locking fixes

index 54a8e65e18b6..7d026bf27713 100644
@@ -25,7 +25,20 @@
 #include <asm-generic/qrwlock_types.h>
 
 /*
- * Writer states & reader shift and bias
+ * Writer states & reader shift and bias.
+ *
+ *       | +0 | +1 | +2 | +3 |
+ *   ----+----+----+----+----+
+ *    LE | 78 | 56 | 34 | 12 | 0x12345678
+ *   ----+----+----+----+----+
+ *       | wr |      rd      |
+ *       +----+----+----+----+
+ *
+ *   ----+----+----+----+----+
+ *    BE | 12 | 34 | 56 | 78 | 0x12345678
+ *   ----+----+----+----+----+
+ *       |      rd      | wr |
+ *       +----+----+----+----+
  */
 #define	_QW_WAITING	1		/* A writer is waiting	   */
 #define	_QW_LOCKED	0xff		/* A writer holds the lock */

@@ -134,12 +147,22 @@ static inline void queued_read_unlock(struct qrwlock *lock)
 }
 
 /**
+ * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: the write byte address of a queue rwlock
+ */
+static inline u8 *__qrwlock_write_byte(struct qrwlock *lock)
+{
+	return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN);
+}
+
+/**
  * queued_write_unlock - release write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	smp_store_release((u8 *)&lock->cnts, 0);
+	smp_store_release(__qrwlock_write_byte(lock), 0);
 }
 
 /*

index 33664f70e2d2..46cb3a301bc1 100644
@@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled;
  * Futex flags used to encode options to functions and preserve them across
  * restarts.
  */
-#define FLAGS_SHARED		0x01
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED		0x01
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED		0x00
+#endif
 #define FLAGS_CLOCKRT		0x02
 #define FLAGS_HAS_TIMEOUT	0x04
 

@@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key)
 	if (!key->both.ptr)
 		return;
 
+	/*
+	 * On MMU less systems futexes are always "private" as there is no per
+	 * process address space. We need the smp wmb nevertheless - yes,
+	 * arch/blackfin has MMU less SMP ...
+	 */
+	if (!IS_ENABLED(CONFIG_MMU)) {
+		smp_mb(); /* explicit smp_mb(); (B) */
+		return;
+	}
+
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
 		ihold(key->shared.inode); /* implies smp_mb(); (B) */

@@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key)
 		return;
 	}
 
+	if (!IS_ENABLED(CONFIG_MMU))
+		return;
+
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
 		iput(key->shared.inode);

index 37649e69056c..8a99abf58080 100644
@@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 				goto gotlock;
 			}
 		}
-		WRITE_ONCE(pn->state, vcpu_halted);
+		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
 		pv_wait(&l->locked, _Q_SLOW_VAL);

index 22e025309845..b9d031516254 100644
@@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf,
 		 */
 		if ((counter == qstat_pv_latency_kick) ||
 		    (counter == qstat_pv_latency_wake)) {
-			stat = 0;
 			if (kicks)
 				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
 		}