locking/qspinlock: Extract out code snippets for the next patch
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 queued_spin_trylock() directly.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paolo Bonzini <paolo.bonzini@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: virtualization@lists.linux-foundation.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1429901803-29771-5-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index af9c2ef..82bb4a9 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -97,6 +97,42 @@
#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 queued 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 queued 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;
+}
+
+/**
* queued_spin_lock_slowpath - acquire the queued spinlock
* @lock: Pointer to queued spinlock structure
* @val: Current value of the queued spinlock 32-bit word
@@ -178,15 +214,7 @@
*
* *,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 @@
node->next = NULL;
/*
+ * 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.
+ */
+ if (queued_spin_trylock(lock))
+ goto release;
+
+ /*
* 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.
+ * p,*,* -> n,*,*
*/
- 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;
- }
-
- /*
- * we won the trylock; forget about queueing.
- */
- 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);
