From: Waiman Long <Waiman.Long@hp.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>
Cc: linux-arch@vger.kernel.org, Waiman Long <Waiman.Long@hp.com>,
Rik van Riel <riel@redhat.com>,
Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
kvm@vger.kernel.org,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
Daniel J Blueman <daniel@numascale.com>,
x86@kernel.org, Paolo Bonzini <paolo.bonzini@gmail.com>,
linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org,
Scott J Norton <scott.norton@hp.com>,
David Vrabel <david.vrabel@citrix.com>,
Oleg Nesterov <oleg@redhat.com>,
xen-devel@lists.xenproject.org,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Douglas Hatch <doug.hatch@hp.com>
Subject: [PATCH v15 04/15] qspinlock: Extract out code snippets for the next patch
Date: Mon, 6 Apr 2015 22:55:39 -0400 [thread overview]
Message-ID: <1428375350-9213-5-git-send-email-Waiman.Long@hp.com> (raw)
In-Reply-To: <1428375350-9213-1-git-send-email-Waiman.Long@hp.com>
This is a preparatory patch that extracts out the following 2 code
snippets to prepare for the next performance optimization patch.
1) the logic for the exchange of new and previous tail code words
into a new xchg_tail() function.
2) the logic for clearing the pending bit and setting the locked bit
into a new clear_pending_set_locked() function.
This patch also simplifies the trylock operation before queuing by
calling queue_spin_trylock() directly.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
include/asm-generic/qspinlock_types.h | 2 +
kernel/locking/qspinlock.c | 79 ++++++++++++++++++++-------------
2 files changed, 50 insertions(+), 31 deletions(-)
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 9c3f5c2..ef36613 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -58,6 +58,8 @@ 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 0351f78..11f6ad9 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -97,6 +97,42 @@ static inline struct mcs_spinlock *decode_tail(u32 tail)
#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queue spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * 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
+ * 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 old, new, val = atomic_read(&lock->val);
+
+ for (;;) {
+ new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+ return old;
+}
+
+/**
* queue_spin_lock_slowpath - acquire the queue spinlock
* @lock: Pointer to queue spinlock structure
* @val: Current value of the queue spinlock 32-bit word
@@ -178,15 +214,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
*
* *,1,0 -> *,0,1
*/
- for (;;) {
- new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
-
- old = atomic_cmpxchg(&lock->val, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ clear_pending_set_locked(lock);
return;
/*
@@ -203,37 +231,26 @@ queue:
node->next = NULL;
/*
- * We have already touched the queueing cacheline; don't bother with
- * pending stuff.
- *
- * trylock || xchg(lock, node)
- *
- * 0,0,0 -> 0,0,1 ; no tail, not locked -> no tail, locked.
- * p,y,x -> n,y,x ; tail was p -> tail is n; preserving locked.
+ * We touched a (possibly) cold cacheline in the per-cpu queue node;
+ * attempt the trylock once more in the hope someone let go while we
+ * weren't watching.
*/
- 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 (queue_spin_trylock(lock))
+ goto release;
/*
- * we won the trylock; forget about queueing.
+ * We have 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);
/*
* if there was a previous node; link it and wait until reaching the
* head of the waitqueue.
*/
- if (old & ~_Q_LOCKED_PENDING_MASK) {
+ if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
WRITE_ONCE(prev->next, node);
--
1.7.1
WARNING: multiple messages have this Message-ID (diff)
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>,
Boris Ostrovsky <boris.ostrovsky@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>,
Daniel J Blueman <daniel@numascale.com>,
Scott J Norton <scott.norton@hp.com>,
Douglas Hatch <doug.hatch@hp.com>,
Waiman Long <Waiman.Long@hp.com>
Subject: [PATCH v15 04/15] qspinlock: Extract out code snippets for the next patch
Date: Mon, 6 Apr 2015 22:55:39 -0400 [thread overview]
Message-ID: <1428375350-9213-5-git-send-email-Waiman.Long@hp.com> (raw)
Message-ID: <20150407025539.T2Tr5iWG6Axd_YAlkZ3BpLu7v6dQBz7fWxi6cRe6tME@z> (raw)
In-Reply-To: <1428375350-9213-1-git-send-email-Waiman.Long@hp.com>
This is a preparatory patch that extracts out the following 2 code
snippets to prepare for the next performance optimization patch.
1) the logic for the exchange of new and previous tail code words
into a new xchg_tail() function.
2) the logic for clearing the pending bit and setting the locked bit
into a new clear_pending_set_locked() function.
This patch also simplifies the trylock operation before queuing by
calling queue_spin_trylock() directly.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
include/asm-generic/qspinlock_types.h | 2 +
kernel/locking/qspinlock.c | 79 ++++++++++++++++++++-------------
2 files changed, 50 insertions(+), 31 deletions(-)
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 9c3f5c2..ef36613 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -58,6 +58,8 @@ 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 0351f78..11f6ad9 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -97,6 +97,42 @@ static inline struct mcs_spinlock *decode_tail(u32 tail)
#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queue spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * 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
+ * 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 old, new, val = atomic_read(&lock->val);
+
+ for (;;) {
+ new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+ return old;
+}
+
+/**
* queue_spin_lock_slowpath - acquire the queue spinlock
* @lock: Pointer to queue spinlock structure
* @val: Current value of the queue spinlock 32-bit word
@@ -178,15 +214,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
*
* *,1,0 -> *,0,1
*/
- for (;;) {
- new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
-
- old = atomic_cmpxchg(&lock->val, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ clear_pending_set_locked(lock);
return;
/*
@@ -203,37 +231,26 @@ queue:
node->next = NULL;
/*
- * We have already touched the queueing cacheline; don't bother with
- * pending stuff.
- *
- * trylock || xchg(lock, node)
- *
- * 0,0,0 -> 0,0,1 ; no tail, not locked -> no tail, locked.
- * p,y,x -> n,y,x ; tail was p -> tail is n; preserving locked.
+ * We touched a (possibly) cold cacheline in the per-cpu queue node;
+ * attempt the trylock once more in the hope someone let go while we
+ * weren't watching.
*/
- 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 (queue_spin_trylock(lock))
+ goto release;
/*
- * we won the trylock; forget about queueing.
+ * We have 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);
/*
* if there was a previous node; link it and wait until reaching the
* head of the waitqueue.
*/
- if (old & ~_Q_LOCKED_PENDING_MASK) {
+ if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
WRITE_ONCE(prev->next, node);
--
1.7.1
next prev parent reply other threads:[~2015-04-07 2:55 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-04-07 2:55 [PATCH v15 00/15] qspinlock: a 4-byte queue spinlock with PV support Waiman Long
2015-04-07 2:55 ` [PATCH v15 01/15] qspinlock: A simple generic 4-byte queue spinlock Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 02/15] qspinlock, x86: Enable x86-64 to use " Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 03/15] qspinlock: Add pending bit Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` Waiman Long [this message]
2015-04-07 2:55 ` [PATCH v15 04/15] qspinlock: Extract out code snippets for the next patch Waiman Long
2015-04-07 2:55 ` [PATCH v15 05/15] qspinlock: Optimize for smaller NR_CPUS Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 06/15] qspinlock: Use a simple write to grab the lock Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 07/15] qspinlock: Revert to test-and-set on hypervisors Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 08/15] lfsr: a simple binary Galois linear feedback shift register Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 09/15] pvqspinlock: Implement simple paravirt support for the qspinlock Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-09 18:13 ` Peter Zijlstra
2015-04-09 18:13 ` Peter Zijlstra
2015-04-09 18:23 ` Peter Zijlstra
2015-04-09 18:23 ` Peter Zijlstra
2015-04-09 20:36 ` Waiman Long
2015-04-09 20:36 ` Waiman Long
2015-04-09 21:41 ` Waiman Long
2015-04-09 21:41 ` Waiman Long
2015-04-13 14:47 ` Peter Zijlstra
2015-04-13 15:45 ` Waiman Long
2015-04-13 15:45 ` Waiman Long
2015-04-13 15:08 ` Peter Zijlstra
2015-04-13 15:51 ` Waiman Long
2015-04-13 15:51 ` Waiman Long
2015-04-13 15:09 ` Peter Zijlstra
2015-04-13 16:19 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 10/15] pvqspinlock: Implement the paravirt qspinlock for x86 Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 11/15] pvqspinlock, x86: Enable PV qspinlock for KVM Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 12/15] pvqspinlock, x86: Enable PV qspinlock for Xen Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-08 12:01 ` [Xen-devel] " David Vrabel
2015-04-08 12:01 ` David Vrabel
2015-04-08 17:42 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 13/15] pvqspinlock: Only kick CPU at unlock time Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-09 19:57 ` Peter Zijlstra
2015-04-09 20:07 ` Peter Zijlstra
2015-04-09 20:07 ` Peter Zijlstra
2015-04-09 22:06 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 14/15] pvqspinlock: Improve slowpath performance by avoiding cmpxchg Waiman Long
2015-04-07 2:55 ` Waiman Long
2015-04-07 2:55 ` [PATCH v15 15/15] pvqspinlock: Add debug code to check for PV lock hash sanity Waiman Long
2015-04-07 2:55 ` 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=1428375350-9213-5-git-send-email-Waiman.Long@hp.com \
--to=waiman.long@hp.com \
--cc=boris.ostrovsky@oracle.com \
--cc=daniel@numascale.com \
--cc=david.vrabel@citrix.com \
--cc=doug.hatch@hp.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).