
From: Zhenzhong Duan <zhenzhong.duan@oracle.com> mainline inclusion from mainline-5.1 commit 05eee619ed61c8cd89633954d38c4e5653086845 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3T22N CVE: NA There are cases where a guest tries to switch spinlocks to bare metal behavior (e.g. by setting "xen_nopvspin" on XEN platform and "hv_nopvspin" on HYPER_V). That feature is missed on KVM, add a new parameter "nopvspin" to disable PV spinlocks for KVM guest. The new 'nopvspin' parameter will also replace Xen and Hyper-V specific parameters in future patches. Define variable nopvsin as global because it will be used in future patches as above. Signed-off-by: Zhenzhong Duan <zhenzhong.duan@oracle.com> Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Sean Christopherson <sean.j.christopherson@intel.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Wanpeng Li <wanpengli@tencent.com> Cc: Jim Mattson <jmattson@google.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Jiajun Chen <chenjiajun8@huawei.com> Reviewed-by: Xiangyou Xie <xiexiangyou@huawei.com> Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> --- .../admin-guide/kernel-parameters.txt | 5 +++ arch/x86/include/asm/qspinlock.h | 1 + arch/x86/kernel/kvm.c | 41 +++++++++++++++---- kernel/locking/qspinlock.c | 7 ++++ 4 files changed, 47 insertions(+), 7 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 05b9b8c6034cd..40dc1e3e89d93 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5392,6 +5392,11 @@ with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. + nopvspin [X86,KVM] + Disables the qspinlock slow path using PV optimizations + which allow the hypervisor to 'idle' the guest on lock + contention. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index e34ffb0af6bd2..4d425673d831a 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -39,6 +39,7 @@ extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); extern void __pv_init_lock_hash(void); extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock); +extern bool nopvspin; #define queued_spin_unlock queued_spin_unlock /** diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9c52eec69bfc6..d1ccd5bbf6231 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -843,16 +843,36 @@ void __init kvm_spinlock_init(void) { if (!kvm_para_available()) return; - /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ - if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + /* + * In case host doesn't support KVM_FEATURE_PV_UNHALT there is still an + * advantage of keeping virt_spin_lock_key enabled: virt_spin_lock() is + * preferred over native qspinlock when vCPU is preempted. + */ + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) { + pr_info("PV spinlocks disabled, no host support\n"); return; + } - if (kvm_para_has_hint(KVM_HINTS_REALTIME)) - return; + /* + * Disable PV spinlocks and use native qspinlock when dedicated pCPUs + * are available. + */ + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) { + pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints\n"); + goto out; + } - /* Don't use the pvqspinlock code if there is only 1 vCPU. */ - if (num_possible_cpus() == 1) - return; + if (num_possible_cpus() == 1) { + pr_info("PV spinlocks disabled, single CPU\n"); + goto out; + } + + if (nopvspin) { + pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter\n"); + goto out; + } + + pr_info("PV spinlocks enabled\n"); __pv_init_lock_hash(); pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; @@ -864,6 +884,13 @@ void __init kvm_spinlock_init(void) pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); } + /* + * When PV spinlock is enabled which is preferred over + * virt_spin_lock(), virt_spin_lock_key's value is meaningless. + * Just disable it anyway. + */ +out: + static_branch_disable(&virt_spin_lock_key); } #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index a33c509199fd8..fd148973080f6 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -631,4 +631,11 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath); #include "qspinlock_paravirt.h" #include "qspinlock.c" +bool nopvspin __initdata; +static __init int parse_nopvspin(char *arg) +{ + nopvspin = true; + return 0; +} +early_param("nopvspin", parse_nopvspin); #endif -- 2.25.1