From 0a21ab2c4bf42405de6b11549ad80937b19d677f Mon Sep 17 00:00:00 2001
From: Andrew Turner <andrew@FreeBSD.org>
Date: Mon, 7 Sep 2015 14:01:18 +0000
Subject: [PATCH] Use load-acquire semantics while waiting for td_lock to be
 released. The store should have release semantics and will have due to the
 dsb above it so add a comment to explain this. [1]

While here update the code to not reload the current thread, it's already
in a register, we just need to not trash it.

Suggested by:	kib [1]
Sponsored by:	ABT Systems Ltd
---
 sys/arm64/arm64/swtch.S | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/sys/arm64/arm64/swtch.S b/sys/arm64/arm64/swtch.S
index fbffaed437a..bc2e5210341 100644
--- a/sys/arm64/arm64/swtch.S
+++ b/sys/arm64/arm64/swtch.S
@@ -160,17 +160,18 @@ ENTRY(cpu_switch)
 	dsb	sy
 	isb
 
-	/* Release the old thread */
+	/*
+	 * Release the old thread. This doesn't need to be a store-release
+	 * as the above dsb instruction will provide release semantics.
+	 */
 	str	x2, [x0, #TD_LOCK]
 #if defined(SCHED_ULE) && defined(SMP)
 	/* Read the value in blocked_lock */
 	ldr	x0, =_C_LABEL(blocked_lock)
-	ldr	x1, [x0]
-	/* Load curthread */
-	ldr	x2, [x18, #PC_CURTHREAD]
+	ldr	x2, [x0]
 1:
-	ldr	x3, [x2, #TD_LOCK]
-	cmp	x3, x1
+	ldar	x3, [x1, #TD_LOCK]
+	cmp	x3, x2
 	b.eq	1b
 #endif