Re: [PATCH] ftrace: Do not copy old hash when resetting.

[Steven Rostedt <rostedt@goodmis.org>]

On Mon, 14 Jul 2014 12:10:00 +0800
Wang Nan <wangnan0@huawei.com> wrote:

> If we are going to reset hash, we don't need to duplicate old hash
> and remove every entries right after allocation.
> 
> Signed-off-by: Wang Nan <wangnan0@huawei.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Ingo Molnar <mingo@redhat.com>
> ---
>  kernel/trace/ftrace.c | 8 +++++---
>  1 file changed, 5 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
> index 5b372e3..52d6931 100644
> --- a/kernel/trace/ftrace.c
> +++ b/kernel/trace/ftrace.c
> @@ -3471,14 +3471,16 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
>  	else
>  		orig_hash = &ops->notrace_hash;
>  
> -	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
> +	if (!reset)
> +		hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
> +	else
> +		hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);

I'm fine with this patch, but please swap the if statement above. I
prefer the if condition being positive if there's also an else
statement above. That is:

	if (reset)
		hash = alloc_ftrace_hash();
	else
		hash = alloc_and_copy_ftrace_hash();

-- Steve

> +
>  	if (!hash) {
>  		ret = -ENOMEM;
>  		goto out_regex_unlock;
>  	}
>  
> -	if (reset)
> -		ftrace_filter_reset(hash);
>  	if (buf && !ftrace_match_records(hash, buf, len)) {
>  		ret = -EINVAL;
>  		goto out_regex_unlock;