6 files changed, 150 insertions, 76 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 02ff2b19dbe2..4d10b1e047f4 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -316,12 +316,16 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 				kvm_assigned_dev_intr, 0,
 				"kvm_assigned_msix_device",
 				(void *)dev);
-		/* FIXME: free requested_irq's on failure */
 		if (r)
-			return r;
+			goto err;
 	}
 
 	return 0;
+err:
+	for (i -= 1; i >= 0; i--)
+		free_irq(dev->host_msix_entries[i].vector, (void *)dev);
+	pci_disable_msix(dev->dev);
+	return r;
 }
 
 #endif
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 36e258029649..53850177163f 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -120,8 +120,10 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	return ret;
 
 out_free_dev:
+	kvm->coalesced_mmio_dev = NULL;
 	kfree(dev);
 out_free_page:
+	kvm->coalesced_mmio_ring = NULL;
 	__free_page(page);
 out_err:
 	return ret;
@@ -139,7 +141,7 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
 
 	if (dev == NULL)
-		return -EINVAL;
+		return -ENXIO;
 
 	mutex_lock(&kvm->slots_lock);
 	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
@@ -162,7 +164,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 	struct kvm_coalesced_mmio_zone *z;
 
 	if (dev == NULL)
-		return -EINVAL;
+		return -ENXIO;
 
 	mutex_lock(&kvm->slots_lock);
 
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 03a5eb22da2b..7c79c1d76d0c 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -197,7 +197,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
 		entry = ioapic->redirtbl[irq];
 		level ^= entry.fields.polarity;
@@ -214,7 +214,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 		}
 		trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 
 	return ret;
 }
@@ -238,9 +238,9 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 		 * is dropped it will be put into irr and will be delivered
 		 * after ack notifier returns.
 		 */
-		mutex_unlock(&ioapic->lock);
+		spin_unlock(&ioapic->lock);
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
-		mutex_lock(&ioapic->lock);
+		spin_lock(&ioapic->lock);
 
 		if (trigger_mode != IOAPIC_LEVEL_TRIG)
 			continue;
@@ -259,9 +259,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 	smp_rmb();
 	if (!test_bit(vector, ioapic->handled_vectors))
 		return;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 }
 
 static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
@@ -287,7 +287,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	addr &= 0xff;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		result = ioapic->ioregsel;
@@ -301,7 +301,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 		result = 0;
 		break;
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 
 	switch (len) {
 	case 8:
@@ -338,7 +338,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	}
 
 	addr &= 0xff;
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		ioapic->ioregsel = data;
@@ -356,7 +356,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		break;
 	}
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -386,7 +386,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
 	if (!ioapic)
 		return -ENOMEM;
-	mutex_init(&ioapic->lock);
+	spin_lock_init(&ioapic->lock);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -419,9 +419,9 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
 	if (!ioapic)
 		return -EINVAL;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -431,9 +431,9 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
 	if (!ioapic)
 		return -EINVAL;
 
-	mutex_lock(&ioapic->lock);
+	spin_lock(&ioapic->lock);
 	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
 	update_handled_vectors(ioapic);
-	mutex_unlock(&ioapic->lock);
+	spin_unlock(&ioapic->lock);
 	return 0;
 }
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 8a751b78a430..0b190c34ccc3 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -45,7 +45,7 @@ struct kvm_ioapic {
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
-	struct mutex lock;
+	spinlock_t lock;
 	DECLARE_BITMAP(handled_vectors, 256);
 };
 
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 80fd3ad3b2de..d2f06be63354 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -32,12 +32,30 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm);
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
+static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
+			   gfn_t gfn, unsigned long size)
+{
+	gfn_t end_gfn;
+	pfn_t pfn;
+
+	pfn     = gfn_to_pfn_memslot(kvm, slot, gfn);
+	end_gfn = gfn + (size >> PAGE_SHIFT);
+	gfn    += 1;
+
+	if (is_error_pfn(pfn))
+		return pfn;
+
+	while (gfn < end_gfn)
+		gfn_to_pfn_memslot(kvm, slot, gfn++);
+
+	return pfn;
+}
+
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
-	gfn_t gfn = slot->base_gfn;
-	unsigned long npages = slot->npages;
+	gfn_t gfn, end_gfn;
 	pfn_t pfn;
-	int i, r = 0;
+	int r = 0;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
 	int flags;
 
@@ -45,31 +63,62 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	if (!domain)
 		return 0;
 
+	gfn     = slot->base_gfn;
+	end_gfn = gfn + slot->npages;
+
 	flags = IOMMU_READ | IOMMU_WRITE;
 	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
 		flags |= IOMMU_CACHE;
 
-	for (i = 0; i < npages; i++) {
-		/* check if already mapped */
-		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
+
+	while (gfn < end_gfn) {
+		unsigned long page_size;
+
+		/* Check if already mapped */
+		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+			gfn += 1;
+			continue;
+		}
+
+		/* Get the page size we could use to map */
+		page_size = kvm_host_page_size(kvm, gfn);
+
+		/* Make sure the page_size does not exceed the memslot */
+		while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+			page_size >>= 1;
+
+		/* Make sure gfn is aligned to the page size we want to map */
+		while ((gfn << PAGE_SHIFT) & (page_size - 1))
+			page_size >>= 1;
+
+		/*
+		 * Pin all pages we are about to map in memory. This is
+		 * important because we unmap and unpin in 4kb steps later.
+		 */
+		pfn = kvm_pin_pages(kvm, slot, gfn, page_size);
+		if (is_error_pfn(pfn)) {
+			gfn += 1;
 			continue;
+		}
 
-		pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
-		r = iommu_map_range(domain,
-				    gfn_to_gpa(gfn),
-				    pfn_to_hpa(pfn),
-				    PAGE_SIZE, flags);
+		/* Map into IO address space */
+		r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+			      get_order(page_size), flags);
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%lx\n", pfn);
 			goto unmap_pages;
 		}
-		gfn++;
+
+		gfn += page_size >> PAGE_SHIFT;
+
+
 	}
+
 	return 0;
 
 unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, i);
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
 	return r;
 }
 
@@ -78,7 +127,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm)
 	int i, r = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		r = kvm_iommu_map_pages(kvm, &slots->memslots[i]);
@@ -189,27 +238,47 @@ out_unmap:
 	return r;
 }
 
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages)
 {
-	gfn_t gfn = base_gfn;
+	struct iommu_domain *domain;
+	gfn_t end_gfn, gfn;
 	pfn_t pfn;
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	unsigned long i;
 	u64 phys;
 
+	domain  = kvm->arch.iommu_domain;
+	end_gfn = base_gfn + npages;
+	gfn     = base_gfn;
+
 	/* check if iommu exists and in use */
 	if (!domain)
 		return;
 
-	for (i = 0; i < npages; i++) {
+	while (gfn < end_gfn) {
+		unsigned long unmap_pages;
+		int order;
+
+		/* Get physical address */
 		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
-		pfn = phys >> PAGE_SHIFT;
-		kvm_release_pfn_clean(pfn);
-		gfn++;
-	}
+		pfn  = phys >> PAGE_SHIFT;
+
+		/* Unmap address from IO address space */
+		order       = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+		unmap_pages = 1ULL << order;
 
-	iommu_unmap_range(domain, gfn_to_gpa(base_gfn), PAGE_SIZE * npages);
+		/* Unpin all pages we just unmapped to not leak any memory */
+		kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+		gfn += unmap_pages;
+	}
 }
 
 static int kvm_iommu_unmap_memslots(struct kvm *kvm)
@@ -217,7 +286,7 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm)
 	int i;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c82ae2492634..f032806a212f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -422,9 +422,6 @@ 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;
 
@@ -560,6 +557,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
+	r = -EINVAL;
+	if (npages > KVM_MEM_MAX_NR_PAGES)
+		goto out;
+
 	if (!npages)
 		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
@@ -833,7 +834,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; ++i) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -855,7 +856,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 
 	gfn = unalias_gfn_instantiation(kvm, gfn);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
@@ -899,7 +900,7 @@ out:
 int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *memslot = NULL;
 
 	gfn = unalias_gfn(kvm, gfn);
@@ -914,6 +915,11 @@ int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return memslot - slots->memslots;
 }
 
+static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+}
+
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot;
@@ -922,7 +928,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 	slot = gfn_to_memslot_unaliased(kvm, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return bad_hva();
-	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
+	return gfn_to_hva_memslot(slot, gfn);
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
@@ -972,11 +978,6 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
-static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
-{
-	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
-}
-
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn)
 {
@@ -1190,13 +1191,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	memslot = gfn_to_memslot_unaliased(kvm, gfn);
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
-		unsigned long *p = memslot->dirty_bitmap +
-					rel_gfn / BITS_PER_LONG;
-		int offset = rel_gfn % BITS_PER_LONG;
 
-		/* avoid RMW */
-		if (!generic_test_le_bit(offset, p))
-			generic___set_le_bit(offset, p);
+		generic___set_le_bit(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 
@@ -1609,7 +1605,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		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;
@@ -1621,7 +1616,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		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;
@@ -1755,12 +1749,19 @@ static struct file_operations kvm_vm_fops = {
 
 static int kvm_dev_ioctl_create_vm(void)
 {
-	int fd;
+	int fd, r;
 	struct kvm *kvm;
 
 	kvm = kvm_create_vm();
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	r = kvm_coalesced_mmio_init(kvm);
+	if (r < 0) {
+		kvm_put_kvm(kvm);
+		return r;
+	}
+#endif
 	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (fd < 0)
 		kvm_put_kvm(kvm);
@@ -1928,11 +1929,6 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 		       cpu);
 		hardware_disable(NULL);
 		break;
-	case CPU_UP_CANCELED:
-		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
-		       cpu);
-		smp_call_function_single(cpu, hardware_disable, NULL, 1);
-		break;
 	case CPU_ONLINE:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
@@ -1991,7 +1987,9 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
 	int i;
-	struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]);
+	struct kvm_io_bus *bus;
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
 	for (i = 0; i < bus->dev_count; i++)
 		if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
 			return 0;
@@ -2003,8 +2001,9 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val)
 {
 	int i;
-	struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]);
+	struct kvm_io_bus *bus;
 
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
 	for (i = 0; i < bus->dev_count; i++)
 		if (!kvm_iodevice_read(bus->devs[i], addr, len, val))
 			return 0;
@@ -2179,7 +2178,7 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 	kvm_arch_vcpu_put(vcpu);
 }
 
-int kvm_init(void *opaque, unsigned int vcpu_size,
+int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		  struct module *module)
 {
 	int r;
@@ -2229,8 +2228,9 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		goto out_free_4;
 
 	/* A kmem cache lets us meet the alignment requirements of fx_save. */
-	kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size,
-					   __alignof__(struct kvm_vcpu),
+	if (!vcpu_align)
+		vcpu_align = __alignof__(struct kvm_vcpu);
+	kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align,
 					   0, NULL);
 	if (!kvm_vcpu_cache) {
 		r = -ENOMEM;
@@ -2279,7 +2279,6 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	tracepoint_synchronize_unregister();
 	kvm_exit_debug();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);