Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (106 commits)
  KVM: Replace enum by #define
  KVM: Skip pio instruction when it is emulated, not executed
  KVM: x86 emulator: popf
  KVM: x86 emulator: fix src, dst value initialization
  KVM: x86 emulator: jmp abs
  KVM: x86 emulator: lea
  KVM: X86 emulator: jump conditional short
  KVM: x86 emulator: imlpement jump conditional relative
  KVM: x86 emulator: sort opcodes into ascending order
  KVM: Improve emulation failure reporting
  KVM: x86 emulator: pushf
  KVM: x86 emulator: call near
  KVM: x86 emulator: push imm8
  KVM: VMX: Fix exit qualification width on i386
  KVM: Move main vcpu loop into subarch independent code
  KVM: VMX: Move vm entry failure handling to the exit handler
  KVM: MMU: Don't do GFP_NOWAIT allocations
  KVM: Rename kvm_arch_ops to kvm_x86_ops
  KVM: Simplify memory allocation
  KVM: Hoist SVM's get_cs_db_l_bits into core code.
  ...

20 files changed, 4848 insertions, 1875 deletions

diff --git a/drivers/kvm/Kconfig b/drivers/kvm/Kconfig
index 0a419a0de60..8749fa4ffce 100644
--- a/drivers/kvm/Kconfig
+++ b/drivers/kvm/Kconfig
@@ -17,6 +17,7 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on X86 && EXPERIMENTAL
+	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
diff --git a/drivers/kvm/Makefile b/drivers/kvm/Makefile
index c0a789fa9d6..e5a8f4d3e97 100644
--- a/drivers/kvm/Makefile
+++ b/drivers/kvm/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-kvm-objs := kvm_main.o mmu.o x86_emulate.o
+kvm-objs := kvm_main.o mmu.o x86_emulate.o i8259.o irq.o lapic.o ioapic.o
 obj-$(CONFIG_KVM) += kvm.o
 kvm-intel-objs = vmx.o
 obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/drivers/kvm/i8259.c b/drivers/kvm/i8259.c
new file mode 100644
index 00000000000..a679157bc59
--- /dev/null
+++ b/drivers/kvm/i8259.c
@@ -0,0 +1,450 @@
+/*
+ * 8259 interrupt controller emulation
+ *
+ * Copyright (c) 2003-2004 Fabrice Bellard
+ * Copyright (c) 2007 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ * Authors:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *   Port from Qemu.
+ */
+#include <linux/mm.h>
+#include "irq.h"
+
+/*
+ * set irq level. If an edge is detected, then the IRR is set to 1
+ */
+static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
+{
+	int mask;
+	mask = 1 << irq;
+	if (s->elcr & mask)	/* level triggered */
+		if (level) {
+			s->irr |= mask;
+			s->last_irr |= mask;
+		} else {
+			s->irr &= ~mask;
+			s->last_irr &= ~mask;
+		}
+	else	/* edge triggered */
+		if (level) {
+			if ((s->last_irr & mask) == 0)
+				s->irr |= mask;
+			s->last_irr |= mask;
+		} else
+			s->last_irr &= ~mask;
+}
+
+/*
+ * return the highest priority found in mask (highest = smallest
+ * number). Return 8 if no irq
+ */
+static inline int get_priority(struct kvm_kpic_state *s, int mask)
+{
+	int priority;
+	if (mask == 0)
+		return 8;
+	priority = 0;
+	while ((mask & (1 << ((priority + s->priority_add) & 7))) == 0)
+		priority++;
+	return priority;
+}
+
+/*
+ * return the pic wanted interrupt. return -1 if none
+ */
+static int pic_get_irq(struct kvm_kpic_state *s)
+{
+	int mask, cur_priority, priority;
+
+	mask = s->irr & ~s->imr;
+	priority = get_priority(s, mask);
+	if (priority == 8)
+		return -1;
+	/*
+	 * compute current priority. If special fully nested mode on the
+	 * master, the IRQ coming from the slave is not taken into account
+	 * for the priority computation.
+	 */
+	mask = s->isr;
+	if (s->special_fully_nested_mode && s == &s->pics_state->pics[0])
+		mask &= ~(1 << 2);
+	cur_priority = get_priority(s, mask);
+	if (priority < cur_priority)
+		/*
+		 * higher priority found: an irq should be generated
+		 */
+		return (priority + s->priority_add) & 7;
+	else
+		return -1;
+}
+
+/*
+ * raise irq to CPU if necessary. must be called every time the active
+ * irq may change
+ */
+static void pic_update_irq(struct kvm_pic *s)
+{
+	int irq2, irq;
+
+	irq2 = pic_get_irq(&s->pics[1]);
+	if (irq2 >= 0) {
+		/*
+		 * if irq request by slave pic, signal master PIC
+		 */
+		pic_set_irq1(&s->pics[0], 2, 1);
+		pic_set_irq1(&s->pics[0], 2, 0);
+	}
+	irq = pic_get_irq(&s->pics[0]);
+	if (irq >= 0)
+		s->irq_request(s->irq_request_opaque, 1);
+	else
+		s->irq_request(s->irq_request_opaque, 0);
+}
+
+void kvm_pic_update_irq(struct kvm_pic *s)
+{
+	pic_update_irq(s);
+}
+
+void kvm_pic_set_irq(void *opaque, int irq, int level)
+{
+	struct kvm_pic *s = opaque;
+
+	pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
+	pic_update_irq(s);
+}
+
+/*
+ * acknowledge interrupt 'irq'
+ */
+static inline void pic_intack(struct kvm_kpic_state *s, int irq)
+{
+	if (s->auto_eoi) {
+		if (s->rotate_on_auto_eoi)
+			s->priority_add = (irq + 1) & 7;
+	} else
+		s->isr |= (1 << irq);
+	/*
+	 * We don't clear a level sensitive interrupt here
+	 */
+	if (!(s->elcr & (1 << irq)))
+		s->irr &= ~(1 << irq);
+}
+
+int kvm_pic_read_irq(struct kvm_pic *s)
+{
+	int irq, irq2, intno;
+
+	irq = pic_get_irq(&s->pics[0]);
+	if (irq >= 0) {
+		pic_intack(&s->pics[0], irq);
+		if (irq == 2) {
+			irq2 = pic_get_irq(&s->pics[1]);
+			if (irq2 >= 0)
+				pic_intack(&s->pics[1], irq2);
+			else
+				/*
+				 * spurious IRQ on slave controller
+				 */
+				irq2 = 7;
+			intno = s->pics[1].irq_base + irq2;
+			irq = irq2 + 8;
+		} else
+			intno = s->pics[0].irq_base + irq;
+	} else {
+		/*
+		 * spurious IRQ on host controller
+		 */
+		irq = 7;
+		intno = s->pics[0].irq_base + irq;
+	}
+	pic_update_irq(s);
+
+	return intno;
+}
+
+static void pic_reset(void *opaque)
+{
+	struct kvm_kpic_state *s = opaque;
+
+	s->last_irr = 0;
+	s->irr = 0;
+	s->imr = 0;
+	s->isr = 0;
+	s->priority_add = 0;
+	s->irq_base = 0;
+	s->read_reg_select = 0;
+	s->poll = 0;
+	s->special_mask = 0;
+	s->init_state = 0;
+	s->auto_eoi = 0;
+	s->rotate_on_auto_eoi = 0;
+	s->special_fully_nested_mode = 0;
+	s->init4 = 0;
+}
+
+static void pic_ioport_write(void *opaque, u32 addr, u32 val)
+{
+	struct kvm_kpic_state *s = opaque;
+	int priority, cmd, irq;
+
+	addr &= 1;
+	if (addr == 0) {
+		if (val & 0x10) {
+			pic_reset(s);	/* init */
+			/*
+			 * deassert a pending interrupt
+			 */
+			s->pics_state->irq_request(s->pics_state->
+						   irq_request_opaque, 0);
+			s->init_state = 1;
+			s->init4 = val & 1;
+			if (val & 0x02)
+				printk(KERN_ERR "single mode not supported");
+			if (val & 0x08)
+				printk(KERN_ERR
+				       "level sensitive irq not supported");
+		} else if (val & 0x08) {
+			if (val & 0x04)
+				s->poll = 1;
+			if (val & 0x02)
+				s->read_reg_select = val & 1;
+			if (val & 0x40)
+				s->special_mask = (val >> 5) & 1;
+		} else {
+			cmd = val >> 5;
+			switch (cmd) {
+			case 0:
+			case 4:
+				s->rotate_on_auto_eoi = cmd >> 2;
+				break;
+			case 1:	/* end of interrupt */
+			case 5:
+				priority = get_priority(s, s->isr);
+				if (priority != 8) {
+					irq = (priority + s->priority_add) & 7;
+					s->isr &= ~(1 << irq);
+					if (cmd == 5)
+						s->priority_add = (irq + 1) & 7;
+					pic_update_irq(s->pics_state);
+				}
+				break;
+			case 3:
+				irq = val & 7;
+				s->isr &= ~(1 << irq);
+				pic_update_irq(s->pics_state);
+				break;
+			case 6:
+				s->priority_add = (val + 1) & 7;
+				pic_update_irq(s->pics_state);
+				break;
+			case 7:
+				irq = val & 7;
+				s->isr &= ~(1 << irq);
+				s->priority_add = (irq + 1) & 7;
+				pic_update_irq(s->pics_state);
+				break;
+			default:
+				break;	/* no operation */
+			}
+		}
+	} else
+		switch (s->init_state) {
+		case 0:		/* normal mode */
+			s->imr = val;
+			pic_update_irq(s->pics_state);
+			break;
+		case 1:
+			s->irq_base = val & 0xf8;
+			s->init_state = 2;
+			break;
+		case 2:
+			if (s->init4)
+				s->init_state = 3;
+			else
+				s->init_state = 0;
+			break;
+		case 3:
+			s->special_fully_nested_mode = (val >> 4) & 1;
+			s->auto_eoi = (val >> 1) & 1;
+			s->init_state = 0;
+			break;
+		}
+}
+
+static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1)
+{
+	int ret;
+
+	ret = pic_get_irq(s);
+	if (ret >= 0) {
+		if (addr1 >> 7) {
+			s->pics_state->pics[0].isr &= ~(1 << 2);
+			s->pics_state->pics[0].irr &= ~(1 << 2);
+		}
+		s->irr &= ~(1 << ret);
+		s->isr &= ~(1 << ret);
+		if (addr1 >> 7 || ret != 2)
+			pic_update_irq(s->pics_state);
+	} else {
+		ret = 0x07;
+		pic_update_irq(s->pics_state);
+	}
+
+	return ret;
+}
+
+static u32 pic_ioport_read(void *opaque, u32 addr1)
+{
+	struct kvm_kpic_state *s = opaque;
+	unsigned int addr;
+	int ret;
+
+	addr = addr1;
+	addr &= 1;
+	if (s->poll) {
+		ret = pic_poll_read(s, addr1);
+		s->poll = 0;
+	} else
+		if (addr == 0)
+			if (s->read_reg_select)
+				ret = s->isr;
+			else
+				ret = s->irr;
+		else
+			ret = s->imr;
+	return ret;
+}
+
+static void elcr_ioport_write(void *opaque, u32 addr, u32 val)
+{
+	struct kvm_kpic_state *s = opaque;
+	s->elcr = val & s->elcr_mask;
+}
+
+static u32 elcr_ioport_read(void *opaque, u32 addr1)
+{
+	struct kvm_kpic_state *s = opaque;
+	return s->elcr;
+}
+
+static int picdev_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+	switch (addr) {
+	case 0x20:
+	case 0x21:
+	case 0xa0:
+	case 0xa1:
+	case 0x4d0:
+	case 0x4d1:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static void picdev_write(struct kvm_io_device *this,
+			 gpa_t addr, int len, const void *val)
+{
+	struct kvm_pic *s = this->private;
+	unsigned char data = *(unsigned char *)val;
+
+	if (len != 1) {
+		if (printk_ratelimit())
+			printk(KERN_ERR "PIC: non byte write\n");
+		return;
+	}
+	switch (addr) {
+	case 0x20:
+	case 0x21:
+	case 0xa0:
+	case 0xa1:
+		pic_ioport_write(&s->pics[addr >> 7], addr, data);
+		break;
+	case 0x4d0:
+	case 0x4d1:
+		elcr_ioport_write(&s->pics[addr & 1], addr, data);
+		break;
+	}
+}
+
+static void picdev_read(struct kvm_io_device *this,
+			gpa_t addr, int len, void *val)
+{
+	struct kvm_pic *s = this->private;
+	unsigned char data = 0;
+
+	if (len != 1) {
+		if (printk_ratelimit())
+			printk(KERN_ERR "PIC: non byte read\n");
+		return;
+	}
+	switch (addr) {
+	case 0x20:
+	case 0x21:
+	case 0xa0:
+	case 0xa1:
+		data = pic_ioport_read(&s->pics[addr >> 7], addr);
+		break;
+	case 0x4d0:
+	case 0x4d1:
+		data = elcr_ioport_read(&s->pics[addr & 1], addr);
+		break;
+	}
+	*(unsigned char *)val = data;
+}
+
+/*
+ * callback when PIC0 irq status changed
+ */
+static void pic_irq_request(void *opaque, int level)
+{
+	struct kvm *kvm = opaque;
+	struct kvm_vcpu *vcpu = kvm->vcpus[0];
+
+	pic_irqchip(kvm)->output = level;
+	if (vcpu)
+		kvm_vcpu_kick(vcpu);
+}
+
+struct kvm_pic *kvm_create_pic(struct kvm *kvm)
+{
+	struct kvm_pic *s;
+	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL);
+	if (!s)
+		return NULL;
+	s->pics[0].elcr_mask = 0xf8;
+	s->pics[1].elcr_mask = 0xde;
+	s->irq_request = pic_irq_request;
+	s->irq_request_opaque = kvm;
+	s->pics[0].pics_state = s;
+	s->pics[1].pics_state = s;
+
+	/*
+	 * Initialize PIO device
+	 */
+	s->dev.read = picdev_read;
+	s->dev.write = picdev_write;
+	s->dev.in_range = picdev_in_range;
+	s->dev.private = s;
+	kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev);
+	return s;
+}
diff --git a/drivers/kvm/ioapic.c b/drivers/kvm/ioapic.c
new file mode 100644
index 00000000000..c7992e667fd
--- /dev/null
+++ b/drivers/kvm/ioapic.c
@@ -0,0 +1,388 @@
+/*
+ *  Copyright (C) 2001  MandrakeSoft S.A.
+ *
+ *    MandrakeSoft S.A.
+ *    43, rue d'Aboukir
+ *    75002 Paris - France
+ *    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.
+ */
+
+#include "kvm.h"
+#include <linux/kvm.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/smp.h>
+#include <linux/hrtimer.h>
+#include <linux/io.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+#include <asm/page.h>
+#include <asm/current.h>
+#include <asm/apicdef.h>
+#include <asm/io_apic.h>
+#include "irq.h"
+/* #define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
+#define ioapic_debug(fmt, arg...)
+static void ioapic_deliver(struct kvm_ioapic *vioapic, int irq);
+
+static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
+					  unsigned long addr,
+					  unsigned long length)
+{
+	unsigned long result = 0;
+
+	switch (ioapic->ioregsel) {
+	case IOAPIC_REG_VERSION:
+		result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16)
+			  | (IOAPIC_VERSION_ID & 0xff));
+		break;
+
+	case IOAPIC_REG_APIC_ID:
+	case IOAPIC_REG_ARB_ID:
+		result = ((ioapic->id & 0xf) << 24);
+		break;
+
+	default:
+		{
+			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
+			u64 redir_content;
+
+			ASSERT(redir_index < IOAPIC_NUM_PINS);
+
+			redir_content = ioapic->redirtbl[redir_index].bits;
+			result = (ioapic->ioregsel & 0x1) ?
+			    (redir_content >> 32) & 0xffffffff :
+			    redir_content & 0xffffffff;
+			break;
+		}
+	}
+
+	return result;
+}
+
+static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
+{
+	union ioapic_redir_entry *pent;
+
+	pent = &ioapic->redirtbl[idx];
+
+	if (!pent->fields.mask) {
+		ioapic_deliver(ioapic, idx);
+		if (pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
+			pent->fields.remote_irr = 1;
+	}
+	if (!pent->fields.trig_mode)
+		ioapic->irr &= ~(1 << idx);
+}
+
+static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
+{
+	unsigned index;
+
+	switch (ioapic->ioregsel) {
+	case IOAPIC_REG_VERSION:
+		/* Writes are ignored. */
+		break;
+
+	case IOAPIC_REG_APIC_ID:
+		ioapic->id = (val >> 24) & 0xf;
+		break;
+
+	case IOAPIC_REG_ARB_ID:
+		break;
+
+	default:
+		index = (ioapic->ioregsel - 0x10) >> 1;
+
+		ioapic_debug("change redir index %x val %x", index, val);
+		if (index >= IOAPIC_NUM_PINS)
+			return;
+		if (ioapic->ioregsel & 1) {
+			ioapic->redirtbl[index].bits &= 0xffffffff;
+			ioapic->redirtbl[index].bits |= (u64) val << 32;
+		} else {
+			ioapic->redirtbl[index].bits &= ~0xffffffffULL;
+			ioapic->redirtbl[index].bits |= (u32) val;
+			ioapic->redirtbl[index].fields.remote_irr = 0;
+		}
+		if (ioapic->irr & (1 << index))
+			ioapic_service(ioapic, index);
+		break;
+	}
+}
+
+static void ioapic_inj_irq(struct kvm_ioapic *ioapic,
+			   struct kvm_lapic *target,
+			   u8 vector, u8 trig_mode, u8 delivery_mode)
+{
+	ioapic_debug("irq %d trig %d deliv %d", vector, trig_mode,
+		     delivery_mode);
+
+	ASSERT((delivery_mode == dest_Fixed) ||
+	       (delivery_mode == dest_LowestPrio));
+
+	kvm_apic_set_irq(target, vector, trig_mode);
+}
+
+static u32 ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
+				       u8 dest_mode)
+{
+	u32 mask = 0;
+	int i;
+	struct kvm *kvm = ioapic->kvm;
+	struct kvm_vcpu *vcpu;
+
+	ioapic_debug("dest %d dest_mode %d", dest, dest_mode);
+
+	if (dest_mode == 0) {	/* Physical mode. */
+		if (dest == 0xFF) {	/* Broadcast. */
+			for (i = 0; i < KVM_MAX_VCPUS; ++i)
+				if (kvm->vcpus[i] && kvm->vcpus[i]->apic)
+					mask |= 1 << i;
+			return mask;
+		}
+		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+			vcpu = kvm->vcpus[i];
+			if (!vcpu)
+				continue;
+			if (kvm_apic_match_physical_addr(vcpu->apic, dest)) {
+				if (vcpu->apic)
+					mask = 1 << i;
+				break;
+			}
+		}
+	} else if (dest != 0)	/* Logical mode, MDA non-zero. */
+		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+			vcpu = kvm->vcpus[i];
+			if (!vcpu)
+				continue;
+			if (vcpu->apic &&
+			    kvm_apic_match_logical_addr(vcpu->apic, dest))
+				mask |= 1 << vcpu->vcpu_id;
+		}
+	ioapic_debug("mask %x", mask);
+	return mask;
+}
+
+static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
+{
+	u8 dest = ioapic->redirtbl[irq].fields.dest_id;
+	u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode;
+	u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode;
+	u8 vector = ioapic->redirtbl[irq].fields.vector;
+	u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode;
+	u32 deliver_bitmask;
+	struct kvm_lapic *target;
+	struct kvm_vcpu *vcpu;
+	int vcpu_id;
+
+	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
+		     "vector=%x trig_mode=%x",
+		     dest, dest_mode, delivery_mode, vector, trig_mode);
+
+	deliver_bitmask = ioapic_get_delivery_bitmask(ioapic, dest, dest_mode);
+	if (!deliver_bitmask) {
+		ioapic_debug("no target on destination");
+		return;
+	}
+
+	switch (delivery_mode) {
+	case dest_LowestPrio:
+		target =
+		    kvm_apic_round_robin(ioapic->kvm, vector, deliver_bitmask);
+		if (target != NULL)
+			ioapic_inj_irq(ioapic, target, vector,
+				       trig_mode, delivery_mode);
+		else
+			ioapic_debug("null round robin: "
+				     "mask=%x vector=%x delivery_mode=%x",
+				     deliver_bitmask, vector, dest_LowestPrio);
+		break;
+	case dest_Fixed:
+		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
+			if (!(deliver_bitmask & (1 << vcpu_id)))
+				continue;
+			deliver_bitmask &= ~(1 << vcpu_id);
+			vcpu = ioapic->kvm->vcpus[vcpu_id];
+			if (vcpu) {
+				target = vcpu->apic;
+				ioapic_inj_irq(ioapic, target, vector,
+					       trig_mode, delivery_mode);
+			}
+		}
+		break;
+
+		/* TODO: NMI */
+	default:
+		printk(KERN_WARNING "Unsupported delivery mode %d\n",
+		       delivery_mode);
+		break;
+	}
+}
+
+void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
+{
+	u32 old_irr = ioapic->irr;
+	u32 mask = 1 << irq;
+	union ioapic_redir_entry entry;
+
+	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
+		entry = ioapic->redirtbl[irq];
+		level ^= entry.fields.polarity;
+		if (!level)
+			ioapic->irr &= ~mask;
+		else {
+			ioapic->irr |= mask;
+			if ((!entry.fields.trig_mode && old_irr != ioapic->irr)
+			    || !entry.fields.remote_irr)
+				ioapic_service(ioapic, irq);
+		}
+	}
+}
+
+static int get_eoi_gsi(struct kvm_ioapic *ioapic, int vector)
+{
+	int i;
+
+	for (i = 0; i < IOAPIC_NUM_PINS; i++)
+		if (ioapic->redirtbl[i].fields.vector == vector)
+			return i;
+	return -1;
+}
+
+void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
+{
+	struct kvm_ioapic *ioapic = kvm->vioapic;
+	union ioapic_redir_entry *ent;
+	int gsi;
+
+	gsi = get_eoi_gsi(ioapic, vector);
+	if (gsi == -1) {
+		printk(KERN_WARNING "Can't find redir item for %d EOI\n",
+		       vector);
+		return;
+	}
+
+	ent = &ioapic->redirtbl[gsi];
+	ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
+
+	ent->fields.remote_irr = 0;
+	if (!ent->fields.mask && (ioapic->irr & (1 << gsi)))
+		ioapic_deliver(ioapic, gsi);
+}
+
+static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+
+	return ((addr >= ioapic->base_address &&
+		 (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
+}
+
+static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
+			     void *val)
+{
+	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	u32 result;
+
+	ioapic_debug("addr %lx", (unsigned long)addr);
+	ASSERT(!(addr & 0xf));	/* check alignment */
+
+	addr &= 0xff;
+	switch (addr) {
+	case IOAPIC_REG_SELECT:
+		result = ioapic->ioregsel;
+		break;
+
+	case IOAPIC_REG_WINDOW:
+		result = ioapic_read_indirect(ioapic, addr, len);
+		break;
+
+	default:
+		result = 0;
+		break;
+	}
+	switch (len) {
+	case 8:
+		*(u64 *) val = result;
+		break;
+	case 1:
+	case 2:
+	case 4:
+		memcpy(val, (char *)&result, len);
+		break;
+	default:
+		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
+	}
+}
+
+static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
+			      const void *val)
+{
+	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	u32 data;
+
+	ioapic_debug("ioapic_mmio_write addr=%lx len=%d val=%p\n",
+		     addr, len, val);
+	ASSERT(!(addr & 0xf));	/* check alignment */
+	if (len == 4 || len == 8)
+		data = *(u32 *) val;
+	else {
+		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
+		return;
+	}
+
+	addr &= 0xff;
+	switch (addr) {
+	case IOAPIC_REG_SELECT:
+		ioapic->ioregsel = data;
+		break;
+
+	case IOAPIC_REG_WINDOW:
+		ioapic_write_indirect(ioapic, data);
+		break;
+
+	default:
+		break;
+	}
+}
+
+int kvm_ioapic_init(struct kvm *kvm)
+{
+	struct kvm_ioapic *ioapic;
+	int i;
+
+	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
+	if (!ioapic)
+		return -ENOMEM;
+	kvm->vioapic = ioapic;
+	for (i = 0; i < IOAPIC_NUM_PINS; i++)
+		ioapic->redirtbl[i].fields.mask = 1;
+	ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
+	ioapic->dev.read = ioapic_mmio_read;
+	ioapic->dev.write = ioapic_mmio_write;
+	ioapic->dev.in_range = ioapic_in_range;
+	ioapic->dev.private = ioapic;
+	ioapic->kvm = kvm;
+	kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
+	return 0;
+}
diff --git a/drivers/kvm/irq.c b/drivers/kvm/irq.c
new file mode 100644
index 00000000000..7628c7ff628
--- /dev/null
+++ b/drivers/kvm/irq.c
@@ -0,0 +1,98 @@
+/*
+ * irq.c: API for in kernel interrupt controller
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * Authors:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+
+#include "kvm.h"
+#include "irq.h"
+
+/*
+ * check if there is pending interrupt without
+ * intack.
+ */
+int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
+{
+	struct kvm_pic *s;
+
+	if (kvm_apic_has_interrupt(v) == -1) {	/* LAPIC */
+		if (kvm_apic_accept_pic_intr(v)) {
+			s = pic_irqchip(v->kvm);	/* PIC */
+			return s->output;
+		} else
+			return 0;
+	}
+	return 1;
+}
+EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
+
+/*
+ * Read pending interrupt vector and intack.
+ */
+int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
+{
+	struct kvm_pic *s;
+	int vector;
+
+	vector = kvm_get_apic_interrupt(v);	/* APIC */
+	if (vector == -1) {
+		if (kvm_apic_accept_pic_intr(v)) {
+			s = pic_irqchip(v->kvm);
+			s->output = 0;		/* PIC */
+			vector = kvm_pic_read_irq(s);
+		}
+	}
+	return vector;
+}
+EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
+
+static void vcpu_kick_intr(void *info)
+{
+#ifdef DEBUG
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
+	printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu);
+#endif
+}
+
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	int ipi_pcpu = vcpu->cpu;
+
+	if (waitqueue_active(&vcpu->wq)) {
+		wake_up_interruptible(&vcpu->wq);
+		++vcpu->stat.halt_wakeup;
+	}
+	if (vcpu->guest_mode)
+		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+}
+
+void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
+{
+	kvm_inject_apic_timer_irqs(vcpu);
+	/* TODO: PIT, RTC etc. */
+}
+EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
+
+void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
+{
+	kvm_apic_timer_intr_post(vcpu, vec);
+	/* TODO: PIT, RTC etc. */
+}
+EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
diff --git a/drivers/kvm/irq.h b/drivers/kvm/irq.h
new file mode 100644
index 00000000000..11fc014e2b3
--- /dev/null
+++ b/drivers/kvm/irq.h
@@ -0,0 +1,165 @@
+/*
+ * irq.h: in kernel interrupt controller related definitions
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * Authors:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include "kvm.h"
+
+typedef void irq_request_func(void *opaque, int level);
+
+struct kvm_kpic_state {
+	u8 last_irr;	/* edge detection */
+	u8 irr;		/* interrupt request register */
+	u8 imr;		/* interrupt mask register */
+	u8 isr;		/* interrupt service register */
+	u8 priority_add;	/* highest irq priority */
+	u8 irq_base;
+	u8 read_reg_select;
+	u8 poll;
+	u8 special_mask;
+	u8 init_state;
+	u8 auto_eoi;
+	u8 rotate_on_auto_eoi;
+	u8 special_fully_nested_mode;
+	u8 init4;		/* true if 4 byte init */
+	u8 elcr;		/* PIIX edge/trigger selection */
+	u8 elcr_mask;
+	struct kvm_pic *pics_state;
+};
+
+struct kvm_pic {
+	struct kvm_kpic_state pics[2]; /* 0