Synchronize bsaes-armv7.pl with upstream.

This pulls in upstream's 0822d41b6d54132df96c02cc6f6fa9b179378351 and a
portion of a285992763f3961f69a8d86bf7dfff020a08cef9. The former, in
particular, fixes a crash on iOS.

Change-Id: I3c083975d8d11e58b5a2919fcabbf83628f36340
Reviewed-on: https://boringssl-review.googlesource.com/14383
Reviewed-by: Steven Valdez <svaldez@chromium.org>
Reviewed-by: David Benjamin <davidben@google.com>
Commit-Queue: David Benjamin <davidben@google.com>
CQ-Verified: CQ bot account: commit-bot@chromium.org <commit-bot@chromium.org>
diff --git a/crypto/aes/asm/bsaes-armv7.pl b/crypto/aes/asm/bsaes-armv7.pl
index d645de4..92f5ece 100644
--- a/crypto/aes/asm/bsaes-armv7.pl
+++ b/crypto/aes/asm/bsaes-armv7.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2012-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (the "License").  You may not use
+# this file except in compliance with the License.  You can obtain a copy
+# in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+
 
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -731,6 +738,7 @@
 .thumb
 #else
 .code   32
+# undef __thumb2__
 #endif
 
 .type	_bsaes_decrypt8,%function
@@ -1357,7 +1365,7 @@
 	vmov	@XMM[4],@XMM[15]		@ just in case ensure that IV
 	vmov	@XMM[5],@XMM[0]			@ and input are preserved
 	bl	AES_decrypt
-	vld1.8	{@XMM[0]}, [$fp,:64]		@ load result
+	vld1.8	{@XMM[0]}, [$fp]		@ load result
 	veor	@XMM[0], @XMM[0], @XMM[4]	@ ^= IV
 	vmov	@XMM[15], @XMM[5]		@ @XMM[5] holds input
 	vst1.8	{@XMM[0]}, [$rounds]		@ write output