From: Waiman Long <Waiman.Long@hp.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Peter Zijlstra <peterz@infradead.org>
Cc: linux-arch@vger.kernel.org, x86@kernel.org,
linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org,
xen-devel@lists.xenproject.org, kvm@vger.kernel.org,
Paolo Bonzini <paolo.bonzini@gmail.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Rik van Riel <riel@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
David Vrabel <david.vrabel@citrix.com>,
Oleg Nesterov <oleg@redhat.com>, Gleb Natapov <gleb@redhat.com>,
Scott J Norton <scott.norton@hp.com>,
Chegu Vinod <chegu_vinod@hp.com>,
Waiman Long <Waiman.Long@hp.com>
Subject: [PATCH v9 04/19] qspinlock: Extract out the exchange of tail code word
Date: Thu, 17 Apr 2014 11:03:56 -0400 [thread overview]
Message-ID: <1397747051-15401-5-git-send-email-Waiman.Long@hp.com> (raw)
In-Reply-To: <1397747051-15401-1-git-send-email-Waiman.Long@hp.com>
This patch extracts the logic for the exchange of new and previous tail
code words into a new xchg_tail() function which can be optimized in a
later patch.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
include/asm-generic/qspinlock_types.h | 2 +
kernel/locking/qspinlock.c | 61 +++++++++++++++++++++------------
2 files changed, 41 insertions(+), 22 deletions(-)
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index bd25081..ed5d89a 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -61,6 +61,8 @@ typedef struct qspinlock {
#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET)
#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU)
+#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)
#define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET)
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index d35362a..fcf06cb 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -86,6 +86,34 @@ static inline struct mcs_spinlock *decode_tail(u32 tail)
#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queue spinlock structure
+ * @tail : The new queue tail code word
+ * @pval : Pointer to current value of the queue spinlock 32-bit word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32
+xchg_tail(struct qspinlock *lock, u32 tail, u32 *pval)
+{
+ u32 old, new, val = *pval;
+
+ for (;;) {
+ new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+ *pval = new;
+ return old;
+}
+
+/**
* trylock_pending - try to acquire queue spinlock using the pending bit
* @lock : Pointer to queue spinlock structure
* @pval : Pointer to value of the queue spinlock 32-bit word
@@ -192,36 +220,25 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
node->next = NULL;
/*
- * we already touched the queueing cacheline; don't bother with pending
- * stuff.
- *
- * trylock || xchg(lock, node)
- *
- * 0,0,0 -> 0,0,1 ; trylock
- * p,y,x -> n,y,x ; prev = xchg(lock, node)
+ * We touched a (possibly) cold cacheline; attempt the trylock once
+ * more in the hope someone let go while we weren't watching as long
+ * as no one was queuing.
*/
- for (;;) {
- new = _Q_LOCKED_VAL;
- if (val)
- new = tail | (val & _Q_LOCKED_PENDING_MASK);
-
- old = atomic_cmpxchg(&lock->val, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ if (!(val & _Q_TAIL_MASK) && queue_spin_trylock(lock))
+ goto release;
/*
- * we won the trylock; forget about queueing.
+ * we already touched the queueing cacheline; don't bother with pending
+ * stuff.
+ *
+ * p,*,* -> n,*,*
*/
- if (new == _Q_LOCKED_VAL)
- goto release;
+ old = xchg_tail(lock, tail, &val);
/*
* if there was a previous node; link it and wait.
*/
- if (old & ~_Q_LOCKED_PENDING_MASK) {
+ if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
ACCESS_ONCE(prev->next) = node;
--
1.7.1
next prev parent reply other threads:[~2014-04-17 15:04 UTC|newest]
Thread overview: 131+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-17 15:03 [PATCH v9 00/19] qspinlock: a 4-byte queue spinlock with PV support Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 15:03 ` [PATCH v9 01/19] qspinlock: A simple generic 4-byte queue spinlock Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 15:03 ` [PATCH v9 02/19] qspinlock, x86: Enable x86-64 to use " Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 15:03 ` [PATCH v9 03/19] qspinlock: Add pending bit Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 15:42 ` Peter Zijlstra
2014-04-17 15:42 ` Peter Zijlstra
2014-04-17 21:20 ` Waiman Long
2014-04-18 8:13 ` Peter Zijlstra
2014-04-18 8:13 ` Peter Zijlstra
2014-04-18 17:07 ` Waiman Long
2014-04-18 17:07 ` Waiman Long
2014-04-18 7:42 ` Ingo Molnar
2014-04-18 7:42 ` Ingo Molnar
2014-04-18 16:23 ` Waiman Long
2014-04-18 16:23 ` Waiman Long
2014-04-18 16:35 ` Konrad Rzeszutek Wilk
2014-04-18 16:35 ` Konrad Rzeszutek Wilk
2014-04-18 18:12 ` Waiman Long
2014-04-18 18:12 ` Waiman Long
2014-04-17 15:03 ` Waiman Long [this message]
2014-04-17 15:49 ` [PATCH v9 04/19] qspinlock: Extract out the exchange of tail code word Peter Zijlstra
2014-04-17 15:49 ` Peter Zijlstra
2014-04-17 21:28 ` Waiman Long
2014-04-17 21:28 ` Waiman Long
2014-04-18 8:15 ` Peter Zijlstra
2014-04-18 8:15 ` Peter Zijlstra
2014-04-18 17:32 ` Waiman Long
2014-04-18 17:32 ` Waiman Long
2014-04-18 17:53 ` Peter Zijlstra
2014-04-18 17:53 ` Peter Zijlstra
2014-04-18 18:13 ` Waiman Long
2014-04-18 18:13 ` Waiman Long
2014-04-17 15:03 ` [PATCH v9 05/19] qspinlock: Optimize for smaller NR_CPUS Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 15:50 ` Peter Zijlstra
2014-04-17 15:50 ` Peter Zijlstra
2014-04-17 21:29 ` Waiman Long
2014-04-17 21:29 ` Waiman Long
2014-04-17 15:51 ` Peter Zijlstra
2014-04-17 15:51 ` Peter Zijlstra
2014-04-17 21:33 ` Waiman Long
2014-04-17 21:33 ` Waiman Long
2014-04-17 15:56 ` Peter Zijlstra
2014-04-17 15:56 ` Peter Zijlstra
2014-04-17 21:46 ` Waiman Long
2014-04-17 21:46 ` Waiman Long
2014-04-18 8:27 ` Peter Zijlstra
2014-04-18 8:27 ` Peter Zijlstra
2014-04-18 17:52 ` Waiman Long
2014-04-18 17:52 ` Waiman Long
2014-04-18 19:05 ` Peter Zijlstra
2014-04-18 19:05 ` Peter Zijlstra
2014-04-18 21:40 ` Waiman Long
2014-04-18 21:40 ` Waiman Long
2014-04-23 14:23 ` Waiman Long
2014-04-23 14:23 ` Waiman Long
2014-04-23 14:56 ` Konrad Rzeszutek Wilk
2014-04-23 14:56 ` Konrad Rzeszutek Wilk
2014-04-23 17:43 ` Waiman Long
2014-04-23 17:43 ` Waiman Long
2014-04-23 17:55 ` Konrad Rzeszutek Wilk
2014-04-23 17:55 ` Konrad Rzeszutek Wilk
2014-04-23 22:24 ` Waiman Long
2014-04-23 22:24 ` Waiman Long
2014-04-23 23:48 ` Waiman Long
2014-04-23 23:48 ` Waiman Long
2014-04-17 15:58 ` Peter Zijlstra
2014-04-17 15:58 ` Peter Zijlstra
2014-04-17 21:49 ` Waiman Long
2014-04-17 21:49 ` Waiman Long
2014-04-18 7:46 ` Ingo Molnar
2014-04-18 7:46 ` Ingo Molnar
2014-04-18 16:26 ` Waiman Long
2014-04-18 16:26 ` Waiman Long
2014-04-19 9:24 ` Ingo Molnar
2014-04-19 9:24 ` Ingo Molnar
2014-04-17 15:03 ` [PATCH v9 06/19] qspinlock: prolong the stay in the pending bit path Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 16:36 ` Peter Zijlstra
2014-04-17 16:36 ` Peter Zijlstra
2014-04-18 1:46 ` Waiman Long
2014-04-18 1:46 ` Waiman Long
2014-04-18 8:33 ` Peter Zijlstra
2014-04-18 8:33 ` Peter Zijlstra
2014-04-18 18:07 ` Waiman Long
2014-04-18 18:07 ` Waiman Long
2014-04-17 15:03 ` [PATCH v9 07/19] qspinlock: Use a simple write to grab the lock, if applicable Waiman Long
2014-04-17 15:03 ` Waiman Long
2014-04-17 16:54 ` Peter Zijlstra
2014-04-17 16:54 ` Peter Zijlstra
2014-04-17 15:04 ` [PATCH v9 08/19] qspinlock: Make a new qnode structure to support virtualization Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 09/19] qspinlock: Prepare for unfair lock support Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 10/19] qspinlock, x86: Allow unfair spinlock in a virtual guest Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 11/19] qspinlock: Split the MCS queuing code into a separate slowerpath Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 12/19] unfair qspinlock: Variable frequency lock stealing mechanism Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 13/19] unfair qspinlock: Enable lock stealing in lock waiters Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 14/19] pvqspinlock, x86: Rename paravirt_ticketlocks_enabled Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 15/19] pvqspinlock, x86: Add PV data structure & methods Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 16/19] pvqspinlock: Enable coexistence with the unfair lock Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 17/19] pvqspinlock: Add qspinlock para-virtualization support Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 18/19] pvqspinlock, x86: Enable PV qspinlock PV for KVM Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 15:04 ` [PATCH v9 19/19] pvqspinlock, x86: Enable PV qspinlock for XEN Waiman Long
2014-04-17 15:04 ` Waiman Long
2014-04-17 17:23 ` [PATCH v9 00/19] qspinlock: a 4-byte queue spinlock with PV support Konrad Rzeszutek Wilk
2014-04-17 17:23 ` Konrad Rzeszutek Wilk
2014-04-17 17:40 ` Raghavendra K T
2014-04-17 17:40 ` Raghavendra K T
2014-04-18 1:50 ` Waiman Long
2014-04-18 1:48 ` Waiman Long
2014-04-18 1:48 ` Waiman Long
2014-04-18 13:18 ` Konrad Rzeszutek Wilk
2014-04-18 13:18 ` Konrad Rzeszutek Wilk
2014-04-18 17:05 ` Waiman Long
2014-04-18 17:05 ` Waiman Long
2014-04-27 18:09 ` Raghavendra K T
2014-05-07 15:00 ` Waiman Long
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=1397747051-15401-5-git-send-email-Waiman.Long@hp.com \
--to=waiman.long@hp.com \
--cc=chegu_vinod@hp.com \
--cc=david.vrabel@citrix.com \
--cc=gleb@redhat.com \
--cc=hpa@zytor.com \
--cc=konrad.wilk@oracle.com \
--cc=kvm@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=paolo.bonzini@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=raghavendra.kt@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=scott.norton@hp.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=virtualization@lists.linux-foundation.org \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xenproject.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).