Merge branch 'master' into for-next

Conflicts:
	drivers/devfreq/exynos4_bus.c

Sync with Linus' tree to be able to apply patches that are
against newer code (mvneta).

5 files changed, 123 insertions, 71 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 23a41a9f8db9..3642239252b0 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -105,6 +105,15 @@ static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
 }
 
 #ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+				       assigned_dev->irq_source_id,
+				       assigned_dev->guest_irq, 1);
+	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
 static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
@@ -117,6 +126,23 @@ static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
 #endif
 
 #ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int index = find_index_from_host_irq(assigned_dev, irq);
+	u32 vector;
+	int ret = 0;
+
+	if (index >= 0) {
+		vector = assigned_dev->guest_msix_entries[index].vector;
+		ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+					   assigned_dev->irq_source_id,
+					   vector, 1);
+	}
+
+	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
 static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
@@ -334,11 +360,6 @@ 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)
 {
@@ -363,11 +384,6 @@ 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)
 {
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 9718e98d6d2a..b6eea5cc7b34 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -35,6 +35,7 @@
 
 #include "iodev.h"
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -332,7 +333,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		mutex_lock(&kvm->irqfds.resampler_lock);
 
 		list_for_each_entry(resampler,
-				    &kvm->irqfds.resampler_list, list) {
+				    &kvm->irqfds.resampler_list, link) {
 			if (resampler->notifier.gsi == irqfd->gsi) {
 				irqfd->resampler = resampler;
 				break;
@@ -425,17 +426,21 @@ fail:
 	kfree(irqfd);
 	return ret;
 }
+#endif
 
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
+#ifdef __KVM_HAVE_IOAPIC
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
 	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -555,6 +560,7 @@ static void __exit irqfd_module_exit(void)
 
 module_init(irqfd_module_init);
 module_exit(irqfd_module_exit);
+#endif
 
 /*
  * --------------------------------------------------------------------
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 037cb6730e68..4a340cb23013 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -52,7 +52,7 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	end_gfn = gfn + (size >> PAGE_SHIFT);
 	gfn    += 1;
 
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return pfn;
 
 	while (gfn < end_gfn)
@@ -106,7 +106,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
 		pfn = kvm_pin_pages(slot, gfn, page_size);
-		if (is_error_pfn(pfn)) {
+		if (is_error_noslot_pfn(pfn)) {
 			gfn += 1;
 			continue;
 		}
@@ -168,11 +168,7 @@ int kvm_assign_device(struct kvm *kvm,
 
 	r = iommu_attach_device(domain, &pdev->dev);
 	if (r) {
-		printk(KERN_ERR "assign device %x:%x:%x.%x failed",
-			pci_domain_nr(pdev->bus),
-			pdev->bus->number,
-			PCI_SLOT(pdev->devfn),
-			PCI_FUNC(pdev->devfn));
+		dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
 		return r;
 	}
 
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 2eb58af7ee99..656fa455e154 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -102,6 +102,23 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+				   struct kvm_lapic_irq *irq)
+{
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+	irq->dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq->vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq->delivery_mode = e->msi.data & 0x700;
+	irq->level = 1;
+	irq->shorthand = 0;
+	/* TODO Deal with RH bit of MSI message address */
+}
+
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level)
 {
@@ -110,22 +127,26 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	if (!level)
 		return -1;
 
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+	kvm_set_msi_irq(e, &irq);
 
-	irq.dest_id = (e->msi.address_lo &
-			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
-	irq.vector = (e->msi.data &
-			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
-	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
-	irq.delivery_mode = e->msi.data & 0x700;
-	irq.level = 1;
-	irq.shorthand = 0;
-
-	/* TODO Deal with RH bit of MSI message address */
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			 struct kvm *kvm)
+{
+	struct kvm_lapic_irq irq;
+	int r;
+
+	kvm_set_msi_irq(e, &irq);
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
+		return r;
+	else
+		return -EWOULDBLOCK;
+}
+
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
 {
 	struct kvm_kernel_irq_routing_entry route;
@@ -178,6 +199,44 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	return ret;
 }
 
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	struct kvm_irq_routing_table *irq_rt;
+	struct hlist_node *n;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	rcu_read_lock();
+	irq_rt = rcu_dereference(kvm->irq_routing);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, n, &irq_rt->map[irq], link) {
+			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+				ret = kvm_set_msi_inatomic(e, kvm);
+			else
+				ret = -EWOULDBLOCK;
+			break;
+		}
+	rcu_read_unlock();
+	return ret;
+}
+
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index be70035fd42a..1cd693a76a51 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -212,6 +212,11 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 	make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm)
+{
+	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+}
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -709,8 +714,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int r;
 	gfn_t base_gfn;
 	unsigned long npages;
-	unsigned long i;
-	struct kvm_memory_slot *memslot;
+	struct kvm_memory_slot *memslot, *slot;
 	struct kvm_memory_slot old, new;
 	struct kvm_memslots *slots, *old_memslots;
 
@@ -761,13 +765,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	/* Check for overlaps */
 	r = -EEXIST;
-	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
-		struct kvm_memory_slot *s = &kvm->memslots->memslots[i];
-
-		if (s == memslot || !s->npages)
+	kvm_for_each_memslot(slot, kvm->memslots) {
+		if (slot->id >= KVM_MEMORY_SLOTS || slot == memslot)
 			continue;
-		if (!((base_gfn + npages <= s->base_gfn) ||
-		      (base_gfn >= s->base_gfn + s->npages)))
+		if (!((base_gfn + npages <= slot->base_gfn) ||
+		      (base_gfn >= slot->base_gfn + slot->npages)))
 			goto out_free;
 	}
 
@@ -1208,7 +1210,7 @@ __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
 		return KVM_PFN_ERR_RO_FAULT;
 
 	if (kvm_is_error_hva(addr))
-		return KVM_PFN_ERR_BAD;
+		return KVM_PFN_NOSLOT;
 
 	/* Do not map writable pfn in the readonly memslot. */
 	if (writable && memslot_is_readonly(slot)) {
@@ -1290,7 +1292,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
 static struct page *kvm_pfn_to_page(pfn_t pfn)
 {
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return KVM_ERR_PTR_BAD_PAGE;
 
 	if (kvm_is_mmio_pfn(pfn)) {
@@ -1322,7 +1324,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
@@ -1848,6 +1850,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	atomic_inc(&kvm->online_vcpus);
 
 	mutex_unlock(&kvm->lock);
+	kvm_arch_vcpu_postcreate(vcpu);
 	return r;
 
 unlock_vcpu_destroy:
@@ -1929,10 +1932,6 @@ out_free1:
 			goto out;
 		}
 		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
-		if (r)
-			goto out_free2;
-		r = 0;
-out_free2:
 		kfree(kvm_regs);
 		break;
 	}
@@ -1954,12 +1953,10 @@ out_free2:
 		kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs));
 		if (IS_ERR(kvm_sregs)) {
 			r = PTR_ERR(kvm_sregs);
+			kvm_sregs = NULL;
 			goto out;
 		}
 		r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 	case KVM_GET_MP_STATE: {
@@ -1981,9 +1978,6 @@ out_free2:
 		if (copy_from_user(&mp_state, argp, sizeof mp_state))
 			goto out;
 		r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 	case KVM_TRANSLATE: {
@@ -2008,9 +2002,6 @@ out_free2:
 		if (copy_from_user(&dbg, argp, sizeof dbg))
 			goto out;
 		r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 	case KVM_SET_SIGNAL_MASK: {
@@ -2054,12 +2045,10 @@ out_free2:
 		fpu = memdup_user(argp, sizeof(*fpu));
 		if (IS_ERR(fpu)) {
 			r = PTR_ERR(fpu);
+			fpu = NULL;
 			goto out;
 		}
 		r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 	default:
@@ -2129,8 +2118,6 @@ static long kvm_vm_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_CREATE_VCPU:
 		r = kvm_vm_ioctl_create_vcpu(kvm, arg);
-		if (r < 0)
-			goto out;
 		break;
 	case KVM_SET_USER_MEMORY_REGION: {
 		struct kvm_userspace_memory_region kvm_userspace_mem;
@@ -2141,8 +2128,6 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 
 		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
-		if (r)
-			goto out;
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
@@ -2152,8 +2137,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&log, argp, sizeof log))
 			goto out;
 		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
-		if (r)
-			goto out;
 		break;
 	}
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
@@ -2163,9 +2146,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&zone, argp, sizeof zone))
 			goto out;
 		r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 	case KVM_UNREGISTER_COALESCED_MMIO: {
@@ -2174,9 +2154,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&zone, argp, sizeof zone))
 			goto out;
 		r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
-		if (r)
-			goto out;
-		r = 0;
 		break;
 	}
 #endif
@@ -2285,8 +2262,6 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 		log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
 
 		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
-		if (r)
-			goto out;
 		break;
 	}
 	default: