@@ -103,24 +103,33 @@ static inline struct mcs_spinlock *decode_tail(u32 tail)
* By using the whole 2nd least significant byte for the pending bit, we
* can allow better optimization of the lock acquisition for the pending
* bit holder.
+ *
+ * This internal structure is also used by the set_locked function which
+ * is not restricted to _Q_PENDING_BITS == 8.
*/
-#if _Q_PENDING_BITS == 8
-
struct __qspinlock {
union {
atomic_t val;
- struct {
#ifdef __LITTLE_ENDIAN
+ u8 locked;
+ struct {
u16 locked_pending;
u16 tail;
+ };
#else
+ struct {
u16 tail;
u16 locked_pending;
-#endif
};
+ struct {
+ u8 reserved[3];
+ u8 locked;
+ };
+#endif
};
};
+#if _Q_PENDING_BITS == 8
/**
* clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queue spinlock structure
@@ -207,6 +216,19 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
#endif /* _Q_PENDING_BITS == 8 */
/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queue spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ ACCESS_ONCE(l->locked) = _Q_LOCKED_VAL;
+}
+
+/**
* queue_spin_lock_slowpath - acquire the queue spinlock
* @lock: Pointer to queue spinlock structure
* @val: Current value of the queue spinlock 32-bit word
@@ -339,10 +361,13 @@ queue:
/*
* we're at the head of the waitqueue, wait for the owner & pending to
* go away.
+ * Load-acquired is used here because the set_locked()
+ * function below may not be a full memory barrier.
*
* *,x,y -> *,0,0
*/
- while ((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK)
+ while ((val = smp_load_acquire(&lock->val.counter)) &
+ _Q_LOCKED_PENDING_MASK)
cpu_relax();
/*
@@ -350,15 +375,19 @@ queue:
*
* n,0,0 -> 0,0,1 : lock, uncontended
* *,0,0 -> *,0,1 : lock, contended
+ *
+ * If the queue head is the only one in the queue (lock value == tail),
+ * clear the tail code and grab the lock. Otherwise, we only need
+ * to grab the lock.
*/
for (;;) {
- new = _Q_LOCKED_VAL;
- if (val != tail)
- new |= val;
-
- old = atomic_cmpxchg(&lock->val, val, new);
- if (old == val)
+ if (val != tail) {
+ set_locked(lock);
break;
+ }
+ old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+ if (old == val)
+ goto release; /* No contention */
val = old;
}
@@ -366,12 +395,10 @@ queue:
/*
* contended path; wait for next, release.
*/
- if (new != _Q_LOCKED_VAL) {
- while (!(next = ACCESS_ONCE(node->next)))
- cpu_relax();
+ while (!(next = ACCESS_ONCE(node->next)))
+ cpu_relax();
- arch_mcs_spin_unlock_contended(&next->locked);
- }
+ arch_mcs_spin_unlock_contended(&next->locked);
release:
/*
Currently, atomic_cmpxchg() is used to get the lock. However, this is not really necessary if there is more than one task in the queue and the queue head don't need to reset the tail code. For that case, a simple write to set the lock bit is enough as the queue head will be the only one eligible to get the lock as long as it checks that both the lock and pending bits are not set. The current pending bit waiting code will ensure that the bit will not be set as soon as the tail code in the lock is set. With that change, the are some slight improvement in the performance of the queue spinlock in the 5M loop micro-benchmark run on a 4-socket Westere-EX machine as shown in the tables below. [Standalone/Embedded - same node] # of tasks Before patch After patch %Change ---------- ----------- ---------- ------- 3 2324/2321 2248/2265 -3%/-2% 4 2890/2896 2819/2831 -2%/-2% 5 3611/3595 3522/3512 -2%/-2% 6 4281/4276 4173/4160 -3%/-3% 7 5018/5001 4875/4861 -3%/-3% 8 5759/5750 5563/5568 -3%/-3% [Standalone/Embedded - different nodes] # of tasks Before patch After patch %Change ---------- ----------- ---------- ------- 3 12242/12237 12087/12093 -1%/-1% 4 10688/10696 10507/10521 -2%/-2% It was also found that this change produced a much bigger performance improvement in the newer IvyBridge-EX chip and was essentially to close the performance gap between the ticket spinlock and queue spinlock. The disk workload of the AIM7 benchmark was run on a 4-socket Westmere-EX machine with both ext4 and xfs RAM disks at 3000 users on a 3.14 based kernel. The results of the test runs were: AIM7 XFS Disk Test kernel JPM Real Time Sys Time Usr Time ----- --- --------- -------- -------- ticketlock 5678233 3.17 96.61 5.81 qspinlock 5750799 3.13 94.83 5.97 AIM7 EXT4 Disk Test kernel JPM Real Time Sys Time Usr Time ----- --- --------- -------- -------- ticketlock 1114551 16.15 509.72 7.11 qspinlock 2184466 8.24 232.99 6.01 The ext4 filesystem run had a much higher spinlock contention than the xfs filesystem run. The "ebizzy -m" test was also run with the following results: kernel records/s Real Time Sys Time Usr Time ----- --------- --------- -------- -------- ticketlock 2075 10.00 216.35 3.49 qspinlock 3023 10.00 198.20 4.80 Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> --- kernel/locking/qspinlock.c | 59 ++++++++++++++++++++++++++++++++------------ 1 files changed, 43 insertions(+), 16 deletions(-)