Re: [PATCH 2/3] tracing/kprobes: Kill probe_enable_lock

[Masami Hiramatsu]

(2013/06/17 2:21), Oleg Nesterov wrote:
> enable_trace_probe() and disable_trace_probe() should not worry about
> serialization, the caller (perf_trace_init or __ftrace_set_clr_event)
> holds event_mutex.
> 
> They are also called by kprobe_trace_self_tests_init(), but this __init
> function can't race with itself or trace_events.c

Right,
For safety, we should comment this at the caller side, because
those calls are the reason why I have introduced this lock.

Thank you,

> And note that this code depended on event_mutex even before 41a7dd420c
> which introduced probe_enable_lock. In fact it assumes that the caller
> kprobe_register() can never race with itself. Otherwise, say, tp->flags
> manipulations are racy.
> 
> Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
> ---
>  kernel/trace/trace_kprobe.c |   33 ++++++++++-----------------------
>  1 files changed, 10 insertions(+), 23 deletions(-)
> 
> diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
> index c0af476..5a73de0 100644
> --- a/kernel/trace/trace_kprobe.c
> +++ b/kernel/trace/trace_kprobe.c
> @@ -183,16 +183,15 @@ static struct trace_probe *find_trace_probe(const char *event,
>  	return NULL;
>  }
>  
> +/*
> + * This and enable_trace_probe/disable_trace_probe rely on event_mutex
> + * held by the caller, __ftrace_set_clr_event().
> + */
>  static int trace_probe_nr_files(struct trace_probe *tp)
>  {
> -	struct ftrace_event_file **file;
> +	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
>  	int ret = 0;
>  
> -	/*
> -	 * Since all tp->files updater is protected by probe_enable_lock,
> -	 * we don't need to lock an rcu_read_lock.
> -	 */
> -	file = rcu_dereference_raw(tp->files);
>  	if (file)
>  		while (*(file++))
>  			ret++;
> @@ -200,8 +199,6 @@ static int trace_probe_nr_files(struct trace_probe *tp)
>  	return ret;
>  }
>  
> -static DEFINE_MUTEX(probe_enable_lock);
> -
>  /*
>   * Enable trace_probe
>   * if the file is NULL, enable "perf" handler, or enable "trace" handler.
> @@ -211,8 +208,6 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  {
>  	int ret = 0;
>  
> -	mutex_lock(&probe_enable_lock);
> -
>  	if (file) {
>  		struct ftrace_event_file **new, **old;
>  		int n = trace_probe_nr_files(tp);
> @@ -223,7 +218,7 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  			      GFP_KERNEL);
>  		if (!new) {
>  			ret = -ENOMEM;
> -			goto out_unlock;
> +			goto out;
>  		}
>  		memcpy(new, old, n * sizeof(struct ftrace_event_file *));
>  		new[n] = file;
> @@ -247,10 +242,7 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  		else
>  			ret = enable_kprobe(&tp->rp.kp);
>  	}
> -
> - out_unlock:
> -	mutex_unlock(&probe_enable_lock);
> -
> + out:
>  	return ret;
>  }
>  
> @@ -283,8 +275,6 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  {
>  	int ret = 0;
>  
> -	mutex_lock(&probe_enable_lock);
> -
>  	if (file) {
>  		struct ftrace_event_file **new, **old;
>  		int n = trace_probe_nr_files(tp);
> @@ -293,7 +283,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  		old = rcu_dereference_raw(tp->files);
>  		if (n == 0 || trace_probe_file_index(tp, file) < 0) {
>  			ret = -EINVAL;
> -			goto out_unlock;
> +			goto out;
>  		}
>  
>  		if (n == 1) {	/* Remove the last file */
> @@ -304,7 +294,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  				      GFP_KERNEL);
>  			if (!new) {
>  				ret = -ENOMEM;
> -				goto out_unlock;
> +				goto out;
>  			}
>  
>  			/* This copy & check loop copies the NULL stopper too */
> @@ -327,10 +317,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
>  		else
>  			disable_kprobe(&tp->rp.kp);
>  	}
> -
> - out_unlock:
> -	mutex_unlock(&probe_enable_lock);
> -
> + out:
>  	return ret;
>  }
>  
> 


-- 
Masami HIRAMATSU
IT Management Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@xxxxxxxxxxx


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/