From: "Paul E. McKenney" <paulmck@linux.ibm.com>
To: NeilBrown <neilb@suse.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>,
Thomas Graf <tgraf@suug.ch>,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/4] rhashtable: use bit_spin_locks to protect hash bucket.
Date: Wed, 27 Mar 2019 08:04:02 -0700 [thread overview]
Message-ID: <20190327150402.GX4102@linux.ibm.com> (raw)
In-Reply-To: <874l7p463d.fsf@notabene.neil.brown.name>
On Wed, Mar 27, 2019 at 09:35:18AM +1100, NeilBrown wrote:
> On Tue, Mar 26 2019, Herbert Xu wrote:
>
> > On Mon, Mar 25, 2019 at 04:05:39PM +1100, NeilBrown wrote:
> >>
> >> + * Sometimes we unlock a bucket by writing a new pointer there. In that
> >> + * case we don't need to unlock, but we do need to reset state such as
> >> + * local_bh. For that we have rht_unlocked(). This doesn't include
> >> + * the memory barrier that bit_spin_unlock() provides, but rcu_assign_pointer()
> >> + * will have provided that.
> >
> > Hmm, are you sure that's enough? IIRC rcu_assign_pointer only
> > provides a write barrier compared to the more complete (but one-way)
> > barrier that a spin-lock provides.
> >
>
> The bit_spin_unlock(), which I am avoiding as unnecessary, would have
> provided release semantics.
> i.e. any write by this CPU that happened before the releasing write
> will be visible to other CPUs before (or when) they see the result of
> the releasing write.
> This is (as I understand it) exactly that rcu_assign_pointer() promises
> - even before acquire semantics were added as Paul just reported.
>
> So yes, I am sure (surer now that I've walked through it carefully).
But why not construct a litmus test and apply tools/memory-model? ;-)
Thanx, Paul
next prev parent reply other threads:[~2019-03-27 15:04 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-25 5:05 [PATCH 0/4] Convert rhashtable to use bitlocks NeilBrown
2019-03-25 5:05 ` [PATCH 3/4] rhashtable: use bit_spin_locks to protect hash bucket NeilBrown
2019-03-26 5:03 ` Herbert Xu
2019-03-26 15:36 ` Paul E. McKenney
2019-03-27 3:45 ` Herbert Xu
2019-03-26 22:35 ` NeilBrown
2019-03-27 3:45 ` Herbert Xu
2019-03-27 15:04 ` Paul E. McKenney [this message]
2019-03-26 5:27 ` Herbert Xu
2019-03-26 22:40 ` NeilBrown
2019-03-25 5:05 ` [PATCH 1/4] rhashtable: use cmpxchg() in nested_table_alloc() NeilBrown
2019-03-25 5:05 ` [PATCH 4/4] rhashtable: add lockdep tracking to bucket bit-spin-locks NeilBrown
2019-03-25 5:05 ` [PATCH 2/4] rhashtable: allow rht_bucket_var to return NULL NeilBrown
-- strict thread matches above, loose matches on Subject: below --
2019-04-01 23:07 [PATCH 0/4 v2] Convert rhashtable to use bitlocks NeilBrown
2019-04-01 23:07 ` [PATCH 3/4] rhashtable: use bit_spin_locks to protect hash bucket NeilBrown
2019-04-02 10:11 ` David Laight
2019-04-02 21:10 ` NeilBrown
2019-04-03 9:26 ` David Laight
2019-04-04 0:13 ` NeilBrown
2019-04-08 2:34 ` Herbert Xu
2019-04-10 19:34 ` Guenter Roeck
2019-04-11 0:48 ` NeilBrown
2019-04-11 2:15 ` David Miller
2019-04-11 6:13 ` NeilBrown
2019-04-11 6:40 ` NeilBrown
2019-04-11 12:44 ` Guenter Roeck
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190327150402.GX4102@linux.ibm.com \
--to=paulmck@linux.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=linux-kernel@vger.kernel.org \
--cc=neilb@suse.com \
--cc=netdev@vger.kernel.org \
--cc=tgraf@suug.ch \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).