From a2486020a82eefad686993695eb42d1b64f3f2fd Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 26 May 2021 14:20:14 -0300 Subject: [PATCH] KVM: VMX: update vcpu posted-interrupt descriptor when assigning device For VMX, when a vcpu enters HLT emulation, pi_post_block will: 1) Add vcpu to per-cpu list of blocked vcpus. 2) Program the posted-interrupt descriptor "notification vector" to POSTED_INTR_WAKEUP_VECTOR With interrupt remapping, an interrupt will set the PIR bit for the vector programmed for the device on the CPU, test-and-set the ON bit on the posted interrupt descriptor, and if the ON bit is clear generate an interrupt for the notification vector. This way, the target CPU wakes upon a device interrupt and wakes up the target vcpu. Problem is that pi_post_block only programs the notification vector if kvm_arch_has_assigned_device() is true. Its possible for the following to happen: 1) vcpu V HLTs on pcpu P, kvm_arch_has_assigned_device is false, notification vector is not programmed 2) device is assigned to VM 3) device interrupts vcpu V, sets ON bit (notification vector not programmed, so pcpu P remains in idle) 4) vcpu 0 IPIs vcpu V (in guest), but since pi descriptor ON bit is set, kvm_vcpu_kick is skipped 5) vcpu 0 busy spins on vcpu V's response for several seconds, until RCU watchdog NMIs all vCPUs. To fix this, use the start_assignment kvm_x86_ops callback to kick vcpus out of the halt loop, so the notification vector is properly reprogrammed to the wakeup vector. Reported-by: Pei Zhang Signed-off-by: Marcelo Tosatti Message-Id: <20210526172014.GA29007@fuller.cnet> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/posted_intr.c | 14 ++++++++++++++ arch/x86/kvm/vmx/posted_intr.h | 1 + arch/x86/kvm/vmx/vmx.c | 1 + virt/kvm/kvm_main.c | 1 + 4 files changed, 17 insertions(+) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 459748680daf..5f81ef092bd4 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -237,6 +237,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) } +/* + * Bail out of the block loop if the VM has an assigned + * device, but the blocking vCPU didn't reconfigure the + * PI.NV to the wakeup vector, i.e. the assigned device + * came along after the initial check in pi_pre_block(). + */ +void vmx_pi_start_assignment(struct kvm *kvm) +{ + if (!irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); +} + /* * pi_update_irte - set IRTE for Posted-Interrupts * diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b..7f7b2326caf5 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +void vmx_pi_start_assignment(struct kvm *kvm); #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4bceb5ca3a89..639ec3eba9b8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7721,6 +7721,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .update_pi_irte = pi_update_irte, + .start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 .set_hv_timer = vmx_set_hv_timer, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 37a2d500a148..6a6bc7af0e28 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -307,6 +307,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { return kvm_make_all_cpus_request_except(kvm, req, NULL); } +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm)