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

Pull KVM leftovers from Radim Krčmář:
 "This is a combination of two pull requests for 4.7-rc8 that were not
  merged due to looking hairy.  I have changed the tag message to focus
  on circumstances of contained reverts as they were likely the reason
  behind rejection.

  This merge introduces three patches that are later reverted,

   - Switching of MSR_TSC_AUX in SVM was thought to cause a host
     misbehavior, but it was later cleared of those doubts and the patch
     moved code to a hot path, so we reverted it.  That patch also
     needed a fix for 32 bit builds and both were reverted in one go.

   - Al Viro noticed that a fix for a leak in an error path was not
     valid with the given API and provided a better fix, so the original
     patch was reverted.

  Then there are two VMX fixes that move code around because VMCS was
  not accessed between vcpu_load() and vcpu_put(), a simple ARM VHE fix,
  and two one-liners for PML and MTRR"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  arm64: KVM: VHE: Context switch MDSCR_EL1
  KVM: VMX: handle PML full VMEXIT that occurs during event delivery
  Revert "KVM: SVM: fix trashing of MSR_TSC_AUX"
  KVM: SVM: do not set MSR_TSC_AUX on 32-bit builds
  KVM: don't use anon_inode_getfd() before possible failures
  Revert "KVM: release anon file in failure path of vm creation"
  KVM: release anon file in failure path of vm creation
  KVM: nVMX: Fix memory corruption when using VMCS shadowing
  kvm: vmx: ensure VMCS is current while enabling PML
  KVM: SVM: fix trashing of MSR_TSC_AUX
  KVM: MTRR: fix kvm_mtrr_check_gfn_range_consistency page fault

arch/arm64/kvm/hyp/sysreg-sr.c

@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
- * guest must save everything.
+ * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
+ * pstate, and guest must save everything.
  */
 
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -37,6 +37,7 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
@@ -61,7 +62,6 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
 	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
@@ -90,6 +90,7 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
 	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
@@ -114,7 +115,6 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
 	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],		mdscr_el1);
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);

arch/x86/kvm/mtrr.c

@@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
 
 	iter->fixed = false;
 	iter->start_max = iter->start;
+	iter->range = NULL;
 	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
 
 	__mtrr_lookup_var_next(iter);

arch/x86/kvm/vmx.c

@@ -4979,6 +4979,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
+	if (enable_pml) {
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	return 0;
 }
 
@@ -7937,22 +7943,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
-	struct page *pml_pg;
-
-	pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!pml_pg)
-		return -ENOMEM;
-
-	vmx->pml_pg = pml_pg;
-
-	vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
-	return 0;
-}
-
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
 	if (vmx->pml_pg) {
@@ -8224,6 +8214,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8854,6 +8845,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8862,8 +8869,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
@@ -8885,14 +8891,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	err = -ENOMEM;
+
+	/*
+	 * If PML is turned on, failure on enabling PML just results in failure
+	 * of creating the vcpu, therefore we can simplify PML logic (by
+	 * avoiding dealing with cases, such as enabling PML partially on vcpus
+	 * for the guest, etc.
+	 */
+	if (enable_pml) {
+		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vmx->pml_pg)
+			goto uninit_vcpu;
+	}
+
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
 		     > PAGE_SIZE);
 
-	err = -ENOMEM;
-	if (!vmx->guest_msrs) {
-		goto uninit_vcpu;
-	}
+	if (!vmx->guest_msrs)
+		goto free_pml;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
@@ -8936,18 +8954,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.current_vmptr = -1ull;
 	vmx->nested.current_vmcs12 = NULL;
 
-	/*
-	 * If PML is turned on, failure on enabling PML just results in failure
-	 * of creating the vcpu, therefore we can simplify PML logic (by
-	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
-	 */
-	if (enable_pml) {
-		err = vmx_create_pml_buffer(vmx);
-		if (err)
-			goto free_vmcs;
-	}
-
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -8955,6 +8961,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
+free_pml:
+	vmx_destroy_pml_buffer(vmx);
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:

virt/kvm/kvm_main.c

@@ -148,6 +148,7 @@ int vcpu_load(struct kvm_vcpu *vcpu)
 	put_cpu();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vcpu_load);
 
 void vcpu_put(struct kvm_vcpu *vcpu)
 {
@@ -157,6 +158,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
 }
+EXPORT_SYMBOL_GPL(vcpu_put);
 
 static void ack_flush(void *_completed)
 {
@@ -3048,6 +3050,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
 	struct kvm *kvm;
+	struct file *file;
 
 	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
@@ -3059,17 +3062,25 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return r;
 	}
 #endif
-	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
+	r = get_unused_fd_flags(O_CLOEXEC);
 	if (r < 0) {
 		kvm_put_kvm(kvm);
 		return r;
 	}
+	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	if (IS_ERR(file)) {
+		put_unused_fd(r);
+		kvm_put_kvm(kvm);
+		return PTR_ERR(file);
+	}
 
 	if (kvm_create_vm_debugfs(kvm, r) < 0) {
-		kvm_put_kvm(kvm);
+		put_unused_fd(r);
+		fput(file);
 		return -ENOMEM;
 	}
 
+	fd_install(r, file);
 	return r;
 }