Merge branch 'lsk/v3.14/topic/kvm' into lsk/lsk-with-kvm-v3.14

Conflicts:
	arch/arm64/include/asm/debug-monitors.h

8 files changed, 369 insertions, 96 deletions

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 6d9aeddc09bf..ad9db6045b2f 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -67,6 +67,10 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
+int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
+
 #else
 static inline int kvm_timer_hyp_init(void)
 {
@@ -84,6 +88,16 @@ static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {}
+
+static inline int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+	return 0;
+}
+
+static inline u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index f27000f55a83..2f2aac8448a4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -24,26 +24,26 @@
 #include <linux/irqreturn.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
-#include <linux/irqchip/arm-gic.h>
 
-#define VGIC_NR_IRQS		256
+#define VGIC_NR_IRQS_LEGACY	256
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_NR_SHARED_IRQS	(VGIC_NR_IRQS - VGIC_NR_PRIVATE_IRQS)
-#define VGIC_MAX_CPUS		KVM_MAX_VCPUS
-#define VGIC_MAX_LRS		(1 << 6)
+
+#define VGIC_V2_MAX_LRS		(1 << 6)
+#define VGIC_V3_MAX_LRS		16
+#define VGIC_MAX_IRQS		1024
 
 /* Sanity checks... */
-#if (VGIC_MAX_CPUS > 8)
+#if (KVM_MAX_VCPUS > 8)
 #error	Invalid number of CPU interfaces
 #endif
 
-#if (VGIC_NR_IRQS & 31)
+#if (VGIC_NR_IRQS_LEGACY & 31)
 #error "VGIC_NR_IRQS must be a multiple of 32"
 #endif
 
-#if (VGIC_NR_IRQS > 1024)
+#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
 #error "VGIC_NR_IRQS must be <= 1024"
 #endif
 
@@ -53,26 +53,96 @@
  * - a bunch of shared interrupts (SPI)
  */
 struct vgic_bitmap {
-	union {
-		u32 reg[VGIC_NR_PRIVATE_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_PRIVATE_IRQS);
-	} percpu[VGIC_MAX_CPUS];
-	union {
-		u32 reg[VGIC_NR_SHARED_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_SHARED_IRQS);
-	} shared;
+	/*
+	 * - One UL per VCPU for private interrupts (assumes UL is at
+	 *   least 32 bits)
+	 * - As many UL as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, one UL per vcpu (the state for vcpu n is in
+	 * private[n]). The shared interrupts are accessed via the
+	 * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
+	 */
+	unsigned long *private;
+	unsigned long *shared;
 };
 
 struct vgic_bytemap {
-	u32 percpu[VGIC_MAX_CPUS][VGIC_NR_PRIVATE_IRQS / 4];
-	u32 shared[VGIC_NR_SHARED_IRQS  / 4];
+	/*
+	 * - 8 u32 per VCPU for private interrupts
+	 * - As many u32 as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, (the state for vcpu n is in private[n*8] to
+	 * private[n*8 + 7]). The shared interrupts are accessed via
+	 * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
+	 * shared[(n-32)/4] word).
+	 */
+	u32 *private;
+	u32 *shared;
+};
+
+struct kvm_vcpu;
+
+enum vgic_type {
+	VGIC_V2,		/* Good ol' GICv2 */
+	VGIC_V3,		/* New fancy GICv3 */
+};
+
+#define LR_STATE_PENDING	(1 << 0)
+#define LR_STATE_ACTIVE		(1 << 1)
+#define LR_STATE_MASK		(3 << 0)
+#define LR_EOI_INT		(1 << 2)
+
+struct vgic_lr {
+	u16	irq;
+	u8	source;
+	u8	state;
+};
+
+struct vgic_vmcr {
+	u32	ctlr;
+	u32	abpr;
+	u32	bpr;
+	u32	pmr;
+};
+
+struct vgic_ops {
+	struct vgic_lr	(*get_lr)(const struct kvm_vcpu *, int);
+	void	(*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
+	void	(*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
+	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
+	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
+	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
+	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
+	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
+	void	(*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+	void	(*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+	void	(*enable)(struct kvm_vcpu *vcpu);
+};
+
+struct vgic_params {
+	/* vgic type */
+	enum vgic_type	type;
+	/* Physical address of vgic virtual cpu interface */
+	phys_addr_t	vcpu_base;
+	/* Number of list registers */
+	u32		nr_lr;
+	/* Interrupt number */
+	unsigned int	maint_irq;
+	/* Virtual control interface base address */
+	void __iomem	*vctrl_base;
 };
 
 struct vgic_dist {
 #ifdef CONFIG_KVM_ARM_VGIC
 	spinlock_t		lock;
+	bool			in_kernel;
 	bool			ready;
 
+	int			nr_cpus;
+	int			nr_irqs;
+
 	/* Virtual control interface mapping */
 	void __iomem		*vctrl_base;
 
@@ -86,11 +156,25 @@ struct vgic_dist {
 	/* Interrupt enabled (one bit per IRQ) */
 	struct vgic_bitmap	irq_enabled;
 
-	/* Interrupt 'pin' level */
-	struct vgic_bitmap	irq_state;
+	/* Level-triggered interrupt external input is asserted */
+	struct vgic_bitmap	irq_level;
+
+	/*
+	 * Interrupt state is pending on the distributor
+	 */
+	struct vgic_bitmap	irq_pending;
 
-	/* Level-triggered interrupt in progress */
-	struct vgic_bitmap	irq_active;
+	/*
+	 * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
+	 * interrupts.  Essentially holds the state of the flip-flop in
+	 * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
+	 * Once set, it is only cleared for level-triggered interrupts on
+	 * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
+	 */
+	struct vgic_bitmap	irq_soft_pend;
+
+	/* Level-triggered interrupt queued on VCPU interface */
+	struct vgic_bitmap	irq_queued;
 
 	/* Interrupt priority. Not used yet. */
 	struct vgic_bytemap	irq_priority;
@@ -98,46 +182,90 @@ struct vgic_dist {
 	/* Level/edge triggered */
 	struct vgic_bitmap	irq_cfg;
 
-	/* Source CPU per SGI and target CPU */
-	u8			irq_sgi_sources[VGIC_MAX_CPUS][VGIC_NR_SGIS];
-
-	/* Target CPU for each IRQ */
-	u8			irq_spi_cpu[VGIC_NR_SHARED_IRQS];
-	struct vgic_bitmap	irq_spi_target[VGIC_MAX_CPUS];
+	/*
+	 * Source CPU per SGI and target CPU:
+	 *
+	 * Each byte represent a SGI observable on a VCPU, each bit of
+	 * this byte indicating if the corresponding VCPU has
+	 * generated this interrupt. This is a GICv2 feature only.
+	 *
+	 * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
+	 * the SGIs observable on VCPUn.
+	 */
+	u8			*irq_sgi_sources;
+
+	/*
+	 * Target CPU for each SPI:
+	 *
+	 * Array of available SPI, each byte indicating the target
+	 * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
+	 */
+	u8			*irq_spi_cpu;
+
+	/*
+	 * Reverse lookup of irq_spi_cpu for faster compute pending:
+	 *
+	 * Array of bitmaps, one per VCPU, describing if IRQn is
+	 * routed to a particular VCPU.
+	 */
+	struct vgic_bitmap	*irq_spi_target;
 
 	/* Bitmap indicating which CPU has something pending */
-	unsigned long		irq_pending_on_cpu;
+	unsigned long		*irq_pending_on_cpu;
+#endif
+};
+
+struct vgic_v2_cpu_if {
+	u32		vgic_hcr;
+	u32		vgic_vmcr;
+	u32		vgic_misr;	/* Saved only */
+	u32		vgic_eisr[2];	/* Saved only */
+	u32		vgic_elrsr[2];	/* Saved only */
+	u32		vgic_apr;
+	u32		vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_ARM_GIC_V3
+	u32		vgic_hcr;
+	u32		vgic_vmcr;
+	u32		vgic_misr;	/* Saved only */
+	u32		vgic_eisr;	/* Saved only */
+	u32		vgic_elrsr;	/* Saved only */
+	u32		vgic_ap0r[4];
+	u32		vgic_ap1r[4];
+	u64		vgic_lr[VGIC_V3_MAX_LRS];
 #endif
 };
 
 struct vgic_cpu {
 #ifdef CONFIG_KVM_ARM_VGIC
 	/* per IRQ to LR mapping */
-	u8		vgic_irq_lr_map[VGIC_NR_IRQS];
+	u8		*vgic_irq_lr_map;
 
 	/* Pending interrupts on this VCPU */
 	DECLARE_BITMAP(	pending_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(	pending_shared, VGIC_NR_SHARED_IRQS);
+	unsigned long	*pending_shared;
 
 	/* Bitmap of used/free list registers */
-	DECLARE_BITMAP(	lr_used, VGIC_MAX_LRS);
+	DECLARE_BITMAP(	lr_used, VGIC_V2_MAX_LRS);
 
 	/* Number of list registers on this CPU */
 	int		nr_lr;
 
 	/* CPU vif control registers for world switch */
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr[2];	/* Saved only */
-	u32		vgic_elrsr[2];	/* Saved only */
-	u32		vgic_apr;
-	u32		vgic_lr[VGIC_MAX_LRS];
+	union {
+		struct vgic_v2_cpu_if	vgic_v2;
+		struct vgic_v3_cpu_if	vgic_v3;
+	};
 #endif
 };
 
 #define LR_EMPTY	0xff
 
+#define INT_STATUS_EOI		(1 << 0)
+#define INT_STATUS_UNDERFLOW	(1 << 1)
+
 struct kvm;
 struct kvm_vcpu;
 struct kvm_run;
@@ -148,7 +276,8 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
@@ -157,9 +286,25 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		      struct kvm_exit_mmio *mmio);
 
-#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.vctrl_base))
+#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	((k)->arch.vgic.ready)
 
+int vgic_v2_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params);
+#ifdef CONFIG_ARM_GIC_V3
+int vgic_v3_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params);
+#else
+static inline int vgic_v3_probe(struct device_node *vgic_node,
+				const struct vgic_ops **ops,
+				const struct vgic_params **params)
+{
+	return -ENODEV;
+}
+#endif
+
 #else
 static inline int kvm_vgic_hyp_init(void)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b8e9a43e501a..55d75a7cba73 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -138,8 +138,6 @@ static inline bool is_error_page(struct page *page)
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
-struct kvm;
-struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
 extern spinlock_t kvm_lock;
@@ -192,7 +190,7 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 		       struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
@@ -313,25 +311,6 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-
-struct kvm_irq_routing_table {
-	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
-	struct kvm_kernel_irq_routing_entry *rt_entries;
-	u32 nr_rt_entries;
-	/*
-	 * Array indexed by gsi. Each entry contains list of irq chips
-	 * the gsi is connected to.
-	 */
-	struct hlist_head map[0];
-};
-
-#else
-
-struct kvm_irq_routing_table {};
-
-#endif
-
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
@@ -358,6 +337,7 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots;
 	struct srcu_struct srcu;
+	struct srcu_struct irq_srcu;
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	u32 bsp_vcpu_id;
 #endif
@@ -388,11 +368,12 @@ struct kvm {
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	/*
-	 * Update side is protected by irq_lock and,
-	 * if configured, irqfds.lock.
+	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
 	struct hlist_head mask_notifier_list;
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
@@ -442,7 +423,7 @@ 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
+#ifdef CONFIG_HAVE_KVM_IRQFD
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -531,6 +512,8 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
+				      bool *writable);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
@@ -589,7 +572,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
 int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
-int kvm_dev_ioctl_check_extension(long ext);
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 
 int kvm_get_dirty_log(struct kvm *kvm,
 			struct kvm_dirty_log *log, int *is_dirty);
@@ -627,6 +610,8 @@ void kvm_arch_exit(void);
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
+
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
@@ -635,8 +620,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
@@ -739,6 +724,10 @@ 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);
 
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
+
 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);
@@ -868,6 +857,13 @@ static inline hpa_t pfn_to_hpa(pfn_t pfn)
 	return (hpa_t)pfn << PAGE_SHIFT;
 }
 
+static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+{
+	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	return kvm_is_error_hva(hva);
+}
+
 static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
 	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
@@ -918,28 +914,27 @@ 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,
+int kvm_set_routing_entry(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);
-
 #else
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 #endif
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef CONFIG_HAVE_KVM_IRQFD
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
-void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
+void kvm_irq_routing_update(struct kvm *);
 #else
 static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
@@ -961,10 +956,8 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 static inline void kvm_irqfd_release(struct kvm *kvm) {}
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm,
-					  struct kvm_irq_routing_table *irq_rt)
+static inline void kvm_irq_routing_update(struct kvm *kvm)
 {
-	rcu_assign_pointer(kvm->irq_routing, irq_rt);
 }
 #endif
 
@@ -1025,8 +1018,6 @@ 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;
@@ -1059,11 +1050,11 @@ struct kvm_device_ops {
 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);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b0bcce0ddc95..b606bb689a3e 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -17,6 +17,20 @@
 #ifndef __KVM_TYPES_H__
 #define __KVM_TYPES_H__
 
+struct kvm;
+struct kvm_async_pf;
+struct kvm_device_ops;
+struct kvm_interrupt;
+struct kvm_irq_routing_table;
+struct kvm_memory_slot;
+struct kvm_one_reg;
+struct kvm_run;
+struct kvm_userspace_memory_region;
+struct kvm_vcpu;
+struct kvm_vcpu_init;
+
+enum kvm_mr_change;
+
 #include <asm/types.h>
 
 /*
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 131a0bda7aec..908925ace776 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(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -57,7 +57,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -124,7 +124,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
 
 TRACE_EVENT(kvm_ack_irq,
 	TP_PROTO(unsigned int irqchip, unsigned int pin),
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_ack_irq,
 #endif
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
 
 
 
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 3ce25b5d75a9..3da5dfed2629 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -316,6 +316,7 @@ header-y += ppp-ioctl.h
 header-y += ppp_defs.h
 header-y += pps.h
 header-y += prctl.h
+header-y += psci.h
 header-y += ptp_clock.h
 header-y += ptrace.h
 header-y += qnx4_fs.h
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 932d7f2637d6..cbc65ee211a4 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -171,6 +171,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_WATCHDOG         21
 #define KVM_EXIT_S390_TSCH        22
 #define KVM_EXIT_EPR              23
+#define KVM_EXIT_SYSTEM_EVENT     24
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -301,6 +302,13 @@ struct kvm_run {
 		struct {
 			__u32 epr;
 		} epr;
+		/* KVM_EXIT_SYSTEM_EVENT */
+		struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+			__u32 type;
+			__u64 flags;
+		} system_event;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -391,8 +399,9 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
-/* for KVM_SET_MPSTATE */
+/* for KVM_SET_MP_STATE */
 
+/* not all states are valid on all architectures */
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
 #define KVM_MP_STATE_INIT_RECEIVED     2
@@ -573,9 +582,7 @@ struct kvm_ppc_smmu_info {
 #endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
-#ifdef __KVM_HAVE_USER_NMI
 #define KVM_CAP_USER_NMI 22
-#endif
 #ifdef __KVM_HAVE_GUEST_DEBUG
 #define KVM_CAP_SET_GUEST_DEBUG 23
 #endif
@@ -657,9 +664,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
-#ifdef __KVM_HAVE_READONLY_MEM
 #define KVM_CAP_READONLY_MEM 81
-#endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
@@ -675,6 +680,8 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_SPAPR_MULTITCE 94
 #define KVM_CAP_EXT_EMUL_CPUID 95
 #define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_CHECK_EXTENSION_VM 105
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -847,14 +854,25 @@ struct kvm_device_attr {
 	__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
-#define KVM_DEV_TYPE_VFIO		4
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
-#define KVM_DEV_TYPE_ARM_VGIC_V2	5
+
+enum kvm_device_type {
+	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20	KVM_DEV_TYPE_FSL_MPIC_20
+	KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42	KVM_DEV_TYPE_FSL_MPIC_42
+	KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS		KVM_DEV_TYPE_XICS
+	KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO		KVM_DEV_TYPE_VFIO
+	KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
+	KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_MAX,
+};
 
 /*
  * ioctls for VM fds
@@ -992,7 +1010,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_INITIAL_RESET    _IO(KVMIO,   0x97)
 #define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
-/* Available with KVM_CAP_NMI */
+/* Available with KVM_CAP_USER_NMI */
 #define KVM_NMI                   _IO(KVMIO,   0x9a)
 /* Available with KVM_CAP_SET_GUEST_DEBUG */
 #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
new file mode 100644
index 000000000000..310d83e0a91b
--- /dev/null
+++ b/include/uapi/linux/psci.h
@@ -0,0 +1,90 @@
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <anup.patel@linaro.org>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE			0x84000000
+#define PSCI_0_2_FN(n)				(PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT				0x40000000
+#define PSCI_0_2_FN64_BASE			\
+					(PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n)			(PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION		PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND			PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF			PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON			PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO		PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE			PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE		PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU		PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF			PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET		PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND		PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON			PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO		PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE			PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT		0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT		16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK		\
+				(0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT		24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK		\
+				(0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON		0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF		1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING	2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE			0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE		1
+#define PSCI_0_2_TOS_MP				2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT		16
+#define PSCI_VERSION_MINOR_MASK			\
+		((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK			~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver)			\
+		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver)			\
+		((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS			0
+#define PSCI_RET_NOT_SUPPORTED			-1
+#define PSCI_RET_INVALID_PARAMS			-2
+#define PSCI_RET_DENIED				-3
+#define PSCI_RET_ALREADY_ON			-4
+#define PSCI_RET_ON_PENDING			-5
+#define PSCI_RET_INTERNAL_FAILURE		-6
+#define PSCI_RET_NOT_PRESENT			-7
+#define PSCI_RET_DISABLED			-8
+
+#endif /* _UAPI_LINUX_PSCI_H */