Merge branch 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Avi Kivity:
 "Changes include timekeeping improvements, support for assigning host
  PCI devices that share interrupt lines, s390 user-controlled guests, a
  large ppc update, and random fixes."

This is with the sign-off's fixed, hopefully next merge window we won't
have rebased commits.

* 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: Convert intx_mask_lock to spin lock
  KVM: x86: fix kvm_write_tsc() TSC matching thinko
  x86: kvmclock: abstract save/restore sched_clock_state
  KVM: nVMX: Fix erroneous exception bitmap check
  KVM: Ignore the writes to MSR_K7_HWCR(3)
  KVM: MMU: make use of ->root_level in reset_rsvds_bits_mask
  KVM: PMU: add proper support for fixed counter 2
  KVM: PMU: Fix raw event check
  KVM: PMU: warn when pin control is set in eventsel msr
  KVM: VMX: Fix delayed load of shared MSRs
  KVM: use correct tlbs dirty type in cmpxchg
  KVM: Allow host IRQ sharing for assigned PCI 2.3 devices
  KVM: Ensure all vcpus are consistent with in-kernel irqchip settings
  KVM: x86 emulator: Allow PM/VM86 switch during task switch
  KVM: SVM: Fix CPL updates
  KVM: x86 emulator: VM86 segments must have DPL 3
  KVM: x86 emulator: Fix task switch privilege checks
  arch/powerpc/kvm/book3s_hv.c: included linux/sched.h twice
  KVM: x86 emulator: correctly mask pmc index bits in RDPMC instruction emulation
  KVM: mmu_notifier: Flush TLBs before releasing mmu_lock
  ...

2 files changed, 155 insertions, 12 deletions

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 68e67e50d02..6c322a90b92 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -162,6 +162,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
+#define KVM_EXIT_S390_UCONTROL	  20
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -249,6 +250,11 @@ struct kvm_run {
 #define KVM_S390_RESET_CPU_INIT  8
 #define KVM_S390_RESET_IPL       16
 		__u64 s390_reset_flags;
+		/* KVM_EXIT_S390_UCONTROL */
+		struct {
+			__u64 trans_exc_code;
+			__u32 pgm_code;
+		} s390_ucontrol;
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
@@ -273,6 +279,20 @@ struct kvm_run {
 		/* Fix the size of the union. */
 		char padding[256];
 	};
+
+	/*
+	 * shared registers between kvm and userspace.
+	 * kvm_valid_regs specifies the register classes set by the host
+	 * kvm_dirty_regs specified the register classes dirtied by userspace
+	 * struct kvm_sync_regs is architecture specific, as well as the
+	 * bits for kvm_valid_regs and kvm_dirty_regs
+	 */
+	__u64 kvm_valid_regs;
+	__u64 kvm_dirty_regs;
+	union {
+		struct kvm_sync_regs regs;
+		char padding[1024];
+	} s;
 };
 
 /* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
@@ -431,6 +451,11 @@ struct kvm_ppc_pvinfo {
 
 #define KVMIO 0xAE
 
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL	1
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -555,9 +580,15 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_SMT 64
 #define KVM_CAP_PPC_RMA	65
 #define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
+#define KVM_CAP_PPC_HIOR 67
 #define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
+#define KVM_CAP_ONE_REG 70
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
+#define KVM_CAP_PCI_2_3 75
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -637,6 +668,52 @@ struct kvm_clock_data {
 	__u32 pad[9];
 };
 
+#define KVM_MMU_FSL_BOOKE_NOHV		0
+#define KVM_MMU_FSL_BOOKE_HV		1
+
+struct kvm_config_tlb {
+	__u64 params;
+	__u64 array;
+	__u32 mmu_type;
+	__u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+	__u64 bitmap;
+	__u32 num_dirty;
+};
+
+/* Available with KVM_CAP_ONE_REG */
+
+#define KVM_REG_ARCH_MASK	0xff00000000000000ULL
+#define KVM_REG_GENERIC		0x0000000000000000ULL
+
+/*
+ * Architecture specific registers are to be defined in arch headers and
+ * ORed with the arch identifier.
+ */
+#define KVM_REG_PPC		0x1000000000000000ULL
+#define KVM_REG_X86		0x2000000000000000ULL
+#define KVM_REG_IA64		0x3000000000000000ULL
+#define KVM_REG_ARM		0x4000000000000000ULL
+#define KVM_REG_S390		0x5000000000000000ULL
+
+#define KVM_REG_SIZE_SHIFT	52
+#define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
+#define KVM_REG_SIZE_U8		0x0000000000000000ULL
+#define KVM_REG_SIZE_U16	0x0010000000000000ULL
+#define KVM_REG_SIZE_U32	0x0020000000000000ULL
+#define KVM_REG_SIZE_U64	0x0030000000000000ULL
+#define KVM_REG_SIZE_U128	0x0040000000000000ULL
+#define KVM_REG_SIZE_U256	0x0050000000000000ULL
+#define KVM_REG_SIZE_U512	0x0060000000000000ULL
+#define KVM_REG_SIZE_U1024	0x0070000000000000ULL
+
+struct kvm_one_reg {
+	__u64 id;
+	__u64 addr;
+};
+
 /*
  * ioctls for VM fds
  */
@@ -655,6 +732,17 @@ struct kvm_clock_data {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+	__u64 user_addr;
+	__u64 vcpu_addr;
+	__u64 length;
+};
+#define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
+
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
 #define KVM_IRQ_LINE              _IOW(KVMIO,  0x61, struct kvm_irq_level)
@@ -697,6 +785,9 @@ struct kvm_clock_data {
 /* Available with KVM_CAP_TSC_CONTROL */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
+/* Available with KVM_CAP_PCI_2_3 */
+#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
+				       struct kvm_assigned_pci_dev)
 
 /*
  * ioctls for vcpu fds
@@ -763,8 +854,15 @@ struct kvm_clock_data {
 #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 */
+#define KVM_GET_ONE_REG		  _IOW(KVMIO,  0xab, struct kvm_one_reg)
+#define KVM_SET_ONE_REG		  _IOW(KVMIO,  0xac, struct kvm_one_reg)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+#define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
 
 struct kvm_assigned_pci_dev {
 	__u32 assigned_dev_id;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ca1b153585d..665a260c7e0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -172,11 +172,6 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
  */
 #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
 
-struct kvm_lpage_info {
-	unsigned long rmap_pde;
-	int write_count;
-};
-
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
@@ -185,7 +180,7 @@ struct kvm_memory_slot {
 	unsigned long *dirty_bitmap;
 	unsigned long *dirty_bitmap_head;
 	unsigned long nr_dirty_pages;
-	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
 	int user_alloc;
 	int id;
@@ -377,6 +372,9 @@ int kvm_set_memory_region(struct kvm *kvm,
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
 			    int user_alloc);
+void kvm_arch_free_memslot(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_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
@@ -386,6 +384,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 
@@ -451,6 +450,7 @@ 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);
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_dev_ioctl_check_extension(long ext);
 
@@ -521,7 +521,7 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-int kvm_arch_init_vm(struct kvm *kvm);
+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);
 void kvm_arch_sync_events(struct kvm *kvm);
@@ -547,6 +547,7 @@ struct kvm_assigned_dev_kernel {
 	unsigned int entries_nr;
 	int host_irq;
 	bool host_irq_disabled;
+	bool pci_2_3;
 	struct msix_entry *host_msix_entries;
 	int guest_irq;
 	struct msix_entry *guest_msix_entries;
@@ -556,6 +557,7 @@ struct kvm_assigned_dev_kernel {
 	struct pci_dev *dev;
 	struct kvm *kvm;
 	spinlock_t intx_lock;
+	spinlock_t intx_mask_lock;
 	char irq_name[32];
 	struct pci_saved_state *pci_saved_state;
 };
@@ -651,11 +653,43 @@ static inline void kvm_guest_exit(void)
 	current->flags &= ~PF_VCPU;
 }
 
+/*
+ * search_memslots() and __gfn_to_memslot() are here because they are
+ * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
+ * gfn_to_memslot() itself isn't here as an inline because that would
+ * bloat other code too much.
+ */
+static inline struct kvm_memory_slot *
+search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot;
+
+	kvm_for_each_memslot(memslot, slots)
+		if (gfn >= memslot->base_gfn &&
+		      gfn < memslot->base_gfn + memslot->npages)
+			return memslot;
+
+	return NULL;
+}
+
+static inline struct kvm_memory_slot *
+__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
+{
+	return search_memslots(slots, gfn);
+}
+
 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 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
 					       gfn_t gfn)
 {
@@ -702,12 +736,16 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 	if (unlikely(vcpu->kvm->mmu_notifier_count))
 		return 1;
 	/*
-	 * Both reads happen under the mmu_lock and both values are
-	 * modified under mmu_lock, so there's no need of smb_rmb()
-	 * here in between, otherwise mmu_notifier_count should be
-	 * read before mmu_notifier_seq, see
-	 * mmu_notifier_invalidate_range_end write side.
+	 * Ensure the read of mmu_notifier_count happens before the read
+	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
+	 * mmu_notifier_invalidate_range_end to make sure that the caller
+	 * either sees the old (non-zero) value of mmu_notifier_count or
+	 * the new (incremented) value of mmu_notifier_seq.
+	 * PowerPC Book3s HV KVM calls this under a per-page lock
+	 * rather than under kvm->mmu_lock, for scalability, so
+	 * can't rely on kvm->mmu_lock to keep things ordered.
 	 */
+	smp_rmb();
 	if (vcpu->kvm->mmu_notifier_seq != mmu_seq)
 		return 1;
 	return 0;
@@ -770,6 +808,13 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
 }
+
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
+
+#else
+
+static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
+
 #endif
 
 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT