Skip to contentSkip to conversation

VMX: configure posted interrupt descriptor when assigning device (v4)

PATCH In review Marcelo Tosatti 2 participants 6 messages May 12, 2021

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

cover VMX: configure posted interrupt descriptor when assigning device (v4)

Configuration of the posted interrupt descriptor is incorrect when devices are hotplugged to the guest (and vcpus are halted).

See patch 4 for details.

---

v4: remove NULL assignments from kvm_x86_ops (Peter Xu)

    check for return value of ->start_assignment directly (Peter Xu)

v3: improved comments (Sean)
use kvm_vcpu_wake_up (Sean)
drop device_count from start_assignment function (Peter Xu)

v2: rather than using a potentially racy IPI (vs vcpu->cpu switches),
kick the vcpus when assigning a device and let the blocked per-CPU list manipulation happen locally at ->pre_block and ->post_block (Sean Christopherson).

#1 lore raw

PATCH 1/4 KVM: x86: add start_assignment hook to kvm_x86_ops

Add a start_assignment hook to kvm_x86_ops, which is called when kvm_arch_start_assignment is done.

The hook is required to update the wakeup vector of a sleeping vCPU when a device is assigned to the guest.

arch/x86/include/asm/kvm_host.h +1 -0
Index: kvm/arch/x86/include/asm/kvm_host.h
===================================================================
@@ -1322,6 +1322,7 @@ struct kvm_x86_ops {
 
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
+	void (*start_assignment)(struct kvm *kvm);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
 	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
 
arch/x86/kvm/x86.c +2 -1
Index: kvm/arch/x86/kvm/x86.c
===================================================================
@@ -11295,7 +11295,8 @@ bool kvm_arch_can_dequeue_async_page_pre
 
 void kvm_arch_start_assignment(struct kvm *kvm)
 {
-	atomic_inc(&kvm->arch.assigned_device_count);
+	if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
+		static_call_cond(kvm_x86_start_assignment)(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
 
arch/x86/include/asm/kvm-x86-ops.h +1 -0
Index: kvm/arch/x86/include/asm/kvm-x86-ops.h
===================================================================
@@ -99,6 +99,7 @@ KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)
 KVM_X86_OP_NULL(vcpu_unblocking)
 KVM_X86_OP_NULL(update_pi_irte)
+KVM_X86_OP_NULL(start_assignment)
 KVM_X86_OP_NULL(apicv_post_state_restore)
 KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt)
 KVM_X86_OP_NULL(set_hv_timer)
#5 lore raw

PATCH 4/4 KVM: VMX: update vcpu posted-interrupt descriptor when assigning device

In reply to Marcelo Tosatti

For VMX, when a vcpu enters HLT emulation, pi_post_block will:

1) Add vcpu to per-cpu list of blocked vcpus.

2) Program the posted-interrupt descriptor "notification vector" to POSTED_INTR_WAKEUP_VECTOR

With interrupt remapping, an interrupt will set the PIR bit for the vector programmed for the device on the CPU, test-and-set the ON bit on the posted interrupt descriptor, and if the ON bit is clear generate an interrupt for the notification vector.

This way, the target CPU wakes upon a device interrupt and wakes up the target vcpu.

Problem is that pi_post_block only programs the notification vector if kvm_arch_has_assigned_device() is true. Its possible for the following to happen:

1) vcpu V HLTs on pcpu P, kvm_arch_has_assigned_device is false, notification vector is not programmed
2) device is assigned to VM
3) device interrupts vcpu V, sets ON bit
(notification vector not programmed, so pcpu P remains in idle)
4) vcpu 0 IPIs vcpu V (in guest), but since pi descriptor ON bit is set, kvm_vcpu_kick is skipped
5) vcpu 0 busy spins on vcpu V's response for several seconds, until RCU watchdog NMIs all vCPUs.

To fix this, use the start_assignment kvm_x86_ops callback to kick vcpus out of the halt loop, so the notification vector is properly reprogrammed to the wakeup vector.

arch/x86/kvm/vmx/posted_intr.c +45 -0
Index: kvm/arch/x86/kvm/vmx/posted_intr.c
===================================================================
@@ -204,6 +204,32 @@ void pi_post_block(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 vcpu_block().
+ */
+
+int vmx_vcpu_check_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!irq_remapping_cap(IRQ_POSTING_CAP))
+		return 0;
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return 0;
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
+		return 0;
+
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR)
+		return 0;
+
+	return 1;
+}
+
+/*
  * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
  */
 void pi_wakeup_handler(void)
@@ -236,6 +262,25 @@ bool pi_has_pending_interrupt(struct kvm
 		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
 }
 
+void vmx_pi_start_assignment(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	if (!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	/*
+	 * Wakeup will cause the vCPU to bail out of kvm_vcpu_block() and
+	 * go back through vcpu_block().
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_vcpu_apicv_active(vcpu))
+			continue;
+
+		kvm_vcpu_wake_up(vcpu);
+	}
+}
 
 /*
  * pi_update_irte - set IRTE for Posted-Interrupts
arch/x86/kvm/vmx/posted_intr.h +2 -0
Index: kvm/arch/x86/kvm/vmx/posted_intr.h
===================================================================
@@ -95,5 +95,7 @@ void __init pi_init_cpu(int cpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 		   bool set);
+void vmx_pi_start_assignment(struct kvm *kvm);
+int vmx_vcpu_check_block(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_X86_VMX_POSTED_INTR_H */
arch/x86/kvm/vmx/vmx.c +2 -0
Index: kvm/arch/x86/kvm/vmx/vmx.c
===================================================================
@@ -7727,11 +7727,13 @@ static struct kvm_x86_ops vmx_x86_ops __
 
 	.pre_block = vmx_pre_block,
 	.post_block = vmx_post_block,
+	.vcpu_check_block = vmx_vcpu_check_block,
 
 	.pmu_ops = &intel_pmu_ops,
 	.nested_ops = &vmx_nested_ops,
 
 	.update_pi_irte = pi_update_irte,
+	.start_assignment = vmx_pi_start_assignment,
 
 #ifdef CONFIG_X86_64
 	.set_hv_timer = vmx_set_hv_timer,
#3 lore raw

PATCH 2/4 KVM: add arch specific vcpu_check_block callback

In reply to Marcelo Tosatti

Add callback in kvm_vcpu_check_block, so that architectures can direct a vcpu to exit the vcpu block loop without requiring events that would unhalt it.

include/linux/kvm_host.h +7 -0
Index: kvm/include/linux/kvm_host.h
===================================================================
@@ -971,6 +971,13 @@ static inline int kvm_arch_flush_remote_
 }
 #endif
 
+#ifndef __KVM_HAVE_ARCH_VCPU_CHECK_BLOCK
+static inline int kvm_arch_vcpu_check_block(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+#endif
+
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
 void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
virt/kvm/kvm_main.c +2 -0
Index: kvm/virt/kvm/kvm_main.c
===================================================================
@@ -2794,6 +2794,8 @@ static int kvm_vcpu_check_block(struct k
 		goto out;
 	if (signal_pending(current))
 		goto out;
+	if (kvm_arch_vcpu_check_block(vcpu))
+		goto out;
 
 	ret = 0;
 out:
#4 lore raw

PATCH 3/4 KVM: x86: implement kvm_arch_vcpu_check_block callback

In reply to Marcelo Tosatti

Implement kvm_arch_vcpu_check_block for x86. Next patch will add implementation of kvm_x86_ops.vcpu_check_block for VMX.

arch/x86/include/asm/kvm_host.h +11 -0
Index: kvm/arch/x86/include/asm/kvm_host.h
===================================================================
@@ -1320,6 +1320,8 @@ struct kvm_x86_ops {
 	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
 	void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
 
+	int (*vcpu_check_block)(struct kvm_vcpu *vcpu);
+
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
 	void (*start_assignment)(struct kvm *kvm);
@@ -1801,6 +1803,15 @@ static inline bool kvm_irq_is_postable(s
 		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
+#define __KVM_HAVE_ARCH_VCPU_CHECK_BLOCK
+static inline int kvm_arch_vcpu_check_block(struct kvm_vcpu *vcpu)
+{
+	if (kvm_x86_ops.vcpu_check_block)
+		return static_call(kvm_x86_vcpu_check_block)(vcpu);
+
+	return 0;
+}
+
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
 	static_call_cond(kvm_x86_vcpu_blocking)(vcpu);
arch/x86/include/asm/kvm-x86-ops.h +1 -0
Index: kvm/arch/x86/include/asm/kvm-x86-ops.h
===================================================================
@@ -98,6 +98,7 @@ KVM_X86_OP_NULL(pre_block)
 KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)
 KVM_X86_OP_NULL(vcpu_unblocking)
+KVM_X86_OP_NULL(vcpu_check_block)
 KVM_X86_OP_NULL(update_pi_irte)
 KVM_X86_OP_NULL(start_assignment)
 KVM_X86_OP_NULL(apicv_post_state_restore)
Reviewed-by on v1 1/4
#2 lore raw

Re: [patch 1/4] KVM: x86: add start_assignment hook to kvm_x86_ops

In reply to Marcelo Tosatti
Quoted 7 lines · Marcelo Tosatti

Add a start_assignment hook to kvm_x86_ops, which is called when kvm_arch_start_assignment is done.

The hook is required to update the wakeup vector of a sleeping vCPU when a device is assigned to the guest.

Thanks,

Signature · 1 line
Peter Xu