Merge branch 'master' of /home/cbou/linux-2.6

Conflicts:

	drivers/power/Kconfig
	drivers/power/Makefile

6 files changed, 392 insertions, 87 deletions

diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
new file mode 100644
index 00000000000..5ae620d32fa
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.c
@@ -0,0 +1,156 @@
+/*
+ * 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;
+}
diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h
new file mode 100644
index 00000000000..5ac0ec62846
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.h
@@ -0,0 +1,23 @@
+/*
+ * 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);
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 4232fd75dd2..c0d22870ee9 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -45,7 +45,7 @@
 #else
 #define ioapic_debug(fmt, arg...)
 #endif
-static void ioapic_deliver(struct kvm_ioapic *vioapic, int irq);
+static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq);
 
 static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 					  unsigned long addr,
@@ -89,8 +89,8 @@ static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
 	pent = &ioapic->redirtbl[idx];
 
 	if (!pent->fields.mask) {
-		ioapic_deliver(ioapic, idx);
-		if (pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
+		int injected = ioapic_deliver(ioapic, idx);
+		if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
 			pent->fields.remote_irr = 1;
 	}
 	if (!pent->fields.trig_mode)
@@ -133,7 +133,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	}
 }
 
-static void ioapic_inj_irq(struct kvm_ioapic *ioapic,
+static int ioapic_inj_irq(struct kvm_ioapic *ioapic,
 			   struct kvm_vcpu *vcpu,
 			   u8 vector, u8 trig_mode, u8 delivery_mode)
 {
@@ -143,7 +143,12 @@ static void ioapic_inj_irq(struct kvm_ioapic *ioapic,
 	ASSERT((delivery_mode == IOAPIC_FIXED) ||
 	       (delivery_mode == IOAPIC_LOWEST_PRIORITY));
 
-	kvm_apic_set_irq(vcpu, vector, trig_mode);
+	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,
@@ -186,7 +191,7 @@ static u32 ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
 	return mask;
 }
 
-static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
+static int 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;
@@ -195,7 +200,7 @@ static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode;
 	u32 deliver_bitmask;
 	struct kvm_vcpu *vcpu;
-	int vcpu_id;
+	int vcpu_id, r = 0;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
@@ -204,7 +209,7 @@ static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	deliver_bitmask = ioapic_get_delivery_bitmask(ioapic, dest, dest_mode);
 	if (!deliver_bitmask) {
 		ioapic_debug("no target on destination\n");
-		return;
+		return 0;
 	}
 
 	switch (delivery_mode) {
@@ -216,7 +221,7 @@ static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 			vcpu = ioapic->kvm->vcpus[0];
 #endif
 		if (vcpu != NULL)
-			ioapic_inj_irq(ioapic, vcpu, vector,
+			r = ioapic_inj_irq(ioapic, vcpu, vector,
 				       trig_mode, delivery_mode);
 		else
 			ioapic_debug("null lowest prio vcpu: "
@@ -234,18 +239,30 @@ static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 			deliver_bitmask &= ~(1 << vcpu_id);
 			vcpu = ioapic->kvm->vcpus[vcpu_id];
 			if (vcpu) {
-				ioapic_inj_irq(ioapic, vcpu, vector,
+				r = ioapic_inj_irq(ioapic, vcpu, vector,
 					       trig_mode, delivery_mode);
 			}
 		}
 		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);
 		break;
 	}
+	return r;
 }
 
 void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
@@ -268,38 +285,30 @@ void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	}
 }
 
-static int get_eoi_gsi(struct kvm_ioapic *ioapic, int vector)
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi)
 {
-	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->arch.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);
+		ioapic_service(ioapic, gsi);
+}
+
+void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	int i;
+
+	for (i = 0; i < IOAPIC_NUM_PINS; i++)
+		if (ioapic->redirtbl[i].fields.vector == 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;
 
diff --git a/virt/kvm/iodev.h b/virt/kvm/iodev.h
index c14e642027b..55e8846ac3a 100644
--- a/virt/kvm/iodev.h
+++ b/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)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e89338e2b04..a845890b680 100644
--- a/virt/kvm/kvm_main.c
+++ b/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);
@@ -522,6 +559,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 		return bad_hva();
 	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(gfn_to_hva);
 
 /*
  * Requires current->mm->mmap_sem to be held
@@ -531,6 +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();
 
@@ -543,19 +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;
+
+		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 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);
@@ -568,7 +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);
 
@@ -593,21 +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);
 
@@ -757,25 +820,26 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
  */
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-	add_wait_queue(&vcpu->wq, &wait);
+		if (kvm_cpu_has_interrupt(vcpu))
+			break;
+		if (kvm_cpu_has_pending_timer(vcpu))
+			break;
+		if (kvm_arch_vcpu_runnable(vcpu))
+			break;
+		if (signal_pending(current))
+			break;
 
-	/*
-	 * We will block until either an interrupt or a signal wakes us up
-	 */
-	while (!kvm_cpu_has_interrupt(vcpu)
-	       && !kvm_cpu_has_pending_timer(vcpu)
-	       && !signal_pending(current)
-	       && !kvm_arch_vcpu_runnable(vcpu)) {
-		set_current_state(TASK_INTERRUPTIBLE);
 		vcpu_put(vcpu);
 		schedule();
 		vcpu_load(vcpu);
 	}
 
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&vcpu->wq, &wait);
+	finish_wait(&vcpu->wq, &wait);
 }
 
 void kvm_resched(struct kvm_vcpu *vcpu)
@@ -797,6 +861,10 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	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;
 	get_page(page);
@@ -834,7 +902,7 @@ static const struct file_operations kvm_vcpu_fops = {
  */
 static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 {
-	int fd = anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu);
+	int fd = anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, 0);
 	if (fd < 0)
 		kvm_put_kvm(vcpu->kvm);
 	return fd;
@@ -1119,6 +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);
 	}
@@ -1167,7 +1261,7 @@ static int kvm_dev_ioctl_create_vm(void)
 	kvm = kvm_create_vm();
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
-	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm);
+	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, 0);
 	if (fd < 0)
 		kvm_put_kvm(kvm);
 
@@ -1177,7 +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) {
@@ -1194,7 +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;
@@ -1204,6 +1297,9 @@ static long kvm_dev_ioctl(struct file *filp,
 #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:
 	case KVM_TRACE_PAUSE:
@@ -1245,7 +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);
 }
 
@@ -1264,17 +1359,29 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	case CPU_UP_CANCELED:
 		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
 		       cpu);
-		smp_call_function_single(cpu, hardware_disable, NULL, 0, 1);
+		smp_call_function_single(cpu, hardware_disable, NULL, 1);
 		break;
 	case CPU_ONLINE:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
-		smp_call_function_single(cpu, hardware_enable, NULL, 0, 1);
+		smp_call_function_single(cpu, hardware_enable, NULL, 1);
 		break;
 	}
 	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)
 {
@@ -1284,7 +1391,8 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		 * in vmx root mode.
 		 */
 		printk(KERN_INFO "kvm: exiting hardware virtualization\n");
-		on_each_cpu(hardware_disable, NULL, 0, 1);
+		kvm_rebooting = true;
+		on_each_cpu(hardware_disable, NULL, 1);
 	}
 	return NOTIFY_OK;
 }
@@ -1310,14 +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;
 	}
 
@@ -1472,12 +1581,12 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu,
 				kvm_arch_check_processor_compat,
-				&r, 0, 1);
+				&r, 1);
 		if (r < 0)
 			goto out_free_1;
 	}
 
-	on_each_cpu(hardware_enable, NULL, 0, 1);
+	on_each_cpu(hardware_enable, NULL, 1);
 	r = register_cpu_notifier(&kvm_cpu_notifier);
 	if (r)
 		goto out_free_2;
@@ -1523,7 +1632,7 @@ out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 out_free_2:
-	on_each_cpu(hardware_disable, NULL, 0, 1);
+	on_each_cpu(hardware_disable, NULL, 1);
 out_free_1:
 	kvm_arch_hardware_unsetup();
 out_free_0:
@@ -1545,7 +1654,7 @@ void kvm_exit(void)
 	sysdev_class_unregister(&kvm_sysdev_class);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
-	on_each_cpu(hardware_disable, NULL, 0, 1);
+	on_each_cpu(hardware_disable, NULL, 1);
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
 	kvm_exit_debug();
diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c
index 0e495470788..58141f31ea8 100644
--- a/virt/kvm/kvm_trace.c
+++ b/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);