1 files changed, 231 insertions, 124 deletions

diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 4e822ad363f3..2c2783296aed 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: LGPL-2.1-or-later
 /*
  *  Copyright (C) 2001  MandrakeSoft S.A.
  *  Copyright 2010 Red Hat, Inc. and/or its affiliates.
@@ -8,24 +9,11 @@
  *    http://www.linux-mandrake.com/
  *    http://www.mandrakesoft.com/
  *
- *  This library is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU Lesser General Public
- *  License as published by the Free Software Foundation; either
- *  version 2 of the License, or (at your option) any later version.
- *
- *  This library is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  Lesser General Public License for more details.
- *
- *  You should have received a copy of the GNU Lesser General Public
- *  License along with this library; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  *  Yunhong Jiang <yunhong.jiang@intel.com>
  *  Yaozu (Eddie) Dong <eddie.dong@intel.com>
  *  Based on Xen 3.1 code.
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
@@ -36,26 +24,25 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/nospec.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
-#include <trace/events/kvm.h>
 
 #include "ioapic.h"
 #include "lapic.h"
 #include "irq.h"
+#include "trace.h"
 
-#if 0
-#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
-#else
-#define ioapic_debug(fmt, arg...)
-#endif
 static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
 		bool line_status);
 
-static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
-					  unsigned long addr,
-					  unsigned long length)
+static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu,
+				      struct kvm_ioapic *ioapic,
+				      int trigger_mode,
+				      int pin);
+
+static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic)
 {
 	unsigned long result = 0;
 
@@ -73,13 +60,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 	default:
 		{
 			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
-			u64 redir_content;
+			u64 redir_content = ~0ULL;
 
-			if (redir_index < IOAPIC_NUM_PINS)
-				redir_content =
-					ioapic->redirtbl[redir_index].bits;
-			else
-				redir_content = ~0ULL;
+			if (redir_index < IOAPIC_NUM_PINS) {
+				u32 index = array_index_nospec(
+					redir_index, IOAPIC_NUM_PINS);
+
+				redir_content = ioapic->redirtbl[index].bits;
+			}
 
 			result = (ioapic->ioregsel & 0x1) ?
 			    (redir_content >> 32) & 0xffffffff :
@@ -94,7 +82,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_IDS);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
@@ -113,8 +101,9 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 	union kvm_ioapic_redirect_entry *e;
 
 	e = &ioapic->redirtbl[RTC_GSI];
-	if (!kvm_apic_match_dest(vcpu, NULL, 0,	e->fields.dest_id,
-				e->fields.dest_mode))
+	if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+				 e->fields.dest_id,
+				 kvm_lapic_irq_dest_mode(!!e->fields.dest_mode)))
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
@@ -146,7 +135,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 {
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 
 	if (RTC_GSI >= IOAPIC_NUM_PINS)
 		return;
@@ -156,10 +145,16 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 	    __rtc_irq_eoi_tracking_restore_one(vcpu);
 }
 
-static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
+static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu,
+			int vector)
 {
-	if (test_and_clear_bit(vcpu->vcpu_id,
-			       ioapic->rtc_status.dest_map.map)) {
+	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
+
+	/* RTC special handling */
+	if (test_bit(vcpu->vcpu_id, dest_map->map) &&
+	    (vector == dest_map->vectors[vcpu->vcpu_id]) &&
+	    (test_and_clear_bit(vcpu->vcpu_id,
+				ioapic->rtc_status.dest_map.map))) {
 		--ioapic->rtc_status.pending_eoi;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
@@ -173,6 +168,28 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
 	return false;
 }
 
+static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq)
+{
+	unsigned long i;
+	struct kvm_vcpu *vcpu;
+	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+
+	kvm_for_each_vcpu(i, vcpu, ioapic->kvm) {
+		if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+					 entry->fields.dest_id,
+					 entry->fields.dest_mode) ||
+		    kvm_apic_pending_eoi(vcpu, entry->fields.vector))
+			continue;
+
+		/*
+		 * If no longer has pending EOI in LAPICs, update
+		 * EOI for this vector.
+		 */
+		rtc_irq_eoi(ioapic, vcpu, entry->fields.vector);
+		break;
+	}
+}
+
 static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 		int irq_level, bool line_status)
 {
@@ -191,9 +208,18 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 	}
 
 	/*
+	 * AMD SVM AVIC accelerate EOI write iff the interrupt is edge
+	 * triggered, in which case the in-kernel IOAPIC will not be able
+	 * to receive the EOI.  In this case, we do a lazy update of the
+	 * pending EOI when trying to set IOAPIC irq.
+	 */
+	if (edge && kvm_apicv_activated(ioapic->kvm))
+		ioapic_lazy_update_eoi(ioapic, irq);
+
+	/*
 	 * Return 0 for coalesced interrupts; for edge-triggered interrupts,
 	 * this only happens if a previous edge has not been delivered due
-	 * do masking.  For level interrupts, the remote_irr field tells
+	 * to masking.  For level interrupts, the remote_irr field tells
 	 * us if the interrupt is waiting for an EOI.
 	 *
 	 * RTC is special: it is edge-triggered, but userspace likes to know
@@ -255,11 +281,10 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
 		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
 		    index == RTC_GSI) {
-			if (kvm_apic_match_dest(vcpu, NULL, 0,
-			             e->fields.dest_id, e->fields.dest_mode) ||
-			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
-				__set_bit(e->fields.vector,
-					  ioapic_handled_vectors);
+			u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
+
+			kvm_scan_ioapic_irq(vcpu, e->fields.dest_id, dm,
+					    e->fields.vector, ioapic_handled_vectors);
 		}
 	}
 	spin_unlock(&ioapic->lock);
@@ -272,12 +297,49 @@ void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
 	kvm_make_scan_ioapic_request(kvm);
 }
 
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+				    struct kvm_irq_mask_notifier *kimn)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	mutex_lock(&kvm->irq_lock);
+	kimn->irq = irq;
+	hlist_add_head_rcu(&kimn->link, &ioapic->mask_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+				      struct kvm_irq_mask_notifier *kimn)
+{
+	mutex_lock(&kvm->irq_lock);
+	hlist_del_rcu(&kimn->link);
+	mutex_unlock(&kvm->irq_lock);
+	synchronize_srcu(&kvm->irq_srcu);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	struct kvm_irq_mask_notifier *kimn;
+	int idx, gsi;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link)
+			if (kimn->irq == gsi)
+				kimn->func(kimn, mask);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
 static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
-	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
+	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -294,14 +356,16 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	default:
 		index = (ioapic->ioregsel - 0x10) >> 1;
 
-		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
+		index = array_index_nospec(index, IOAPIC_NUM_PINS);
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
 		/* Preserve read-only fields */
 		old_remote_irr = e->fields.remote_irr;
 		old_delivery_status = e->fields.delivery_status;
+		old_dest_id = e->fields.dest_id;
+		old_dest_mode = e->fields.dest_mode;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
@@ -324,10 +388,73 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
-		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
-		    && ioapic->irr & (1 << index))
-			ioapic_service(ioapic, index, false);
-		kvm_make_scan_ioapic_request(ioapic->kvm);
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+		    ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) {
+			/*
+			 * Pending status in irr may be outdated: the IRQ line may have
+			 * already been deasserted by a device while the IRQ was masked.
+			 * This occurs, for instance, if the interrupt is handled in a
+			 * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this
+			 * case the guest acknowledges the interrupt to the device in
+			 * its threaded irq handler, i.e. after the EOI but before
+			 * unmasking, so at the time of unmasking the IRQ line is
+			 * already down but our pending irr bit is still set. In such
+			 * cases, injecting this pending interrupt to the guest is
+			 * buggy: the guest will receive an extra unwanted interrupt.
+			 *
+			 * So we need to check here if the IRQ is actually still pending.
+			 * As we are generally not able to probe the IRQ line status
+			 * directly, we do it through irqfd resampler. Namely, we clear
+			 * the pending status and notify the resampler that this interrupt
+			 * is done, without actually injecting it into the guest. If the
+			 * IRQ line is actually already deasserted, we are done. If it is
+			 * still asserted, a new interrupt will be shortly triggered
+			 * through irqfd and injected into the guest.
+			 *
+			 * If, however, it's not possible to resample (no irqfd resampler
+			 * registered for this irq), then unconditionally inject this
+			 * pending interrupt into the guest, so the guest will not miss
+			 * an interrupt, although may get an extra unwanted interrupt.
+			 */
+			if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index))
+				ioapic->irr &= ~(1 << index);
+			else
+				ioapic_service(ioapic, index, false);
+		}
+		if (e->fields.delivery_mode == APIC_DM_FIXED) {
+			struct kvm_lapic_irq irq;
+
+			irq.vector = e->fields.vector;
+			irq.delivery_mode = e->fields.delivery_mode << 8;
+			irq.dest_mode =
+			    kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
+			irq.level = false;
+			irq.trig_mode = e->fields.trig_mode;
+			irq.shorthand = APIC_DEST_NOSHORT;
+			irq.dest_id = e->fields.dest_id;
+			irq.msi_redir_hint = false;
+			bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+						 vcpu_bitmap);
+			if (old_dest_mode != e->fields.dest_mode ||
+			    old_dest_id != e->fields.dest_id) {
+				/*
+				 * Update vcpu_bitmap with vcpus specified in
+				 * the previous request as well. This is done to
+				 * keep ioapic_handled_vectors synchronized.
+				 */
+				irq.dest_id = old_dest_id;
+				irq.dest_mode =
+				    kvm_lapic_irq_dest_mode(
+					!!e->fields.dest_mode);
+				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+							 vcpu_bitmap);
+			}
+			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
+							  vcpu_bitmap);
+		} else {
+			kvm_make_scan_ioapic_request(ioapic->kvm);
+		}
 		break;
 	}
 }
@@ -343,19 +470,13 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	    entry->fields.remote_irr))
 		return -1;
 
-	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
-		     "vector=%x trig_mode=%x\n",
-		     entry->fields.dest_id, entry->fields.dest_mode,
-		     entry->fields.delivery_mode, entry->fields.vector,
-		     entry->fields.trig_mode);
-
 	irqe.dest_id = entry->fields.dest_id;
 	irqe.vector = entry->fields.vector;
-	irqe.dest_mode = entry->fields.dest_mode;
+	irqe.dest_mode = kvm_lapic_irq_dest_mode(!!entry->fields.dest_mode);
 	irqe.trig_mode = entry->fields.trig_mode;
 	irqe.delivery_mode = entry->fields.delivery_mode << 8;
 	irqe.level = 1;
-	irqe.shorthand = 0;
+	irqe.shorthand = APIC_DEST_NOSHORT;
 	irqe.msi_redir_hint = false;
 
 	if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
@@ -381,9 +502,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	return ret;
 }
 
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
-		       int level, bool line_status)
+int kvm_ioapic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+		       int irq_source_id, int level, bool line_status)
 {
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	int irq = e->irqchip.pin;
 	int ret, irq_level;
 
 	BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
@@ -398,16 +521,6 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 	return ret;
 }
 
-void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
-{
-	int i;
-
-	spin_lock(&ioapic->lock);
-	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
-		__clear_bit(irq_source_id, &ioapic->irq_states[i]);
-	spin_unlock(&ioapic->lock);
-}
-
 static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
 {
 	int i;
@@ -427,72 +540,68 @@ static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
 }
 
 #define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
-
-static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
-			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
+static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu,
+				      struct kvm_ioapic *ioapic,
+				      int trigger_mode,
+				      int pin)
 {
-	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	int i;
+	union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[pin];
 
-	/* RTC special handling */
-	if (test_bit(vcpu->vcpu_id, dest_map->map) &&
-	    vector == dest_map->vectors[vcpu->vcpu_id])
-		rtc_irq_eoi(ioapic, vcpu);
-
-	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
-		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
-
-		if (ent->fields.vector != vector)
-			continue;
-
-		/*
-		 * We are dropping lock while calling ack notifiers because ack
-		 * notifier callbacks for assigned devices call into IOAPIC
-		 * recursively. Since remote_irr is cleared only after call
-		 * to notifiers if the same vector will be delivered while lock
-		 * is dropped it will be put into irr and will be delivered
-		 * after ack notifier returns.
-		 */
-		spin_unlock(&ioapic->lock);
-		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
-		spin_lock(&ioapic->lock);
+	/*
+	 * We are dropping lock while calling ack notifiers because ack
+	 * notifier callbacks for assigned devices call into IOAPIC
+	 * recursively. Since remote_irr is cleared only after call
+	 * to notifiers if the same vector will be delivered while lock
+	 * is dropped it will be put into irr and will be delivered
+	 * after ack notifier returns.
+	 */
+	spin_unlock(&ioapic->lock);
+	kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin);
+	spin_lock(&ioapic->lock);
 
-		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
-		    kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
-			continue;
+	if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+	    kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
+		return;
 
-		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
-		ent->fields.remote_irr = 0;
-		if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
-			++ioapic->irq_eoi[i];
-			if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
-				/*
-				 * Real hardware does not deliver the interrupt
-				 * immediately during eoi broadcast, and this
-				 * lets a buggy guest make slow progress
-				 * even if it does not correctly handle a
-				 * level-triggered interrupt.  Emulate this
-				 * behavior if we detect an interrupt storm.
-				 */
-				schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
-				ioapic->irq_eoi[i] = 0;
-				trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
-			} else {
-				ioapic_service(ioapic, i, false);
-			}
+	ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
+	ent->fields.remote_irr = 0;
+	if (!ent->fields.mask && (ioapic->irr & (1 << pin))) {
+		++ioapic->irq_eoi[pin];
+		if (ioapic->irq_eoi[pin] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+			/*
+			 * Real hardware does not deliver the interrupt
+			 * immediately during eoi broadcast, and this
+			 * lets a buggy guest make slow progress
+			 * even if it does not correctly handle a
+			 * level-triggered interrupt.  Emulate this
+			 * behavior if we detect an interrupt storm.
+			 */
+			schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+			ioapic->irq_eoi[pin] = 0;
+			trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
 		} else {
-			ioapic->irq_eoi[i] = 0;
+			ioapic_service(ioapic, pin, false);
 		}
+	} else {
+		ioapic->irq_eoi[pin] = 0;
 	}
 }
 
 void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
 {
+	int i;
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
 
 	spin_lock(&ioapic->lock);
-	__kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode);
+	rtc_irq_eoi(ioapic, vcpu, vector);
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+		if (ent->fields.vector != vector)
+			continue;
+		kvm_ioapic_update_eoi_one(vcpu, ioapic, trigger_mode, i);
+	}
 	spin_unlock(&ioapic->lock);
 }
 
@@ -515,7 +624,6 @@ static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	addr &= 0xff;
@@ -526,7 +634,7 @@ static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 		break;
 
 	case IOAPIC_REG_WINDOW:
-		result = ioapic_read_indirect(ioapic, addr, len);
+		result = ioapic_read_indirect(ioapic);
 		break;
 
 	default:
@@ -558,8 +666,6 @@ static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
-		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	switch (len) {
@@ -622,11 +728,12 @@ int kvm_ioapic_init(struct kvm *kvm)
 	struct kvm_ioapic *ioapic;
 	int ret;
 
-	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
+	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL_ACCOUNT);
 	if (!ioapic)
 		return -ENOMEM;
 	spin_lock_init(&ioapic->lock);
 	INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
+	INIT_HLIST_HEAD(&ioapic->mask_notifier_list);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);