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

Pull kvm fixes from Paolo Bonzini:
 "Generic:

   - 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.

  ARM:

   - Do not redo the mapping of vLPIs, if they have already been mapped

  s390:

   - Do not leave bits behind in PTEs

   - Properly catch page invalidations that affect the prefix of a
     nested guest

  x86:

   - 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).

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

  Selftests:

   - Makefile tweak for dependency generation

   - '-Wformat' fix"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: SVM: Update EFER software model on CR0 trap for SEV-ES
  KVM: selftests: add -MP to CFLAGS
  KVM: selftests: Actually print out magic token in NX hugepages skip message
  KVM: x86: Remove 'return void' expression for 'void function'
  Revert "KVM: Prevent module exit until all VMs are freed"
  KVM: Set file_operations.owner appropriately for all such structures
  KVM: x86: Get CPL directly when checking if loaded vCPU is in kernel mode
  KVM: arm64: GICv4: Do not perform a map to a mapped vLPI
  KVM: s390/mm: Properly reset no-dat
  KVM: s390: vsie: fix wrong VIR 37 when MSO is used

arch/arm64/kvm/vgic/vgic-v4.c

@@ -436,6 +436,10 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 	if (ret)
 		goto out;
 
+	/* Silently exit if the vLPI is already mapped */
+	if (irq->hw)
+		goto out;
+
 	/*
 	 * Emit the mapping request. If it fails, the ITS probably
 	 * isn't v4 compatible, so let's silently bail out. Holding

arch/s390/kvm/vsie.c

@@ -587,10 +587,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 
 	if (!gmap_is_shadow(gmap))
 		return;
-	if (start >= 1UL << 31)
-		/* We are only interested in prefix pages */
-		return;
-
 	/*
 	 * Only new shadow blocks are added to the list during runtime,
 	 * therefore we can safely reference them all the time.

arch/s390/mm/pgtable.c

@@ -756,7 +756,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 		pte_clear(mm, addr, ptep);
 	}
 	if (reset)
-		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }

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,

arch/x86/kvm/svm/svm.c

@@ -1855,14 +1855,16 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	bool old_paging = is_paging(vcpu);
 
 #ifdef CONFIG_X86_64
-	if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) {
+	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer |= EFER_LMA;
+			if (!vcpu->arch.guest_state_protected)
 				svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
 		}
 
 		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer &= ~EFER_LMA;
+			if (!vcpu->arch.guest_state_protected)
 				svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
 		}
 	}

arch/x86/kvm/x86.c

@@ -5518,7 +5518,7 @@ 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,
+	kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
 				      sizeof(guest_xsave->region));
 }
 
@@ -13031,7 +13031,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_state_protected)
 		return true;
 
+	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)

tools/testing/selftests/kvm/Makefile

@@ -224,7 +224,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD\
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP \
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \

tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c

@@ -259,7 +259,7 @@ int main(int argc, char **argv)
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
 		       "This test must be run with the magic token %d.\n"
 		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.");
+		       "also handles environment setup for the test.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);

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 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 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;