From 17e433b54393a6269acbcb792da97791fe1592d8 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 5 Aug 2019 10:03:19 +0800 Subject: KVM: Fix leak vCPU's VMCS value into other pCPU After commit d73eb57b80b (KVM: Boost vCPUs that are delivering interrupts), a five years old bug is exposed. Running ebizzy benchmark in three 80 vCPUs VMs on one 80 pCPUs Skylake server, a lot of rcu_sched stall warning splatting in the VMs after stress testing: INFO: rcu_sched detected stalls on CPUs/tasks: { 4 41 57 62 77} (detected by 15, t=60004 jiffies, g=899, c=898, q=15073) Call Trace: flush_tlb_mm_range+0x68/0x140 tlb_flush_mmu.part.75+0x37/0xe0 tlb_finish_mmu+0x55/0x60 zap_page_range+0x142/0x190 SyS_madvise+0x3cd/0x9c0 system_call_fastpath+0x1c/0x21 swait_active() sustains to be true before finish_swait() is called in kvm_vcpu_block(), voluntarily preempted vCPUs are taken into account by kvm_vcpu_on_spin() loop greatly increases the probability condition kvm_arch_vcpu_runnable(vcpu) is checked and can be true, when APICv is enabled the yield-candidate vCPU's VMCS RVI field leaks(by vmx_sync_pir_to_irr()) into spinning-on-a-taken-lock vCPU's current VMCS. This patch fixes it by checking conservatively a subset of events. Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Christian Borntraeger Cc: Marc Zyngier Cc: stable@vger.kernel.org Fixes: 98f4a1467 (KVM: add kvm_arch_vcpu_runnable() test to kvm_vcpu_on_spin() loop) Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ed061d8a457c..1f05aeb9da27 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2477,6 +2477,29 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) #endif } +/* + * Unlike kvm_arch_vcpu_runnable, this function is called outside + * a vcpu_load/vcpu_put pair. However, for most architectures + * kvm_arch_vcpu_runnable does not require vcpu_load. + */ +bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + +static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (kvm_arch_dy_runnable(vcpu)) + return true; + +#ifdef CONFIG_KVM_ASYNC_PF + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; +#endif + + return false; +} + void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; @@ -2506,7 +2529,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu)) -- cgit v1.2.3-55-g7522