S390: Implement mempcpy with help of memcpy. [BZ #19765]

There exist optimized memcpy functions on s390, but no optimized mempcpy.
This patch adds mempcpy entry points in memcpy.S files, which
use the memcpy implementation. Now mempcpy itself is also an IFUNC function
as memcpy is and the variants are listed in ifunc-impl-list.c.

The s390 string.h does not define _HAVE_STRING_ARCH_mempcpy.
Instead mempcpy string/string.h inlines memcpy() + n.
If n is constant and small enough, GCC emits instructions like mvi or mvc
and avoids the function call to memcpy.
If n is not constant, then memcpy is called and n is added afterwards.
If _HAVE_STRING_ARCH_mempcpy would be defined, mempcpy would be called in
every case.

According to PR70140 "Inefficient expansion of __builtin_mempcpy"
(https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70140) GCC should handle a
call to mempcpy in the same way as memcpy. Then either the mempcpy macro
in string/string.h has to be removed or _HAVE_STRING_ARCH_mempcpy has to
be defined for S390.

ChangeLog:

	[BZ #19765]
	* sysdeps/s390/mempcpy.S: New File.
	* sysdeps/s390/multiarch/mempcpy.c: Likewise.
	* sysdeps/s390/multiarch/Makefile (sysdep_routines): Add mempcpy.
	* sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list):
	Add mempcpy variants.
	* sysdeps/s390/s390-32/memcpy.S: Add mempcpy entry point.
	(memcpy): Adjust to be usable from mempcpy entry point.
	(__memcpy_mvcle): Likewise.
	* sysdeps/s390/s390-64/memcpy.S: Likewise.
	* sysdeps/s390/s390-32/multiarch/memcpy-s390.S: Add entry points
	____mempcpy_z196, ____mempcpy_z10 and add __GI_ symbols for mempcpy.
	(__memcpy_z196): Adjust to be usable from mempcpy entry point.
	(__memcpy_z10): Likewise.
	* sysdeps/s390/s390-64/multiarch/memcpy-s390x.S: Likewise.

1 files changed, 29 insertions, 2 deletions

diff --git a/sysdeps/s390/s390-32/multiarch/memcpy-s390.S b/sysdeps/s390/s390-32/multiarch/memcpy-s390.S
index 92ffaea5ed..297a8943b1 100644
--- a/sysdeps/s390/s390-32/multiarch/memcpy-s390.S
+++ b/sysdeps/s390/s390-32/multiarch/memcpy-s390.S
@@ -29,14 +29,23 @@
 
 #if defined SHARED && IS_IN (libc)
 
+ENTRY(____mempcpy_z196)
+	.machine "z196"
+	.machinemode "zarch_nohighgprs"
+	lr      %r1,%r2         # Use as dest
+	la      %r2,0(%r4,%r2)  # Return dest + n
+	j	.L_Z196_start
+END(____mempcpy_z196)
+
 ENTRY(__memcpy_z196)
 	.machine "z196"
 	.machinemode "zarch_nohighgprs"
+	lr      %r1,%r2         # r1: Use as dest ; r2: Return dest
+.L_Z196_start:
 	llgfr   %r4,%r4
 	ltgr    %r4,%r4
 	je      .L_Z196_4
 	aghi    %r4,-1
-	lr      %r1,%r2
 	srlg    %r5,%r4,8
 	ltgr    %r5,%r5
 	jne     .L_Z196_5
@@ -60,13 +69,22 @@ ENTRY(__memcpy_z196)
 	mvc     0(1,%r1),0(%r3)
 END(__memcpy_z196)
 
+ENTRY(____mempcpy_z10)
+	.machine "z10"
+	.machinemode "zarch_nohighgprs"
+	lr      %r1,%r2         # Use as dest
+	la      %r2,0(%r4,%r2)  # Return dest + n
+	j	.L_Z10_start
+END(____mempcpy_z10)
+
 ENTRY(__memcpy_z10)
 	.machine "z10"
 	.machinemode "zarch_nohighgprs"
+	lr      %r1,%r2         # r1: Use as dest ; r2: Return dest
+.L_Z10_start:
 	llgfr   %r4,%r4
 	cgije   %r4,0,.L_Z10_4
 	aghi    %r4,-1
-	lr      %r1,%r2
 	srlg    %r5,%r4,8
 	cgijlh  %r5,0,.L_Z10_13
 .L_Z10_3:
@@ -88,14 +106,23 @@ ENTRY(__memcpy_z10)
 	mvc     0(1,%r1),0(%r3)
 END(__memcpy_z10)
 
+# define __mempcpy ____mempcpy_default
 #endif /* SHARED && IS_IN (libc) */
 
+#define memcpy __memcpy_default
 #include "../memcpy.S"
+#undef memcpy
 
 #if defined SHARED && IS_IN (libc)
 .globl   __GI_memcpy
 .set     __GI_memcpy,__memcpy_default
+.globl   __GI_mempcpy
+.set     __GI_mempcpy,____mempcpy_default
+.globl   __GI___mempcpy
+.set     __GI___mempcpy,____mempcpy_default
 #else
 .globl   memcpy
 .set     memcpy,__memcpy_default
+.weak    mempcpy
+.set     mempcpy,__mempcpy
 #endif