glibc aarch64 memcpy fix for cortex-a72

0001-Aarch64-Make-memcpy-more-compatible-with-device-memo.patch

From 6cf513dc8c5ab758072d894f10a58fbb4a146bd6 Mon Sep 17 00:00:00 2001
From: Jon Nettleton <jon@solid-run.com>
Date: Wed, 6 Oct 2021 09:16:35 -0400
Subject: [PATCH] Aarch64: Make memcpy more compatible with device memory

For normal non-cacheable memory ACE supports 4x128 bit r/w WRAP
transfers or 1x128 bit r/w INCR transfers.  By re-ordering the
stp's in memcpy / memmove we can accomodate this better without
impacting the existing code.

This fixes an issue seen on multiple Cortex-A72 SOCs when writing
directly to a PCIe memmapped frame-buffer, which resulted in
corruption.

Signed-off-by: Jon Nettleton <jon@solid-run.com>
---
 sysdeps/aarch64/memcpy.S | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/sysdeps/aarch64/memcpy.S b/sysdeps/aarch64/memcpy.S
index 0adc5246..b4f3b3aa 100644
--- a/sysdeps/aarch64/memcpy.S
+++ b/sysdeps/aarch64/memcpy.S
@@ -152,12 +152,12 @@ L(copy128):
 	stp	G_l, G_h, [dstend, -64]
 	stp	H_l, H_h, [dstend, -48]
 L(copy96):
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
 	stp	A_l, A_h, [dstin]
 	stp	B_l, B_h, [dstin, 16]
 	stp	E_l, E_h, [dstin, 32]
 	stp	F_l, F_h, [dstin, 48]
-	stp	C_l, C_h, [dstend, -32]
-	stp	D_l, D_h, [dstend, -16]
 	ret
 
 	.p2align 4
@@ -274,10 +274,10 @@ L(copy64_from_start):
 	stp	C_l, C_h, [dstend, -48]
 	ldp	C_l, C_h, [src]
 	stp	D_l, D_h, [dstend, -64]
-	stp	G_l, G_h, [dstin, 48]
-	stp	A_l, A_h, [dstin, 32]
-	stp	B_l, B_h, [dstin, 16]
 	stp	C_l, C_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	A_l, A_h, [dstin, 32]
+	stp	G_l, G_h, [dstin, 48]
 	ret
 
 END (MEMMOVE)
-- 
2.32.0