[PATCH][GIT PULL] tracing: Fix recursive user stack trace

[PATCH][GIT PULL] tracing: Fix recursive user stack trace

[Steven Rostedt]

Ingo,

This also includes the two other patches I submitted previously.
I just rebased the third patch with Eric's recommendation.

Please pull the latest tip/perf/urgent-3 tree, which can be found at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/perf/urgent-3


Steven Rostedt (1):
      tracing: Fix recursive user stack trace

----
 kernel/trace/trace.c |   19 +++++++++++++++++++
 1 files changed, 19 insertions(+), 0 deletions(-)
---------------------------
commit 91e86e560d0b3ce4c5fc64fd2bbb99f856a30a4e
Author: Steven Rostedt <srostedt@redhat.com>
Date:   Wed Nov 10 12:56:12 2010 +0100

    tracing: Fix recursive user stack trace
    
    The user stack trace can fault when examining the trace. Which
    would call the do_page_fault handler, which would trace again,
    which would do the user stack trace, which would fault and call
    do_page_fault again ...
    
    Thus this is causing a recursive bug. We need to have a recursion
    detector here.
    
    [ Resubmitted by Jiri Olsa ]
    
    [ Eric Dumazet recommended using __this_cpu_* instead of __get_cpu_* ]
    
    Cc: Eric Dumazet <eric.dumazet@gmail.com>
    Signed-off-by: Jiri Olsa <jolsa@redhat.com>
    LKML-Reference: <1289390172-9730-3-git-send-email-jolsa@redhat.com>
    Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b81..ee6a733 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1284,6 +1284,8 @@ void trace_dump_stack(void)
 	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
 }
 
+static DEFINE_PER_CPU(int, user_stack_count);
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1302,6 +1304,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (unlikely(in_nmi()))
 		return;
 
+	/*
+	 * prevent recursion, since the user stack tracing may
+	 * trigger other kernel events.
+	 */
+	preempt_disable();
+	if (__this_cpu_read(user_stack_count))
+		goto out;
+
+	__this_cpu_inc(user_stack_count);
+
+
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1319,6 +1333,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	save_stack_trace_user(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+	__this_cpu_dec(user_stack_count);
+
+ out:
+	preempt_enable();
 }
 
 #ifdef UNUSED

Re: [PATCH][GIT PULL] tracing: Fix recursive user stack trace

[Steven Rostedt]

On Fri, 2010-11-12 at 21:57 -0500, Steven Rostedt wrote:
> Ingo,
> 
> This also includes the two other patches I submitted previously.
> I just rebased the third patch with Eric's recommendation.
> 
> Please pull the latest tip/perf/urgent-3 tree, which can be found at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/perf/urgent-3
> 
> 
> Steven Rostedt (1):
>       tracing: Fix recursive user stack trace

ping?

I did run this through several tests with ktest.pl, and it looks pretty
solid.

-- Steve

> 
> ----
>  kernel/trace/trace.c |   19 +++++++++++++++++++
>  1 files changed, 19 insertions(+), 0 deletions(-)
> ---------------------------
> commit 91e86e560d0b3ce4c5fc64fd2bbb99f856a30a4e
> Author: Steven Rostedt <srostedt@redhat.com>
> Date:   Wed Nov 10 12:56:12 2010 +0100
> 
>     tracing: Fix recursive user stack trace
>     
>     The user stack trace can fault when examining the trace. Which
>     would call the do_page_fault handler, which would trace again,
>     which would do the user stack trace, which would fault and call
>     do_page_fault again ...
>     
>     Thus this is causing a recursive bug. We need to have a recursion
>     detector here.
>     
>     [ Resubmitted by Jiri Olsa ]
>     
>     [ Eric Dumazet recommended using __this_cpu_* instead of __get_cpu_* ]
>     
>     Cc: Eric Dumazet <eric.dumazet@gmail.com>
>     Signed-off-by: Jiri Olsa <jolsa@redhat.com>
>     LKML-Reference: <1289390172-9730-3-git-send-email-jolsa@redhat.com>
>     Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> 
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index 82d9b81..ee6a733 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -1284,6 +1284,8 @@ void trace_dump_stack(void)
>  	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
>  }
>  
> +static DEFINE_PER_CPU(int, user_stack_count);
> +
>  void
>  ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
>  {
> @@ -1302,6 +1304,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
>  	if (unlikely(in_nmi()))
>  		return;
>  
> +	/*
> +	 * prevent recursion, since the user stack tracing may
> +	 * trigger other kernel events.
> +	 */
> +	preempt_disable();
> +	if (__this_cpu_read(user_stack_count))
> +		goto out;
> +
> +	__this_cpu_inc(user_stack_count);
> +
> +
> +
>  	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
>  					  sizeof(*entry), flags, pc);
>  	if (!event)
> @@ -1319,6 +1333,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
>  	save_stack_trace_user(&trace);
>  	if (!filter_check_discard(call, entry, buffer, event))
>  		ring_buffer_unlock_commit(buffer, event);
> +
> +	__this_cpu_dec(user_stack_count);
> +
> + out:
> +	preempt_enable();
>  }
>  
>  #ifdef UNUSED
> 

Re: [PATCH][GIT PULL] tracing: Fix recursive user stack trace

[Ingo Molnar]

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

> 
> Ingo,
> 
> This also includes the two other patches I submitted previously.
> I just rebased the third patch with Eric's recommendation.
> 
> Please pull the latest tip/perf/urgent-3 tree, which can be found at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/perf/urgent-3
> 
> 
> Steven Rostedt (1):
>       tracing: Fix recursive user stack trace

Pulled, thanks a lot Steve!

	Ingo