KVM: SVM: Drop AVIC's intermediate avic_set_running() helper

Drop avic_set_running() in favor of calling avic_vcpu_{load,put}()
directly, and modify the block+put path to use preempt_disable/enable()
instead of get/put_cpu(), as it doesn't actually care about the current
pCPU associated with the vCPU.  Opportunistically add lockdep assertions
as being preempted in avic_vcpu_put() would lead to consuming stale data,
even though doing so _in the current code base_ would not be fatal.

Add a much needed comment explaining why svm_vcpu_blocking() needs to
unload the AVIC and update the IRTE _before_ the vCPU starts blocking.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211208015236.1616697-22-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 36 insertions, 20 deletions

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index b7353e11da2e..522f859408cb 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -978,6 +978,8 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
 	/*
 	 * Since the host physical APIC id is 8 bits,
 	 * we can support host APIC ID upto 255.
@@ -1011,6 +1013,8 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 
 	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
@@ -1023,30 +1027,42 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
-/*
- * This function is called during VCPU halt/unhalt.
- */
-static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
-{
-	int cpu = get_cpu();
-
-	WARN_ON(cpu != vcpu->cpu);
-
-	if (kvm_vcpu_apicv_active(vcpu)) {
-		if (is_run)
-			avic_vcpu_load(vcpu, cpu);
-		else
-			avic_vcpu_put(vcpu);
-	}
-	put_cpu();
-}
-
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
-	avic_set_running(vcpu, false);
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	preempt_disable();
+
+       /*
+        * Unload the AVIC when the vCPU is about to block, _before_
+        * the vCPU actually blocks.
+        *
+        * Any IRQs that arrive before IsRunning=0 will not cause an
+        * incomplete IPI vmexit on the source, therefore vIRR will also
+        * be checked by kvm_vcpu_check_block() before blocking.  The
+        * memory barrier implicit in set_current_state orders writing
+        * IsRunning=0 before reading the vIRR.  The processor needs a
+        * matching memory barrier on interrupt delivery between writing
+        * IRR and reading IsRunning; the lack of this barrier might be
+        * the cause of errata #1235).
+        */
+	avic_vcpu_put(vcpu);
+
+	preempt_enable();
 }
 
 void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	avic_set_running(vcpu, true);
+	int cpu;
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	cpu = get_cpu();
+	WARN_ON(cpu != vcpu->cpu);
+
+	avic_vcpu_load(vcpu, cpu);
+
+	put_cpu();
 }