Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Fri, 17 May 2019 10:59:06 -0700
In-Reply-To: <20190517084712.GL2623@hirez.programming.kicks-ass.net>
Message-Id: <20190517175906.78742-1-yabinc@google.com>
Mime-Version: 1.0
References: <20190517084712.GL2623@hirez.programming.kicks-ass.net>
Subject: Re: [PATCH] perf/ring_buffer: Fix exposing a temporarily decreased data_head.
From:   Yabin Cui <yabinc@google.com>
To:     Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@redhat.com>,
        Namhyung Kim <namhyung@kernel.org>
Cc:     linux-kernel@vger.kernel.org, Yabin Cui <yabinc@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

> > -	local_inc(&rb->nest);
> > +	rb->nest++;
> > +	barrier();

> Urgh; almost but not quite. You just lost the 'volatile' qualifier and
> now the compiler can mess things up for you.

I thought the barriers added could force the compiler to forget what it knows
about rb->nest, and do the write as been told to. I appreciate it if you can
tell me more details about it. Anyway, it's a good choice to be protective
and always use WRITE_ONCE/READ_ONCE for rb->nest.

> What I'm going to do is split this into two patches, one fixes the
> problem and marked for backport, and one changing away from local_t.

I read the split patches. They totally LGTM. Thanks for all your help
and rapid reply! I appreciate it :)