glibc/sysdeps/s390/s390-32/memcpy.S
Stefan Liebler 1f16923552 S390: Do not clobber r13 with memcpy on 31bit with copies >1MB.
If the default memcpy variant is called with a length of >1MB on 31bit,
r13 is clobbered as the algorithm is switching to mvcle. The mvcle code
returns without restoring r13. All other cases are restoring r13.

If memcpy is called from outside libc the ifunc resolver will only select
this variant if running on machines older than z10.
Otherwise or if memcpy is called from inside libc, this default memcpy
variant is called.
The testcase timezone/tst-tzset is triggering this issue in some combinations
of gcc versions and optimization levels.

This bug was introduced in commit 04bb21ac93
and thus is a regression compared to former glibc 2.23 release.

This patch removes the usage of r13 at all. Thus it is not saved and restored.
The base address for execute-instruction is now stored in r5 which is obtained
after r5 is not needed anymore as 256byte block counter.

ChangeLog:

	* sysdeps/s390/s390-32/memcpy.S (memcpy): Eliminate the usage
	of r13 as it is not restored in mvcle case.
2016-07-20 08:29:43 +02:00

90 lines
2.6 KiB
ArmAsm

/* memcpy - copy a block from source to destination. S/390 version.
Copyright (C) 2012-2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
#include "sysdep.h"
#include "asm-syntax.h"
/* INPUT PARAMETERS
%r2 = address of destination memory area
%r3 = address of source memory area
%r4 = number of bytes to copy. */
.text
ENTRY(__mempcpy)
.machine "g5"
lr %r1,%r2 # Use as dest
la %r2,0(%r4,%r2) # Return dest + n
j .L_G5_start
END(__mempcpy)
#ifndef USE_MULTIARCH
libc_hidden_def (__mempcpy)
weak_alias (__mempcpy, mempcpy)
libc_hidden_builtin_def (mempcpy)
#endif
ENTRY(memcpy)
.machine "g5"
lr %r1,%r2 # r1: Use as dest ; r2: Return dest
.L_G5_start:
ltr %r4,%r4
je .L_G5_99
ahi %r4,-1
lr %r5,%r4
srl %r5,8
ltr %r5,%r5
jne .L_G5_13
.L_G5_4:
basr %r5,0
.L_G5_16:
ex %r4,.L_G5_17-.L_G5_16(%r5)
.L_G5_99:
br %r14
.L_G5_13:
chi %r5,4096 # Switch to mvcle for copies >1MB
jh __memcpy_mvcle
.L_G5_12:
mvc 0(256,%r1),0(%r3)
la %r1,256(%r1)
la %r3,256(%r3)
brct %r5,.L_G5_12
j .L_G5_4
.L_G5_17:
mvc 0(1,%r1),0(%r3)
END(memcpy)
#ifndef USE_MULTIARCH
libc_hidden_builtin_def (memcpy)
#endif
ENTRY(__memcpy_mvcle)
# Using as standalone function will result in unexpected
# results since the length field is incremented by 1 in order to
# compensate the changes already done in the functions above.
lr %r0,%r2 # backup return dest [ + n ]
ahi %r4,1 # length + 1
lr %r5,%r4 # source length
lr %r4,%r3 # source address
lr %r2,%r1 # destination address
lr %r3,%r5 # destination length = source length
.L_MVCLE_1:
mvcle %r2,%r4,0 # thats it, MVCLE is your friend
jo .L_MVCLE_1
lr %r2,%r0 # return destination address
br %r14
END(__memcpy_mvcle)