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
  ...

5 files changed, 110 insertions, 21 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ea831c858195..5bddbdcbc4a3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,6 +556,51 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 }
 
+static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
+{
+	u64 msr;
+
+	/*
+	 * BIOS support is required for SME and SEV.
+	 *   For SME: If BIOS has enabled SME then adjust x86_phys_bits by
+	 *	      the SME physical address space reduction value.
+	 *	      If BIOS has not enabled SME then don't advertise the
+	 *	      SME feature (set in scattered.c).
+	 *   For SEV: If BIOS has not enabled SEV then don't advertise the
+	 *            SEV feature (set in scattered.c).
+	 *
+	 *   In all cases, since support for SME and SEV requires long mode,
+	 *   don't advertise the feature under CONFIG_X86_32.
+	 */
+	if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
+		/* Check if memory encryption is enabled */
+		rdmsrl(MSR_K8_SYSCFG, msr);
+		if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+			goto clear_all;
+
+		/*
+		 * Always adjust physical address bits. Even though this
+		 * will be a value above 32-bits this is still done for
+		 * CONFIG_X86_32 so that accurate values are reported.
+		 */
+		c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
+
+		if (IS_ENABLED(CONFIG_X86_32))
+			goto clear_all;
+
+		rdmsrl(MSR_K7_HWCR, msr);
+		if (!(msr & MSR_K7_HWCR_SMMLOCK))
+			goto clear_sev;
+
+		return;
+
+clear_all:
+		clear_cpu_cap(c, X86_FEATURE_SME);
+clear_sev:
+		clear_cpu_cap(c, X86_FEATURE_SEV);
+	}
+}
+
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
 	u32 dummy;
@@ -627,26 +672,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (cpu_has_amd_erratum(c, amd_erratum_400))
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
-	/*
-	 * BIOS support is required for SME. If BIOS has enabled SME then
-	 * adjust x86_phys_bits by the SME physical address space reduction
-	 * value. If BIOS has not enabled SME then don't advertise the
-	 * feature (set in scattered.c). Also, since the SME support requires
-	 * long mode, don't advertise the feature under CONFIG_X86_32.
-	 */
-	if (cpu_has(c, X86_FEATURE_SME)) {
-		u64 msr;
-
-		/* Check if SME is enabled */
-		rdmsrl(MSR_K8_SYSCFG, msr);
-		if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) {
-			c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
-			if (IS_ENABLED(CONFIG_X86_32))
-				clear_cpu_cap(c, X86_FEATURE_SME);
-		} else {
-			clear_cpu_cap(c, X86_FEATURE_SME);
-		}
-	}
+	early_detect_mem_encrypt(c);
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 85eb5fc180c8..9340f41ce8d3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void)
 	hyperv_setup_mmu_ops();
 	/* Setup the IDT for hypervisor callback */
 	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
+	/* Setup the IDT for reenlightenment notifications */
+	if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+		alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
+				hyperv_reenlightenment_vector);
+
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 4075d2be5357..772c219b6889 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -30,6 +30,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
 	{ X86_FEATURE_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
+	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 68e1867cca80..45fb4d2565f8 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -142,6 +142,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_puts(p, "  Hypervisor callback interrupts\n");
 	}
 #endif
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
+		seq_printf(p, "%*s: ", prec, "HRE");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				   irq_stats(j)->irq_hv_reenlightenment_count);
+		seq_puts(p, "  Hyper-V reenlightenment interrupts\n");
+	}
+#endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b40ffbf156c1..4e37d1a851a6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -498,6 +498,34 @@ static void __init kvm_apf_trap_init(void)
 	update_intr_gate(X86_TRAP_PF, async_page_fault);
 }
 
+static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
+
+static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+			const struct flush_tlb_info *info)
+{
+	u8 state;
+	int cpu;
+	struct kvm_steal_time *src;
+	struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+
+	cpumask_copy(flushmask, cpumask);
+	/*
+	 * We have to call flush only on online vCPUs. And
+	 * queue flush_on_enter for pre-empted vCPUs
+	 */
+	for_each_cpu(cpu, flushmask) {
+		src = &per_cpu(steal_time, cpu);
+		state = READ_ONCE(src->preempted);
+		if ((state & KVM_VCPU_PREEMPTED)) {
+			if (try_cmpxchg(&src->preempted, &state,
+					state | KVM_VCPU_FLUSH_TLB))
+				__cpumask_clear_cpu(cpu, flushmask);
+		}
+	}
+
+	native_flush_tlb_others(flushmask, info);
+}
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -517,6 +545,9 @@ static void __init kvm_guest_init(void)
 		pv_time_ops.steal_clock = kvm_steal_clock;
 	}
 
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
+
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		apic_set_eoi_write(kvm_guest_apic_eoi_write);
 
@@ -598,6 +629,22 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
+static __init int kvm_setup_pv_tlb_flush(void)
+{
+	int cpu;
+
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+		for_each_possible_cpu(cpu) {
+			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+				GFP_KERNEL, cpu_to_node(cpu));
+		}
+		pr_info("KVM setup pv remote TLB flush\n");
+	}
+
+	return 0;
+}
+arch_initcall(kvm_setup_pv_tlb_flush);
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 /* Kick a cpu by its apicid. Used to wake up a halted vcpu */
@@ -643,7 +690,7 @@ __visible bool __kvm_vcpu_is_preempted(long cpu)
 {
 	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
 
-	return !!src->preempted;
+	return !!(src->preempted & KVM_VCPU_PREEMPTED);
 }
 PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);