Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

3 files changed, 110 insertions, 9 deletions

diff --git a/include/asm-generic/kvm_para.h b/include/asm-generic/kvm_para.h
new file mode 100644
index 000000000000..5cba37f9eae1
--- /dev/null
+++ b/include/asm-generic/kvm_para.h
@@ -0,0 +1,22 @@
+#ifndef _ASM_GENERIC_KVM_PARA_H
+#define _ASM_GENERIC_KVM_PARA_H
+
+#ifdef __KERNEL__
+
+/*
+ * This function is used by architectures that support kvm to avoid issuing
+ * false soft lockup messages.
+ */
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif	/* _KERNEL__ */
+
+#endif
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 6c322a90b92f..09f2b3aa2da7 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -449,6 +449,30 @@ struct kvm_ppc_pvinfo {
 	__u8  pad[108];
 };
 
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ	8
+
+struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL		0x00000001
+#define KVM_PPC_1T_SEGMENTS		0x00000002
+
+struct kvm_ppc_smmu_info {
+	__u64 flags;
+	__u32 slb_size;
+	__u32 pad;
+	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -589,6 +613,10 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_S390_UCONTROL 73
 #define KVM_CAP_SYNC_REGS 74
 #define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
+#define KVM_CAP_S390_COW 79
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -714,6 +742,14 @@ struct kvm_one_reg {
 	__u64 addr;
 };
 
+struct kvm_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 flags;
+	__u8  pad[16];
+};
+
 /*
  * ioctls for VM fds
  */
@@ -788,6 +824,10 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_PCI_2_3 */
 #define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
 				       struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 
 /*
  * ioctls for vcpu fds
@@ -859,6 +899,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_ONE_REG */
 #define KVM_GET_ONE_REG		  _IOW(KVMIO,  0xab, struct kvm_one_reg)
 #define KVM_SET_ONE_REG		  _IOW(KVMIO,  0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL	  _IO(KVMIO,   0xad)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 72cbf08d45fb..c4464356b35b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -35,6 +35,20 @@
 #endif
 
 /*
+ * If we support unaligned MMIO, at most one fragment will be split into two:
+ */
+#ifdef KVM_UNALIGNED_MMIO
+#  define KVM_EXTRA_MMIO_FRAGMENTS 1
+#else
+#  define KVM_EXTRA_MMIO_FRAGMENTS 0
+#endif
+
+#define KVM_USER_MMIO_SIZE 8
+
+#define KVM_MAX_MMIO_FRAGMENTS \
+	(KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
+
+/*
  * vcpu->requests bit members
  */
 #define KVM_REQ_TLB_FLUSH          0
@@ -68,10 +82,11 @@ struct kvm_io_range {
 	struct kvm_io_device *dev;
 };
 
+#define NR_IOBUS_DEVS 1000
+
 struct kvm_io_bus {
 	int                   dev_count;
-#define NR_IOBUS_DEVS 300
-	struct kvm_io_range range[NR_IOBUS_DEVS];
+	struct kvm_io_range range[];
 };
 
 enum kvm_bus {
@@ -113,7 +128,18 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 enum {
 	OUTSIDE_GUEST_MODE,
 	IN_GUEST_MODE,
-	EXITING_GUEST_MODE
+	EXITING_GUEST_MODE,
+	READING_SHADOW_PAGE_TABLES,
+};
+
+/*
+ * Sometimes a large or cross-page mmio needs to be broken up into separate
+ * exits for userspace servicing.
+ */
+struct kvm_mmio_fragment {
+	gpa_t gpa;
+	void *data;
+	unsigned len;
 };
 
 struct kvm_vcpu {
@@ -143,10 +169,9 @@ struct kvm_vcpu {
 	int mmio_needed;
 	int mmio_read_completed;
 	int mmio_is_write;
-	int mmio_size;
-	int mmio_index;
-	unsigned char mmio_data[KVM_MMIO_SIZE];
-	gpa_t mmio_phys_addr;
+	int mmio_cur_fragment;
+	int mmio_nr_fragments;
+	struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
 #endif
 
 #ifdef CONFIG_KVM_ASYNC_PF
@@ -178,8 +203,6 @@ struct kvm_memory_slot {
 	unsigned long flags;
 	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
-	unsigned long *dirty_bitmap_head;
-	unsigned long nr_dirty_pages;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
 	int user_alloc;
@@ -438,6 +461,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			     gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
@@ -506,6 +531,7 @@ 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_vcpu_should_kick(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -521,6 +547,15 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
+static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+{
+#ifdef __KVM_HAVE_ARCH_WQP
+	return vcpu->arch.wqp;
+#else
+	return &vcpu->wq;
+#endif
+}
+
 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);
@@ -769,6 +804,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			unsigned flags);
 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) {}