Received-SPF: pass (google.com: domain of linux-kernel+bounces-147222-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Tue, 16 Apr 2024 18:19:17 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Elizabeth Figura <zfigura@codeweavers.com>
Cc: Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Jonathan Corbet <corbet@lwn.net>, Shuah Khan <shuah@kernel.org>,
	linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	wine-devel@winehq.org,
	=?iso-8859-1?Q?Andr=E9?= Almeida <andrealmeid@igalia.com>,
	Wolfram Sang <wsa@kernel.org>,
	Arkadiusz Hiler <ahiler@codeweavers.com>,
	Andy Lutomirski <luto@kernel.org>, linux-doc@vger.kernel.org,
	linux-kselftest@vger.kernel.org,
	Randy Dunlap <rdunlap@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
	Waiman Long <longman@redhat.com>, Boqun Feng <boqun.feng@gmail.com>
Subject: Re: [PATCH v4 00/30] NT synchronization primitive driver
Message-ID: <20240416161917.GD12673@noisy.programming.kicks-ass.net>
References: <20240416010837.333694-1-zfigura@codeweavers.com>
 <20240416081421.GB31647@noisy.programming.kicks-ass.net>
 <20240416155014.GB12673@noisy.programming.kicks-ass.net>
 <20240416155345.GC12673@noisy.programming.kicks-ass.net>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240416155345.GC12673@noisy.programming.kicks-ass.net>

On Tue, Apr 16, 2024 at 05:53:45PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 16, 2024 at 05:50:14PM +0200, Peter Zijlstra wrote:
> > On Tue, Apr 16, 2024 at 10:14:21AM +0200, Peter Zijlstra wrote:
> > 
> > > > Some aspects of the implementation may deserve particular comment:
> > > > 
> > > > * In the interest of performance, each object is governed only by a single
> > > >   spinlock. However, NTSYNC_IOC_WAIT_ALL requires that the state of multiple
> > > >   objects be changed as a single atomic operation. In order to achieve this, we
> > > >   first take a device-wide lock ("wait_all_lock") any time we are going to lock
> > > >   more than one object at a time.
> > > > 
> > > >   The maximum number of objects that can be used in a vectored wait, and
> > > >   therefore the maximum that can be locked simultaneously, is 64. This number is
> > > >   NT's own limit.
> > 
> > AFAICT:
> > 
> > 	spin_lock(&dev->wait_all_lock);
> > 	  list_for_each_entry(entry, &obj->all_waiters, node)
> > 	    for (i=0; i<count; i++)
> > 	      spin_lock_nest_lock(q->entries[i].obj->lock, &dev->wait_all_lock);
> > 
> > Where @count <= NTSYNC_MAX_WAIT_COUNT.
> > 
> > So while this nests at most 65 spinlocks, there is no actual bound on
> > the amount of nested lock sections in total. That is, all_waiters list
> > can be grown without limits.
> > 
> > Can we pretty please make wait_all_lock a mutex ?
> 
> Hurmph, it's worse, you do that list walk while holding some obj->lock
> spinlokc too. Still need to figure out how all that works....

So the point of having that other lock around is so that things like:

	try_wake_all_obj(dev, sem)
	try_wake_any_sem(sem)

are done under the same lock?

Where I seem to note that both those functions do that same list
iteration.

Can't you write things like:

static void try_wake_all_obj(struct nysync_device *dev,
			     struct ntsync_obj *obj,
			     void (*wake_obj)(struct ntsync_obj *obj))
{
	list_for_each_entry(entry, &obj->all_waiters, node) {
		spin_lock(&obj->lock);
		try_wake_all(dev, event->q, obj);
		wake_obj(obj);
		spin_unlock(&obj->lock);
	}
}

And then instead of the above, write:

	try_wake_all_obj(dev, sem, wake_sem);

[[ Also, should not something like try_wake_any_sem -- wake_sem in the
   above -- have something like:

	WARN_ON_ONCE(sem->type != NTSYNC_TYPE_SEM);
]]