From: Waiman Long <Waiman.Long@hp.com>
To: Davidlohr Bueso <davidlohr.bueso@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
David Howells <dhowells@redhat.com>,
Dave Jones <davej@redhat.com>,
Clark Williams <williams@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
linux-kernel@vger.kernel.org, x86@kernel.org,
linux-arch@vger.kernel.org, "Chandramouleeswaran,
Aswin" <aswin@hp.com>, "Norton, Scott J" <scott.norton@hp.com>,
Rik van Riel <riel@redhat.com>
Subject: Re: [PATCH v2 2/3] mutex: Queue mutex spinners with MCS lock to reduce cacheline contention
Date: Tue, 16 Apr 2013 08:05:21 -0400 [thread overview]
Message-ID: <516D3E81.6060307@hp.com> (raw)
In-Reply-To: <1366086275.22463.25.camel@buesod1.americas.hpqcorp.net>
On 04/16/2013 12:24 AM, Davidlohr Bueso wrote:
> On Mon, 2013-04-15 at 10:37 -0400, Waiman Long wrote:
> [...]
>> +typedef struct mspin_node {
>> + struct mspin_node *next;
>> + int locked; /* 1 if lock acquired */
>> +} mspin_node_t;
>> +
>> +typedef mspin_node_t *mspin_lock_t;
> I think we could do without the typedefs, specially mspin_lock_t.
Yes, we can do without the typedefs.
>> +
>> +#define MLOCK(mutex) ((mspin_lock_t *)&((mutex)->spin_mlock))
>> +
>> +static noinline void mspin_lock(mspin_lock_t *lock, mspin_node_t *node)
>> +{
>> + mspin_node_t *prev;
>> +
>> + /* Init node */
>> + node->locked = 0;
>> + node->next = NULL;
>> +
>> + prev = xchg(lock, node);
>> + if (likely(prev == NULL)) {
>> + /* Lock acquired */
>> + node->locked = 1;
>> + return;
>> + }
>> + ACCESS_ONCE(prev->next) = node;
>> + smp_wmb();
>> + /* Wait until the lock holder passes the lock down */
>> + while (!ACCESS_ONCE(node->locked))
>> + arch_mutex_cpu_relax();
>> +}
>> +
>> +static void mspin_unlock(mspin_lock_t *lock, mspin_node_t *node)
>> +{
>> + mspin_node_t *next = ACCESS_ONCE(node->next);
>> +
>> + if (likely(!next)) {
>> + /*
>> + * Release the lock by setting it to NULL
>> + */
>> + if (cmpxchg(lock, node, NULL) == node)
>> + return;
>> + /* Wait until the next pointer is set */
>> + while (!(next = ACCESS_ONCE(node->next)))
>> + arch_mutex_cpu_relax();
>> + }
>> + barrier();
>> + ACCESS_ONCE(next->locked) = 1;
>> + smp_wmb();
> Do we really need the compiler barrier call? The CPUs can reorder
> anyway. I assume the smp_wbm() call makes sure no there's no funny
> business before the next lock is acquired, might be worth commenting.
The smp_wmb() calls are to make sure that the writes are committed to
memory rather than staying in the cache only. They are safety measures.
The barrier() call probably is not needed because of the next pointer
data dependency, but it doesn't have an actual cost either as it doesn't
translate to any instruction.
Regards,
Longman
next prev parent reply other threads:[~2013-04-16 12:05 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-15 14:37 [PATCH 0/3 v2] mutex: Improve mutex performance by doing less atomic-ops & better spinning Waiman Long
2013-04-15 14:37 ` [PATCH v2 1/3] mutex: Make more scalable by doing less atomic operations Waiman Long
2013-04-15 14:45 ` Rik van Riel
2013-04-15 14:37 ` [PATCH v2 2/3] mutex: Queue mutex spinners with MCS lock to reduce cacheline contention Waiman Long
2013-04-15 14:37 ` Waiman Long
2013-04-15 16:27 ` Rik van Riel
2013-04-16 4:24 ` Davidlohr Bueso
2013-04-16 12:05 ` Waiman Long [this message]
2013-04-16 9:10 ` Ingo Molnar
2013-04-16 14:26 ` Waiman Long
2013-04-17 7:50 ` Ingo Molnar
2013-04-17 7:50 ` Ingo Molnar
2013-04-15 14:37 ` [PATCH v2 optional 3/3] mutex: back out architecture specific check for negative mutex count Waiman Long
2013-04-15 14:37 ` Waiman Long
2013-04-16 10:05 ` Will Deacon
2013-04-16 12:10 ` Waiman Long
2013-04-16 9:12 ` [PATCH 0/3 v2] mutex: Improve mutex performance by doing less atomic-ops & better spinning Ingo Molnar
2013-04-16 9:12 ` Ingo Molnar
2013-04-16 11:49 ` Waiman Long
2013-04-16 13:09 ` Ingo Molnar
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=516D3E81.6060307@hp.com \
--to=waiman.long@hp.com \
--cc=aswin@hp.com \
--cc=davej@redhat.com \
--cc=davidlohr.bueso@hp.com \
--cc=dhowells@redhat.com \
--cc=hpa@zytor.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=scott.norton@hp.com \
--cc=tglx@linutronix.de \
--cc=williams@redhat.com \
--cc=x86@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 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).