Merge branch 'kvm-updates-2.6.27' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'kvm-updates-2.6.27' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (70 commits)
  KVM: Adjust smp_call_function_mask() callers to new requirements
  KVM: MMU: Fix potential race setting upper shadow ptes on nonpae hosts
  KVM: x86 emulator: emulate clflush
  KVM: MMU: improve invalid shadow root page handling
  KVM: MMU: nuke shadowed pgtable pages and ptes on memslot destruction
  KVM: Prefix some x86 low level function with kvm_, to avoid namespace issues
  KVM: check injected pic irq within valid pic irqs
  KVM: x86 emulator: Fix HLT instruction
  KVM: Apply the kernel sigmask to vcpus blocked due to being uninitialized
  KVM: VMX: Add ept_sync_context in flush_tlb
  KVM: mmu_shrink: kvm_mmu_zap_page requires slots_lock to be held
  x86: KVM guest: make kvm_smp_prepare_boot_cpu() static
  KVM: SVM: fix suspend/resume support
  KVM: s390: rename private structures
  KVM: s390: Set guest storage limit and offset to sane values
  KVM: Fix memory leak on guest exit
  KVM: s390: dont allocate dirty bitmap
  KVM: move slots_lock acquision down to vapic_exit
  KVM: VMX: Fake emulate Intel perfctr MSRs
  KVM: VMX: Fix a wrong usage of vmcs_config
  ...

arch/ia64/kvm/Makefile

@@ -43,7 +43,8 @@ $(obj)/$(offsets-file): arch/ia64/kvm/asm-offsets.s
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
+		coalesced_mmio.o)
 
 kvm-objs := $(common-objs) kvm-ia64.o kvm_fw.o
 obj-$(CONFIG_KVM) += kvm.o

arch/ia64/kvm/kvm-ia64.c

@@ -187,6 +187,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 		r = 1;
 		break;
+	case KVM_CAP_COALESCED_MMIO:
+		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
+		break;
 	default:
 		r = 0;
 	}
@@ -195,11 +198,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 }
 
 static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-					gpa_t addr)
+					gpa_t addr, int len, int is_write)
 {
 	struct kvm_io_device *dev;
 
-	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write);
 
 	return dev;
 }
@@ -231,7 +234,7 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
 mmio:
-	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr);
+	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir);
 	if (mmio_dev) {
 		if (!p->dir)
 			kvm_iodevice_write(mmio_dev, p->addr, p->size,
@@ -1035,14 +1038,6 @@ static void kvm_free_vmm_area(void)
 	}
 }
 
-/*
- * Make sure that a cpu that is being hot-unplugged does not have any vcpus
- * cached on it. Leave it as blank for IA64.
- */
-void decache_vcpus_on_cpu(int cpu)
-{
-}
-
 static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 }
@@ -1460,6 +1455,9 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
 
 long kvm_arch_dev_ioctl(struct file *filp,
 		unsigned int ioctl, unsigned long arg)

arch/powerpc/kvm/Makefile

@@ -4,7 +4,7 @@
 
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
 
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
 kvm-objs := $(common-objs) powerpc.o emulate.o booke_guest.o
 obj-$(CONFIG_KVM) += kvm.o

arch/powerpc/kvm/powerpc.c

@@ -145,6 +145,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_USER_MEMORY:
 		r = 1;
 		break;
+	case KVM_CAP_COALESCED_MMIO:
+		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
+		break;
 	default:
 		r = 0;
 		break;
@@ -167,6 +170,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
@@ -240,10 +247,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 }
 
-void decache_vcpus_on_cpu(int cpu)
-{
-}
-
 int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
                                     struct kvm_debug_guest *dbg)
 {

arch/s390/kvm/interrupt.c

@@ -31,7 +31,7 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 }
 
 static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
-				      struct interrupt_info *inti)
+				      struct kvm_s390_interrupt_info *inti)
 {
 	switch (inti->type) {
 	case KVM_S390_INT_EMERGENCY:
@@ -91,7 +91,7 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
 }
 
 static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
-				      struct interrupt_info *inti)
+				      struct kvm_s390_interrupt_info *inti)
 {
 	switch (inti->type) {
 	case KVM_S390_INT_EMERGENCY:
@@ -111,7 +111,7 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 }
 
 static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
-				   struct interrupt_info *inti)
+				   struct kvm_s390_interrupt_info *inti)
 {
 	const unsigned short table[] = { 2, 4, 4, 6 };
 	int rc, exception = 0;
@@ -290,9 +290,9 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 {
-	struct local_interrupt *li = &vcpu->arch.local_int;
-	struct float_interrupt *fi = vcpu->arch.local_int.float_int;
-	struct interrupt_info  *inti;
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *inti;
 	int rc = 0;
 
 	if (atomic_read(&li->active)) {
@@ -408,9 +408,9 @@ void kvm_s390_idle_wakeup(unsigned long data)
 
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 {
-	struct local_interrupt *li = &vcpu->arch.local_int;
-	struct float_interrupt *fi = vcpu->arch.local_int.float_int;
-	struct interrupt_info  *n, *inti = NULL;
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
 	int deliver;
 
 	__reset_intercept_indicators(vcpu);
@@ -465,8 +465,8 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 {
-	struct local_interrupt *li = &vcpu->arch.local_int;
-	struct interrupt_info *inti;
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_interrupt_info *inti;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
@@ -487,9 +487,9 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
-	struct local_interrupt *li;
-	struct float_interrupt *fi;
-	struct interrupt_info *inti;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti;
 	int sigcpu;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
@@ -544,8 +544,8 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 			 struct kvm_s390_interrupt *s390int)
 {
-	struct local_interrupt *li;
-	struct interrupt_info *inti;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)

arch/s390/kvm/kvm-s390.c

@@ -79,10 +79,6 @@ void kvm_arch_hardware_disable(void *garbage)
 {
 }
 
-void decache_vcpus_on_cpu(int cpu)
-{
-}
-
 int kvm_arch_hardware_setup(void)
 {
 	return 0;
@@ -198,6 +194,7 @@ out_nokvm:
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	debug_unregister(kvm->arch.dbf);
+	kvm_free_physmem(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	kfree(kvm);
 	module_put(THIS_MODULE);
@@ -250,11 +247,16 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gbea = 1;
 }
 
+/* The current code can have up to 256 pages for virtio */
+#define VIRTIODESCSPACE (256ul * 4096ul)
+
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
-	vcpu->arch.sie_block->gmslm = 0xffffffffffUL;
-	vcpu->arch.sie_block->gmsor = 0x000000000000;
+	vcpu->arch.sie_block->gmslm = vcpu->kvm->arch.guest_memsize +
+				      vcpu->kvm->arch.guest_origin +
+				      VIRTIODESCSPACE - 1ul;
+	vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin;
 	vcpu->arch.sie_block->ecb   = 2;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
@@ -273,7 +275,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	if (!vcpu)
 		goto out_nomem;
 
-	vcpu->arch.sie_block = (struct sie_block *) get_zeroed_page(GFP_KERNEL);
+	vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
+					get_zeroed_page(GFP_KERNEL);
 
 	if (!vcpu->arch.sie_block)
 		goto out_free_cpu;
@@ -672,6 +675,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;

arch/s390/kvm/priv.c

@@ -199,7 +199,7 @@ out:
 
 static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 {
-	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int cpus = 0;
 	int n;
 

arch/s390/kvm/sigp.c

@@ -45,7 +45,7 @@
 
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg)
 {
-	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int rc;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
@@ -71,9 +71,9 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg)
 
 static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
-	struct local_interrupt *li;
-	struct interrupt_info *inti;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
 	int rc;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
@@ -108,9 +108,9 @@ unlock:
 
 static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
 {
-	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
-	struct local_interrupt *li;
-	struct interrupt_info *inti;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
 	int rc;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
@@ -169,9 +169,9 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 			     u64 *reg)
 {
-	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
-	struct local_interrupt *li;
-	struct interrupt_info *inti;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
 	int rc;
 	u8 tmp;
 

arch/x86/kernel/kvmclock.c

@@ -113,7 +113,7 @@ static void kvm_setup_secondary_clock(void)
 #endif
 
 #ifdef CONFIG_SMP
-void __init kvm_smp_prepare_boot_cpu(void)
+static void __init kvm_smp_prepare_boot_cpu(void)
 {
 	WARN_ON(kvm_register_clock("primary cpu clock"));
 	native_smp_prepare_boot_cpu();

arch/x86/kvm/Makefile

@@ -2,7 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
+                coalesced_mmio.o)
 ifeq ($(CONFIG_KVM_TRACE),y)
 common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o)
 endif

arch/x86/kvm/i8254.c

@@ -91,7 +91,7 @@ static void pit_set_gate(struct kvm *kvm, int channel, u32 val)
 	c->gate = val;
 }
 
-int pit_get_gate(struct kvm *kvm, int channel)
+static int pit_get_gate(struct kvm *kvm, int channel)
 {
 	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
 
@@ -193,19 +193,16 @@ static void pit_latch_status(struct kvm *kvm, int channel)
 	}
 }
 
-int __pit_timer_fn(struct kvm_kpit_state *ps)
+static int __pit_timer_fn(struct kvm_kpit_state *ps)
 {
 	struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0];
 	struct kvm_kpit_timer *pt = &ps->pit_timer;
 
-	atomic_inc(&pt->pending);
-	smp_mb__after_atomic_inc();
-	if (vcpu0) {
+	if (!atomic_inc_and_test(&pt->pending))
 		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
-		if (waitqueue_active(&vcpu0->wq)) {
-			vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-			wake_up_interruptible(&vcpu0->wq);
-		}
+	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
+		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		wake_up_interruptible(&vcpu0->wq);
 	}
 
 	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
@@ -308,6 +305,7 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 		create_pit_timer(&ps->pit_timer, val, 0);
 		break;
 	case 2:
+	case 3:
 		create_pit_timer(&ps->pit_timer, val, 1);
 		break;
 	default:
@@ -459,7 +457,8 @@ static void pit_ioport_read(struct kvm_io_device *this,
 	mutex_unlock(&pit_state->lock);
 }
 
-static int pit_in_range(struct kvm_io_device *this, gpa_t addr)
+static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
+			int len, int is_write)
 {
 	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
 		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
@@ -500,7 +499,8 @@ static void speaker_ioport_read(struct kvm_io_device *this,
 	mutex_unlock(&pit_state->lock);
 }
 
-static int speaker_in_range(struct kvm_io_device *this, gpa_t addr)
+static int speaker_in_range(struct kvm_io_device *this, gpa_t addr,
+			    int len, int is_write)
 {
 	return (addr == KVM_SPEAKER_BASE_ADDRESS);
 }
@@ -575,7 +575,7 @@ void kvm_free_pit(struct kvm *kvm)
 	}
 }
 
-void __inject_pit_timer_intr(struct kvm *kvm)
+static void __inject_pit_timer_intr(struct kvm *kvm)
 {
 	mutex_lock(&kvm->lock);
 	kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 1);

arch/x86/kvm/i8259.c

@@ -130,8 +130,10 @@ 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);
+	if (irq >= 0 && irq < PIC_NUM_PINS) {
+		pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
+		pic_update_irq(s);
+	}
 }
 
 /*
@@ -346,7 +348,8 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1)
 	return s->elcr;
 }
 
-static int picdev_in_range(struct kvm_io_device *this, gpa_t addr)
+static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int is_write)
 {
 	switch (addr) {
 	case 0x20:

arch/x86/kvm/irq.h

@@ -30,6 +30,8 @@
 #include "ioapic.h"
 #include "lapic.h"
 
+#define PIC_NUM_PINS 16
+
 struct kvm;
 struct kvm_vcpu;
 

arch/x86/kvm/lapic.c

@@ -356,8 +356,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_SMI:
 		printk(KERN_DEBUG "Ignoring guest SMI\n");
 		break;
+
 	case APIC_DM_NMI:
-		printk(KERN_DEBUG "Ignoring guest NMI\n");
+		kvm_inject_nmi(vcpu);
 		break;
 
 	case APIC_DM_INIT:
@@ -572,6 +573,8 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 {
 	u32 val = 0;
 
+	KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
+
 	if (offset >= LAPIC_MMIO_LENGTH)
 		return 0;
 
@@ -695,6 +698,8 @@ static void apic_mmio_write(struct kvm_io_device *this,
 
 	offset &= 0xff0;
 
+	KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
+
 	switch (offset) {
 	case APIC_ID:		/* Local APIC ID */
 		apic_set_reg(apic, APIC_ID, val);
@@ -780,7 +785,8 @@ static void apic_mmio_write(struct kvm_io_device *this,
 
 }
 
-static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr)
+static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int size)
 {
 	struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
 	int ret = 0;
@@ -939,8 +945,8 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 	int result = 0;
 	wait_queue_head_t *q = &apic->vcpu->wq;
 
-	atomic_inc(&apic->timer.pending);
-	set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
+	if(!atomic_inc_and_test(&apic->timer.pending))
+		set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
 	if (waitqueue_active(q)) {
 		apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(q);

arch/x86/kvm/lapic.h

@@ -31,6 +31,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu);
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
+u64 kvm_lapic_get_base(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);

arch/x86/kvm/mmu.c

@@ -66,7 +66,8 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
 #endif
 
 #if defined(MMU_DEBUG) || defined(AUDIT)
-static int dbg = 1;
+static int dbg = 0;
+module_param(dbg, bool, 0644);
 #endif
 
 #ifndef MMU_DEBUG
@@ -776,6 +777,15 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
 	BUG();
 }
 
+static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
+				    struct kvm_mmu_page *sp)
+{
+	int i;
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+		sp->spt[i] = shadow_trap_nonpresent_pte;
+}
+
 static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 {
 	unsigned index;
@@ -841,7 +851,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	hlist_add_head(&sp->hash_link, bucket);
 	if (!metaphysical)
 		rmap_write_protect(vcpu->kvm, gfn);
-	vcpu->arch.mmu.prefetch_page(vcpu, sp);
+	if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte)
+		vcpu->arch.mmu.prefetch_page(vcpu, sp);
+	else
+		nonpaging_prefetch_page(vcpu, sp);
 	return sp;
 }
 
@@ -917,14 +930,17 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 	}
 	kvm_mmu_page_unlink_children(kvm, sp);
 	if (!sp->root_count) {
-		if (!sp->role.metaphysical)
+		if (!sp->role.metaphysical && !sp->role.invalid)
 			unaccount_shadowed(kvm, sp->gfn);
 		hlist_del(&sp->hash_link);
 		kvm_mmu_free_page(kvm, sp);
 	} else {
+		int invalid = sp->role.invalid;
 		list_move(&sp->link, &kvm->arch.active_mmu_pages);
 		sp->role.invalid = 1;
 		kvm_reload_remote_mmus(kvm);
+		if (!sp->role.metaphysical && !invalid)
+			unaccount_shadowed(kvm, sp->gfn);
 	}
 	kvm_mmu_reset_last_pte_updated(kvm);
 }
@@ -1103,7 +1119,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		mark_page_dirty(vcpu->kvm, gfn);
 
 	pgprintk("%s: setting spte %llx\n", __func__, spte);
-	pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n",
+	pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n",
 		 (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB",
 		 (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte);
 	set_shadow_pte(shadow_pte, spte);
@@ -1122,8 +1138,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		else
 			kvm_release_pfn_clean(pfn);
 	}
-	if (!ptwrite || !*ptwrite)
+	if (speculative) {
 		vcpu->arch.last_pte_updated = shadow_pte;
+		vcpu->arch.last_pte_gfn = gfn;
+	}
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
@@ -1171,9 +1189,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 				return -ENOMEM;
 			}
 
-			table[index] = __pa(new_table->spt)
-				| PT_PRESENT_MASK | PT_WRITABLE_MASK
-				| shadow_user_mask | shadow_x_mask;
+			set_shadow_pte(&table[index],
+				       __pa(new_table->spt)
+				       | PT_PRESENT_MASK | PT_WRITABLE_MASK
+				       | shadow_user_mask | shadow_x_mask);
 		}
 		table_addr = table[index] & PT64_BASE_ADDR_MASK;
 	}
@@ -1211,15 +1230,6 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 }
 
 
-static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
-				    struct kvm_mmu_page *sp)
-{
-	int i;
-
-	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
-		sp->spt[i] = shadow_trap_nonpresent_pte;
-}
-
 static void mmu_free_roots(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -1671,6 +1681,18 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	vcpu->arch.update_pte.pfn = pfn;
 }
 
+static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	u64 *spte = vcpu->arch.last_pte_updated;
+
+	if (spte
+	    && vcpu->arch.last_pte_gfn == gfn
+	    && shadow_accessed_mask
+	    && !(*spte & shadow_accessed_mask)
+	    && is_shadow_present_pte(*spte))
+		set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+}
+
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes)
 {
@@ -1694,6 +1716,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 	mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
 	spin_lock(&vcpu->kvm->mmu_lock);
+	kvm_mmu_access_page(vcpu, gfn);
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, "pre pte write");
@@ -1948,7 +1971,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	kvm_flush_remote_tlbs(kvm);
 }
 
-void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
 {
 	struct kvm_mmu_page *page;
 
@@ -1968,6 +1991,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int npages;
 
+		if (!down_read_trylock(&kvm->slots_lock))
+			continue;
 		spin_lock(&kvm->mmu_lock);
 		npages = kvm->arch.n_alloc_mmu_pages -
 			 kvm->arch.n_free_mmu_pages;
@@ -1980,6 +2005,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 		nr_to_scan--;
 
 		spin_unlock(&kvm->mmu_lock);
+		up_read(&kvm->slots_lock);
 	}
 	if (kvm_freed)
 		list_move_tail(&kvm_freed->vm_list, &vm_list);

arch/x86/kvm/mmu.h

@@ -15,7 +15,8 @@
 #define PT_USER_MASK (1ULL << 2)
 #define PT_PWT_MASK (1ULL << 3)
 #define PT_PCD_MASK (1ULL << 4)
-#define PT_ACCESSED_MASK (1ULL << 5)
+#define PT_ACCESSED_SHIFT 5
+#define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
 #define PT_DIRTY_MASK (1ULL << 6)
 #define PT_PAGE_SIZE_MASK (1ULL << 7)
 #define PT_PAT_MASK (1ULL << 7)

arch/x86/kvm/paging_tmpl.h

@@ -460,8 +460,9 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
 static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 				 struct kvm_mmu_page *sp)
 {
-	int i, offset = 0, r = 0;
-	pt_element_t pt;
+	int i, j, offset, r;
+	pt_element_t pt[256 / sizeof(pt_element_t)];
+	gpa_t pte_gpa;
 
 	if (sp->role.metaphysical
 	    || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) {
@@ -469,19 +470,20 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 		return;
 	}
 
-	if (PTTYPE == 32)
+	pte_gpa = gfn_to_gpa(sp->gfn);
+	if (PTTYPE == 32) {
 		offset = sp->role.quadrant << PT64_LEVEL_BITS;
+		pte_gpa += offset * sizeof(pt_element_t);
+	}
 
-	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
-		gpa_t pte_gpa = gfn_to_gpa(sp->gfn);
-		pte_gpa += (i+offset) * sizeof(pt_element_t);
-
-		r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &pt,
-					  sizeof(pt_element_t));
-		if (r || is_present_pte(pt))
-			sp->spt[i] = shadow_trap_nonpresent_pte;
-		else
-			sp->spt[i] = shadow_notrap_nonpresent_pte;
+	for (i = 0; i < PT64_ENT_PER_PAGE; i += ARRAY_SIZE(pt)) {
+		r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, pt, sizeof pt);
+		pte_gpa += ARRAY_SIZE(pt) * sizeof(pt_element_t);
+		for (j = 0; j < ARRAY_SIZE(pt); ++j)
+			if (r || is_present_pte(pt[j]))
+				sp->spt[i+j] = shadow_trap_nonpresent_pte;
+			else
+				sp->spt[i+j] = shadow_notrap_nonpresent_pte;
 	}
 }
 

arch/x86/kvm/svm.c

@@ -27,6 +27,8 @@
 
 #include <asm/desc.h>
 
+#define __ex(x) __kvm_handle_fault_on_reboot(x)
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
@@ -129,17 +131,17 @@ static inline void push_irq(struct kvm_vcpu *vcpu, u8 irq)
 
 static inline void clgi(void)
 {
-	asm volatile (SVM_CLGI);
+	asm volatile (__ex(SVM_CLGI));
 }
 
 static inline void stgi(void)
 {
-	asm volatile (SVM_STGI);
+	asm volatile (__ex(SVM_STGI));
 }
 
 static inline void invlpga(unsigned long addr, u32 asid)
 {
-	asm volatile (SVM_INVLPGA :: "a"(addr), "c"(asid));
+	asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
 }
 
 static inline unsigned long kvm_read_cr2(void)
@@ -270,19 +272,11 @@ static int has_svm(void)
 
 static void svm_hardware_disable(void *garbage)
 {
-	struct svm_cpu_data *svm_data
-		= per_cpu(svm_data, raw_smp_processor_id());
-
-	if (svm_data) {
-		uint64_t efer;
+	uint64_t efer;
 
-		wrmsrl(MSR_VM_HSAVE_PA, 0);
-		rdmsrl(MSR_EFER, efer);
-		wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
-		per_cpu(svm_data, raw_smp_processor_id()) = NULL;
-		__free_page(svm_data->save_area);
-		kfree(svm_data);
-	}
+	wrmsrl(MSR_VM_HSAVE_PA, 0);
+	rdmsrl(MSR_EFER, efer);
+	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
 }
 
 static void svm_hardware_enable(void *garbage)
@@ -321,6 +315,19 @@ static void svm_hardware_enable(void *garbage)
 	       page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
 }
 
+static void svm_cpu_uninit(int cpu)
+{
+	struct svm_cpu_data *svm_data
+		= per_cpu(svm_data, raw_smp_processor_id());
+
+	if (!svm_data)
+		return;
+
+	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
+	__free_page(svm_data->save_area);
+	kfree(svm_data);
+}
+
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *svm_data;
@@ -458,6 +465,11 @@ err:
 
 static __exit void svm_hardware_unsetup(void)
 {
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		svm_cpu_uninit(cpu);
+
 	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
 	iopm_base = 0;
 }
@@ -707,10 +719,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	rdtscll(vcpu->arch.host_tsc);
 }
 
-static void svm_vcpu_decache(struct kvm_vcpu *vcpu)
-{
-}
-
 static void svm_cache_regs(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -949,7 +957,9 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
 
 static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
 {
-	return to_svm(vcpu)->db_regs[dr];
+	unsigned long val = to_svm(vcpu)->db_regs[dr];
+	KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
+	return val;
 }
 
 static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
@@ -1004,6 +1014,16 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 
 	fault_address  = svm->vmcb->control.exit_info_2;
 	error_code = svm->vmcb->control.exit_info_1;
+
+	if (!npt_enabled)
+		KVMTRACE_3D(PAGE_FAULT, &svm->vcpu, error_code,
+			    (u32)fault_address, (u32)(fault_address >> 32),
+			    handler);
+	else
+		KVMTRACE_3D(TDP_FAULT, &svm->vcpu, error_code,
+			    (u32)fault_address, (u32)(fault_address >> 32),
+			    handler);
+
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
@@ -1081,6 +1101,19 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
 }
 
+static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	KVMTRACE_0D(NMI, &svm->vcpu, handler);
+	return 1;
+}
+
+static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	++svm->vcpu.stat.irq_exits;
+	KVMTRACE_0D(INTR, &svm->vcpu, handler);
+	return 1;
+}
+
 static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	return 1;
@@ -1219,6 +1252,9 @@ static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	if (svm_get_msr(&svm->vcpu, ecx, &data))
 		kvm_inject_gp(&svm->vcpu, 0);
 	else {
+		KVMTRACE_3D(MSR_READ, &svm->vcpu, ecx, (u32)data,
+			    (u32)(data >> 32), handler);
+
 		svm->vmcb->save.rax = data & 0xffffffff;
 		svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32;
 		svm->next_rip = svm->vmcb->save.rip + 2;
@@ -1284,16 +1320,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	case MSR_K7_EVNTSEL1:
 	case MSR_K7_EVNTSEL2:
 	case MSR_K7_EVNTSEL3:
+	case MSR_K7_PERFCTR0:
+	case MSR_K7_PERFCTR1:
+	case MSR_K7_PERFCTR2:
+	case MSR_K7_PERFCTR3:
 		/*
-		 * only support writing 0 to the performance counters for now
-		 * to make Windows happy. Should be replaced by a real
-		 * performance counter emulation later.
+		 * Just discard all writes to the performance counters; this
+		 * should keep both older linux and windows 64-bit guests
+		 * happy
 		 */
-		if (data != 0)
-			goto unhandled;
+		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data);
+
 		break;
 	default:
-	unhandled:
 		return kvm_set_msr_common(vcpu, ecx, data);
 	}
 	return 0;
@@ -1304,6 +1343,10 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u64 data = (svm->vmcb->save.rax & -1u)
 		| ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32);
+
+	KVMTRACE_3D(MSR_WRITE, &svm->vcpu, ecx, (u32)data, (u32)(data >> 32),
+		    handler);
+
 	svm->next_rip = svm->vmcb->save.rip + 2;
 	if (svm_set_msr(&svm->vcpu, ecx, data))
 		kvm_inject_gp(&svm->vcpu, 0);
@@ -1323,6 +1366,8 @@ static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 static int interrupt_window_interception(struct vcpu_svm *svm,
 				   struct kvm_run *kvm_run)
 {
+	KVMTRACE_0D(PEND_INTR, &svm->vcpu, handler);
+
 	svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	/*
@@ -1364,8 +1409,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_EXCP_BASE + PF_VECTOR] 	= pf_interception,
 	[SVM_EXIT_EXCP_BASE + NM_VECTOR] 	= nm_interception,
 	[SVM_EXIT_EXCP_BASE + MC_VECTOR] 	= mc_interception,
-	[SVM_EXIT_INTR] 			= nop_on_interception,
-	[SVM_EXIT_NMI]				= nop_on_interception,
+	[SVM_EXIT_INTR] 			= intr_interception,
+	[SVM_EXIT_NMI]				= nmi_interception,
 	[SVM_EXIT_SMI]				= nop_on_interception,
 	[SVM_EXIT_INIT]				= nop_on_interception,
 	[SVM_EXIT_VINTR]			= interrupt_window_interception,
@@ -1397,6 +1442,9 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 exit_code = svm->vmcb->control.exit_code;
 
+	KVMTRACE_3D(VMEXIT, vcpu, exit_code, (u32)svm->vmcb->save.rip,
+		    (u32)((u64)svm->vmcb->save.rip >> 32), entryexit);
+
 	if (npt_enabled) {
 		int mmu_reload = 0;
 		if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
@@ -1470,6 +1518,8 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
 {
 	struct vmcb_control_area *control;
 
+	KVMTRACE_1D(INJ_VIRQ, &svm->vcpu, (u32)irq, handler);
+
 	control = &svm->vmcb->control;
 	control->int_vector = irq;
 	control->int_ctl &= ~V_INTR_PRIO_MASK;
@@ -1660,9 +1710,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	sync_lapic_to_cr8(vcpu);
 
 	save_host_msrs(vcpu);
-	fs_selector = read_fs();
-	gs_selector = read_gs();
-	ldt_selector = read_ldt();
+	fs_selector = kvm_read_fs();
+	gs_selector = kvm_read_gs();
+	ldt_selector = kvm_read_ldt();
 	svm->host_cr2 = kvm_read_cr2();
 	svm->host_dr6 = read_dr6();
 	svm->host_dr7 = read_dr7();
@@ -1716,17 +1766,17 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		/* Enter guest mode */
 		"push %%rax \n\t"
 		"mov %c[vmcb](%[svm]), %%rax \n\t"
-		SVM_VMLOAD "\n\t"
-		SVM_VMRUN "\n\t"
-		SVM_VMSAVE "\n\t"
+		__ex(SVM_VMLOAD) "\n\t"
+		__ex(SVM_VMRUN) "\n\t"
+		__ex(SVM_VMSAVE) "\n\t"
 		"pop %%rax \n\t"
 #else
 		/* Enter guest mode */
 		"push %%eax \n\t"
 		"mov %c[vmcb](%[svm]), %%eax \n\t"
-		SVM_VMLOAD "\n\t"
-		SVM_VMRUN "\n\t"
-		SVM_VMSAVE "\n\t"
+		__ex(SVM_VMLOAD) "\n\t"
+		__ex(SVM_VMRUN) "\n\t"
+		__ex(SVM_VMSAVE) "\n\t"
 		"pop %%eax \n\t"
 #endif
 
@@ -1795,9 +1845,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	write_dr7(svm->host_dr7);
 	kvm_write_cr2(svm->host_cr2);
 
-	load_fs(fs_selector);
-	load_gs(gs_selector);
-	load_ldt(ldt_selector);
+	kvm_load_fs(fs_selector);
+	kvm_load_gs(gs_selector);
+	kvm_load_ldt(ldt_selector);
 	load_host_msrs(vcpu);
 
 	reload_tss(vcpu);
@@ -1889,7 +1939,6 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.prepare_guest_switch = svm_prepare_guest_switch,
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
-	.vcpu_decache = svm_vcpu_decache,
 
 	.set_guest_debug = svm_guest_debug,
 	.get_msr = svm_get_msr,

arch/x86/kvm/vmx.h

@@ -40,6 +40,7 @@
 #define CPU_BASED_CR8_LOAD_EXITING              0x00080000
 #define CPU_BASED_CR8_STORE_EXITING             0x00100000
 #define CPU_BASED_TPR_SHADOW                    0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
 #define CPU_BASED_MOV_DR_EXITING                0x00800000
 #define CPU_BASED_UNCOND_IO_EXITING             0x01000000
 #define CPU_BASED_USE_IO_BITMAPS                0x02000000
@@ -216,7 +217,7 @@ enum vmcs_field {
 #define EXIT_REASON_TRIPLE_FAULT        2
 
 #define EXIT_REASON_PENDING_INTERRUPT   7
-
+#define EXIT_REASON_NMI_WINDOW		8
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
 #define EXIT_REASON_HLT                 12
@@ -251,7 +252,9 @@ enum vmcs_field {
 #define INTR_INFO_VECTOR_MASK           0xff            /* 7:0 */
 #define INTR_INFO_INTR_TYPE_MASK        0x700           /* 10:8 */
 #define INTR_INFO_DELIVER_CODE_MASK     0x800           /* 11 */
+#define INTR_INFO_UNBLOCK_NMI		0x1000		/* 12 */
 #define INTR_INFO_VALID_MASK            0x80000000      /* 31 */
+#define INTR_INFO_RESVD_BITS_MASK       0x7ffff000
 
 #define VECTORING_INFO_VECTOR_MASK           	INTR_INFO_VECTOR_MASK
 #define VECTORING_INFO_TYPE_MASK        	INTR_INFO_INTR_TYPE_MASK
@@ -259,9 +262,16 @@ enum vmcs_field {
 #define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
+#define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
 #define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
 
+/* GUEST_INTERRUPTIBILITY_INFO flags. */
+#define GUEST_INTR_STATE_STI		0x00000001
+#define GUEST_INTR_STATE_MOV_SS		0x00000002
+#define GUEST_INTR_STATE_SMI		0x00000004
+#define GUEST_INTR_STATE_NMI		0x00000008
+
 /*
  * Exit Qualifications for MOV for Control Register Access
  */

include/asm-ia64/kvm_host.h

@@ -38,6 +38,7 @@
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
 
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* define exit reasons from vmm to kvm*/
 #define EXIT_REASON_VM_PANIC		0
@@ -521,4 +522,6 @@ 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

include/asm-powerpc/kvm_host.h

@@ -31,6 +31,8 @@
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
 
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 /* We don't currently support large pages. */
 #define KVM_PAGES_PER_HPAGE (1<<31)
 

include/asm-s390/kvm_host.h

@@ -62,7 +62,7 @@ struct sca_block {
 #define CPUSTAT_J          0x00000002
 #define CPUSTAT_P          0x00000001
 
-struct sie_block {
+struct kvm_s390_sie_block {
 	atomic_t cpuflags;		/* 0x0000 */
 	__u32	prefix;			/* 0x0004 */
 	__u8	reserved8[32];		/* 0x0008 */
@@ -140,14 +140,14 @@ struct kvm_vcpu_stat {
 	u32 diagnose_44;
 };
 
-struct io_info {
+struct kvm_s390_io_info {
 	__u16        subchannel_id;            /* 0x0b8 */
 	__u16        subchannel_nr;            /* 0x0ba */
 	__u32        io_int_parm;              /* 0x0bc */
 	__u32        io_int_word;              /* 0x0c0 */
 };
 
-struct ext_info {
+struct kvm_s390_ext_info {
 	__u32 ext_params;
 	__u64 ext_params2;
 };
@@ -160,22 +160,22 @@ struct ext_info {
 #define PGM_SPECIFICATION        0x06
 #define PGM_DATA                 0x07
 
-struct pgm_info {
+struct kvm_s390_pgm_info {
 	__u16 code;
 };
 
-struct prefix_info {
+struct kvm_s390_prefix_info {
 	__u32 address;
 };
 
-struct interrupt_info {
+struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
 	union {
-		struct io_info io;
-		struct ext_info ext;
-		struct pgm_info pgm;
-		struct prefix_info prefix;
+		struct kvm_s390_io_info io;
+		struct kvm_s390_ext_info ext;
+		struct kvm_s390_pgm_info pgm;
+		struct kvm_s390_prefix_info prefix;
 	};
 };
 
@@ -183,35 +183,35 @@ struct interrupt_info {
 #define ACTION_STORE_ON_STOP 1
 #define ACTION_STOP_ON_STOP  2
 
-struct local_interrupt {
+struct kvm_s390_local_interrupt {
 	spinlock_t lock;
 	struct list_head list;
 	atomic_t active;
-	struct float_interrupt *float_int;
+	struct kvm_s390_float_interrupt *float_int;
 	int timer_due; /* event indicator for waitqueue below */
 	wait_queue_head_t wq;
 	atomic_t *cpuflags;
 	unsigned int action_bits;
 };
 
-struct float_interrupt {
+struct kvm_s390_float_interrupt {
 	spinlock_t lock;
 	struct list_head list;
 	atomic_t active;
 	int next_rr_cpu;
 	unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)];
-	struct local_interrupt *local_int[64];
+	struct kvm_s390_local_interrupt *local_int[64];
 };
 
 
 struct kvm_vcpu_arch {
-	struct sie_block *sie_block;
+	struct kvm_s390_sie_block *sie_block;
 	unsigned long	  guest_gprs[16];
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
 	unsigned int      guest_acrs[NUM_ACRS];
-	struct local_interrupt local_int;
+	struct kvm_s390_local_interrupt local_int;
 	struct timer_list ckc_timer;
 	union  {
 		cpuid_t	  cpu_id;
@@ -228,8 +228,8 @@ struct kvm_arch{
 	unsigned long guest_memsize;
 	struct sca_block *sca;
 	debug_info_t *dbf;
-	struct float_interrupt float_int;
+	struct kvm_s390_float_interrupt float_int;
 };
 
-extern int sie64a(struct sie_block *, __u64 *);
+extern int sie64a(struct kvm_s390_sie_block *, __u64 *);
 #endif

include/asm-x86/kvm.h

@@ -228,5 +228,6 @@ struct kvm_pit_state {
 #define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
 #define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
 #define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
 
 #endif

include/asm-x86/kvm_host.h

@@ -27,6 +27,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 4
 
 #define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
@@ -79,6 +80,7 @@
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_VAR_MTRR 8
 
 extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
@@ -109,12 +111,12 @@ enum {
 };
 
 enum {
+	VCPU_SREG_ES,
 	VCPU_SREG_CS,
+	VCPU_SREG_SS,
 	VCPU_SREG_DS,
-	VCPU_SREG_ES,
 	VCPU_SREG_FS,
 	VCPU_SREG_GS,
-	VCPU_SREG_SS,
 	VCPU_SREG_TR,
 	VCPU_SREG_LDTR,
 };
@@ -243,6 +245,7 @@ struct kvm_vcpu_arch {
 	gfn_t last_pt_write_gfn;
 	int   last_pt_write_count;
 	u64  *last_pte_updated;
+	gfn_t last_pte_gfn;
 
 	struct {
 		gfn_t gfn;	/* presumed gfn during guest pte update */
@@ -287,6 +290,10 @@ struct kvm_vcpu_arch {
 	unsigned int hv_clock_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
+
+	bool nmi_pending;
+
+	u64 mtrr[0x100];
 };
 
 struct kvm_mem_alias {
@@ -344,6 +351,7 @@ struct kvm_vcpu_stat {
 	u32 mmio_exits;
 	u32 signal_exits;
 	u32 irq_window_exits;
+	u32 nmi_window_exits;
 	u32 halt_exits;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
@@ -379,7 +387,6 @@ struct kvm_x86_ops {
 	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
-	void (*vcpu_decache)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
 			       struct kvm_debug_guest *dbg);
@@ -497,6 +504,10 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 		    unsigned long value);
 
+void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+				int type_bits, int seg);
+
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -515,6 +526,8 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
 			   u32 error_code);
 
+void kvm_inject_nmi(struct kvm_vcpu *vcpu);
+
 void fx_init(struct kvm_vcpu *vcpu);
 
 int emulator_read_std(unsigned long addr,
@@ -554,55 +567,53 @@ static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 	return (struct kvm_mmu_page *)page_private(page);
 }
 
-static inline u16 read_fs(void)
+static inline u16 kvm_read_fs(void)
 {
 	u16 seg;
 	asm("mov %%fs, %0" : "=g"(seg));
 	return seg;
 }
 
-static inline u16 read_gs(void)
+static inline u16 kvm_read_gs(void)
 {
 	u16 seg;
 	asm("mov %%gs, %0" : "=g"(seg));
 	return seg;
 }
 
-static inline u16 read_ldt(void)
+static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
 	asm("sldt %0" : "=g"(ldt));
 	return ldt;
 }
 
-static inline void load_fs(u16 sel)
+static inline void kvm_load_fs(u16 sel)
 {
 	asm("mov %0, %%fs" : : "rm"(sel));
 }
 
-static inline void load_gs(u16 sel)
+static inline void kvm_load_gs(u16 sel)
 {
 	asm("mov %0, %%gs" : : "rm"(sel));
 }
 
-#ifndef load_ldt
-static inline void load_ldt(u16 sel)
+static inline void kvm_load_ldt(u16 sel)
 {
 	asm("lldt %0" : : "rm"(sel));
 }
-#endif
 
-static inline void get_idt(struct descriptor_table *table)
+static inline void kvm_get_idt(struct descriptor_table *table)
 {
 	asm("sidt %0" : "=m"(*table));
 }
 
-static inline void get_gdt(struct descriptor_table *table)
+static inline void kvm_get_gdt(struct descriptor_table *table)
 {
 	asm("sgdt %0" : "=m"(*table));
 }
 
-static inline unsigned long read_tr_base(void)
+static inline unsigned long kvm_read_tr_base(void)
 {
 	u16 tr;
 	asm("str %0" : "=g"(tr));
@@ -619,17 +630,17 @@ static inline unsigned long read_msr(unsigned long msr)
 }
 #endif
 
-static inline void fx_save(struct i387_fxsave_struct *image)
+static inline void kvm_fx_save(struct i387_fxsave_struct *image)
 {
 	asm("fxsave (%0)":: "r" (image));
 }
 
-static inline void fx_restore(struct i387_fxsave_struct *image)
+static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
 {
 	asm("fxrstor (%0)":: "r" (image));
 }
 
-static inline void fx_finit(void)
+static inline void kvm_fx_finit(void)
 {
 	asm("finit");
 }
@@ -691,4 +702,28 @@ enum {
 	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
 						vcpu, 0, 0, 0, 0, 0, 0)
 
+#ifdef CONFIG_64BIT
+#define KVM_EX_ENTRY ".quad"
+#else
+#define KVM_EX_ENTRY ".long"
+#endif
+
+/*
+ * Hardware virtualization extension instructions may fault if a
+ * reboot turns off virtualization while processes are running.
+ * Trap the fault and ignore the instruction if that happens.
+ */
+asmlinkage void kvm_handle_fault_on_reboot(void);
+
+#define __kvm_handle_fault_on_reboot(insn) \
+	"666: " insn "\n\t" \
+	".pushsection .text.fixup, \"ax\" \n" \
+	"667: \n\t" \
+	"push $666b \n\t" \
+	"jmp kvm_handle_fault_on_reboot \n\t" \
+	".popsection \n\t" \
+	".pushsection __ex_table, \"a\" \n\t" \
+	KVM_EX_ENTRY " 666b, 667b \n\t" \
+	".popsection"
+
 #endif

include/asm-x86/kvm_x86_emulate.h

@@ -124,7 +124,8 @@ struct decode_cache {
 	u8 rex_prefix;
 	struct operand src;
 	struct operand dst;
-	unsigned long *override_base;
+	bool has_seg_override;
+	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
 	unsigned long eip;
@@ -134,6 +135,7 @@ struct decode_cache {
 	u8 modrm_reg;
 	u8 modrm_rm;
 	u8 use_modrm_ea;
+	bool rip_relative;
 	unsigned long modrm_ea;
 	void *modrm_ptr;
 	unsigned long modrm_val;
@@ -150,12 +152,7 @@ struct x86_emulate_ctxt {
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
 
-	unsigned long cs_base;
-	unsigned long ds_base;
-	unsigned long es_base;
-	unsigned long ss_base;
-	unsigned long gs_base;
-	unsigned long fs_base;
+	u32 cs_base;
 
 	/* decode cache */
 

include/linux/kvm.h

@@ -173,6 +173,30 @@ struct kvm_run {
 	};
 };
 
+/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
+
+struct kvm_coalesced_mmio_zone {
+	__u64 addr;
+	__u32 size;
+	__u32 pad;
+};
+
+struct kvm_coalesced_mmio {
+	__u64 phys_addr;
+	__u32 len;
+	__u32 pad;
+	__u8  data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+	__u32 first, last;
+	struct kvm_coalesced_mmio coalesced_mmio[0];
+};
+
+#define KVM_COALESCED_MMIO_MAX \
+	((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \
+	 sizeof(struct kvm_coalesced_mmio))
+
 /* for KVM_TRANSLATE */
 struct kvm_translation {
 	/* in */
@@ -294,14 +318,14 @@ struct kvm_trace_rec {
 	__u32 vcpu_id;
 	union {
 		struct {
-			__u32 cycle_lo, cycle_hi;
+			__u64 cycle_u64;
 			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
 		} cycle;
 		struct {
 			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
 		} nocycle;
 	} u;
-};
+} __attribute__((packed));
 
 #define KVMIO 0xAE
 
@@ -346,6 +370,7 @@ struct kvm_trace_rec {
 #define KVM_CAP_NOP_IO_DELAY 12
 #define KVM_CAP_PV_MMU 13
 #define KVM_CAP_MP_STATE 14
+#define KVM_CAP_COALESCED_MMIO 15
 
 /*
  * ioctls for VM fds
@@ -371,6 +396,10 @@ struct kvm_trace_rec {
 #define KVM_CREATE_PIT		  _IO(KVMIO,  0x64)
 #define KVM_GET_PIT		  _IOWR(KVMIO, 0x65, struct kvm_pit_state)
 #define KVM_SET_PIT		  _IOR(KVMIO,  0x66, struct kvm_pit_state)
+#define KVM_REGISTER_COALESCED_MMIO \
+			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
+#define KVM_UNREGISTER_COALESCED_MMIO \
+			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
 
 /*
  * ioctls for vcpu fds

include/linux/kvm_host.h

@@ -52,7 +52,8 @@ struct kvm_io_bus {
 
 void kvm_io_bus_init(struct kvm_io_bus *bus);
 void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr);
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
+					  gpa_t addr, int len, int is_write);
 void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
 			     struct kvm_io_device *dev);
 
@@ -116,6 +117,10 @@ struct kvm {
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	atomic_t users_count;
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	struct kvm_coalesced_mmio_dev *coalesced_mmio_dev;
+	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
+#endif
 };
 
 /* The guest did something we don't support. */
@@ -135,9 +140,6 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-void decache_vcpus_on_cpu(int cpu);
-
-
 int kvm_init(void *opaque, unsigned int vcpu_size,
 		  struct module *module);
 void kvm_exit(void);
@@ -166,6 +168,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+void kvm_arch_flush_shadow(struct kvm *kvm);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);

virt/kvm/coalesced_mmio.c

+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ *
+ *  Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#include "iodev.h"
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+
+#include "coalesced_mmio.h"
+
+static int coalesced_mmio_in_range(struct kvm_io_device *this,
+				   gpa_t addr, int len, int is_write)
+{
+	struct kvm_coalesced_mmio_dev *dev =
+				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_zone *zone;
+	int next;
+	int i;
+
+	if (!is_write)
+		return 0;
+
+	/* kvm->lock is taken by the caller and must be not released before
+         * dev.read/write
+         */
+
+	/* Are we able to batch it ? */
+
+	/* last is the first free entry
+	 * check if we don't meet the first used entry
+	 * there is always one unused entry in the buffer
+	 */
+
+	next = (dev->kvm->coalesced_mmio_ring->last + 1) %
+							KVM_COALESCED_MMIO_MAX;
+	if (next == dev->kvm->coalesced_mmio_ring->first) {
+		/* full */
+		return 0;
+	}
+
+	/* is it in a batchable area ? */
+
+	for (i = 0; i < dev->nb_zones; i++) {
+		zone = &dev->zone[i];
+
+		/* (addr,len) is fully included in
+		 * (zone->addr, zone->size)
+		 */
+
+		if (zone->addr <= addr &&
+		    addr + len <= zone->addr + zone->size)
+			return 1;
+	}
+	return 0;
+}
+
+static void coalesced_mmio_write(struct kvm_io_device *this,
+				 gpa_t addr, int len, const void *val)
+{
+	struct kvm_coalesced_mmio_dev *dev =
+				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+
+	/* kvm->lock must be taken by caller before call to in_range()*/
+
+	/* copy data in first free entry of the ring */
+
+	ring->coalesced_mmio[ring->last].phys_addr = addr;
+	ring->coalesced_mmio[ring->last].len = len;
+	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
+	smp_wmb();
+	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
+}
+
+static void coalesced_mmio_destructor(struct kvm_io_device *this)
+{
+	kfree(this);
+}
+
+int kvm_coalesced_mmio_init(struct kvm *kvm)
+{
+	struct kvm_coalesced_mmio_dev *dev;
+
+	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	dev->dev.write  = coalesced_mmio_write;
+	dev->dev.in_range  = coalesced_mmio_in_range;
+	dev->dev.destructor  = coalesced_mmio_destructor;
+	dev->dev.private  = dev;
+	dev->kvm = kvm;
+	kvm->coalesced_mmio_dev = dev;
+	kvm_io_bus_register_dev(&kvm->mmio_bus, &dev->dev);
+
+	return 0;
+}
+
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+				         struct kvm_coalesced_mmio_zone *zone)
+{
+	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
+
+	if (dev == NULL)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
+		mutex_unlock(&kvm->lock);
+		return -ENOBUFS;
+	}
+
+	dev->zone[dev->nb_zones] = *zone;
+	dev->nb_zones++;
+
+	mutex_unlock(&kvm->lock);
+	return 0;
+}
+
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+					   struct kvm_coalesced_mmio_zone *zone)
+{
+	int i;
+	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
+	struct kvm_coalesced_mmio_zone *z;
+
+	if (dev == NULL)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	i = dev->nb_zones;
+	while(i) {
+		z = &dev->zone[i - 1];
+
+		/* unregister all zones
+		 * included in (zone->addr, zone->size)
+		 */
+
+		if (zone->addr <= z->addr &&
+		    z->addr + z->size <= zone->addr + zone->size) {
+			dev->nb_zones--;
+			*z = dev->zone[dev->nb_zones];
+		}
+		i--;
+	}
+
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}

virt/kvm/coalesced_mmio.h

+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ *
+ *  Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#define KVM_COALESCED_MMIO_ZONE_MAX 100
+
+struct kvm_coalesced_mmio_dev {
+	struct kvm_io_device dev;
+	struct kvm *kvm;
+	int nb_zones;
+	struct kvm_coalesced_mmio_zone zone[KVM_COALESCED_MMIO_ZONE_MAX];
+};
+
+int kvm_coalesced_mmio_init(struct kvm *kvm);
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+                                       struct kvm_coalesced_mmio_zone *zone);
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+                                         struct kvm_coalesced_mmio_zone *zone);

virt/kvm/ioapic.c

@@ -146,6 +146,11 @@ static int ioapic_inj_irq(struct kvm_ioapic *ioapic,
 	return kvm_apic_set_irq(vcpu, vector, trig_mode);
 }
 
+static void ioapic_inj_nmi(struct kvm_vcpu *vcpu)
+{
+	kvm_inject_nmi(vcpu);
+}
+
 static u32 ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
 				       u8 dest_mode)
 {
@@ -239,8 +244,19 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 			}
 		}
 		break;
-
-		/* TODO: NMI */
+	case IOAPIC_NMI:
+		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)
+				ioapic_inj_nmi(vcpu);
+			else
+				ioapic_debug("NMI to vcpu %d failed\n",
+						vcpu->vcpu_id);
+		}
+		break;
 	default:
 		printk(KERN_WARNING "Unsupported delivery mode %d\n",
 		       delivery_mode);
@@ -291,7 +307,8 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
 			__kvm_ioapic_update_eoi(ioapic, i);
 }
 
-static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr)
+static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int is_write)
 {
 	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
 

virt/kvm/iodev.h

@@ -27,7 +27,8 @@ struct kvm_io_device {
 		      gpa_t addr,
 		      int len,
 		      const void *val);
-	int (*in_range)(struct kvm_io_device *this, gpa_t addr);
+	int (*in_range)(struct kvm_io_device *this, gpa_t addr, int len,
+			int is_write);
 	void (*destructor)(struct kvm_io_device *this);
 
 	void             *private;
@@ -49,9 +50,10 @@ static inline void kvm_iodevice_write(struct kvm_io_device *dev,
 	dev->write(dev, addr, len, val);
 }
 
-static inline int kvm_iodevice_inrange(struct kvm_io_device *dev, gpa_t addr)
+static inline int kvm_iodevice_inrange(struct kvm_io_device *dev,
+				       gpa_t addr, int len, int is_write)
 {
-	return dev->in_range(dev, addr);
+	return dev->in_range(dev, addr, len, is_write);
 }
 
 static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)

virt/kvm/kvm_main.c

@@ -47,6 +47,10 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#include "coalesced_mmio.h"
+#endif
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
@@ -65,6 +69,8 @@ struct dentry *kvm_debugfs_dir;
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
 
+bool kvm_rebooting;
+
 static inline int valid_vcpu(int n)
 {
 	return likely(n >= 0 && n < KVM_MAX_VCPUS);
@@ -99,10 +105,11 @@ static void ack_flush(void *_completed)
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	int i, cpu;
+	int i, cpu, me;
 	cpumask_t cpus;
 	struct kvm_vcpu *vcpu;
 
+	me = get_cpu();
 	cpus_clear(cpus);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		vcpu = kvm->vcpus[i];
@@ -111,21 +118,24 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 		if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
 			continue;
 		cpu = vcpu->cpu;
-		if (cpu != -1 && cpu != raw_smp_processor_id())
+		if (cpu != -1 && cpu != me)
 			cpu_set(cpu, cpus);
 	}
 	if (cpus_empty(cpus))
-		return;
+		goto out;
 	++kvm->stat.remote_tlb_flush;
 	smp_call_function_mask(cpus, ack_flush, NULL, 1);
+out:
+	put_cpu();
 }
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
-	int i, cpu;
+	int i, cpu, me;
 	cpumask_t cpus;
 	struct kvm_vcpu *vcpu;
 
+	me = get_cpu();
 	cpus_clear(cpus);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		vcpu = kvm->vcpus[i];
@@ -134,12 +144,14 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
 			continue;
 		cpu = vcpu->cpu;
-		if (cpu != -1 && cpu != raw_smp_processor_id())
+		if (cpu != -1 && cpu != me)
 			cpu_set(cpu, cpus);
 	}
 	if (cpus_empty(cpus))
-		return;
+		goto out;
 	smp_call_function_mask(cpus, ack_flush, NULL, 1);
+out:
+	put_cpu();
 }
 
 
@@ -183,10 +195,23 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
 static struct kvm *kvm_create_vm(void)
 {
 	struct kvm *kvm = kvm_arch_create_vm();
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	struct page *page;
+#endif
 
 	if (IS_ERR(kvm))
 		goto out;
 
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page) {
+		kfree(kvm);
+		return ERR_PTR(-ENOMEM);
+	}
+	kvm->coalesced_mmio_ring =
+			(struct kvm_coalesced_mmio_ring *)page_address(page);
+#endif
+
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	spin_lock_init(&kvm->mmu_lock);
@@ -198,6 +223,9 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	kvm_coalesced_mmio_init(kvm);
+#endif
 out:
 	return kvm;
 }
@@ -240,6 +268,10 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_unlock(&kvm_lock);
 	kvm_io_bus_destroy(&kvm->pio_bus);
 	kvm_io_bus_destroy(&kvm->mmio_bus);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	if (kvm->coalesced_mmio_ring != NULL)
+		free_page((unsigned long)kvm->coalesced_mmio_ring);
+#endif
 	kvm_arch_destroy_vm(kvm);
 	mmdrop(mm);
 }
@@ -333,6 +365,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	r = -ENOMEM;
 
 	/* Allocate if a slot is being created */
+#ifndef CONFIG_S390
 	if (npages && !new.rmap) {
 		new.rmap = vmalloc(npages * sizeof(struct page *));
 
@@ -373,10 +406,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			goto out_free;
 		memset(new.dirty_bitmap, 0, dirty_bytes);
 	}
+#endif /* not defined CONFIG_S390 */
 
 	if (mem->slot >= kvm->nmemslots)
 		kvm->nmemslots = mem->slot + 1;
 
+	if (!npages)
+		kvm_arch_flush_shadow(kvm);
+
 	*memslot = new;
 
 	r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc);
@@ -532,6 +569,7 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 	struct page *page[1];
 	unsigned long addr;
 	int npages;
+	pfn_t pfn;
 
 	might_sleep();
 
@@ -544,19 +582,38 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 	npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page,
 				NULL);
 
-	if (npages != 1) {
-		get_page(bad_page);
-		return page_to_pfn(bad_page);
-	}
+	if (unlikely(npages != 1)) {
+		struct vm_area_struct *vma;
 
-	return page_to_pfn(page[0]);
+		vma = find_vma(current->mm, addr);
+		if (vma == NULL || addr < vma->vm_start ||
+		    !(vma->vm_flags & VM_PFNMAP)) {
+			get_page(bad_page);
+			return page_to_pfn(bad_page);
+		}
+
+		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+		BUG_ON(pfn_valid(pfn));
+	} else
+		pfn = page_to_pfn(page[0]);
+
+	return pfn;
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
-	return pfn_to_page(gfn_to_pfn(kvm, gfn));
+	pfn_t pfn;
+
+	pfn = gfn_to_pfn(kvm, gfn);
+	if (pfn_valid(pfn))
+		return pfn_to_page(pfn);
+
+	WARN_ON(!pfn_valid(pfn));
+
+	get_page(bad_page);
+	return bad_page;
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_page);
@@ -569,7 +626,8 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	put_page(pfn_to_page(pfn));
+	if (pfn_valid(pfn))
+		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
@@ -594,21 +652,25 @@ EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
 
 void kvm_set_pfn_dirty(pfn_t pfn)
 {
-	struct page *page = pfn_to_page(pfn);
-	if (!PageReserved(page))
-		SetPageDirty(page);
+	if (pfn_valid(pfn)) {
+		struct page *page = pfn_to_page(pfn);
+		if (!PageReserved(page))
+			SetPageDirty(page);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(pfn_t pfn)
 {
-	mark_page_accessed(pfn_to_page(pfn));
+	if (pfn_valid(pfn))
+		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
 void kvm_get_pfn(pfn_t pfn)
 {
-	get_page(pfn_to_page(pfn));
+	if (pfn_valid(pfn))
+		get_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_get_pfn);
 
@@ -798,6 +860,10 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 #ifdef CONFIG_X86
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
+#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
+		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
 	else
 		return VM_FAULT_SIGBUS;
@@ -1121,6 +1187,32 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		break;
 	}
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	case KVM_REGISTER_COALESCED_MMIO: {
+		struct kvm_coalesced_mmio_zone zone;
+		r = -EFAULT;
+		if (copy_from_user(&zone, argp, sizeof zone))
+			goto out;
+		r = -ENXIO;
+		r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_UNREGISTER_COALESCED_MMIO: {
+		struct kvm_coalesced_mmio_zone zone;
+		r = -EFAULT;
+		if (copy_from_user(&zone, argp, sizeof zone))
+			goto out;
+		r = -ENXIO;
+		r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -1179,7 +1271,6 @@ static int kvm_dev_ioctl_create_vm(void)
 static long kvm_dev_ioctl(struct file *filp,
 			  unsigned int ioctl, unsigned long arg)
 {
-	void __user *argp = (void __user *)arg;
 	long r = -EINVAL;
 
 	switch (ioctl) {
@@ -1196,7 +1287,7 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = kvm_dev_ioctl_create_vm();
 		break;
 	case KVM_CHECK_EXTENSION:
-		r = kvm_dev_ioctl_check_extension((long)argp);
+		r = kvm_dev_ioctl_check_extension(arg);
 		break;
 	case KVM_GET_VCPU_MMAP_SIZE:
 		r = -EINVAL;
@@ -1205,6 +1296,9 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = PAGE_SIZE;     /* struct kvm_run */
 #ifdef CONFIG_X86
 		r += PAGE_SIZE;    /* pio data page */
+#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
 	case KVM_TRACE_ENABLE:
@@ -1247,7 +1341,6 @@ static void hardware_disable(void *junk)
 	if (!cpu_isset(cpu, cpus_hardware_enabled))
 		return;
 	cpu_clear(cpu, cpus_hardware_enabled);
-	decache_vcpus_on_cpu(cpu);
 	kvm_arch_hardware_disable(NULL);
 }
 
@@ -1277,6 +1370,18 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	return NOTIFY_OK;
 }
 
+
+asmlinkage void kvm_handle_fault_on_reboot(void)
+{
+	if (kvm_rebooting)
+		/* spin while reset goes on */
+		while (true)
+			;
+	/* Fault while not rebooting.  We want the trace. */
+	BUG();
+}
+EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);
+
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
@@ -1286,6 +1391,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		 * in vmx root mode.
 		 */
 		printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+		kvm_rebooting = true;
 		on_each_cpu(hardware_disable, NULL, 1);
 	}
 	return NOTIFY_OK;
@@ -1312,14 +1418,15 @@ void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	}
 }
 
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr)
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
+					  gpa_t addr, int len, int is_write)
 {
 	int i;
 
 	for (i = 0; i < bus->dev_count; i++) {
 		struct kvm_io_device *pos = bus->devs[i];
 
-		if (pos->in_range(pos, addr))
+		if (pos->in_range(pos, addr, len, is_write))
 			return pos;
 	}
 

virt/kvm/kvm_trace.c

@@ -72,11 +72,7 @@ static void kvm_add_trace(void *probe_private, void *call_data,
 	rec.cycle_in 	= p->cycle_in;
 
 	if (rec.cycle_in) {
-		u64 cycle = 0;
-
-		cycle = get_cycles();
-		rec.u.cycle.cycle_lo = (u32)cycle;
-		rec.u.cycle.cycle_hi = (u32)(cycle >> 32);
+		rec.u.cycle.cycle_u64 = get_cycles();
 
 		for (i = 0; i < rec.extra_u32; i++)
 			rec.u.cycle.extra_u32[i] = va_arg(*args, u32);
@@ -114,8 +110,18 @@ static int kvm_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 {
 	struct kvm_trace *kt;
 
-	if (!relay_buf_full(buf))
+	if (!relay_buf_full(buf)) {
+		if (!prev_subbuf) {
+			/*
+			 * executed only once when the channel is opened
+			 * save metadata as first record
+			 */
+			subbuf_start_reserve(buf, sizeof(u32));
+			*(u32 *)subbuf = 0x12345678;
+		}
+
 		return 1;
+	}
 
 	kt = buf->chan->private_data;
 	atomic_inc(&kt->lost_records);