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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - VHE optimizations

   - EL2 address space randomization

   - speculative execution mitigations ("variant 3a", aka execution past
     invalid privilege register access)

   - bugfixes and cleanups

  PPC:
   - improvements for the radix page fault handler for HV KVM on POWER9

  s390:
   - more kvm stat counters

   - virtio gpu plumbing

   - documentation

   - facilities improvements

  x86:
   - support for VMware magic I/O port and pseudo-PMCs

   - AMD pause loop exiting

   - support for AMD core performance extensions

   - support for synchronous register access

   - expose nVMX capabilities to userspace

   - support for Hyper-V signaling via eventfd

   - use Enlightened VMCS when running on Hyper-V

   - allow userspace to disable MWAIT/HLT/PAUSE vmexits

   - usual roundup of optimizations and nested virtualization bugfixes

  Generic:
   - API selftest infrastructure (though the only tests are for x86 as
     of now)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (174 commits)
  kvm: x86: fix a prototype warning
  kvm: selftests: add sync_regs_test
  kvm: selftests: add API testing infrastructure
  kvm: x86: fix a compile warning
  KVM: X86: Add Force Emulation Prefix for "emulate the next instruction"
  KVM: X86: Introduce handle_ud()
  KVM: vmx: unify adjacent #ifdefs
  x86: kvm: hide the unused 'cpu' variable
  KVM: VMX: remove bogus WARN_ON in handle_ept_misconfig
  Revert "KVM: X86: Fix SMRAM accessing even if VM is shutdown"
  kvm: Add emulation for movups/movupd
  KVM: VMX: raise internal error for exception during invalid protected mode state
  KVM: nVMX: Optimization: Dont set KVM_REQ_EVENT when VMExit with nested_run_pending
  KVM: nVMX: Require immediate-exit when event reinjected to L2 and L1 event pending
  KVM: x86: Fix misleading comments on handling pending exceptions
  KVM: x86: Rename interrupt.pending to interrupt.injected
  KVM: VMX: No need to clear pending NMI/interrupt on inject realmode interrupt
  x86/kvm: use Enlightened VMCS when running on Hyper-V
  x86/hyper-v: detect nested features
  x86/hyper-v: define struct hv_enlightened_vmcs and clean field bits
  ...

4 files changed, 48 insertions, 9 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 348cf4821240..4702fbd98f92 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -487,7 +487,7 @@ void load_percpu_segment(int cpu)
 	loadsegment(fs, __KERNEL_PERCPU);
 #else
 	__loadsegment_simple(gs, 0);
-	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #endif
 	load_stack_canary_segment();
 }
@@ -1398,6 +1398,7 @@ __setup("clearcpuid=", setup_clearcpuid);
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
 
 /*
  * The following percpu variables are hot.  Align current_task to
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4488cf0dd499..031082c96db8 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -22,7 +22,7 @@
 #include <linux/kexec.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
-#include <asm/hyperv.h>
+#include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/desc.h>
 #include <asm/irq_regs.h>
@@ -216,8 +216,8 @@ static void __init ms_hyperv_init_platform(void)
 	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
 		ms_hyperv.features, ms_hyperv.hints);
 
-	ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS);
-	ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS);
+	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
+	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
 
 	pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
 		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
@@ -225,11 +225,12 @@ static void __init ms_hyperv_init_platform(void)
 	/*
 	 * Extract host information.
 	 */
-	if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) {
-		hv_host_info_eax = cpuid_eax(HVCPUID_VERSION);
-		hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION);
-		hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION);
-		hv_host_info_edx = cpuid_edx(HVCPUID_VERSION);
+	if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >=
+	    HYPERV_CPUID_VERSION) {
+		hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION);
+		hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION);
+		hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION);
+		hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION);
 
 		pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n",
 			hv_host_info_eax, hv_host_info_ebx >> 16,
@@ -243,6 +244,11 @@ static void __init ms_hyperv_init_platform(void)
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
+	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
+		ms_hyperv.nested_features =
+			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
+	}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index fae86e36e399..7867417cfaff 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -454,6 +454,13 @@ static void __init sev_map_percpu_data(void)
 }
 
 #ifdef CONFIG_SMP
+static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+	native_smp_prepare_cpus(max_cpus);
+	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+		static_branch_disable(&virt_spin_lock_key);
+}
+
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
 	/*
@@ -546,6 +553,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
@@ -556,6 +564,7 @@ static void __init kvm_guest_init(void)
 		kvm_setup_vsyscall_timeinfo();
 
 #ifdef CONFIG_SMP
+	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
 				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
@@ -605,6 +614,11 @@ unsigned int kvm_arch_para_features(void)
 	return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
 }
 
+unsigned int kvm_arch_para_hints(void)
+{
+	return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
+}
+
 static uint32_t __init kvm_detect(void)
 {
 	return kvm_cpuid_base();
@@ -635,6 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
 	int cpu;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -730,6 +745,9 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
+	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+		return;
+
 	__pv_init_lock_hash();
 	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
 	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9eb448c7859d..4b100fe0f508 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -205,6 +205,20 @@ static __always_inline void save_fsgs(struct task_struct *task)
 	save_base_legacy(task, task->thread.gsindex, GS);
 }
 
+#if IS_ENABLED(CONFIG_KVM)
+/*
+ * While a process is running,current->thread.fsbase and current->thread.gsbase
+ * may not match the corresponding CPU registers (see save_base_legacy()). KVM
+ * wants an efficient way to save and restore FSBASE and GSBASE.
+ * When FSGSBASE extensions are enabled, this will have to use RD{FS,GS}BASE.
+ */
+void save_fsgs_for_kvm(void)
+{
+	save_fsgs(current);
+}
+EXPORT_SYMBOL_GPL(save_fsgs_for_kvm);
+#endif
+
 static __always_inline void loadseg(enum which_selector which,
 				    unsigned short sel)
 {