From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sean Christopherson Date: Wed, 2 Nov 2022 23:19:04 +0000 Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> References: <20221102231911.3107438-1-seanjc@google.com> Message-ID: <20221102231911.3107438-38-seanjc@google.com> List-Id: To: kvm-riscv@lists.infradead.org MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog From mboxrd@z Thu Jan 1 00:00:00 1970 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 mm01.cs.columbia.edu (mm01.cs.columbia.edu [128.59.11.253]) by smtp.lore.kernel.org (Postfix) with ESMTP id 54635C433FE for ; Wed, 2 Nov 2022 23:20:28 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by mm01.cs.columbia.edu (Postfix) with ESMTP id 021F74B863; Wed, 2 Nov 2022 19:20:28 -0400 (EDT) X-Virus-Scanned: at lists.cs.columbia.edu Authentication-Results: mm01.cs.columbia.edu (amavisd-new); dkim=softfail (fail, message has been altered) header.i=@google.com Received: from mm01.cs.columbia.edu ([127.0.0.1]) by localhost (mm01.cs.columbia.edu [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id buH69c8BNz2P; Wed, 2 Nov 2022 19:20:26 -0400 (EDT) Received: from mm01.cs.columbia.edu (localhost [127.0.0.1]) by mm01.cs.columbia.edu (Postfix) with ESMTP id BBC514B88E; Wed, 2 Nov 2022 19:20:23 -0400 (EDT) Received: from localhost (localhost [127.0.0.1]) by mm01.cs.columbia.edu (Postfix) with ESMTP id 0EF214B881 for ; Wed, 2 Nov 2022 19:20:22 -0400 (EDT) X-Virus-Scanned: at lists.cs.columbia.edu Received: from mm01.cs.columbia.edu ([127.0.0.1]) by localhost (mm01.cs.columbia.edu [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id c4rWauh0bnOl for ; Wed, 2 Nov 2022 19:20:20 -0400 (EDT) Received: from mail-pl1-f201.google.com (mail-pl1-f201.google.com [209.85.214.201]) by mm01.cs.columbia.edu (Postfix) with ESMTPS id 68E924B6DD for ; Wed, 2 Nov 2022 19:20:18 -0400 (EDT) Received: by mail-pl1-f201.google.com with SMTP id l1-20020a170902f68100b00187117d8e44so243707plg.2 for ; Wed, 02 Nov 2022 16:20:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:from:to:cc:subject:date:message-id:reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=P098Tzj2rpCJt/4nT8TrXTmUFPSgbhycgPry+JJrhxDuao4X1xtJJMmkpRB4trEL+1 55zpGfmzGI5TBm87M6Zs05xZAzJVQeNB6vBpk6WWQfA3tICCm87E6sO59+ssVnP2DMV3 hznDyqUbjHe4LGoM3DU21pBPc947dC5uIYbWgsImqI8pmwnLywsM+KMu/sYgtS/f8Vg6 ulJ7edDhRMBnHlx6lfmMwV1MS6wrSEBngjldBD8LoOWj74JJvfznExcwtcTban7qi7hz //M7aBh24hO/B6RinKg6thqufqaedpAYEyt0W7Am9UJmOQXk6WzZPIZJVcSMq0UtYuH2 blnQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=6clbi6InnI5LYCldIKHkS1RlkOE6Iaz5RjT9aiAGwqIQlAePY/kWGOE2mWOEFdhsvV Q7WbNSeMQjBE5E2RwtLBzRkjL9jCOxxBaw+xDf967jB6sqY9MDqPMtjXgNUrXqnSz5IU LFVA5fbfDFgmrdWjN1xd01vO1f8ufb45qrtnj4x5IOZuDjLgHhXOhnkSATFEF697AGTP HMr1eTQjHuZL0zjJmTauc18ObYuQ+C+FA4tkYeeszlCqH+Jd9G6kMlLCwIqViq4Rv6uC D8nRLPJwYswnfQiu+HyjFkvR/ovYRucgQrjVMTwTpTdhYs33MkmtDbd0thGWofEYLX25 8vig== X-Gm-Message-State: ACrzQf1rvurnkt5lagDneP8zIKW4KnH+0b5pvSkRzllSgAEV9amGvbAE +aY7OY8/G03afzAhPUJ3RXFLgYG6MeE= X-Google-Smtp-Source: AMsMyM5ohXm4oyR4jft0wXrIcDwmrJUMZ0my1jgH1DEVPjOvKwP7xekYGMEgfn4JBdiC2vhG8AasDNojAdM= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a62:8141:0:b0:56b:c435:f003 with SMTP id t62-20020a628141000000b0056bc435f003mr27425626pfd.15.1667431217428; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) Date: Wed, 2 Nov 2022 23:19:04 +0000 In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> Mime-Version: 1.0 References: <20221102231911.3107438-1-seanjc@google.com> X-Mailer: git-send-email 2.38.1.431.g37b22c650d-goog Message-ID: <20221102231911.3107438-38-seanjc@google.com> Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section From: Sean Christopherson To: Paolo Bonzini , Marc Zyngier , Huacai Chen , Aleksandar Markovic , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Christian Borntraeger , Janosch Frank , Claudio Imbrenda , Matthew Rosato , Eric Farman , Sean Christopherson , Vitaly Kuznetsov Cc: kvm@vger.kernel.org, David Hildenbrand , Atish Patra , linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org, kvmarm@lists.cs.columbia.edu, linux-s390@vger.kernel.org, Michael Ellerman , Chao Gao , Yuan Yao , kvmarm@lists.linux.dev, Thomas Gleixner , linux-arm-kernel@lists.infradead.org, Isaku Yamahata , Fabiano Rosas , linux-mips@vger.kernel.org, kvm-riscv@lists.infradead.org, linuxppc-dev@lists.ozlabs.org X-BeenThere: kvmarm@lists.cs.columbia.edu X-Mailman-Version: 2.1.14 Precedence: list Reply-To: Sean Christopherson List-Id: Where KVM/ARM decisions are made List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: kvmarm-bounces@lists.cs.columbia.edu Sender: kvmarm-bounces@lists.cs.columbia.edu From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog _______________________________________________ kvmarm mailing list kvmarm@lists.cs.columbia.edu https://lists.cs.columbia.edu/mailman/listinfo/kvmarm From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-pf1-f201.google.com (mail-pf1-f201.google.com [209.85.210.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EF7A324F21 for ; Wed, 2 Nov 2022 23:20:17 +0000 (UTC) Received: by mail-pf1-f201.google.com with SMTP id cw4-20020a056a00450400b00561ec04e77aso9422pfb.12 for ; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:from:to:cc:subject:date:message-id:reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=P098Tzj2rpCJt/4nT8TrXTmUFPSgbhycgPry+JJrhxDuao4X1xtJJMmkpRB4trEL+1 55zpGfmzGI5TBm87M6Zs05xZAzJVQeNB6vBpk6WWQfA3tICCm87E6sO59+ssVnP2DMV3 hznDyqUbjHe4LGoM3DU21pBPc947dC5uIYbWgsImqI8pmwnLywsM+KMu/sYgtS/f8Vg6 ulJ7edDhRMBnHlx6lfmMwV1MS6wrSEBngjldBD8LoOWj74JJvfznExcwtcTban7qi7hz //M7aBh24hO/B6RinKg6thqufqaedpAYEyt0W7Am9UJmOQXk6WzZPIZJVcSMq0UtYuH2 blnQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=hQ3dfBYUSxKqOn6RjTCLmMx3ePVvMO1Px826fUardxShQC7Bf3InuoQerhafuKqLCo rePJpVvHjTVubIs4+Mu5aktSVsV7C9lc+f9peWb9U6BbnkgxgWItyz9Wxl7rsrocTgYs CjKCKUWwyQogGPFyzD4hhVbZQvWSD8NK9NZMLYzuk5cJ+HiFI++s1NYONPsYtLELHMxv 98QfvUaVTcQJWPhb+IKrSbYnUL+8se2orDmLImwlXfkIpi6lIr8mvpto5W8E/5yywTzf pdNWnxQx09W+hy9TXo003POk0GkJgSk8YBR16a5mP5kDxiXkn3qsSODREJDDYZHRnVBv homQ== X-Gm-Message-State: ACrzQf3XIZLfeWxn238s3RG6Bhk90oA2eLi4o0dAXKsRswva+FuaEfwg CPaBLdk4/PHC+6okobTDI2LUS4KPNig= X-Google-Smtp-Source: AMsMyM5ohXm4oyR4jft0wXrIcDwmrJUMZ0my1jgH1DEVPjOvKwP7xekYGMEgfn4JBdiC2vhG8AasDNojAdM= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a62:8141:0:b0:56b:c435:f003 with SMTP id t62-20020a628141000000b0056bc435f003mr27425626pfd.15.1667431217428; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) Reply-To: Sean Christopherson Date: Wed, 2 Nov 2022 23:19:04 +0000 In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> Precedence: bulk X-Mailing-List: kvmarm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20221102231911.3107438-1-seanjc@google.com> X-Mailer: git-send-email 2.38.1.431.g37b22c650d-goog Message-ID: <20221102231911.3107438-38-seanjc@google.com> Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section From: Sean Christopherson To: Paolo Bonzini , Marc Zyngier , Huacai Chen , Aleksandar Markovic , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Christian Borntraeger , Janosch Frank , Claudio Imbrenda , Matthew Rosato , Eric Farman , Sean Christopherson , Vitaly Kuznetsov Cc: James Morse , Alexandru Elisei , Suzuki K Poulose , Oliver Upton , Atish Patra , David Hildenbrand , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, kvmarm@lists.cs.columbia.edu, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org, Isaku Yamahata , Fabiano Rosas , Michael Ellerman , Chao Gao , Thomas Gleixner , Yuan Yao Content-Type: text/plain; charset="UTF-8" Message-ID: <20221102231904.7Ne1fOJRi7suVosDw86aDVTbqJdetOnlbY6wbNcV2HQ@z> From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog From mboxrd@z Thu Jan 1 00:00:00 1970 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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id A7FC3C4332F for ; Wed, 2 Nov 2022 23:42:21 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:Reply-To:List-Subscribe:List-Help: List-Post:List-Archive:List-Unsubscribe:List-Id:Cc:To:From:Subject:Message-ID :References:Mime-Version:In-Reply-To:Date:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=LAI9Qc/u1uz7MnH+WYgHpGch/Av1OLgfz9dAXM2jIxc=; b=IN/IzrM5rhP6eQ M8rEDAAnqWwiwrf32pUf6MYRfGtVwHxWm12mNd5FNNo5bKKKHR7UX6VoNrZaOUOY0+wIQHtLa234z Mg8eOW3v3Kin4mq9lWfRuWXWx1xeoAV5ihnOsg9w8n+XHS6iedBMs6rMJ4tHZ8yQaN45svl+Lkv3u 1k/ogeXMXqv5g47Abv/Y4ckabvOvzvCV3d60mR64ox2g8WrtAZMZM6d5O/OfOpSAfjvbngDepDwC2 vV+BGbcXrlALFIAsWbcWUBUHuKfqznwhq2Yaw7TVVpBMQG5cTG9UkxtynQWMawXRnhLmfjAyaEdQ3 AoBjQ01qVJaffIwehxng==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqNN5-00F5Xt-EA; Wed, 02 Nov 2022 23:42:11 +0000 Received: from casper.infradead.org ([2001:8b0:10b:1236::1]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqNGV-00F1m3-5t for linux-riscv@bombadil.infradead.org; Wed, 02 Nov 2022 23:35:23 +0000 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Type:Cc:To:From:Subject: Message-ID:References:Mime-Version:In-Reply-To:Date:Reply-To:Sender: Content-Transfer-Encoding:Content-ID:Content-Description; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=k0f5NcaejmRXfEXLIIr29cMr9K LP6MLpgWdIZfD/t8Ma/f1095Oytr7plShbFIuFXADIP3y7lazJjKTTg3m+t5mWBhGzgeBST7i9Tjx /5EczjKyzp0/qPRU/ovkyjqBOlppNMGpMyVexxqe6H/Rz3tYjYwGKbV51yHfARgCw5ZjXeXEf5tOO tIHt+e8uvndtc3lDKbshUPBxglkUvQ8BEhbtibcJOxyqHbhK8Qz5EJcX6/EsQ/SWkN2HcE53tijhk r3PPRHEt2Pvho54ct02mUYuZHY2WHe/ZH3jQaBGjZRCSY70kXLyX2OpIppEkZXu3xrytu25+8GDpm iUJOI6Tg==; Received: from mail-pf1-x449.google.com ([2607:f8b0:4864:20::449]) by casper.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqN20-005vw5-Hm for linux-riscv@lists.infradead.org; Wed, 02 Nov 2022 23:20:27 +0000 Received: by mail-pf1-x449.google.com with SMTP id z19-20020a056a001d9300b0056df4b6f421so15516pfw.4 for ; Wed, 02 Nov 2022 16:20:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:from:to:cc:subject:date:message-id:reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=P098Tzj2rpCJt/4nT8TrXTmUFPSgbhycgPry+JJrhxDuao4X1xtJJMmkpRB4trEL+1 55zpGfmzGI5TBm87M6Zs05xZAzJVQeNB6vBpk6WWQfA3tICCm87E6sO59+ssVnP2DMV3 hznDyqUbjHe4LGoM3DU21pBPc947dC5uIYbWgsImqI8pmwnLywsM+KMu/sYgtS/f8Vg6 ulJ7edDhRMBnHlx6lfmMwV1MS6wrSEBngjldBD8LoOWj74JJvfznExcwtcTban7qi7hz //M7aBh24hO/B6RinKg6thqufqaedpAYEyt0W7Am9UJmOQXk6WzZPIZJVcSMq0UtYuH2 blnQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=l0+criJIq/9voKy25c3oHX2K/8oKkuHbAhWxMXcmV9Q80J9LRtDQyjAdJE2YbZxwoN dHeLbpLch4ih8yYpDDeQVYN8ke9qVz8g8KHqQyBQYO1PHTKsjf1PmPNvDOfqABrfzoBc GDGAQRqwwhNEm3GePEX9fpvgQcs6iNQi9qHgsnwf1EIoiIXEvfDDW/SbM5yqy2MmoWHt PCJrySMrjzBi9NgelMA1dhzXKtOXVKv9zFHi2a8SP4FHsYEiSmqZv0Bot9Yd4LHtEt7C tdoYqUG/Rj9A/5K7g+KDtCidw1LDjrwM/TkyKouxGPitjnzTEX/OgOz2QBelr7HqqTxs h79Q== X-Gm-Message-State: ACrzQf2kBVFmxQOw1uQfEx+F97mmAy6ZhuERm3N9HFfXMIeNXyVTCOtt b+gnBLl9zdrSz7Us6WMe2FQSr0puKEc= X-Google-Smtp-Source: AMsMyM5ohXm4oyR4jft0wXrIcDwmrJUMZ0my1jgH1DEVPjOvKwP7xekYGMEgfn4JBdiC2vhG8AasDNojAdM= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a62:8141:0:b0:56b:c435:f003 with SMTP id t62-20020a628141000000b0056bc435f003mr27425626pfd.15.1667431217428; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) Date: Wed, 2 Nov 2022 23:19:04 +0000 In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> Mime-Version: 1.0 References: <20221102231911.3107438-1-seanjc@google.com> X-Mailer: git-send-email 2.38.1.431.g37b22c650d-goog Message-ID: <20221102231911.3107438-38-seanjc@google.com> Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section From: Sean Christopherson To: Paolo Bonzini , Marc Zyngier , Huacai Chen , Aleksandar Markovic , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Christian Borntraeger , Janosch Frank , Claudio Imbrenda , Matthew Rosato , Eric Farman , Sean Christopherson , Vitaly Kuznetsov Cc: James Morse , Alexandru Elisei , Suzuki K Poulose , Oliver Upton , Atish Patra , David Hildenbrand , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, kvmarm@lists.cs.columbia.edu, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org, Isaku Yamahata , Fabiano Rosas , Michael Ellerman , Chao Gao , Thomas Gleixner , Yuan Yao X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20221102_232024_625290_E3C93C7B X-CRM114-Status: GOOD ( 14.16 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Sean Christopherson Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv From mboxrd@z Thu Jan 1 00:00:00 1970 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 lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 4BAAFC4332F for ; Wed, 2 Nov 2022 23:53:51 +0000 (UTC) Received: from boromir.ozlabs.org (localhost [IPv6:::1]) by lists.ozlabs.org (Postfix) with ESMTP id 4N2kHd6kGkz3g2x for ; Thu, 3 Nov 2022 10:53:49 +1100 (AEDT) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=google.com header.i=@google.com header.a=rsa-sha256 header.s=20210112 header.b=P098Tzj2; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=flex--seanjc.bounces.google.com (client-ip=2607:f8b0:4864:20::44a; helo=mail-pf1-x44a.google.com; envelope-from=3mftiywykdnqi40d926ee6b4.2ecb8dknff2-34lb8iji.epb01i.eh6@flex--seanjc.bounces.google.com; receiver=) Authentication-Results: lists.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=google.com header.i=@google.com header.a=rsa-sha256 header.s=20210112 header.b=P098Tzj2; dkim-atps=neutral Received: from mail-pf1-x44a.google.com (mail-pf1-x44a.google.com [IPv6:2607:f8b0:4864:20::44a]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4N2jXz1xSBz3cL1 for ; Thu, 3 Nov 2022 10:20:19 +1100 (AEDT) Received: by mail-pf1-x44a.google.com with SMTP id k131-20020a628489000000b0056b3e1a9629so10689pfd.8 for ; Wed, 02 Nov 2022 16:20:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:from:to:cc:subject:date:message-id:reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=P098Tzj2rpCJt/4nT8TrXTmUFPSgbhycgPry+JJrhxDuao4X1xtJJMmkpRB4trEL+1 55zpGfmzGI5TBm87M6Zs05xZAzJVQeNB6vBpk6WWQfA3tICCm87E6sO59+ssVnP2DMV3 hznDyqUbjHe4LGoM3DU21pBPc947dC5uIYbWgsImqI8pmwnLywsM+KMu/sYgtS/f8Vg6 ulJ7edDhRMBnHlx6lfmMwV1MS6wrSEBngjldBD8LoOWj74JJvfznExcwtcTban7qi7hz //M7aBh24hO/B6RinKg6thqufqaedpAYEyt0W7Am9UJmOQXk6WzZPIZJVcSMq0UtYuH2 blnQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=SlYp5i2yxUVOqJeJ6qRBQ3QPfvirB0zd00NR77LfoXO/ft0jkqoGmAUVHc0us1QzIz ufmyAXvt/l3NNP9tL4pYM314Sc8KOwhKekghVlTowaV97moCCxihynW8UD07mc9rWQaW o1Rvb3cLQkVNt17twG+VCfCyyxHBibuEkVJHxpYq0RyTBefbWwghA3cMvNTS4ff50hlZ sio925F1wKXPow8Y5nxJmZHhTiCJBQfiT3koS/jrL3rvPhEiX+Wh73+5s2CLjD+pIzIl B18wFQV7WjW0mpoZaclVo4qLMmeZzERtAX+5WgLBew12Odaq2utTq4qbfffTdTgDZT01 dBBQ== X-Gm-Message-State: ACrzQf2T9e/nQe84MVmCZpmayJ9valgG7WAQQ24q2167diReJlKVCRjT JqfqJeHNdGYgtsYxYFjt5uY9ZkxzDIg= X-Google-Smtp-Source: AMsMyM5ohXm4oyR4jft0wXrIcDwmrJUMZ0my1jgH1DEVPjOvKwP7xekYGMEgfn4JBdiC2vhG8AasDNojAdM= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a62:8141:0:b0:56b:c435:f003 with SMTP id t62-20020a628141000000b0056bc435f003mr27425626pfd.15.1667431217428; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) Date: Wed, 2 Nov 2022 23:19:04 +0000 In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> Mime-Version: 1.0 References: <20221102231911.3107438-1-seanjc@google.com> X-Mailer: git-send-email 2.38.1.431.g37b22c650d-goog Message-ID: <20221102231911.3107438-38-seanjc@google.com> Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section From: Sean Christopherson To: Paolo Bonzini , Marc Zyngier , Huacai Chen , Aleksandar Markovic , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Christian Borntraeger , Janosch Frank , Claudio Imbrenda , Matthew Rosato , Eric Farman , Sean Christopherson , Vitaly Kuznetsov Content-Type: text/plain; charset="UTF-8" X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Sean Christopherson Cc: kvm@vger.kernel.org, David Hildenbrand , Atish Patra , linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org, kvmarm@lists.cs.columbia.edu, linux-s390@vger.kernel.org, Chao Gao , Suzuki K Poulose , Yuan Yao , kvmarm@lists.linux.dev, Thomas Gleixner , Alexandru Elisei , linux-arm-kernel@lists.infradead.org, Isaku Yamahata , Fabiano Rosas , linux-mips@vger.kernel.org, Oliver Upton , James Morse , kvm-riscv@lists.infradead.org, linuxppc-dev@lists.ozlabs.org Errors-To: linuxppc-dev-bounces+linuxppc-dev=archiver.kernel.org@lists.ozlabs.org Sender: "Linuxppc-dev" From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog From mboxrd@z Thu Jan 1 00:00:00 1970 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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 8CDDFC433FE for ; Wed, 2 Nov 2022 23:43:40 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:Reply-To:List-Subscribe:List-Help: List-Post:List-Archive:List-Unsubscribe:List-Id:Cc:To:From:Subject:Message-ID :References:Mime-Version:In-Reply-To:Date:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=H4MSbRKYrw+yE66i0Pkx39L/1jQ5lj/D3ZNNLKBQrIo=; b=1OKtku9mUkKiLm WMiD8SVitVx/tXwMI5czbVYCIyJ3i324ZyCQkO0i4uUpDy4TFfZ+3bOSJXG9MB2XNJYQgIwxSodCR kFCF+htffMafZCSE832EZbJap7sB2GzuAi2ZqmOJxwrHclJ4EB98E7w2pugylD9xwCJGOr97zKCxm SYxn/OpZqHMhCk4xFjoHnvY0OGKVRHSC8zi0kWqGYZXFh2vT1ylG1O2PlOow7Xbz2UpyaDsiJjveR dFpxHexUlq3OZ2o3osWPW9jWNR+uWmxQynCk66ZqpOlsxHhLbj8oBVQXAzljiHi6d+pUX3iyWoH2H 5USp8YPRYAcyxCrHhW/w==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqNNF-00F5cB-Qy; Wed, 02 Nov 2022 23:42:23 +0000 Received: from casper.infradead.org ([2001:8b0:10b:1236::1]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqNGV-00F1m3-TJ for linux-arm-kernel@bombadil.infradead.org; Wed, 02 Nov 2022 23:35:24 +0000 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Type:Cc:To:From:Subject: Message-ID:References:Mime-Version:In-Reply-To:Date:Reply-To:Sender: Content-Transfer-Encoding:Content-ID:Content-Description; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=k0f5NcaejmRXfEXLIIr29cMr9K LP6MLpgWdIZfD/t8Ma/f1095Oytr7plShbFIuFXADIP3y7lazJjKTTg3m+t5mWBhGzgeBST7i9Tjx /5EczjKyzp0/qPRU/ovkyjqBOlppNMGpMyVexxqe6H/Rz3tYjYwGKbV51yHfARgCw5ZjXeXEf5tOO tIHt+e8uvndtc3lDKbshUPBxglkUvQ8BEhbtibcJOxyqHbhK8Qz5EJcX6/EsQ/SWkN2HcE53tijhk r3PPRHEt2Pvho54ct02mUYuZHY2WHe/ZH3jQaBGjZRCSY70kXLyX2OpIppEkZXu3xrytu25+8GDpm iUJOI6Tg==; Received: from mail-pj1-x104a.google.com ([2607:f8b0:4864:20::104a]) by casper.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1oqN1z-005vsB-Do for linux-arm-kernel@lists.infradead.org; Wed, 02 Nov 2022 23:20:25 +0000 Received: by mail-pj1-x104a.google.com with SMTP id pj8-20020a17090b4f4800b002140219b2b3so3130883pjb.0 for ; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:from:to:cc:subject:date:message-id:reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=P098Tzj2rpCJt/4nT8TrXTmUFPSgbhycgPry+JJrhxDuao4X1xtJJMmkpRB4trEL+1 55zpGfmzGI5TBm87M6Zs05xZAzJVQeNB6vBpk6WWQfA3tICCm87E6sO59+ssVnP2DMV3 hznDyqUbjHe4LGoM3DU21pBPc947dC5uIYbWgsImqI8pmwnLywsM+KMu/sYgtS/f8Vg6 ulJ7edDhRMBnHlx6lfmMwV1MS6wrSEBngjldBD8LoOWj74JJvfznExcwtcTban7qi7hz //M7aBh24hO/B6RinKg6thqufqaedpAYEyt0W7Am9UJmOQXk6WzZPIZJVcSMq0UtYuH2 blnQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:reply-to:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=XOm5gmY5yRxyVbM7h5atP3/v80uNjlEWUwmtqPuKnrU=; b=56V3uUVUHyUSagoOXUAz427Jp5D3VrVi6KfU4WfpICAb4KDVlTr6y9jGqrrlPFpZJF QT2lo8UsNr15z50gIUOuEE9FdjXgmDwxNSXpdHYvqF1wQXiejNBawyyWovwRjEfiIaIp eQz2fgUeTI6huxNJRJYkmi7Dd4LgNaD1d1WVrwHdlL7AmGiFmQUqiw/F1bfosSNi5P9k NsrQOXCBsvBzlenQn+TeH8pgG2YEnoIwyeGRlma8Jox1J8SZmtRIQ7cLK9pWTu88FWW2 UZXxTaArq5qcIstuypfGtT6EGS8isArsQIqBjvulnqijUeIbL+gETY1Lh7Q+nFMceosr TXyw== X-Gm-Message-State: ACrzQf0lAmquP6tbjDE9eq56Wguvmq8cXsRSwlm2f3Qr+s1qHjQXLPCr DeijQQe/GXkgNe0s+4JTKR3jvEYdMDI= X-Google-Smtp-Source: AMsMyM5ohXm4oyR4jft0wXrIcDwmrJUMZ0my1jgH1DEVPjOvKwP7xekYGMEgfn4JBdiC2vhG8AasDNojAdM= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a62:8141:0:b0:56b:c435:f003 with SMTP id t62-20020a628141000000b0056bc435f003mr27425626pfd.15.1667431217428; Wed, 02 Nov 2022 16:20:17 -0700 (PDT) Date: Wed, 2 Nov 2022 23:19:04 +0000 In-Reply-To: <20221102231911.3107438-1-seanjc@google.com> Mime-Version: 1.0 References: <20221102231911.3107438-1-seanjc@google.com> X-Mailer: git-send-email 2.38.1.431.g37b22c650d-goog Message-ID: <20221102231911.3107438-38-seanjc@google.com> Subject: [PATCH 37/44] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section From: Sean Christopherson To: Paolo Bonzini , Marc Zyngier , Huacai Chen , Aleksandar Markovic , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Christian Borntraeger , Janosch Frank , Claudio Imbrenda , Matthew Rosato , Eric Farman , Sean Christopherson , Vitaly Kuznetsov Cc: James Morse , Alexandru Elisei , Suzuki K Poulose , Oliver Upton , Atish Patra , David Hildenbrand , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, kvmarm@lists.cs.columbia.edu, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org, Isaku Yamahata , Fabiano Rosas , Michael Ellerman , Chao Gao , Thomas Gleixner , Yuan Yao X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20221102_232023_519031_0AC9E290 X-CRM114-Status: GOOD ( 15.61 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Sean Christopherson Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org From: Chao Gao The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Reviewed-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao Signed-off-by: Sean Christopherson --- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7337414e4947..de45be38dd27 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,7 +185,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -200,6 +199,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dd13af9f06d5..fd9e39c85549 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5026,13 +5026,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5045,7 +5059,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5822,8 +5836,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5897,7 +5911,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -5923,7 +5937,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- 2.38.1.431.g37b22c650d-goog _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel