Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "Considerable KVM/PPC work, x86 kvmclock vsyscall support,
  IA32_TSC_ADJUST MSR emulation, amongst others."

Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.

* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
  KVM: emulator: fix real mode segment checks in address linearization
  VMX: remove unneeded enable_unrestricted_guest check
  KVM: VMX: fix DPL during entry to protected mode
  x86/kexec: crash_vmclear_local_vmcss needs __rcu
  kvm: Fix irqfd resampler list walk
  KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
  x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
  KVM: MMU: optimize for set_spte
  KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
  KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
  KVM: PPC: bookehv: Add guest computation mode for irq delivery
  KVM: PPC: Make EPCR a valid field for booke64 and bookehv
  KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
  KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
  KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
  KVM: PPC: e500: Add emulation helper for getting instruction ea
  KVM: PPC: bookehv64: Add support for interrupt handling
  KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
  KVM: PPC: booke: Fix get_tb() compile error on 64-bit
  KVM: PPC: e500: Silence bogus GCC warning in tlb code
  ...

4 files changed, 73 insertions, 18 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d5cddd8dcc5..2c497ab0d03 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -47,28 +47,40 @@
 
 /*
  * For the normal pfn, the highest 12 bits should be zero,
- * so we can mask these bits to indicate the error.
+ * so we can mask bit 62 ~ bit 52  to indicate the error pfn,
+ * mask bit 63 to indicate the noslot pfn.
  */
-#define KVM_PFN_ERR_MASK	(0xfffULL << 52)
+#define KVM_PFN_ERR_MASK	(0x7ffULL << 52)
+#define KVM_PFN_ERR_NOSLOT_MASK	(0xfffULL << 52)
+#define KVM_PFN_NOSLOT		(0x1ULL << 63)
 
 #define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
 #define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
-#define KVM_PFN_ERR_BAD		(KVM_PFN_ERR_MASK + 2)
-#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)
 
+/*
+ * error pfns indicate that the gfn is in slot but faild to
+ * translate it to pfn on host.
+ */
 static inline bool is_error_pfn(pfn_t pfn)
 {
 	return !!(pfn & KVM_PFN_ERR_MASK);
 }
 
-static inline bool is_noslot_pfn(pfn_t pfn)
+/*
+ * error_noslot pfns indicate that the gfn can not be
+ * translated to pfn - it is not in slot or failed to
+ * translate it to pfn.
+ */
+static inline bool is_error_noslot_pfn(pfn_t pfn)
 {
-	return pfn == KVM_PFN_ERR_BAD;
+	return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
 }
 
-static inline bool is_invalid_pfn(pfn_t pfn)
+/* noslot pfn indicates that the gfn is not in slot. */
+static inline bool is_noslot_pfn(pfn_t pfn)
 {
-	return !is_noslot_pfn(pfn) && is_error_pfn(pfn);
+	return pfn == KVM_PFN_NOSLOT;
 }
 
 #define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
@@ -107,6 +119,9 @@ static inline bool is_error_page(struct page *page)
 #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_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -516,6 +531,7 @@ 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);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -569,9 +585,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
 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_vcpu_reset(struct kvm_vcpu *vcpu);
 int kvm_arch_hardware_enable(void *garbage);
 void kvm_arch_hardware_disable(void *garbage);
 int kvm_arch_hardware_setup(void);
@@ -666,6 +682,7 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
 				   unsigned long *deliver_bitmask);
 #endif
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+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);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
@@ -838,9 +855,9 @@ extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
+static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(kvm->mmu_notifier_count))
 		return 1;
 	/*
 	 * Ensure the read of mmu_notifier_count happens before the read
@@ -853,7 +870,7 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 	 * can't rely on kvm->mmu_lock to keep things ordered.
 	 */
 	smp_rmb();
-	if (vcpu->kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_notifier_seq != mmu_seq)
 		return 1;
 	return 0;
 }
@@ -881,10 +898,20 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 #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
 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 *);
-int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+#else
+static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	return -EINVAL;
+}
+
+static inline void kvm_irqfd_release(struct kvm *kvm) {}
+#endif
 
 #else
 
diff --git a/include/linux/pvclock_gtod.h b/include/linux/pvclock_gtod.h
new file mode 100644
index 00000000000..0ca75825b60
--- /dev/null
+++ b/include/linux/pvclock_gtod.h
@@ -0,0 +1,9 @@
+#ifndef _PVCLOCK_GTOD_H
+#define _PVCLOCK_GTOD_H
+
+#include <linux/notifier.h>
+
+extern int pvclock_gtod_register_notifier(struct notifier_block *nb);
+extern int pvclock_gtod_unregister_notifier(struct notifier_block *nb);
+
+#endif /* _PVCLOCK_GTOD_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 651b51a3671..2c2f3072bee 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -107,6 +107,14 @@ extern unsigned long this_cpu_load(void);
 extern void calc_global_load(unsigned long ticks);
 extern void update_cpu_load_nohz(void);
 
+/* Notifier for when a task gets migrated to a new CPU */
+struct task_migration_notifier {
+	struct task_struct *task;
+	int from_cpu;
+	int to_cpu;
+};
+extern void register_task_migration_notifier(struct notifier_block *n);
+
 extern unsigned long get_parent_ip(unsigned long addr);
 
 extern void dump_cpu_task(int cpu);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 0a6d6ba44c8..e6e5d4b1370 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -167,10 +167,15 @@ struct kvm_pit_config {
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
 #define KVM_EXIT_S390_UCONTROL	  20
+#define KVM_EXIT_WATCHDOG         21
 
 /* For KVM_EXIT_INTERNAL_ERROR */
-#define KVM_INTERNAL_ERROR_EMULATION 1
-#define KVM_INTERNAL_ERROR_SIMUL_EX 2
+/* Emulate instruction failed. */
+#define KVM_INTERNAL_ERROR_EMULATION	1
+/* Encounter unexpected simultaneous exceptions. */
+#define KVM_INTERNAL_ERROR_SIMUL_EX	2
+/* Encounter unexpected vm-exit due to delivery event. */
+#define KVM_INTERNAL_ERROR_DELIVERY_EV	3
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -477,6 +482,8 @@ struct kvm_ppc_smmu_info {
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -626,6 +633,8 @@ struct kvm_ppc_smmu_info {
 #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
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -848,6 +857,11 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 /* Available with KVM_CAP_PPC_ALLOC_HTAB */
 #define KVM_PPC_ALLOCATE_HTAB	  _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD	  _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
 
 /*
  * ioctls for vcpu fds
@@ -911,9 +925,6 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_XCRS */
 #define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
 #define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)
-#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
-/* Available with KVM_CAP_RMA */
-#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 /* Available with KVM_CAP_SW_TLB */
 #define KVM_DIRTY_TLB		  _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
 /* Available with KVM_CAP_ONE_REG */