From patchwork Fri May 27 18:06:13 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 576536 Delivered-To: patch@linaro.org Received: by 2002:a05:7000:8607:0:0:0:0 with SMTP id bb7csp872281mab; Fri, 27 May 2022 11:17:40 -0700 (PDT) X-Google-Smtp-Source: ABdhPJx0nshlFeuDYUjH8jqNBSF2hqU0f5AZfeiF3OpZzZ4ZP7hRPxOSnJEAYef7bJGkqzj7xPeP X-Received: by 2002:a05:620a:d87:b0:6a5:a699:15fc with SMTP id q7-20020a05620a0d8700b006a5a69915fcmr8635337qkl.224.1653675460170; Fri, 27 May 2022 11:17:40 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1653675460; cv=none; d=google.com; s=arc-20160816; b=xxpm7dhKv9Gyv2Mv1dJw6hH3JDrcKPcL5fzc8UHSYwqDZeg6P0HA31G9NvjBkD6abQ iPEl11Rk+QwEkUty5altgtHb2n0P75XiQlxfJU76nNU2TrApivWVJJKjOBz4fnZSUtNi lvH/pJVCjA7Mm7tlWPArZV3L16jgRTtL5UDP+gxT3nxplunDFLMOLm5fkSJ81TL9a+X4 6dRczd3LUXeJg1z/+q87MuIhqlulbhE+YyDCbpQUrzdppB7aWlxDlc30CKOKeB+AxBpY IChlmXVVDhffFnAkrRP+WGIhQKn2pd/4rONAOCgnk3+9KRtmzpAxOSoqvjjz6lKAxUQK 6XZg== 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:cc:to :from:dkim-signature; bh=gvNRQC8KhINJ3YSuAmDpp0PT7w00RoWpHA0CJJcyrMM=; b=m5GFofbuwlJbI6Rj5N0s9bRO4OuPGv41Iylmuq45lfrVO1UZvC6IeoKUi1iULxCSDq 2f2Y9eDn1neHlBhlwfhzBUD2a23OsiNgjskytJdMY5h9nnhof1pKdL53yvxjFa+I6ATd WrVlVbgb2foh5QcWWtclR/GkyLPJwX5mJfZ+8ivwsTj02hv1dzaYlgwDhpcp7B3v88rG /7JqjSk/7tvZN0GOM/bLBlQXzPsGXVfN179cFcR57XYIKIqeoQEOMbJZQKIZIFVsQ/W9 ZCetj9fzPO3Sj6oEYaret/gNIQePbfKo0Iw4EyJ2YGtstfY7rUJPIMbGkmAWig3TCS+i GvlQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=kKgYIXTD; 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 q22-20020a05620a0d9600b006a5faff6614si95449qkl.341.2022.05.27.11.17.40 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Fri, 27 May 2022 11:17:40 -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=kKgYIXTD; 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]:39676 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1nueWp-0000ri-O3 for patch@linaro.org; Fri, 27 May 2022 14:17:39 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:38936) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1nueMI-0003NA-LX for qemu-devel@nongnu.org; Fri, 27 May 2022 14:06:46 -0400 Received: from mail-pj1-x1030.google.com ([2607:f8b0:4864:20::1030]:41544) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1nueM2-0001dl-Mo for qemu-devel@nongnu.org; Fri, 27 May 2022 14:06:46 -0400 Received: by mail-pj1-x1030.google.com with SMTP id l20-20020a17090a409400b001dd2a9d555bso5031632pjg.0 for ; Fri, 27 May 2022 11:06:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=gvNRQC8KhINJ3YSuAmDpp0PT7w00RoWpHA0CJJcyrMM=; b=kKgYIXTDt8ctekqLOIrD+/dyaNvgL+9EKD0JMTaAWWpN2aMLN7Fyh0oz0rO2pYrMel r3PDt6kIBdhozzrGieDAZOuVmUuwGWQMUwGmTqVUawfsSxHx2hO3ck28Rnk3wwT0seZr gKTfJanW4s5nX1j7WeGS4uoYB3TNOTkjuHzZetytH4r/hovcsv7dXMX97ye7cZ4O1xIk 9w/hUljZ2acnqz1s+jmyFqUUa9rZTJrY3ORn+/VTktqf2gFI4pZpKN6kwuvTAsoYhix8 GM3QI+RUf5Jim+FioIz6QB5ey6d1LUmXo+e8DKOscE628/epSgKUo+EYLep3dhS0PxjF +QwA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=gvNRQC8KhINJ3YSuAmDpp0PT7w00RoWpHA0CJJcyrMM=; b=tbUQW5b9rF2RTw/PbOE01jL4+JIo0RoWXlj1BNwroQZdzu+tcxDgLKlzEsusMt6WiV Akh+hOBMip6vcxZMkgsYgg8BTOChAVcfcSY9vObJm3RTrAJWaBxLrmxHR7Gz5r84J2qt 4gdr1HbFpOvXAUjA0OGUhTG2jfhGw5cgPJz8HfmYqHKqU/xuVVpUIHsv8taijG3UAylS RvNIGQvnyb2ptfmJgTRvQwcHdLtUL7IA/+OBu9UAWTxzLwLqWYw6+GiPQLVPevxcipfs tNfxrBc+PRIQ9DchAekM7tO7w6IjGiBwqJ3xWvEo22SBzOsDxXJIz7uYbWWvqH5AaiLI xRSg== X-Gm-Message-State: AOAM530ZQ+iYsgDcAvLggIEYya2F+gvdKeX5lYpgNIRQMAbNiqjYwScI GY2iJz5pcV6R2Ym8DkxKPR8rHE1/3hULqw== X-Received: by 2002:a17:90a:6b41:b0:1e0:e082:14c7 with SMTP id x1-20020a17090a6b4100b001e0e08214c7mr9422100pjl.92.1653674789119; Fri, 27 May 2022 11:06:29 -0700 (PDT) Received: from stoup.. (174-21-71-225.tukw.qwest.net. [174.21.71.225]) by smtp.gmail.com with ESMTPSA id e10-20020a170902cf4a00b001618fee3900sm3934492plg.196.2022.05.27.11.06.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 27 May 2022 11:06:28 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org, Peter Maydell Subject: [PATCH v3 05/15] target/arm: Use uint32_t instead of bitmap for sve vq's Date: Fri, 27 May 2022 11:06:13 -0700 Message-Id: <20220527180623.185261-6-richard.henderson@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220527180623.185261-1-richard.henderson@linaro.org> References: <20220527180623.185261-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::1030; envelope-from=richard.henderson@linaro.org; helo=mail-pj1-x1030.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, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=unavailable 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" 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 --- 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 69e71fdcec..a86e8d6548 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 199d1bf630..b587901be1 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -1299,4 +1299,9 @@ void aa32_max_features(ARMCPU *cpu); bool arm_singlestep_active(CPUARMState *env); bool arm_generate_debug_exceptions(CPUARMState *env, int cur_el); +/* 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 b7f78b5215..99017b635c 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 3ff9219ca3..51c5d8d4bc 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) @@ -978,7 +974,7 @@ 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); @@ -1025,12 +1021,11 @@ 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 66036c85d7..93784cb073 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -6223,7 +6223,6 @@ 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 && (arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) { @@ -6236,12 +6235,8 @@ 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 363032da90..b3f635fc95 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, ®); }