summaryrefslogtreecommitdiff
path: root/kernel/locking/qspinlock.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/locking/qspinlock.c')
-rw-r--r--kernel/locking/qspinlock.c31
1 files changed, 20 insertions, 11 deletions
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index b9515fcc9b29..7d96bed718e4 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -22,6 +22,7 @@
#include <linux/prefetch.h>
#include <asm/byteorder.h>
#include <asm/qspinlock.h>
+#include <trace/events/lock.h>
/*
* Include queued spinlock statistics code
@@ -219,21 +220,18 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
*/
static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
{
- u32 old, new, val = atomic_read(&lock->val);
+ u32 old, new;
- for (;;) {
- new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_read(&lock->val);
+ do {
+ new = (old & _Q_LOCKED_PENDING_MASK) | tail;
/*
* We can use relaxed semantics since the caller ensures that
* the MCS node is properly initialized before updating the
* tail.
*/
- old = atomic_cmpxchg_relaxed(&lock->val, val, new);
- if (old == val)
- break;
+ } while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
- val = old;
- }
return old;
}
#endif /* _Q_PENDING_BITS == 8 */
@@ -312,7 +310,7 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
* contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' :
* queue : ^--' :
*/
-void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
struct mcs_spinlock *prev, *next, *node;
u32 old, tail;
@@ -370,7 +368,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
/*
* We're pending, wait for the owner to go away.
*
- * 0,1,1 -> 0,1,0
+ * 0,1,1 -> *,1,0
*
* this wait loop must be a load-acquire such that we match the
* store-release that clears the locked bit and create lock
@@ -379,7 +377,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
* barriers.
*/
if (val & _Q_LOCKED_MASK)
- atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK));
+ smp_cond_load_acquire(&lock->locked, !VAL);
/*
* take ownership and clear the pending bit.
@@ -401,6 +399,8 @@ pv_queue:
idx = node->count++;
tail = encode_tail(smp_processor_id(), idx);
+ trace_contention_begin(lock, LCB_F_SPIN);
+
/*
* 4 nodes are allocated based on the assumption that there will
* not be nested NMIs taking spinlocks. That may not be true in
@@ -554,6 +554,8 @@ locked:
pv_kick_node(lock, next);
release:
+ trace_contention_end(lock, 0);
+
/*
* release the node
*/
@@ -581,4 +583,11 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
#include "qspinlock_paravirt.h"
#include "qspinlock.c"
+bool nopvspin;
+static __init int parse_nopvspin(char *arg)
+{
+ nopvspin = true;
+ return 0;
+}
+early_param("nopvspin", parse_nopvspin);
#endif