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

Pull more KVM updates from Paolo Bonzini:
 "Mostly bugfixes, but also:

   - s390 support for KVM selftests

   - LAPIC timer offloading to housekeeping CPUs

   - Extend an s390 optimization for overcommitted hosts to all
     architectures

   - Debugging cleanups and improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
  KVM: x86: Add fixed counters to PMU filter
  KVM: nVMX: do not use dangling shadow VMCS after guest reset
  KVM: VMX: dump VMCS on failed entry
  KVM: x86/vPMU: refine kvm_pmu err msg when event creation failed
  KVM: s390: Use kvm_vcpu_wake_up in kvm_s390_vcpu_wakeup
  KVM: Boost vCPUs that are delivering interrupts
  KVM: selftests: Remove superfluous define from vmx.c
  KVM: SVM: Fix detection of AMD Errata 1096
  KVM: LAPIC: Inject timer interrupt via posted interrupt
  KVM: LAPIC: Make lapic timer unpinned
  KVM: x86/vPMU: reset pmc->counter to 0 for pmu fixed_counters
  KVM: nVMX: Ignore segment base for VMX memory operand when segment not FS or GS
  kvm: x86: ioapic and apic debug macros cleanup
  kvm: x86: some tsc debug cleanup
  kvm: vmx: fix coccinelle warnings
  x86: kvm: avoid constant-conversion warning
  x86: kvm: avoid -Wsometimes-uninitized warning
  KVM: x86: expose AVX512_BF16 feature to guest
  KVM: selftests: enable pgste option for the linker on s390
  KVM: selftests: Move kvm_create_max_vcpus test to generic code
  ...

Documentation/virtual/kvm/api.txt

@@ -4090,17 +4090,22 @@ Parameters: struct kvm_pmu_event_filter (in)
 Returns: 0 on success, -1 on error
 
 struct kvm_pmu_event_filter {
-       __u32 action;
-       __u32 nevents;
-       __u64 events[0];
+	__u32 action;
+	__u32 nevents;
+	__u32 fixed_counter_bitmap;
+	__u32 flags;
+	__u32 pad[4];
+	__u64 events[0];
 };
 
 This ioctl restricts the set of PMU events that the guest can program.
 The argument holds a list of events which will be allowed or denied.
 The eventsel+umask of each event the guest attempts to program is compared
 against the events field to determine whether the guest should have access.
-This only affects general purpose counters; fixed purpose counters can
-be disabled by changing the perfmon CPUID leaf.
+The events field only controls general purpose counters; fixed purpose
+counters are controlled by the fixed_counter_bitmap.
+
+No flags are defined yet, the field must be zero.
 
 Valid values for 'action':
 #define KVM_PMU_EVENT_ALLOW 0

MAINTAINERS

@@ -8878,6 +8878,8 @@ F:	arch/s390/include/asm/gmap.h
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
 F:	arch/s390/mm/gmap.c
+F:	tools/testing/selftests/kvm/s390x/
+F:	tools/testing/selftests/kvm/*/s390x/
 
 KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
 M:	Paolo Bonzini <[email protected]>

arch/s390/kvm/interrupt.c

@@ -1224,28 +1224,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 
 void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * We cannot move this into the if, as the CPU might be already
-	 * in kvm_vcpu_block without having the waitqueue set (polling)
-	 */
 	vcpu->valid_wakeup = true;
+	kvm_vcpu_wake_up(vcpu);
+
 	/*
-	 * This is mostly to document, that the read in swait_active could
-	 * be moved before other stores, leading to subtle races.
-	 * All current users do not store or use an atomic like update
-	 */
-	smp_mb__after_atomic();
-	if (swait_active(&vcpu->wq)) {
-		/*
-		 * The vcpu gave up the cpu voluntarily, mark it as a good
-		 * yield-candidate.
-		 */
-		vcpu->preempted = true;
-		swake_up_one(&vcpu->wq);
-		vcpu->stat.halt_wakeup++;
-	}
-	/*
-	 * The VCPU might not be sleeping but is executing the VSIE. Let's
+	 * The VCPU might not be sleeping but rather executing VSIE. Let's
 	 * kick it, so it leaves the SIE to process the request.
 	 */
 	kvm_s390_vsie_kick(vcpu);

arch/x86/include/uapi/asm/kvm.h

@@ -435,9 +435,12 @@ struct kvm_nested_state {
 
 /* for KVM_CAP_PMU_EVENT_FILTER */
 struct kvm_pmu_event_filter {
-       __u32 action;
-       __u32 nevents;
-       __u64 events[0];
+	__u32 action;
+	__u32 nevents;
+	__u32 fixed_counter_bitmap;
+	__u32 flags;
+	__u32 pad[4];
+	__u64 events[0];
 };
 
 #define KVM_PMU_EVENT_ALLOW 0

arch/x86/kvm/cpuid.c

@@ -368,9 +368,13 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
 		F(MD_CLEAR);
 
+	/* cpuid 7.1.eax */
+	const u32 kvm_cpuid_7_1_eax_x86_features =
+		F(AVX512_BF16);
+
 	switch (index) {
 	case 0:
-		entry->eax = 0;
+		entry->eax = min(entry->eax, 1u);
 		entry->ebx &= kvm_cpuid_7_0_ebx_x86_features;
 		cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
 		/* TSC_ADJUST is emulated */
@@ -394,6 +398,12 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 		 */
 		entry->edx |= F(ARCH_CAPABILITIES);
 		break;
+	case 1:
+		entry->eax &= kvm_cpuid_7_1_eax_x86_features;
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		entry->eax = 0;

arch/x86/kvm/hyperv.c

@@ -1594,7 +1594,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
 	u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS;
 	uint16_t code, rep_idx, rep_cnt;
-	bool fast, longmode, rep;
+	bool fast, rep;
 
 	/*
 	 * hypercall generates UD from non zero cpl and real mode
@@ -1605,23 +1605,21 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
-	longmode = is_64_bit_mode(vcpu);
-
-	if (!longmode) {
+#ifdef CONFIG_X86_64
+	if (is_64_bit_mode(vcpu)) {
+		param = kvm_rcx_read(vcpu);
+		ingpa = kvm_rdx_read(vcpu);
+		outgpa = kvm_r8_read(vcpu);
+	} else
+#endif
+	{
 		param = ((u64)kvm_rdx_read(vcpu) << 32) |
 			(kvm_rax_read(vcpu) & 0xffffffff);
 		ingpa = ((u64)kvm_rbx_read(vcpu) << 32) |
 			(kvm_rcx_read(vcpu) & 0xffffffff);
 		outgpa = ((u64)kvm_rdi_read(vcpu) << 32) |
 			(kvm_rsi_read(vcpu) & 0xffffffff);
 	}
-#ifdef CONFIG_X86_64
-	else {
-		param = kvm_rcx_read(vcpu);
-		ingpa = kvm_rdx_read(vcpu);
-		outgpa = kvm_r8_read(vcpu);
-	}
-#endif
 
 	code = param & 0xffff;
 	fast = !!(param & HV_HYPERCALL_FAST_BIT);

arch/x86/kvm/ioapic.c

@@ -45,11 +45,6 @@
 #include "lapic.h"
 #include "irq.h"
 
-#if 0
-#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
-#else
-#define ioapic_debug(fmt, arg...)
-#endif
 static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
 		bool line_status);
 
@@ -294,7 +289,6 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	default:
 		index = (ioapic->ioregsel - 0x10) >> 1;
 
-		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
 		e = &ioapic->redirtbl[index];
@@ -343,12 +337,6 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	    entry->fields.remote_irr))
 		return -1;
 
-	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
-		     "vector=%x trig_mode=%x\n",
-		     entry->fields.dest_id, entry->fields.dest_mode,
-		     entry->fields.delivery_mode, entry->fields.vector,
-		     entry->fields.trig_mode);
-
 	irqe.dest_id = entry->fields.dest_id;
 	irqe.vector = entry->fields.vector;
 	irqe.dest_mode = entry->fields.dest_mode;
@@ -515,7 +503,6 @@ static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	addr &= 0xff;
@@ -558,8 +545,6 @@ static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
-		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	switch (len) {