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

Pull KVM updates from Paolo Bonzini:
 "Small release, the most interesting stuff is x86 nested virt
  improvements.

  x86:
   - userspace can now hide nested VMX features from guests
   - nested VMX can now run Hyper-V in a guest
   - support for AVX512_4VNNIW and AVX512_FMAPS in KVM
   - infrastructure support for virtual Intel GPUs.

  PPC:
   - support for KVM guests on POWER9
   - improved support for interrupt polling
   - optimizations and cleanups.

  s390:
   - two small optimizations, more stuff is in flight and will be in
     4.11.

  ARM:
   - support for the GICv3 ITS on 32bit platforms"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (94 commits)
  arm64: KVM: pmu: Reset PMSELR_EL0.SEL to a sane value before entering the guest
  KVM: arm/arm64: timer: Check for properly initialized timer on init
  KVM: arm/arm64: vgic-v2: Limit ITARGETSR bits to number of VCPUs
  KVM: x86: Handle the kthread worker using the new API
  KVM: nVMX: invvpid handling improvements
  KVM: nVMX: check host CR3 on vmentry and vmexit
  KVM: nVMX: introduce nested_vmx_load_cr3 and call it on vmentry
  KVM: nVMX: propagate errors from prepare_vmcs02
  KVM: nVMX: fix CR3 load if L2 uses PAE paging and EPT
  KVM: nVMX: load GUEST_EFER after GUEST_CR0 during emulated VM-entry
  KVM: nVMX: generate MSR_IA32_CR{0,4}_FIXED1 from guest CPUID
  KVM: nVMX: fix checks on CR{0,4} during virtual VMX operation
  KVM: nVMX: support restore of VMX capability MSRs
  KVM: nVMX: generate non-true VMX MSRs based on true versions
  KVM: x86: Do not clear RFLAGS.TF when a singlestep trap occurs.
  KVM: x86: Add kvm_skip_emulated_instruction and use it.
  KVM: VMX: Move skip_emulated_instruction out of nested_vmx_check_vmcs12
  KVM: VMX: Reorder some skip_emulated_instruction calls
  KVM: x86: Add a return value to kvm_emulate_cpuid
  KVM: PPC: Book3S: Move prototypes for KVM functions into kvm_ppc.h
  ...

virt/kvm/arm/arch_timer.c

@@ -425,6 +425,11 @@ int kvm_timer_hyp_init(void)
 	info = arch_timer_get_kvm_info();
 	timecounter = &info->timecounter;
 
+	if (!timecounter->cc) {
+		kvm_err("kvm_arch_timer: uninitialized timecounter\n");
+		return -ENODEV;
+	}
+
 	if (info->virtual_irq <= 0) {
 		kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
 			info->virtual_irq);
@@ -498,17 +503,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
-
-	/*
-	 * There is a potential race here between VCPUs starting for the first
-	 * time, which may be enabling the timer multiple times.  That doesn't
-	 * hurt though, because we're just setting a variable to the same
-	 * variable that it already was.  The important thing is that all
-	 * VCPUs have the enabled variable set, before entering the guest, if
-	 * the arch timers are enabled.
-	 */
-	if (timecounter)
-		timer->enabled = 1;
+	timer->enabled = 1;
 
 	return 0;
 }

virt/kvm/arm/vgic/vgic-its.c

@@ -632,21 +632,22 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 	int index;
 	u64 indirect_ptr;
 	gfn_t gfn;
+	int esz = GITS_BASER_ENTRY_SIZE(baser);
 
 	if (!(baser & GITS_BASER_INDIRECT)) {
 		phys_addr_t addr;
 
-		if (id >= (l1_tbl_size / GITS_BASER_ENTRY_SIZE(baser)))
+		if (id >= (l1_tbl_size / esz))
 			return false;
 
-		addr = BASER_ADDRESS(baser) + id * GITS_BASER_ENTRY_SIZE(baser);
+		addr = BASER_ADDRESS(baser) + id * esz;
 		gfn = addr >> PAGE_SHIFT;
 
 		return kvm_is_visible_gfn(its->dev->kvm, gfn);
 	}
 
 	/* calculate and check the index into the 1st level */
-	index = id / (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
+	index = id / (SZ_64K / esz);
 	if (index >= (l1_tbl_size / sizeof(u64)))
 		return false;
 
@@ -670,8 +671,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 	indirect_ptr &= GENMASK_ULL(51, 16);
 
 	/* Find the address of the actual entry */
-	index = id % (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
-	indirect_ptr += index * GITS_BASER_ENTRY_SIZE(baser);
+	index = id % (SZ_64K / esz);
+	indirect_ptr += index * esz;
 	gfn = indirect_ptr >> PAGE_SHIFT;
 
 	return kvm_is_visible_gfn(its->dev->kvm, gfn);

virt/kvm/arm/vgic/vgic-kvm-device.c

@@ -221,11 +221,9 @@ int kvm_register_vgic_device(unsigned long type)
 		ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops,
 					      KVM_DEV_TYPE_ARM_VGIC_V3);
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 		if (ret)
 			break;
 		ret = kvm_vgic_register_its_device();
-#endif
 		break;
 	}
 

virt/kvm/arm/vgic/vgic-mmio-v2.c

@@ -129,6 +129,7 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 				   unsigned long val)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+	u8 cpu_mask = GENMASK(atomic_read(&vcpu->kvm->online_vcpus) - 1, 0);
 	int i;
 
 	/* GICD_ITARGETSR[0-7] are read-only */
@@ -141,7 +142,7 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 
 		spin_lock(&irq->irq_lock);
 
-		irq->targets = (val >> (i * 8)) & 0xff;
+		irq->targets = (val >> (i * 8)) & cpu_mask;
 		target = irq->targets ? __ffs(irq->targets) : 0;
 		irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target);
 

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -42,7 +42,6 @@ u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len,
 	return reg | ((u64)val << lower);
 }
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 bool vgic_has_its(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
@@ -52,7 +51,6 @@ bool vgic_has_its(struct kvm *kvm)
 
 	return dist->has_its;
 }
-#endif
 
 static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 					    gpa_t addr, unsigned int len)

virt/kvm/arm/vgic/vgic.h

@@ -84,37 +84,11 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 int vgic_register_its_iodevs(struct kvm *kvm);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
 int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
-#else
-static inline int vgic_register_its_iodevs(struct kvm *kvm)
-{
-	return -ENODEV;
-}
-
-static inline bool vgic_has_its(struct kvm *kvm)
-{
-	return false;
-}
-
-static inline int kvm_vgic_register_its_device(void)
-{
-	return -ENODEV;
-}
-
-static inline void vgic_enable_lpis(struct kvm_vcpu *vcpu)
-{
-}
-
-static inline int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
-{
-	return -ENODEV;
-}
-#endif
 
 int kvm_register_vgic_device(unsigned long type);
 int vgic_lazy_init(struct kvm *kvm);

virt/kvm/kvm_main.c

@@ -70,16 +70,19 @@ MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */
-static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
+unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
 module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns);
 
 /* Default doubles per-vcpu halt_poll_ns. */
-static unsigned int halt_poll_ns_grow = 2;
+unsigned int halt_poll_ns_grow = 2;
 module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
 
 /* Default resets per-vcpu halt_poll_ns . */
-static unsigned int halt_poll_ns_shrink;
+unsigned int halt_poll_ns_shrink;
 module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
 
 /*
  * Ordering of locks:
@@ -595,7 +598,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 		stat_data->kvm = kvm;
 		stat_data->offset = p->offset;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		if (!debugfs_create_file(p->name, 0444,
+		if (!debugfs_create_file(p->name, 0644,
 					 kvm->debugfs_dentry,
 					 stat_data,
 					 stat_fops_per_vm[p->kind]))
@@ -3669,11 +3672,23 @@ static int vm_stat_get_per_vm(void *data, u64 *val)
 	return 0;
 }
 
+static int vm_stat_clear_per_vm(void *data, u64 val)
+{
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+	if (val)
+		return -EINVAL;
+
+	*(ulong *)((void *)stat_data->kvm + stat_data->offset) = 0;
+
+	return 0;
+}
+
 static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file)
 {
 	__simple_attr_check_format("%llu\n", 0ull);
 	return kvm_debugfs_open(inode, file, vm_stat_get_per_vm,
-				NULL, "%llu\n");
+				vm_stat_clear_per_vm, "%llu\n");
 }
 
 static const struct file_operations vm_stat_get_per_vm_fops = {
@@ -3699,11 +3714,26 @@ static int vcpu_stat_get_per_vm(void *data, u64 *val)
 	return 0;
 }
 
+static int vcpu_stat_clear_per_vm(void *data, u64 val)
+{
+	int i;
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+	struct kvm_vcpu *vcpu;
+
+	if (val)
+		return -EINVAL;
+
+	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
+		*(u64 *)((void *)vcpu + stat_data->offset) = 0;
+
+	return 0;
+}
+
 static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file)
 {
 	__simple_attr_check_format("%llu\n", 0ull);
 	return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm,
-				 NULL, "%llu\n");
+				 vcpu_stat_clear_per_vm, "%llu\n");
 }
 
 static const struct file_operations vcpu_stat_get_per_vm_fops = {
@@ -3738,7 +3768,26 @@ static int vm_stat_get(void *_offset, u64 *val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n");
+static int vm_stat_clear(void *_offset, u64 val)
+{
+	unsigned offset = (long)_offset;
+	struct kvm *kvm;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+
+	if (val)
+		return -EINVAL;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
+	}
+	spin_unlock(&kvm_lock);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
 
 static int vcpu_stat_get(void *_offset, u64 *val)
 {
@@ -3758,7 +3807,27 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n");
+static int vcpu_stat_clear(void *_offset, u64 val)
+{
+	unsigned offset = (long)_offset;
+	struct kvm *kvm;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+
+	if (val)
+		return -EINVAL;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
+	}
+	spin_unlock(&kvm_lock);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
+			"%llu\n");
 
 static const struct file_operations *stat_fops[] = {
 	[KVM_STAT_VCPU] = &vcpu_stat_fops,
@@ -3776,7 +3845,7 @@ static int kvm_init_debug(void)
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
+		if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
 					 (void *)(long)p->offset,
 					 stat_fops[p->kind]))
 			goto out_dir;