From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) by sourceware.org (Postfix) with ESMTPS id 6A5093858024 for ; Fri, 26 Mar 2021 10:07:45 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.3.2 sourceware.org 6A5093858024 Received: from pps.filterd (m0098394.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 12QA3W40088396 for ; Fri, 26 Mar 2021 06:07:44 -0400 Received: from ppma06ams.nl.ibm.com (66.31.33a9.ip4.static.sl-reverse.com [169.51.49.102]) by mx0a-001b2d01.pphosted.com with ESMTP id 37hcc3t3rr-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT) for ; Fri, 26 Mar 2021 06:07:44 -0400 Received: from pps.filterd (ppma06ams.nl.ibm.com [127.0.0.1]) by ppma06ams.nl.ibm.com (8.16.0.43/8.16.0.43) with SMTP id 12QA7f0F006333 for ; Fri, 26 Mar 2021 10:07:41 GMT Received: from b06cxnps4076.portsmouth.uk.ibm.com (d06relay13.portsmouth.uk.ibm.com [9.149.109.198]) by ppma06ams.nl.ibm.com with ESMTP id 37h1510he0-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT) for ; Fri, 26 Mar 2021 10:07:41 +0000 Received: from d06av23.portsmouth.uk.ibm.com (d06av23.portsmouth.uk.ibm.com [9.149.105.59]) by b06cxnps4076.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 12QA7dZr37552550 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 26 Mar 2021 10:07:39 GMT Received: from d06av23.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 1330FA4051; Fri, 26 Mar 2021 10:07:39 +0000 (GMT) Received: from d06av23.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id DCA4CA4040; Fri, 26 Mar 2021 10:07:38 +0000 (GMT) Received: from li-ab9d22cc-354d-11b2-a85c-e984af76f811.ibm.com (unknown [9.171.2.19]) by d06av23.portsmouth.uk.ibm.com (Postfix) with ESMTP; Fri, 26 Mar 2021 10:07:38 +0000 (GMT) Subject: Re: [PATCH] S390: Also check vector support in memmove ifunc-selector [BZ #27511] To: GNU C Library References: <20210323162926.869418-1-stli@linux.ibm.com> Cc: Stefan Liebler From: Stefan Liebler Message-ID: <17e2e772-9376-0b73-6d94-1e8e13f64c4b@linux.ibm.com> Date: Fri, 26 Mar 2021 11:07:38 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.8.1 MIME-Version: 1.0 In-Reply-To: <20210323162926.869418-1-stli@linux.ibm.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit X-TM-AS-GCONF: 00 X-Proofpoint-GUID: hIXxS6tOPyyTmgyTrajl15p-3GQrk2dh X-Proofpoint-ORIG-GUID: hIXxS6tOPyyTmgyTrajl15p-3GQrk2dh X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.369, 18.0.761 definitions=2021-03-26_03:2021-03-26, 2021-03-26 signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 mlxscore=0 mlxlogscore=999 bulkscore=0 adultscore=0 clxscore=1015 lowpriorityscore=0 malwarescore=0 phishscore=0 spamscore=0 suspectscore=0 impostorscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2103250000 definitions=main-2103260073 X-Spam-Status: No, score=-11.7 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_EF, GIT_PATCH_0, NICE_REPLY_A, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H3, RCVD_IN_MSPIKE_WL, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.2 X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 26 Mar 2021 10:07:49 -0000 On 23/03/2021 17:29, Stefan Liebler wrote: > The arch13 memmove variant is currently selected by the ifunc selector > if the Miscellaneous-Instruction-Extensions Facility 3 facility bit > is present, but the function is also using vector instructions. > If the vector support is not present, one is receiving an operation > exception. > > Therefore this patch also checks for vector support in the ifunc > selector and in ifunc-impl-list.c. > > Just to be sure, the configure check is now also testing an arch13 > vector instruction and an arch13 Miscellaneous-Instruction-Extensions > Facility 3 instruction. > --- > sysdeps/s390/configure | 8 ++++++-- > sysdeps/s390/configure.ac | 8 ++++++-- > sysdeps/s390/memmove.c | 2 +- > sysdeps/s390/multiarch/ifunc-impl-list.c | 3 ++- > 4 files changed, 15 insertions(+), 6 deletions(-) > > diff --git a/sysdeps/s390/configure b/sysdeps/s390/configure > index 5f98640d0f..7eaefbabcf 100644 > --- a/sysdeps/s390/configure > +++ b/sysdeps/s390/configure > @@ -123,7 +123,9 @@ void testinsn (char *buf) > __asm__ (".machine \"arch13\" \n\t" > ".machinemode \"zarch_nohighgprs\" \n\t" > "lghi %%r0,16 \n\t" > - "mvcrl 0(%0),32(%0)" : : "a" (buf) : "memory", "r0"); > + "mvcrl 0(%0),32(%0) \n\t" > + "vstrs %%v20,%%v20,%%v20,%%v20,0,2" > + : : "a" (buf) : "memory", "r0"); > } > EOF > if { ac_try='${CC-cc} $CFLAGS $CPPFLAGS $LDFLAGS --shared conftest.c > @@ -271,7 +273,9 @@ else > void testinsn (char *buf) > { > __asm__ ("lghi %%r0,16 \n\t" > - "mvcrl 0(%0),32(%0)" : : "a" (buf) : "memory", "r0"); > + "mvcrl 0(%0),32(%0) \n\t" > + "vstrs %%v20,%%v20,%%v20,%%v20,0,2" > + : : "a" (buf) : "memory", "r0"); > } > EOF > if { ac_try='${CC-cc} $CFLAGS $CPPFLAGS $LDFLAGS --shared conftest.c > diff --git a/sysdeps/s390/configure.ac b/sysdeps/s390/configure.ac > index dfe007a774..e6df624919 100644 > --- a/sysdeps/s390/configure.ac > +++ b/sysdeps/s390/configure.ac > @@ -88,7 +88,9 @@ void testinsn (char *buf) > __asm__ (".machine \"arch13\" \n\t" > ".machinemode \"zarch_nohighgprs\" \n\t" > "lghi %%r0,16 \n\t" > - "mvcrl 0(%0),32(%0)" : : "a" (buf) : "memory", "r0"); > + "mvcrl 0(%0),32(%0) \n\t" > + "vstrs %%v20,%%v20,%%v20,%%v20,0,2" > + : : "a" (buf) : "memory", "r0"); > } > EOF > dnl test, if assembler supports S390 arch13 instructions > @@ -195,7 +197,9 @@ cat > conftest.c <<\EOF > void testinsn (char *buf) > { > __asm__ ("lghi %%r0,16 \n\t" > - "mvcrl 0(%0),32(%0)" : : "a" (buf) : "memory", "r0"); > + "mvcrl 0(%0),32(%0) \n\t" > + "vstrs %%v20,%%v20,%%v20,%%v20,0,2" > + : : "a" (buf) : "memory", "r0"); > } > EOF > dnl test, if assembler supports S390 arch13 zarch instructions as default > diff --git a/sysdeps/s390/memmove.c b/sysdeps/s390/memmove.c > index f88ea79d97..1a7d3369f2 100644 > --- a/sysdeps/s390/memmove.c > +++ b/sysdeps/s390/memmove.c > @@ -43,7 +43,7 @@ extern __typeof (__redirect_memmove) MEMMOVE_ARCH13 attribute_hidden; > s390_libc_ifunc_expr (__redirect_memmove, memmove, > ({ > s390_libc_ifunc_expr_stfle_init (); > - (HAVE_MEMMOVE_ARCH13 > + (HAVE_MEMMOVE_ARCH13 && (hwcap & HWCAP_S390_VXRS_EXT2) > && S390_IS_ARCH13_MIE3 (stfle_bits)) > ? MEMMOVE_ARCH13 > : (HAVE_MEMMOVE_Z13 && (hwcap & HWCAP_S390_VX)) > diff --git a/sysdeps/s390/multiarch/ifunc-impl-list.c b/sysdeps/s390/multiarch/ifunc-impl-list.c > index 4b170e4459..2ef38b72dd 100644 > --- a/sysdeps/s390/multiarch/ifunc-impl-list.c > +++ b/sysdeps/s390/multiarch/ifunc-impl-list.c > @@ -171,7 +171,8 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, > IFUNC_IMPL (i, name, memmove, > # if HAVE_MEMMOVE_ARCH13 > IFUNC_IMPL_ADD (array, i, memmove, > - S390_IS_ARCH13_MIE3 (stfle_bits), > + ((dl_hwcap & HWCAP_S390_VXRS_EXT2) > + && S390_IS_ARCH13_MIE3 (stfle_bits)), > MEMMOVE_ARCH13) > # endif > # if HAVE_MEMMOVE_Z13 > I've just committed this patch after testing by booting with "novx" kernel parameter which disables all vector related HWCAPs and the enabling the vector part in the kernel. Thanks, Stefan