Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
  MAINTAINERS: update KVM entry
  KVM: correct error-handling code
  KVM: fix compile warnings on s390
  KVM: VMX: Check cpl before emulating debug register access
  KVM: fix misreporting of coalesced interrupts by kvm tracer
  KVM: x86: drop duplicate kvm_flush_remote_tlb calls
  KVM: VMX: call vmx_load_host_state() only if msr is cached
  KVM: VMX: Conditionally reload debug register 6
  KVM: Use thread debug register storage instead of kvm specific data
  KVM guest: do not batch pte updates from interrupt context
  KVM: Fix coalesced interrupt reporting in IOAPIC
  KVM guest: fix bogus wallclock physical address calculation
  KVM: VMX: Fix cr8 exiting control clobbering by EPT
  KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
  KVM: Document KVM_CAP_IRQCHIP
  KVM: Protect update_cr8_intercept() when running without an apic
  KVM: VMX: Fix EPT with WP bit change during paging
  KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
  KVM: x86 emulator: Add adc and sbb missing decoder flags
  KVM: Add missing #include
  ...

4 files changed, 167 insertions, 79 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 334a3593cdf..cff4a101f26 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -268,6 +268,10 @@ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \
       		  $(srctree)/include/asm-$(SRCARCH)/kvm.h),)
 unifdef-y += kvm.h
 endif
+ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \
+		  $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),)
+unifdef-y += kvm_para.h
+endif
 unifdef-y += llc.h
 unifdef-y += loop.h
 unifdef-y += lp.h
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 3db5d8d3748..f8f8900fc5e 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -14,7 +14,7 @@
 
 #define KVM_API_VERSION 12
 
-/* for KVM_TRACE_ENABLE */
+/* for KVM_TRACE_ENABLE, deprecated */
 struct kvm_user_trace_setup {
 	__u32 buf_size; /* sub_buffer size of each per-cpu */
 	__u32 buf_nr; /* the number of sub_buffers of each per-cpu */
@@ -70,6 +70,14 @@ struct kvm_irqchip {
 	} chip;
 };
 
+/* for KVM_CREATE_PIT2 */
+struct kvm_pit_config {
+	__u32 flags;
+	__u32 pad[15];
+};
+
+#define KVM_PIT_SPEAKER_DUMMY     1
+
 #define KVM_EXIT_UNKNOWN          0
 #define KVM_EXIT_EXCEPTION        1
 #define KVM_EXIT_IO               2
@@ -87,6 +95,10 @@ struct kvm_irqchip {
 #define KVM_EXIT_S390_RESET       14
 #define KVM_EXIT_DCR              15
 #define KVM_EXIT_NMI              16
+#define KVM_EXIT_INTERNAL_ERROR   17
+
+/* For KVM_EXIT_INTERNAL_ERROR */
+#define KVM_INTERNAL_ERROR_EMULATION 1
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -173,6 +185,9 @@ struct kvm_run {
 			__u32 data;
 			__u8  is_write;
 		} dcr;
+		struct {
+			__u32 suberror;
+		} internal;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -292,6 +307,28 @@ struct kvm_guest_debug {
 	struct kvm_guest_debug_arch arch;
 };
 
+enum {
+	kvm_ioeventfd_flag_nr_datamatch,
+	kvm_ioeventfd_flag_nr_pio,
+	kvm_ioeventfd_flag_nr_deassign,
+	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_VALID_FLAG_MASK  ((1 << kvm_ioeventfd_flag_nr_max) - 1)
+
+struct kvm_ioeventfd {
+	__u64 datamatch;
+	__u64 addr;        /* legal pio/mmio address */
+	__u32 len;         /* 1, 2, 4, or 8 bytes    */
+	__s32 fd;
+	__u32 flags;
+	__u8  pad[36];
+};
+
 #define KVM_TRC_SHIFT           16
 /*
  * kvm trace categories
@@ -310,35 +347,6 @@ struct kvm_guest_debug {
 #define KVM_TRC_CYCLE_SIZE      8
 #define KVM_TRC_EXTRA_MAX       7
 
-/* This structure represents a single trace buffer record. */
-struct kvm_trace_rec {
-	/* variable rec_val
-	 * is split into:
-	 * bits 0 - 27  -> event id
-	 * bits 28 -30  -> number of extra data args of size u32
-	 * bits 31      -> binary indicator for if tsc is in record
-	 */
-	__u32 rec_val;
-	__u32 pid;
-	__u32 vcpu_id;
-	union {
-		struct {
-			__u64 timestamp;
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} __attribute__((packed)) timestamp;
-		struct {
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} notimestamp;
-	} u;
-};
-
-#define TRACE_REC_EVENT_ID(val) \
-		(0x0fffffff & (val))
-#define TRACE_REC_NUM_DATA_ARGS(val) \
-		(0x70000000 & ((val) << 28))
-#define TRACE_REC_TCS(val) \
-		(0x80000000 & ((val) << 31))
-
 #define KVMIO 0xAE
 
 /*
@@ -415,6 +423,19 @@ struct kvm_trace_rec {
 #define KVM_CAP_ASSIGN_DEV_IRQ 29
 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
+#ifdef __KVM_HAVE_MCE
+#define KVM_CAP_MCE 31
+#endif
+#define KVM_CAP_IRQFD 32
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_PIT2 33
+#endif
+#define KVM_CAP_SET_BOOT_CPU_ID 34
+#ifdef __KVM_HAVE_PIT_STATE2
+#define KVM_CAP_PIT_STATE2 35
+#endif
+#define KVM_CAP_IOEVENTFD 36
+#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -454,15 +475,32 @@ struct kvm_irq_routing {
 
 #endif
 
+#ifdef KVM_CAP_MCE
+/* x86 MCE */
+struct kvm_x86_mce {
+	__u64 status;
+	__u64 addr;
+	__u64 misc;
+	__u64 mcg_status;
+	__u8 bank;
+	__u8 pad1[7];
+	__u64 pad2[3];
+};
+#endif
+
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+
+struct kvm_irqfd {
+	__u32 fd;
+	__u32 gsi;
+	__u32 flags;
+	__u8  pad[20];
+};
+
 /*
  * ioctls for VM fds
  */
 #define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 0x40, struct kvm_memory_region)
-#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO, 0x44)
-#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO, 0x45)
-#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\
-					struct kvm_userspace_memory_region)
-#define KVM_SET_TSS_ADDR          _IO(KVMIO, 0x47)
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
@@ -470,6 +508,12 @@ struct kvm_irq_routing {
 #define KVM_CREATE_VCPU           _IO(KVMIO,  0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 0x42, struct kvm_dirty_log)
 #define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO, 0x43, struct kvm_memory_alias)
+#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO, 0x44)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO, 0x45)
+#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\
+					struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR          _IO(KVMIO, 0x47)
+#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64)
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP	  _IO(KVMIO,  0x60)
 #define KVM_IRQ_LINE		  _IOW(KVMIO, 0x61, struct kvm_irq_level)
@@ -498,6 +542,10 @@ struct kvm_irq_routing {
 #define KVM_ASSIGN_SET_MSIX_ENTRY \
 			_IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
 #define KVM_DEASSIGN_DEV_IRQ       _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
+#define KVM_IRQFD                  _IOW(KVMIO, 0x76, struct kvm_irqfd)
+#define KVM_CREATE_PIT2		   _IOW(KVMIO, 0x77, struct kvm_pit_config)
+#define KVM_SET_BOOT_CPU_ID        _IO(KVMIO, 0x78)
+#define KVM_IOEVENTFD             _IOW(KVMIO, 0x79, struct kvm_ioeventfd)
 
 /*
  * ioctls for vcpu fds
@@ -541,6 +589,10 @@ struct kvm_irq_routing {
 #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)
+/* MCE for x86 */
+#define KVM_X86_SETUP_MCE         _IOW(KVMIO,  0x9c, __u64)
+#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO,  0x9d, __u64)
+#define KVM_X86_SET_MCE           _IOW(KVMIO,  0x9e, struct kvm_x86_mce)
 
 /*
  * Deprecated interfaces
@@ -563,6 +615,9 @@ struct kvm_debug_guest {
 #define KVM_IA64_VCPU_GET_STACK   _IOR(KVMIO,  0x9a, void *)
 #define KVM_IA64_VCPU_SET_STACK   _IOW(KVMIO,  0x9b, void *)
 
+#define KVM_GET_PIT2   _IOR(KVMIO,   0x9f, struct kvm_pit_state2)
+#define KVM_SET_PIT2   _IOW(KVMIO,   0xa0, struct kvm_pit_state2)
+
 #define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
 #define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
 #define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
@@ -633,7 +688,7 @@ struct kvm_assigned_msix_nr {
 	__u16 padding;
 };
 
-#define KVM_MAX_MSIX_PER_DEV		512
+#define KVM_MAX_MSIX_PER_DEV		256
 struct kvm_assigned_msix_entry {
 	__u32 assigned_dev_id;
 	__u32 gsi;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3060bdc35ff..4af56036a6b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -42,6 +42,7 @@
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0
 
+struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
@@ -59,10 +60,18 @@ struct kvm_io_bus {
 
 void kvm_io_bus_init(struct kvm_io_bus *bus);
 void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
-					  gpa_t addr, int len, int is_write);
-void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
-			     struct kvm_io_device *dev);
+int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, int len,
+		     const void *val);
+int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len,
+		    void *val);
+int __kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+			       struct kvm_io_device *dev);
+int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus,
+			    struct kvm_io_device *dev);
+void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus,
+				 struct kvm_io_device *dev);
+void kvm_io_bus_unregister_dev(struct kvm *kvm, struct kvm_io_bus *bus,
+			       struct kvm_io_device *dev);
 
 struct kvm_vcpu {
 	struct kvm *kvm;
@@ -103,7 +112,7 @@ struct kvm_memory_slot {
 	struct {
 		unsigned long rmap_pde;
 		int write_count;
-	} *lpage_info;
+	} *lpage_info[KVM_NR_PAGE_SIZES - 1];
 	unsigned long userspace_addr;
 	int user_alloc;
 };
@@ -124,7 +133,6 @@ struct kvm_kernel_irq_routing_entry {
 };
 
 struct kvm {
-	struct mutex lock; /* protects the vcpus array and APIC accesses */
 	spinlock_t mmu_lock;
 	spinlock_t requests_lock;
 	struct rw_semaphore slots_lock;
@@ -132,10 +140,23 @@ struct kvm {
 	int nmemslots;
 	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
 					KVM_PRIVATE_MEM_SLOTS];
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+	u32 bsp_vcpu_id;
+	struct kvm_vcpu *bsp_vcpu;
+#endif
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+	atomic_t online_vcpus;
 	struct list_head vm_list;
+	struct mutex lock;
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
+#ifdef CONFIG_HAVE_KVM_EVENTFD
+	struct {
+		spinlock_t        lock;
+		struct list_head  items;
+	} irqfds;
+	struct list_head ioeventfds;
+#endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	atomic_t users_count;
@@ -144,6 +165,7 @@ struct kvm {
 	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
 #endif
 
+	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */
 	struct hlist_head mask_notifier_list;
@@ -167,6 +189,17 @@ struct kvm {
 #define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
 #define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)
 
+static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
+{
+	smp_rmb();
+	return kvm->vcpus[i];
+}
+
+#define kvm_for_each_vcpu(idx, vcpup, kvm) \
+	for (idx = 0, vcpup = kvm_get_vcpu(kvm, idx); \
+	     idx < atomic_read(&kvm->online_vcpus) && vcpup; \
+	     vcpup = kvm_get_vcpu(kvm, ++idx))
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 
@@ -201,6 +234,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
@@ -243,8 +277,6 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
-void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
-void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 
 int kvm_dev_ioctl_check_extension(long ext);
 
@@ -300,7 +332,6 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -309,8 +340,6 @@ 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_get_interrupt(struct kvm_vcpu *v);
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
@@ -366,7 +395,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian);
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				   struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
@@ -459,37 +489,6 @@ struct kvm_stats_debugfs_item {
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
-#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 5, d1, d2, d3, d4, d5)
-#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 4, d1, d2, d3, d4, 0)
-#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 3, d1, d2, d3, 0, 0)
-#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 2, d1, d2, 0, 0, 0)
-#define KVMTRACE_1D(evt, vcpu, d1, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 1, d1, 0, 0, 0, 0)
-#define KVMTRACE_0D(evt, vcpu, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 0, 0, 0, 0, 0, 0)
-
-#ifdef CONFIG_KVM_TRACE
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg);
-void kvm_trace_cleanup(void);
-#else
-static inline
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
-{
-	return -EINVAL;
-}
-#define kvm_trace_cleanup() ((void)0)
-#endif
-
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
 static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
 {
@@ -525,4 +524,33 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 #endif
 
+#ifdef CONFIG_HAVE_KVM_EVENTFD
+
+void kvm_eventfd_init(struct kvm *kvm);
+int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
+void kvm_irqfd_release(struct kvm *kvm);
+int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+
+#else
+
+static inline void kvm_eventfd_init(struct kvm *kvm) {}
+static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+{
+	return -EINVAL;
+}
+
+static inline void kvm_irqfd_release(struct kvm *kvm) {}
+static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	return -ENOSYS;
+}
+
+#endif /* CONFIG_HAVE_KVM_EVENTFD */
+
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
+}
+#endif
 #endif
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 3ddce03766c..d73109243fd 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -13,6 +13,7 @@
 #define KVM_ENOSYS		1000
 #define KVM_EFAULT		EFAULT
 #define KVM_E2BIG		E2BIG
+#define KVM_EPERM		EPERM
 
 #define KVM_HC_VAPIC_POLL_IRQ		1
 #define KVM_HC_MMU_OP			2