From patchwork Thu May 12 14:38:52 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kyle Huey X-Patchwork-Id: 12847801 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6391AC433F5 for ; Thu, 12 May 2022 14:39:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237704AbiELOjA (ORCPT ); Thu, 12 May 2022 10:39:00 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43972 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1355078AbiELOi6 (ORCPT ); Thu, 12 May 2022 10:38:58 -0400 Received: from mail-pf1-x436.google.com (mail-pf1-x436.google.com [IPv6:2607:f8b0:4864:20::436]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7E57CE52A3 for ; Thu, 12 May 2022 07:38:54 -0700 (PDT) Received: by mail-pf1-x436.google.com with SMTP id v11so4972646pff.6 for ; Thu, 12 May 2022 07:38:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kylehuey.com; s=google; h=from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=X563ow73jftQ4W+z+PiKxErhhMubQrl6u1ftt0xf2S0=; b=IIZEift+c0AGCoC1E3YRFIGS0rn0l/IAje9AcP4WCoZZoOJ6x8PDmufYQvHnLNtNu2 F8bMW8LPTD6GZh5Xq7dME44mGMaZu5kUhMDj9UzW6HJXEIY9vekVnkv0DpVMgTzcwZMa RusiuMImzz2iAhLDTkjMAzfyxtiNRx8XI5SLD3c/zrNGo3QuMQoZJVVkN8sppVQC2IQX XloxLFVTeiCEf348kui0beBE0XiwjUsRuvmHhPJ4TUrH6hrHFaX7OFhN+2LCaGm+TUEK znwbNMdBg9HkRqwn1CB1/yfhqyRPEV537RwYIjY72ZFdcKvlhAV6haHZX+O6/kOoao7q ovFQ== 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:mime-version :content-transfer-encoding; bh=X563ow73jftQ4W+z+PiKxErhhMubQrl6u1ftt0xf2S0=; b=QvWS6CMx8iSncXH2nBbDyyI+iBT0qyUNyYljripLGLH/VH4rhyg0TEdQ5TuHbi+ty5 h4fTyJ2n9+nJgES4DoVNIe6/KYSonwUOHVUtd2yTGJMLMSphLvRK68y6kQ0yd1ncfzf2 tb/POX/8TsX/fZEGbr82gjwIgp9FOwqo2LpiL/E//6oZF1OLzHNu1abcrMnkSjRn9Z/O MZG362g1dpOIi9TzV77bnvVLz8/NL8gVszLtsHj2lDoKZqGatZgFPrY7c+bMXdC5z3PP 9AIqRB3nXMx9GbspOfeYOHUnsjfFv5s+DBwT4Xr3aZjT7KE6tGit4tQqAfWPq7yPZhB4 XvIA== X-Gm-Message-State: AOAM532jpCFApR/IGEtTil15efazCt4O2KIbNYapX43whGY690DfZhBm BZ+SVQArMZQZ2YgW9FXYziCPoA== X-Google-Smtp-Source: ABdhPJziqh055XJ8frBiWpVb8lq9HcmQI05bhFvZa3C6uaslhcluEy/hglRPHQdDzwb22ixZcBr4CQ== X-Received: by 2002:a05:6a00:2141:b0:4ca:cc46:20c7 with SMTP id o1-20020a056a00214100b004cacc4620c7mr11764820pfk.44.1652366333921; Thu, 12 May 2022 07:38:53 -0700 (PDT) Received: from minbar.home.kylehuey.com (c-71-198-251-229.hsd1.ca.comcast.net. [71.198.251.229]) by smtp.gmail.com with ESMTPSA id k24-20020a63d858000000b003c14af50610sm2025732pgj.40.2022.05.12.07.38.52 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 12 May 2022 07:38:53 -0700 (PDT) From: Kyle Huey X-Google-Original-From: Kyle Huey To: stable@vger.kernel.org Cc: kvm@vger.kernel.org, x86@kernel.org, Robert O'Callahan , Keno Fischer , Kyle Huey , Paolo Bonzini Subject: [PATCH 5.4] KVM: x86/svm: Account for family 17h event renumberings in amd_pmc_perf_hw_id Date: Thu, 12 May 2022 07:38:52 -0700 Message-Id: <20220512143852.90281-1-khuey@kylehuey.com> X-Mailer: git-send-email 2.36.0 MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org From: Kyle Huey commit 5eb849322d7f7ae9d5c587c7bc3b4f7c6872cd2f upstream Zen renumbered some of the performance counters that correspond to the well known events in perf_hw_id. This code in KVM was never updated for that, so guest that attempt to use counters on Zen that correspond to the pre-Zen perf_hw_id values will silently receive the wrong values. This has been observed in the wild with rr[0] when running in Zen 3 guests. rr uses the retired conditional branch counter 00d1 which is incorrectly recognized by KVM as PERF_COUNT_HW_STALLED_CYCLES_BACKEND. [0] https://rr-project.org/ Signed-off-by: Kyle Huey Message-Id: <20220503050136.86298-1-khuey@kylehuey.com> Cc: stable@vger.kernel.org [Check guest family, not host. - Paolo] Signed-off-by: Paolo Bonzini [Backport to 5.15: adjusted context] Signed-off-by: Kyle Huey --- arch/x86/kvm/pmu_amd.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index f843c6bbcd31..799b9a3144e3 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -44,6 +44,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -128,19 +144,25 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */