Merge tag 'kvm-x86-fixes-6.7-rcN' of https://github.com/kvm-x86/linux into kvm-master

KVM fixes for 6.7-rcN:

 - When checking if a _running_ vCPU is "in-kernel", i.e. running at CPL0,
   get the CPL directly instead of relying on preempted_in_kernel, which
   is valid if and only if the vCPU was preempted, i.e. NOT running.

 - Set .owner for various KVM file_operations so that files refcount the
   KVM module until KVM is done executing _all_ code, including the last
   few instructions of kvm_put_kvm().  And then revert the misguided
   attempt to rely on "struct kvm" refcounts to pin KVM-the-module.

 - Fix a benign "return void" that was recently introduced.

3 files changed, 15 insertions, 13 deletions

diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index ee8c4c3496ed..eea6ea7f14af 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -182,6 +182,7 @@ static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations mmu_rmaps_stat_fops = {
+	.owner		= THIS_MODULE,
 	.open		= kvm_mmu_rmaps_stat_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c924075f6f1..1a3aaa7dafae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5518,8 +5518,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
-					     sizeof(guest_xsave->region));
+	kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+				      sizeof(guest_xsave->region));
 }
 
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -13031,7 +13031,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_state_protected)
 		return true;
 
-	return vcpu->arch.preempted_in_kernel;
+	if (vcpu != kvm_get_running_vcpu())
+		return vcpu->arch.preempted_in_kernel;
+
+	return static_call(kvm_x86_get_cpl)(vcpu) == 0;
 }
 
 unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 486800a7024b..3b1b9e8dd70c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -115,8 +115,6 @@ EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
 static const struct file_operations stat_fops_per_vm;
 
-static struct file_operations kvm_chardev_ops;
-
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
 #ifdef CONFIG_KVM_COMPAT
@@ -1157,9 +1155,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
-	__module_get(kvm_chardev_ops.owner);
-
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1279,7 +1274,6 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
-	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -1348,7 +1342,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	preempt_notifier_dec();
 	hardware_disable_all();
 	mmdrop(mm);
-	module_put(kvm_chardev_ops.owner);
 }
 
 void kvm_get_kvm(struct kvm *kvm)
@@ -3887,7 +3880,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_vcpu_fops = {
+static struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.mmap           = kvm_vcpu_mmap,
@@ -4081,6 +4074,7 @@ static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vcpu_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vcpu_stats_read,
 	.release = kvm_vcpu_stats_release,
 	.llseek = noop_llseek,
@@ -4431,7 +4425,7 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_device_fops = {
+static struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
 	.release = kvm_device_release,
 	KVM_COMPAT(kvm_device_ioctl),
@@ -4759,6 +4753,7 @@ static int kvm_vm_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vm_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vm_stats_read,
 	.release = kvm_vm_stats_release,
 	.llseek = noop_llseek,
@@ -5060,7 +5055,7 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 }
 #endif
 
-static const struct file_operations kvm_vm_fops = {
+static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 	.llseek		= noop_llseek,
@@ -6095,6 +6090,9 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 		goto err_async_pf;
 
 	kvm_chardev_ops.owner = module;
+	kvm_vm_fops.owner = module;
+	kvm_vcpu_fops.owner = module;
+	kvm_device_fops.owner = module;
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;