Merge tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Gleb Natapov:
 "Highlights of the updates are:

  general:
   - new emulated device API
   - legacy device assignment is now optional
   - irqfd interface is more generic and can be shared between arches

  x86:
   - VMCS shadow support and other nested VMX improvements
   - APIC virtualization and Posted Interrupt hardware support
   - Optimize mmio spte zapping

  ppc:
    - BookE: in-kernel MPIC emulation with irqfd support
    - Book3S: in-kernel XICS emulation (incomplete)
    - Book3S: HV: migration fixes
    - BookE: more debug support preparation
    - BookE: e6500 support

  ARM:
   - reworking of Hyp idmaps

  s390:
   - ioeventfd for virtio-ccw

  And many other bug fixes, cleanups and improvements"

* tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  kvm: Add compat_ioctl for device control API
  KVM: x86: Account for failing enable_irq_window for NMI window request
  KVM: PPC: Book3S: Add API for in-kernel XICS emulation
  kvm/ppc/mpic: fix missing unlock in set_base_addr()
  kvm/ppc: Hold srcu lock when calling kvm_io_bus_read/write
  kvm/ppc/mpic: remove users
  kvm/ppc/mpic: fix mmio region lists when multiple guests used
  kvm/ppc/mpic: remove default routes from documentation
  kvm: KVM_CAP_IOMMU only available with device assignment
  ARM: KVM: iterate over all CPUs for CPU compatibility check
  KVM: ARM: Fix spelling in error message
  ARM: KVM: define KVM_ARM_MAX_VCPUS unconditionally
  KVM: ARM: Fix API documentation for ONE_REG encoding
  ARM: KVM: promote vfp_host pointer to generic host cpu context
  ARM: KVM: add architecture specific hook for capabilities
  ARM: KVM: perform HYP initilization for hotplugged CPUs
  ARM: KVM: switch to a dual-step HYP init code
  ARM: KVM: rework HYP page table freeing
  ARM: KVM: enforce maximum size for identity mapped code
  ARM: KVM: move to a KVM provided HYP idmap
  ...

3 files changed, 161 insertions, 62 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c13958251927..f0eea07d2c2b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -117,14 +117,13 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_APF_HALT          12
 #define KVM_REQ_STEAL_UPDATE      13
 #define KVM_REQ_NMI               14
-#define KVM_REQ_IMMEDIATE_EXIT    15
-#define KVM_REQ_PMU               16
-#define KVM_REQ_PMI               17
-#define KVM_REQ_WATCHDOG          18
-#define KVM_REQ_MASTERCLOCK_UPDATE 19
-#define KVM_REQ_MCLOCK_INPROGRESS 20
-#define KVM_REQ_EPR_EXIT          21
-#define KVM_REQ_EOIBITMAP         22
+#define KVM_REQ_PMU               15
+#define KVM_REQ_PMI               16
+#define KVM_REQ_WATCHDOG          17
+#define KVM_REQ_MASTERCLOCK_UPDATE 18
+#define KVM_REQ_MCLOCK_INPROGRESS 19
+#define KVM_REQ_EPR_EXIT          20
+#define KVM_REQ_SCAN_IOAPIC       21
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -133,6 +132,9 @@ struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
+extern raw_spinlock_t kvm_lock;
+extern struct list_head vm_list;
+
 struct kvm_io_range {
 	gpa_t addr;
 	int len;
@@ -149,6 +151,7 @@ struct kvm_io_bus {
 enum kvm_bus {
 	KVM_MMIO_BUS,
 	KVM_PIO_BUS,
+	KVM_VIRTIO_CCW_NOTIFY_BUS,
 	KVM_NR_BUSES
 };
 
@@ -252,6 +255,7 @@ struct kvm_vcpu {
 		bool dy_eligible;
 	} spin_loop;
 #endif
+	bool preempted;
 	struct kvm_vcpu_arch arch;
 };
 
@@ -285,7 +289,8 @@ struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
 	u32 type;
 	int (*set)(struct kvm_kernel_irq_routing_entry *e,
-		   struct kvm *kvm, int irq_source_id, int level);
+		   struct kvm *kvm, int irq_source_id, int level,
+		   bool line_status);
 	union {
 		struct {
 			unsigned irqchip;
@@ -296,10 +301,10 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
 struct kvm_irq_routing_table {
-	int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS];
+	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
 	struct kvm_kernel_irq_routing_entry *rt_entries;
 	u32 nr_rt_entries;
 	/*
@@ -385,6 +390,7 @@ struct kvm {
 	long mmu_notifier_count;
 #endif
 	long tlbs_dirty;
+	struct list_head devices;
 };
 
 #define kvm_err(fmt, ...) \
@@ -424,6 +430,19 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 int __must_check vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+int kvm_irqfd_init(void);
+void kvm_irqfd_exit(void);
+#else
+static inline int kvm_irqfd_init(void)
+{
+	return 0;
+}
+
+static inline void kvm_irqfd_exit(void)
+{
+}
+#endif
 int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		  struct module *module);
 void kvm_exit(void);
@@ -452,24 +471,39 @@ id_to_memslot(struct kvm_memslots *slots, int id)
 	return slot;
 }
 
+/*
+ * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
+ * - create a new memory slot
+ * - delete an existing memory slot
+ * - modify an existing memory slot
+ *   -- move it in the guest physical memory space
+ *   -- just change its flags
+ *
+ * Since flags can be changed by some of these operations, the following
+ * differentiation is the best we can do for __kvm_set_memory_region():
+ */
+enum kvm_mr_change {
+	KVM_MR_CREATE,
+	KVM_MR_DELETE,
+	KVM_MR_MOVE,
+	KVM_MR_FLAGS_ONLY,
+};
+
 int kvm_set_memory_region(struct kvm *kvm,
-			  struct kvm_userspace_memory_region *mem,
-			  bool user_alloc);
+			  struct kvm_userspace_memory_region *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    struct kvm_userspace_memory_region *mem,
-			    bool user_alloc);
+			    struct kvm_userspace_memory_region *mem);
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont);
 int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
-				struct kvm_memory_slot old,
 				struct kvm_userspace_memory_region *mem,
-				bool user_alloc);
+				enum kvm_mr_change change);
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
-				struct kvm_memory_slot old,
-				bool user_alloc);
+				const struct kvm_memory_slot *old,
+				enum kvm_mr_change change);
 bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
 /* flush all memory translations */
@@ -539,7 +573,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
-void kvm_make_update_eoibitmap_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -555,10 +589,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 				struct kvm_dirty_log *log);
 
 int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-				   struct
-				   kvm_userspace_memory_region *mem,
-				   bool user_alloc);
-int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
+				   struct kvm_userspace_memory_region *mem);
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
+			bool line_status);
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg);
 
@@ -632,7 +665,6 @@ static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
 void kvm_arch_destroy_vm(struct kvm *kvm);
-void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
@@ -684,15 +716,11 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask);
 
-#ifdef __KVM_HAVE_IOAPIC
-void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
-				   union kvm_ioapic_redirect_entry *entry,
-				   unsigned long *deliver_bitmask);
-#endif
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+		bool line_status);
 int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
-		int irq_source_id, int level);
+		int irq_source_id, int level, bool line_status);
 bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
@@ -705,7 +733,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 /* For vcpu->arch.iommu_flags */
 #define KVM_IOMMU_CACHE_COHERENCY	0x1
 
-#ifdef CONFIG_IOMMU_API
+#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
 int kvm_iommu_map_guest(struct kvm *kvm);
@@ -714,7 +742,7 @@ int kvm_assign_device(struct kvm *kvm,
 		      struct kvm_assigned_dev_kernel *assigned_dev);
 int kvm_deassign_device(struct kvm *kvm,
 			struct kvm_assigned_dev_kernel *assigned_dev);
-#else /* CONFIG_IOMMU_API */
+#else
 static inline int kvm_iommu_map_pages(struct kvm *kvm,
 				      struct kvm_memory_slot *slot)
 {
@@ -726,28 +754,11 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
 {
 }
 
-static inline int kvm_iommu_map_guest(struct kvm *kvm)
-{
-	return -ENODEV;
-}
-
 static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
 {
 	return 0;
 }
-
-static inline int kvm_assign_device(struct kvm *kvm,
-		struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	return 0;
-}
-
-static inline int kvm_deassign_device(struct kvm *kvm,
-		struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	return 0;
-}
-#endif /* CONFIG_IOMMU_API */
+#endif
 
 static inline void __guest_enter(void)
 {
@@ -921,7 +932,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 }
 #endif
 
-#ifdef KVM_CAP_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
 #define KVM_MAX_IRQ_ROUTES 1024
 
@@ -930,6 +941,9 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+			  struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue);
 void kvm_free_irq_routing(struct kvm *kvm);
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
@@ -998,11 +1012,13 @@ static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
 
 #endif
 
-#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
+#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 
 long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 				  unsigned long arg);
 
+void kvm_free_all_assigned_devices(struct kvm *kvm);
+
 #else
 
 static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
@@ -1011,6 +1027,8 @@ static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 	return -ENOTTY;
 }
 
+static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
+
 #endif
 
 static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
@@ -1028,6 +1046,46 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 	}
 }
 
+extern bool kvm_rebooting;
+
+struct kvm_device_ops;
+
+struct kvm_device {
+	struct kvm_device_ops *ops;
+	struct kvm *kvm;
+	void *private;
+	struct list_head vm_node;
+};
+
+/* create, destroy, and name are mandatory */
+struct kvm_device_ops {
+	const char *name;
+	int (*create)(struct kvm_device *dev, u32 type);
+
+	/*
+	 * Destroy is responsible for freeing dev.
+	 *
+	 * Destroy may be called before or after destructors are called
+	 * on emulated I/O regions, depending on whether a reference is
+	 * held by a vcpu or other kvm component that gets destroyed
+	 * after the emulated I/O.
+	 */
+	void (*destroy)(struct kvm_device *dev);
+
+	int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
+	int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
+	int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
+	long (*ioctl)(struct kvm_device *dev, unsigned int ioctl,
+		      unsigned long arg);
+};
+
+void kvm_device_get(struct kvm_device *dev);
+void kvm_device_put(struct kvm_device *dev);
+struct kvm_device *kvm_device_from_filp(struct file *filp);
+
+extern struct kvm_device_ops kvm_mpic_ops;
+extern struct kvm_device_ops kvm_xics_ops;
+
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
 static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 19911dddaeb7..7005d1109ec9 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -37,7 +37,7 @@ TRACE_EVENT(kvm_userspace_exit,
 		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
 );
 
-#if defined(__KVM_HAVE_IRQ_LINE)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -122,6 +122,10 @@ TRACE_EVENT(kvm_msi_set_irq,
 	{KVM_IRQCHIP_PIC_SLAVE,		"PIC slave"},		\
 	{KVM_IRQCHIP_IOAPIC,		"IOAPIC"}
 
+#endif /* defined(__KVM_HAVE_IOAPIC) */
+
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+
 TRACE_EVENT(kvm_ack_irq,
 	TP_PROTO(unsigned int irqchip, unsigned int pin),
 	TP_ARGS(irqchip, pin),
@@ -136,14 +140,18 @@ TRACE_EVENT(kvm_ack_irq,
 		__entry->pin		= pin;
 	),
 
+#ifdef kvm_irqchips
 	TP_printk("irqchip %s pin %u",
 		  __print_symbolic(__entry->irqchip, kvm_irqchips),
 		 __entry->pin)
+#else
+	TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin)
+#endif
 );
 
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 
-#endif /* defined(__KVM_HAVE_IOAPIC) */
 
 #define KVM_TRACE_MMIO_READ_UNSATISFIED 0
 #define KVM_TRACE_MMIO_READ 1
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 3c56ba3d80c1..a5c86fc34a37 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -449,12 +449,15 @@ enum {
 	kvm_ioeventfd_flag_nr_datamatch,
 	kvm_ioeventfd_flag_nr_pio,
 	kvm_ioeventfd_flag_nr_deassign,
+	kvm_ioeventfd_flag_nr_virtio_ccw_notify,
 	kvm_ioeventfd_flag_nr_max,
 };
 
 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
 #define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
 #define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+	(1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
 
 #define KVM_IOEVENTFD_VALID_FLAG_MASK  ((1 << kvm_ioeventfd_flag_nr_max) - 1)
 
@@ -558,9 +561,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_MP_STATE 14
 #define KVM_CAP_COALESCED_MMIO 15
 #define KVM_CAP_SYNC_MMU 16  /* Changes to host mmap are reflected in guest */
-#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
 #define KVM_CAP_DEVICE_ASSIGNMENT 17
-#endif
 #define KVM_CAP_IOMMU 18
 #ifdef __KVM_HAVE_MSI
 #define KVM_CAP_DEVICE_MSI 20
@@ -576,13 +577,9 @@ struct kvm_ppc_smmu_info {
 #ifdef __KVM_HAVE_PIT
 #define KVM_CAP_REINJECT_CONTROL 24
 #endif
-#ifdef __KVM_HAVE_IOAPIC
 #define KVM_CAP_IRQ_ROUTING 25
-#endif
 #define KVM_CAP_IRQ_INJECT_STATUS 26
-#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
 #define KVM_CAP_DEVICE_DEASSIGNMENT 27
-#endif
 #ifdef __KVM_HAVE_MSIX
 #define KVM_CAP_DEVICE_MSIX 28
 #endif
@@ -665,6 +662,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_EPR 86
 #define KVM_CAP_ARM_PSCI 87
 #define KVM_CAP_ARM_SET_DEVICE_ADDR 88
+#define KVM_CAP_DEVICE_CTRL 89
+#define KVM_CAP_IRQ_MPIC 90
+#define KVM_CAP_PPC_RTAS 91
+#define KVM_CAP_IRQ_XICS 92
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -818,6 +819,28 @@ struct kvm_arm_device_addr {
 };
 
 /*
+ * Device control API, available with KVM_CAP_DEVICE_CTRL
+ */
+#define KVM_CREATE_DEVICE_TEST		1
+
+struct kvm_create_device {
+	__u32	type;	/* in: KVM_DEV_TYPE_xxx */
+	__u32	fd;	/* out: device handle */
+	__u32	flags;	/* in: KVM_CREATE_DEVICE_xxx */
+};
+
+struct kvm_device_attr {
+	__u32	flags;		/* no flags currently defined */
+	__u32	group;		/* device-defined */
+	__u64	attr;		/* group-defined */
+	__u64	addr;		/* userspace address of attr data */
+};
+
+#define KVM_DEV_TYPE_FSL_MPIC_20	1
+#define KVM_DEV_TYPE_FSL_MPIC_42	2
+#define KVM_DEV_TYPE_XICS		3
+
+/*
  * ioctls for VM fds
  */
 #define KVM_SET_MEMORY_REGION     _IOW(KVMIO,  0x40, struct kvm_memory_region)
@@ -904,6 +927,16 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_HTAB_FD	  _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
 /* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */
 #define KVM_ARM_SET_DEVICE_ADDR	  _IOW(KVMIO,  0xab, struct kvm_arm_device_addr)
+/* Available with KVM_CAP_PPC_RTAS */
+#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO,  0xac, struct kvm_rtas_token_args)
+
+/* ioctl for vm fd */
+#define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
+
+/* ioctls for fds returned by KVM_CREATE_DEVICE */
+#define KVM_SET_DEVICE_ATTR	  _IOW(KVMIO,  0xe1, struct kvm_device_attr)
+#define KVM_GET_DEVICE_ATTR	  _IOW(KVMIO,  0xe2, struct kvm_device_attr)
+#define KVM_HAS_DEVICE_ATTR	  _IOW(KVMIO,  0xe3, struct kvm_device_attr)
 
 /*
  * ioctls for vcpu fds