Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 23 Apr 2020 20:31:59 -0700
From:   Andrew Morton <akpm@linux-foundation.org>
To:     Khazhismel Kumykov <khazhy@google.com>
Cc:     viro@zeniv.linux.org.uk, rpenyaev@suse.de, r@hev.cc,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        Jason Baron <jbaron@akamai.com>
Subject: Re: [PATCH] eventpoll: fix missing wakeup for ovflist in
 ep_poll_callback
Message-Id: <20200423203159.c9fc9988649e08d59e13e64d@linux-foundation.org>
In-Reply-To: <20200424025057.118641-1-khazhy@google.com>
References: <20200424025057.118641-1-khazhy@google.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, 23 Apr 2020 19:50:57 -0700 Khazhismel Kumykov <khazhy@google.com> wrote:

> In the event that we add to ovflist, before 339ddb53d373 we would be
> woken up by ep_scan_ready_list, and did no wakeup in ep_poll_callback.
> With that wakeup removed, if we add to ovflist here, we may never wake
> up. Rather than adding back the ep_scan_ready_list wakeup - which was
> resulting un uncessary wakeups, trigger a wake-up in ep_poll_callback.
> 
> We noticed that one of our workloads was missing wakeups starting with
> 339ddb53d373 and upon manual inspection, this wakeup seemed missing to
> me. With this patch added, we no longer see missing wakeups. I haven't
> yet tried to make a small reproducer, but the existing kselftests in
> filesystem/epoll passed for me with this patch.

I'm no longer familiar with this code, so I'll await input from others.

> Fixes: 339ddb53d373 ("fs/epoll: remove unnecessary wakeups of nested epoll")
> Signed-off-by: Khazhismel Kumykov <khazhy@google.com>

However it sounds like a cc:stable would be warranted here, so that
earlier affected kernels get the fix?