Merge tag 'v4.4.16' into linux-linaro-lsk-v4.4

This is the 4.4.16 stable release

# gpg: Signature made Wed 27 Jul 2016 17:48:38 BST using RSA key ID 6092693E
# gpg: requesting key 6092693E from hkp server the.earth.li
# gpg: key 6092693E: public key "Greg Kroah-Hartman (Linux kernel stable release signing key) <greg@kroah.com>" imported
# gpg: public key of ultimately trusted key B4B0BED6 not found
# gpg: 2 marginal(s) needed, 1 complete(s) needed, PGP trust model
# gpg: depth: 0  valid:   1  signed:   0  trust: 0-, 0q, 0n, 0m, 0f, 1u
# gpg: Total number processed: 1
# gpg:               imported: 1  (RSA: 1)
# gpg: Good signature from "Greg Kroah-Hartman (Linux kernel stable release signing key) <greg@kroah.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 647F 2865 4894 E3BD 4571  99BE 38DB BDC8 6092 693E

1 files changed, 60 insertions, 0 deletions

diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 87e9ce6a63c5..8173bc7fec92 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -255,6 +255,66 @@ static __always_inline void __pv_wait_head(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
+ *
+ *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
+ *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	u32 val;
+
+	for (;;) {
+		val = atomic_read(&lock->val);
+
+		if (!val) /* not locked, we're done */
+			goto done;
+
+		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+			break;
+
+		/* not locked, but pending, wait until we observe the lock */
+		cpu_relax();
+	}
+
+	/* any unlock is good */
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+done:
+	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**