From mboxrd@z Thu Jan  1 00:00:00 1970
From: Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH v5 perf, bpf-next 3/7] perf, bpf: introduce
 PERF_RECORD_BPF_EVENT
Date: Tue, 8 Jan 2019 20:59:23 +0100
Message-ID: <20190108195923.GD30894@hirez.programming.kicks-ass.net>
References: <20181220182904.4193196-1-songliubraving@fb.com>
 <20181220182904.4193196-4-songliubraving@fb.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
        acme@kernel.org, ast@kernel.org, daniel@iogearbox.net,
        kernel-team@fb.com
To: Song Liu <songliubraving@fb.com>
Return-path: <linux-kernel-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <20181220182904.4193196-4-songliubraving@fb.com>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: netdev.vger.kernel.org

On Thu, Dec 20, 2018 at 10:29:00AM -0800, Song Liu wrote:
> +static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
> +					 enum perf_bpf_event_type type)
> +{
> +	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
> +	int i;
> +
> +	if (prog->aux->func_cnt == 0) {
> +		perf_event_ksymbol(PERF_RECORD_MISC_KSYMBOL_TYPE_BPF,
> +				   (u64)(unsigned long)prog->bpf_func,
> +				   prog->jited_len, unregister,
> +				   perf_event_bpf_get_name, prog);
> +	} else {
> +		for (i = 0; i < prog->aux->func_cnt; i++) {
> +			struct bpf_prog *subprog = prog->aux->func[i];
> +
> +			perf_event_ksymbol(
> +				PERF_RECORD_MISC_KSYMBOL_TYPE_BPF,
> +				(u64)(unsigned long)subprog->bpf_func,
> +				subprog->jited_len, unregister,
> +				perf_event_bpf_get_name, subprog);
> +		}
> +	}
> +}

That's a bit unexpected, but yes sure, that works for now.

I was expecting it to be hooked up in your kallsym rbtree thing, but
whatever, we can fix that when needed.