * Normal:
+		 *	field:TYPE VAR
+		 * If TYPE := TYPE[LEN], it is shown:
+		 *	field:TYPE VAR[LEN]
+		 */
+		const char *array_descriptor = strchr(field->type, '[');
+
+		if (!strncmp(field->type, "__data_loc", 10))
+			array_descriptor = NULL;
+
+		if (!array_descriptor) {
+			r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					field->type, field->name, field->offset,
+					field->size, !!field->is_signed);
+		} else {
+			r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					(int)(array_descriptor - field->type),
+					field->type, field->name,
+					array_descriptor, field->offset,
+					field->size, !!field->is_signed);
+		}
+
+		if (--common_field_count == 0)
+			r = trace_seq_printf(s, "\n");
+
+		if (!r)
+			break;
+	}
+
+	if (r)
+		r = trace_seq_printf(s, "\nprint fmt: %s\n",
+				call->print_fmt);
+
 	if (!r) {
 		/*
 		 * ug!  The format output is bigger than a PAGE!!
-- 
1.6.5

[PATCH 07/11] tracing: Remove show_format and related macros from TRACE_EVENT

[Steven Rostedt]

[-- Attachment #1: 0007-tracing-Remove-show_format-and-related-macros-from-T.patch --]
[-- Type: text/plain, Size: 17856 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

The previous patches added the use of print_fmt string and changes
the trace_define_field() function to also create the fields and
format output for the event format files.

   text	   data	    bss	    dec	    hex	filename
5857201	1355780	9336808	16549789	 fc879d	vmlinux
5884589	1351684	9337896	16574169	 fce6d9	vmlinux-orig

The above shows the size of the vmlinux after this patch set
compared to the vmlinux-orig which is before the patch set.

This saves us 27k on text, 1k on bss and adds just 4k of data.

The total savings of 24k in size.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D4D.40604@cn.fujitsu.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h  |    2 -
 include/linux/syscalls.h      |    2 -
 include/trace/ftrace.h        |  133 ++---------------------------------------
 include/trace/syscall.h       |    4 -
 kernel/trace/trace_events.c   |   12 ----
 kernel/trace/trace_export.c   |   73 ----------------------
 kernel/trace/trace_kprobe.c   |   78 ------------------------
 kernel/trace/trace_syscalls.c |   66 --------------------
 8 files changed, 6 insertions(+), 364 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index bd23d8e..84a5629 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -123,8 +123,6 @@ struct ftrace_event_call {
 	int			id;
 	const char		*print_fmt;
 	int			(*raw_init)(struct ftrace_event_call *);
-	int			(*show_format)(struct ftrace_event_call *,
-					       struct trace_seq *);
 	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
 	int			filter_active;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ed353d2..7b21969 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -144,7 +144,6 @@ struct perf_event_attr;
 		.system                 = "syscalls",			\
 		.event                  = &enter_syscall_print_##sname,	\
 		.raw_init		= init_syscall_trace,		\
-		.show_format		= syscall_enter_format,		\
 		.define_fields		= syscall_enter_define_fields,	\
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
@@ -166,7 +165,6 @@ struct perf_event_attr;
 		.system                 = "syscalls",			\
 		.event                  = &exit_syscall_print_##sname,	\
 		.raw_init		= init_syscall_trace,		\
-		.show_format		= syscall_exit_format,		\
 		.define_fields		= syscall_exit_define_fields,	\
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3351d85..df65b99 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -131,130 +131,6 @@
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Setup the showing format of trace point.
- *
- * int
- * ftrace_format_##call(struct trace_seq *s)
- * {
- *	struct ftrace_raw_##call field;
- *	int ret;
- *
- *	ret = trace_seq_printf(s, #type " " #item ";"
- *			       " offset:%u; size:%u;\n",
- *			       offsetof(struct ftrace_raw_##call, item),
- *			       sizeof(field.type));
- *
- * }
- */
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef __field
-#define __field(type, item)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item),	\
-			       (unsigned int)is_signed_type(type));	\
-	if (!ret)							\
-		return 0;
-
-#undef __field_ext
-#define __field_ext(type, item, filter_type)	__field(type, item)
-
-#undef __array
-#define __array(type, item, len)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
-			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item),	\
-			       (unsigned int)is_signed_type(type));	\
-	if (!ret)							\
-		return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)				       \
-	ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\
-			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	       \
-			       (unsigned int)offsetof(typeof(field),	       \
-					__data_loc_##item),		       \
-			       (unsigned int)sizeof(field.__data_loc_##item), \
-			       (unsigned int)is_signed_type(type));	\
-	if (!ret)							       \
-		return 0;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __entry
-#define __entry REC
-
-#undef __print_symbolic
-#undef __get_dynamic_array
-#undef __get_str
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "\"%s\", %s\n", fmt, __stringify(args)
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TP_perf_assign
-#define TP_perf_assign(args...)
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
-static int								\
-ftrace_format_setup_##call(struct ftrace_event_call *unused,		\
-			   struct trace_seq *s)				\
-{									\
-	struct ftrace_raw_##call field __attribute__((unused));		\
-	int ret = 0;							\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}									\
-									\
-static int								\
-ftrace_format_##call(struct ftrace_event_call *unused,			\
-		     struct trace_seq *s)				\
-{									\
-	int ret = 0;							\
-									\
-	ret = ftrace_format_setup_##call(unused, s);			\
-	if (!ret)							\
-		return ret;						\
-									\
-	ret = trace_seq_printf(s, "\nprint fmt: " print);		\
-									\
-	return ret;							\
-}
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)		\
-static int								\
-ftrace_format_##name(struct ftrace_event_call *unused,			\
-		      struct trace_seq *s)				\
-{									\
-	int ret = 0;							\
-									\
-	ret = ftrace_format_setup_##template(unused, s);		\
-	if (!ret)							\
-		return ret;						\
-									\
-	trace_seq_printf(s, "\nprint fmt: " print);			\
-									\
-	return ret;							\
-}
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-
-/*
  * Stage 3 of the trace events.
  *
  * Override the macros in <trace/trace_events.h> to include the following:
@@ -622,7 +498,6 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
  *	.raw_init		= trace_event_raw_init,
  *	.regfunc		= ftrace_reg_event_<call>,
  *	.unregfunc		= ftrace_unreg_event_<call>,
- *	.show_format		= ftrace_format_<call>,
  * }
  *
  */
@@ -657,6 +532,12 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
 #define __assign_str(dst, src)						\
 	strcpy(__get_str(dst), src);
 
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TP_perf_assign
+#define TP_perf_assign(args...)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 									\
@@ -750,7 +631,6 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##template,			\
-	.show_format		= ftrace_format_##template,		\
 	.define_fields		= ftrace_define_fields_##template,	\
 	_TRACE_PROFILE_INIT(call)					\
 }
@@ -770,7 +650,6 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##call,			\
-	.show_format		= ftrace_format_##call,			\
 	.define_fields		= ftrace_define_fields_##template,	\
 	_TRACE_PROFILE_INIT(call)					\
 }
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 961fda3..8cd4102 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -34,10 +34,6 @@ struct syscall_metadata {
 extern unsigned long arch_syscall_addr(int nr);
 extern int init_syscall_trace(struct ftrace_event_call *call);
 
-extern int syscall_enter_format(struct ftrace_event_call *call,
-				struct trace_seq *s);
-extern int syscall_exit_format(struct ftrace_event_call *call,
-				struct trace_seq *s);
 extern int syscall_enter_define_fields(struct ftrace_event_call *call);
 extern int syscall_exit_define_fields(struct ftrace_event_call *call);
 extern int reg_event_syscall_enter(struct ftrace_event_call *call);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 250ec86..c2a3077 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -520,14 +520,6 @@ out:
 	return ret;
 }
 
-extern char *__bad_type_size(void);
-
-#undef FIELD
-#define FIELD(type, name)						\
-	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
-	#type, "common_" #name, offsetof(typeof(field), name),		\
-		sizeof(field.name), is_signed_type(type)
-
 static ssize_t
 event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
@@ -965,10 +957,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 				  filter);
 	}
 
-	/* A trace may not want to export its format */
-	if (!call->show_format)
-		return 0;
-
 	trace_create_file("format", 0444, call->dir, call,
 			  format);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 95d14b6..e091f64 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -62,78 +62,6 @@ static void __always_unused ____ftrace_check_##name(void)	\
 
 #include "trace_entries.h"
 
-
-#undef __field
-#define __field(type, item)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       sizeof(field.item), is_signed_type(type)); \
-	if (!ret)							\
-		return 0;
-
-#undef __field_desc
-#define __field_desc(type, container, item)				\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef __array
-#define __array(type, item, len)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       sizeof(field.item), is_signed_type(type)); \
-	if (!ret)							\
-		return 0;
-
-#undef __array_desc
-#define __array_desc(type, container, item, len)			\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:0;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef F_printk
-#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef __entry
-#define __entry REC
-
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
-static int								\
-ftrace_format_##name(struct ftrace_event_call *unused,			\
-		     struct trace_seq *s)				\
-{									\
-	struct struct_name field __attribute__((unused));		\
-	int ret = 0;							\
-									\
-	tstruct;							\
-									\
-	trace_seq_printf(s, "\nprint fmt: " print);			\
-									\
-	return ret;							\
-}
-
-#include "trace_entries.h"
-
 #undef __field
 #define __field(type, item)						\
 	ret = trace_define_field(event_call, #type, #item,		\
@@ -235,7 +163,6 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.raw_init		= ftrace_raw_init_event,		\
 	.print_fmt		= print,				\
-	.show_format		= ftrace_format_##call,			\
 	.define_fields		= ftrace_define_fields_##call,		\
 };									\
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 147491d..c990299 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1174,82 +1174,6 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 	return 0;
 }
 
-static int __probe_event_show_format(struct trace_seq *s,
-				     struct trace_probe *tp, const char *fmt,
-				     const char *arg)
-{
-	int i;
-
-	/* Show format */
-	if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
-		return 0;
-
-	for (i = 0; i < tp->nr_args; i++)
-		if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
-			return 0;
-
-	if (!trace_seq_printf(s, "\", %s", arg))
-		return 0;
-
-	for (i = 0; i < tp->nr_args; i++)
-		if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
-			return 0;
-
-	return trace_seq_puts(s, "\n");
-}
-
-#undef SHOW_FIELD
-#define SHOW_FIELD(type, item, name)					\
-	do {								\
-		ret = trace_seq_printf(s, "\tfield:" #type " %s;\t"	\
-				"offset:%u;\tsize:%u;\tsigned:%d;\n", name,\
-				(unsigned int)offsetof(typeof(field), item),\
-				(unsigned int)sizeof(type),		\
-				is_signed_type(type));			\
-		if (!ret)						\
-			return 0;					\
-	} while (0)
-
-static int kprobe_event_show_format(struct ftrace_event_call *call,
-				    struct trace_seq *s)
-{
-	struct kprobe_trace_entry field __attribute__((unused));
-	int ret, i;
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
-	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
-
-	/* Show fields */
-	for (i = 0; i < tp->nr_args; i++)
-		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
-	trace_seq_puts(s, "\n");
-
-	return __probe_event_show_format(s, tp, "(%lx)",
-					 "REC->" FIELD_STRING_IP);
-}
-
-static int kretprobe_event_show_format(struct ftrace_event_call *call,
-				       struct trace_seq *s)
-{
-	struct kretprobe_trace_entry field __attribute__((unused));
-	int ret, i;
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
-	SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
-	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
-
-	/* Show fields */
-	for (i = 0; i < tp->nr_args; i++)
-		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
-	trace_seq_puts(s, "\n");
-
-	return __probe_event_show_format(s, tp, "(%lx <- %lx)",
-					 "REC->" FIELD_STRING_FUNC
-					 ", REC->" FIELD_STRING_RETIP);
-}
-
 static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 {
 	int i;
@@ -1504,12 +1428,10 @@ static int register_probe_event(struct trace_probe *tp)
 	if (probe_is_return(tp)) {
 		tp->event.trace = print_kretprobe_event;
 		call->raw_init = probe_event_raw_init;
-		call->show_format = kretprobe_event_show_format;
 		call->define_fields = kretprobe_event_define_fields;
 	} else {
 		tp->event.trace = print_kprobe_event;
 		call->raw_init = probe_event_raw_init;
-		call->show_format = kprobe_event_show_format;
 		call->define_fields = kprobe_event_define_fields;
 	}
 	if (set_print_fmt(tp) < 0)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a78e863..49cea70 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -143,54 +143,6 @@ extern char *__bad_type_size(void);
 		#type, #name, offsetof(typeof(trace), name),		\
 		sizeof(trace.name), is_signed_type(type)
 
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
-{
-	int i;
-	int ret;
-	struct syscall_metadata *entry = call->data;
-	struct syscall_trace_enter trace;
-	int offset = offsetof(struct syscall_trace_enter, args);
-
-	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n",
-			       SYSCALL_FIELD(int, nr));
-	if (!ret)
-		return 0;
-
-	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
-				        entry->args[i]);
-		if (!ret)
-			return 0;
-		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
-				       "\tsigned:%u;\n", offset,
-				       sizeof(unsigned long),
-				       is_signed_type(unsigned long));
-		if (!ret)
-			return 0;
-		offset += sizeof(unsigned long);
-	}
-
-	trace_seq_puts(s, "\nprint fmt: \"");
-	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
-				        sizeof(unsigned long),
-					i == entry->nb_args - 1 ? "" : ", ");
-		if (!ret)
-			return 0;
-	}
-	trace_seq_putc(s, '"');
-
-	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
-				       entry->args[i]);
-		if (!ret)
-			return 0;
-	}
-
-	return trace_seq_putc(s, '\n');
-}
-
 static
 int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
@@ -252,24 +204,6 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
 		kfree(call->print_fmt);
 }
 
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
-{
-	int ret;
-	struct syscall_trace_exit trace;
-
-	ret = trace_seq_printf(s,
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n"
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n",
-			       SYSCALL_FIELD(int, nr),
-			       SYSCALL_FIELD(long, ret));
-	if (!ret)
-		return 0;
-
-	return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
-}
-
 int syscall_enter_define_fields(struct ftrace_event_call *call)
 {
 	struct syscall_trace_enter trace;
-- 
1.6.5

[PATCH 08/11] tracing: Consolidate protection of reader access to the ring buffer

[Steven Rostedt]

[-- Attachment #1: 0008-tracing-Consolidate-protection-of-reader-access-to-t.patch --]
[-- Type: text/plain, Size: 9466 bytes --]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

At the beginning, access to the ring buffer was fully serialized
by trace_types_lock. Patch d7350c3f4569 gives more freedom to readers,
and patch b04cc6b1f6 adds code to protect trace_pipe and cpu#/trace_pipe.

But actually it is not enough, ring buffer readers are not always
read-only, they may consume data.

This patch makes accesses to trace, trace_pipe, trace_pipe_raw
cpu#/trace, cpu#/trace_pipe and cpu#/trace_pipe_raw serialized.
And removes tracing_reader_cpumask which is used to protect trace_pipe.

Details:

Ring buffer serializes readers, but it is low level protection.
The validity of the events (which returns by ring_buffer_peek() ..etc)
are not protected by ring buffer.

The content of events may become garbage if we allow another process to consume
these events concurrently:
  A) the page of the consumed events may become a normal page
     (not reader page) in ring buffer, and this page will be rewritten
     by the events producer.
  B) The page of the consumed events may become a page for splice_read,
     and this page will be returned to system.

This patch adds trace_access_lock() and trace_access_unlock() primitives.

These primitives allow multi process access to different cpu ring buffers
concurrently.

These primitives don't distinguish read-only and read-consume access.
Multi read-only access is also serialized.

And we don't use these primitives when we open files,
we only use them when we read files.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B447D52.1050602@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |  136 +++++++++++++++++++++++++++++++++++--------------
 1 files changed, 97 insertions(+), 39 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f..abdd333 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -32,6 +32,7 @@
 #include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/string.h>
+#include <linux/rwsem.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -102,9 +103,6 @@ static inline void ftrace_enable_cpu(void)
 
 static cpumask_var_t __read_mostly	tracing_buffer_mask;
 
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t			tracing_reader_cpumask;
-
 #define for_each_tracing_cpu(cpu)	\
 	for_each_cpu(cpu, tracing_buffer_mask)
 
@@ -243,12 +241,91 @@ static struct tracer		*current_trace __read_mostly;
 
 /*
  * trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
  */
 static DEFINE_MUTEX(trace_types_lock);
 
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ *   A) the page of the consumed events may become a normal page
+ *      (not reader page) in ring buffer, and this page will be rewrited
+ *      by events producer.
+ *   B) The page of the consumed events may become a page for splice_read,
+ *      and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		/* gain it for accessing the whole ring buffer. */
+		down_write(&all_cpu_access_lock);
+	} else {
+		/* gain it for accessing a cpu ring buffer. */
+
+		/* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+		down_read(&all_cpu_access_lock);
+
+		/* Secondly block other access to this @cpu ring buffer. */
+		mutex_lock(&per_cpu(cpu_access_lock, cpu));
+	}
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		up_write(&all_cpu_access_lock);
+	} else {
+		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+		up_read(&all_cpu_access_lock);
+	}
+}
+
+static inline void trace_access_lock_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	(void)cpu;
+	mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	(void)cpu;
+	mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
 /* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
@@ -1580,12 +1657,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 }
 
 /*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
  * The current tracer is copied to avoid a global locking
  * all around.
  */
@@ -1640,12 +1711,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(cpu_file);
 	return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
+	struct trace_iterator *iter = m->private;
+
 	atomic_dec(&trace_record_cmdline_disabled);
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
 
@@ -2836,22 +2911,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	mutex_lock(&trace_types_lock);
 
-	/* We only allow one reader per cpu */
-	if (cpu_file == TRACE_PIPE_ALL_CPU) {
-		if (!cpumask_empty(tracing_reader_cpumask)) {
-			ret = -EBUSY;
-			goto out;
-		}
-		cpumask_setall(tracing_reader_cpumask);
-	} else {
-		if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
-			cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
-		else {
-			ret = -EBUSY;
-			goto out;
-		}
-	}
-
 	/* create a buffer to store the information to pass to userspace */
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter) {
@@ -2907,12 +2966,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
-		cpumask_clear(tracing_reader_cpumask);
-	else
-		cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
-
-
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
 
@@ -3074,6 +3127,7 @@ waitagain:
 	iter->pos = -1;
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
@@ -3090,6 +3144,7 @@ waitagain:
 		if (iter->seq.len >= cnt)
 			break;
 	}
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 
 	/* Now copy what we have to the user */
@@ -3215,6 +3270,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 
 	/* Fill as many pages as possible. */
 	for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
@@ -3238,6 +3294,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		trace_seq_init(&iter->seq);
 	}
 
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 	mutex_unlock(&iter->mutex);
 
@@ -3539,10 +3596,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
 
+	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
 				    count,
 				    info->cpu, 0);
+	trace_access_unlock(info->cpu);
 	if (ret < 0)
 		return 0;
 
@@ -3670,6 +3729,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	trace_access_lock(info->cpu);
 	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 
 	for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
@@ -3717,6 +3777,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 	}
 
+	trace_access_unlock(info->cpu);
 	spd.nr_pages = i;
 
 	/* did we read anything? */
@@ -4153,6 +4214,8 @@ static __init int tracer_init_debugfs(void)
 	struct dentry *d_tracer;
 	int cpu;
 
+	trace_access_lock_init();
+
 	d_tracer = tracing_init_dentry();
 
 	trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4387,9 +4450,6 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
-		goto out_free_tracing_cpumask;
-
 	/* To save memory, keep the ring buffer size to its minimum */
 	if (ring_buffer_expanded)
 		ring_buf_size = trace_buf_size;
@@ -4447,8 +4507,6 @@ __init static int tracer_alloc_buffers(void)
 	return 0;
 
 out_free_cpumask:
-	free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
 	free_cpumask_var(tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
-- 
1.6.5

[PATCH 09/11] tracing: optimize recordmcount.pl for offsets-handling

[Steven Rostedt]

[-- Attachment #1: 0009-tracing-optimize-recordmcount.pl-for-offsets-handlin.patch --]
[-- Type: text/plain, Size: 1700 bytes --]

From: Wolfram Sang <w.sang@pengutronix.de>

- move check for open file in front of the writing loop
- use perl-constructs to access the array

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
LKML-Reference: <1262716072-14414-2-git-send-email-w.sang@pengutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 scripts/recordmcount.pl |   18 +++++++++---------
 1 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 92f09fe..5de12c7 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -432,14 +432,14 @@ sub update_funcs
 
     # Loop through all the mcount caller offsets and print a reference
     # to the caller based from the ref_func.
-    for (my $i=0; $i <= $#offsets; $i++) {
-	if (!$opened) {
-	    open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
-	    $opened = 1;
-	    print FILE "\t.section $mcount_section,\"a\",$section_type\n";
-	    print FILE "\t.align $alignment\n" if (defined($alignment));
-	}
-	printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
+    if (!$opened) {
+	open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
+	$opened = 1;
+	print FILE "\t.section $mcount_section,\"a\",$section_type\n";
+	print FILE "\t.align $alignment\n" if (defined($alignment));
+    }
+    foreach my $cur_offset (@offsets) {
+	printf FILE "\t%s %s + %d\n", $type, $ref_func, $cur_offset - $offset;
     }
 }
 
@@ -514,7 +514,7 @@ while (<IN>) {
     }
     # is this a call site to mcount? If so, record it to print later
     if ($text_found && /$mcount_regex/) {
-	$offsets[$#offsets + 1] = hex $1;
+	push(@offsets, hex $1);
     }
 }
 
-- 
1.6.5

[PATCH 10/11] tracing: Use appropriate perl constructs in recordmcount.pl

[Steven Rostedt]

[-- Attachment #1: 0010-tracing-Use-appropriate-perl-constructs-in-recordmco.patch --]
[-- Type: text/plain, Size: 1928 bytes --]

From: Wolfram Sang <w.sang@pengutronix.de>

Modified recordmcount.pl to use perl constructs that are still
understandable by C hackers that are not perl programmers.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
LKML-Reference: <1262724082-9517-1-git-send-email-w.sang@pengutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 scripts/recordmcount.pl |   29 +++++++++++------------------
 1 files changed, 11 insertions(+), 18 deletions(-)

diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 5de12c7..545fe71 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -136,13 +136,14 @@ my %text_sections = (
      ".text.unlikely" => 1,
 );
 
-$objdump = "objdump" if ((length $objdump) == 0);
-$objcopy = "objcopy" if ((length $objcopy) == 0);
-$cc = "gcc" if ((length $cc) == 0);
-$ld = "ld" if ((length $ld) == 0);
-$nm = "nm" if ((length $nm) == 0);
-$rm = "rm" if ((length $rm) == 0);
-$mv = "mv" if ((length $mv) == 0);
+# Note: we are nice to C-programmers here, thus we skip the '||='-idiom.
+$objdump = 'objdump' if (!$objdump);
+$objcopy = 'objcopy' if (!$objcopy);
+$cc = 'gcc' if (!$cc);
+$ld = 'ld' if (!$ld);
+$nm = 'nm' if (!$nm);
+$rm = 'rm' if (!$rm);
+$mv = 'mv' if (!$mv);
 
 #print STDERR "running: $P '$arch' '$objdump' '$objcopy' '$cc' '$ld' " .
 #    "'$nm' '$rm' '$mv' '$inputfile'\n";
@@ -194,12 +195,8 @@ sub check_objcopy
     }
 }
 
-if ($arch eq "x86") {
-    if ($bits == 64) {
-	$arch = "x86_64";
-    } else {
-	$arch = "i386";
-    }
+if ($arch eq 'x86') {
+    $arch = ($bits == 64) ? 'x86_64' : 'i386';
 }
 
 #
@@ -476,11 +473,7 @@ while (<IN>) {
 	$read_headers = 0;
 
 	# Only record text sections that we know are safe
-	if (defined($text_sections{$1})) {
-	    $read_function = 1;
-	} else {
-	    $read_function = 0;
-	}
+	$read_function = defined($text_sections{$1});
 	# print out any recorded offsets
 	update_funcs();
 
-- 
1.6.5

[PATCH 11/11] tracing: Add stack dump to trace_printk if stacktrace option is set

[Steven Rostedt]

[-- Attachment #1: 0011-tracing-Add-stack-dump-to-trace_printk-if-stacktrace.patch --]
[-- Type: text/plain, Size: 1311 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

If the ftrace stacktrace option is set, then add the stack dumps to
trace_printk.

Requested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |    8 ++++++--
 1 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index abdd333..5314c90 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1392,8 +1392,10 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, flags, 6, pc);
+	}
 
 out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
@@ -1466,8 +1468,10 @@ int trace_array_vprintk(struct trace_array *tr,
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = '\0';
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, irq_flags, 6, pc);
+	}
 
  out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
-- 
1.6.5

Re: [PATCH 0/11][GIT PULL] tracing: various updates for 2.6.34

[Ingo Molnar]

* Steven Rostedt <rostedt@goodmis.org> wrote:

> 
> Ingo,
> 
> Please pull the latest tip/tracing/core tree, which can be found at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/tracing/core
> 
> 
> Lai Jiangshan (7):
>       tracing: Have __dynamic_array() define a field
>       tracing: Add print_fmt field
>       tracing/syscalls: Init print_fmt for syscall events
>       tracing/kprobes: Init print_fmt for kprobe events
>       tracing: Use defined fields and print_fmt to print formats
>       tracing: Remove show_format and related macros from TRACE_EVENT
>       tracing: Consolidate protection of reader access to the ring buffer
> 
> Steven Rostedt (2):
>       tracing: Have syscall tracing call its own init function
>       tracing: Add stack dump to trace_printk if stacktrace option is set
> 
> Wolfram Sang (2):
>       tracing: optimize recordmcount.pl for offsets-handling
>       tracing: Use appropriate perl constructs in recordmcount.pl
> 
> ----
>  include/linux/ftrace_event.h  |    3 +-
>  include/linux/syscalls.h      |    6 +-
>  include/trace/ftrace.h        |  161 +++++++++--------------------------------
>  include/trace/syscall.h       |    4 -
>  kernel/trace/trace.c          |  144 ++++++++++++++++++++++++++-----------
>  kernel/trace/trace_events.c   |   77 +++++++++++---------
>  kernel/trace/trace_export.c   |   87 ++++-------------------
>  kernel/trace/trace_kprobe.c   |  104 +++++++++++---------------
>  kernel/trace/trace_syscalls.c |  106 ++++++++++++++--------------
>  scripts/recordmcount.pl       |   47 +++++-------
>  10 files changed, 310 insertions(+), 429 deletions(-)

Pulled, thanks a lot Steve!

	Ingo