@@ -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)
@@ -95,6 +95,54 @@ 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
+ * @val : Current value of the queue spinlock 32-bit word
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void
+clear_pending_set_locked(struct qspinlock *lock, u32 val)
+{
+ u32 new, old;
+
+ for (;;) {
+ new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+}
+
+/**
+ * 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
@@ -176,15 +224,7 @@ 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, val);
return;
/*
@@ -201,37 +241,26 @@ 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);
ACCESS_ONCE(prev->next) = node;
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 <peterz@infradead.org> --- include/asm-generic/qspinlock_types.h | 2 + kernel/locking/qspinlock.c | 91 +++++++++++++++++++++----------- 2 files changed, 62 insertions(+), 31 deletions(-)