@@ -20,9 +20,15 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 	return !!(READ_ONCE(lock->val) & _Q_TAIL_CPU_MASK);
 }
 
+static __always_inline u32 queued_spin_get_locked_val(void)
+{
+	/* XXX: make this use lock value in paca like simple spinlocks? */
+	return _Q_LOCKED_VAL | (smp_processor_id() << _Q_OWNER_CPU_OFFSET);
+}
+
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
-	u32 new = _Q_LOCKED_VAL;
+	u32 new = queued_spin_get_locked_val();
 	u32 prev;
 
 	asm volatile(

@@ -29,6 +29,8 @@ typedef struct qspinlock {
  * Bitfields in the lock word:
  *
  *     0: locked bit
+ *  1-14: lock holder cpu
+ *    15: unused bit
  *    16: must queue bit
  * 17-31: tail cpu (+1)
  */

@@ -39,6 +41,14 @@ typedef struct qspinlock {
 #define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
 #define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
 
+#define _Q_OWNER_CPU_OFFSET	1
+#define _Q_OWNER_CPU_BITS	14
+#define _Q_OWNER_CPU_MASK	_Q_SET_MASK(OWNER_CPU)
+
+#if CONFIG_NR_CPUS > (1U << _Q_OWNER_CPU_BITS)
+#error "qspinlock does not support such large CONFIG_NR_CPUS"
+#endif
+
 #define _Q_MUST_Q_OFFSET	16
 #define _Q_MUST_Q_BITS		1
 #define _Q_MUST_Q_MASK		_Q_SET_MASK(MUST_Q)

@@ -50,7 +50,7 @@ static inline int get_tail_cpu(u32 val)
 /* Take the lock by setting the lock bit, no other CPUs will touch it. */
 static __always_inline void lock_set_locked(struct qspinlock *lock)
 {
-	u32 new = _Q_LOCKED_VAL;
+	u32 new = queued_spin_get_locked_val();
 	u32 prev;
 
 	asm volatile(

@@ -68,7 +68,7 @@ static __always_inline void lock_set_locked(struct qspinlock *lock)
 /* Take lock, clearing tail, cmpxchg with old (which must not be locked) */
 static __always_inline int trylock_clear_tail_cpu(struct qspinlock *lock, u32 old)
 {
-	u32 new = _Q_LOCKED_VAL;
+	u32 new = queued_spin_get_locked_val();
 	u32 prev;
 
 	BUG_ON(old & _Q_LOCKED_VAL);

@@ -116,7 +116,7 @@ static __always_inline u32 __trylock_cmpxchg(struct qspinlock *lock, u32 old, u3
 /* Take lock, preserving tail, cmpxchg with val (which must not be locked) */
 static __always_inline int trylock_with_tail_cpu(struct qspinlock *lock, u32 val)
 {
-	u32 newval = _Q_LOCKED_VAL | (val & _Q_TAIL_CPU_MASK);
+	u32 newval = queued_spin_get_locked_val() | (val & _Q_TAIL_CPU_MASK);
 
 	if (__trylock_cmpxchg(lock, val, newval) == val)
 		return 1;