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.

The eventpoll struct is released by whoever - among EP file close() and
and the monitored file close() drops its last reference.

Additionally, this introduces a new 'dying' flag to prevent races between
the EP file close() and the monitored file close().
ep_eventpoll_release() marks, under f_lock spinlock, each epitem as dying
before removing it, while EP file close() does not touch dying epitems.

The above is needed as both close operations could run concurrently and
drop the EP reference acquired via the epitem entry. Without the above
flag, the monitored file close() could reach the EP struct via the epitem
list while the epitem is still listed and then try to put it after its
disposal.

An alternative could be avoiding touching the references acquired via
the epitems at EP file close() time, but that could leave the EP struct
alive for potentially unlimited time after EP file close(), with nasty
side effects.

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%.

To make the change more readable this additionally renames ep_free() to
ep_clear_and_put(), and moves the actual memory cleanup in a separate
ep_free() helper.

Link: https://lkml.kernel.org/r/4a57788dcaf28f5eb4f8dfddcc3a8b172a7357bb.1679504153.git.pabeni@redhat.comSigned-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Xiumei Mu <xmu@redhiat.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Carlos Maiolino <cmaiolino@redhat.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>