From patchwork Thu Jun 9 09:05:28 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 580271 Delivered-To: patch@linaro.org Received: by 2002:a05:7000:5806:0:0:0:0 with SMTP id j6csp644175max; Thu, 9 Jun 2022 03:32:31 -0700 (PDT) X-Google-Smtp-Source: ABdhPJwGh3OPtY0XrHGySAZCWe0BlGZ6MrqwslSF+S5SbZhnbPRR/2AOh5VY0maLVwk1yqWXv79K X-Received: by 2002:ac8:7f52:0:b0:305:8c5:2f5d with SMTP id g18-20020ac87f52000000b0030508c52f5dmr4387310qtk.577.1654770751287; Thu, 09 Jun 2022 03:32:31 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1654770751; cv=none; d=google.com; s=arc-20160816; b=xGeuUCTE3ey9Su430pXvV55f89RaXO0tgf+RAJXf4aYG2LfvKfUfZCRdf9QMTSw0+2 4ZvHTdGXmQJBegqqBdVd73DwSxnsjDSkc+0Aano0xJTp5UXj5XDGL0+gEhGW2qCpDpwa Px0+JHUm4C9IHJ2lWE0o03Me4QmVGcykL7ekWRlO70CL0ntz6ZVUEV/T6VR1UalF7KoF CrMUFSry/PO1pSnY8jjmzBL2LoW38vhkL2fDd7T6Upe6+swPj2ko5OW5dHt3YmRBzf92 XxljL4Q7fQH37ezxFo7h4ju9hzm6pRNMzE43g+EWVV4BrrQWvW3aABDszRzGy3uwm/Mu ouZg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=RzISLAIsm/HQUCbU5drdl/7AuVQMoSI54OKREy/L1no=; b=UCI/ixwM/2Y5DRW3YB3Q2O5zN2MCTR44yH7QQlKNScZ1C2iSUElVXaaZgh3Pnr7EuW sIrGwYD+zw0IyneKk72kLYu6xvBuMgb3gxxzzk+KimGOMIl99l94Itd78v6a/9c0aPaM TfWJV46ruvP66ZMArA3y5HuIpb0c+ni1kq9kHSuJK2hiBtPQaaSyH4xhpuRknQZ0nN5T D5qPHnjX3WVrM7f2iUw6Vx6PiqpCOK2sDGkqSLCQ1uy2cS0Mw/kw/GFxORdHdqrBg2X1 qScVU6A53Oo8YP6ckSZ0K2+f9jbsN0ZcAWb2dmgHKRDbVxuT5GQr7lUxsuCiGti6VYDG U3aA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=pdT8R7UO; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d6-20020a05622a05c600b00300c8625c9asi12873374qtb.238.2022.06.09.03.32.31 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Thu, 09 Jun 2022 03:32:31 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=pdT8R7UO; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:43426 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1nzFSo-0007C6-Pq for patch@linaro.org; Thu, 09 Jun 2022 06:32:30 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:39980) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1nzE7d-0001hH-UD for qemu-devel@nongnu.org; Thu, 09 Jun 2022 05:06:34 -0400 Received: from mail-wm1-x32c.google.com ([2a00:1450:4864:20::32c]:51017) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1nzE7a-00068f-K9 for qemu-devel@nongnu.org; Thu, 09 Jun 2022 05:06:32 -0400 Received: by mail-wm1-x32c.google.com with SMTP id e5so5272909wma.0 for ; Thu, 09 Jun 2022 02:06:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references:mime-version :content-transfer-encoding; bh=RzISLAIsm/HQUCbU5drdl/7AuVQMoSI54OKREy/L1no=; b=pdT8R7UOBjH98ntFTJOA7FaJDD6BEFL5G79O1tegmwEz6IqpA2E4Oiiry7DFGrsTwA QH8dPxU6xbWjiG6+HZUsTqUr7xGMjng9pUbU+VHramWqxsD+S6rsLBOTkVNGiVLCPNCJ kg/Us/yjM7z5zBNyVLk+9fmqllesCGQdCKytrFeh5rMFZhAHi4fevbAE+ygjAOlXmarU xE2wI+lfTnUcVZ2rkJRE6kuP3QvAPPBhGC6tJpKWLOd6Jv1Af/gJVFjHt5sNMPfY80tr ma8kyagHy6kAh9mprQ0k4oWW3JQyJtx0FVZQ2Y57hCgjreB7CRpTr8fmYD0i/6k7A0Qm TIQQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=RzISLAIsm/HQUCbU5drdl/7AuVQMoSI54OKREy/L1no=; b=W13HTntDtOrrFRpKWGX/NOm9eGA5oWrRkclJ3ScCu6DM+RWBrQB8lUj3OYorodrsEC Jr6ADiEgBklqzd38ZYze/jTlJlLGSqdNAmUPKixRUZIP4tzvk8AX2DdRAQHgQGteUvLM Dg+J4HD9iUPtrnpz3M9dm1VTqsz6Wkd2pGkt7hOFtwWuW9MMdqLeOTME0Tnnb24DtEHt Clg2du58sjc4Dm9BJAjeMPGoOiFiE6Wa86hZnFUNwi84wZoBbnmQKsqfVrIA9qzyKH80 /VWHBZ+OmPkKh+nGMRP0MfZcmpWDuqpRuu3h4t3cx/+JSV3Z9auqXlKOdiduUT/rdGud +5Uw== X-Gm-Message-State: AOAM532LKONF2qITHCZZHlJOExbR1frzRjBCo0bgVzCu8HEZLxbayeez qLvfO7XlsBT5aBsZNkYa1rVlB3//NnZMgg== X-Received: by 2002:a1c:4682:0:b0:39c:4459:6a84 with SMTP id t124-20020a1c4682000000b0039c44596a84mr2213102wma.167.1654765589048; Thu, 09 Jun 2022 02:06:29 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id c13-20020adffb0d000000b002183cf9cd69sm11349796wrr.15.2022.06.09.02.06.27 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 09 Jun 2022 02:06:28 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 46/55] target/arm: Use uint32_t instead of bitmap for sve vq's Date: Thu, 9 Jun 2022 10:05:28 +0100 Message-Id: <20220609090537.1971756-47-peter.maydell@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220609090537.1971756-1-peter.maydell@linaro.org> References: <20220609090537.1971756-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::32c; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x32c.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" From: Richard Henderson The bitmap need only hold 15 bits; bitmap is over-complicated. We can simplify operations quite a bit with plain logical ops. The introduction of SVE_VQ_POW2_MAP eliminates the need for looping in order to search for powers of two. Simply perform the logical ops and use count leading or trailing zeros as required to find the result. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20220607203306.657998-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/cpu.h | 6 +-- target/arm/internals.h | 5 ++ target/arm/kvm_arm.h | 7 ++- target/arm/cpu64.c | 117 ++++++++++++++++++++--------------------- target/arm/helper.c | 9 +--- target/arm/kvm64.c | 36 +++---------- 6 files changed, 75 insertions(+), 105 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index f5af88b686d..73f24a57603 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -1041,9 +1041,9 @@ struct ArchCPU { * Bits set in sve_vq_supported represent valid vector lengths for * the CPU type. */ - DECLARE_BITMAP(sve_vq_map, ARM_MAX_VQ); - DECLARE_BITMAP(sve_vq_init, ARM_MAX_VQ); - DECLARE_BITMAP(sve_vq_supported, ARM_MAX_VQ); + uint32_t sve_vq_map; + uint32_t sve_vq_init; + uint32_t sve_vq_supported; /* Generic timer counter frequency, in Hz */ uint64_t gt_cntfrq_hz; diff --git a/target/arm/internals.h b/target/arm/internals.h index 79eb4637538..a1bae4588ae 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -1340,4 +1340,9 @@ bool el_is_in_host(CPUARMState *env, int el); void aa32_max_features(ARMCPU *cpu); +/* Powers of 2 for sve_vq_map et al. */ +#define SVE_VQ_POW2_MAP \ + ((1 << (1 - 1)) | (1 << (2 - 1)) | \ + (1 << (4 - 1)) | (1 << (8 - 1)) | (1 << (16 - 1))) + #endif diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index b7f78b52154..99017b635ce 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -239,13 +239,12 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf); /** * kvm_arm_sve_get_vls: * @cs: CPUState - * @map: bitmap to fill in * * Get all the SVE vector lengths supported by the KVM host, setting * the bits corresponding to their length in quadwords minus one - * (vq - 1) in @map up to ARM_MAX_VQ. + * (vq - 1) up to ARM_MAX_VQ. Return the resulting map. */ -void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map); +uint32_t kvm_arm_sve_get_vls(CPUState *cs); /** * kvm_arm_set_cpu_features_from_host: @@ -439,7 +438,7 @@ static inline void kvm_arm_steal_time_finalize(ARMCPU *cpu, Error **errp) g_assert_not_reached(); } -static inline void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) +static inline uint32_t kvm_arm_sve_get_vls(CPUState *cs) { g_assert_not_reached(); } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index cce68dd82a2..15665c962b2 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -355,8 +355,11 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * any of the above. Finally, if SVE is not disabled, then at least one * vector length must be enabled. */ - DECLARE_BITMAP(tmp, ARM_MAX_VQ); - uint32_t vq, max_vq = 0; + uint32_t vq_map = cpu->sve_vq_map; + uint32_t vq_init = cpu->sve_vq_init; + uint32_t vq_supported; + uint32_t vq_mask = 0; + uint32_t tmp, vq, max_vq = 0; /* * CPU models specify a set of supported vector lengths which are @@ -364,10 +367,16 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * in the supported bitmap results in an error. When KVM is enabled we * fetch the supported bitmap from the host. */ - if (kvm_enabled() && kvm_arm_sve_supported()) { - kvm_arm_sve_get_vls(CPU(cpu), cpu->sve_vq_supported); - } else if (kvm_enabled()) { - assert(!cpu_isar_feature(aa64_sve, cpu)); + if (kvm_enabled()) { + if (kvm_arm_sve_supported()) { + cpu->sve_vq_supported = kvm_arm_sve_get_vls(CPU(cpu)); + vq_supported = cpu->sve_vq_supported; + } else { + assert(!cpu_isar_feature(aa64_sve, cpu)); + vq_supported = 0; + } + } else { + vq_supported = cpu->sve_vq_supported; } /* @@ -375,8 +384,9 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * From the properties, sve_vq_map implies sve_vq_init. * Check first for any sve enabled. */ - if (!bitmap_empty(cpu->sve_vq_map, ARM_MAX_VQ)) { - max_vq = find_last_bit(cpu->sve_vq_map, ARM_MAX_VQ) + 1; + if (vq_map != 0) { + max_vq = 32 - clz32(vq_map); + vq_mask = MAKE_64BIT_MASK(0, max_vq); if (cpu->sve_max_vq && max_vq > cpu->sve_max_vq) { error_setg(errp, "cannot enable sve%d", max_vq * 128); @@ -392,15 +402,10 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * For KVM we have to automatically enable all supported unitialized * lengths, even when the smaller lengths are not all powers-of-two. */ - bitmap_andnot(tmp, cpu->sve_vq_supported, cpu->sve_vq_init, max_vq); - bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq); + vq_map |= vq_supported & ~vq_init & vq_mask; } else { /* Propagate enabled bits down through required powers-of-two. */ - for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { - if (!test_bit(vq - 1, cpu->sve_vq_init)) { - set_bit(vq - 1, cpu->sve_vq_map); - } - } + vq_map |= SVE_VQ_POW2_MAP & ~vq_init & vq_mask; } } else if (cpu->sve_max_vq == 0) { /* @@ -413,25 +418,18 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) if (kvm_enabled()) { /* Disabling a supported length disables all larger lengths. */ - for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { - if (test_bit(vq - 1, cpu->sve_vq_init) && - test_bit(vq - 1, cpu->sve_vq_supported)) { - break; - } - } + tmp = vq_init & vq_supported; } else { /* Disabling a power-of-two disables all larger lengths. */ - for (vq = 1; vq <= ARM_MAX_VQ; vq <<= 1) { - if (test_bit(vq - 1, cpu->sve_vq_init)) { - break; - } - } + tmp = vq_init & SVE_VQ_POW2_MAP; } + vq = ctz32(tmp) + 1; max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; - bitmap_andnot(cpu->sve_vq_map, cpu->sve_vq_supported, - cpu->sve_vq_init, max_vq); - if (max_vq == 0 || bitmap_empty(cpu->sve_vq_map, max_vq)) { + vq_mask = MAKE_64BIT_MASK(0, max_vq); + vq_map = vq_supported & ~vq_init & vq_mask; + + if (max_vq == 0 || vq_map == 0) { error_setg(errp, "cannot disable sve%d", vq * 128); error_append_hint(errp, "Disabling sve%d results in all " "vector lengths being disabled.\n", @@ -441,7 +439,8 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) return; } - max_vq = find_last_bit(cpu->sve_vq_map, max_vq) + 1; + max_vq = 32 - clz32(vq_map); + vq_mask = MAKE_64BIT_MASK(0, max_vq); } /* @@ -451,9 +450,9 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) */ if (cpu->sve_max_vq != 0) { max_vq = cpu->sve_max_vq; + vq_mask = MAKE_64BIT_MASK(0, max_vq); - if (!test_bit(max_vq - 1, cpu->sve_vq_map) && - test_bit(max_vq - 1, cpu->sve_vq_init)) { + if (vq_init & ~vq_map & (1 << (max_vq - 1))) { error_setg(errp, "cannot disable sve%d", max_vq * 128); error_append_hint(errp, "The maximum vector length must be " "enabled, sve-max-vq=%d (%d bits)\n", @@ -462,8 +461,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) } /* Set all bits not explicitly set within sve-max-vq. */ - bitmap_complement(tmp, cpu->sve_vq_init, max_vq); - bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq); + vq_map |= ~vq_init & vq_mask; } /* @@ -472,13 +470,14 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * are clear, just in case anybody looks. */ assert(max_vq != 0); - bitmap_clear(cpu->sve_vq_map, max_vq, ARM_MAX_VQ - max_vq); + assert(vq_mask != 0); + vq_map &= vq_mask; /* Ensure the set of lengths matches what is supported. */ - bitmap_xor(tmp, cpu->sve_vq_map, cpu->sve_vq_supported, max_vq); - if (!bitmap_empty(tmp, max_vq)) { - vq = find_last_bit(tmp, max_vq) + 1; - if (test_bit(vq - 1, cpu->sve_vq_map)) { + tmp = vq_map ^ (vq_supported & vq_mask); + if (tmp) { + vq = 32 - clz32(tmp); + if (vq_map & (1 << (vq - 1))) { if (cpu->sve_max_vq) { error_setg(errp, "cannot set sve-max-vq=%d", cpu->sve_max_vq); error_append_hint(errp, "This CPU does not support " @@ -502,15 +501,15 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) return; } else { /* Ensure all required powers-of-two are enabled. */ - for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { - if (!test_bit(vq - 1, cpu->sve_vq_map)) { - error_setg(errp, "cannot disable sve%d", vq * 128); - error_append_hint(errp, "sve%d is required as it " - "is a power-of-two length smaller " - "than the maximum, sve%d\n", - vq * 128, max_vq * 128); - return; - } + tmp = SVE_VQ_POW2_MAP & vq_mask & ~vq_map; + if (tmp) { + vq = 32 - clz32(tmp); + error_setg(errp, "cannot disable sve%d", vq * 128); + error_append_hint(errp, "sve%d is required as it " + "is a power-of-two length smaller " + "than the maximum, sve%d\n", + vq * 128, max_vq * 128); + return; } } } @@ -530,6 +529,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) /* From now on sve_max_vq is the actual maximum supported length. */ cpu->sve_max_vq = max_vq; + cpu->sve_vq_map = vq_map; } static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name, @@ -590,7 +590,7 @@ static void cpu_arm_get_sve_vq(Object *obj, Visitor *v, const char *name, if (!cpu_isar_feature(aa64_sve, cpu)) { value = false; } else { - value = test_bit(vq - 1, cpu->sve_vq_map); + value = extract32(cpu->sve_vq_map, vq - 1, 1); } visit_type_bool(v, name, &value, errp); } @@ -612,12 +612,8 @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name, return; } - if (value) { - set_bit(vq - 1, cpu->sve_vq_map); - } else { - clear_bit(vq - 1, cpu->sve_vq_map); - } - set_bit(vq - 1, cpu->sve_vq_init); + cpu->sve_vq_map = deposit32(cpu->sve_vq_map, vq - 1, 1, value); + cpu->sve_vq_init |= 1 << (vq - 1); } static bool cpu_arm_get_sve(Object *obj, Error **errp) @@ -979,7 +975,7 @@ static void aarch64_max_initfn(Object *obj) cpu->dcz_blocksize = 7; /* 512 bytes */ #endif - bitmap_fill(cpu->sve_vq_supported, ARM_MAX_VQ); + cpu->sve_vq_supported = MAKE_64BIT_MASK(0, ARM_MAX_VQ); aarch64_add_pauth_properties(obj); aarch64_add_sve_properties(obj); @@ -1026,12 +1022,11 @@ static void aarch64_a64fx_initfn(Object *obj) cpu->gic_vprebits = 5; cpu->gic_pribits = 5; - /* Suppport of A64FX's vector length are 128,256 and 512bit only */ + /* The A64FX supports only 128, 256 and 512 bit vector lengths */ aarch64_add_sve_properties(obj); - bitmap_zero(cpu->sve_vq_supported, ARM_MAX_VQ); - set_bit(0, cpu->sve_vq_supported); /* 128bit */ - set_bit(1, cpu->sve_vq_supported); /* 256bit */ - set_bit(3, cpu->sve_vq_supported); /* 512bit */ + cpu->sve_vq_supported = (1 << 0) /* 128bit */ + | (1 << 1) /* 256bit */ + | (1 << 3); /* 512bit */ cpu->isar.reset_pmcr_el0 = 0x46014040; diff --git a/target/arm/helper.c b/target/arm/helper.c index de159c644cd..90aac6bc12d 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -6219,7 +6219,6 @@ uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) { ARMCPU *cpu = env_archcpu(env); uint32_t len = cpu->sve_max_vq - 1; - uint32_t end_len; if (el <= 1 && !el_is_in_host(env, el)) { len = MIN(len, 0xf & (uint32_t)env->vfp.zcr_el[1]); @@ -6231,12 +6230,8 @@ uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) len = MIN(len, 0xf & (uint32_t)env->vfp.zcr_el[3]); } - end_len = len; - if (!test_bit(len, cpu->sve_vq_map)) { - end_len = find_last_bit(cpu->sve_vq_map, len); - assert(end_len < len); - } - return end_len; + len = 31 - clz32(cpu->sve_vq_map & MAKE_64BIT_MASK(0, len + 1)); + return len; } static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index 363032da903..b3f635fc952 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -760,15 +760,13 @@ bool kvm_arm_steal_time_supported(void) QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1); -void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) +uint32_t kvm_arm_sve_get_vls(CPUState *cs) { /* Only call this function if kvm_arm_sve_supported() returns true. */ static uint64_t vls[KVM_ARM64_SVE_VLS_WORDS]; static bool probed; uint32_t vq = 0; - int i, j; - - bitmap_zero(map, ARM_MAX_VQ); + int i; /* * KVM ensures all host CPUs support the same set of vector lengths. @@ -809,46 +807,24 @@ void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) if (vq > ARM_MAX_VQ) { warn_report("KVM supports vector lengths larger than " "QEMU can enable"); + vls[0] &= MAKE_64BIT_MASK(0, ARM_MAX_VQ); } } - for (i = 0; i < KVM_ARM64_SVE_VLS_WORDS; ++i) { - if (!vls[i]) { - continue; - } - for (j = 1; j <= 64; ++j) { - vq = j + i * 64; - if (vq > ARM_MAX_VQ) { - return; - } - if (vls[i] & (1UL << (j - 1))) { - set_bit(vq - 1, map); - } - } - } + return vls[0]; } static int kvm_arm_sve_set_vls(CPUState *cs) { - uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = {0}; + ARMCPU *cpu = ARM_CPU(cs); + uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = { cpu->sve_vq_map }; struct kvm_one_reg reg = { .id = KVM_REG_ARM64_SVE_VLS, .addr = (uint64_t)&vls[0], }; - ARMCPU *cpu = ARM_CPU(cs); - uint32_t vq; - int i, j; assert(cpu->sve_max_vq <= KVM_ARM64_SVE_VQ_MAX); - for (vq = 1; vq <= cpu->sve_max_vq; ++vq) { - if (test_bit(vq - 1, cpu->sve_vq_map)) { - i = (vq - 1) / 64; - j = (vq - 1) % 64; - vls[i] |= 1UL << j; - } - } - return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); }