Merge tag 'v3.6-rc2' into next

Linux 3.6-rc2

Resync with Linus.

6 files changed, 76 insertions, 59 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 01f572c..23a41a9 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -334,6 +334,11 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 }
 
 #ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
+{
+	return IRQ_WAKE_THREAD;
+}
+
 static int assigned_device_enable_host_msi(struct kvm *kvm,
 					   struct kvm_assigned_dev_kernel *dev)
 {
@@ -346,7 +351,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 	}
 
 	dev->host_irq = dev->dev->irq;
-	if (request_threaded_irq(dev->host_irq, NULL,
+	if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi,
 				 kvm_assigned_dev_thread_msi, 0,
 				 dev->irq_name, dev)) {
 		pci_disable_msi(dev->dev);
@@ -358,6 +363,11 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 #endif
 
 #ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
+{
+	return IRQ_WAKE_THREAD;
+}
+
 static int assigned_device_enable_host_msix(struct kvm *kvm,
 					    struct kvm_assigned_dev_kernel *dev)
 {
@@ -374,7 +384,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 
 	for (i = 0; i < dev->entries_nr; i++) {
 		r = request_threaded_irq(dev->host_msix_entries[i].vector,
-					 NULL, kvm_assigned_dev_thread_msix,
+					 kvm_assigned_dev_msix,
+					 kvm_assigned_dev_thread_msix,
 					 0, dev->irq_name, dev);
 		if (r)
 			goto err;
@@ -635,7 +646,6 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	int r = 0, idx;
 	struct kvm_assigned_dev_kernel *match;
 	struct pci_dev *dev;
-	u8 header_type;
 
 	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
 		return -EINVAL;
@@ -668,8 +678,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	}
 
 	/* Don't allow bridges to be assigned */
-	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
-	if ((header_type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) {
+	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) {
 		r = -EPERM;
 		goto out_put;
 	}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index f59c1e8..7d7e2aa 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -198,7 +198,7 @@ static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
 }
 
 static int
-kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
+kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
@@ -212,12 +212,12 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 		return -ENOMEM;
 
 	irqfd->kvm = kvm;
-	irqfd->gsi = gsi;
+	irqfd->gsi = args->gsi;
 	INIT_LIST_HEAD(&irqfd->list);
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
 
-	file = eventfd_fget(fd);
+	file = eventfd_fget(args->fd);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 		goto fail;
@@ -298,19 +298,19 @@ kvm_eventfd_init(struct kvm *kvm)
  * shutdown any irqfd's that match fd+gsi
  */
 static int
-kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
+kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct _irqfd *irqfd, *tmp;
 	struct eventfd_ctx *eventfd;
 
-	eventfd = eventfd_ctx_fdget(fd);
+	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
 	spin_lock_irq(&kvm->irqfds.lock);
 
 	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
-		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi) {
+		if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
 			/*
 			 * This rcu_assign_pointer is needed for when
 			 * another thread calls kvm_irq_routing_update before
@@ -338,12 +338,15 @@ kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
 }
 
 int
-kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	if (flags & KVM_IRQFD_FLAG_DEASSIGN)
-		return kvm_irqfd_deassign(kvm, fd, gsi);
+	if (args->flags & ~KVM_IRQFD_FLAG_DEASSIGN)
+		return -EINVAL;
+
+	if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
+		return kvm_irqfd_deassign(kvm, args);
 
-	return kvm_irqfd_assign(kvm, fd, gsi);
+	return kvm_irqfd_assign(kvm, args);
 }
 
 /*
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 26fd54d..ef61d52 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -191,7 +191,8 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 }
 
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+		       int level)
 {
 	u32 old_irr;
 	u32 mask = 1 << irq;
@@ -201,9 +202,11 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	spin_lock(&ioapic->lock);
 	old_irr = ioapic->irr;
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
+		int irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
+						     irq_source_id, level);
 		entry = ioapic->redirtbl[irq];
-		level ^= entry.fields.polarity;
-		if (!level)
+		irq_level ^= entry.fields.polarity;
+		if (!irq_level)
 			ioapic->irr &= ~mask;
 		else {
 			int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
@@ -221,6 +224,16 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	return ret;
 }
 
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
+{
+	int i;
+
+	spin_lock(&ioapic->lock);
+	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
+		__clear_bit(irq_source_id, &ioapic->irq_states[i]);
+	spin_unlock(&ioapic->lock);
+}
+
 static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 				     int trigger_mode)
 {
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 32872a0..a30abfe 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -74,7 +74,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
 bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
 int kvm_ioapic_init(struct kvm *kvm);
 void kvm_ioapic_destroy(struct kvm *kvm);
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+		       int level);
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 5afb431..83402d7 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -33,26 +33,12 @@
 
 #include "ioapic.h"
 
-static inline int kvm_irq_line_state(unsigned long *irq_state,
-				     int irq_source_id, int level)
-{
-	/* Logical OR for level trig interrupt */
-	if (level)
-		set_bit(irq_source_id, irq_state);
-	else
-		clear_bit(irq_source_id, irq_state);
-
-	return !!(*irq_state);
-}
-
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level)
 {
 #ifdef CONFIG_X86
 	struct kvm_pic *pic = pic_irqchip(kvm);
-	level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
-				   irq_source_id, level);
-	return kvm_pic_set_irq(pic, e->irqchip.pin, level);
+	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
 #else
 	return -1;
 #endif
@@ -62,10 +48,7 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
-				   irq_source_id, level);
-
-	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level);
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -249,8 +232,6 @@ unlock:
 
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 {
-	int i;
-
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 
 	mutex_lock(&kvm->irq_lock);
@@ -263,14 +244,10 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 	if (!irqchip_in_kernel(kvm))
 		goto unlock;
 
-	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
-		clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
-		if (i >= 16)
-			continue;
+	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
 #ifdef CONFIG_X86
-		clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
+	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
 #endif
-	}
 unlock:
 	mutex_unlock(&kvm->irq_lock);
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7e14068..2468523 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -516,16 +516,32 @@ out_err_nodisable:
 	return ERR_PTR(r);
 }
 
+/*
+ * Avoid using vmalloc for a small buffer.
+ * Should not be used when the size is statically known.
+ */
+void *kvm_kvzalloc(unsigned long size)
+{
+	if (size > PAGE_SIZE)
+		return vzalloc(size);
+	else
+		return kzalloc(size, GFP_KERNEL);
+}
+
+void kvm_kvfree(const void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+
 static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
 	if (!memslot->dirty_bitmap)
 		return;
 
-	if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
-		vfree(memslot->dirty_bitmap);
-	else
-		kfree(memslot->dirty_bitmap);
-
+	kvm_kvfree(memslot->dirty_bitmap);
 	memslot->dirty_bitmap = NULL;
 }
 
@@ -617,11 +633,7 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 #ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
-	if (dirty_bytes > PAGE_SIZE)
-		memslot->dirty_bitmap = vzalloc(dirty_bytes);
-	else
-		memslot->dirty_bitmap = kzalloc(dirty_bytes, GFP_KERNEL);
-
+	memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
@@ -1586,7 +1598,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 */
 	for (pass = 0; pass < 2 && !yielded; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			if (!pass && i < last_boosted_vcpu) {
+			if (!pass && i <= last_boosted_vcpu) {
 				i = last_boosted_vcpu;
 				continue;
 			} else if (pass && i > last_boosted_vcpu)
@@ -2047,7 +2059,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&data, argp, sizeof data))
 			goto out;
-		r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags);
+		r = kvm_irqfd(kvm, &data);
 		break;
 	}
 	case KVM_IOEVENTFD: {
@@ -2213,7 +2225,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_SIGNAL_MSI:
 #endif
 		return 1;
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef KVM_CAP_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
@@ -2845,6 +2857,7 @@ void kvm_exit(void)
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
 	free_cpumask_var(cpus_hardware_enabled);
+	__free_page(fault_page);
 	__free_page(hwpoison_page);
 	__free_page(bad_page);
 }