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

Pull KVM changes from Paolo Bonzini:
 "Here are the 3.13 KVM changes.  There was a lot of work on the PPC
  side: the HV and emulation flavors can now coexist in a single kernel
  is probably the most interesting change from a user point of view.

  On the x86 side there are nested virtualization improvements and a few
  bugfixes.

  ARM got transparent huge page support, improved overcommit, and
  support for big endian guests.

  Finally, there is a new interface to connect KVM with VFIO.  This
  helps with devices that use NoSnoop PCI transactions, letting the
  driver in the guest execute WBINVD instructions.  This includes some
  nVidia cards on Windows, that fail to start without these patches and
  the corresponding userspace changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  kvm, vmx: Fix lazy FPU on nested guest
  arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu
  arm/arm64: KVM: MMIO support for BE guest
  kvm, cpuid: Fix sparse warning
  kvm: Delete prototype for non-existent function kvm_check_iopl
  kvm: Delete prototype for non-existent function complete_pio
  hung_task: add method to reset detector
  pvclock: detect watchdog reset at pvclock read
  kvm: optimize out smp_mb after srcu_read_unlock
  srcu: API for barrier after srcu read unlock
  KVM: remove vm mmap method
  KVM: IOMMU: hva align mapping page size
  KVM: x86: trace cpuid emulation when called from emulator
  KVM: emulator: cleanup decode_register_operand() a bit
  KVM: emulator: check rex prefix inside decode_register()
  KVM: x86: fix emulation of "movzbl %bpl, %eax"
  kvm_host: typo fix
  KVM: x86: emulate SAHF instruction
  MAINTAINERS: add tree for kvm.git
  Documentation/kvm: add a 00-INDEX file
  ...

1 files changed, 77 insertions, 31 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5ca72a5cdb..21ef1ba184a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -577,6 +577,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
 	u64 xcr0;
+	u64 valid_bits;
 
 	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
 	if (index != XCR_XFEATURE_ENABLED_MASK)
@@ -586,8 +587,16 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
 		return 1;
-	if (xcr0 & ~host_xcr0)
+
+	/*
+	 * Do not allow the guest to set bits that we do not support
+	 * saving.  However, xcr0 bit 0 is always set, even if the
+	 * emulated CPU does not support XSAVE (see fx_init).
+	 */
+	valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP;
+	if (xcr0 & ~valid_bits)
 		return 1;
+
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 	return 0;
@@ -684,7 +693,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-	vcpu->arch.mmu.new_cr3(vcpu);
+	kvm_mmu_new_cr3(vcpu);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr3);
@@ -2564,6 +2573,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
@@ -2673,15 +2683,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
-	case KVM_GET_SUPPORTED_CPUID: {
+	case KVM_GET_SUPPORTED_CPUID:
+	case KVM_GET_EMULATED_CPUID: {
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
-		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-						      cpuid_arg->entries);
+
+		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+					    ioctl);
 		if (r)
 			goto out;
 
@@ -2715,8 +2727,7 @@ static void wbinvd_ipi(void *garbage)
 
 static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
-	return vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY);
+	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -2984,11 +2995,13 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	if (cpu_has_xsave)
+	if (cpu_has_xsave) {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->xsave,
-			xstate_size);
-	else {
+			vcpu->arch.guest_xstate_size);
+		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
+			vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+	} else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
 			sizeof(struct i387_fxsave_struct));
@@ -3003,10 +3016,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
 
-	if (cpu_has_xsave)
+	if (cpu_has_xsave) {
+		/*
+		 * Here we allow setting states that are not present in
+		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
+		 * with old userspace.
+		 */
+		if (xstate_bv & ~KVM_SUPPORTED_XCR0)
+			return -EINVAL;
+		if (xstate_bv & ~host_xcr0)
+			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, xstate_size);
-	else {
+			guest_xsave->region, vcpu->arch.guest_xstate_size);
+	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
@@ -3042,9 +3064,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 
 	for (i = 0; i < guest_xcrs->nr_xcrs; i++)
 		/* Only support XCR0 currently */
-		if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
+		if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) {
 			r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
-				guest_xcrs->xcrs[0].value);
+				guest_xcrs->xcrs[i].value);
 			break;
 		}
 	if (r)
@@ -4775,8 +4797,8 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 
 static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
 {
-	memset(&ctxt->twobyte, 0,
-	       (void *)&ctxt->_regs - (void *)&ctxt->twobyte);
+	memset(&ctxt->opcode_len, 0,
+	       (void *)&ctxt->_regs - (void *)&ctxt->opcode_len);
 
 	ctxt->fetch.start = 0;
 	ctxt->fetch.end = 0;
@@ -5094,8 +5116,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		ctxt->have_exception = false;
 		ctxt->perm_ok = false;
 
-		ctxt->only_vendor_specific_insn
-			= emulation_type & EMULTYPE_TRAP_UD;
+		ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
 
 		r = x86_decode_insn(ctxt, insn, insn_len);
 
@@ -5263,7 +5284,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
@@ -5273,7 +5294,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 				send_ipi = 1;
 		}
 	}
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -5426,12 +5447,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5945,10 +5966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	vcpu->mode = IN_GUEST_MODE;
 
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+
 	/* We should set ->mode before check ->requests,
 	 * see the comment in make_all_cpus_request.
 	 */
-	smp_mb();
+	smp_mb__after_srcu_read_unlock();
 
 	local_irq_disable();
 
@@ -5958,12 +5981,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = 1;
 		goto cancel_injection;
 	}
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6688,7 +6710,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (r)
 		return r;
 	kvm_vcpu_reset(vcpu);
-	r = kvm_mmu_setup(vcpu);
+	kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
 
 	return r;
@@ -6940,6 +6962,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
+
+	vcpu->arch.guest_supported_xcr0 = 0;
+	vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
@@ -6981,6 +7007,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
+	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
@@ -7065,7 +7092,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 	int i;
@@ -7086,7 +7113,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	int i;
 
@@ -7283,7 +7311,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	int r;
 
 	if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
-	      is_error_page(work->page))
+	      work->wakeup_all)
 		return;
 
 	r = kvm_mmu_reload(vcpu);
@@ -7393,7 +7421,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 	struct x86_exception fault;
 
 	trace_kvm_async_pf_ready(work->arch.token, work->gva);
-	if (is_error_page(work->page))
+	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
@@ -7420,6 +7448,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma);
+
+void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma);
+
+bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);