KVM: s390: pv: add mmu_notifier

Add an mmu_notifier for protected VMs. The callback function is
triggered when the mm is torn down, and will attempt to convert all
protected vCPUs to non-protected. This allows the mm teardown to use
the destroy page UVC instead of export.

Also make KVM select CONFIG_MMU_NOTIFIER, needed to use mmu_notifiers.
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Nico Boehr <nrb@linux.ibm.com>
Link: https://lore.kernel.org/r/20220628135619.32410-10-imbrenda@linux.ibm.com
Message-Id: <20220628135619.32410-10-imbrenda@linux.ibm.com>
[frankja@linux.ibm.com: Conflict resolution for mmu_notifier.h include
and struct kvm_s390_pv]
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>

arch/s390/include/asm/kvm_host.h

@@ -20,6 +20,7 @@
 #include <linux/seqlock.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/mmu_notifier.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
 #include <asm/fpu/api.h>
@@ -929,6 +930,7 @@ struct kvm_s390_pv {
 	unsigned long stor_base;
 	void *stor_var;
 	bool dumping;
+	struct mmu_notifier mmu_notifier;
 };
 
 struct kvm_arch{

arch/s390/kvm/Kconfig

@@ -34,6 +34,7 @@ config KVM
 	select SRCU
 	select KVM_VFIO
 	select INTERVAL_TREE
+	select MMU_NOTIFIER
 	help
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/s390/kvm/kvm-s390.c

@@ -31,6 +31,7 @@
 #include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/pgtable.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
@@ -3198,6 +3199,15 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	 */
 	if (kvm_s390_pv_get_handle(kvm))
 		kvm_s390_pv_deinit_vm(kvm, &rc, &rrc);
+	/*
+	 * Remove the mmu notifier only when the whole KVM VM is torn down,
+	 * and only if one was registered to begin with. If the VM is
+	 * currently not protected, but has been previously been protected,
+	 * then it's possible that the notifier is still registered.
+	 */
+	if (kvm->arch.pv.mmu_notifier.ops)
+		mmu_notifier_unregister(&kvm->arch.pv.mmu_notifier, kvm->mm);
+
 	debug_unregister(kvm->arch.dbf);
 	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))

arch/s390/kvm/pv.c

@@ -15,6 +15,7 @@
 #include <asm/mman.h>
 #include <linux/pagewalk.h>
 #include <linux/sched/mm.h>
+#include <linux/mmu_notifier.h>
 #include "kvm-s390.h"
 
 static void kvm_s390_clear_pv_state(struct kvm *kvm)
@@ -188,6 +189,26 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	return -EIO;
 }
 
+static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription,
+					     struct mm_struct *mm)
+{
+	struct kvm *kvm = container_of(subscription, struct kvm, arch.pv.mmu_notifier);
+	u16 dummy;
+
+	/*
+	 * No locking is needed since this is the last thread of the last user of this
+	 * struct mm.
+	 * When the struct kvm gets deinitialized, this notifier is also
+	 * unregistered. This means that if this notifier runs, then the
+	 * struct kvm is still valid.
+	 */
+	kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
+}
+
+static const struct mmu_notifier_ops kvm_s390_pv_mmu_notifier_ops = {
+	.release = kvm_s390_pv_mmu_notifier_release,
+};
+
 int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 {
 	struct uv_cb_cgc uvcb = {
@@ -229,6 +250,11 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 		return -EIO;
 	}
 	kvm->arch.gmap->guest_handle = uvcb.guest_handle;
+	/* Add the notifier only once. No races because we hold kvm->lock */
+	if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) {
+		kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops;
+		mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm);
+	}
 	return 0;
 }