All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Luck, Tony" <tony.luck@intel.com>
To: linux-ia64@vger.kernel.org
Subject: RE: [git pull] ia64 changes
Date: Mon, 28 Sep 2009 23:01:50 +0000	[thread overview]
Message-ID: <57C9024A16AD2D4C97DC78E552063EA3E2EA361E@orsmsx505.amr.corp.intel.com> (raw)
In-Reply-To: <1FE6DD409037234FAB833C420AA843EC0122AEB1@orsmsx424.amr.corp.intel.com>

>> 	ticket = ia64_fetchadd(1, p, acq);
>> 
>> 	if (!(((ticket >> TICKET_SHIFT) ^ ticket) & ((1L << TICKET_BITS) - 1)))
>> 		return;
>
> I think the above is wrong.
>
> Doesn't 'fetchadd' return the _old_ value?


Yes, It does return the old value ... but that it what we want.  When
we tear the ticket from the machine on the Deli counter, our ticket
number is the OLD value.  The updated value becomes the ticket number
for the next person to come along.

I.e. we start the lock with value 0x00000000, so the ticket showing is
0, and the now serving number is 0.  We fetchadd a ticket and the lock
goes to 0x00000001 ... and we own the lock because the ticket we pulled
matches the now-serving number.  When we are done we bumb the now-serving
value, so the lock goes to 0x00020001 and the lock is free again.

Did I do this differently from x86?

-Tony

  parent reply	other threads:[~2009-09-28 23:01 UTC|newest]

Thread overview: 110+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-04-18 16:34 [git pull] ia64 changes Luck, Tony
2008-04-22 23:36 ` Luck, Tony
2008-04-29 23:36 ` Luck, Tony
2008-05-01 22:57 ` Luck, Tony
2008-05-15 20:46 ` Luck, Tony
2008-05-28 19:52 ` Luck, Tony
2008-06-16 17:28 ` Luck, Tony
2008-06-24 21:49 ` Luck, Tony
2008-06-30 23:52 ` Luck, Tony
2008-07-17 20:31 ` Luck, Tony
2008-07-25 20:30 ` Luck, Tony
2008-08-06 18:32 ` Luck, Tony
2008-08-12 21:55 ` Luck, Tony
2008-08-18 23:46 ` Luck, Tony
2008-08-26 16:59 ` Luck, Tony
2008-09-10 21:17 ` Luck, Tony
2008-09-23 16:59 ` Luck, Tony
2008-09-30 16:18 ` Luck, Tony
2008-10-21 18:01 ` Luck, Tony
2008-11-05  0:43 ` Luck, Tony
2008-11-07 18:00 ` Luck, Tony
2008-11-20 22:47 ` Luck, Tony
2008-12-09 22:28 ` Luck, Tony
2009-01-15 19:45 ` Luck, Tony
2009-02-19 21:02 ` Luck, Tony
2009-02-25 22:44 ` Luck, Tony
2009-03-06 22:17 ` Luck, Tony
2009-03-27 17:46 ` Luck, Tony
2009-04-01 20:20 ` Luck, Tony
2009-04-08 22:33 ` Luck, Tony
2009-04-20 17:32 ` Luck, Tony
2009-05-05 22:42 ` Luck, Tony
2009-06-15 17:20 ` Luck, Tony
2009-07-17 18:11 ` Fenghua Yu
2009-08-11 23:40 ` Fenghua Yu
2009-09-02 17:28 ` Luck, Tony
2009-09-17 17:11 ` Luck, Tony
2009-09-26 19:57 ` Luck, Tony
2009-09-26 20:39 ` Linus Torvalds
2009-09-26 23:16 ` Matthew Wilcox
2009-09-27  0:00 ` Linus Torvalds
2009-09-27  0:08 ` Linus Torvalds
2009-09-27  4:54 ` Luck, Tony
2009-09-27  5:18 ` Linus Torvalds
2009-09-27  5:20 ` Luck, Tony
2009-09-28 19:02 ` Boehm, Hans
2009-09-28 22:35 ` Luck, Tony
2009-09-28 22:54 ` Linus Torvalds
2009-09-28 23:01 ` Linus Torvalds
2009-09-28 23:01 ` Luck, Tony [this message]
2009-09-29  0:03 ` Rick Jones
2009-09-29  0:14 ` Linus Torvalds
2009-09-29 17:53 ` Luck, Tony
2009-09-29 18:07 ` Linus Torvalds
2009-09-30  0:54 ` Robin Holt
2009-09-30  1:24 ` Linus Torvalds
2009-09-30  1:30 ` Linus Torvalds
2009-09-30  2:46 ` Robin Holt
2009-09-30  2:56 ` Linus Torvalds
2009-09-30 18:00 ` Rick Jones
2009-11-02 18:07 ` Luck, Tony
2009-12-15 22:33 ` Luck, Tony
2010-01-08 17:20 ` Luck, Tony
2010-01-08 17:35 ` Linus Torvalds
2010-01-08 17:49 ` Luck, Tony
2010-01-08 19:24 ` Luck, Tony
2010-02-16 19:43 ` Luck, Tony
2010-02-24 17:32 ` Luck, Tony
2010-03-01 18:11 ` Luck, Tony
2010-05-18 17:11 ` Luck, Tony
2010-05-18 20:43 ` Robin Holt
2010-05-18 22:04 ` Luck, Tony
2010-07-01 15:22 ` Luck, Tony
2010-08-04 16:09 ` Luck, Tony
2010-08-14  4:04 ` Luck, Tony
2010-08-18 20:06 ` Luck, Tony
2010-09-13 18:33 ` Luck, Tony
2010-09-14  6:06 ` Petr Tesarik
2010-09-14  7:02 ` Petr Tesarik
2010-09-14 17:37 ` Luck, Tony
2010-09-14 20:38 ` Petr Tesarik
2010-09-14 20:57 ` Tony Luck
2010-09-16 15:57 ` Luck, Tony
2010-10-21 16:00 ` Luck, Tony
2010-10-21 21:33 ` Linus Torvalds
2011-01-10 18:01 ` Luck, Tony
2011-01-13 18:08 ` Luck, Tony
2011-01-13 23:10 ` Luck, Tony
2011-01-14 19:33 ` Luck, Tony
2011-03-30 19:09 ` Luck, Tony
2011-05-31 20:20 ` Luck, Tony
2011-08-01 16:57 ` Luck, Tony
2011-11-02 21:06 ` Luck, Tony
2012-01-05 17:42 ` Luck, Tony
2012-03-23 17:23 ` [GIT PULL] " Luck, Tony
2008-04-24 23:51 [git pull] " Luck, Tony
2008-04-24 23:51 ` Luck, Tony
2008-04-25  0:16 ` Adrian Bunk
2008-04-25  0:16   ` Adrian Bunk
2008-04-25  0:25   ` Luck, Tony
2008-04-25  0:25     ` Luck, Tony
2008-04-25  0:41     ` [2.6 patch] ia64: let NUMA select SMP Adrian Bunk
2008-04-25  0:41       ` Adrian Bunk
2008-04-25  1:01       ` Luck, Tony
2008-04-25  1:01         ` Luck, Tony
2008-04-25 12:50       ` Mike Travis
2008-04-25 12:50         ` Mike Travis
2010-07-21 16:40 [git pull] ia64 changes Luck, Tony
2011-03-24 16:29 Luck, Tony
2011-03-24 16:29 ` Luck, Tony

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=57C9024A16AD2D4C97DC78E552063EA3E2EA361E@orsmsx505.amr.corp.intel.com \
    --to=tony.luck@intel.com \
    --cc=linux-ia64@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.