Context tracking for KVM happens way too early in the vcpu_run() code. Anything after guest_enter_irqoff() and before guest_exit_irqoff() cannot use RCU and should also be not instrumented.
The current way of doing this covers way too much code. Move it closer to the actual vmenter/exit code. Signed-off-by: Thomas Gleixner <[email protected]> Reviewed-by: Alexandre Chartre <[email protected]> Acked-by: Peter Zijlstra <[email protected]> Acked-by: Paolo Bonzini <[email protected]> Link: https://lkml.kernel.org/r/[email protected] diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4e9cd2a73ad0..40242e0af20d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3389,6 +3389,14 @@ static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); + /* + * Tell context tracking that this CPU is about to enter guest + * mode. This has to be after x86_spec_ctrl_set_guest() because + * that can take locks (lockdep needs RCU) and calls into world and + * some more. + */ + guest_enter_irqoff(); + __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); #ifdef CONFIG_X86_64 @@ -3399,6 +3407,14 @@ static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(gs, svm->host.gs); #endif #endif + /* + * Tell context tracking that this CPU is back. + * + * This needs to be done before the below as native_read_msr() + * contains a tracepoint and x86_spec_ctrl_restore_host() calls + * into world and some more. + */ + guest_exit_irqoff(); /* * We do not use IBRS in the kernel. If this vCPU has used the diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6a03c27ff314..ad0159f68ce4 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6724,6 +6724,11 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); + /* + * Tell context tracking that this CPU is about to enter guest mode. + */ + guest_enter_irqoff(); + /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); @@ -6739,6 +6744,11 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.cr2 = read_cr2(); /* + * Tell context tracking that this CPU is back. + */ + guest_exit_irqoff(); + + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and * turn it off. This is much more efficient than blindly adding diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 471fccf7f850..28663a6688d1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8438,7 +8438,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } trace_kvm_entry(vcpu->vcpu_id); - guest_enter_irqoff(); fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -8500,7 +8499,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_disable(); kvm_after_interrupt(vcpu); - guest_exit_irqoff(); if (lapic_in_kernel(vcpu)) { s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; if (delta != S64_MIN) {
