From patchwork Fri Sep 23 06:18:14 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Cyril Bur X-Patchwork-Id: 673832 Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from lists.ozlabs.org (lists.ozlabs.org [103.22.144.68]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3sgNWc5wmjz9stY for ; Fri, 23 Sep 2016 16:20:12 +1000 (AEST) Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) by lists.ozlabs.org (Postfix) with ESMTP id 3sgNWc4yJWzDsqS for ; Fri, 23 Sep 2016 16:20:12 +1000 (AEST) X-Original-To: linuxppc-dev@lists.ozlabs.org Delivered-To: linuxppc-dev@lists.ozlabs.org Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3sgNV810RVzDsmY for ; Fri, 23 Sep 2016 16:18:55 +1000 (AEST) Received: from pps.filterd (m0098410.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.17/8.16.0.17) with SMTP id u8N6HdPO052295 for ; Fri, 23 Sep 2016 02:18:53 -0400 Received: from e23smtp09.au.ibm.com (e23smtp09.au.ibm.com [202.81.31.142]) by mx0a-001b2d01.pphosted.com with ESMTP id 25mqb81d8q-1 (version=TLSv1.2 cipher=AES256-SHA bits=256 verify=NOT) for ; Fri, 23 Sep 2016 02:18:53 -0400 Received: from localhost by e23smtp09.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 23 Sep 2016 16:18:51 +1000 Received: from d23dlp01.au.ibm.com (202.81.31.203) by e23smtp09.au.ibm.com (202.81.31.206) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Fri, 23 Sep 2016 16:18:49 +1000 Received: from d23relay09.au.ibm.com (d23relay09.au.ibm.com [9.185.63.181]) by d23dlp01.au.ibm.com (Postfix) with ESMTP id 650C72CE805C for ; Fri, 23 Sep 2016 16:18:48 +1000 (EST) Received: from d23av02.au.ibm.com (d23av02.au.ibm.com [9.190.235.138]) by d23relay09.au.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id u8N6ImBo47710348 for ; Fri, 23 Sep 2016 16:18:48 +1000 Received: from d23av02.au.ibm.com (localhost [127.0.0.1]) by d23av02.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id u8N6ImGi031299 for ; Fri, 23 Sep 2016 16:18:48 +1000 Received: from ozlabs.au.ibm.com (ozlabs.au.ibm.com [9.192.253.14]) by d23av02.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVin) with ESMTP id u8N6IlRR031287; Fri, 23 Sep 2016 16:18:48 +1000 Received: from camb691.ozlabs.ibm.com (haven.au.ibm.com [9.192.254.114]) (using TLSv1.2 with cipher DHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ozlabs.au.ibm.com (Postfix) with ESMTPSA id D8E85A024A; Fri, 23 Sep 2016 16:18:47 +1000 (AEST) From: Cyril Bur To: mpe@ellerman.id.au, linuxppc-dev@lists.ozlabs.org Subject: [PATCH v5 08/20] selftests/powerpc: Rework FPU stack placement macros and move to header file Date: Fri, 23 Sep 2016 16:18:14 +1000 X-Mailer: git-send-email 2.10.0 In-Reply-To: <20160923061826.30790-1-cyrilbur@gmail.com> References: <20160923061826.30790-1-cyrilbur@gmail.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 16092306-0052-0000-0000-000001D1D926 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 16092306-0053-0000-0000-000006DBC2F6 Message-Id: <20160923061826.30790-9-cyrilbur@gmail.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:, , definitions=2016-09-23_02:, , signatures=0 X-Proofpoint-Spam-Details: rule=outbound_spam_definite policy=outbound score=100 spamscore=100 suspectscore=0 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1609020000 definitions=main-1609230114 X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org Sender: "Linuxppc-dev" The FPU regs are placed at the top of the stack frame. Currently the position expected to be passed to the macro. The macros now should be passed the stack frame size and from there they can calculate where to put the regs, this makes the use simpler. Also move them to a header file to be used in an different area of the powerpc selftests Signed-off-by: Cyril Bur --- tools/testing/selftests/powerpc/fpu_asm.h | 81 ++++++++++++++++++++++++++ tools/testing/selftests/powerpc/math/fpu_asm.S | 73 ++--------------------- 2 files changed, 86 insertions(+), 68 deletions(-) create mode 100644 tools/testing/selftests/powerpc/fpu_asm.h diff --git a/tools/testing/selftests/powerpc/fpu_asm.h b/tools/testing/selftests/powerpc/fpu_asm.h new file mode 100644 index 0000000..24061b8 --- /dev/null +++ b/tools/testing/selftests/powerpc/fpu_asm.h @@ -0,0 +1,81 @@ +/* + * Copyright 2016, Cyril Bur, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _SELFTESTS_POWERPC_FPU_ASM_H +#define _SELFTESTS_POWERPC_FPU_ASM_H +#include "basic_asm.h" + +#define PUSH_FPU(stack_size) \ + stfd f31,(stack_size + STACK_FRAME_MIN_SIZE)(%r1); \ + stfd f30,(stack_size + STACK_FRAME_MIN_SIZE - 8)(%r1); \ + stfd f29,(stack_size + STACK_FRAME_MIN_SIZE - 16)(%r1); \ + stfd f28,(stack_size + STACK_FRAME_MIN_SIZE - 24)(%r1); \ + stfd f27,(stack_size + STACK_FRAME_MIN_SIZE - 32)(%r1); \ + stfd f26,(stack_size + STACK_FRAME_MIN_SIZE - 40)(%r1); \ + stfd f25,(stack_size + STACK_FRAME_MIN_SIZE - 48)(%r1); \ + stfd f24,(stack_size + STACK_FRAME_MIN_SIZE - 56)(%r1); \ + stfd f23,(stack_size + STACK_FRAME_MIN_SIZE - 64)(%r1); \ + stfd f22,(stack_size + STACK_FRAME_MIN_SIZE - 72)(%r1); \ + stfd f21,(stack_size + STACK_FRAME_MIN_SIZE - 80)(%r1); \ + stfd f20,(stack_size + STACK_FRAME_MIN_SIZE - 88)(%r1); \ + stfd f19,(stack_size + STACK_FRAME_MIN_SIZE - 96)(%r1); \ + stfd f18,(stack_size + STACK_FRAME_MIN_SIZE - 104)(%r1); \ + stfd f17,(stack_size + STACK_FRAME_MIN_SIZE - 112)(%r1); \ + stfd f16,(stack_size + STACK_FRAME_MIN_SIZE - 120)(%r1); \ + stfd f15,(stack_size + STACK_FRAME_MIN_SIZE - 128)(%r1); \ + stfd f14,(stack_size + STACK_FRAME_MIN_SIZE - 136)(%r1); + +#define POP_FPU(stack_size) \ + lfd f31,(stack_size + STACK_FRAME_MIN_SIZE)(%r1); \ + lfd f30,(stack_size + STACK_FRAME_MIN_SIZE - 8)(%r1); \ + lfd f29,(stack_size + STACK_FRAME_MIN_SIZE - 16)(%r1); \ + lfd f28,(stack_size + STACK_FRAME_MIN_SIZE - 24)(%r1); \ + lfd f27,(stack_size + STACK_FRAME_MIN_SIZE - 32)(%r1); \ + lfd f26,(stack_size + STACK_FRAME_MIN_SIZE - 40)(%r1); \ + lfd f25,(stack_size + STACK_FRAME_MIN_SIZE - 48)(%r1); \ + lfd f24,(stack_size + STACK_FRAME_MIN_SIZE - 56)(%r1); \ + lfd f23,(stack_size + STACK_FRAME_MIN_SIZE - 64)(%r1); \ + lfd f22,(stack_size + STACK_FRAME_MIN_SIZE - 72)(%r1); \ + lfd f21,(stack_size + STACK_FRAME_MIN_SIZE - 80)(%r1); \ + lfd f20,(stack_size + STACK_FRAME_MIN_SIZE - 88)(%r1); \ + lfd f19,(stack_size + STACK_FRAME_MIN_SIZE - 96)(%r1); \ + lfd f18,(stack_size + STACK_FRAME_MIN_SIZE - 104)(%r1); \ + lfd f17,(stack_size + STACK_FRAME_MIN_SIZE - 112)(%r1); \ + lfd f16,(stack_size + STACK_FRAME_MIN_SIZE - 120)(%r1); \ + lfd f15,(stack_size + STACK_FRAME_MIN_SIZE - 128)(%r1); \ + lfd f14,(stack_size + STACK_FRAME_MIN_SIZE - 136)(%r1); + +/* + * Careful calling this, it will 'clobber' fpu (by design) + * Don't call this from C + */ +FUNC_START(load_fpu) + lfd f14,0(r3) + lfd f15,8(r3) + lfd f16,16(r3) + lfd f17,24(r3) + lfd f18,32(r3) + lfd f19,40(r3) + lfd f20,48(r3) + lfd f21,56(r3) + lfd f22,64(r3) + lfd f23,72(r3) + lfd f24,80(r3) + lfd f25,88(r3) + lfd f26,96(r3) + lfd f27,104(r3) + lfd f28,112(r3) + lfd f29,120(r3) + lfd f30,128(r3) + lfd f31,136(r3) + blr +FUNC_END(load_fpu) + +#endif /* _SELFTESTS_POWERPC_FPU_ASM_H */ + diff --git a/tools/testing/selftests/powerpc/math/fpu_asm.S b/tools/testing/selftests/powerpc/math/fpu_asm.S index f3711d8..241f067 100644 --- a/tools/testing/selftests/powerpc/math/fpu_asm.S +++ b/tools/testing/selftests/powerpc/math/fpu_asm.S @@ -8,70 +8,7 @@ */ #include "../basic_asm.h" - -#define PUSH_FPU(pos) \ - stfd f14,pos(sp); \ - stfd f15,pos+8(sp); \ - stfd f16,pos+16(sp); \ - stfd f17,pos+24(sp); \ - stfd f18,pos+32(sp); \ - stfd f19,pos+40(sp); \ - stfd f20,pos+48(sp); \ - stfd f21,pos+56(sp); \ - stfd f22,pos+64(sp); \ - stfd f23,pos+72(sp); \ - stfd f24,pos+80(sp); \ - stfd f25,pos+88(sp); \ - stfd f26,pos+96(sp); \ - stfd f27,pos+104(sp); \ - stfd f28,pos+112(sp); \ - stfd f29,pos+120(sp); \ - stfd f30,pos+128(sp); \ - stfd f31,pos+136(sp); - -#define POP_FPU(pos) \ - lfd f14,pos(sp); \ - lfd f15,pos+8(sp); \ - lfd f16,pos+16(sp); \ - lfd f17,pos+24(sp); \ - lfd f18,pos+32(sp); \ - lfd f19,pos+40(sp); \ - lfd f20,pos+48(sp); \ - lfd f21,pos+56(sp); \ - lfd f22,pos+64(sp); \ - lfd f23,pos+72(sp); \ - lfd f24,pos+80(sp); \ - lfd f25,pos+88(sp); \ - lfd f26,pos+96(sp); \ - lfd f27,pos+104(sp); \ - lfd f28,pos+112(sp); \ - lfd f29,pos+120(sp); \ - lfd f30,pos+128(sp); \ - lfd f31,pos+136(sp); - -# Careful calling this, it will 'clobber' fpu (by design) -# Don't call this from C -FUNC_START(load_fpu) - lfd f14,0(r3) - lfd f15,8(r3) - lfd f16,16(r3) - lfd f17,24(r3) - lfd f18,32(r3) - lfd f19,40(r3) - lfd f20,48(r3) - lfd f21,56(r3) - lfd f22,64(r3) - lfd f23,72(r3) - lfd f24,80(r3) - lfd f25,88(r3) - lfd f26,96(r3) - lfd f27,104(r3) - lfd f28,112(r3) - lfd f29,120(r3) - lfd f30,128(r3) - lfd f31,136(r3) - blr -FUNC_END(load_fpu) +#include "../fpu_asm.h" FUNC_START(check_fpu) mr r4,r3 @@ -138,9 +75,9 @@ FUNC_START(test_fpu) # r4 holds pointer to the pid # f14-f31 are non volatiles PUSH_BASIC_STACK(256) + PUSH_FPU(256) std r3,STACK_FRAME_PARAM(0)(sp) # Address of darray std r4,STACK_FRAME_PARAM(1)(sp) # Address of pid - PUSH_FPU(STACK_FRAME_LOCAL(2,0)) bl load_fpu nop @@ -155,7 +92,7 @@ FUNC_START(test_fpu) bl check_fpu nop - POP_FPU(STACK_FRAME_LOCAL(2,0)) + POP_FPU(256) POP_BASIC_STACK(256) blr FUNC_END(test_fpu) @@ -166,10 +103,10 @@ FUNC_END(test_fpu) # registers while running is not zero. FUNC_START(preempt_fpu) PUSH_BASIC_STACK(256) + PUSH_FPU(256) std r3,STACK_FRAME_PARAM(0)(sp) # double *darray std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting std r5,STACK_FRAME_PARAM(2)(sp) # int *running - PUSH_FPU(STACK_FRAME_LOCAL(3,0)) bl load_fpu nop @@ -192,7 +129,7 @@ FUNC_START(preempt_fpu) cmpwi r5,0 bne 2b -3: POP_FPU(STACK_FRAME_LOCAL(3,0)) +3: POP_FPU(256) POP_BASIC_STACK(256) blr FUNC_END(preempt_fpu)