Merge branch 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: Prevent overflow in largepages calculation
  KVM: Disable large pages on misaligned memory slots
  KVM: Add VT-x machine check support
  KVM: VMX: Rename rmode.active to rmode.vm86_active
  KVM: Move "exit due to NMI" handling into vmx_complete_interrupts()
  KVM: Disable CR8 intercept if tpr patching is active
  KVM: Do not migrate pending software interrupts.
  KVM: inject NMI after IRET from a previous NMI, not before.
  KVM: Always request IRQ/NMI window if an interrupt is pending
  KVM: Do not re-execute INTn instruction.
  KVM: skip_emulated_instruction() decode instruction if size is not known
  KVM: Remove irq_pending bitmap
  KVM: Do not allow interrupt injection from userspace if there is a pending event.
  KVM: Unprotect a page if #PF happens during NMI injection.
  KVM: s390: Verify memory in kvm run
  KVM: s390: Sanity check on validity intercept
  KVM: s390: Unlink vcpu on destroy - v2
  KVM: s390: optimize float int lock: spin_lock_bh --> spin_lock
  KVM: s390: use hrtimer for clock wakeup from idle - v2
  KVM: s390: Fix memory slot versus run - v3
  ...

13 files changed, 285 insertions, 113 deletions

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 4542651e6acb..5f43697aed30 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -371,6 +371,7 @@ struct kvm_vcpu_arch {
 	int last_run_cpu;
 	int vmm_tr_slot;
 	int vm_tr_slot;
+	int sn_rtc_tr_slot;
 
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
@@ -465,6 +466,7 @@ struct kvm_arch {
 	unsigned long	vmm_init_rr;
 
 	int		online_vcpus;
+	int		is_sn2;
 
 	struct kvm_ioapic *vioapic;
 	struct kvm_vm_stat stat;
@@ -472,6 +474,7 @@ struct kvm_arch {
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
+	int iommu_flags;
 	struct hlist_head irq_ack_notifier_list;
 
 	unsigned long irq_sources_bitmap;
@@ -578,6 +581,8 @@ struct kvm_vmm_info{
 	kvm_vmm_entry 	*vmm_entry;
 	kvm_tramp_entry *tramp_entry;
 	unsigned long 	vmm_ivt;
+	unsigned long	patch_mov_ar;
+	unsigned long	patch_mov_ar_sn2;
 };
 
 int kvm_highest_pending_irq(struct kvm_vcpu *vcpu);
@@ -585,7 +590,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 void kvm_sal_emul(struct kvm_vcpu *vcpu);
 
-static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
 #endif /* __ASSEMBLY__*/
 
 #endif
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 7a9bff47564f..0a9cc73d35c7 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -146,6 +146,8 @@
 #define PAGE_GATE	__pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_X_RX)
 #define PAGE_KERNEL	__pgprot(__DIRTY_BITS  | _PAGE_PL_0 | _PAGE_AR_RWX)
 #define PAGE_KERNELRX	__pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_RX)
+#define PAGE_KERNEL_UC	__pgprot(__DIRTY_BITS  | _PAGE_PL_0 | _PAGE_AR_RWX | \
+				 _PAGE_MA_UC)
 
 # ifndef __ASSEMBLY__
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index acc4d19ae62a..b448197728be 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -610,6 +610,9 @@ static struct irqaction ipi_irqaction = {
 	.name =		"IPI"
 };
 
+/*
+ * KVM uses this interrupt to force a cpu out of guest mode
+ */
 static struct irqaction resched_irqaction = {
 	.handler =	dummy_handler,
 	.flags =	IRQF_DISABLED,
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index 0a2d6b86075a..64d520937874 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -23,7 +23,7 @@ if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
-	depends on HAVE_KVM && EXPERIMENTAL
+	depends on HAVE_KVM && MODULES && EXPERIMENTAL
 	# for device assignment:
 	depends on PCI
 	select PREEMPT_NOTIFIERS
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index d20a5db4c4dd..80c57b0a21c4 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -41,6 +41,9 @@
 #include <asm/div64.h>
 #include <asm/tlb.h>
 #include <asm/elf.h>
+#include <asm/sn/addrs.h>
+#include <asm/sn/clksupport.h>
+#include <asm/sn/shub_mmr.h>
 
 #include "misc.h"
 #include "vti.h"
@@ -65,6 +68,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (vcpu->kvm->arch.is_sn2)
+		return rtc_time();
+	else
+#endif
+		return ia64_getreg(_IA64_REG_AR_ITC);
+}
+
 static void kvm_flush_icache(unsigned long start, unsigned long len)
 {
 	int l;
@@ -119,8 +132,7 @@ void kvm_arch_hardware_enable(void *garbage)
 	unsigned long saved_psr;
 	int slot;
 
-	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
-				PAGE_KERNEL));
+	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
 	local_irq_save(saved_psr);
 	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
 	local_irq_restore(saved_psr);
@@ -283,6 +295,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 }
 
+static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector)
+{
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+	if (!test_and_set_bit(vector, &vpd->irr[0])) {
+		vcpu->arch.irq_new_pending = 1;
+		kvm_vcpu_kick(vcpu);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  *  offset: address offset to IPI space.
  *  value:  deliver value.
@@ -292,20 +316,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
 {
 	switch (dm) {
 	case SAPIC_FIXED:
-		kvm_apic_set_irq(vcpu, vector, 0);
 		break;
 	case SAPIC_NMI:
-		kvm_apic_set_irq(vcpu, 2, 0);
+		vector = 2;
 		break;
 	case SAPIC_EXTINT:
-		kvm_apic_set_irq(vcpu, 0, 0);
+		vector = 0;
 		break;
 	case SAPIC_INIT:
 	case SAPIC_PMI:
 	default:
 		printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
-		break;
+		return;
 	}
+	__apic_accept_irq(vcpu, vector);
 }
 
 static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
@@ -413,6 +437,23 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu)
+{
+	unsigned long pte, rtc_phys_addr, map_addr;
+	int slot;
+
+	map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT);
+	rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC;
+	pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC));
+	slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT);
+	vcpu->arch.sn_rtc_tr_slot = slot;
+	if (slot < 0) {
+		printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n");
+		slot = 0;
+	}
+	return slot;
+}
+
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
 
@@ -426,7 +467,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
 
-		vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
+		vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset;
 
 		if (time_after(vcpu_now_itc, vpd->itm)) {
 			vcpu->arch.timer_check = 1;
@@ -447,10 +488,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 		hrtimer_cancel(p_ht);
 		vcpu->arch.ht_active = 0;
 
-		if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
+		if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) ||
+				kvm_cpu_has_pending_timer(vcpu))
 			if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
-				vcpu->arch.mp_state =
-					KVM_MP_STATE_RUNNABLE;
+				vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
 			return -EINTR;
@@ -551,22 +592,35 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		goto out;
 	vcpu->arch.vm_tr_slot = r;
+
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (kvm->arch.is_sn2) {
+		r = kvm_sn2_setup_mappings(vcpu);
+		if (r < 0)
+			goto out;
+	}
+#endif
+
 	r = 0;
 out:
 	return r;
-
 }
 
 static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
 {
-
+	struct kvm *kvm = vcpu->kvm;
 	ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
 	ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
-
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (kvm->arch.is_sn2)
+		ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot);
+#endif
 }
 
 static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
 {
+	unsigned long psr;
+	int r;
 	int cpu = smp_processor_id();
 
 	if (vcpu->arch.last_run_cpu != cpu ||
@@ -578,36 +632,27 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.host_rr6 = ia64_get_rr(RR6);
 	vti_set_rr6(vcpu->arch.vmm_rr);
-	return kvm_insert_vmm_mapping(vcpu);
+	local_irq_save(psr);
+	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
+	return r;
 }
+
 static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
 {
 	kvm_purge_vmm_mapping(vcpu);
 	vti_set_rr6(vcpu->arch.host_rr6);
 }
 
-static int  vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	union context *host_ctx, *guest_ctx;
 	int r;
 
-	/*Get host and guest context with guest address space.*/
-	host_ctx = kvm_get_host_context(vcpu);
-	guest_ctx = kvm_get_guest_context(vcpu);
-
-	r = kvm_vcpu_pre_transition(vcpu);
-	if (r < 0)
-		goto out;
-	kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
-	kvm_vcpu_post_transition(vcpu);
-	r = 0;
-out:
-	return r;
-}
-
-static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
-{
-	int r;
+	/*
+	 * down_read() may sleep and return with interrupts enabled
+	 */
+	down_read(&vcpu->kvm->slots_lock);
 
 again:
 	if (signal_pending(current)) {
@@ -616,26 +661,31 @@ again:
 		goto out;
 	}
 
-	/*
-	 * down_read() may sleep and return with interrupts enabled
-	 */
-	down_read(&vcpu->kvm->slots_lock);
-
 	preempt_disable();
 	local_irq_disable();
 
-	vcpu->guest_mode = 1;
+	/*Get host and guest context with guest address space.*/
+	host_ctx = kvm_get_host_context(vcpu);
+	guest_ctx = kvm_get_guest_context(vcpu);
+
+	clear_bit(KVM_REQ_KICK, &vcpu->requests);
+
+	r = kvm_vcpu_pre_transition(vcpu);
+	if (r < 0)
+		goto vcpu_run_fail;
+
+	up_read(&vcpu->kvm->slots_lock);
 	kvm_guest_enter();
-	r = vti_vcpu_run(vcpu, kvm_run);
-	if (r < 0) {
-		local_irq_enable();
-		preempt_enable();
-		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
-		goto out;
-	}
+
+	/*
+	 * Transition to the guest
+	 */
+	kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
+
+	kvm_vcpu_post_transition(vcpu);
 
 	vcpu->arch.launched = 1;
-	vcpu->guest_mode = 0;
+	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();
 
 	/*
@@ -646,9 +696,10 @@ again:
 	 */
 	barrier();
 	kvm_guest_exit();
-	up_read(&vcpu->kvm->slots_lock);
 	preempt_enable();
 
+	down_read(&vcpu->kvm->slots_lock);
+
 	r = kvm_handle_exit(kvm_run, vcpu);
 
 	if (r > 0) {
@@ -657,12 +708,20 @@ again:
 	}
 
 out:
+	up_read(&vcpu->kvm->slots_lock);
 	if (r > 0) {
 		kvm_resched(vcpu);
+		down_read(&vcpu->kvm->slots_lock);
 		goto again;
 	}
 
 	return r;
+
+vcpu_run_fail:
+	local_irq_enable();
+	preempt_enable();
+	kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+	goto out;
 }
 
 static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
@@ -788,6 +847,9 @@ struct  kvm *kvm_arch_create_vm(void)
 
 	if (IS_ERR(kvm))
 		return ERR_PTR(-ENOMEM);
+
+	kvm->arch.is_sn2 = ia64_platform_is("sn2");
+
 	kvm_init_vm(kvm);
 
 	kvm->arch.online_vcpus = 0;
@@ -884,7 +946,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	RESTORE_REGS(saved_gp);
 
 	vcpu->arch.irq_new_pending = 1;
-	vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
+	vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu);
 	set_bit(KVM_REQ_RESUME, &vcpu->requests);
 
 	vcpu_put(vcpu);
@@ -1043,10 +1105,6 @@ static void kvm_free_vmm_area(void)
 	}
 }
 
-static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-{
-}
-
 static int vti_init_vpd(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -1165,7 +1223,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		regs->cr_iip = PALE_RESET_ENTRY;
 
 		/*Initialize itc offset for vcpus*/
-		itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
+		itc_offset = 0UL - kvm_get_itc(vcpu);
 		for (i = 0; i < kvm->arch.online_vcpus; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
@@ -1237,6 +1295,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
 
 	local_irq_save(psr);
 	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
 	if (r)
 		goto fail;
 	r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
@@ -1254,13 +1313,11 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
 		goto uninit;
 
 	kvm_purge_vmm_mapping(vcpu);
-	local_irq_restore(psr);
 
 	return 0;
 uninit:
 	kvm_vcpu_uninit(vcpu);
 fail:
-	local_irq_restore(psr);
 	return r;
 }
 
@@ -1291,7 +1348,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->kvm = kvm;
 
 	cpu = get_cpu();
-	vti_vcpu_load(vcpu, cpu);
 	r = vti_vcpu_setup(vcpu, id);
 	put_cpu();
 
@@ -1427,7 +1483,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	}
 	for (i = 0; i < 4; i++)
 		regs->insvc[i] = vcpu->arch.insvc[i];
-	regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
+	regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu);
 	SAVE_REGS(xtp);
 	SAVE_REGS(metaphysical_rr0);
 	SAVE_REGS(metaphysical_rr4);
@@ -1574,6 +1630,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
+	kvm_flush_remote_tlbs(kvm);
 }
 
 long kvm_arch_dev_ioctl(struct file *filp,
@@ -1616,8 +1673,37 @@ out:
 	return 0;
 }
 
+
+/*
+ * On SN2, the ITC isn't stable, so copy in fast path code to use the
+ * SN2 RTC, replacing the ITC based default verion.
+ */
+static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info,
+			  struct module *module)
+{
+	unsigned long new_ar, new_ar_sn2;
+	unsigned long module_base;
+
+	if (!ia64_platform_is("sn2"))
+		return;
+
+	module_base = (unsigned long)module->module_core;
+
+	new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base;
+	new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base;
+
+	printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC "
+	       "as source\n");
+
+	/*
+	 * Copy the SN2 version of mov_ar into place. They are both
+	 * the same size, so 6 bundles is sufficient (6 * 0x10).
+	 */
+	memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60);
+}
+
 static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
-						struct module *module)
+			    struct module *module)
 {
 	unsigned long module_base;
 	unsigned long vmm_size;
@@ -1639,6 +1725,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
 		return -EFAULT;
 
 	memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
+	kvm_patch_vmm(vmm_info, module);
 	kvm_flush_icache(kvm_vmm_base, vmm_size);
 
 	/*Recalculate kvm_vmm_info based on new VMM*/
@@ -1792,38 +1879,24 @@ void kvm_arch_hardware_unsetup(void)
 {
 }
 
-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;
-	int cpu = get_cpu();
+	int me;
+	int cpu = vcpu->cpu;
 
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
 
-	if (vcpu->guest_mode && cpu != ipi_pcpu)
-		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
+	me = get_cpu();
+	if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu))
+		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
+			smp_send_reschedule(cpu);
 	put_cpu();
 }
 
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
 {
-
-	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
-
-	if (!test_and_set_bit(vec, &vpd->irr[0])) {
-		vcpu->arch.irq_new_pending = 1;
-		kvm_vcpu_kick(vcpu);
-		return 1;
-	}
-	return 0;
+	return __apic_accept_irq(vcpu, irq->vector);
 }
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
@@ -1836,20 +1909,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 	return 0;
 }
 
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap)
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
-	struct kvm_vcpu *lvcpu = kvm->vcpus[0];
-	int i;
-
-	for (i = 1; i < kvm->arch.online_vcpus; i++) {
-		if (!kvm->vcpus[i])
-			continue;
-		if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
-			lvcpu = kvm->vcpus[i];
-	}
+	return vcpu1->arch.xtp - vcpu2->arch.xtp;
+}
 
-	return lvcpu;
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode)
+{
+	struct kvm_lapic *target = vcpu->arch.apic;
+	return (dest_mode == 0) ?
+		kvm_apic_match_physical_addr(target, dest) :
+		kvm_apic_match_logical_addr(target, dest);
 }
 
 static int find_highest_bits(int *dat)
@@ -1888,6 +1959,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	/* do real check here */
+	return 1;
+}
+
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.timer_fired;
@@ -1918,6 +1995,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
 	long psr;
 	local_irq_save(psr);
 	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
 	if (r)
 		goto fail;
 
@@ -1930,7 +2008,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
 	kvm_purge_vmm_mapping(vcpu);
 	r = 0;
 fail:
-	local_irq_restore(psr);
 	return r;
 }
 
diff --git a/arch/ia64/kvm/kvm_fw.c b/arch/ia64/kvm/kvm_fw.c
index a8ae52ed5635..e4b82319881d 100644
--- a/arch/ia64/kvm/kvm_fw.c
+++ b/arch/ia64/kvm/kvm_fw.c
@@ -21,6 +21,9 @@
 
 #include <linux/kvm_host.h>
 #include <linux/smp.h>
+#include <asm/sn/addrs.h>
+#include <asm/sn/clksupport.h>
+#include <asm/sn/shub_mmr.h>
 
 #include "vti.h"
 #include "misc.h"
@@ -188,12 +191,35 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
 	return result;
 }
 
-static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
+/*
+ * On the SGI SN2, the ITC isn't stable. Emulation backed by the SN2
+ * RTC is used instead. This function patches the ratios from SAL
+ * to match the RTC before providing them to the guest.
+ */
+static void sn2_patch_itc_freq_ratios(struct ia64_pal_retval *result)
 {
+	struct pal_freq_ratio *ratio;
+	unsigned long sal_freq, sal_drift, factor;
+
+	result->status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
+					    &sal_freq, &sal_drift);
+	ratio = (struct pal_freq_ratio *)&result->v2;
+	factor = ((sal_freq * 3) + (sn_rtc_cycles_per_second / 2)) /
+		sn_rtc_cycles_per_second;
+
+	ratio->num = 3;
+	ratio->den = factor;
+}
 
+static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
+{
 	struct ia64_pal_retval result;
 
 	PAL_CALL(result, PAL_FREQ_RATIOS, 0, 0, 0);
+
+	if (vcpu->kvm->arch.is_sn2)
+		sn2_patch_itc_freq_ratios(&result);
+
 	return result;
 }
 
diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h
index 6d6cbcb14893..ee541cebcd78 100644
--- a/arch/ia64/kvm/lapic.h
+++ b/arch/ia64/kvm/lapic.h
@@ -20,6 +20,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
+#define kvm_apic_present(x) (true)
 
 #endif
diff --git a/arch/ia64/kvm/optvfault.S b/arch/ia64/kvm/optvfault.S
index 32254ce9a1bd..f793be3effff 100644
--- a/arch/ia64/kvm/optvfault.S
+++ b/arch/ia64/kvm/optvfault.S
@@ -11,6 +11,7 @@
 
 #include <asm/asmmacro.h>
 #include <asm/processor.h>
+#include <asm/kvm_host.h>
 
 #include "vti.h"
 #include "asm-offsets.h"
@@ -140,6 +141,35 @@ GLOBAL_ENTRY(kvm_asm_mov_from_ar)
 	;;
 END(kvm_asm_mov_from_ar)
 
+/*
+ * Special SGI SN2 optimized version of mov_from_ar using the SN2 RTC
+ * clock as it's source for emulating the ITC. This version will be
+ * copied on top of the original version if the host is determined to
+ * be an SN2.
+ */
+GLOBAL_ENTRY(kvm_asm_mov_from_ar_sn2)
+	add r18=VMM_VCPU_ITC_OFS_OFFSET, r21
+	movl r19 = (KVM_VMM_BASE+(1<<KVM_VMM_SHIFT))
+
+	add r16=VMM_VCPU_LAST_ITC_OFFSET,r21
+	extr.u r17=r25,6,7
+	mov r24=b0
+	;;
+	ld8 r18=[r18]
+	ld8 r19=[r19]
+	addl r20=@gprel(asm_mov_to_reg),gp
+	;;
+	add r19=r19,r18
+	shladd r17=r17,4,r20
+	;;
+	adds r30=kvm_resume_to_guest-asm_mov_to_reg,r20
+	st8 [r16] = r19
+	mov b0=r17
+	br.sptk.few b0
+	;;
+END(kvm_asm_mov_from_ar_sn2)
+
+
 
 // mov r1=rr[r3]
 GLOBAL_ENTRY(kvm_asm_mov_from_rr)
diff --git a/arch/ia64/kvm/process.c b/arch/ia64/kvm/process.c
index b1dc80952d91..a8f84da04b49 100644
--- a/arch/ia64/kvm/process.c
+++ b/arch/ia64/kvm/process.c
@@ -652,20 +652,25 @@ void  kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
 		unsigned long isr, unsigned long iim)
 {
 	struct kvm_vcpu *v = current_vcpu;
+	long psr;
 
 	if (ia64_psr(regs)->cpl == 0) {
 		/* Allow hypercalls only when cpl = 0.  */
 		if (iim == DOMN_PAL_REQUEST) {
+			local_irq_save(psr);
 			set_pal_call_data(v);
 			vmm_transition(v);
 			get_pal_call_result(v);
 			vcpu_increment_iip(v);
+			local_irq_restore(psr);
 			return;
 		} else if (iim == DOMN_SAL_REQUEST) {
+			local_irq_save(psr);
 			set_sal_call_data(v);
 			vmm_transition(v);
 			get_sal_call_result(v);
 			vcpu_increment_iip(v);
+			local_irq_restore(psr);
 			return;
 		}
 	}
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index a18ee17b9192..a2c6c15e4761 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/arch/ia64/kvm/vcpu.c
@@ -788,13 +788,29 @@ void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
 		setfpreg(reg, val, regs);   /* FIXME: handle NATs later*/
 }
 
+/*
+ * The Altix RTC is mapped specially here for the vmm module
+ */
+#define SN_RTC_BASE	(u64 *)(KVM_VMM_BASE+(1UL<<KVM_VMM_SHIFT))
+static long kvm_get_itc(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	struct kvm *kvm = (struct kvm *)KVM_VM_BASE;
+
+	if (kvm->arch.is_sn2)
+		return (*SN_RTC_BASE);
+	else
+#endif
+		return ia64_getreg(_IA64_REG_AR_ITC);
+}
+
 /************************************************************************
  * lsapic timer
  ***********************************************************************/
 u64 vcpu_get_itc(struct kvm_vcpu *vcpu)
 {
 	unsigned long guest_itc;
-	guest_itc = VMX(vcpu, itc_offset) + ia64_getreg(_IA64_REG_AR_ITC);
+	guest_itc = VMX(vcpu, itc_offset) + kvm_get_itc(vcpu);
 
 	if (guest_itc >= VMX(vcpu, last_itc)) {
 		VMX(vcpu, last_itc) = guest_itc;
@@ -809,7 +825,7 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
 	struct kvm_vcpu *v;
 	struct kvm *kvm;
 	int i;
-	long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
+	long itc_offset = val - kvm_get_itc(vcpu);
 	unsigned long vitv = VCPU(vcpu, itv);
 
 	kvm = (struct kvm *)KVM_VM_BASE;
diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c
index 9eee5c04bacc..f4b4c899bb6c 100644
--- a/arch/ia64/kvm/vmm.c
+++ b/arch/ia64/kvm/vmm.c
@@ -30,15 +30,19 @@ MODULE_AUTHOR("Intel");
 MODULE_LICENSE("GPL");
 
 extern char kvm_ia64_ivt;
+extern char kvm_asm_mov_from_ar;
+extern char kvm_asm_mov_from_ar_sn2;
 extern fpswa_interface_t *vmm_fpswa_interface;
 
 long vmm_sanity = 1;
 
 struct kvm_vmm_info vmm_info = {
-	.module	     = THIS_MODULE,
-	.vmm_entry   = vmm_entry,
-	.tramp_entry = vmm_trampoline,
-	.vmm_ivt     = (unsigned long)&kvm_ia64_ivt,
+	.module			= THIS_MODULE,
+	.vmm_entry		= vmm_entry,
+	.tramp_entry		= vmm_trampoline,
+	.vmm_ivt		= (unsigned long)&kvm_ia64_ivt,
+	.patch_mov_ar		= (unsigned long)&kvm_asm_mov_from_ar,
+	.patch_mov_ar_sn2	= (unsigned long)&kvm_asm_mov_from_ar_sn2,
 };
 
 static int __init  kvm_vmm_init(void)
diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S
index 3ef1a017a318..40920c630649 100644
--- a/arch/ia64/kvm/vmm_ivt.S
+++ b/arch/ia64/kvm/vmm_ivt.S
@@ -95,7 +95,7 @@ GLOBAL_ENTRY(kvm_vmm_panic)
 	;;
 	srlz.i    // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -249,7 +249,7 @@ ENTRY(kvm_break_fault)
 	;;
 	srlz.i         // guarantee that interruption collection is on
 	;;
-	//(p15)ssm psr.i               // restore psr.i
+	(p15)ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -439,7 +439,7 @@ kvm_dispatch_vexirq:
 	;;
 	srlz.i // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	adds r3=8,r2                // set up second base pointer
 	;;
 	KVM_SAVE_REST
@@ -819,7 +819,7 @@ ENTRY(kvm_dtlb_miss_dispatch)
 	;;
 	srlz.i     // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
 	;;
 	KVM_SAVE_REST
@@ -842,7 +842,7 @@ ENTRY(kvm_itlb_miss_dispatch)
 	;;
 	srlz.i   // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -871,7 +871,7 @@ ENTRY(kvm_dispatch_reflection)
 	;;
 	srlz.i   // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -898,7 +898,7 @@ ENTRY(kvm_dispatch_virtualization_fault)
 	;;
 	srlz.i    // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
 	;;
 	KVM_SAVE_REST
@@ -920,7 +920,7 @@ ENTRY(kvm_dispatch_interrupt)
 	;;
 	srlz.i
 	;;
-	//(p15) ssm psr.i
+	(p15) ssm psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -1333,7 +1333,7 @@ hostret =   r24
 	;;
 (p7)    srlz.i
 	;;
-//(p6)    ssm psr.i
+(p6)    ssm psr.i
 	;;
 	mov rp=rpsave
 	mov ar.pfs=pfssave
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 2c2501f13159..4290a429bf7c 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -254,7 +254,8 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte)
 			"(p7) st8 [%2]=r9;;"
 			"ssm psr.ic;;"
 			"srlz.d;;"
-			/* "ssm psr.i;;" Once interrupts in vmm open, need fix*/
+			"ssm psr.i;;"
+			"srlz.d;;"
 			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
 
 	return ret;