[PATCH v2] kvm: ioapic: Introduce arch-specific check for lazy update EOI mechanism

[Suravee Suthikulpanit]

commit f458d039db7e ("kvm: ioapic: Lazy update IOAPIC EOI") introduces
the following regression.

BUG: stack guard page was hit at 000000008f595917 \
(stack is 00000000bdefe5a4..00000000ae2b06f5)
kernel stack overflow (double-fault): 0000 [#1] SMP NOPTI
RIP: 0010:kvm_set_irq+0x51/0x160 [kvm]
Call Trace:
 irqfd_resampler_ack+0x32/0x90 [kvm]
 kvm_notify_acked_irq+0x62/0xd0 [kvm]
 kvm_ioapic_update_eoi_one.isra.0+0x30/0x120 [kvm]
 ioapic_set_irq+0x20e/0x240 [kvm]
 kvm_ioapic_set_irq+0x5c/0x80 [kvm]
 kvm_set_irq+0xbb/0x160 [kvm]
 ? kvm_hv_set_sint+0x20/0x20 [kvm]
 irqfd_resampler_ack+0x32/0x90 [kvm]
 kvm_notify_acked_irq+0x62/0xd0 [kvm]
 kvm_ioapic_update_eoi_one.isra.0+0x30/0x120 [kvm]
 ioapic_set_irq+0x20e/0x240 [kvm]
 kvm_ioapic_set_irq+0x5c/0x80 [kvm]
 kvm_set_irq+0xbb/0x160 [kvm]
 ? kvm_hv_set_sint+0x20/0x20 [kvm]
....

This is due to re-entrancy of the lazy update EOI logic
when enable APICv with VFIO pass-through device, which
sets up kvm_irqfd() w/ KVM_IRQFD_FLAG_RESAMPLE.

Fixes by adding re-entrancy check logic.

Reported-by: borisvk@xxxxxxxxxx
Suggested-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Link: https://www.spinics.net/lists/kvm/msg213512.html
Fixes: f458d039db7e ("kvm: ioapic: Lazy update IOAPIC EOI")
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=207489
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
---
 arch/x86/kvm/ioapic.c | 11 +++++++++++
 arch/x86/kvm/ioapic.h |  1 +
 2 files changed, 12 insertions(+)

diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 750ff0b..a68f624 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -188,6 +188,14 @@ static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq)
 	struct kvm_vcpu *vcpu;
 	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
 
+	/*
+	 * Re-entrancy check due to KVM_IRQFD_FLAG_RESAMPLE can cause
+	 * stack overflow where irqfd_resampler_ack() repeatedly calls
+	 * ioapic_set_irq().
+	 */
+	if (atomic_cmpxchg(&ioapic->in_lazy_update_eoi, 0, 1))
+		return;
+
 	kvm_for_each_vcpu(i, vcpu, ioapic->kvm) {
 		if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
 					 entry->fields.dest_id,
@@ -205,6 +213,8 @@ static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq)
 					  irq);
 		break;
 	}
+
+	atomic_set(&ioapic->in_lazy_update_eoi, 0);
 }
 
 static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
@@ -707,6 +717,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 		kvm->arch.vioapic = NULL;
 		kfree(ioapic);
 	}
+	atomic_set(&ioapic->in_lazy_update_eoi, 0);
 
 	return ret;
 }
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 2fb2e3c..898a967 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -91,6 +91,7 @@ struct kvm_ioapic {
 	struct delayed_work eoi_inject;
 	u32 irq_eoi[IOAPIC_NUM_PINS];
 	u32 irr_delivered;
+	atomic_t in_lazy_update_eoi;
 };
 
 #ifdef DEBUG
-- 
1.8.3.1