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;
MIME-Version: 1.0
References: <20200428205903.61704-1-urezki@gmail.com> <20200428205903.61704-10-urezki@gmail.com>
 <20200501212749.GD7560@paulmck-ThinkPad-P72> <20200504124323.GA17577@pc636>
 <20200504152437.GK2869@paulmck-ThinkPad-P72> <20200504174822.GA20446@pc636>
 <20200504180805.GA172409@google.com> <20200504190138.GU2869@paulmck-ThinkPad-P72>
In-Reply-To: <20200504190138.GU2869@paulmck-ThinkPad-P72>
From:   Joel Fernandes <joel@joelfernandes.org>
Date:   Mon, 4 May 2020 15:37:33 -0400
Message-ID: <CAEXW_YQmrfbaDocsc7bLULRR1yUv4=MMMEw3b0s1mXM8sEVVzQ@mail.gmail.com>
Subject: Re: [PATCH 09/24] rcu/tree: cache specified number of objects
To:     "Paul E. McKenney" <paulmck@kernel.org>
Cc:     Uladzislau Rezki <urezki@gmail.com>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-mm <linux-mm@kvack.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Theodore Y . Ts'o" <tytso@mit.edu>,
        Matthew Wilcox <willy@infradead.org>,
        RCU <rcu@vger.kernel.org>,
        Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi Paul,

On Mon, May 4, 2020 at 3:01 PM Paul E. McKenney <paulmck@kernel.org> wrote:
>
> On Mon, May 04, 2020 at 02:08:05PM -0400, Joel Fernandes wrote:
> > On Mon, May 04, 2020 at 07:48:22PM +0200, Uladzislau Rezki wrote:
> > > On Mon, May 04, 2020 at 08:24:37AM -0700, Paul E. McKenney wrote:
> > [..]
> > > > > > Presumably the list can also be accessed without holding this lock,
> > > > > > because otherwise we shouldn't need llist...
> > > > > >
> > > > > Hm... We increase the number of elements in cache, therefore it is not
> > > > > lockless. From the other hand i used llist_head to maintain the cache
> > > > > because it is single linked list, we do not need "*prev" link. Also
> > > > > we do not need to init the list.
> > > > >
> > > > > But i can change it to list_head. Please let me know if i need :)
> > > >
> > > > Hmmm...  Maybe it is time for a non-atomic singly linked list?  In the RCU
> > > > callback processing, the operations were open-coded, but they have been
> > > > pushed into include/linux/rcu_segcblist.h and kernel/rcu/rcu_segcblist.*.
> > > >
> > > > Maybe some non-atomic/protected/whatever macros in the llist.h file?
> > > > Or maybe just open-code the singly linked list?  (Probably not the
> > > > best choice, though.)  Add comments stating that the atomic properties
> > > > of the llist functions aren't neded?  Something else?
> > > >
> > > In order to keep it simple i can replace llist_head by the list_head?
> >
> > Just to clarify for me, what is the disadvantage of using llist here?
>
> Are there some llist APIs that are not set up for concurrency?  I am
> not seeing any.

llist deletion racing with another llist deletion will need locking.
So strictly speaking, some locking is possible with llist usage?

The locklessness as I understand comes when adding and deleting at the
same time. For that no lock is needed. But in the current patch, it
locks anyway to avoid the lost-update of the size of the list.

> The overhead isn't that much of a concern, given that these are not on the
> hotpath, but people reading the code and seeing the cmpxchg operations
> might be forgiven for believing that there is some concurrency involved
> somewhere.
>
> Or am I confused and there are now single-threaded add/delete operations
> for llist?

I do see some examples of llist usage with locking in the kernel code.
One case is: do_init_module() calling llist_add to add to the
init_free_list under module_mutex.

> > Since we don't care about traversing backwards, isn't it better to use llist
> > for this usecase?
> >
> > I think Vlad is using locking as we're also tracking the size of the llist to
> > know when to free pages. This tracking could suffer from the lost-update
> > problem without any locking, 2 lockless llist_add happened simulatenously.
> >
> > Also if list_head is used, it will take more space and still use locking.
>
> Indeed, it would be best to use a non-concurrent singly linked list.

Ok cool :-)

Is it safe to say something like the following is ruled out? ;-) :-D
#define kfree_rcu_list_add llist_add

Thanks,

 - Joel