* [PATCH][GIT PULL] tracing: add trace_stack interface
@ 2009-05-20 0:44 Steven Rostedt
2009-05-20 1:07 ` Frederic Weisbecker
2009-05-20 1:09 ` [PATCH v2][GIT " Steven Rostedt
0 siblings, 2 replies; 8+ messages in thread
From: Steven Rostedt @ 2009-05-20 0:44 UTC (permalink / raw)
To: LKML; +Cc: Ingo Molnar, Frederic Weisbecker, Andrew Morton
Ingo,
Please pull the latest tip/tracing/ftrace tree, which can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/tracing/ftrace
Steven Rostedt (1):
tracing: add trace_stack interface
----
include/linux/kernel.h | 2 ++
kernel/trace/trace.c | 15 +++++++++++++++
2 files changed, 17 insertions(+), 0 deletions(-)
---------------------------
commit b85d1029ba534376d203c3ac83a2e5a4d6876cb6
Author: Steven Rostedt <srostedt@redhat.com>
Date: Tue May 19 18:54:16 2009 -0400
tracing: add trace_stack interface
This patch adds the global function
void trace_stack(void)
This allows a developer to find where a function is called. For example,
if you want to know who calls __netif_reschedule, you can add
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
unsigned long flags;
+ trace_stack();
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
q->next_sched = sd->output_queue;
And see the following in the trace output:
<= __ftrace_trace_stack
<= trace_stack
<= __netif_schedule
<= dev_watchdog
<= run_timer_softirq
<= __do_softirq
<= call_softirq
<= do_softirq
<= irq_exit
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 883cd44..347a0f1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -511,6 +511,7 @@ extern int
__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
extern void ftrace_dump(void);
+extern void trace_stack(void);
#else
static inline void
ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
@@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
return 0;
}
static inline void ftrace_dump(void) { }
+static inline void trace_stack(void) { }
#endif /* CONFIG_TRACING */
/*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dd40d23..33ab502 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1046,6 +1046,21 @@ void __trace_stack(struct trace_array *tr,
__ftrace_trace_stack(tr, flags, skip, pc);
}
+/**
+ * trace_stack - dump the stack into the trace buffer
+ *
+ * Use this to record the stack trace into the ring buffer. If you
+ * want to know a caller of a function, place a call to trace_stack
+ * and the ftrace trace file will display who the callers were.
+ */
+void trace_stack(void)
+{
+ unsigned long flags;
+
+ local_save_flags(flags);
+ __trace_stack(&global_trace, flags, 0, preempt_count());
+}
+
static void ftrace_trace_userstack(struct trace_array *tr,
unsigned long flags, int pc)
{
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH][GIT PULL] tracing: add trace_stack interface
2009-05-20 0:44 [PATCH][GIT PULL] tracing: add trace_stack interface Steven Rostedt
@ 2009-05-20 1:07 ` Frederic Weisbecker
2009-05-20 1:14 ` Steven Rostedt
2009-05-20 1:09 ` [PATCH v2][GIT " Steven Rostedt
1 sibling, 1 reply; 8+ messages in thread
From: Frederic Weisbecker @ 2009-05-20 1:07 UTC (permalink / raw)
To: Steven Rostedt; +Cc: LKML, Ingo Molnar, Andrew Morton
On Tue, May 19, 2009 at 08:44:50PM -0400, Steven Rostedt wrote:
>
> Ingo,
>
> Please pull the latest tip/tracing/ftrace tree, which can be found at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/tracing/ftrace
>
>
> Steven Rostedt (1):
> tracing: add trace_stack interface
>
> ----
> include/linux/kernel.h | 2 ++
> kernel/trace/trace.c | 15 +++++++++++++++
> 2 files changed, 17 insertions(+), 0 deletions(-)
> ---------------------------
> commit b85d1029ba534376d203c3ac83a2e5a4d6876cb6
> Author: Steven Rostedt <srostedt@redhat.com>
> Date: Tue May 19 18:54:16 2009 -0400
>
> tracing: add trace_stack interface
>
> This patch adds the global function
>
> void trace_stack(void)
>
> This allows a developer to find where a function is called. For example,
> if you want to know who calls __netif_reschedule, you can add
>
> static inline void __netif_reschedule(struct Qdisc *q)
> {
> struct softnet_data *sd;
> unsigned long flags;
>
> + trace_stack();
> local_irq_save(flags);
> sd = &__get_cpu_var(softnet_data);
> q->next_sched = sd->output_queue;
>
> And see the following in the trace output:
>
> <= __ftrace_trace_stack
> <= trace_stack
I guess the depth should begin here :-)
> <= __netif_schedule
> <= dev_watchdog
> <= run_timer_softirq
> <= __do_softirq
> <= call_softirq
> <= do_softirq
> <= irq_exit
>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
>
> diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> index 883cd44..347a0f1 100644
> --- a/include/linux/kernel.h
> +++ b/include/linux/kernel.h
> @@ -511,6 +511,7 @@ extern int
> __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
>
> extern void ftrace_dump(void);
> +extern void trace_stack(void);
> #else
> static inline void
> ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
> @@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
> return 0;
> }
> static inline void ftrace_dump(void) { }
> +static inline void trace_stack(void) { }
> #endif /* CONFIG_TRACING */
>
> /*
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index dd40d23..33ab502 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -1046,6 +1046,21 @@ void __trace_stack(struct trace_array *tr,
> __ftrace_trace_stack(tr, flags, skip, pc);
> }
>
> +/**
> + * trace_stack - dump the stack into the trace buffer
> + *
> + * Use this to record the stack trace into the ring buffer. If you
> + * want to know a caller of a function, place a call to trace_stack
> + * and the ftrace trace file will display who the callers were.
> + */
> +void trace_stack(void)
> +{
> + unsigned long flags;
> +
> + local_save_flags(flags);
> + __trace_stack(&global_trace, flags, 0, preempt_count());
> +}
Stupidly I use a very similar patch while working on reiserfs
but I forgot to post it.
Another trick is to use trace_printk() combined with:
echo stacktrace > trace_option
Frederic.
> static void ftrace_trace_userstack(struct trace_array *tr,
> unsigned long flags, int pc)
> {
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH v2][GIT PULL] tracing: add trace_stack interface
2009-05-20 0:44 [PATCH][GIT PULL] tracing: add trace_stack interface Steven Rostedt
2009-05-20 1:07 ` Frederic Weisbecker
@ 2009-05-20 1:09 ` Steven Rostedt
2009-06-03 21:48 ` Frederic Weisbecker
1 sibling, 1 reply; 8+ messages in thread
From: Steven Rostedt @ 2009-05-20 1:09 UTC (permalink / raw)
To: LKML; +Cc: Ingo Molnar, Frederic Weisbecker, Andrew Morton
Ingo,
I rebased because I forgot to add EXPORT_SYMBOL_GPL.
-- Steve
Please pull the latest tip/tracing/ftrace tree, which can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/tracing/ftrace
Steven Rostedt (1):
tracing: add trace_stack interface
----
include/linux/kernel.h | 2 ++
kernel/trace/trace.c | 16 ++++++++++++++++
2 files changed, 18 insertions(+), 0 deletions(-)
---------------------------
commit 9f6b28655254b91c48f684b367ac14bfec0e180a
Author: Steven Rostedt <srostedt@redhat.com>
Date: Tue May 19 18:54:16 2009 -0400
tracing: add trace_stack interface
This patch adds the global function
void trace_stack(void)
This allows a developer to find where a function is called. For example,
if you want to know who calls __netif_reschedule, you can add
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
unsigned long flags;
+ trace_stack();
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
q->next_sched = sd->output_queue;
And see the following in the trace output:
<= __ftrace_trace_stack
<= trace_stack
<= __netif_schedule
<= dev_watchdog
<= run_timer_softirq
<= __do_softirq
<= call_softirq
<= do_softirq
<= irq_exit
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 883cd44..347a0f1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -511,6 +511,7 @@ extern int
__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
extern void ftrace_dump(void);
+extern void trace_stack(void);
#else
static inline void
ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
@@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
return 0;
}
static inline void ftrace_dump(void) { }
+static inline void trace_stack(void) { }
#endif /* CONFIG_TRACING */
/*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dd40d23..7bfd4f2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1046,6 +1046,22 @@ void __trace_stack(struct trace_array *tr,
__ftrace_trace_stack(tr, flags, skip, pc);
}
+/**
+ * trace_stack - dump the stack into the trace buffer
+ *
+ * Use this to record the stack trace into the ring buffer. If you
+ * want to know a caller of a function, place a call to trace_stack
+ * and the ftrace trace file will display who the callers were.
+ */
+void trace_stack(void)
+{
+ unsigned long flags;
+
+ local_save_flags(flags);
+ __trace_stack(&global_trace, flags, 0, preempt_count());
+}
+EXPORT_SYMBOL_GPL(trace_stack);
+
static void ftrace_trace_userstack(struct trace_array *tr,
unsigned long flags, int pc)
{
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH][GIT PULL] tracing: add trace_stack interface
2009-05-20 1:07 ` Frederic Weisbecker
@ 2009-05-20 1:14 ` Steven Rostedt
2009-05-20 1:55 ` Frederic Weisbecker
0 siblings, 1 reply; 8+ messages in thread
From: Steven Rostedt @ 2009-05-20 1:14 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: LKML, Ingo Molnar, Andrew Morton
On Wed, 20 May 2009, Frederic Weisbecker wrote:
> On Tue, May 19, 2009 at 08:44:50PM -0400, Steven Rostedt wrote:
> >
> > Ingo,
> >
> > Please pull the latest tip/tracing/ftrace tree, which can be found at:
> >
> > git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> > tip/tracing/ftrace
> >
> >
> > Steven Rostedt (1):
> > tracing: add trace_stack interface
> >
> > ----
> > include/linux/kernel.h | 2 ++
> > kernel/trace/trace.c | 15 +++++++++++++++
> > 2 files changed, 17 insertions(+), 0 deletions(-)
> > ---------------------------
> > commit b85d1029ba534376d203c3ac83a2e5a4d6876cb6
> > Author: Steven Rostedt <srostedt@redhat.com>
> > Date: Tue May 19 18:54:16 2009 -0400
> >
> > tracing: add trace_stack interface
> >
> > This patch adds the global function
> >
> > void trace_stack(void)
> >
> > This allows a developer to find where a function is called. For example,
> > if you want to know who calls __netif_reschedule, you can add
> >
> > static inline void __netif_reschedule(struct Qdisc *q)
> > {
> > struct softnet_data *sd;
> > unsigned long flags;
> >
> > + trace_stack();
> > local_irq_save(flags);
> > sd = &__get_cpu_var(softnet_data);
> > q->next_sched = sd->output_queue;
> >
> > And see the following in the trace output:
> >
> > <= __ftrace_trace_stack
> > <= trace_stack
>
>
>
> I guess the depth should begin here :-)
Yeah, I thought about that but since it only prints out the stack trace,
this is sorta the "this is a stack trace" header.
>
>
>
> > <= __netif_schedule
> > <= dev_watchdog
> > <= run_timer_softirq
> > <= __do_softirq
> > <= call_softirq
> > <= do_softirq
> > <= irq_exit
> >
> > Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> >
> > diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> > index 883cd44..347a0f1 100644
> > --- a/include/linux/kernel.h
> > +++ b/include/linux/kernel.h
> > @@ -511,6 +511,7 @@ extern int
> > __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
> >
> > extern void ftrace_dump(void);
> > +extern void trace_stack(void);
> > #else
> > static inline void
> > ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
> > @@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
> > return 0;
> > }
> > static inline void ftrace_dump(void) { }
> > +static inline void trace_stack(void) { }
> > #endif /* CONFIG_TRACING */
> >
> > /*
> > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> > index dd40d23..33ab502 100644
> > --- a/kernel/trace/trace.c
> > +++ b/kernel/trace/trace.c
> > @@ -1046,6 +1046,21 @@ void __trace_stack(struct trace_array *tr,
> > __ftrace_trace_stack(tr, flags, skip, pc);
> > }
> >
> > +/**
> > + * trace_stack - dump the stack into the trace buffer
> > + *
> > + * Use this to record the stack trace into the ring buffer. If you
> > + * want to know a caller of a function, place a call to trace_stack
> > + * and the ftrace trace file will display who the callers were.
> > + */
> > +void trace_stack(void)
> > +{
> > + unsigned long flags;
> > +
> > + local_save_flags(flags);
> > + __trace_stack(&global_trace, flags, 0, preempt_count());
> > +}
>
>
>
> Stupidly I use a very similar patch while working on reiserfs
> but I forgot to post it.
>
> Another trick is to use trace_printk() combined with:
>
> echo stacktrace > trace_option
Yeah, but when you are debugging development work, doing that at every
boot up becomes a pain. You can add it to a rc script but still.
I wrote this because of the development I'm doing in the interrupt
threads. I was using this a lot to find what is calling what.
-- Steve
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH][GIT PULL] tracing: add trace_stack interface
2009-05-20 1:14 ` Steven Rostedt
@ 2009-05-20 1:55 ` Frederic Weisbecker
0 siblings, 0 replies; 8+ messages in thread
From: Frederic Weisbecker @ 2009-05-20 1:55 UTC (permalink / raw)
To: Steven Rostedt; +Cc: LKML, Ingo Molnar, Andrew Morton
On Tue, May 19, 2009 at 09:14:13PM -0400, Steven Rostedt wrote:
>
> On Wed, 20 May 2009, Frederic Weisbecker wrote:
>
> > On Tue, May 19, 2009 at 08:44:50PM -0400, Steven Rostedt wrote:
> > >
> > > Ingo,
> > >
> > > Please pull the latest tip/tracing/ftrace tree, which can be found at:
> > >
> > > git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> > > tip/tracing/ftrace
> > >
> > >
> > > Steven Rostedt (1):
> > > tracing: add trace_stack interface
> > >
> > > ----
> > > include/linux/kernel.h | 2 ++
> > > kernel/trace/trace.c | 15 +++++++++++++++
> > > 2 files changed, 17 insertions(+), 0 deletions(-)
> > > ---------------------------
> > > commit b85d1029ba534376d203c3ac83a2e5a4d6876cb6
> > > Author: Steven Rostedt <srostedt@redhat.com>
> > > Date: Tue May 19 18:54:16 2009 -0400
> > >
> > > tracing: add trace_stack interface
> > >
> > > This patch adds the global function
> > >
> > > void trace_stack(void)
> > >
> > > This allows a developer to find where a function is called. For example,
> > > if you want to know who calls __netif_reschedule, you can add
> > >
> > > static inline void __netif_reschedule(struct Qdisc *q)
> > > {
> > > struct softnet_data *sd;
> > > unsigned long flags;
> > >
> > > + trace_stack();
> > > local_irq_save(flags);
> > > sd = &__get_cpu_var(softnet_data);
> > > q->next_sched = sd->output_queue;
> > >
> > > And see the following in the trace output:
> > >
> > > <= __ftrace_trace_stack
> > > <= trace_stack
> >
> >
> >
> > I guess the depth should begin here :-)
>
> Yeah, I thought about that but since it only prints out the stack trace,
> this is sorta the "this is a stack trace" header.
Indeed :)
> >
> >
> >
> > > <= __netif_schedule
> > > <= dev_watchdog
> > > <= run_timer_softirq
> > > <= __do_softirq
> > > <= call_softirq
> > > <= do_softirq
> > > <= irq_exit
> > >
> > > Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> > >
> > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> > > index 883cd44..347a0f1 100644
> > > --- a/include/linux/kernel.h
> > > +++ b/include/linux/kernel.h
> > > @@ -511,6 +511,7 @@ extern int
> > > __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
> > >
> > > extern void ftrace_dump(void);
> > > +extern void trace_stack(void);
> > > #else
> > > static inline void
> > > ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
> > > @@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
> > > return 0;
> > > }
> > > static inline void ftrace_dump(void) { }
> > > +static inline void trace_stack(void) { }
> > > #endif /* CONFIG_TRACING */
> > >
> > > /*
> > > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> > > index dd40d23..33ab502 100644
> > > --- a/kernel/trace/trace.c
> > > +++ b/kernel/trace/trace.c
> > > @@ -1046,6 +1046,21 @@ void __trace_stack(struct trace_array *tr,
> > > __ftrace_trace_stack(tr, flags, skip, pc);
> > > }
> > >
> > > +/**
> > > + * trace_stack - dump the stack into the trace buffer
> > > + *
> > > + * Use this to record the stack trace into the ring buffer. If you
> > > + * want to know a caller of a function, place a call to trace_stack
> > > + * and the ftrace trace file will display who the callers were.
> > > + */
> > > +void trace_stack(void)
> > > +{
> > > + unsigned long flags;
> > > +
> > > + local_save_flags(flags);
> > > + __trace_stack(&global_trace, flags, 0, preempt_count());
> > > +}
> >
> >
> >
> > Stupidly I use a very similar patch while working on reiserfs
> > but I forgot to post it.
> >
> > Another trick is to use trace_printk() combined with:
> >
> > echo stacktrace > trace_option
>
> Yeah, but when you are debugging development work, doing that at every
> boot up becomes a pain. You can add it to a rc script but still.
Right!
> I wrote this because of the development I'm doing in the interrupt
> threads. I was using this a lot to find what is calling what.
>
> -- Steve
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2][GIT PULL] tracing: add trace_stack interface
2009-05-20 1:09 ` [PATCH v2][GIT " Steven Rostedt
@ 2009-06-03 21:48 ` Frederic Weisbecker
2009-06-03 22:18 ` Steven Rostedt
2009-06-04 11:53 ` Ingo Molnar
0 siblings, 2 replies; 8+ messages in thread
From: Frederic Weisbecker @ 2009-06-03 21:48 UTC (permalink / raw)
To: Steven Rostedt, Ingo Molnar; +Cc: LKML, Andrew Morton
On Tue, May 19, 2009 at 09:09:40PM -0400, Steven Rostedt wrote:
>
> Ingo,
>
> I rebased because I forgot to add EXPORT_SYMBOL_GPL.
>
> -- Steve
>
> Please pull the latest tip/tracing/ftrace tree, which can be found at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/tracing/ftrace
>
>
> Steven Rostedt (1):
> tracing: add trace_stack interface
>
> ----
> include/linux/kernel.h | 2 ++
> kernel/trace/trace.c | 16 ++++++++++++++++
> 2 files changed, 18 insertions(+), 0 deletions(-)
> ---------------------------
> commit 9f6b28655254b91c48f684b367ac14bfec0e180a
> Author: Steven Rostedt <srostedt@redhat.com>
> Date: Tue May 19 18:54:16 2009 -0400
>
> tracing: add trace_stack interface
>
> This patch adds the global function
>
> void trace_stack(void)
>
> This allows a developer to find where a function is called. For example,
> if you want to know who calls __netif_reschedule, you can add
>
> static inline void __netif_reschedule(struct Qdisc *q)
> {
> struct softnet_data *sd;
> unsigned long flags;
>
> + trace_stack();
> local_irq_save(flags);
> sd = &__get_cpu_var(softnet_data);
> q->next_sched = sd->output_queue;
>
> And see the following in the trace output:
>
> <= __ftrace_trace_stack
> <= trace_stack
> <= __netif_schedule
> <= dev_watchdog
> <= run_timer_softirq
> <= __do_softirq
> <= call_softirq
> <= do_softirq
> <= irq_exit
>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
I wanted to use it to get the recursive locking points in reiserfs
but I can't find it.
Has it been merged in -tip ?
Thanks.
> diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> index 883cd44..347a0f1 100644
> --- a/include/linux/kernel.h
> +++ b/include/linux/kernel.h
> @@ -511,6 +511,7 @@ extern int
> __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
>
> extern void ftrace_dump(void);
> +extern void trace_stack(void);
> #else
> static inline void
> ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
> @@ -531,6 +532,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
> return 0;
> }
> static inline void ftrace_dump(void) { }
> +static inline void trace_stack(void) { }
> #endif /* CONFIG_TRACING */
>
> /*
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index dd40d23..7bfd4f2 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -1046,6 +1046,22 @@ void __trace_stack(struct trace_array *tr,
> __ftrace_trace_stack(tr, flags, skip, pc);
> }
>
> +/**
> + * trace_stack - dump the stack into the trace buffer
> + *
> + * Use this to record the stack trace into the ring buffer. If you
> + * want to know a caller of a function, place a call to trace_stack
> + * and the ftrace trace file will display who the callers were.
> + */
> +void trace_stack(void)
> +{
> + unsigned long flags;
> +
> + local_save_flags(flags);
> + __trace_stack(&global_trace, flags, 0, preempt_count());
> +}
> +EXPORT_SYMBOL_GPL(trace_stack);
> +
> static void ftrace_trace_userstack(struct trace_array *tr,
> unsigned long flags, int pc)
> {
>
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2][GIT PULL] tracing: add trace_stack interface
2009-06-03 21:48 ` Frederic Weisbecker
@ 2009-06-03 22:18 ` Steven Rostedt
2009-06-04 11:53 ` Ingo Molnar
1 sibling, 0 replies; 8+ messages in thread
From: Steven Rostedt @ 2009-06-03 22:18 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: Ingo Molnar, LKML, Andrew Morton
On Wed, 3 Jun 2009, Frederic Weisbecker wrote:
> On Tue, May 19, 2009 at 09:09:40PM -0400, Steven Rostedt wrote:
> >
> > Ingo,
> >
> > I rebased because I forgot to add EXPORT_SYMBOL_GPL.
> >
> > -- Steve
> >
> > Please pull the latest tip/tracing/ftrace tree, which can be found at:
> >
> > git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> > tip/tracing/ftrace
> >
> >
> > Steven Rostedt (1):
> > tracing: add trace_stack interface
> >
> > ----
> > include/linux/kernel.h | 2 ++
> > kernel/trace/trace.c | 16 ++++++++++++++++
> > 2 files changed, 18 insertions(+), 0 deletions(-)
> > ---------------------------
> > commit 9f6b28655254b91c48f684b367ac14bfec0e180a
> > Author: Steven Rostedt <srostedt@redhat.com>
> > Date: Tue May 19 18:54:16 2009 -0400
> >
> > tracing: add trace_stack interface
> >
> > This patch adds the global function
> >
> > void trace_stack(void)
> >
> > This allows a developer to find where a function is called. For example,
> > if you want to know who calls __netif_reschedule, you can add
> >
> > static inline void __netif_reschedule(struct Qdisc *q)
> > {
> > struct softnet_data *sd;
> > unsigned long flags;
> >
> > + trace_stack();
> > local_irq_save(flags);
> > sd = &__get_cpu_var(softnet_data);
> > q->next_sched = sd->output_queue;
> >
> > And see the following in the trace output:
> >
> > <= __ftrace_trace_stack
> > <= trace_stack
> > <= __netif_schedule
> > <= dev_watchdog
> > <= run_timer_softirq
> > <= __do_softirq
> > <= call_softirq
> > <= do_softirq
> > <= irq_exit
> >
> > Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
>
>
> I wanted to use it to get the recursive locking points in reiserfs
> but I can't find it.
>
> Has it been merged in -tip ?
>
It looks like it hasn't :-(
Luckily, I do not do "git gc" on my relay repo. Otherwise I would have
totally lost this. (it's no longer in my working repo.) I'll make a branch
from it now.
I wish merges were OK, because then I would be know if anything is
missing. When we rebase changes, things can easily get lost.
-- Steve
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2][GIT PULL] tracing: add trace_stack interface
2009-06-03 21:48 ` Frederic Weisbecker
2009-06-03 22:18 ` Steven Rostedt
@ 2009-06-04 11:53 ` Ingo Molnar
1 sibling, 0 replies; 8+ messages in thread
From: Ingo Molnar @ 2009-06-04 11:53 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: Steven Rostedt, LKML, Andrew Morton
* Frederic Weisbecker <fweisbec@gmail.com> wrote:
> On Tue, May 19, 2009 at 09:09:40PM -0400, Steven Rostedt wrote:
> >
> > Ingo,
> >
> > I rebased because I forgot to add EXPORT_SYMBOL_GPL.
> >
> > -- Steve
> >
> > Please pull the latest tip/tracing/ftrace tree, which can be found at:
> >
> > git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> > tip/tracing/ftrace
> >
> >
> > Steven Rostedt (1):
> > tracing: add trace_stack interface
> >
> > ----
> > include/linux/kernel.h | 2 ++
> > kernel/trace/trace.c | 16 ++++++++++++++++
> > 2 files changed, 18 insertions(+), 0 deletions(-)
> > ---------------------------
> > commit 9f6b28655254b91c48f684b367ac14bfec0e180a
> > Author: Steven Rostedt <srostedt@redhat.com>
> > Date: Tue May 19 18:54:16 2009 -0400
> >
> > tracing: add trace_stack interface
> >
> > This patch adds the global function
> >
> > void trace_stack(void)
> >
> > This allows a developer to find where a function is called. For example,
> > if you want to know who calls __netif_reschedule, you can add
> >
> > static inline void __netif_reschedule(struct Qdisc *q)
> > {
> > struct softnet_data *sd;
> > unsigned long flags;
> >
> > + trace_stack();
> > local_irq_save(flags);
> > sd = &__get_cpu_var(softnet_data);
> > q->next_sched = sd->output_queue;
> >
> > And see the following in the trace output:
> >
> > <= __ftrace_trace_stack
> > <= trace_stack
> > <= __netif_schedule
> > <= dev_watchdog
> > <= run_timer_softirq
> > <= __do_softirq
> > <= call_softirq
> > <= do_softirq
> > <= irq_exit
> >
> > Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
>
>
> I wanted to use it to get the recursive locking points in reiserfs
> but I can't find it.
>
> Has it been merged in -tip ?
hm, Steve has not sent it along AFAICS. There were no objections
from me.
Ingo
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2009-06-04 11:53 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2009-05-20 0:44 [PATCH][GIT PULL] tracing: add trace_stack interface Steven Rostedt
2009-05-20 1:07 ` Frederic Weisbecker
2009-05-20 1:14 ` Steven Rostedt
2009-05-20 1:55 ` Frederic Weisbecker
2009-05-20 1:09 ` [PATCH v2][GIT " Steven Rostedt
2009-06-03 21:48 ` Frederic Weisbecker
2009-06-03 22:18 ` Steven Rostedt
2009-06-04 11:53 ` Ingo Molnar
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.