From 87fa7f3e98a1310ef1ac1900e7ee7f9610a038bc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 8 Jul 2020 21:51:54 +0200 Subject: [PATCH] x86/kvm: Move context tracking where it belongs 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 Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Acked-by: Paolo Bonzini Message-Id: <20200708195321.724574345@linutronix.de> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 16 ++++++++++++++++ arch/x86/kvm/vmx/vmx.c | 10 ++++++++++ arch/x86/kvm/x86.c | 2 -- 3 files changed, 26 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9b59e63567bb..0227c4cbe642 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3398,6 +3398,14 @@ static __no_kcsan 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 @@ -3408,6 +3416,14 @@ static __no_kcsan 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 0d526b32f041..4b4796d5123d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6731,6 +6731,11 @@ reenter_guest: */ 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); @@ -6745,6 +6750,11 @@ reenter_guest: 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 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7f32169e8449..d7d82b3c0e4c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8522,7 +8522,6 @@ 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)) @@ -8585,7 +8584,6 @@ 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) { -- 2.20.1