From: Waiman Long <Waiman.Long@xxxxxx>
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@xxxxxx>
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
include/asm-generic/qspinlock_types.h | 2 +
kernel/locking/qspinlock.c | 58 +++++++++++++++++++++-------------
2 files changed, 38 insertions(+), 22 deletions(-)
--- 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)
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -86,6 +86,31 @@ static inline struct mcs_spinlock *decod
#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
+ * 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
@@ -182,36 +207,25 @@ void queue_spin_lock_slowpath(struct qsp
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 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 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.
*/
- if (old & ~_Q_LOCKED_PENDING_MASK) {
+ if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
ACCESS_ONCE(prev->next) = node;
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
