Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Paolo Bonzini:
 "Here are the 3.13 KVM changes.  There was a lot of work on the PPC
  side: the HV and emulation flavors can now coexist in a single kernel
  is probably the most interesting change from a user point of view.

  On the x86 side there are nested virtualization improvements and a few
  bugfixes.

  ARM got transparent huge page support, improved overcommit, and
  support for big endian guests.

  Finally, there is a new interface to connect KVM with VFIO.  This
  helps with devices that use NoSnoop PCI transactions, letting the
  driver in the guest execute WBINVD instructions.  This includes some
  nVidia cards on Windows, that fail to start without these patches and
  the corresponding userspace changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  kvm, vmx: Fix lazy FPU on nested guest
  arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu
  arm/arm64: KVM: MMIO support for BE guest
  kvm, cpuid: Fix sparse warning
  kvm: Delete prototype for non-existent function kvm_check_iopl
  kvm: Delete prototype for non-existent function complete_pio
  hung_task: add method to reset detector
  pvclock: detect watchdog reset at pvclock read
  kvm: optimize out smp_mb after srcu_read_unlock
  srcu: API for barrier after srcu read unlock
  KVM: remove vm mmap method
  KVM: IOMMU: hva align mapping page size
  KVM: x86: trace cpuid emulation when called from emulator
  KVM: emulator: cleanup decode_register_operand() a bit
  KVM: emulator: check rex prefix inside decode_register()
  KVM: x86: fix emulation of "movzbl %bpl, %eax"
  kvm_host: typo fix
  KVM: x86: emulate SAHF instruction
  MAINTAINERS: add tree for kvm.git
  Documentation/kvm: add a 00-INDEX file
  ...

5 files changed, 63 insertions, 22 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0fbbc7aa02c..9523d2ad753 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -142,7 +142,7 @@ struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
-extern raw_spinlock_t kvm_lock;
+extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_io_range {
@@ -189,8 +189,7 @@ struct kvm_async_pf {
 	gva_t gva;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
-	struct page *page;
-	bool done;
+	bool   wakeup_all;
 };
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
@@ -508,9 +507,10 @@ int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, 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_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages);
 void kvm_arch_memslots_updated(struct kvm *kvm);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
@@ -671,6 +671,25 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
+#ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
+void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
+void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
+bool kvm_arch_has_noncoherent_dma(struct kvm *kvm);
+#else
+static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
+{
+}
+
+static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
+{
+}
+
+static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
@@ -747,9 +766,6 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 int kvm_request_irq_source_id(struct kvm *kvm);
 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_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);
@@ -789,7 +805,7 @@ static inline void kvm_guest_enter(void)
 
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
-	 * is very similar to exiting to userspase from rcu point of view. In
+	 * is very similar to exiting to userspace from rcu point of view. In
 	 * addition CPU may stay in a guest mode for quite a long time (up to
 	 * one time slice). Lets treat guest mode as quiescent state, just like
 	 * we do with user-mode execution.
@@ -842,13 +858,6 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return gfn_to_memslot(kvm, gfn)->id;
 }
 
-static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
-{
-	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
-	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
-		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
-}
-
 static inline gfn_t
 hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
 {
@@ -1066,6 +1075,7 @@ 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;
+extern struct kvm_device_ops kvm_vfio_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f7efc860465..6f7ffa46008 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -286,6 +286,14 @@ static inline void lockup_detector_init(void)
 }
 #endif
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+void reset_hung_task_detector(void);
+#else
+static inline void reset_hung_task_detector(void)
+{
+}
+#endif
+
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched		__attribute__((__section__(".sched.text")))
 
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c114614ed17..9b058eecd40 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -237,4 +237,18 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__srcu_read_unlock(sp, idx);
 }
 
+/**
+ * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
+ *
+ * Converts the preceding srcu_read_unlock into a two-way memory barrier.
+ *
+ * Call this after srcu_read_unlock, to guarantee that all memory operations
+ * that occur after smp_mb__after_srcu_read_unlock will appear to happen after
+ * the preceding srcu_read_unlock.
+ */
+static inline void smp_mb__after_srcu_read_unlock(void)
+{
+	/* __srcu_read_unlock has smp_mb() internally so nothing to do here. */
+}
+
 #endif
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 7005d1109ec..131a0bda7ae 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -296,23 +296,21 @@ DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready,
 
 TRACE_EVENT(
 	kvm_async_pf_completed,
-	TP_PROTO(unsigned long address, struct page *page, u64 gva),
-	TP_ARGS(address, page, gva),
+	TP_PROTO(unsigned long address, u64 gva),
+	TP_ARGS(address, gva),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, address)
-		__field(pfn_t, pfn)
 		__field(u64, gva)
 		),
 
 	TP_fast_assign(
 		__entry->address = address;
-		__entry->pfn = page ? page_to_pfn(page) : 0;
 		__entry->gva = gva;
 		),
 
-	TP_printk("gva %#llx address %#lx pfn %#llx",  __entry->gva,
-		  __entry->address, __entry->pfn)
+	TP_printk("gva %#llx address %#lx",  __entry->gva,
+		  __entry->address)
 );
 
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 99c25338ede..902f1246187 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -518,6 +518,10 @@ struct kvm_ppc_smmu_info {
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
 #define KVM_VM_S390_UCONTROL	1
 
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
 /*
@@ -541,6 +545,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 
 /*
  * Extension capability list.
@@ -668,6 +673,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQ_XICS 92
 #define KVM_CAP_ARM_EL1_32BIT 93
 #define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -843,6 +849,10 @@ struct kvm_device_attr {
 #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
 
 /*
  * ioctls for VM fds
@@ -1012,6 +1022,7 @@ struct kvm_s390_ucas_mapping {
 /* VM is being stopped by host */
 #define KVM_KVMCLOCK_CTRL	  _IO(KVMIO,   0xad)
 #define KVM_ARM_VCPU_INIT	  _IOW(KVMIO,  0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET  _IOR(KVMIO,  0xaf, struct kvm_vcpu_init)
 #define KVM_GET_REG_LIST	  _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)