Merge tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "ARM:

   - icache invalidation optimizations, improving VM startup time

   - support for forwarded level-triggered interrupts, improving
     performance for timers and passthrough platform devices

   - a small fix for power-management notifiers, and some cosmetic
     changes

  PPC:

   - add MMIO emulation for vector loads and stores

   - allow HPT guests to run on a radix host on POWER9 v2.2 CPUs without
     requiring the complex thread synchronization of older CPU versions

   - improve the handling of escalation interrupts with the XIVE
     interrupt controller

   - support decrement register migration

   - various cleanups and bugfixes.

  s390:

   - Cornelia Huck passed maintainership to Janosch Frank

   - exitless interrupts for emulated devices

   - cleanup of cpuflag handling

   - kvm_stat counter improvements

   - VSIE improvements

   - mm cleanup

  x86:

   - hypervisor part of SEV

   - UMIP, RDPID, and MSR_SMI_COUNT emulation

   - paravirtualized TLB shootdown using the new KVM_VCPU_PREEMPTED bit

   - allow guests to see TOPOEXT, GFNI, VAES, VPCLMULQDQ, and more
     AVX512 features

   - show vcpu id in its anonymous inode name

   - many fixes and cleanups

   - per-VCPU MSR bitmaps (already merged through x86/pti branch)

   - stable KVM clock when nesting on Hyper-V (merged through
     x86/hyperv)"

* tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (197 commits)
  KVM: PPC: Book3S: Add MMIO emulation for VMX instructions
  KVM: PPC: Book3S HV: Branch inside feature section
  KVM: PPC: Book3S HV: Make HPT resizing work on POWER9
  KVM: PPC: Book3S HV: Fix handling of secondary HPTEG in HPT resizing code
  KVM: PPC: Book3S PR: Fix broken select due to misspelling
  KVM: x86: don't forget vcpu_put() in kvm_arch_vcpu_ioctl_set_sregs()
  KVM: PPC: Book3S PR: Fix svcpu copying with preemption enabled
  KVM: PPC: Book3S HV: Drop locks before reading guest memory
  kvm: x86: remove efer_reload entry in kvm_vcpu_stat
  KVM: x86: AMD Processor Topology Information
  x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO when running nested
  kvm: embed vcpu id to dentry of vcpu anon inode
  kvm: Map PFN-type memory regions as writable (if possible)
  x86/kvm: Make it compile on 32bit and with HYPYERVISOR_GUEST=n
  KVM: arm/arm64: Fixup userspace irqchip static key optimization
  KVM: arm/arm64: Fix userspace_irqchip_in_use counting
  KVM: arm/arm64: Fix incorrect timer_is_pending logic
  MAINTAINERS: update KVM/s390 maintainers
  MAINTAINERS: add Halil as additional vfio-ccw maintainer
  MAINTAINERS: add David as a reviewer for KVM/s390
  ...

10 files changed, 95 insertions, 8 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 1d9199e1c2ad..0dfe4d3f74e2 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -210,6 +210,7 @@
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 51cc979dd364..7c341a74ec8c 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -38,6 +38,9 @@ typedef struct {
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	unsigned int irq_hv_callback_count;
 #endif
+#if IS_ENABLED(CONFIG_HYPERV)
+	unsigned int irq_hv_reenlightenment_count;
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 67421f649cfa..e71c1120426b 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -103,7 +103,12 @@
 #endif
 
 #define MANAGED_IRQ_SHUTDOWN_VECTOR	0xef
-#define LOCAL_TIMER_VECTOR		0xee
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR	0xee
+#endif
+
+#define LOCAL_TIMER_VECTOR		0xed
 
 #define NR_VECTORS			 256
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 516798431328..dd6f57a54a26 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -86,7 +86,7 @@
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
-			  | X86_CR4_SMAP | X86_CR4_PKE))
+			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
@@ -504,6 +504,7 @@ struct kvm_vcpu_arch {
 	int mp_state;
 	u64 ia32_misc_enable_msr;
 	u64 smbase;
+	u64 smi_count;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
 
@@ -760,6 +761,15 @@ enum kvm_irqchip_mode {
 	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
 };
 
+struct kvm_sev_info {
+	bool active;		/* SEV enabled guest */
+	unsigned int asid;	/* ASID used for this guest */
+	unsigned int handle;	/* SEV firmware handle */
+	int fd;			/* SEV device fd */
+	unsigned long pages_locked; /* Number of pages locked */
+	struct list_head regions_list;  /* List of registered regions */
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -847,6 +857,8 @@ struct kvm_arch {
 
 	bool x2apic_format;
 	bool x2apic_broadcast_quirk_disabled;
+
+	struct kvm_sev_info sev_info;
 };
 
 struct kvm_vm_stat {
@@ -883,7 +895,6 @@ struct kvm_vcpu_stat {
 	u64 request_irq_exits;
 	u64 irq_exits;
 	u64 host_state_reload;
-	u64 efer_reload;
 	u64 fpu_reload;
 	u64 insn_emulation;
 	u64 insn_emulation_fail;
@@ -965,7 +976,7 @@ struct kvm_x86_ops {
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 
-	void (*tlb_flush)(struct kvm_vcpu *vcpu);
+	void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 
 	void (*run)(struct kvm_vcpu *vcpu);
 	int (*handle_exit)(struct kvm_vcpu *vcpu);
@@ -1017,6 +1028,7 @@ struct kvm_x86_ops {
 	void (*handle_external_intr)(struct kvm_vcpu *vcpu);
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
+	bool (*umip_emulated)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
@@ -1079,6 +1091,10 @@ struct kvm_x86_ops {
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
 	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
 	int (*enable_smi_window)(struct kvm_vcpu *vcpu);
+
+	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
+	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 };
 
 struct kvm_arch_async_pf {
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index b52af150cbd8..25283f7eb299 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -160,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 #define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
 
 void hyperv_callback_vector(void);
+void hyperv_reenlightenment_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
@@ -316,18 +317,27 @@ void hyper_alloc_mmu(void);
 void hyperv_report_panic(struct pt_regs *regs, long err);
 bool hv_is_hyperv_initialized(void);
 void hyperv_cleanup(void);
+
+void hyperv_reenlightenment_intr(struct pt_regs *regs);
+void set_hv_tscchange_cb(void (*cb)(void));
+void clear_hv_tscchange_cb(void);
+void hyperv_stop_tsc_emulation(void);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline void hyperv_cleanup(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
+static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
+static inline void clear_hv_tscchange_cb(void) {}
+static inline void hyperv_stop_tsc_emulation(void) {};
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
 {
-	u64 scale, offset, cur_tsc;
+	u64 scale, offset;
 	u32 sequence;
 
 	/*
@@ -358,7 +368,7 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 		scale = READ_ONCE(tsc_pg->tsc_scale);
 		offset = READ_ONCE(tsc_pg->tsc_offset);
-		cur_tsc = rdtsc_ordered();
+		*cur_tsc = rdtsc_ordered();
 
 		/*
 		 * Make sure we read sequence after we read all other values
@@ -368,7 +378,14 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
 
-	return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+}
+
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 cur_tsc;
+
+	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
 }
 
 #else
@@ -376,5 +393,12 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return NULL;
 }
+
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
+{
+	BUG();
+	return U64_MAX;
+}
 #endif
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e520a1e6fc11..c9084dedfcfa 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -397,6 +397,8 @@
 #define MSR_K7_PERFCTR3			0xc0010007
 #define MSR_K7_CLK_CTL			0xc001001b
 #define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT		0
+#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 8a3ee355b422..92015c65fa2a 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -22,4 +22,6 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end,
 
 void io_free_memtype(resource_size_t start, resource_size_t end);
 
+bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+
 #endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 78dd9df88157..0487ac054870 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -146,6 +146,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
 #define SVM_VM_CR_SVM_DIS_MASK  0x0010ULL
 
+#define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
+
 struct __attribute__ ((__packed__)) vmcb_seg {
 	u16 selector;
 	u16 attrib;
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 1a5bfead93b4..197c2e6c7376 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -40,6 +40,9 @@
  */
 #define HV_X64_ACCESS_FREQUENCY_MSRS		(1 << 11)
 
+/* AccessReenlightenmentControls privilege */
+#define HV_X64_ACCESS_REENLIGHTENMENT		BIT(13)
+
 /*
  * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
  * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
@@ -234,6 +237,30 @@
 #define HV_X64_MSR_CRASH_PARAMS		\
 		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
 
+/* TSC emulation after migration */
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
+
+struct hv_reenlightenment_control {
+	u64 vector:8;
+	u64 reserved1:8;
+	u64 enabled:1;
+	u64 reserved2:15;
+	u64 target_vp:32;
+};
+
+#define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
+
+struct hv_tsc_emulation_control {
+	u64 enabled:1;
+	u64 reserved:63;
+};
+
+struct hv_tsc_emulation_status {
+	u64 inprogress:1;
+	u64 reserved:63;
+};
+
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 09cc06483bed..7a2ade4aa235 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -25,6 +25,7 @@
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
+#define KVM_FEATURE_PV_TLB_FLUSH	9
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -51,6 +52,9 @@ struct kvm_steal_time {
 	__u32 pad[11];
 };
 
+#define KVM_VCPU_PREEMPTED          (1 << 0)
+#define KVM_VCPU_FLUSH_TLB          (1 << 1)
+
 #define KVM_CLOCK_PAIRING_WALLCLOCK 0
 struct kvm_clock_pairing {
 	__s64 sec;