@@ -29,7 +29,8 @@ typedef struct qspinlock {
  * Bitfields in the lock word:
  *
  *     0: locked bit
- * 16-31: tail cpu (+1)
+ *    16: must queue bit
+ * 17-31: tail cpu (+1)
  */
 #define	_Q_SET_MASK(type)	(((1U << _Q_ ## type ## _BITS) - 1)\
 				      << _Q_ ## type ## _OFFSET)

@@ -38,7 +39,12 @@ typedef struct qspinlock {
 #define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
 #define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
 
-#define _Q_TAIL_CPU_OFFSET	16
+#define _Q_MUST_Q_OFFSET	16
+#define _Q_MUST_Q_BITS		1
+#define _Q_MUST_Q_MASK		_Q_SET_MASK(MUST_Q)
+#define _Q_MUST_Q_VAL		(1U << _Q_MUST_Q_OFFSET)
+
+#define _Q_TAIL_CPU_OFFSET	17
 #define _Q_TAIL_CPU_BITS	(32 - _Q_TAIL_CPU_OFFSET)
 #define _Q_TAIL_CPU_MASK	_Q_SET_MASK(TAIL_CPU)
 

@@ -22,6 +22,7 @@ struct qnodes {
 /* Tuning parameters */
 static int steal_spins __read_mostly = (1<<5);
 static bool maybe_stealers __read_mostly = true;
+static int head_spins __read_mostly = (1<<8);
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
 

@@ -30,6 +31,11 @@ static __always_inline int get_steal_spins(void)
 	return steal_spins;
 }
 
+static __always_inline int get_head_spins(void)
+{
+	return head_spins;
+}
+
 static inline u32 encode_tail_cpu(int cpu)
 {
 	return (cpu + 1) << _Q_TAIL_CPU_OFFSET;

@@ -120,6 +126,22 @@ static __always_inline u32 publish_tail_cpu(struct qspinlock *lock, u32 tail)
 	return prev;
 }
 
+static __always_inline u32 set_mustq(struct qspinlock *lock)
+{
+	u32 prev;
+
+	asm volatile(
+"1:	lwarx	%0,0,%1		# set_mustq				\n"
+"	or	%0,%0,%2						\n"
+"	stwcx.	%0,0,%1							\n"
+"	bne-	1b							\n"
+	: "=&r" (prev)
+	: "r" (&lock->val), "r" (_Q_MUST_Q_VAL)
+	: "cr0", "memory");
+
+	return prev;
+}
+
 static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 {
 	int cpu = decode_tail_cpu(val);

@@ -155,6 +177,9 @@ static inline bool try_to_steal_lock(struct qspinlock *lock)
 	do {
 		u32 val = READ_ONCE(lock->val);
 
+		if (val & _Q_MUST_Q_VAL)
+			break;
+
 		if (unlikely(!(val & _Q_LOCKED_VAL))) {
 			if (trylock_with_tail_cpu(lock, val))
 				return true;

@@ -237,6 +262,9 @@ static inline void queued_spin_lock_mcs_queue(struct qspinlock *lock)
 		/* We must be the owner, just set the lock bit and acquire */
 		set_locked(lock);
 	} else {
+		int iters = 0;
+		bool mustq = false;
+
 again:
 		/* We're at the head of the waitqueue, wait for the lock. */
 		for (;;) {

@@ -245,6 +273,13 @@ static inline void queued_spin_lock_mcs_queue(struct qspinlock *lock)
 				break;
 
 			cpu_relax();
+
+			iters++;
+			if (!mustq && iters >= get_head_spins()) {
+				mustq = true;
+				set_mustq(lock);
+				val |= _Q_MUST_Q_VAL;
+			}
 		}
 
 		/* If we're the last queued, must clean up the tail. */

@@ -332,9 +367,26 @@ static int steal_spins_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_steal_spins, steal_spins_get, steal_spins_set, "%llu\n");
 
+static int head_spins_set(void *data, u64 val)
+{
+	head_spins = val;
+
+	return 0;
+}
+
+static int head_spins_get(void *data, u64 *val)
+{
+	*val = head_spins;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_head_spins, head_spins_get, head_spins_set, "%llu\n");
+
 static __init int spinlock_debugfs_init(void)
 {
 	debugfs_create_file("qspl_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_steal_spins);
+	debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
 
 	return 0;
 }