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

Pull KVM fixes from Paolo Bonzini:
 "Quite a few fixes for x86: nested virtualization save/restore, AMD
  nested virtualization and virtual APIC, 32-bit fixes, an important fix
  to restore operation on older processors, and a bunch of hyper-v
  bugfixes. Several are marked stable.

  There are also fixes for GCC warnings and for a GCC/objtool interaction"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Mark expected switch fall-throughs
  KVM: x86: fix TRACE_INCLUDE_PATH and remove -I. header search paths
  KVM: selftests: check returned evmcs version range
  x86/kvm/hyper-v: nested_enable_evmcs() sets vmcs_version incorrectly
  KVM: VMX: Move vmx_vcpu_run()'s VM-Enter asm blob to a helper function
  kvm: selftests: Fix region overlap check in kvm_util
  kvm: vmx: fix some -Wmissing-prototypes warnings
  KVM: nSVM: clear events pending from svm_complete_interrupts() when exiting to L1
  svm: Fix AVIC incomplete IPI emulation
  svm: Add warning message for AVIC IPI invalid target
  KVM: x86: WARN_ONCE if sending a PV IPI returns a fatal error
  KVM: x86: Fix PV IPIs for 32-bit KVM host
  x86/kvm/hyper-v: recommend using eVMCS only when it is enabled
  x86/kvm/hyper-v: don't recommend doing reset via synthetic MSR
  kvm: x86/vmx: Use kzalloc for cached_vmcs12
  KVM: VMX: Use the correct field var when clearing VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL
  KVM: x86: Fix single-step debugging
  x86/kvm/hyper-v: don't announce GUEST IDLE MSR support

13 files changed, 130 insertions, 115 deletions

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index ba4bfb7f6a36..5c93a65ee1e5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 #else
         u64 ipi_bitmap = 0;
 #endif
+        long ret;
 
         if (cpumask_empty(mask))
                 return;
@@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
                 } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
                         max = apic_id < max ? max : apic_id;
                 } else {
-                        kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+                        ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
                                 (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+                        WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
                         min = max = apic_id;
                         ipi_bitmap = 0;
                 }
@@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
         }
 
         if (ipi_bitmap) {
-                kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+                ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
                         (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+                WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
         }
 
         local_irq_restore(flags);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 69b3a7c30013..31ecf7a76d5a 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -2,10 +2,6 @@
 
 ccflags-y += -Iarch/x86/kvm
 
-CFLAGS_x86.o := -I.
-CFLAGS_svm.o := -I.
-CFLAGS_vmx.o := -I.
-
 KVM := ../../../virt/kvm
 
 kvm-y                   += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c90a5352d158..89d20ed1d2e8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1636,7 +1636,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
                 ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
                 if (ret != HV_STATUS_INVALID_PORT_ID)
                         break;
-                /* maybe userspace knows this conn_id: fall through */
+                /* fall through - maybe userspace knows this conn_id. */
         case HVCALL_POST_MESSAGE:
                 /* don't bother userspace if it has no way to handle it */
                 if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
@@ -1832,7 +1832,6 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
                         ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
                         ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
                         ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
-                        ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE;
                         ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
                         ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
 
@@ -1848,11 +1847,11 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
                 case HYPERV_CPUID_ENLIGHTMENT_INFO:
                         ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
                         ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
-                        ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED;
                         ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
                         ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
                         ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
-                        ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+                        if (evmcs_ver)
+                                ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
 
                         /*
                          * Default number of spinlock retry attempts, matches
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9f089e2e09d0..4b6c2da7265c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1035,6 +1035,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
         switch (delivery_mode) {
         case APIC_DM_LOWEST:
                 vcpu->arch.apic_arb_prio++;
+                /* fall through */
         case APIC_DM_FIXED:
                 if (unlikely(trig_mode && !level))
                         break;
@@ -1874,6 +1875,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
         case APIC_LVT0:
                 apic_manage_nmi_watchdog(apic, val);
+                /* fall through */
         case APIC_LVTTHMR:
         case APIC_LVTPC:
         case APIC_LVT1:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ce770b446238..da9c42349b1f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4371,6 +4371,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
                         rsvd_bits(maxphyaddr, 51);
                 rsvd_check->rsvd_bits_mask[1][4] =
                         rsvd_check->rsvd_bits_mask[0][4];
+                /* fall through */
         case PT64_ROOT_4LEVEL:
                 rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
                         nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a157ca5b6869..f13a3a24d360 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3414,6 +3414,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
         kvm_mmu_reset_context(&svm->vcpu);
         kvm_mmu_load(&svm->vcpu);
 
+        /*
+         * Drop what we picked up for L2 via svm_complete_interrupts() so it
+         * doesn't end up in L1.
+         */
+        svm->vcpu.arch.nmi_injected = false;
+        kvm_clear_exception_queue(&svm->vcpu);
+        kvm_clear_interrupt_queue(&svm->vcpu);
+
         return 0;
 }
 
@@ -4395,7 +4403,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
         case MSR_IA32_APICBASE:
                 if (kvm_vcpu_apicv_active(vcpu))
                         avic_update_vapic_bar(to_svm(vcpu), data);
-                /* Follow through */
+                /* Fall through */
         default:
                 return kvm_set_msr_common(vcpu, msr);
         }
@@ -4504,28 +4512,19 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
                 kvm_lapic_reg_write(apic, APIC_ICR, icrl);
                 break;
         case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
-                int i;
-                struct kvm_vcpu *vcpu;
-                struct kvm *kvm = svm->vcpu.kvm;
                 struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
                 /*
-                 * At this point, we expect that the AVIC HW has already
-                 * set the appropriate IRR bits on the valid target
+                 * Update ICR high and low, then emulate sending IPI,
+                 * which is handled when writing APIC_ICR.