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

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...

6 files changed, 75 insertions, 6 deletions

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 295584f31a4e..f0053f884b4a 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -57,9 +57,7 @@ struct arch_timer_cpu {
 
 int kvm_timer_hyp_init(void);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
-int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
-			 const struct kvm_irq_level *virt_irq,
-			 const struct kvm_irq_level *phys_irq);
+int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
@@ -70,6 +68,10 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
 int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
 
+int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
+int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
+int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
+
 bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx);
 void kvm_timer_schedule(struct kvm_vcpu *vcpu);
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 1ab4633adf4f..f6e030617467 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -35,6 +35,7 @@ struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	bool ready;
+	bool created;
 	bool irq_level;
 };
 
@@ -63,6 +64,7 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 #else
 struct kvm_pmu {
 };
@@ -112,6 +114,10 @@ static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 {
 	return -ENXIO;
 }
+static inline int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index ef718586321c..34dba516ef24 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -38,6 +38,10 @@
 #define VGIC_MIN_LPI		8192
 #define KVM_IRQCHIP_NUM_PINS	(1020 - 32)
 
+#define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS)
+#define irq_is_spi(irq) ((irq) >= VGIC_NR_PRIVATE_IRQS && \
+			 (irq) <= VGIC_MAX_SPI)
+
 enum vgic_type {
 	VGIC_V2,		/* Good ol' GICv2 */
 	VGIC_V3,		/* New fancy GICv3 */
@@ -119,6 +123,9 @@ struct vgic_irq {
 	u8 source;			/* GICv2 SGIs only */
 	u8 priority;
 	enum vgic_irq_config config;	/* Level or edge */
+
+	void *owner;			/* Opaque pointer to reserve an interrupt
+					   for in-kernel devices. */
 };
 
 struct vgic_register_region;
@@ -285,6 +292,7 @@ struct vgic_cpu {
 };
 
 extern struct static_key_false vgic_v2_cpuif_trap;
+extern struct static_key_false vgic_v3_cpuif_trap;
 
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 void kvm_vgic_early_init(struct kvm *kvm);
@@ -298,9 +306,7 @@ int kvm_vgic_hyp_init(void);
 void kvm_vgic_init_cpu_hardware(void);
 
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level);
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			       bool level);
+			bool level, void *owner);
 int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
@@ -341,4 +347,6 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
  */
 int kvm_vgic_setup_default_irq_routing(struct kvm *kvm);
 
+int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner);
+
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 1fa293a37f4a..6a1f87ff94e2 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -405,6 +405,7 @@
 #define ICH_LR_PHYS_ID_SHIFT		32
 #define ICH_LR_PHYS_ID_MASK		(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
 #define ICH_LR_PRIORITY_SHIFT		48
+#define ICH_LR_PRIORITY_MASK		(0xffULL << ICH_LR_PRIORITY_SHIFT)
 
 /* These are for GICv2 emulation only */
 #define GICH_LR_VIRTUALID		(0x3ffUL << 0)
@@ -416,6 +417,11 @@
 
 #define ICH_HCR_EN			(1 << 0)
 #define ICH_HCR_UIE			(1 << 1)
+#define ICH_HCR_TC			(1 << 10)
+#define ICH_HCR_TALL0			(1 << 11)
+#define ICH_HCR_TALL1			(1 << 12)
+#define ICH_HCR_EOIcount_SHIFT		27
+#define ICH_HCR_EOIcount_MASK		(0x1f << ICH_HCR_EOIcount_SHIFT)
 
 #define ICH_VMCR_ACK_CTL_SHIFT		2
 #define ICH_VMCR_ACK_CTL_MASK		(1 << ICH_VMCR_ACK_CTL_SHIFT)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8c0664309815..0b50e7b35ed4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -126,6 +126,13 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_MMU_RELOAD        (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_PENDING_TIMER     2
 #define KVM_REQ_UNHALT            3
+#define KVM_REQUEST_ARCH_BASE     8
+
+#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
+	BUILD_BUG_ON((unsigned)(nr) >= 32 - KVM_REQUEST_ARCH_BASE); \
+	(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
+})
+#define KVM_ARCH_REQ(nr)           KVM_ARCH_REQ_FLAGS(nr, 0)
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -1098,6 +1105,11 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 	set_bit(req & KVM_REQUEST_MASK, &vcpu->requests);
 }
 
+static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
+{
+	return READ_ONCE(vcpu->requests);
+}
+
 static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
 {
 	return test_bit(req & KVM_REQUEST_MASK, &vcpu->requests);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 577429a95ad8..c0b6dfec5f87 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -155,6 +155,35 @@ struct kvm_s390_skeys {
 	__u32 reserved[9];
 };
 
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ *             pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ *        in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+	__u64 start_gfn;
+	__u32 count;
+	__u32 flags;
+	union {
+		__u64 remaining;
+		__u64 mask;
+	};
+	__u64 values;
+};
+
 struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
@@ -895,6 +924,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SPAPR_TCE_VFIO 142
 #define KVM_CAP_X86_GUEST_MWAIT 143
 #define KVM_CAP_ARM_USER_IRQ 144
+#define KVM_CAP_S390_CMMA_MIGRATION 145
+#define KVM_CAP_PPC_FWNMI 146
+#define KVM_CAP_PPC_SMT_POSSIBLE 147
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1318,6 +1350,9 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_GET_IRQ_STATE	  _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
 /* Available with KVM_CAP_X86_SMM */
 #define KVM_SMI                   _IO(KVMIO,   0xb7)
+/* Available with KVM_CAP_S390_CMMA_MIGRATION */
+#define KVM_S390_GET_CMMA_BITS      _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)