KVM: Move x86 VMX's posted interrupt list_head to vcpu_vmx

Move the seemingly generic block_vcpu_list from kvm_vcpu to vcpu_vmx, and rename the list and all associated variables to clarify that it tracks the set of vCPU that need to be poked on a posted interrupt to the wakeup vector. The list is not used to track _all_ vCPUs that are blocking, and the term "blocked" can be misleading as it may refer to a blocking condition in the host or the guest, where as the PI wakeup case is specifically for the vCPUs that are actively blocking from within the guest. No functional change intended. Signed-off-by: Sean Christopherson <[email protected]> Reviewed-by: Maxim Levitsky <[email protected]> Message-Id: <[email protected]> Signed-off-by: Paolo Bonzini <[email protected]>
noroot · Jan 19, 2022 · 12a8eee · 12a8eee
1 parent e6eec09
commit 12a8eee
Show file tree

Hide file tree

Showing 5 changed files with 25 additions and 23 deletions.
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
@@ -19,15 +19,15 @@
  * wake the target vCPUs.  vCPUs are removed from the list and the notification
  * vector is reset when the vCPU is scheduled in.
  */
-static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
 /*
  * Protect the per-CPU list with a per-CPU spinlock to handle task migration.
  * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the
  * ->sched_in() path will need to take the vCPU off the list of the _previous_
  * CPU.  IRQs must be disabled when taking this lock, otherwise deadlock will
  * occur if a wakeup IRQ arrives and attempts to acquire the lock.
  */
-static DEFINE_PER_CPU(raw_spinlock_t, blocked_vcpu_on_cpu_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
@@ -51,6 +51,7 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new)
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct pi_desc old, new;
 	unsigned long flags;
 	unsigned int dest;
@@ -86,9 +87,9 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 * current pCPU if the task was migrated.
 	 */
 	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
-		raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
-		list_del(&vcpu->blocked_vcpu_list);
-		raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		list_del(&vmx->pi_wakeup_list);
+		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 	}
 
 	dest = cpu_physical_id(cpu);
@@ -142,15 +143,16 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
 static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct pi_desc old, new;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
-	list_add_tail(&vcpu->blocked_vcpu_list,
-		      &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu));
-	raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+	list_add_tail(&vmx->pi_wakeup_list,
+		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
+	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 
 	WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
 
@@ -199,24 +201,23 @@ void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
  */
 void pi_wakeup_handler(void)
 {
-	struct kvm_vcpu *vcpu;
 	int cpu = smp_processor_id();
+	struct vcpu_vmx *vmx;
 
-	raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
-			blocked_vcpu_list) {
-		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
+	list_for_each_entry(vmx, &per_cpu(wakeup_vcpus_on_cpu, cpu),
+			    pi_wakeup_list) {
 
-		if (pi_test_on(pi_desc))
-			kvm_vcpu_kick(vcpu);
+		if (pi_test_on(&vmx->pi_desc))
+			kvm_vcpu_kick(&vmx->vcpu);
 	}
-	raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
 }
 
 void __init pi_init_cpu(int cpu)
 {
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	raw_spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	INIT_LIST_HEAD(&per_cpu(wakeup_vcpus_on_cpu, cpu));
+	raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
 }
 
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
@@ -6943,6 +6943,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
 	vmx = to_vmx(vcpu);
 
+	INIT_LIST_HEAD(&vmx->pi_wakeup_list);
+
 	err = -ENOMEM;
 
 	vmx->vpid = allocate_vpid();

diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
@@ -317,6 +317,9 @@ struct vcpu_vmx {
 	/* Posted interrupt descriptor */
 	struct pi_desc pi_desc;
 
+	/* Used if this vCPU is waiting for PI notification wakeup. */
+	struct list_head pi_wakeup_list;
+
 	/* Support for a guest hypervisor (nested VMX) */
 	struct nested_vmx nested;
 

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
@@ -309,8 +309,6 @@ struct kvm_vcpu {
 	u64 requests;
 	unsigned long guest_debug;
 
-	struct list_head blocked_vcpu_list;
-
 	struct mutex mutex;
 	struct kvm_run *run;
 

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
@@ -427,8 +427,6 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 #endif
 	kvm_async_pf_vcpu_init(vcpu);
 
-	INIT_LIST_HEAD(&vcpu->blocked_vcpu_list);
-
 	kvm_vcpu_set_in_spin_loop(vcpu, false);
 	kvm_vcpu_set_dy_eligible(vcpu, false);
 	vcpu->preempted = false;