netdev - Re: [PATCH v3] epoll: use refcount to reduce ep

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <Y5gVJz+qDfw0tEP1@sol.localdomain>
Date:   Mon, 12 Dec 2022 22:01:11 -0800
From:   Eric Biggers <ebiggers@...nel.org>
To:     Paolo Abeni <pabeni@...hat.com>
Cc:     linux-fsdevel@...r.kernel.org,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Al Viro <viro@...iv.linux.org.uk>,
        Davidlohr Bueso <dave@...olabs.net>,
        Jason Baron <jbaron@...mai.com>, netdev@...r.kernel.org,
        Carlos Maiolino <cmaiolino@...hat.com>
Subject: Re: [PATCH v3] epoll: use refcount to reduce ep_mutex contention

On Mon, Nov 28, 2022 at 07:00:10PM +0100, Paolo Abeni wrote:
> We are observing huge contention on the epmutex during an http
> connection/rate test:
> 
>  83.17% 0.25%  nginx            [kernel.kallsyms]         [k] entry_SYSCALL_64_after_hwframe
> [...]
>            |--66.96%--__fput
>                       |--60.04%--eventpoll_release_file
>                                  |--58.41%--__mutex_lock.isra.6
>                                            |--56.56%--osq_lock
> 
> The application is multi-threaded, creates a new epoll entry for
> each incoming connection, and does not delete it before the
> connection shutdown - that is, before the connection's fd close().
> 
> Many different threads compete frequently for the epmutex lock,
> affecting the overall performance.
> 
> To reduce the contention this patch introduces explicit reference counting
> for the eventpoll struct. Each registered event acquires a reference,
> and references are released at ep_remove() time.
> 
> Additionally, this introduces a new 'dying' flag to prevent races between
> ep_free() and eventpoll_release_file(): the latter marks, under f_lock
> spinlock, each epitem as before removing it, while ep_free() does not
> touch dying epitems.
> 
> The eventpoll struct is released by whoever - among ep_free() and
> eventpoll_release_file() drops its last reference.
> 
> With all the above in place, we can drop the epmutex usage at disposal time.
> 
> Overall this produces a significant performance improvement in the
> mentioned connection/rate scenario: the mutex operations disappear from
> the topmost offenders in the perf report, and the measured connections/rate
> grows by ~60%.
> 
> Tested-by: Xiumei Mu <xmu@...hat.com>
> Signed-off-by: Paolo Abeni <pabeni@...hat.com>

I am trying to understand whether this patch is correct.

One thing that would help would be to use more standard naming:

	ep_put => ep_refcount_dec_and_test (or ep_put_and_test)
	ep_dispose => ep_free
	ep_free => ep_clear_and_put

- Eric