From patchwork Fri Mar 15 11:01:55 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jan Beulich X-Patchwork-Id: 10854533 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0FF3B15AC for ; Fri, 15 Mar 2019 11:04:23 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id EBD1928AA8 for ; Fri, 15 Mar 2019 11:04:22 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id DFC6A28B1C; Fri, 15 Mar 2019 11:04:22 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.2 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) (using TLSv1.2 with cipher AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 6E34628AA8 for ; Fri, 15 Mar 2019 11:04:21 +0000 (UTC) Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.89) (envelope-from ) id 1h4kb9-0000oX-4I; Fri, 15 Mar 2019 11:01:59 +0000 Received: from all-amaz-eas1.inumbo.com ([34.197.232.57] helo=us1-amaz-eas2.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.89) (envelope-from ) id 1h4kb7-0000oD-FI for xen-devel@lists.xenproject.org; Fri, 15 Mar 2019 11:01:57 +0000 X-Inumbo-ID: bebc2e36-4711-11e9-8b95-afa5702a057b Received: from prv1-mh.provo.novell.com (unknown [137.65.248.33]) by us1-amaz-eas2.inumbo.com (Halon) with ESMTPS id bebc2e36-4711-11e9-8b95-afa5702a057b; Fri, 15 Mar 2019 11:01:55 +0000 (UTC) Received: from INET-PRV1-MTA by prv1-mh.provo.novell.com with Novell_GroupWise; Fri, 15 Mar 2019 05:01:54 -0600 Message-Id: <5C8B8623020000780021F2B2@prv1-mh.provo.novell.com> X-Mailer: Novell GroupWise Internet Agent 18.1.0 Date: Fri, 15 Mar 2019 05:01:55 -0600 From: "Jan Beulich" To: "xen-devel" References: <5B6BF83602000078001DC548@prv1-mh.provo.novell.com> <5C8B7EC0020000780021F10B@prv1-mh.provo.novell.com> In-Reply-To: <5C8B7EC0020000780021F10B@prv1-mh.provo.novell.com> Mime-Version: 1.0 Content-Disposition: inline Subject: [Xen-devel] [PATCH v8 38/50] x86emul: support of AVX512* population count insns X-BeenThere: xen-devel@lists.xenproject.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Cc: George Dunlap , Andrew Cooper , Wei Liu , Roger Pau Monne Errors-To: xen-devel-bounces@lists.xenproject.org Sender: "Xen-devel" X-Virus-Scanned: ClamAV using ClamSMTP Plus the only other AVX512_BITALG one. As in a few cases before, since the insns here and in particular their memory access patterns follow the usual scheme, I didn't think it was necessary to add a contrived test specifically for them, beyond the Disp8 scaling one. Signed-off-by: Jan Beulich --- v7: Re-base. v6: New. --- a/tools/tests/x86_emulator/evex-disp8.c +++ b/tools/tests/x86_emulator/evex-disp8.c @@ -538,6 +538,11 @@ static const struct test avx512pf_512[] INSNX(scatterpf1q, 66, 0f38, c7, 6, vl, sd, el), }; +static const struct test avx512_bitalg_all[] = { + INSN(popcnt, 66, 0f38, 54, vl, bw, vl), + INSN(pshufbitqmb, 66, 0f38, 8f, vl, b, vl), +}; + static const struct test avx512_vbmi_all[] = { INSN(permb, 66, 0f38, 8d, vl, b, vl), INSN(permi2b, 66, 0f38, 75, vl, b, vl), @@ -550,6 +555,10 @@ static const struct test avx512_vbmi2_al INSN(pexpand, 66, 0f38, 62, vl, bw, el), }; +static const struct test avx512_vpopcntdq_all[] = { + INSN(popcnt, 66, 0f38, 55, vl, dq, vl) +}; + static const unsigned char vl_all[] = { VL_512, VL_128, VL_256 }; static const unsigned char vl_128[] = { VL_128 }; static const unsigned char vl_no128[] = { VL_512, VL_256 }; @@ -919,6 +928,8 @@ void evex_disp8_test(void *instr, struct RUN(avx512er, 512); #define cpu_has_avx512pf cpu_has_avx512f RUN(avx512pf, 512); + RUN(avx512_bitalg, all); RUN(avx512_vbmi, all); RUN(avx512_vbmi2, all); + RUN(avx512_vpopcntdq, all); } --- a/tools/tests/x86_emulator/x86-emulate.h +++ b/tools/tests/x86_emulator/x86-emulate.h @@ -143,6 +143,8 @@ static inline bool xcr0_mask(uint64_t ma #define cpu_has_avx512vl (cp.feat.avx512vl && xcr0_mask(0xe6)) #define cpu_has_avx512_vbmi (cp.feat.avx512_vbmi && xcr0_mask(0xe6)) #define cpu_has_avx512_vbmi2 (cp.feat.avx512_vbmi2 && xcr0_mask(0xe6)) +#define cpu_has_avx512_bitalg (cp.feat.avx512_bitalg && xcr0_mask(0xe6)) +#define cpu_has_avx512_vpopcntdq (cp.feat.avx512_vpopcntdq && xcr0_mask(0xe6)) #define cpu_has_xgetbv1 (cpu_has_xsave && cp.xstate.xgetbv1) --- a/xen/arch/x86/x86_emulate/x86_emulate.c +++ b/xen/arch/x86/x86_emulate/x86_emulate.c @@ -479,6 +479,7 @@ static const struct ext0f38_table { [0x4d] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq }, [0x4e] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl }, [0x4f] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq }, + [0x54 ... 0x55] = { .simd_size = simd_packed_int, .two_op = 1, .d8s = d8s_vl }, [0x58] = { .simd_size = simd_other, .two_op = 1, .d8s = 2 }, [0x59] = { .simd_size = simd_other, .two_op = 1, .d8s = 3 }, [0x5a] = { .simd_size = simd_128, .two_op = 1, .d8s = 4 }, @@ -501,6 +502,7 @@ static const struct ext0f38_table { [0x8c] = { .simd_size = simd_packed_int }, [0x8d] = { .simd_size = simd_packed_int, .d8s = d8s_vl }, [0x8e] = { .simd_size = simd_packed_int, .to_mem = 1 }, + [0x8f] = { .simd_size = simd_packed_int, .d8s = d8s_vl }, [0x90 ... 0x93] = { .simd_size = simd_other, .vsib = 1, .d8s = d8s_dq }, [0x96 ... 0x98] = { .simd_size = simd_packed_fp, .d8s = d8s_vl }, [0x99] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq }, @@ -1915,6 +1917,8 @@ static bool vcpu_has( #define vcpu_has_avx512vl() vcpu_has( 7, EBX, 31, ctxt, ops) #define vcpu_has_avx512_vbmi() vcpu_has( 7, ECX, 1, ctxt, ops) #define vcpu_has_avx512_vbmi2() vcpu_has( 7, ECX, 6, ctxt, ops) +#define vcpu_has_avx512_bitalg() vcpu_has( 7, ECX, 12, ctxt, ops) +#define vcpu_has_avx512_vpopcntdq() vcpu_has( 7, ECX, 14, ctxt, ops) #define vcpu_has_rdpid() vcpu_has( 7, ECX, 22, ctxt, ops) #define vcpu_has_clzero() vcpu_has(0x80000008, EBX, 0, ctxt, ops) @@ -8923,6 +8927,19 @@ x86_emulate( generate_exception_if(vex.l, EXC_UD); goto simd_0f_avx; + case X86EMUL_OPC_EVEX_66(0x0f38, 0x8f): /* vpshufbitqmb [xyz]mm/mem,[xyz]mm,k{k} */ + generate_exception_if(evex.w || !evex.r || !evex.R || evex.z, EXC_UD); + /* fall through */ + case X86EMUL_OPC_EVEX_66(0x0f38, 0x54): /* vpopcnt{b,w} [xyz]mm/mem,[xyz]mm{k} */ + host_and_vcpu_must_have(avx512_bitalg); + generate_exception_if(evex.brs, EXC_UD); + elem_bytes = 1 << evex.w; + goto avx512f_no_sae; + + case X86EMUL_OPC_EVEX_66(0x0f38, 0x55): /* vpopcnt{d,q} [xyz]mm/mem,[xyz]mm{k} */ + host_and_vcpu_must_have(avx512_vpopcntdq); + goto avx512f_no_sae; + case X86EMUL_OPC_VEX_66(0x0f38, 0x58): /* vpbroadcastd xmm/m32,{x,y}mm */ case X86EMUL_OPC_VEX_66(0x0f38, 0x59): /* vpbroadcastq xmm/m64,{x,y}mm */ case X86EMUL_OPC_VEX_66(0x0f38, 0x78): /* vpbroadcastb xmm/m8,{x,y}mm */ --- a/xen/include/asm-x86/cpufeature.h +++ b/xen/include/asm-x86/cpufeature.h @@ -111,6 +111,8 @@ /* CPUID level 0x00000007:0.ecx */ #define cpu_has_avx512_vbmi boot_cpu_has(X86_FEATURE_AVX512_VBMI) #define cpu_has_avx512_vbmi2 boot_cpu_has(X86_FEATURE_AVX512_VBMI2) +#define cpu_has_avx512_bitalg boot_cpu_has(X86_FEATURE_AVX512_BITALG) +#define cpu_has_avx512_vpopcntdq boot_cpu_has(X86_FEATURE_AVX512_VPOPCNTDQ) #define cpu_has_rdpid boot_cpu_has(X86_FEATURE_RDPID) /* CPUID level 0x80000007.edx */ --- a/xen/include/public/arch-x86/cpufeatureset.h +++ b/xen/include/public/arch-x86/cpufeatureset.h @@ -229,6 +229,7 @@ XEN_CPUFEATURE(UMIP, 6*32+ 2) / XEN_CPUFEATURE(PKU, 6*32+ 3) /*H Protection Keys for Userspace */ XEN_CPUFEATURE(OSPKE, 6*32+ 4) /*! OS Protection Keys Enable */ XEN_CPUFEATURE(AVX512_VBMI2, 6*32+ 6) /*A Additional AVX-512 Vector Byte Manipulation Instrs */ +XEN_CPUFEATURE(AVX512_BITALG, 6*32+12) /*A Support for VPOPCNT[B,W] and VPSHUFBITQMB */ XEN_CPUFEATURE(AVX512_VPOPCNTDQ, 6*32+14) /*A POPCNT for vectors of DW/QW */ XEN_CPUFEATURE(RDPID, 6*32+22) /*A RDPID instruction */ --- a/xen/tools/gen-cpuid.py +++ b/xen/tools/gen-cpuid.py @@ -269,7 +269,7 @@ def crunch_numbers(state): # AVX512 extensions acting (solely) on vectors of bytes/words are made # dependents of AVX512BW (as to requiring wider than 16-bit mask # registers), despite the SDM not formally making this connection. - AVX512BW: [AVX512_VBMI, AVX512_VBMI2], + AVX512BW: [AVX512_VBMI, AVX512_BITALG, AVX512_VBMI2], # The features: # * Single Thread Indirect Branch Predictors