From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673447946518661.9780694931094; Wed, 11 Jan 2023 06:39:06 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475455.737184 (Exim 4.92) (envelope-from ) id 1pFcFX-0001WW-Tg; Wed, 11 Jan 2023 14:38:43 +0000 Received: by outflank-mailman (output) from mailman id 475455.737184; Wed, 11 Jan 2023 14:38:43 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFX-0001UQ-N2; Wed, 11 Jan 2023 14:38:43 +0000 Received: by outflank-mailman (input) for mailman id 475455; Wed, 11 Jan 2023 14:38:42 +0000 Received: from se1-gles-flk1-in.inumbo.com ([94.247.172.50] helo=se1-gles-flk1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFW-0001NK-Dl for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:42 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-flk1.inumbo.com (Halon) with ESMTP id a38f1210-91bd-11ed-b8d0-410ff93cb8f0; Wed, 11 Jan 2023 15:38:40 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 618DA13D5; Wed, 11 Jan 2023 06:39:21 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 5539A3F71A; Wed, 11 Jan 2023 06:38:38 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a38f1210-91bd-11ed-b8d0-410ff93cb8f0 From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 1/8] xen/arm: enable SVE extension for Xen Date: Wed, 11 Jan 2023 14:38:19 +0000 Message-Id: <20230111143826.3224-2-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673447947514100002 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Enable Xen to handle the SVE extension, add code in cpufeature module to handle ZCR SVE register, disable trapping SVE feature on system boot, it will be restored later on vcpu creation and running. While there, correct coding style for the comment on coprocessor trapping. Change the KConfig entry to make ARM64_SVE symbol selectable, by default it will be not selected. Create sve module and sve_asm.S that contains assembly routines for the SVE feature, this code is inspired from linux and it uses instruction encoding to be compatible with compilers that does not support SVE. Signed-off-by: Luca Fancellu --- xen/arch/arm/Kconfig | 3 +- xen/arch/arm/arm64/Makefile | 1 + xen/arch/arm/arm64/cpufeature.c | 7 ++-- xen/arch/arm/arm64/sve.c | 38 +++++++++++++++++++ xen/arch/arm/arm64/sve_asm.S | 48 ++++++++++++++++++++++++ xen/arch/arm/cpufeature.c | 6 ++- xen/arch/arm/domain.c | 4 ++ xen/arch/arm/include/asm/arm64/sve.h | 43 +++++++++++++++++++++ xen/arch/arm/include/asm/arm64/sysregs.h | 1 + xen/arch/arm/include/asm/cpufeature.h | 14 +++++++ xen/arch/arm/include/asm/domain.h | 1 + xen/arch/arm/include/asm/processor.h | 2 + xen/arch/arm/setup.c | 5 ++- xen/arch/arm/traps.c | 34 ++++++++++++----- 14 files changed, 188 insertions(+), 19 deletions(-) create mode 100644 xen/arch/arm/arm64/sve.c create mode 100644 xen/arch/arm/arm64/sve_asm.S create mode 100644 xen/arch/arm/include/asm/arm64/sve.h diff --git a/xen/arch/arm/Kconfig b/xen/arch/arm/Kconfig index 239d3aed3c7f..2a5151f3c718 100644 --- a/xen/arch/arm/Kconfig +++ b/xen/arch/arm/Kconfig @@ -112,11 +112,10 @@ config ARM64_PTR_AUTH This feature is not supported in Xen. =20 config ARM64_SVE - def_bool n + bool "Enable Scalar Vector Extension support" if EXPERT depends on ARM_64 help Scalar Vector Extension support. - This feature is not supported in Xen. =20 config ARM64_MTE def_bool n diff --git a/xen/arch/arm/arm64/Makefile b/xen/arch/arm/arm64/Makefile index 6d507da0d44d..1d59c3b0ec89 100644 --- a/xen/arch/arm/arm64/Makefile +++ b/xen/arch/arm/arm64/Makefile @@ -12,6 +12,7 @@ obj-y +=3D insn.o obj-$(CONFIG_LIVEPATCH) +=3D livepatch.o obj-y +=3D smc.o obj-y +=3D smpboot.o +obj-$(CONFIG_ARM64_SVE) +=3D sve.o sve_asm.o obj-y +=3D traps.o obj-y +=3D vfp.o obj-y +=3D vsysreg.o diff --git a/xen/arch/arm/arm64/cpufeature.c b/xen/arch/arm/arm64/cpufeatur= e.c index d9039d37b2d1..b4656ff4d80f 100644 --- a/xen/arch/arm/arm64/cpufeature.c +++ b/xen/arch/arm/arm64/cpufeature.c @@ -455,15 +455,11 @@ static const struct arm64_ftr_bits ftr_id_dfr1[] =3D { ARM64_FTR_END, }; =20 -#if 0 -/* TODO: use this to sanitize SVE once we support it */ - static const struct arm64_ftr_bits ftr_zcr[] =3D { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0), /* LEN */ ARM64_FTR_END, }; -#endif =20 /* * Common ftr bits for a 32bit register with all hidden, strict @@ -603,6 +599,9 @@ void update_system_features(const struct cpuinfo_arm *n= ew) =20 SANITIZE_ID_REG(zfr64, 0, aa64zfr0); =20 + if ( cpu_has_sve ) + SANITIZE_REG(zcr64, 0, zcr); + /* * Comment from Linux: * Userspace may perform DC ZVA instructions. Mismatched block sizes diff --git a/xen/arch/arm/arm64/sve.c b/xen/arch/arm/arm64/sve.c new file mode 100644 index 000000000000..326389278292 --- /dev/null +++ b/xen/arch/arm/arm64/sve.c @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Arm SVE feature code + * + * Copyright (C) 2022 ARM Ltd. + */ + +#include +#include +#include + +extern unsigned int sve_get_hw_vl(void); + +register_t compute_max_zcr(void) +{ + register_t zcr =3D vl_to_zcr(SVE_VL_MAX_BITS); + unsigned int hw_vl; + + /* + * Set the maximum SVE vector length, doing that we will know the VL + * supported by the platform, calling sve_get_hw_vl() + */ + WRITE_SYSREG(zcr, ZCR_EL2); + + /* + * Read the maximum VL, which could be lower than what we imposed befo= re, + * hw_vl contains VL in bytes, multiply it by 8 to use vl_to_zcr() lat= er + */ + hw_vl =3D sve_get_hw_vl() * 8U; + + return vl_to_zcr(hw_vl); +} + +/* Takes a vector length in bits and returns the ZCR_ELx encoding */ +register_t vl_to_zcr(uint16_t vl) +{ + return ((vl / SVE_VL_MULTIPLE_VAL) - 1U) & ZCR_ELx_LEN_MASK; +} diff --git a/xen/arch/arm/arm64/sve_asm.S b/xen/arch/arm/arm64/sve_asm.S new file mode 100644 index 000000000000..4d1549344733 --- /dev/null +++ b/xen/arch/arm/arm64/sve_asm.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Arm SVE assembly routines + * + * Copyright (C) 2022 ARM Ltd. + * + * Some macros and instruction encoding in this file are taken from linux = 6.1.1, + * file arch/arm64/include/asm/fpsimdmacros.h, some of them are a modified + * version. + */ + +/* Sanity-check macros to help avoid encoding garbage instructions */ + +.macro _check_general_reg nr + .if (\nr) < 0 || (\nr) > 30 + .error "Bad register number \nr." + .endif +.endm + +.macro _check_num n, min, max + .if (\n) < (\min) || (\n) > (\max) + .error "Number \n out of range [\min,\max]" + .endif +.endm + +/* SVE instruction encodings for non-SVE-capable assemblers */ +/* (pre binutils 2.28, all kernel capable clang versions support SVE) */ + +/* RDVL X\nx, #\imm */ +.macro _sve_rdvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5000 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* Gets the current vector register size in bytes */ +GLOBAL(sve_get_hw_vl) + _sve_rdvl 0, 1 + ret + +/* + * Local variables: + * mode: ASM + * indent-tabs-mode: nil + * End: + */ diff --git a/xen/arch/arm/cpufeature.c b/xen/arch/arm/cpufeature.c index c4ec38bb2554..83b84368f6d5 100644 --- a/xen/arch/arm/cpufeature.c +++ b/xen/arch/arm/cpufeature.c @@ -9,6 +9,7 @@ #include #include #include +#include #include =20 DECLARE_BITMAP(cpu_hwcaps, ARM_NCAPS); @@ -143,6 +144,9 @@ void identify_cpu(struct cpuinfo_arm *c) =20 c->zfr64.bits[0] =3D READ_SYSREG(ID_AA64ZFR0_EL1); =20 + if ( cpu_has_sve ) + c->zcr64.bits[0] =3D compute_max_zcr(); + c->dczid.bits[0] =3D READ_SYSREG(DCZID_EL0); =20 c->ctr.bits[0] =3D READ_SYSREG(CTR_EL0); @@ -199,7 +203,7 @@ static int __init create_guest_cpuinfo(void) guest_cpuinfo.pfr64.mpam =3D 0; guest_cpuinfo.pfr64.mpam_frac =3D 0; =20 - /* Hide SVE as Xen does not support it */ + /* Hide SVE by default to the guests */ guest_cpuinfo.pfr64.sve =3D 0; guest_cpuinfo.zfr64.bits[0] =3D 0; =20 diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c index 99577adb6c69..8ea3843ea8e8 100644 --- a/xen/arch/arm/domain.c +++ b/xen/arch/arm/domain.c @@ -181,6 +181,8 @@ static void ctxt_switch_to(struct vcpu *n) /* VGIC */ gic_restore_state(n); =20 + WRITE_SYSREG(n->arch.cptr_el2, CPTR_EL2); + /* VFP */ vfp_restore_state(n); =20 @@ -548,6 +550,8 @@ int arch_vcpu_create(struct vcpu *v) =20 v->arch.vmpidr =3D MPIDR_SMP | vcpuid_to_vaffinity(v->vcpu_id); =20 + v->arch.cptr_el2 =3D get_default_cptr_flags(); + v->arch.hcr_el2 =3D get_default_hcr_flags(); =20 v->arch.mdcr_el2 =3D HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; diff --git a/xen/arch/arm/include/asm/arm64/sve.h b/xen/arch/arm/include/as= m/arm64/sve.h new file mode 100644 index 000000000000..bd56e2f24230 --- /dev/null +++ b/xen/arch/arm/include/asm/arm64/sve.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Arm SVE feature code + * + * Copyright (C) 2022 ARM Ltd. + */ + +#ifndef _ARM_ARM64_SVE_H +#define _ARM_ARM64_SVE_H + +#define SVE_VL_MAX_BITS (2048U) + +/* Vector length must be multiple of 128 */ +#define SVE_VL_MULTIPLE_VAL (128U) + +#ifdef CONFIG_ARM64_SVE + +register_t compute_max_zcr(void); +register_t vl_to_zcr(uint16_t vl); + +#else /* !CONFIG_ARM64_SVE */ + +static inline register_t compute_max_zcr(void) +{ + return 0; +} + +static inline register_t vl_to_zcr(uint16_t vl) +{ + return 0; +} + +#endif + +#endif /* _ARM_ARM64_SVE_H */ +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/xen/arch/arm/include/asm/arm64/sysregs.h b/xen/arch/arm/includ= e/asm/arm64/sysregs.h index 463899951414..4cabb9eb4d5e 100644 --- a/xen/arch/arm/include/asm/arm64/sysregs.h +++ b/xen/arch/arm/include/asm/arm64/sysregs.h @@ -24,6 +24,7 @@ #define ICH_EISR_EL2 S3_4_C12_C11_3 #define ICH_ELSR_EL2 S3_4_C12_C11_5 #define ICH_VMCR_EL2 S3_4_C12_C11_7 +#define ZCR_EL2 S3_4_C1_C2_0 =20 #define __LR0_EL2(x) S3_4_C12_C12_ ## x #define __LR8_EL2(x) S3_4_C12_C13_ ## x diff --git a/xen/arch/arm/include/asm/cpufeature.h b/xen/arch/arm/include/a= sm/cpufeature.h index c62cf6293fd6..6d703e051906 100644 --- a/xen/arch/arm/include/asm/cpufeature.h +++ b/xen/arch/arm/include/asm/cpufeature.h @@ -32,6 +32,12 @@ #define cpu_has_thumbee (boot_cpu_feature32(thumbee) =3D=3D 1) #define cpu_has_aarch32 (cpu_has_arm || cpu_has_thumb) =20 +#ifdef CONFIG_ARM64_SVE +#define cpu_has_sve (boot_cpu_feature64(sve) =3D=3D 1) +#else +#define cpu_has_sve (0) +#endif + #ifdef CONFIG_ARM_32 #define cpu_has_gicv3 (boot_cpu_feature32(gic) >=3D 1) #define cpu_has_gentimer (boot_cpu_feature32(gentimer) =3D=3D 1) @@ -323,6 +329,14 @@ struct cpuinfo_arm { }; } isa64; =20 + union { + register_t bits[1]; + struct { + unsigned long len:4; + unsigned long __res0:60; + }; + } zcr64; + struct { register_t bits[1]; } zfr64; diff --git a/xen/arch/arm/include/asm/domain.h b/xen/arch/arm/include/asm/d= omain.h index 0e310601e846..42eb5df320a7 100644 --- a/xen/arch/arm/include/asm/domain.h +++ b/xen/arch/arm/include/asm/domain.h @@ -190,6 +190,7 @@ struct arch_vcpu register_t tpidrro_el0; =20 /* HYP configuration */ + register_t cptr_el2; register_t hcr_el2; register_t mdcr_el2; =20 diff --git a/xen/arch/arm/include/asm/processor.h b/xen/arch/arm/include/as= m/processor.h index 1dd81d7d528f..0e38926b94db 100644 --- a/xen/arch/arm/include/asm/processor.h +++ b/xen/arch/arm/include/asm/processor.h @@ -583,6 +583,8 @@ void do_trap_guest_serror(struct cpu_user_regs *regs); =20 register_t get_default_hcr_flags(void); =20 +register_t get_default_cptr_flags(void); + /* * Synchronize SError unless the feature is selected. * This is relying on the SErrors are currently unmasked. diff --git a/xen/arch/arm/setup.c b/xen/arch/arm/setup.c index 1f26f67b90e3..5459cc4f5e62 100644 --- a/xen/arch/arm/setup.c +++ b/xen/arch/arm/setup.c @@ -135,10 +135,11 @@ static void __init processor_id(void) cpu_has_el2_32 ? "64+32" : cpu_has_el2_64 ? "64" : "No", cpu_has_el1_32 ? "64+32" : cpu_has_el1_64 ? "64" : "No", cpu_has_el0_32 ? "64+32" : cpu_has_el0_64 ? "64" : "No"); - printk(" Extensions:%s%s%s\n", + printk(" Extensions:%s%s%s%s\n", cpu_has_fp ? " FloatingPoint" : "", cpu_has_simd ? " AdvancedSIMD" : "", - cpu_has_gicv3 ? " GICv3-SysReg" : ""); + cpu_has_gicv3 ? " GICv3-SysReg" : "", + cpu_has_sve ? " SVE" : ""); =20 /* Warn user if we find unknown floating-point features */ if ( cpu_has_fp && (boot_cpu_feature64(fp) >=3D 2) ) diff --git a/xen/arch/arm/traps.c b/xen/arch/arm/traps.c index 061c92acbd68..45163fd3afb0 100644 --- a/xen/arch/arm/traps.c +++ b/xen/arch/arm/traps.c @@ -93,6 +93,21 @@ register_t get_default_hcr_flags(void) HCR_TID3|HCR_TSC|HCR_TAC|HCR_SWIO|HCR_TIDCP|HCR_FB|HCR_TSW); } =20 +register_t get_default_cptr_flags(void) +{ + /* + * Trap all coprocessor registers (0-13) except cp10 and + * cp11 for VFP. + * + * /!\ All coprocessors except cp10 and cp11 cannot be used in Xen. + * + * On ARM64 the TCPx bits which we set here (0..9,12,13) are all + * RES1, i.e. they would trap whether we did this write or not. + */ + return ((HCPTR_CP_MASK & ~(HCPTR_CP(10) | HCPTR_CP(11))) | + HCPTR_TTA | HCPTR_TAM); +} + static enum { SERRORS_DIVERSE, SERRORS_PANIC, @@ -122,6 +137,7 @@ __initcall(update_serrors_cpu_caps); =20 void init_traps(void) { + register_t cptr_bits =3D get_default_cptr_flags(); /* * Setup Hyp vector base. Note they might get updated with the * branch predictor hardening. @@ -135,17 +151,15 @@ void init_traps(void) /* Trap CP15 c15 used for implementation defined registers */ WRITE_SYSREG(HSTR_T(15), HSTR_EL2); =20 - /* Trap all coprocessor registers (0-13) except cp10 and - * cp11 for VFP. - * - * /!\ All coprocessors except cp10 and cp11 cannot be used in Xen. - * - * On ARM64 the TCPx bits which we set here (0..9,12,13) are all - * RES1, i.e. they would trap whether we did this write or not. +#ifdef CONFIG_ARM64_SVE + /* + * Don't trap SVE now, Xen might need to access ZCR reg in cpufeature = code, + * trapping again or not will be handled on vcpu creation/scheduling l= ater */ - WRITE_SYSREG((HCPTR_CP_MASK & ~(HCPTR_CP(10) | HCPTR_CP(11))) | - HCPTR_TTA | HCPTR_TAM, - CPTR_EL2); + cptr_bits &=3D ~HCPTR_CP(8); +#endif + + WRITE_SYSREG(cptr_bits, CPTR_EL2); =20 /* * Configure HCR_EL2 with the bare minimum to run Xen until a guest --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673447946214517.8126716061544; Wed, 11 Jan 2023 06:39:06 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475456.737199 (Exim 4.92) (envelope-from ) id 1pFcFZ-0001v4-59; Wed, 11 Jan 2023 14:38:45 +0000 Received: by outflank-mailman (output) from mailman id 475456.737199; Wed, 11 Jan 2023 14:38:45 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFZ-0001u5-0e; Wed, 11 Jan 2023 14:38:45 +0000 Received: by outflank-mailman (input) for mailman id 475456; Wed, 11 Jan 2023 14:38:43 +0000 Received: from se1-gles-flk1-in.inumbo.com ([94.247.172.50] helo=se1-gles-flk1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFX-0001NK-JO for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:43 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-flk1.inumbo.com (Halon) with ESMTP id a472b751-91bd-11ed-b8d0-410ff93cb8f0; Wed, 11 Jan 2023 15:38:41 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id E4BDE15DB; Wed, 11 Jan 2023 06:39:22 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 885FB3F71A; Wed, 11 Jan 2023 06:38:39 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a472b751-91bd-11ed-b8d0-410ff93cb8f0 From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk , Andrew Cooper , George Dunlap , Jan Beulich , Wei Liu Subject: [RFC PATCH 2/8] xen/arm: add sve_vl_bits field to domain Date: Wed, 11 Jan 2023 14:38:20 +0000 Message-Id: <20230111143826.3224-3-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673447947496100001 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Add sve_vl_bits field to arch_domain and xen_arch_domainconfig structure, to allow the domain to have an information about the SVE feature and the number of SVE register bits that are allowed for this domain. The field is used also to allow or forbid a domain to use SVE, because a value equal to zero means the guest is not allowed to use the feature. When the guest is allowed to use SVE, the zcr_el2 register is updated on context switch to restict the domain on the allowed number of bits chosen, this value is the minimum among the chosen value and the platform supported value. Signed-off-by: Luca Fancellu --- xen/arch/arm/arm64/sve.c | 9 ++++++ xen/arch/arm/domain.c | 45 ++++++++++++++++++++++++++++ xen/arch/arm/include/asm/arm64/sve.h | 12 ++++++++ xen/arch/arm/include/asm/domain.h | 6 ++++ xen/include/public/arch-arm.h | 2 ++ xen/include/public/domctl.h | 2 +- 6 files changed, 75 insertions(+), 1 deletion(-) diff --git a/xen/arch/arm/arm64/sve.c b/xen/arch/arm/arm64/sve.c index 326389278292..b7695834f4ba 100644 --- a/xen/arch/arm/arm64/sve.c +++ b/xen/arch/arm/arm64/sve.c @@ -6,6 +6,7 @@ */ =20 #include +#include #include #include =20 @@ -36,3 +37,11 @@ register_t vl_to_zcr(uint16_t vl) { return ((vl / SVE_VL_MULTIPLE_VAL) - 1U) & ZCR_ELx_LEN_MASK; } + +/* Get the system sanitized value for VL in bits */ +uint16_t get_sys_vl_len(void) +{ + /* ZCR_ELx len field is ((len+1) * 128) =3D vector bits length */ + return ((system_cpuinfo.zcr64.bits[0] & ZCR_ELx_LEN_MASK) + 1U) * + SVE_VL_MULTIPLE_VAL; +} diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c index 8ea3843ea8e8..27f38729302b 100644 --- a/xen/arch/arm/domain.c +++ b/xen/arch/arm/domain.c @@ -13,6 +13,7 @@ #include =20 #include +#include #include #include #include @@ -183,6 +184,11 @@ static void ctxt_switch_to(struct vcpu *n) =20 WRITE_SYSREG(n->arch.cptr_el2, CPTR_EL2); =20 +#ifdef CONFIG_ARM64_SVE + if ( is_sve_domain(n->domain) ) + WRITE_SYSREG(n->arch.zcr_el2, ZCR_EL2); +#endif + /* VFP */ vfp_restore_state(n); =20 @@ -551,6 +557,11 @@ int arch_vcpu_create(struct vcpu *v) v->arch.vmpidr =3D MPIDR_SMP | vcpuid_to_vaffinity(v->vcpu_id); =20 v->arch.cptr_el2 =3D get_default_cptr_flags(); + if ( is_sve_domain(v->domain) ) + { + v->arch.cptr_el2 &=3D ~HCPTR_CP(8); + v->arch.zcr_el2 =3D vl_to_zcr(v->domain->arch.sve_vl_bits); + } =20 v->arch.hcr_el2 =3D get_default_hcr_flags(); =20 @@ -595,6 +606,7 @@ int arch_sanitise_domain_config(struct xen_domctl_creat= edomain *config) unsigned int max_vcpus; unsigned int flags_required =3D (XEN_DOMCTL_CDF_hvm | XEN_DOMCTL_CDF_h= ap); unsigned int flags_optional =3D (XEN_DOMCTL_CDF_iommu | XEN_DOMCTL_CDF= _vpmu); + unsigned int sve_vl_bits =3D config->arch.sve_vl_bits; =20 if ( (config->flags & ~flags_optional) !=3D flags_required ) { @@ -603,6 +615,36 @@ int arch_sanitise_domain_config(struct xen_domctl_crea= tedomain *config) return -EINVAL; } =20 + /* Check feature flags */ + if ( sve_vl_bits > 0 ) { + unsigned int zcr_max_bits; + + if ( !cpu_has_sve ) + { + dprintk(XENLOG_INFO, "SVE is unsupported on this machine.\n"); + return -EINVAL; + } + else if ( !is_vl_valid(sve_vl_bits) ) + { + dprintk(XENLOG_INFO, "Unsupported SVE vector length (%u)\n", + sve_vl_bits); + return -EINVAL; + } + /* + * get_sys_vl_len() is the common safe value among all cpus, so if= the + * value specified by the user is above that value, use the safe v= alue + * instead. + */ + zcr_max_bits =3D get_sys_vl_len(); + if ( sve_vl_bits > zcr_max_bits ) + { + config->arch.sve_vl_bits =3D zcr_max_bits; + dprintk(XENLOG_INFO, + "SVE vector length lowered to %u, safe value among CPU= s\n", + zcr_max_bits); + } + } + /* The P2M table must always be shared between the CPU and the IOMMU */ if ( config->iommu_opts & XEN_DOMCTL_IOMMU_no_sharept ) { @@ -745,6 +787,9 @@ int arch_domain_create(struct domain *d, if ( (rc =3D domain_vpci_init(d)) !=3D 0 ) goto fail; =20 + /* Copy sve_vl_bits to the domain configuration */ + d->arch.sve_vl_bits =3D config->arch.sve_vl_bits; + return 0; =20 fail: diff --git a/xen/arch/arm/include/asm/arm64/sve.h b/xen/arch/arm/include/as= m/arm64/sve.h index bd56e2f24230..f4a660e402ca 100644 --- a/xen/arch/arm/include/asm/arm64/sve.h +++ b/xen/arch/arm/include/asm/arm64/sve.h @@ -13,10 +13,17 @@ /* Vector length must be multiple of 128 */ #define SVE_VL_MULTIPLE_VAL (128U) =20 +static inline bool is_vl_valid(uint16_t vl) +{ + /* SVE vector length is multiple of 128 and maximum 2048 */ + return ((vl % SVE_VL_MULTIPLE_VAL) =3D=3D 0) && (vl <=3D SVE_VL_MAX_BI= TS); +} + #ifdef CONFIG_ARM64_SVE =20 register_t compute_max_zcr(void); register_t vl_to_zcr(uint16_t vl); +uint16_t get_sys_vl_len(void); =20 #else /* !CONFIG_ARM64_SVE */ =20 @@ -30,6 +37,11 @@ static inline register_t vl_to_zcr(uint16_t vl) return 0; } =20 +static inline uint16_t get_sys_vl_len(void) +{ + return 0; +} + #endif =20 #endif /* _ARM_ARM64_SVE_H */ diff --git a/xen/arch/arm/include/asm/domain.h b/xen/arch/arm/include/asm/d= omain.h index 42eb5df320a7..e4794a9fd2ab 100644 --- a/xen/arch/arm/include/asm/domain.h +++ b/xen/arch/arm/include/asm/domain.h @@ -31,6 +31,8 @@ enum domain_type { =20 #define is_domain_direct_mapped(d) ((d)->cdf & CDF_directmap) =20 +#define is_sve_domain(d) ((d)->arch.sve_vl_bits > 0) + /* * Is the domain using the host memory layout? * @@ -114,6 +116,9 @@ struct arch_domain void *tee; #endif =20 + /* max SVE vector length in bits */ + uint16_t sve_vl_bits; + } __cacheline_aligned; =20 struct arch_vcpu @@ -190,6 +195,7 @@ struct arch_vcpu register_t tpidrro_el0; =20 /* HYP configuration */ + register_t zcr_el2; register_t cptr_el2; register_t hcr_el2; register_t mdcr_el2; diff --git a/xen/include/public/arch-arm.h b/xen/include/public/arch-arm.h index 1528ced5097a..e18a075105f0 100644 --- a/xen/include/public/arch-arm.h +++ b/xen/include/public/arch-arm.h @@ -304,6 +304,8 @@ struct xen_arch_domainconfig { uint16_t tee_type; /* IN */ uint32_t nr_spis; + /* IN */ + uint16_t sve_vl_bits; /* * OUT * Based on the property clock-frequency in the DT timer node. diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h index 51be28c3de7c..616d7a1c070d 100644 --- a/xen/include/public/domctl.h +++ b/xen/include/public/domctl.h @@ -21,7 +21,7 @@ #include "hvm/save.h" #include "memory.h" =20 -#define XEN_DOMCTL_INTERFACE_VERSION 0x00000015 +#define XEN_DOMCTL_INTERFACE_VERSION 0x00000016 =20 /* * NB. xen_domctl.domain is an IN/OUT parameter for this operation. --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673448345786577.4619793357399; Wed, 11 Jan 2023 06:45:45 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475507.737265 (Exim 4.92) (envelope-from ) id 1pFcLz-00061K-Cx; Wed, 11 Jan 2023 14:45:23 +0000 Received: by outflank-mailman (output) from mailman id 475507.737265; Wed, 11 Jan 2023 14:45:23 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcLz-000617-9H; Wed, 11 Jan 2023 14:45:23 +0000 Received: by outflank-mailman (input) for mailman id 475507; Wed, 11 Jan 2023 14:45:21 +0000 Received: from se1-gles-sth1-in.inumbo.com ([159.253.27.254] helo=se1-gles-sth1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFX-0000FC-Cn for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:43 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-sth1.inumbo.com (Halon) with ESMTP id a51c0bc6-91bd-11ed-91b6-6bf2151ebd3b; Wed, 11 Jan 2023 15:38:42 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 09004169E; Wed, 11 Jan 2023 06:39:24 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 16C5F3F71A; Wed, 11 Jan 2023 06:38:40 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a51c0bc6-91bd-11ed-91b6-6bf2151ebd3b From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 3/8] xen/arm: Expose SVE feature to the guest Date: Wed, 11 Jan 2023 14:38:21 +0000 Message-Id: <20230111143826.3224-4-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673448347251100009 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" When a guest is allowed to use SVE, expose the SVE features through the identification registers. Signed-off-by: Luca Fancellu --- xen/arch/arm/arm64/vsysreg.c | 39 ++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) diff --git a/xen/arch/arm/arm64/vsysreg.c b/xen/arch/arm/arm64/vsysreg.c index 758750983c11..10048bb4d221 100644 --- a/xen/arch/arm/arm64/vsysreg.c +++ b/xen/arch/arm/arm64/vsysreg.c @@ -18,6 +18,7 @@ =20 #include =20 +#include #include #include #include @@ -295,7 +296,28 @@ void do_sysreg(struct cpu_user_regs *regs, GENERATE_TID3_INFO(MVFR0_EL1, mvfr, 0) GENERATE_TID3_INFO(MVFR1_EL1, mvfr, 1) GENERATE_TID3_INFO(MVFR2_EL1, mvfr, 2) - GENERATE_TID3_INFO(ID_AA64PFR0_EL1, pfr64, 0) + + case HSR_SYSREG_ID_AA64PFR0_EL1: + { + register_t guest_reg_value =3D guest_cpuinfo.pfr64.bits[0]; + + if ( is_sve_domain(v->domain) ) + { + /* 4 is the SVE field width in id_aa64pfr0_el1 */ + uint64_t mask =3D GENMASK(ID_AA64PFR0_SVE_SHIFT + 4 - 1, + ID_AA64PFR0_SVE_SHIFT); + /* sysval is the sve field on the system */ + uint64_t sysval =3D cpuid_feature_extract_unsigned_field_width( + system_cpuinfo.pfr64.bits[0], + ID_AA64PFR0_SVE_SHIFT, 4); + guest_reg_value &=3D ~mask; + guest_reg_value |=3D (sysval << ID_AA64PFR0_SVE_SHIFT) & mask; + } + + return handle_ro_read_val(regs, regidx, hsr.sysreg.read, hsr, 1, + guest_reg_value); + } + GENERATE_TID3_INFO(ID_AA64PFR1_EL1, pfr64, 1) GENERATE_TID3_INFO(ID_AA64DFR0_EL1, dbg64, 0) GENERATE_TID3_INFO(ID_AA64DFR1_EL1, dbg64, 1) @@ -306,7 +328,20 @@ void do_sysreg(struct cpu_user_regs *regs, GENERATE_TID3_INFO(ID_AA64MMFR2_EL1, mm64, 2) GENERATE_TID3_INFO(ID_AA64AFR0_EL1, aux64, 0) GENERATE_TID3_INFO(ID_AA64AFR1_EL1, aux64, 1) - GENERATE_TID3_INFO(ID_AA64ZFR0_EL1, zfr64, 0) + + case HSR_SYSREG_ID_AA64ZFR0_EL1: + { + /* + * When the guest has the SVE feature enabled, the whole id_aa64zf= r0_el1 + * needs to be exposed. + */ + register_t guest_reg_value =3D guest_cpuinfo.zfr64.bits[0]; + if ( is_sve_domain(v->domain) ) + guest_reg_value =3D system_cpuinfo.zfr64.bits[0]; + + return handle_ro_read_val(regs, regidx, hsr.sysreg.read, hsr, 1, + guest_reg_value); + } =20 /* * Those cases are catching all Reserved registers trapped by TID3 whi= ch --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673448341041631.155355350907; Wed, 11 Jan 2023 06:45:41 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475504.737254 (Exim 4.92) (envelope-from ) id 1pFcLx-0005iQ-3v; Wed, 11 Jan 2023 14:45:21 +0000 Received: by outflank-mailman (output) from mailman id 475504.737254; Wed, 11 Jan 2023 14:45:21 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcLx-0005iF-0s; Wed, 11 Jan 2023 14:45:21 +0000 Received: by outflank-mailman (input) for mailman id 475504; Wed, 11 Jan 2023 14:45:19 +0000 Received: from se1-gles-sth1-in.inumbo.com ([159.253.27.254] helo=se1-gles-sth1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFY-0000FC-D1 for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:44 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-sth1.inumbo.com (Halon) with ESMTP id a5a241cf-91bd-11ed-91b6-6bf2151ebd3b; Wed, 11 Jan 2023 15:38:43 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 1FD5FFEC; Wed, 11 Jan 2023 06:39:25 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 2E32A3F71A; Wed, 11 Jan 2023 06:38:42 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a5a241cf-91bd-11ed-91b6-6bf2151ebd3b From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 4/8] xen/arm: add SVE exception class handling Date: Wed, 11 Jan 2023 14:38:22 +0000 Message-Id: <20230111143826.3224-5-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673448343221100003 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" SVE has a new exception class with code 0x19, introduce the new code and handle the exception. Signed-off-by: Luca Fancellu --- xen/arch/arm/include/asm/processor.h | 1 + xen/arch/arm/traps.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) diff --git a/xen/arch/arm/include/asm/processor.h b/xen/arch/arm/include/as= m/processor.h index 0e38926b94db..625c2bd0cd6c 100644 --- a/xen/arch/arm/include/asm/processor.h +++ b/xen/arch/arm/include/asm/processor.h @@ -426,6 +426,7 @@ #define HSR_EC_HVC64 0x16 #define HSR_EC_SMC64 0x17 #define HSR_EC_SYSREG 0x18 +#define HSR_EC_SVE 0x19 #endif #define HSR_EC_INSTR_ABORT_LOWER_EL 0x20 #define HSR_EC_INSTR_ABORT_CURR_EL 0x21 diff --git a/xen/arch/arm/traps.c b/xen/arch/arm/traps.c index 45163fd3afb0..66e07197aea5 100644 --- a/xen/arch/arm/traps.c +++ b/xen/arch/arm/traps.c @@ -2168,6 +2168,13 @@ void do_trap_guest_sync(struct cpu_user_regs *regs) perfc_incr(trap_sysreg); do_sysreg(regs, hsr); break; + case HSR_EC_SVE: + GUEST_BUG_ON(regs_mode_is_32bit(regs)); + gprintk(XENLOG_WARNING, + "Domain id %d tried to use SVE while not allowed\n", + current->domain->domain_id); + inject_undef_exception(regs, hsr); + break; #endif =20 case HSR_EC_INSTR_ABORT_LOWER_EL: @@ -2197,6 +2204,11 @@ void do_trap_hyp_sync(struct cpu_user_regs *regs) case HSR_EC_BRK: do_trap_brk(regs, hsr); break; + case HSR_EC_SVE: + /* An SVE exception is a bug somewhere in hypervisor code */ + printk("SVE trap at EL2.\n"); + do_unexpected_trap("Hypervisor", regs); + break; #endif case HSR_EC_DATA_ABORT_CURR_EL: case HSR_EC_INSTR_ABORT_CURR_EL: --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673447948550126.68878433816076; Wed, 11 Jan 2023 06:39:08 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475458.737210 (Exim 4.92) (envelope-from ) id 1pFcFd-0002Ge-FU; Wed, 11 Jan 2023 14:38:49 +0000 Received: by outflank-mailman (output) from mailman id 475458.737210; Wed, 11 Jan 2023 14:38:49 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFd-0002GV-An; Wed, 11 Jan 2023 14:38:49 +0000 Received: by outflank-mailman (input) for mailman id 475458; Wed, 11 Jan 2023 14:38:47 +0000 Received: from se1-gles-flk1-in.inumbo.com ([94.247.172.50] helo=se1-gles-flk1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFb-0001NK-Ku for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:47 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-flk1.inumbo.com (Halon) with ESMTP id a681ec48-91bd-11ed-b8d0-410ff93cb8f0; Wed, 11 Jan 2023 15:38:44 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 51FE913D5; Wed, 11 Jan 2023 06:39:26 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 45D913F71A; Wed, 11 Jan 2023 06:38:43 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a681ec48-91bd-11ed-b8d0-410ff93cb8f0 From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 5/8] arm/sve: save/restore SVE context switch Date: Wed, 11 Jan 2023 14:38:23 +0000 Message-Id: <20230111143826.3224-6-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673447949333100007 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Save/restore context switch for SVE, allocate memory to contain the Z0-31 registers whose length is maximum 2048 bits each and FFR who can be maximum 256 bits, the allocated memory depends on how many bits is the vector length for the domain and how many bits are supported by the platform. Save P0-15 whose length is maximum 256 bits each, in this case the memory used is from the fpregs field in struct vfp_state, because V0-31 are part of Z0-31 and this space would have been unused for SVE domain otherwise. Create zcr_el1 field in arch_vcpu and save/restore ZCR_EL1 value on context switch. Remove headers from sve.c that are already included using xen/sched.h. Signed-off-by: Luca Fancellu --- xen/arch/arm/arm64/sve.c | 58 +++++++++- xen/arch/arm/arm64/sve_asm.S | 141 +++++++++++++++++++++++ xen/arch/arm/arm64/vfp.c | 79 +++++++------ xen/arch/arm/domain.c | 12 ++ xen/arch/arm/include/asm/arm64/sve.h | 13 +++ xen/arch/arm/include/asm/arm64/sysregs.h | 3 + xen/arch/arm/include/asm/arm64/vfp.h | 10 ++ xen/arch/arm/include/asm/domain.h | 1 + 8 files changed, 280 insertions(+), 37 deletions(-) diff --git a/xen/arch/arm/arm64/sve.c b/xen/arch/arm/arm64/sve.c index b7695834f4ba..c7b325700fe4 100644 --- a/xen/arch/arm/arm64/sve.c +++ b/xen/arch/arm/arm64/sve.c @@ -5,12 +5,29 @@ * Copyright (C) 2022 ARM Ltd. */ =20 -#include -#include +#include +#include #include -#include =20 extern unsigned int sve_get_hw_vl(void); +extern void sve_save_ctx(uint64_t *sve_ctx, uint64_t *pregs, int save_ffr); +extern void sve_load_ctx(uint64_t const *sve_ctx, uint64_t const *pregs, + int restore_ffr); + +static inline uint16_t sve_zreg_ctx_size(uint16_t vl) +{ + /* + * Z0-31 registers size in bytes is computed from VL that is in bits, = so VL + * in bytes is VL/8. + */ + return (vl / 8U) * 32U; +} + +static inline uint16_t sve_ffrreg_ctx_size(uint16_t vl) +{ + /* FFR register size is VL/8, which is in bytes (VL/8)/8 */ + return (vl / 64U); +} =20 register_t compute_max_zcr(void) { @@ -45,3 +62,38 @@ uint16_t get_sys_vl_len(void) return ((system_cpuinfo.zcr64.bits[0] & ZCR_ELx_LEN_MASK) + 1U) * SVE_VL_MULTIPLE_VAL; } + +int sve_context_init(struct vcpu *v) +{ + uint64_t *ctx =3D _xzalloc(sve_zreg_ctx_size(v->domain->arch.sve_vl_bi= ts) + + sve_ffrreg_ctx_size(v->domain->arch.sve_vl_bi= ts), + L1_CACHE_BYTES); + + if ( !ctx ) + return -ENOMEM; + + v->arch.vfp.sve_context =3D ctx; + + return 0; +} + +void sve_context_free(struct vcpu *v) +{ + xfree(v->arch.vfp.sve_context); +} + +void sve_save_state(struct vcpu *v) +{ + uint64_t *sve_ctx_zreg_end =3D v->arch.vfp.sve_context + + (sve_zreg_ctx_size(v->domain->arch.sve_vl_bits) / sizeof(uint6= 4_t)); + + sve_save_ctx(sve_ctx_zreg_end, v->arch.vfp.fpregs, 1); +} + +void sve_restore_state(struct vcpu *v) +{ + uint64_t *sve_ctx_zreg_end =3D v->arch.vfp.sve_context + + (sve_zreg_ctx_size(v->domain->arch.sve_vl_bits) / sizeof(uint6= 4_t)); + + sve_load_ctx(sve_ctx_zreg_end, v->arch.vfp.fpregs, 1); +} diff --git a/xen/arch/arm/arm64/sve_asm.S b/xen/arch/arm/arm64/sve_asm.S index 4d1549344733..8c37d7bc95d5 100644 --- a/xen/arch/arm/arm64/sve_asm.S +++ b/xen/arch/arm/arm64/sve_asm.S @@ -17,6 +17,18 @@ .endif .endm =20 +.macro _sve_check_zreg znr + .if (\znr) < 0 || (\znr) > 31 + .error "Bad Scalable Vector Extension vector register number \znr." + .endif +.endm + +.macro _sve_check_preg pnr + .if (\pnr) < 0 || (\pnr) > 15 + .error "Bad Scalable Vector Extension predicate register number \p= nr." + .endif +.endm + .macro _check_num n, min, max .if (\n) < (\min) || (\n) > (\max) .error "Number \n out of range [\min,\max]" @@ -26,6 +38,54 @@ /* SVE instruction encodings for non-SVE-capable assemblers */ /* (pre binutils 2.28, all kernel capable clang versions support SVE) */ =20 +/* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */ +.macro _sve_str_v nz, nxbase, offset=3D0 + _sve_check_zreg \nz + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe5804000 \ + | (\nz) \ + | ((\nxbase) << 5) \ + | (((\offset) & 7) << 10) \ + | (((\offset) & 0x1f8) << 13) +.endm + +/* LDR (vector): LDR Z\nz, [X\nxbase, #\offset, MUL VL] */ +.macro _sve_ldr_v nz, nxbase, offset=3D0 + _sve_check_zreg \nz + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0x85804000 \ + | (\nz) \ + | ((\nxbase) << 5) \ + | (((\offset) & 7) << 10) \ + | (((\offset) & 0x1f8) << 13) +.endm + +/* STR (predicate): STR P\np, [X\nxbase, #\offset, MUL VL] */ +.macro _sve_str_p np, nxbase, offset=3D0 + _sve_check_preg \np + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe5800000 \ + | (\np) \ + | ((\nxbase) << 5) \ + | (((\offset) & 7) << 10) \ + | (((\offset) & 0x1f8) << 13) +.endm + +/* LDR (predicate): LDR P\np, [X\nxbase, #\offset, MUL VL] */ +.macro _sve_ldr_p np, nxbase, offset=3D0 + _sve_check_preg \np + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0x85800000 \ + | (\np) \ + | ((\nxbase) << 5) \ + | (((\offset) & 7) << 10) \ + | (((\offset) & 0x1f8) << 13) +.endm + /* RDVL X\nx, #\imm */ .macro _sve_rdvl nx, imm _check_general_reg \nx @@ -35,11 +95,92 @@ | (((\imm) & 0x3f) << 5) .endm =20 +/* RDFFR (unpredicated): RDFFR P\np.B */ +.macro _sve_rdffr np + _sve_check_preg \np + .inst 0x2519f000 \ + | (\np) +.endm + +/* WRFFR P\np.B */ +.macro _sve_wrffr np + _sve_check_preg \np + .inst 0x25289000 \ + | ((\np) << 5) +.endm + +.macro __for from:req, to:req + .if (\from) =3D=3D (\to) + _for__body %\from + .else + __for %\from, %((\from) + ((\to) - (\from)) / 2) + __for %((\from) + ((\to) - (\from)) / 2 + 1), %\to + .endif +.endm + +.macro _for var:req, from:req, to:req, insn:vararg + .macro _for__body \var:req + .noaltmacro + \insn + .altmacro + .endm + + .altmacro + __for \from, \to + .noaltmacro + + .purgem _for__body +.endm + +.macro sve_save nxzffrctx, nxpctx, save_ffr + _for n, 0, 31, _sve_str_v \n, \nxzffrctx, \n - 32 + _for n, 0, 15, _sve_str_p \n, \nxpctx, \n + cbz \save_ffr, 1f + _sve_rdffr 0 + _sve_str_p 0, \nxzffrctx + _sve_ldr_p 0, \nxpctx + b 2f +1: + str xzr, [x\nxzffrctx] // Zero out FFR +2: +.endm + +.macro sve_load nxzffrctx, nxpctx, restore_ffr + _for n, 0, 31, _sve_ldr_v \n, \nxzffrctx, \n - 32 + cbz \restore_ffr, 1f + _sve_ldr_p 0, \nxzffrctx + _sve_wrffr 0 +1: + _for n, 0, 15, _sve_ldr_p \n, \nxpctx, \n +.endm + /* Gets the current vector register size in bytes */ GLOBAL(sve_get_hw_vl) _sve_rdvl 0, 1 ret =20 +/* + * Save the SVE context + * + * x0 - pointer to buffer for Z0-31 + FFR + * x1 - pointer to buffer for P0-15 + * x2 - Save FFR if non-zero + */ +GLOBAL(sve_save_ctx) + sve_save 0, 1, x2 + ret + +/* + * Load the SVE context + * + * x0 - pointer to buffer for Z0-31 + FFR + * x1 - pointer to buffer for P0-15 + * x2 - Restore FFR if non-zero + */ +GLOBAL(sve_load_ctx) + sve_load 0, 1, x2 + ret + /* * Local variables: * mode: ASM diff --git a/xen/arch/arm/arm64/vfp.c b/xen/arch/arm/arm64/vfp.c index 47885e76baae..2d0d7c2e6ddb 100644 --- a/xen/arch/arm/arm64/vfp.c +++ b/xen/arch/arm/arm64/vfp.c @@ -2,29 +2,35 @@ #include #include #include +#include =20 void vfp_save_state(struct vcpu *v) { if ( !cpu_has_fp ) return; =20 - asm volatile("stp q0, q1, [%1, #16 * 0]\n\t" - "stp q2, q3, [%1, #16 * 2]\n\t" - "stp q4, q5, [%1, #16 * 4]\n\t" - "stp q6, q7, [%1, #16 * 6]\n\t" - "stp q8, q9, [%1, #16 * 8]\n\t" - "stp q10, q11, [%1, #16 * 10]\n\t" - "stp q12, q13, [%1, #16 * 12]\n\t" - "stp q14, q15, [%1, #16 * 14]\n\t" - "stp q16, q17, [%1, #16 * 16]\n\t" - "stp q18, q19, [%1, #16 * 18]\n\t" - "stp q20, q21, [%1, #16 * 20]\n\t" - "stp q22, q23, [%1, #16 * 22]\n\t" - "stp q24, q25, [%1, #16 * 24]\n\t" - "stp q26, q27, [%1, #16 * 26]\n\t" - "stp q28, q29, [%1, #16 * 28]\n\t" - "stp q30, q31, [%1, #16 * 30]\n\t" - : "=3DQ" (*v->arch.vfp.fpregs) : "r" (v->arch.vfp.fpregs)= ); + if ( is_sve_domain(v->domain) ) + sve_save_state(v); + else + { + asm volatile("stp q0, q1, [%1, #16 * 0]\n\t" + "stp q2, q3, [%1, #16 * 2]\n\t" + "stp q4, q5, [%1, #16 * 4]\n\t" + "stp q6, q7, [%1, #16 * 6]\n\t" + "stp q8, q9, [%1, #16 * 8]\n\t" + "stp q10, q11, [%1, #16 * 10]\n\t" + "stp q12, q13, [%1, #16 * 12]\n\t" + "stp q14, q15, [%1, #16 * 14]\n\t" + "stp q16, q17, [%1, #16 * 16]\n\t" + "stp q18, q19, [%1, #16 * 18]\n\t" + "stp q20, q21, [%1, #16 * 20]\n\t" + "stp q22, q23, [%1, #16 * 22]\n\t" + "stp q24, q25, [%1, #16 * 24]\n\t" + "stp q26, q27, [%1, #16 * 26]\n\t" + "stp q28, q29, [%1, #16 * 28]\n\t" + "stp q30, q31, [%1, #16 * 30]\n\t" + : "=3DQ" (*v->arch.vfp.fpregs) : "r" (v->arch.vfp.fpr= egs)); + } =20 v->arch.vfp.fpsr =3D READ_SYSREG(FPSR); v->arch.vfp.fpcr =3D READ_SYSREG(FPCR); @@ -37,23 +43,28 @@ void vfp_restore_state(struct vcpu *v) if ( !cpu_has_fp ) return; =20 - asm volatile("ldp q0, q1, [%1, #16 * 0]\n\t" - "ldp q2, q3, [%1, #16 * 2]\n\t" - "ldp q4, q5, [%1, #16 * 4]\n\t" - "ldp q6, q7, [%1, #16 * 6]\n\t" - "ldp q8, q9, [%1, #16 * 8]\n\t" - "ldp q10, q11, [%1, #16 * 10]\n\t" - "ldp q12, q13, [%1, #16 * 12]\n\t" - "ldp q14, q15, [%1, #16 * 14]\n\t" - "ldp q16, q17, [%1, #16 * 16]\n\t" - "ldp q18, q19, [%1, #16 * 18]\n\t" - "ldp q20, q21, [%1, #16 * 20]\n\t" - "ldp q22, q23, [%1, #16 * 22]\n\t" - "ldp q24, q25, [%1, #16 * 24]\n\t" - "ldp q26, q27, [%1, #16 * 26]\n\t" - "ldp q28, q29, [%1, #16 * 28]\n\t" - "ldp q30, q31, [%1, #16 * 30]\n\t" - : : "Q" (*v->arch.vfp.fpregs), "r" (v->arch.vfp.fpregs)); + if ( is_sve_domain(v->domain) ) + sve_restore_state(v); + else + { + asm volatile("ldp q0, q1, [%1, #16 * 0]\n\t" + "ldp q2, q3, [%1, #16 * 2]\n\t" + "ldp q4, q5, [%1, #16 * 4]\n\t" + "ldp q6, q7, [%1, #16 * 6]\n\t" + "ldp q8, q9, [%1, #16 * 8]\n\t" + "ldp q10, q11, [%1, #16 * 10]\n\t" + "ldp q12, q13, [%1, #16 * 12]\n\t" + "ldp q14, q15, [%1, #16 * 14]\n\t" + "ldp q16, q17, [%1, #16 * 16]\n\t" + "ldp q18, q19, [%1, #16 * 18]\n\t" + "ldp q20, q21, [%1, #16 * 20]\n\t" + "ldp q22, q23, [%1, #16 * 22]\n\t" + "ldp q24, q25, [%1, #16 * 24]\n\t" + "ldp q26, q27, [%1, #16 * 26]\n\t" + "ldp q28, q29, [%1, #16 * 28]\n\t" + "ldp q30, q31, [%1, #16 * 30]\n\t" + : : "Q" (*v->arch.vfp.fpregs), "r" (v->arch.vfp.fpreg= s)); + } =20 WRITE_SYSREG(v->arch.vfp.fpsr, FPSR); WRITE_SYSREG(v->arch.vfp.fpcr, FPCR); diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c index 27f38729302b..228cd2f7627e 100644 --- a/xen/arch/arm/domain.c +++ b/xen/arch/arm/domain.c @@ -159,6 +159,11 @@ static void ctxt_switch_from(struct vcpu *p) /* VFP */ vfp_save_state(p); =20 +#ifdef CONFIG_ARM64_SVE + if ( is_sve_domain(p->domain) ) + p->arch.zcr_el1 =3D READ_SYSREG(ZCR_EL1); +#endif + /* VGIC */ gic_save_state(p); =20 @@ -186,7 +191,10 @@ static void ctxt_switch_to(struct vcpu *n) =20 #ifdef CONFIG_ARM64_SVE if ( is_sve_domain(n->domain) ) + { + WRITE_SYSREG(n->arch.zcr_el1, ZCR_EL1); WRITE_SYSREG(n->arch.zcr_el2, ZCR_EL2); + } #endif =20 /* VFP */ @@ -559,6 +567,8 @@ int arch_vcpu_create(struct vcpu *v) v->arch.cptr_el2 =3D get_default_cptr_flags(); if ( is_sve_domain(v->domain) ) { + if ( (rc =3D sve_context_init(v)) !=3D 0 ) + goto fail; v->arch.cptr_el2 &=3D ~HCPTR_CP(8); v->arch.zcr_el2 =3D vl_to_zcr(v->domain->arch.sve_vl_bits); } @@ -591,6 +601,8 @@ fail: =20 void arch_vcpu_destroy(struct vcpu *v) { + if ( is_sve_domain(v->domain) ) + sve_context_free(v); vcpu_timer_destroy(v); vcpu_vgic_free(v); free_xenheap_pages(v->arch.stack, STACK_ORDER); diff --git a/xen/arch/arm/include/asm/arm64/sve.h b/xen/arch/arm/include/as= m/arm64/sve.h index f4a660e402ca..28c31b329233 100644 --- a/xen/arch/arm/include/asm/arm64/sve.h +++ b/xen/arch/arm/include/asm/arm64/sve.h @@ -24,6 +24,10 @@ static inline bool is_vl_valid(uint16_t vl) register_t compute_max_zcr(void); register_t vl_to_zcr(uint16_t vl); uint16_t get_sys_vl_len(void); +int sve_context_init(struct vcpu *v); +void sve_context_free(struct vcpu *v); +void sve_save_state(struct vcpu *v); +void sve_restore_state(struct vcpu *v); =20 #else /* !CONFIG_ARM64_SVE */ =20 @@ -42,6 +46,15 @@ static inline uint16_t get_sys_vl_len(void) return 0; } =20 +static inline int sve_context_init(struct vcpu *v) +{ + return 0; +} + +static inline void sve_context_free(struct vcpu *v) {} +static inline void sve_save_state(struct vcpu *v) {} +static inline void sve_restore_state(struct vcpu *v) {} + #endif =20 #endif /* _ARM_ARM64_SVE_H */ diff --git a/xen/arch/arm/include/asm/arm64/sysregs.h b/xen/arch/arm/includ= e/asm/arm64/sysregs.h index 4cabb9eb4d5e..3fdeb9d8cdef 100644 --- a/xen/arch/arm/include/asm/arm64/sysregs.h +++ b/xen/arch/arm/include/asm/arm64/sysregs.h @@ -88,6 +88,9 @@ #ifndef ID_AA64ISAR2_EL1 #define ID_AA64ISAR2_EL1 S3_0_C0_C6_2 #endif +#ifndef ZCR_EL1 +#define ZCR_EL1 S3_0_C1_C2_0 +#endif =20 /* ID registers (imported from arm64/include/asm/sysreg.h in Linux) */ =20 diff --git a/xen/arch/arm/include/asm/arm64/vfp.h b/xen/arch/arm/include/as= m/arm64/vfp.h index e6e8c363bc16..8af714cb8ecc 100644 --- a/xen/arch/arm/include/asm/arm64/vfp.h +++ b/xen/arch/arm/include/asm/arm64/vfp.h @@ -6,7 +6,17 @@ =20 struct vfp_state { + /* + * When SVE is enabled for the guest, fpregs memory will be used to + * save/restore P0-P15 registers, otherwise it will be used for the V0= -V31 + * registers. + */ uint64_t fpregs[64] __vfp_aligned; + /* + * When SVE is enabled for the guest, sve_context contains memory to + * save/restore Z0-Z31 registers and FFR. + */ + uint64_t *sve_context; register_t fpcr; register_t fpexc32_el2; register_t fpsr; diff --git a/xen/arch/arm/include/asm/domain.h b/xen/arch/arm/include/asm/d= omain.h index e4794a9fd2ab..4d1066750a9b 100644 --- a/xen/arch/arm/include/asm/domain.h +++ b/xen/arch/arm/include/asm/domain.h @@ -195,6 +195,7 @@ struct arch_vcpu register_t tpidrro_el0; =20 /* HYP configuration */ + register_t zcr_el1; register_t zcr_el2; register_t cptr_el2; register_t hcr_el2; --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673448347864239.47140897637337; Wed, 11 Jan 2023 06:45:47 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475509.737271 (Exim 4.92) (envelope-from ) id 1pFcLz-00064Q-RZ; Wed, 11 Jan 2023 14:45:23 +0000 Received: by outflank-mailman (output) from mailman id 475509.737271; Wed, 11 Jan 2023 14:45:23 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcLz-00063i-Ir; Wed, 11 Jan 2023 14:45:23 +0000 Received: by outflank-mailman (input) for mailman id 475509; Wed, 11 Jan 2023 14:45:21 +0000 Received: from se1-gles-sth1-in.inumbo.com ([159.253.27.254] helo=se1-gles-sth1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFb-0000FC-Er for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:47 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-sth1.inumbo.com (Halon) with ESMTP id a760cc4e-91bd-11ed-91b6-6bf2151ebd3b; Wed, 11 Jan 2023 15:38:46 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id D45BEFEC; Wed, 11 Jan 2023 06:39:27 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 78DB13F71A; Wed, 11 Jan 2023 06:38:44 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a760cc4e-91bd-11ed-91b6-6bf2151ebd3b From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Andrew Cooper , George Dunlap , Jan Beulich , Julien Grall , Stefano Stabellini , Wei Liu , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 6/8] xen/arm: enable Dom0 to use SVE feature Date: Wed, 11 Jan 2023 14:38:24 +0000 Message-Id: <20230111143826.3224-7-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673448349359100001 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Add a command line parameter to allow Dom0 the use of SVE resources, the command line parameter dom0_sve controls the feature on this domain and sets the maximum SVE vector length for Dom0. Signed-off-by: Luca Fancellu --- docs/misc/xen-command-line.pandoc | 12 ++++++++++++ xen/arch/arm/arm64/sve.c | 5 +++++ xen/arch/arm/domain_build.c | 4 ++++ xen/arch/arm/include/asm/arm64/sve.h | 4 ++++ 4 files changed, 25 insertions(+) diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line= .pandoc index 923910f553c5..940a96f4207c 100644 --- a/docs/misc/xen-command-line.pandoc +++ b/docs/misc/xen-command-line.pandoc @@ -995,6 +995,18 @@ restrictions set up here. Note that the values to be s= pecified here are ACPI PXM ones, not Xen internal node numbers. `relaxed` sets up vCPU affinities to prefer but be not limited to the specified node(s). =20 +### dom0_sve (arm) +> `=3D ` + +> Default: `0` + +Enable arm SVE usage for Dom0 domain and sets the maximum SVE vector lengt= h. +Values above 0 means feature is enabled for Dom0, otherwise feature is dis= abled. +Possible values are from 0 to maximum 2048, being multiple of 128, that wi= ll be +the maximum vector length. +Please note that the specified value is a maximum allowed vector length, s= o if +the platform supports only a lower value, the lower one will be chosen. + ### dom0_vcpus_pin > `=3D ` =20 diff --git a/xen/arch/arm/arm64/sve.c b/xen/arch/arm/arm64/sve.c index c7b325700fe4..9f8c5d21a59f 100644 --- a/xen/arch/arm/arm64/sve.c +++ b/xen/arch/arm/arm64/sve.c @@ -5,10 +5,15 @@ * Copyright (C) 2022 ARM Ltd. */ =20 +#include #include #include #include =20 +/* opt_dom0_sve: allow Dom0 to use SVE and set maximum vector length. */ +unsigned int __initdata opt_dom0_sve; +integer_param("dom0_sve", opt_dom0_sve); + extern unsigned int sve_get_hw_vl(void); extern void sve_save_ctx(uint64_t *sve_ctx, uint64_t *pregs, int save_ffr); extern void sve_load_ctx(uint64_t const *sve_ctx, uint64_t const *pregs, diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c index 829cea8de84f..48c3fdc28063 100644 --- a/xen/arch/arm/domain_build.c +++ b/xen/arch/arm/domain_build.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -4075,6 +4076,9 @@ void __init create_dom0(void) if ( iommu_enabled ) dom0_cfg.flags |=3D XEN_DOMCTL_CDF_iommu; =20 + if ( opt_dom0_sve > 0 ) + dom0_cfg.arch.sve_vl_bits =3D opt_dom0_sve; + dom0 =3D domain_create(0, &dom0_cfg, CDF_privileged | CDF_directmap); if ( IS_ERR(dom0) || (alloc_dom0_vcpu0(dom0) =3D=3D NULL) ) panic("Error creating domain 0\n"); diff --git a/xen/arch/arm/include/asm/arm64/sve.h b/xen/arch/arm/include/as= m/arm64/sve.h index 28c31b329233..dc6e747cec9e 100644 --- a/xen/arch/arm/include/asm/arm64/sve.h +++ b/xen/arch/arm/include/asm/arm64/sve.h @@ -21,6 +21,8 @@ static inline bool is_vl_valid(uint16_t vl) =20 #ifdef CONFIG_ARM64_SVE =20 +extern unsigned int opt_dom0_sve; + register_t compute_max_zcr(void); register_t vl_to_zcr(uint16_t vl); uint16_t get_sys_vl_len(void); @@ -31,6 +33,8 @@ void sve_restore_state(struct vcpu *v); =20 #else /* !CONFIG_ARM64_SVE */ =20 +#define opt_dom0_sve (0) + static inline register_t compute_max_zcr(void) { return 0; --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673448343103336.6145567813925; Wed, 11 Jan 2023 06:45:43 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475493.737231 (Exim 4.92) (envelope-from ) id 1pFcLs-000597-Ie; Wed, 11 Jan 2023 14:45:16 +0000 Received: by outflank-mailman (output) from mailman id 475493.737231; Wed, 11 Jan 2023 14:45:16 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcLs-000590-Ft; Wed, 11 Jan 2023 14:45:16 +0000 Received: by outflank-mailman (input) for mailman id 475493; Wed, 11 Jan 2023 14:45:15 +0000 Received: from se1-gles-sth1-in.inumbo.com ([159.253.27.254] helo=se1-gles-sth1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFc-0000FC-GM for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:48 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-sth1.inumbo.com (Halon) with ESMTP id a8093cec-91bd-11ed-91b6-6bf2151ebd3b; Wed, 11 Jan 2023 15:38:47 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 1281615DB; Wed, 11 Jan 2023 06:39:29 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 064353F71A; Wed, 11 Jan 2023 06:38:45 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a8093cec-91bd-11ed-91b6-6bf2151ebd3b From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Wei Liu , Anthony PERARD , George Dunlap , Nick Rosbrook , Juergen Gross Subject: [RFC PATCH 7/8] xen/tools: add sve parameter in XL configuration Date: Wed, 11 Jan 2023 14:38:25 +0000 Message-Id: <20230111143826.3224-8-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673448345246100007 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Add sve parameter in XL configuration to allow guests to use SVE feature. Signed-off-by: Luca Fancellu --- docs/man/xl.cfg.5.pod.in | 11 +++++++++++ tools/golang/xenlight/helpers.gen.go | 2 ++ tools/golang/xenlight/types.gen.go | 1 + tools/include/libxl.h | 5 +++++ tools/libs/light/libxl_arm.c | 2 ++ tools/libs/light/libxl_types.idl | 1 + tools/xl/xl_parse.c | 10 ++++++++++ 7 files changed, 32 insertions(+) diff --git a/docs/man/xl.cfg.5.pod.in b/docs/man/xl.cfg.5.pod.in index 024bceeb61b2..60412f7e32a0 100644 --- a/docs/man/xl.cfg.5.pod.in +++ b/docs/man/xl.cfg.5.pod.in @@ -2903,6 +2903,17 @@ Currently, only the "sbsa_uart" model is supported f= or ARM. =20 =3Dback =20 +=3Ditem B + +To enable SVE, user must specify a number different from zero, maximum 204= 8 and +multiple of 128. That value will be the maximum number of SVE registers bi= ts +that the hypervisor will impose to this guest. If the platform has a lower= bits +value, then the lower value will be chosen. +A value equal to zero is the default and it means this guest is not allowe= d to +use SVE. + +=3Dback + =3Dhead3 x86 =20 =3Dover 4 diff --git a/tools/golang/xenlight/helpers.gen.go b/tools/golang/xenlight/h= elpers.gen.go index 3ac4938858f2..7f3b1e758b00 100644 --- a/tools/golang/xenlight/helpers.gen.go +++ b/tools/golang/xenlight/helpers.gen.go @@ -1117,6 +1117,7 @@ default: return fmt.Errorf("invalid union key '%v'", x.Type)} x.ArchArm.GicVersion =3D GicVersion(xc.arch_arm.gic_version) x.ArchArm.Vuart =3D VuartType(xc.arch_arm.vuart) +x.ArchArm.Sve =3D int(xc.arch_arm.sve) if err :=3D x.ArchX86.MsrRelaxed.fromC(&xc.arch_x86.msr_relaxed);err !=3D = nil { return fmt.Errorf("converting field ArchX86.MsrRelaxed: %v", err) } @@ -1602,6 +1603,7 @@ default: return fmt.Errorf("invalid union key '%v'", x.Type)} xc.arch_arm.gic_version =3D C.libxl_gic_version(x.ArchArm.GicVersion) xc.arch_arm.vuart =3D C.libxl_vuart_type(x.ArchArm.Vuart) +xc.arch_arm.sve =3D C.int(x.Sve) if err :=3D x.ArchX86.MsrRelaxed.toC(&xc.arch_x86.msr_relaxed); err !=3D n= il { return fmt.Errorf("converting field ArchX86.MsrRelaxed: %v", err) } diff --git a/tools/golang/xenlight/types.gen.go b/tools/golang/xenlight/typ= es.gen.go index 16ce879e3fb7..ed144325682e 100644 --- a/tools/golang/xenlight/types.gen.go +++ b/tools/golang/xenlight/types.gen.go @@ -537,6 +537,7 @@ TypeUnion DomainBuildInfoTypeUnion ArchArm struct { GicVersion GicVersion Vuart VuartType +Sve uint32 } ArchX86 struct { MsrRelaxed Defbool diff --git a/tools/include/libxl.h b/tools/include/libxl.h index d652895075a0..1057962e2e3f 100644 --- a/tools/include/libxl.h +++ b/tools/include/libxl.h @@ -278,6 +278,11 @@ */ #define LIBXL_HAVE_BUILDINFO_ARCH_ARM_TEE 1 =20 +/* + * libxl_domain_build_info has the arch_arm.sve field. + */ +#define LIBXL_HAVE_BUILDINFO_ARCH_ARM_SVE 1 + /* * LIBXL_HAVE_SOFT_RESET indicates that libxl supports performing * 'soft reset' for domains and there is 'soft_reset' shutdown reason diff --git a/tools/libs/light/libxl_arm.c b/tools/libs/light/libxl_arm.c index ddc7b2a15975..31f30e054bf4 100644 --- a/tools/libs/light/libxl_arm.c +++ b/tools/libs/light/libxl_arm.c @@ -211,6 +211,8 @@ int libxl__arch_domain_prepare_config(libxl__gc *gc, return ERROR_FAIL; } =20 + config->arch.sve_vl_bits =3D d_config->b_info.arch_arm.sve; + return 0; } =20 diff --git a/tools/libs/light/libxl_types.idl b/tools/libs/light/libxl_type= s.idl index 0cfad8508dbd..27e22523c7c2 100644 --- a/tools/libs/light/libxl_types.idl +++ b/tools/libs/light/libxl_types.idl @@ -663,6 +663,7 @@ libxl_domain_build_info =3D Struct("domain_build_info",[ =20 ("arch_arm", Struct(None, [("gic_version", libxl_gic_version), ("vuart", libxl_vuart_type), + ("sve", uint32), ])), ("arch_x86", Struct(None, [("msr_relaxed", libxl_defbool), ])), diff --git a/tools/xl/xl_parse.c b/tools/xl/xl_parse.c index 853e9f357a1a..49b2f28807e5 100644 --- a/tools/xl/xl_parse.c +++ b/tools/xl/xl_parse.c @@ -2828,6 +2828,16 @@ skip_usbdev: } } =20 + if (!xlu_cfg_get_long (config, "sve", &l, 0)) { + if (((l % 128) !=3D 0) || (l > 2048)) { + fprintf(stderr, + "Invalid sve value: %ld. Needs to be <=3D 2048 and mul= tiple" + " of 128\n", l); + exit(-ERROR_FAIL); + } + b_info->arch_arm.sve =3D l; + } + parse_vkb_list(config, d_config); =20 d_config->virtios =3D NULL; --=20 2.17.1 From nobody Mon Apr 29 12:48:51 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) client-ip=192.237.175.120; envelope-from=xen-devel-bounces@lists.xenproject.org; helo=lists.xenproject.org; Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of lists.xenproject.org designates 192.237.175.120 as permitted sender) smtp.mailfrom=xen-devel-bounces@lists.xenproject.org; dmarc=fail(p=none dis=none) header.from=arm.com Return-Path: Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) by mx.zohomail.com with SMTPS id 1673448340014848.4681282796431; Wed, 11 Jan 2023 06:45:40 -0800 (PST) Received: from list by lists.xenproject.org with outflank-mailman.475503.737243 (Exim 4.92) (envelope-from ) id 1pFcLv-0005Rh-R6; Wed, 11 Jan 2023 14:45:19 +0000 Received: by outflank-mailman (output) from mailman id 475503.737243; Wed, 11 Jan 2023 14:45:19 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcLv-0005Ra-Nt; Wed, 11 Jan 2023 14:45:19 +0000 Received: by outflank-mailman (input) for mailman id 475503; Wed, 11 Jan 2023 14:45:19 +0000 Received: from se1-gles-sth1-in.inumbo.com ([159.253.27.254] helo=se1-gles-sth1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1pFcFd-0000FC-FX for xen-devel@lists.xenproject.org; Wed, 11 Jan 2023 14:38:49 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-sth1.inumbo.com (Halon) with ESMTP id a8afd8c2-91bd-11ed-91b6-6bf2151ebd3b; Wed, 11 Jan 2023 15:38:48 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 299D6FEC; Wed, 11 Jan 2023 06:39:30 -0800 (PST) Received: from e125770.cambridge.arm.com (e125770.cambridge.arm.com [10.1.195.16]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 3849D3F71A; Wed, 11 Jan 2023 06:38:47 -0800 (PST) X-Outflank-Mailman: Message body and most headers restored to incoming version X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: a8afd8c2-91bd-11ed-91b6-6bf2151ebd3b From: Luca Fancellu To: xen-devel@lists.xenproject.org Cc: wei.chen@arm.com, Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk Subject: [RFC PATCH 8/8] xen/arm: add sve property for dom0less domUs Date: Wed, 11 Jan 2023 14:38:26 +0000 Message-Id: <20230111143826.3224-9-luca.fancellu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20230111143826.3224-1-luca.fancellu@arm.com> References: <20230111143826.3224-1-luca.fancellu@arm.com> X-ZM-MESSAGEID: 1673448341557100001 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Add a device tree property in the dom0less domU configuration to enable the guest to use SVE. Update documentation. Signed-off-by: Luca Fancellu --- docs/misc/arm/device-tree/booting.txt | 7 +++++++ xen/arch/arm/domain_build.c | 7 +++++++ 2 files changed, 14 insertions(+) diff --git a/docs/misc/arm/device-tree/booting.txt b/docs/misc/arm/device-t= ree/booting.txt index 3879340b5e0a..3d1ce652317e 100644 --- a/docs/misc/arm/device-tree/booting.txt +++ b/docs/misc/arm/device-tree/booting.txt @@ -193,6 +193,13 @@ with the following properties: Optional. Handle to a xen,cpupool device tree node that identifies the cpupool where the guest will be started at boot. =20 +- sve + + Optional. A number that, when above 0, enables SVE for this guest and = sets + its maximum SVE vector length. The default value is 0, that means this + guest is not allowed to use SVE, the maximum value allowed is 2048, any + other value must be multiple of 128. + - xen,enhanced =20 A string property. Possible property values are: diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c index 48c3fdc28063..05b2bfc9195f 100644 --- a/xen/arch/arm/domain_build.c +++ b/xen/arch/arm/domain_build.c @@ -3959,6 +3959,13 @@ void __init create_domUs(void) d_cfg.max_maptrack_frames =3D val; } =20 + if ( dt_property_read_u32(node, "sve", &val) ) + { + if ( val > UINT16_MAX ) + panic("sve property value (%"PRIu32") overflow\n", val); + d_cfg.arch.sve_vl_bits =3D val; + } + /* * The variable max_init_domid is initialized with zero, so here i= t's * very important to use the pre-increment operator to call --=20 2.17.1