!123 revert memcpy optimize for kunpeng to avoid performance regression when input large than kbyte.

From: @liqingqing_1229
Reviewed-by: @wswsamao
Signed-off-by: @wswsamao

backport-aarch64-revert-memcpy-optimze-for-kunpeng-to-avoid-p.patch

@@ -0,0 +1,57 @@
+From 28f2ce27722d890a884cc7fa2f6d2bc0cb418f26 Mon Sep 17 00:00:00 2001
+From: Shuo Wang <wangshuo47@huawei.com>
+Date: Wed, 20 Jan 2021 15:20:44 +0800
+Subject: [PATCH] aarch64: revert memcpy optimze for kunpeng to avoid
+ performance degradation
+
+In commit 863d775c481704baaa41855fc93e5a1ca2dc6bf6, kunpeng920 is added to default memcpy version,
+however, there is performance degradation when the copy size is some large bytes, eg: 100k.
+This is the result, tested in glibc-2.28:
+             before backport  after backport	 Performance improvement
+memcpy_1k      0.005              0.005                 0.00%
+memcpy_10k     0.032              0.029                 10.34%
+memcpy_100k    0.356              0.429                 -17.02%
+memcpy_1m      7.470              11.153                -33.02%
+
+This is the demo
+#include "stdio.h"
+#include "string.h"
+#include "stdlib.h"
+
+char a[1024*1024] = {12};
+char b[1024*1024] = {13};
+int main(int argc, char *argv[])
+{
+    int i = atoi(argv[1]);
+    int j;
+    int size = atoi(argv[2]);
+
+    for (j = 0; j < i; j++)
+        memcpy(b, a, size*1024);
+    return 0;
+}
+
+# gcc -g -O0 memcpy.c -o memcpy
+# time taskset -c 10 ./memcpy 100000 1024
+
+Co-authored-by: liqingqing <liqingqing3@huawei.com>
+---
+ sysdeps/aarch64/multiarch/memcpy.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/sysdeps/aarch64/multiarch/memcpy.c b/sysdeps/aarch64/multiarch/memcpy.c
+index 27259d3..0e0a5cb 100644
+--- a/sysdeps/aarch64/multiarch/memcpy.c
++++ b/sysdeps/aarch64/multiarch/memcpy.c
+@@ -37,7 +37,7 @@ extern __typeof (__redirect_memcpy) __memcpy_falkor attribute_hidden;
+ libc_ifunc (__libc_memcpy,
+             (IS_THUNDERX (midr)
+ 	     ? __memcpy_thunderx
+-	     : (IS_FALKOR (midr) || IS_PHECDA (midr) || IS_KUNPENG920 (midr)
++	     : (IS_FALKOR (midr) || IS_PHECDA (midr)
+ 		? __memcpy_falkor
+ 		: (IS_THUNDERX2 (midr) || IS_THUNDERX2PA (midr)
+ 		  ? __memcpy_thunderx2
+-- 
+1.8.3.1
+

glibc.spec

@@ -59,7 +59,7 @@
 ##############################################################################
 Name: 	 	glibc
 Version: 	2.28
-Release: 	52
+Release: 	53
 Summary: 	The GNU libc libraries
 License:	%{all_license}
 URL: 		http://www.gnu.org/software/glibc/
@@ -108,6 +108,7 @@ Patch31: backport-addmntent-Remove-unbounded-alloca-usage-from-getmnte.patch
 Patch32: backport-Use-O_CLOEXEC-in-sysconf-BZ-26791.patch
 Patch33: backport-aarch64-Add-unwind-information-to-_start-bug-26853.patch
 Patch34: disable-threads-in-Intel-vm-environment.patch
+Patch35: backport-aarch64-revert-memcpy-optimze-for-kunpeng-to-avoid-p.patch
 
 Provides: ldconfig rtld(GNU_HASH) bundled(gnulib)
 
@@ -1103,6 +1104,9 @@ fi
 %doc hesiod/README.hesiod
 
 %changelog
+* Fri Jan 22 2021 Qingqing Li<liqingqing3@huawei.com> - 2.28-53
+- revert memcpy optimze for kunpeng to avoid performance regression when input large than kbyte. 
+
 * Thu Jan 21 2021 Wang Shuo<wangshuo_1994@foxmail.com> - 2.28-52
 - Disable threads in Intel vm environment to avoid performance degradation