[PATCH 00/15] [GIT PULL] tracing: updates for 2.6.39

[PATCH 00/15] [GIT PULL] tracing: updates for 2.6.39

[Steven Rostedt]

Ingo,

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

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


David Sharp (8):
      tracing: Add an 'overwrite' trace_option.
      ring-buffer: Remove unused #include <linux/trace_irq.h>
      tracing: Fix event alignment: ftrace:context_switch and ftrace:wakeup
      tracing: Fix event alignment: module:module_request
      tracing: Fix event alignment: kvm:kvm_hv_hypercall
      tracing: Fix event alignment: mce:mce_record
      tracing: Fix event alignment: skb:kfree_skb
      tracing: Adjust conditional expression latency formatting.

Jiri Olsa (1):
      tracing: Explain about unstable clock on resume with ring buffer warning

Steven Rostedt (5):
      tracing: Remove lock_depth from event entry
      ftrace: Add .ref.text as one of the safe areas to trace
      ftrace/graph: Trace function entry before updating index
      tracing: Align 4 byte ints together in struct tracer
      tracing: Fix irqoff selftest expanding max buffer

Yuanhan Liu (1):
      tracing: Export trace_set_clr_event()

----
 Documentation/trace/ftrace.txt |    5 +++++
 arch/x86/kernel/ftrace.c       |   15 ++++++++-------
 arch/x86/kvm/trace.h           |    8 ++++----
 include/linux/ftrace_event.h   |    1 -
 include/linux/ring_buffer.h    |    2 ++
 include/trace/events/mce.h     |    8 ++++----
 include/trace/events/module.h  |    5 ++---
 include/trace/events/skb.h     |    4 ++--
 kernel/trace/ring_buffer.c     |   24 +++++++++++++++++++++---
 kernel/trace/trace.c           |   34 +++++++++++++++++++++++-----------
 kernel/trace/trace.h           |    3 ++-
 kernel/trace/trace_entries.h   |    6 +++---
 kernel/trace/trace_events.c    |    2 +-
 kernel/trace/trace_output.c    |   36 ++++++++++++++++++++----------------
 scripts/recordmcount.c         |    3 ++-
 scripts/recordmcount.pl        |    1 +
 16 files changed, 100 insertions(+), 57 deletions(-)

[PATCH 01/15] tracing: Add an overwrite trace_option.

[Steven Rostedt]

[-- Attachment #1: 0001-tracing-Add-an-overwrite-trace_option.patch --]
[-- Type: text/plain, Size: 5630 bytes --]

From: David Sharp <dhsharp@google.com>

Add an "overwrite" trace_option for ftrace to control whether the buffer should
be overwritten on overflow or not. The default remains to overwrite old events
when the buffer is full. This patch adds the option to instead discard newest
events when the buffer is full. This is useful to get a snapshot of traces just
after enabling traces. Dropping the current event is also a simpler code path.

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291844807-15481-1-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.txt |    5 +++++
 include/linux/ring_buffer.h    |    2 ++
 kernel/trace/ring_buffer.c     |   11 +++++++++++
 kernel/trace/trace.c           |   17 +++++++++++------
 kernel/trace/trace.h           |    1 +
 5 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 67f1cc4..1ebc24c 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -454,6 +454,11 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
                    latencies, as described in "Latency
                    trace format".
 
+  overwrite - This controls what happens when the trace buffer is
+              full. If "1" (default), the oldest events are
+              discarded and overwritten. If "0", then the newest
+              events are discarded.
+
 ftrace_enabled
 --------------
 
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a248..ab38ac8 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
 						   unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a..269db80 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1429,6 +1429,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+	mutex_lock(&buffer->mutex);
+	if (val)
+		buffer->flags |= RB_FL_OVERWRITE;
+	else
+		buffer->flags &= ~RB_FL_OVERWRITE;
+	mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8dc8da6..85e3ee1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-#define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
 	"sleep-time",
 	"graph-time",
 	"record-cmd",
+	"overwrite",
 	NULL
 };
 
@@ -2529,6 +2528,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
+
+	if (mask == TRACE_ITER_OVERWRITE)
+		ring_buffer_change_overwrite(global_trace.buffer, enabled);
 }
 
 static ssize_t
@@ -4555,9 +4557,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 __init static int tracer_alloc_buffers(void)
 {
 	int ring_buf_size;
+	enum ring_buffer_flags rb_flags;
 	int i;
 	int ret = -ENOMEM;
 
+
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
@@ -4570,12 +4574,13 @@ __init static int tracer_alloc_buffers(void)
 	else
 		ring_buf_size = 1;
 
+	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
-						   TRACE_BUFFER_FLAGS);
+	global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
@@ -4585,7 +4590,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+	max_tr.buffer = ring_buffer_alloc(1, rb_flags);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 856e73c..951d0b7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_SLEEP_TIME		= 0x40000,
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
 	TRACE_ITER_RECORD_CMD		= 0x100000,
+	TRACE_ITER_OVERWRITE		= 0x200000,
 };
 
 /*
-- 
1.7.2.3

[PATCH 02/15] ring-buffer: Remove unused #include <linux/trace_irq.h>

[Steven Rostedt]

[-- Attachment #1: 0002-ring-buffer-Remove-unused-include-linux-trace_irq.h.patch --]
[-- Type: text/plain, Size: 683 bytes --]

From: David Sharp <dhsharp@google.com>

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-3-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 269db80..3237d96 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5,7 +5,6 @@
  */
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
-- 
1.7.2.3

[PATCH 03/15] tracing: Remove lock_depth from event entry

[Steven Rostedt]

[-- Attachment #1: 0003-tracing-Remove-lock_depth-from-event-entry.patch --]
[-- Type: text/plain, Size: 3550 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

The lock_depth field in the event headers was added as a temporary
data point for help in removing the BKL. Now that the BKL is pretty
much been removed, we can remove this field.

This in turn changes the header from 12 bytes to 8 bytes,
removing the 4 byte buffer that gcc would insert if the first field
in the data load was 8 bytes in size.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |    1 -
 kernel/trace/trace.c         |    8 +++-----
 kernel/trace/trace_events.c  |    1 -
 kernel/trace/trace_output.c  |   10 ++--------
 4 files changed, 5 insertions(+), 15 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 1a99e79..22b32af 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			lock_depth;
 };
 
 #define FTRACE_MAX_EVENT						\
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 85e3ee1..fd6e1b9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1101,7 +1101,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->lock_depth		= (tsk) ? tsk->lock_depth : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1748,10 +1747,9 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /_--=> lock-depth       \n");
-	seq_puts(m, "#                |||||/     delay             \n");
-	seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
+	seq_puts(m, "#                |||| /     delay             \n");
+	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5f499e0..e1d579b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, lock_depth);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272ba..151f32e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,7 +529,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  * @entry: The trace entry field from the ring buffer
  *
  * Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
@@ -554,13 +554,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	else
 		ret = trace_seq_putc(s, '.');
 
-	if (!ret)
-		return 0;
-
-	if (entry->lock_depth < 0)
-		return trace_seq_putc(s, '.');
-
-	return trace_seq_printf(s, "%d", entry->lock_depth);
+	return ret;
 }
 
 static int
-- 
1.7.2.3

[PATCH 04/15] tracing: Fix event alignment: ftrace:context_switch and ftrace:wakeup

[Steven Rostedt]

[-- Attachment #1: 0004-tracing-Fix-event-alignment-ftrace-context_switch-an.patch --]
[-- Type: text/plain, Size: 1057 bytes --]

From: David Sharp <dhsharp@google.com>

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-6-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_entries.h |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 6cf2237..1516cb3 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
  */
 #define FTRACE_CTX_FIELDS					\
 	__field(	unsigned int,	prev_pid	)	\
+	__field(	unsigned int,	next_pid	)	\
+	__field(	unsigned int,	next_cpu	)       \
 	__field(	unsigned char,	prev_prio	)	\
 	__field(	unsigned char,	prev_state	)	\
-	__field(	unsigned int,	next_pid	)	\
 	__field(	unsigned char,	next_prio	)	\
-	__field(	unsigned char,	next_state	)	\
-	__field(	unsigned int,	next_cpu	)
+	__field(	unsigned char,	next_state	)
 
 FTRACE_ENTRY(context_switch, ctx_switch_entry,
 
-- 
1.7.2.3

[PATCH 05/15] tracing: Fix event alignment: module:module_request

[Steven Rostedt]

[-- Attachment #1: 0005-tracing-Fix-event-alignment-module-module_request.patch --]
[-- Type: text/plain, Size: 1017 bytes --]

From: David Sharp <dhsharp@google.com>

Acked-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-7-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/module.h |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36..21a546d 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
 	TP_ARGS(name, wait, ip),
 
 	TP_STRUCT__entry(
-		__field(	bool,		wait		)
 		__field(	unsigned long,	ip		)
+		__field(	bool,		wait		)
 		__string(	name,		name		)
 	),
 
 	TP_fast_assign(
-		__entry->wait	= wait;
 		__entry->ip	= ip;
+		__entry->wait	= wait;
 		__assign_str(name, name);
 	),
 
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
-
-- 
1.7.2.3

[PATCH 06/15] tracing: Fix event alignment: kvm:kvm_hv_hypercall

[Steven Rostedt]

[-- Attachment #1: 0006-tracing-Fix-event-alignment-kvm-kvm_hv_hypercall.patch --]
[-- Type: text/plain, Size: 1181 bytes --]

From: David Sharp <dhsharp@google.com>

Acked-by: Avi Kivity <avi@redhat.com>
Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-8-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kvm/trace.h |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1357d7c..db93276 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -62,21 +62,21 @@ TRACE_EVENT(kvm_hv_hypercall,
 	TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa),
 
 	TP_STRUCT__entry(
-		__field(	__u16, 		code		)
-		__field(	bool,		fast		)
 		__field(	__u16,		rep_cnt		)
 		__field(	__u16,		rep_idx		)
 		__field(	__u64,		ingpa		)
 		__field(	__u64,		outgpa		)
+		__field(	__u16, 		code		)
+		__field(	bool,		fast		)
 	),
 
 	TP_fast_assign(
-		__entry->code		= code;
-		__entry->fast		= fast;
 		__entry->rep_cnt	= rep_cnt;
 		__entry->rep_idx	= rep_idx;
 		__entry->ingpa		= ingpa;
 		__entry->outgpa		= outgpa;
+		__entry->code		= code;
+		__entry->fast		= fast;
 	),
 
 	TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx",
-- 
1.7.2.3

[PATCH 07/15] tracing: Fix event alignment: mce:mce_record

[Steven Rostedt]

[-- Attachment #1: 0007-tracing-Fix-event-alignment-mce-mce_record.patch --]
[-- Type: text/plain, Size: 1557 bytes --]

From: David Sharp <dhsharp@google.com>

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-9-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/mce.h |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee778..4cbbcef 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
 	TP_STRUCT__entry(
 		__field(	u64,		mcgcap		)
 		__field(	u64,		mcgstatus	)
-		__field(	u8,		bank		)
 		__field(	u64,		status		)
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
 		__field(	u64,		ip		)
-		__field(	u8,		cs		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
 		__field(	u32,		cpu		)
 		__field(	u32,		cpuid		)
 		__field(	u32,		apicid		)
 		__field(	u32,		socketid	)
+		__field(	u8,		cs		)
+		__field(	u8,		bank		)
 		__field(	u8,		cpuvendor	)
 	),
 
 	TP_fast_assign(
 		__entry->mcgcap		= m->mcgcap;
 		__entry->mcgstatus	= m->mcgstatus;
-		__entry->bank		= m->bank;
 		__entry->status		= m->status;
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
 		__entry->ip		= m->ip;
-		__entry->cs		= m->cs;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
 		__entry->cpu		= m->extcpu;
 		__entry->cpuid		= m->cpuid;
 		__entry->apicid		= m->apicid;
 		__entry->socketid	= m->socketid;
+		__entry->cs		= m->cs;
+		__entry->bank		= m->bank;
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
-- 
1.7.2.3

[PATCH 08/15] tracing: Fix event alignment: skb:kfree_skb

[Steven Rostedt]

[-- Attachment #1: 0008-tracing-Fix-event-alignment-skb-kfree_skb.patch --]
[-- Type: text/plain, Size: 972 bytes --]

From: David Sharp <dhsharp@google.com>

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-10-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/skb.h |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c..0c68ae22 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
 
 	TP_STRUCT__entry(
 		__field(	void *,		skbaddr		)
-		__field(	unsigned short,	protocol	)
 		__field(	void *,		location	)
+		__field(	unsigned short,	protocol	)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		__entry->protocol = ntohs(skb->protocol);
 		__entry->location = location;
+		__entry->protocol = ntohs(skb->protocol);
 	),
 
 	TP_printk("skbaddr=%p protocol=%u location=%p",
-- 
1.7.2.3

[PATCH 09/15] tracing: Adjust conditional expression latency formatting.

[Steven Rostedt]

[-- Attachment #1: 0009-tracing-Adjust-conditional-expression-latency-format.patch --]
[-- Type: text/plain, Size: 1787 bytes --]

From: David Sharp <dhsharp@google.com>

Formatting change only to improve code readability. No code changes except to
introduce intermediate variables.

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-13-git-send-email-dhsharp@google.com>

[ Keep variable declarations and assignment separate ]

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_output.c |   26 ++++++++++++++++++--------
 1 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 151f32e..456be90 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -533,20 +533,30 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
-	int hardirq, softirq;
+	char hardsoft_irq;
+	char need_resched;
+	char irqs_off;
+	int hardirq;
+	int softirq;
 	int ret;
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
+	irqs_off =
+		(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+		(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+		'.';
+	need_resched =
+		(entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+	hardsoft_irq =
+		(hardirq && softirq) ? 'H' :
+		hardirq ? 'h' :
+		softirq ? 's' :
+		'.';
+
 	if (!trace_seq_printf(s, "%c%c%c",
-			      (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
-				(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
-				  'X' : '.',
-			      (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
-				'N' : '.',
-			      (hardirq && softirq) ? 'H' :
-				hardirq ? 'h' : softirq ? 's' : '.'))
+			      irqs_off, need_resched, hardsoft_irq))
 		return 0;
 
 	if (entry->preempt_count)
-- 
1.7.2.3

[PATCH 10/15] ftrace: Add .ref.text as one of the safe areas to trace

[Steven Rostedt]

[-- Attachment #1: 0010-ftrace-Add-.ref.text-as-one-of-the-safe-areas-to-tra.patch --]
[-- Type: text/plain, Size: 1323 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

The section .ref.text will not go away unexpectedly and is
safe to trace. Add it to the safe list of sections to allow
tracing.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 scripts/recordmcount.c  |    3 ++-
 scripts/recordmcount.pl |    1 +
 2 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 038b3d1..f9f6f52 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -206,7 +206,8 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return 0 == strcmp(".text",          txtname) ||
+	return 0 == strcmp(".text",           txtname) ||
+		0 == strcmp(".ref.text",      txtname) ||
 		0 == strcmp(".sched.text",    txtname) ||
 		0 == strcmp(".spinlock.text", txtname) ||
 		0 == strcmp(".irqentry.text", txtname) ||
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 1d7963f..4be0dee 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -130,6 +130,7 @@ if ($inputfile =~ m,kernel/trace/ftrace\.o$,) {
 # Acceptable sections to record.
 my %text_sections = (
      ".text" => 1,
+     ".ref.text" => 1,
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,
-- 
1.7.2.3

[PATCH 11/15] ftrace/graph: Trace function entry before updating index

[Steven Rostedt]

[-- Attachment #1: 0011-ftrace-graph-Trace-function-entry-before-updating-in.patch --]
[-- Type: text/plain, Size: 2245 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Currently the index to the ret_stack is updated and the real return address
is saved in the ret_stack. Then we call the trace function. The trace
function could decide that it doesn't want to trace this function
(ex. set_graph_function does not match) and it will return 0 which means
not to trace this call.

The normal function graph tracer has this code:

	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
	      ftrace_graph_ignore_irqs())
		return 0;

What this states is, if the trace depth (which is curr_ret_stack)
is zero (top of nested functions) then test if we want to trace this
function. If this function is not to be traced, then return  0 and
the rest of the function graph tracer logic will not trace this function.

The problem arises when an interrupt comes in after we updated the
curr_ret_stack. The next function that gets called will have a trace->depth
of 1. Which fools this trace code into thinking that we are in a nested
function, and that we should trace. This causes interrupts to be traced
when they should not be.

The solution is to trace the function first and then update the ret_stack.

Reported-by: zhiping zhong <xzhong86@163.com>
Reported-by: wu zhangjin <wuzhangjin@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kernel/ftrace.c |   15 ++++++++-------
 1 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 382eb29..a93742a 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 	}
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-		    frame_pointer) == -EBUSY) {
-		*parent = old;
-		return;
-	}
-
 	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
 	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
 		*parent = old;
+		return;
+	}
+
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+		    frame_pointer) == -EBUSY) {
+		*parent = old;
+		return;
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-- 
1.7.2.3

[PATCH 12/15] tracing: Explain about unstable clock on resume with ring buffer warning

[Steven Rostedt]

[-- Attachment #1: 0012-tracing-Explain-about-unstable-clock-on-resume-with-.patch --]
[-- Type: text/plain, Size: 1804 bytes --]

From: Jiri Olsa <jolsa@redhat.com>

The "Delta way too big" warning might appear on a system with a
unstable shed clock right after the system is resumed and tracing
was enabled at time of suspend.

Since it's not realy a bug, and the unstable sched clock is working
fast and reliable otherwise, Steven suggested to keep using the
sched clock in any case and just to make note in the warning itself.

v2 changes:
- added #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
LKML-Reference: <20110218145219.GD2604@jolsa.brq.redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3237d96..db7b439 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2172,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 	if (likely(ts >= cpu_buffer->write_stamp)) {
 		delta = diff;
 		if (unlikely(test_time_stamp(delta))) {
+			int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+			local_clock_stable = sched_clock_stable;
+#endif
 			WARN_ONCE(delta > (1ULL << 59),
-				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
 				  (unsigned long long)delta,
 				  (unsigned long long)ts,
-				  (unsigned long long)cpu_buffer->write_stamp);
+				  (unsigned long long)cpu_buffer->write_stamp,
+				  local_clock_stable ? "" :
+				  "If you just came from a suspend/resume,\n"
+				  "please switch to the trace global clock:\n"
+				  "  echo global > /sys/kernel/debug/tracing/trace_clock\n");
 			add_timestamp = 1;
 		}
 	}
-- 
1.7.2.3

[PATCH 13/15] tracing: Export trace_set_clr_event()

[Steven Rostedt]

[-- Attachment #1: 0013-tracing-Export-trace_set_clr_event.patch --]
[-- Type: text/plain, Size: 1216 bytes --]

From: Yuanhan Liu <yuanhan.liu@linux.intel.com>

Trace events belonging to a module only exists when the module is
loaded. Well, we can use trace_set_clr_event funtion to enable some
trace event at the module init routine, so that we will not miss
something while loading then module.

So, Export the trace_set_clr_event function so that module can use it.

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
LKML-Reference: <1289196312-25323-1-git-send-email-yuanhan.liu@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e1d579b..e88f74f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -325,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 {
 	return __ftrace_set_clr_event(NULL, system, event, set);
 }
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
 /* 128 should be much more than enough */
 #define EVENT_BUF_SIZE		127
-- 
1.7.2.3

[PATCH 14/15] tracing: Align 4 byte ints together in struct tracer

[Steven Rostedt]

[-- Attachment #1: 0014-tracing-Align-4-byte-ints-together-in-struct-tracer.patch --]
[-- Type: text/plain, Size: 650 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Move elements in struct tracer for better alignment.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 951d0b7..5e9dfc6 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,8 +272,8 @@ struct tracer {
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
-	int			print_max;
 	struct tracer_flags	*flags;
+	int			print_max;
 	int			use_max_tr;
 };
 
-- 
1.7.2.3

[PATCH 15/15] tracing: Fix irqoff selftest expanding max buffer

[Steven Rostedt]

[-- Attachment #1: 0015-tracing-Fix-irqoff-selftest-expanding-max-buffer.patch --]
[-- Type: text/plain, Size: 3193 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

If the kernel command line declares a tracer "ftrace=sometracer" and
that tracer is either not defined or is enabled after irqsoff,
then the irqs off selftest will fail with the following error:

Testing tracer irqsoff:
------------[ cut here ]------------
WARNING: at /home/rostedt/work/autotest/nobackup/linux-test.git/kernel/trace/tra
ce.c:713 update_max_tr_single+0xfa/0x11b()
Hardware name:
Modules linked in:
Pid: 1, comm: swapper Not tainted 2.6.38-rc8-test #1
Call Trace:
 [<c0441d9d>] ? warn_slowpath_common+0x65/0x7a
 [<c049adb2>] ? update_max_tr_single+0xfa/0x11b
 [<c0441dc1>] ? warn_slowpath_null+0xf/0x13
 [<c049adb2>] ? update_max_tr_single+0xfa/0x11b
 [<c049e454>] ? stop_critical_timing+0x154/0x204
 [<c049b54b>] ? trace_selftest_startup_irqsoff+0x5b/0xc1
 [<c049b54b>] ? trace_selftest_startup_irqsoff+0x5b/0xc1
 [<c049b54b>] ? trace_selftest_startup_irqsoff+0x5b/0xc1
 [<c049e529>] ? time_hardirqs_on+0x25/0x28
 [<c0468bca>] ? trace_hardirqs_on_caller+0x18/0x12f
 [<c0468cec>] ? trace_hardirqs_on+0xb/0xd
 [<c049b54b>] ? trace_selftest_startup_irqsoff+0x5b/0xc1
 [<c049b6b8>] ? register_tracer+0xf8/0x1a3
 [<c14e93fe>] ? init_irqsoff_tracer+0xd/0x11
 [<c040115e>] ? do_one_initcall+0x71/0x121
 [<c14e93f1>] ? init_irqsoff_tracer+0x0/0x11
 [<c14ce3a9>] ? kernel_init+0x13a/0x1b6
 [<c14ce26f>] ? kernel_init+0x0/0x1b6
 [<c0403842>] ? kernel_thread_helper+0x6/0x10
---[ end trace e93713a9d40cd06c ]---
.. no entries found ..FAILED!

What happens is the "ftrace=..." will expand the ring buffer to its
default size (from its minimum size) but it will not expand the
max ring buffer (the ring buffer to store maximum latencies).
When the irqsoff test runs, it will call the ring buffer swap routine
that checks if the max ring buffer is the same size as the normal
ring buffer, and will fail if it is not. This causes the test to fail.

The solution is to expand the max ring buffer before running the self
test if the max ring buffer is used by that tracer and the normal ring
buffer is expanded. The max ring buffer should be shrunk again after
the test is done to save space.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |    9 +++++++++
 1 files changed, 9 insertions(+), 0 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fd6e1b9..9541c27 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -779,6 +779,11 @@ __acquires(kernel_lock)
 		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
+
+		/* If we expanded the buffers, make sure the max is expanded too */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, trace_buf_size);
+
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
 		ret = type->selftest(type, tr);
@@ -791,6 +796,10 @@ __acquires(kernel_lock)
 		/* Only reset on passing, to avoid touching corrupted buffers */
 		tracing_reset_online_cpus(tr);
 
+		/* Shrink the max buffer again */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, 1);
+
 		printk(KERN_CONT "PASSED\n");
 	}
 #endif
-- 
1.7.2.3

Re: [PATCH 00/15] [GIT PULL] tracing: updates for 2.6.39

[Ingo Molnar]

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

> Ingo,
> 
> Please pull the latest tip/perf/core tree, which can be found at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/perf/core
> 
> 
> David Sharp (8):
>       tracing: Add an 'overwrite' trace_option.
>       ring-buffer: Remove unused #include <linux/trace_irq.h>
>       tracing: Fix event alignment: ftrace:context_switch and ftrace:wakeup
>       tracing: Fix event alignment: module:module_request
>       tracing: Fix event alignment: kvm:kvm_hv_hypercall
>       tracing: Fix event alignment: mce:mce_record
>       tracing: Fix event alignment: skb:kfree_skb
>       tracing: Adjust conditional expression latency formatting.
> 
> Jiri Olsa (1):
>       tracing: Explain about unstable clock on resume with ring buffer warning
> 
> Steven Rostedt (5):
>       tracing: Remove lock_depth from event entry
>       ftrace: Add .ref.text as one of the safe areas to trace
>       ftrace/graph: Trace function entry before updating index
>       tracing: Align 4 byte ints together in struct tracer
>       tracing: Fix irqoff selftest expanding max buffer
> 
> Yuanhan Liu (1):
>       tracing: Export trace_set_clr_event()
> 
> ----
>  Documentation/trace/ftrace.txt |    5 +++++
>  arch/x86/kernel/ftrace.c       |   15 ++++++++-------
>  arch/x86/kvm/trace.h           |    8 ++++----
>  include/linux/ftrace_event.h   |    1 -
>  include/linux/ring_buffer.h    |    2 ++
>  include/trace/events/mce.h     |    8 ++++----
>  include/trace/events/module.h  |    5 ++---
>  include/trace/events/skb.h     |    4 ++--
>  kernel/trace/ring_buffer.c     |   24 +++++++++++++++++++++---
>  kernel/trace/trace.c           |   34 +++++++++++++++++++++++-----------
>  kernel/trace/trace.h           |    3 ++-
>  kernel/trace/trace_entries.h   |    6 +++---
>  kernel/trace/trace_events.c    |    2 +-
>  kernel/trace/trace_output.c    |   36 ++++++++++++++++++++----------------
>  scripts/recordmcount.c         |    3 ++-
>  scripts/recordmcount.pl        |    1 +
>  16 files changed, 100 insertions(+), 57 deletions(-)

Pulled, thanks a lot Steve!

	Ingo