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

Pull KVM updates from Paolo Bonzini:
 "Fixes and features for 3.18.

  Apart from the usual cleanups, here is the summary of new features:

   - s390 moves closer towards host large page support

   - PowerPC has improved support for debugging (both inside the guest
     and via gdbstub) and support for e6500 processors

   - ARM/ARM64 support read-only memory (which is necessary to put
     firmware in emulated NOR flash)

   - x86 has the usual emulator fixes and nested virtualization
     improvements (including improved Windows support on Intel and
     Jailhouse hypervisor support on AMD), adaptive PLE which helps
     overcommitting of huge guests.  Also included are some patches that
     make KVM more friendly to memory hot-unplug, and fixes for rare
     caching bugs.

  Two patches have trivial mm/ parts that were acked by Rik and Andrew.

  Note: I will soon switch to a subkey for signing purposes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (157 commits)
  kvm: do not handle APIC access page if in-kernel irqchip is not in use
  KVM: s390: count vcpu wakeups in stat.halt_wakeup
  KVM: s390/facilities: allow TOD-CLOCK steering facility bit
  KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode
  arm/arm64: KVM: Report correct FSC for unsupported fault types
  arm/arm64: KVM: Fix VTTBR_BADDR_MASK and pgd alloc
  kvm: Fix kvm_get_page_retry_io __gup retval check
  arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset
  kvm: x86: Unpin and remove kvm_arch->apic_access_page
  kvm: vmx: Implement set_apic_access_page_addr
  kvm: x86: Add request bit to reload APIC access page address
  kvm: Add arch specific mmu notifier for page invalidation
  kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static
  kvm: Fix page ageing bugs
  kvm/x86/mmu: Pass gfn and level to rmapp callback.
  x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
  kvm: x86: use macros to compute bank MSRs
  KVM: x86: Remove debug assertion of non-PAE reserved bits
  kvm: don't take vcpu mutex for obviously invalid vcpu ioctls
  kvm: Faults which trigger IO release the mmap_sem
  ...

1 files changed, 110 insertions, 38 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f1e22d3b286..5430e4b0af29 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,7 +246,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -408,12 +408,14 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
 
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
 	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
 		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
 	else
 		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+
+	return fault->nested_page_fault;
 }
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -457,11 +459,12 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			    gfn_t ngfn, void *data, int offset, int len,
 			    u32 access)
 {
+	struct x86_exception exception;
 	gfn_t real_gfn;
 	gpa_t ngpa;
 
 	ngpa     = gfn_to_gpa(ngfn);
-	real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
+	real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception);
 	if (real_gfn == UNMAPPED_GVA)
 		return -EFAULT;
 
@@ -726,7 +729,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
 		kvm_mmu_sync_roots(vcpu);
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		return 0;
 	}
 
@@ -1518,7 +1521,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	pvclock_update_vm_gtod_copy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
 	/* guest entries allowed */
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -1661,7 +1664,7 @@ static void kvmclock_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
 }
@@ -1670,7 +1673,7 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
 {
 	struct kvm *kvm = v->kvm;
 
-	set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+	kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
 	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
 					KVMCLOCK_UPDATE_DELAY);
 }
@@ -1723,9 +1726,10 @@ static bool valid_mtrr_type(unsigned t)
 	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
 }
 
-static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	int i;
+	u64 mask;
 
 	if (!msr_mtrr_valid(msr))
 		return false;
@@ -1747,14 +1751,31 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	}
 
 	/* variable MTRRs */
-	return valid_mtrr_type(data & 0xff);
+	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
+
+	mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	if ((msr & 1) == 0) {
+		/* MTRR base */
+		if (!valid_mtrr_type(data & 0xff))
+			return false;
+		mask |= 0xf00;
+	} else
+		/* MTRR mask */
+		mask |= 0x7ff;
+	if (data & mask) {
+		kvm_inject_gp(vcpu, 0);
+		return false;
+	}
+
+	return true;
 }
+EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
 
 static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
 
-	if (!mtrr_valid(vcpu, msr, data))
+	if (!kvm_mtrr_valid(vcpu, msr, data))
 		return 1;
 
 	if (msr == MSR_MTRRdefType) {
@@ -1805,7 +1826,7 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
-		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+		    msr < MSR_IA32_MCx_CTL(bank_num)) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
@@ -2164,7 +2185,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
-	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return set_msr_mce(vcpu, msr, data);
 
 	/* Performance counters are not protected by a CPUID bit,
@@ -2330,7 +2351,7 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		break;
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
-		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+		    msr < MSR_IA32_MCx_CTL(bank_num)) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
 			data = vcpu->arch.mce_banks[offset];
 			break;
@@ -2419,7 +2440,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K7_EVNTSEL0:
+	case MSR_K7_EVNTSEL1:
+	case MSR_K7_EVNTSEL2:
+	case MSR_K7_EVNTSEL3:
 	case MSR_K7_PERFCTR0:
+	case MSR_K7_PERFCTR1:
+	case MSR_K7_PERFCTR2:
+	case MSR_K7_PERFCTR3:
 	case MSR_K8_INT_PENDING_MSG:
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
@@ -2505,7 +2532,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_CAP:
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
-	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr, pdata);
 	case MSR_K7_CLK_CTL:
 		/*
@@ -2823,7 +2850,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
 		vcpu->arch.tsc_offset_adjustment = 0;
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	}
 
 	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
@@ -4040,16 +4067,16 @@ void kvm_get_segment(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->get_segment(vcpu, var, seg);
 }
 
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+			   struct x86_exception *exception)
 {
 	gpa_t t_gpa;
-	struct x86_exception exception;
 
 	BUG_ON(!mmu_is_nested(vcpu));
 
 	/* NPT walks are always user-walks */
 	access |= PFERR_USER_MASK;
-	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
+	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
 
 	return t_gpa;
 }
@@ -4906,16 +4933,18 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 	}
 }
 
-static void inject_emulated_exception(struct kvm_vcpu *vcpu)
+static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	if (ctxt->exception.vector == PF_VECTOR)
-		kvm_propagate_fault(vcpu, &ctxt->exception);
-	else if (ctxt->exception.error_code_valid)
+		return kvm_propagate_fault(vcpu, &ctxt->exception);
+
+	if (ctxt->exception.error_code_valid)
 		kvm_queue_exception_e(vcpu, ctxt->exception.vector,
 				      ctxt->exception.error_code);
 	else
 		kvm_queue_exception(vcpu, ctxt->exception.vector);
+	return false;
 }
 
 static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -4972,7 +5001,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
-	if (!is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
@@ -5224,6 +5253,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 		ctxt->interruptibility = 0;
 		ctxt->have_exception = false;
+		ctxt->exception.vector = -1;
 		ctxt->perm_ok = false;
 
 		ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
@@ -5276,8 +5306,9 @@ restart:
 	}
 
 	if (ctxt->have_exception) {
-		inject_emulated_exception(vcpu);
 		r = EMULATE_DONE;
+		if (inject_emulated_exception(vcpu))
+			return r;
 	} else if (vcpu->arch.pio.count) {
 		if (!vcpu->arch.pio.in) {
 			/* FIXME: return into emulator if single-stepping.  */
@@ -5545,7 +5576,7 @@ static void kvm_set_mmio_spte_mask(void)
 	 * entry to generate page fault with PFER.RSV = 1.
 	 */
 	 /* Mask the reserved physical address bits. */
-	mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr;
+	mask = rsvd_bits(maxphyaddr, 51);
 
 	/* Bit 62 is always reserved for 32bit host. */
 	mask |= 0x3ull << 62;
@@ -5576,7 +5607,7 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	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);
+			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
 	spin_unlock(&kvm_lock);
 }
@@ -5989,6 +6020,44 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	kvm_apic_update_tmr(vcpu, tmr);
 }
 
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	kvm_x86_ops->tlb_flush(vcpu);
+}
+
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+{
+	struct page *page = NULL;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return;
+
+	if (!kvm_x86_ops->set_apic_access_page_addr)
+		return;
+
+	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
+
+	/*
+	 * Do not pin apic access page in memory, the MMU notifier
+	 * will call us again if it is migrated or swapped out.
+	 */
+	put_page(page);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+					   unsigned long address)
+{
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 /*
  * Returns 1 to let __vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -6018,7 +6087,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			kvm_x86_ops->tlb_flush(vcpu);
+			kvm_vcpu_flush_tlb(vcpu);
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
@@ -6049,6 +6118,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
 			vcpu_scan_ioapic(vcpu);
+		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
+			kvm_vcpu_reload_apic_access_page(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -6934,7 +7005,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
 	kvm_rip_write(vcpu, 0);
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -6945,7 +7016,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	ret = kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable();
 	if (ret != 0)
 		return ret;
 
@@ -6954,7 +7025,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (!stable && vcpu->cpu == smp_processor_id())
-				set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			if (stable && vcpu->arch.last_host_tsc > local_tsc) {
 				backwards_tsc = true;
 				if (vcpu->arch.last_host_tsc > max_tsc)
@@ -7008,8 +7079,7 @@ int kvm_arch_hardware_enable(void *garbage)
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;
 				vcpu->arch.last_host_tsc = local_tsc;
-				set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
-					&vcpu->requests);
+				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 			}
 
 			/*
@@ -7026,10 +7096,10 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
-	kvm_x86_ops->hardware_disable(garbage);
-	drop_user_return_notifiers(garbage);
+	kvm_x86_ops->hardware_disable();
+	drop_user_return_notifiers();
 }
 
 int kvm_arch_hardware_setup(void)
@@ -7146,6 +7216,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvm_x86_ops->sched_in(vcpu, cpu);
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	if (type)
@@ -7237,10 +7312,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
-	if (kvm->arch.apic_access_page)
-		put_page(kvm->arch.apic_access_page);
-	if (kvm->arch.ept_identity_pagetable)
-		put_page(kvm->arch.ept_identity_pagetable);
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
@@ -7643,3 +7714,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);