1 files changed, 128 insertions, 140 deletions

diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 1c94783b5a54..aa1fe9085d77 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -11,58 +11,109 @@
 #include "vmx.h"
 
 /*
- * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we
- * can find which vCPU should be waken up.
+ * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler()
+ * when a WAKEUP_VECTOR interrupted is posted.  vCPUs are added to the list when
+ * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled.
+ * The vCPUs posted interrupt descriptor is updated at the same time to set its
+ * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices
+ * 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(spinlock_t, blocked_vcpu_on_cpu_lock);
+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, wakeup_vcpus_on_cpu_lock);
 
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
 	return &(to_vmx(vcpu)->pi_desc);
 }
 
+static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new)
+{
+	/*
+	 * PID.ON can be set at any time by a different vCPU or by hardware,
+	 * e.g. a device.  PID.control must be written atomically, and the
+	 * update must be retried with a fresh snapshot an ON change causes
+	 * the cmpxchg to fail.
+	 */
+	if (cmpxchg64(&pi_desc->control, old, new) != old)
+		return -EBUSY;
+
+	return 0;
+}
+
 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;
 
 	/*
-	 * In case of hot-plug or hot-unplug, we may have to undo
-	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
-	 * always keep PI.NDST up to date for simplicity: it makes the
-	 * code easier, and CPU migration is not a fast path.
+	 * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and
+	 * PI.SN up-to-date even if there is no assigned device or if APICv is
+	 * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC.
 	 */
-	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+	if (!enable_apicv || !lapic_in_kernel(vcpu))
 		return;
 
 	/*
-	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
-	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
-	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
-	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
-	 * correctly.
+	 * If the vCPU wasn't on the wakeup list and wasn't migrated, then the
+	 * full update can be skipped as neither the vector nor the destination
+	 * needs to be changed.
 	 */
-	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
-		pi_clear_sn(pi_desc);
-		goto after_clear_sn;
+	if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) {
+		/*
+		 * Clear SN if it was set due to being preempted.  Again, do
+		 * this even if there is no assigned device for simplicity.
+		 */
+		if (pi_test_and_clear_sn(pi_desc))
+			goto after_clear_sn;
+		return;
 	}
 
-	/* The full case.  */
-	do {
-		old.control = new.control = pi_desc->control;
+	local_irq_save(flags);
 
-		dest = cpu_physical_id(cpu);
+	/*
+	 * If the vCPU was waiting for wakeup, remove the vCPU from the wakeup
+	 * list of the _previous_ pCPU, which will not be the same as the
+	 * current pCPU if the task was migrated.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
+		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));
+	}
 
-		if (x2apic_mode)
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
+	dest = cpu_physical_id(cpu);
+	if (!x2apic_mode)
+		dest = (dest << 8) & 0xFF00;
+
+	do {
+		old.control = new.control = READ_ONCE(pi_desc->control);
 
+		/*
+		 * Clear SN (as above) and refresh the destination APIC ID to
+		 * handle task migration (@cpu != vcpu->cpu).
+		 */
+		new.ndst = dest;
 		new.sn = 0;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
+
+		/*
+		 * Restore the notification vector; in the blocking case, the
+		 * descriptor was modified on "put" to use the wakeup vector.
+		 */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (pi_try_set_control(pi_desc, old.control, new.control));
+
+	local_irq_restore(flags);
 
 after_clear_sn:
 
@@ -85,126 +136,64 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
 		irq_remapping_cap(IRQ_POSTING_CAP);
 }
 
-void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!vmx_can_use_vtd_pi(vcpu->kvm))
-		return;
-
-	/* Set SN when the vCPU is preempted */
-	if (vcpu->preempted)
-		pi_set_sn(pi_desc);
-}
-
-static void __pi_post_block(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	do {
-		old.control = new.control = pi_desc->control;
-		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
-		     "Wakeup handler not enabled while the VCPU is blocked\n");
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_mode)
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		vcpu->pre_pcpu = -1;
-	}
-}
-
 /*
- * This routine does the following things for vCPU which is going
- * to be blocked if VT-d PI is enabled.
- * - Store the vCPU to the wakeup list, so when interrupts happen
- *   we can find the right vCPU to wake up.
- * - Change the Posted-interrupt descriptor as below:
- *      'NDST' <-- vcpu->pre_pcpu
- *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
- * - If 'ON' is set during this process, which means at least one
- *   interrupt is posted for this vCPU, we cannot block it, in
- *   this case, return 1, otherwise, return 0.
- *
+ * Put the vCPU on this pCPU's list of vCPUs that needs to be awakened and set
+ * WAKEUP as the notification vector in the PI descriptor.
  */
-int pi_pre_block(struct kvm_vcpu *vcpu)
+static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 {
-	unsigned int dest;
-	struct pi_desc old, new;
 	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;
 
-	if (!vmx_can_use_vtd_pi(vcpu->kvm))
-		return 0;
-
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
-		vcpu->pre_pcpu = vcpu->cpu;
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_add_tail(&vcpu->blocked_vcpu_list,
-			      &per_cpu(blocked_vcpu_on_cpu,
-				       vcpu->pre_pcpu));
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-	}
-
-	do {
-		old.control = new.control = pi_desc->control;
+	local_irq_save(flags);
 
-		WARN((pi_desc->sn == 1),
-		     "Warning: SN field of posted-interrupts "
-		     "is set before blocking\n");
+	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));
 
-		/*
-		 * Since vCPU can be preempted during this process,
-		 * vcpu->cpu could be different with pre_pcpu, we
-		 * need to set pre_pcpu as the destination of wakeup
-		 * notification event, then we can find the right vCPU
-		 * to wakeup in wakeup handler if interrupts happen
-		 * when the vCPU is in blocked state.
-		 */
-		dest = cpu_physical_id(vcpu->pre_pcpu);
+	WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
 
-		if (x2apic_mode)
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
+	do {
+		old.control = new.control = READ_ONCE(pi_desc->control);
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
+	} while (pi_try_set_control(pi_desc, old.control, new.control));
 
-	/* We should not block the vCPU if an interrupt is posted for it.  */
-	if (pi_test_on(pi_desc) == 1)
-		__pi_post_block(vcpu);
+	/*
+	 * Send a wakeup IPI to this CPU if an interrupt may have been posted
+	 * before the notification vector was updated, in which case the IRQ
+	 * will arrive on the non-wakeup vector.  An IPI is needed as calling
+	 * try_to_wake_up() from ->sched_out() isn't allowed (IRQs are not
+	 * enabled until it is safe to call try_to_wake_up() on the task being
+	 * scheduled out).
+	 */
+	if (pi_test_on(&new))
+		apic->send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
 
-	local_irq_enable();
-	return (vcpu->pre_pcpu == -1);
+	local_irq_restore(flags);
 }
 
-void pi_post_block(struct kvm_vcpu *vcpu)
+void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->pre_pcpu == -1)
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	__pi_post_block(vcpu);
-	local_irq_enable();
+	if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
+		pi_enable_wakeup_handler(vcpu);
+
+	/*
+	 * Set SN when the vCPU is preempted.  Note, the vCPU can both be seen
+	 * as blocking and preempted, e.g. if it's preempted between setting
+	 * its wait state and manually scheduling out.
+	 */
+	if (vcpu->preempted)
+		pi_set_sn(pi_desc);
 }
 
 /*
@@ -212,24 +201,23 @@ void pi_post_block(struct kvm_vcpu *vcpu)
  */
 void pi_wakeup_handler(void)
 {
-	struct kvm_vcpu *vcpu;
 	int cpu = smp_processor_id();
+	struct vcpu_vmx *vmx;
 
-	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) == 1)
-			kvm_vcpu_kick(vcpu);
+		if (pi_test_on(&vmx->pi_desc))
+			kvm_vcpu_wake_up(&vmx->vcpu);
 	}
-	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));
-	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)
@@ -245,7 +233,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
  * Bail out of the block loop if the VM has an assigned
  * device, but the blocking vCPU didn't reconfigure the
  * PI.NV to the wakeup vector, i.e. the assigned device
- * came along after the initial check in pi_pre_block().
+ * came along after the initial check in vmx_vcpu_pi_put().
  */
 void vmx_pi_start_assignment(struct kvm *kvm)
 {