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 <tglx@linutronix.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200708195321.724574345@linutronix.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9b59e63567bbe1a621abef25ce784673c30cf0de..0227c4cbe6420734a58be29874f7a0d1f6f99b3f 100644 (file)
--- 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 0d526b32f041f1964407efd4d0d0569598fec17d..4b4796d5123d763fcccba98c15feb199dc9a63c8 100644 (file)
--- 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 7f32169e8449f88386a9b5a961b727f23245d583..d7d82b3c0e4ce3bb342055f2320c2be8c1f4c4a3 100644 (file)
--- 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) {