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

Pull vkm fixes from Paolo Bonzini:
 "s390:

   - fix a lot of small bugs and races

  x86:

   - fix missing locking related to KVM_CAP_MOVE_ENC_CONTEXT_FROM

   - warn on creating a new page table that is the child of an invalid
     one, and limit damage before it's too late

   - disable use of INVLPGA when NPT is enabled, because it doesn't seem
     to flush TLBs correctly"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (26 commits)
  KVM: x86/mmu: WARN and clear role.invalid when creating a child shadow page
  KVM: SVM: Serialize accesses to the owner and mirror list with separate lock
  KVM: SVM: make svm_flush_tlb_gva do a full asid flush if NPT enabled
  KVM: s390: Fix cleanup in kvm_s390_pv_create_cpu()
  KVM: s390: Fix ordering when adding to SCA
  KVM: s390: Return -EINTR if a signal is pending while faulting-in
  KVM: s390: Free the mmu cache when kvm_arch_vcpu_create() fails
  KVM: s390: ucontrol: Add missing locking around gmap_remove_child()
  KVM: s390: cmma: Fix dirty tracking when removing memslot
  KVM: s390: Fix race in __do_essa()
  KVM: s390: Fix leaking of PGM_ADDRESSING to userspace
  KVM: s390: ucontrol: Fix sca_clear_ext_call()
  KVM: s390: Fix overclearing ESCA in case of error
  KVM: s390: Fix kvm_s390_vcpu_unsetup_cmma()
  KVM: s390: Do not free SCA if it was not allocated
  KVM: s390: Fix unlikely NULL gmap dereference
  s390/vfio_ccw: Implement a crw lock
  s390/vfio_ccw: Selectively expand io_mutex
  s390/vfio_ccw: Move cp cleanup out of not operational
  s390/vfio_ccw: Cancel existing workqueues
  ...

25 files changed, 378 insertions, 142 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index c172f9b212d1..b4182ca4435f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -440,6 +440,7 @@ struct kvm_vcpu_arch {
 	bool skey_enabled;
 	/* Indicator if the access registers have been loaded from guest */
 	bool acrs_loaded;
+	bool initialized;
 	struct kvm_s390_pv_vcpu pv;
 	union diag318_info diag318_info;
 	struct kvm_s390_mmu_cache *mc;
diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index ed4259d17629..3f2d6e8902d7 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -755,13 +755,15 @@ int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gf
 	return rc;
 }
 
-int dat_reset_reference_bit(union asce asce, gfn_t gfn)
+int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey)
 {
 	union pgste pgste, old;
 	union crste *crstep;
 	union pte *ptep;
 	int rc;
 
+	skey->skey = 0;
+
 	rc = dat_entry_walk(NULL, gfn, asce, DAT_WALK_ANY, TABLE_TYPE_PAGE_TABLE, &crstep, &ptep);
 	if (rc)
 		return rc;
@@ -771,21 +773,23 @@ int dat_reset_reference_bit(union asce asce, gfn_t gfn)
 
 		if (!crste.h.fc || !crste.s.fc1.pr)
 			return 0;
-		return page_reset_referenced(large_crste_to_phys(*crstep, gfn));
+		skey->skey = page_reset_referenced(large_crste_to_phys(*crstep, gfn)) << 1;
+		return 0;
 	}
 	old = pgste_get_lock(ptep);
 	pgste = old;
 
 	if (!ptep->h.i) {
-		rc = page_reset_referenced(pte_origin(*ptep));
-		pgste.hr = rc >> 1;
+		skey->skey = page_reset_referenced(pte_origin(*ptep)) << 1;
+		pgste.hr = skey->r;
 	}
-	rc |= (pgste.gr << 1) | pgste.gc;
+	skey->r |= pgste.gr;
+	skey->c |= pgste.gc;
 	pgste.gr = 0;
 
 	dat_update_ptep_sd(old, pgste, ptep);
 	pgste_set_unlock(ptep, pgste);
-	return rc;
+	return 0;
 }
 
 static long dat_reset_skeys_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
@@ -846,6 +850,7 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal
 	struct slot_priv *p = walk->priv;
 	union crste dummy = { .val = p->token };
 	union pte new_pte, pte = READ_ONCE(*ptep);
+	union pgste pgste;
 
 	new_pte = _PTE_TOK(dummy.tok.type, dummy.tok.par);
 
@@ -853,7 +858,11 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal
 	if (pte.val == new_pte.val)
 		return 0;
 
-	dat_ptep_xchg(ptep, new_pte, gfn, walk->asce, false);
+	pgste = pgste_get_lock(ptep);
+	pgste = __dat_ptep_xchg(ptep, pgste, new_pte, gfn, walk->asce, false);
+	pgste.cmma_d = 0;
+	pgste_set_unlock(ptep, pgste);
+
 	return 0;
 }
 
diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h
index fad605305e05..141ee7b9f019 100644
--- a/arch/s390/kvm/dat.h
+++ b/arch/s390/kvm/dat.h
@@ -537,7 +537,7 @@ int dat_set_storage_key(struct kvm_s390_mmu_cache *mc, union asce asce, gfn_t gf
 			union skey skey, bool nq);
 int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gfn_t gfn,
 			     union skey skey, union skey *oldkey, bool nq, bool mr, bool mc);
-int dat_reset_reference_bit(union asce asce, gfn_t gfn);
+int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey);
 long dat_reset_skeys(union asce asce, gfn_t start);
 
 unsigned long dat_get_ptval(struct page_table *table, struct ptval_param param);
diff --git a/arch/s390/kvm/faultin.c b/arch/s390/kvm/faultin.c
index fee80047bd94..3cc45f7f5b2d 100644
--- a/arch/s390/kvm/faultin.c
+++ b/arch/s390/kvm/faultin.c
@@ -91,9 +91,9 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa
 		/* Access outside memory, addressing exception. */
 		if (is_noslot_pfn(f->pfn))
 			return PGM_ADDRESSING;
-		/* Signal pending: try again. */
-		if (f->pfn == KVM_PFN_ERR_SIGPENDING)
-			return -EAGAIN;
+		/* Fatal signal pending: bail out. */
+		if (is_sigpending_pfn(f->pfn))
+			return -EINTR;
 		/* Check if it's read-only memory; don't try to actually handle that case. */
 		if (f->pfn == KVM_PFN_ERR_RO_FAULT)
 			return -EOPNOTSUPP;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 7514d9e2403c..8f24bcd1a6d3 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -45,13 +45,16 @@ static struct kvm_s390_gib *gib;
 static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
 	struct esca_block *sca = vcpu->kvm->arch.sca;
-	union esca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	union esca_sigp_ctrl sigp_ctrl;
 
 	if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND))
 		return 0;
+	if (kvm_is_ucontrol(vcpu->kvm))
+		return 0;
 
 	BUG_ON(!kvm_s390_use_sca_entries());
 
+	sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 	if (src_id)
 		*src_id = sigp_ctrl.scn;
 
@@ -60,13 +63,16 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 
 static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 {
-	struct esca_block *sca = vcpu->kvm->arch.sca;
-	union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 	union esca_sigp_ctrl old_val, new_val = {.scn = src_id, .c = 1};
+	struct esca_block *sca = vcpu->kvm->arch.sca;
+	union esca_sigp_ctrl *sigp_ctrl;
 	int expect, rc;
 
 	BUG_ON(!kvm_s390_use_sca_entries());
+	if (kvm_is_ucontrol(vcpu->kvm))
+		return -EINVAL;
 
+	sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 	old_val = READ_ONCE(*sigp_ctrl);
 	old_val.c = 0;
 
@@ -84,10 +90,13 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 {
 	struct esca_block *sca = vcpu->kvm->arch.sca;
-	union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	union esca_sigp_ctrl *sigp_ctrl;
 
-	if (!kvm_s390_use_sca_entries())
+	if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized || kvm_is_ucontrol(vcpu->kvm))
 		return;
+
+	/* Initialize after the above check, to prevent going out of bounds */
+	sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
 
 	WRITE_ONCE(sigp_ctrl->value, 0);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 150b5dd2170e..518a69c55e85 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -571,7 +571,7 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op
 	switch (op) {
 	case KVM_S390_KEYOP_SSKE:
 		r = dat_cond_set_storage_key(mc, asce, gfn, skey, &skey, 0, 0, 0);
-		if (r >= 0)
+		if (r == 0 || r == 1)
 			return skey.skey;
 		break;
 	case KVM_S390_KEYOP_ISKE:
@@ -580,14 +580,14 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op
 			return skey.skey;
 		break;
 	case KVM_S390_KEYOP_RRBE:
-		r = dat_reset_reference_bit(asce, gfn);
-		if (r > 0)
-			return r << 1;
+		r = dat_reset_reference_bit(asce, gfn, &skey);
+		if (!r)
+			return skey.skey;
 		break;
 	default:
 		return -EINVAL;
 	}
-	return r;
+	return r > 0 ? -EFAULT : r;
 }
 
 /* Section: device related */
@@ -1219,8 +1219,8 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 
 /*
  * Must be called with kvm->srcu held to avoid races on memslots, and with
- * kvm->slots_lock to avoid races with ourselves, kvm_s390_vm_stop_migration(),
- * and kvm_s390_get_cmma_bits().
+ * kvm->slots_arch_lock to avoid races with ourselves,
+ * kvm_s390_vm_stop_migration(), and kvm_s390_get_cmma_bits().
  */
 static int kvm_s390_vm_start_migration(struct kvm *kvm)
 {
@@ -1265,7 +1265,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 }
 
 /*
- * Must be called with kvm->slots_lock to avoid races with ourselves,
+ * Must be called with kvm->slots_arch_lock to avoid races with ourselves,
  * kvm_s390_vm_start_migration() and kvm_s390_get_cmma_bits().
  */
 static int kvm_s390_vm_stop_migration(struct kvm *kvm)
@@ -1300,7 +1300,9 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 {
 	int res = -ENXIO;
 
-	mutex_lock(&kvm->slots_lock);
+	guard(srcu)(&kvm->srcu);
+	guard(mutex)(&kvm->slots_arch_lock);
+
 	switch (attr->attr) {
 	case KVM_S390_VM_MIGRATION_START:
 		res = kvm_s390_vm_start_migration(kvm);
@@ -1311,7 +1313,6 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 	default:
 		break;
 	}
-	mutex_unlock(&kvm->slots_lock);
 
 	return res;
 }
@@ -2214,7 +2215,7 @@ static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	}
 
 	kvfree(keys);
-	return r;
+	return r <= 0 ? r : -EFAULT;
 }
 
 static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
@@ -2276,7 +2277,7 @@ static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	kvm_s390_free_mmu_cache(mc);
 out:
 	kvfree(keys);
-	return r;
+	return r <= 0 ? r : -EFAULT;
 }
 
 /*
@@ -2386,7 +2387,7 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm,
 
 	set_bit(GMAP_FLAG_USES_CMM, &kvm->arch.gmap->flags);
 
-	return r;
+	return r <= 0 ? r : -EFAULT;
 }
 
 /**
@@ -2934,6 +2935,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	case KVM_S390_INTERRUPT: {
 		struct kvm_s390_interrupt s390int;
 
+		r = -EINVAL;
+		if (kvm_is_ucontrol(kvm))
+			break;
 		r = -EFAULT;
 		if (copy_from_user(&s390int, argp, sizeof(s390int)))
 			break;
@@ -2998,9 +3002,8 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
-		mutex_lock(&kvm->slots_lock);
-		r = kvm_s390_get_cmma_bits(kvm, &args);
-		mutex_unlock(&kvm->slots_lock);
+		scoped_guard(mutex, &kvm->slots_arch_lock)
+			r = kvm_s390_get_cmma_bits(kvm, &args);
 		if (!r) {
 			r = copy_to_user(argp, &args, sizeof(args));
 			if (r)
@@ -3014,9 +3017,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
-		mutex_lock(&kvm->slots_lock);
+		mutex_lock(&kvm->slots_arch_lock);
 		r = kvm_s390_set_cmma_bits(kvm, &args);
-		mutex_unlock(&kvm->slots_lock);
+		mutex_unlock(&kvm->slots_arch_lock);
 		break;
 	}
 	case KVM_S390_PV_COMMAND: {
@@ -3247,7 +3250,8 @@ static void kvm_s390_crypto_init(struct kvm *kvm)
 
 static void sca_dispose(struct kvm *kvm)
 {
-	free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca));
+	if (kvm->arch.sca)
+		free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca));
 	kvm->arch.sca = NULL;
 }
 
@@ -3461,7 +3465,7 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct esca_block *sca = vcpu->kvm->arch.sca;
 
-	if (!kvm_s390_use_sca_entries())
+	if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized)
 		return;
 
 	clear_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn);
@@ -3481,8 +3485,8 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu)
 	if (!kvm_s390_use_sca_entries())
 		return;
 
+	WRITE_ONCE(sca->cpu[vcpu->vcpu_id].sda, virt_to_phys(vcpu->arch.sie_block));
 	set_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn);
-	sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block);
 }
 
 static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
@@ -3613,6 +3617,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0 ||
 	    vcpu->kvm->arch.user_operexec)
 		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
+
+	/* Pairs with smp_load_acquire() in kvm_arch_vcpu_ioctl_run() and kvm_arch_vcpu_ioctl() */
+	smp_store_release(&vcpu->arch.initialized, true);
 }
 
 static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr)
@@ -3674,7 +3681,8 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
 
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
 {
-	free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo));
+	if (vcpu->arch.sie_block->cbrlo)
+		free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo));
 	vcpu->arch.sie_block->cbrlo = 0;
 }
 
@@ -3792,21 +3800,21 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 	return 0;
 }
 
+DEFINE_FREE(sie_page, struct sie_page *, if (_T) free_page((unsigned long)(_T)))
+
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	struct sie_page *sie_page;
+	struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL;
+	struct sie_page *sie_page __free(sie_page) = NULL;
 	int rc;
 
 	BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
-	vcpu->arch.mc = kvm_s390_new_mmu_cache();
-	if (!vcpu->arch.mc)
+	mc = kvm_s390_new_mmu_cache();
+	if (!mc)
 		return -ENOMEM;
 	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT);
-	if (!sie_page) {
-		kvm_s390_free_mmu_cache(vcpu->arch.mc);
-		vcpu->arch.mc = NULL;
+	if (!sie_page)
 		return -ENOMEM;
-	}
 
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = virt_to_phys(&sie_page->itdb);
@@ -3848,10 +3856,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
 
 	if (kvm_is_ucontrol(vcpu->kvm)) {
-		rc = -ENOMEM;
 		vcpu->arch.gmap = gmap_new_child(vcpu->kvm->arch.gmap, -1UL);
 		if (!vcpu->arch.gmap)
-			goto out_free_sie_block;
+			return -ENOMEM;
 	}
 
 	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p",
@@ -3859,20 +3866,19 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
 
 	rc = kvm_s390_vcpu_setup(vcpu);
-	if (rc)
-		goto out_ucontrol_uninit;
+	if (rc) {
+		if (kvm_is_ucontrol(vcpu->kvm)) {
+			scoped_guard(spinlock, &vcpu->kvm->arch.gmap->children_lock)
+				gmap_remove_child(vcpu->arch.gmap);
+			vcpu->arch.gmap = gmap_put(vcpu->arch.gmap);
+		}
+		return rc;
+	}
 
+	vcpu->arch.mc = no_free_ptr(mc);
+	sie_page = NULL;
 	kvm_s390_update_topology_change_report(vcpu->kvm, 1);
 	return 0;
-
-out_ucontrol_uninit:
-	if (kvm_is_ucontrol(vcpu->kvm)) {
-		gmap_remove_child(vcpu->arch.gmap);
-		vcpu->arch.gmap = gmap_put(vcpu->arch.gmap);
-	}
-out_free_sie_block:
-	free_page((unsigned long)(vcpu->arch.sie_block));
-	return rc;
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
@@ -5039,6 +5045,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	    kvm_run->kvm_dirty_regs & ~KVM_SYNC_S390_VALID_FIELDS)
 		return -EINVAL;
 
+	/* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */
+	if (!smp_load_acquire(&vcpu->arch.initialized))
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 
 	if (guestdbg_exit_pending(vcpu)) {
@@ -5447,6 +5457,8 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl,
 		struct kvm_s390_interrupt s390int;
 		struct kvm_s390_irq s390irq = {};
 
+		if (kvm_is_ucontrol(vcpu->kvm))
+			return -EINVAL;
 		if (copy_from_user(&s390int, argp, sizeof(s390int)))
 			return -EFAULT;
 		if (s390int_to_s390irq(&s390int, &s390irq))
@@ -5523,6 +5535,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	long r;
 	u16 rc, rrc;
 
+	/* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */
+	if (!smp_load_acquire(&vcpu->arch.initialized))
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 
 	switch (ioctl) {
@@ -5794,14 +5810,30 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+static long cmma_d_count_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
+{
+	union pgste pgste;
+
+	pgste = pgste_get_lock(ptep);
+	if (pgste.cmma_d) {
+		pgste.cmma_d = 0;
+		atomic64_dec(walk->priv);
+	}
+	pgste_set_unlock(ptep, pgste);
+	return 0;
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	struct kvm_s390_mmu_cache *mc = NULL;
+	const struct dat_walk_ops ops = { .pte_entry = cmma_d_count_pte, };
+	struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL;
 	int rc = 0;
 
+	guard(mutex)(&kvm->slots_arch_lock);
+
 	if (change == KVM_MR_FLAGS_ONLY)
 		return;
 
@@ -5812,6 +5844,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	}
 
 	scoped_guard(write_lock, &kvm->mmu_lock) {
+		if (kvm->arch.migration_mode && kvm->arch.use_cmma && old) {
+			_dat_walk_gfn_range(old->base_gfn, old->base_gfn + old->npages,
+					    kvm->arch.gmap->asce, &ops, DAT_WALK_IGN_HOLES,
+					    &kvm->arch.cmma_dirty_pages);
+		}
+
 		switch (change) {
 		case KVM_MR_DELETE:
 			rc = dat_delete_slot(mc, kvm->arch.gmap->asce, old->base_gfn, old->npages);
@@ -5833,7 +5871,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 out:
 	if (rc)
 		pr_warn("failed to commit memory region\n");
-	kvm_s390_free_mmu_cache(mc);
 	return;
 }
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ad0ddc433a73..b1ba24c346ef 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -289,6 +289,7 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 static int handle_rrbe(struct kvm_vcpu *vcpu)
 {
 	unsigned long gaddr;
+	union skey skey;
 	int reg1, reg2;
 	int rc;
 
@@ -307,12 +308,12 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
 	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
 	scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
-		rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr));
+		rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr), &skey);
 	if (rc > 0)
 		return kvm_s390_inject_program_int(vcpu, rc);
 	if (rc < 0)
 		return rc;
-	kvm_s390_set_psw_cc(vcpu, rc);
+	kvm_s390_set_psw_cc(vcpu, (skey.skey >> 1) & 3);
 	return 0;
 }
 
@@ -1260,8 +1261,9 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 		/* Retry the ESSA instruction */
 		kvm_s390_retry_instr(vcpu);
 	} else {
-		scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
-			i = __do_essa(vcpu, orc);
+		scoped_guard(mutex, &vcpu->kvm->slots_arch_lock)
+			scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
+				i = __do_essa(vcpu, orc);
 		if (i < 0)
 			return i;
 		/* Account for the possible extra cbrl entry */
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 1beacc841ca8..b02e0159d3cd 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -244,6 +244,24 @@ static void kvm_s390_clear_pv_state(struct kvm *kvm)
 	kvm->arch.pv.stor_var = NULL;
 }
 
+static void kvm_s390_pv_dispose_cpu(struct kvm_vcpu *vcpu, bool free_stor_base)
+{
+	if (free_stor_base)
+		free_pages(vcpu->arch.pv.stor_base, get_order(uv_info.guest_cpu_stor_len));
+	free_page((unsigned long)sida_addr(vcpu->arch.sie_block));
+	vcpu->arch.sie_block->pv_handle_cpu = 0;
+	vcpu->arch.sie_block->pv_handle_config = 0;
+	memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv));
+	vcpu->arch.sie_block->sdf = 0;
+	/*
+	 * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0).
+	 * Use the reset value of gbea to avoid leaking the kernel pointer of
+	 * the just freed sida.
+	 */
+	vcpu->arch.sie_block->gbea = 1;
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+}
+
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 {
 	int cc;
@@ -258,24 +276,9 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 	WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc);
 
 	/* Intended memory leak for something that should never happen. */
-	if (!cc)
-		free_pages(vcpu->arch.pv.stor_base,
-			   get_order(uv_info.guest_cpu_stor_len));
-
-	free_page((unsigned long)sida_addr(vcpu->arch.sie_block));
-	vcpu->arch.sie_block->pv_handle_cpu = 0;
-	vcpu->arch.sie_block->pv_handle_config = 0;
-	memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv));
-	vcpu->arch.sie_block->sdf = 0;
-	/*
-	 * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0).
-	 * Use the reset value of gbea to avoid leaking the kernel pointer of
-	 * the just freed sida.
-	 */
-	vcpu->arch.sie_block->gbea = 1;
-	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+	kvm_s390_pv_dispose_cpu(vcpu, !cc);
 
-	return cc ? EIO : 0;
+	return cc ? -EIO : 0;
 }
 
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
@@ -319,9 +322,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 		     uvcb.header.rrc);
 
 	if (cc) {
-		u16 dummy;
-
-		kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy);
+		kvm_s390_pv_dispose_cpu(vcpu, true);
 		return -EIO;
 	}
 
@@ -809,7 +810,7 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
 			return -EAGAIN;
 	}
 
-	if (ret && ret != -EAGAIN)
+	if (ret && ret != -EAGAIN && ret != -EINTR)
 		KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
 			     uvcb.gaddr, *rc, *rrc);
 	return ret;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5f6c1ce9673b..6db5b5f79df9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1858,7 +1858,7 @@ struct kvm_x86_ops {
 	 * Can potentially get non-canonical addresses through INVLPGs, which
 	 * the implementation may choose to ignore if appropriate.
 	 */
-	void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr);
+	void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr, bool *full);
 
 	/*
 	 * Flush any TLB entries created by the guest.  Like tlb_flush_gva(),
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index fd4eb1e561f7..d8736b5dfcd3 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1974,6 +1974,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE];
 	int i, j, count;
 	gva_t gva;
+	bool full = false;
 
 	if (!tdp_enabled || !hv_vcpu)
 		return -EINVAL;
@@ -1982,7 +1983,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 
 	count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE);
 
-	for (i = 0; i < count; i++) {
+	for (i = 0; i < count && !full; i++) {
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
@@ -1991,11 +1992,11 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 		 * pages to flush.
 		 */
 		gva = entries[i] & PAGE_MASK;
-		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) {
+		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1 && !full; j++) {
 			if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu))
 				continue;
 
-			kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+			kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE, &full);
 		}
 
 		++vcpu->stat.tlb_flush;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 66e69d2a41b3..a61750f8e1e3 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2442,6 +2442,9 @@ static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct,
 	role.direct = direct;
 	role.passthrough = 0;
 
+	WARN_ON_ONCE(role.invalid);
+	role.invalid = 0;
+
 	/*
 	 * If the guest has 4-byte PTEs then that means it's using 32-bit,
 	 * 2-level, non-PAE paging. KVM shadows such guests with PAE paging
@@ -6652,7 +6655,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		if (is_noncanonical_invlpg_address(addr, vcpu))
 			return;
 
-		kvm_x86_call(flush_tlb_gva)(vcpu, addr);
+		kvm_x86_call(flush_tlb_gva)(vcpu, addr, NULL);
 	}
 
 	if (!mmu->sync_spte)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 944aaea6501f..0f0ea7896af5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -97,6 +97,8 @@ static u64 sev_supported_vmsa_features __ro_after_init;
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
+/* Protects kvm_sev_info's enc_context_owner, mirror_vms and mirror_entry.  */
+static DEFINE_MUTEX(sev_mirror_lock);
 unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned int max_sev_es_asid;
@@ -2018,7 +2020,6 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 	dst->asid = src->asid;
 	dst->handle = src->handle;
 	dst->pages_locked = src->pages_locked;
-	dst->enc_context_owner = src->enc_context_owner;
 	dst->es_active = src->es_active;
 	dst->vmsa_features = src->vmsa_features;
 
@@ -2026,11 +2027,12 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 	src->active = false;
 	src->handle = 0;
 	src->pages_locked = 0;
-	src->enc_context_owner = NULL;
 	src->es_active = false;
 
 	list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
 
+	mutex_lock(&sev_mirror_lock);
+
 	/*
 	 * If this VM has mirrors, "transfer" each mirror's refcount of the
 	 * source to the destination (this KVM).  The caller holds a reference
@@ -2047,12 +2049,15 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 	 * If this VM is a mirror, remove the old mirror from the owners list
 	 * and add the new mirror to the list.
 	 */
-	if (is_mirroring_enc_context(dst_kvm)) {
-		struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner);
+	if (is_mirroring_enc_context(src_kvm)) {
+		struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(src->enc_context_owner);
 
+		dst->enc_context_owner = src->enc_context_owner;
+		src->enc_context_owner = NULL;
 		list_del(&src->mirror_entry);
 		list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms);
 	}
+	mutex_unlock(&sev_mirror_lock);
 
 	kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) {
 		dst_svm = to_svm(dst_vcpu);
@@ -2871,11 +2876,14 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	 * disappear until we're done with it
 	 */
 	source_sev = to_kvm_sev_info(source_kvm);
-	kvm_get_kvm(source_kvm);
-	list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms);
 
 	/* Set enc_context_owner and copy its encryption context over */
+	mutex_lock(&sev_mirror_lock);
+	kvm_get_kvm(source_kvm);
+	list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms);
 	mirror_sev->enc_context_owner = source_kvm;
+	mutex_unlock(&sev_mirror_lock);
+
 	mirror_sev->active = true;
 	mirror_sev->asid = source_sev->asid;
 	mirror_sev->fd = source_sev->fd;
@@ -2963,11 +2971,19 @@ void sev_vm_destroy(struct kvm *kvm)
 	 * Note, mirror VMs don't support registering encrypted regions.
 	 */
 	if (is_mirroring_enc_context(kvm)) {
-		struct kvm *owner_kvm = sev->enc_context_owner;
+		struct kvm *owner_kvm;
 
-		mutex_lock(&owner_kvm->lock);
+		mutex_lock(&sev_mirror_lock);
+		owner_kvm = sev->enc_context_owner;
 		list_del(&sev->mirror_entry);
-		mutex_unlock(&owner_kvm->lock);
+		sev->enc_context_owner = NULL;
+
+		/*
+		 * The reference to owner_kvm cannot move after sev_mirror_lock is
+		 * released.  Release it before kvm_put_kvm() so that owner_kvm is
+		 * never destroyed inside sev_mirror_lock.
+		 */
+		mutex_unlock(&sev_mirror_lock);
 		kvm_put_kvm(owner_kvm);
 		return;
 	}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d0971685034b..60495447f0ca 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4227,18 +4227,31 @@ static void svm_flush_tlb_all(struct kvm_vcpu *vcpu)
 	svm_flush_tlb_asid(vcpu);
 }
 
-static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
+static void svm_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
+	kvm_register_mark_dirty(vcpu, VCPU_REG_ERAPS);
 
-	invlpga(gva, svm->vmcb->control.asid);
+	svm_flush_tlb_asid(vcpu);
 }
 
-static void svm_flush_tlb_guest(struct kvm_vcpu *vcpu)
+static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva, bool *full)
 {
-	kvm_register_mark_dirty(vcpu, VCPU_REG_ERAPS);
+	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm_flush_tlb_asid(vcpu);
+	/*
+	 * INVLPGA has had errata on Genoa and Turin, and even on older
+	 * generations there were reports of Windows BSODs if INVLPGA
+	 * was used for Hyper-V tlbflush.  Use it only for shadow paging
+	 * where it seems to be okay.
+	 */
+	if (!npt_enabled) {
+		invlpga(gva, svm->vmcb->control.asid);
+		return;
+	}
+
+	svm_flush_tlb_guest(vcpu);
+	if (full)
+		*full = true;
 }
 
 static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 716be21fba33..d63e5878988a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -109,6 +109,7 @@ struct kvm_sev_info {
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	u64 vmsa_features;
 	u16 ghcb_version;	/* Highest guest GHCB protocol version allowed */
+	/* The three fields below are protected by sev_mirror_lock */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
 	struct list_head mirror_vms; /* List of VMs mirroring */
 	struct list_head mirror_entry; /* Use as a list entry of mirrors */
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 83d9921277ea..f204a0fc0a57 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -535,12 +535,12 @@ static void vt_flush_tlb_current(struct kvm_vcpu *vcpu)
 	vmx_flush_tlb_current(vcpu);
 }
 
-static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full)
 {
 	if (is_td_vcpu(vcpu))
 		return;
 
-	vmx_flush_tlb_gva(vcpu, addr);
+	vmx_flush_tlb_gva(vcpu, addr, full);
 }
 
 static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cc75feec05da..b8d745f6fd22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3361,7 +3361,7 @@ void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
-void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full)
 {
 	/*
 	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 409858074246..17595d52985c 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -82,7 +82,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 bool vmx_get_if_flag(struct kvm_vcpu *vcpu);
 void vmx_flush_tlb_all(struct kvm_vcpu *vcpu);
 void vmx_flush_tlb_current(struct kvm_vcpu *vcpu);
-void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr);
+void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full);
 void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu);
 void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask);
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
index 420d89ba7f83..4aff0b58fa5d 100644
--- a/drivers/s390/cio/vfio_ccw_async.c
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/vfio.h>
+#include <linux/nospec.h>
 
 #include "vfio_ccw_private.h"
 
@@ -24,11 +25,20 @@ static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_to_user(buf, (void *)region + pos, count))
 		ret = -EFAULT;
 	else
 		ret = count;
+
+out_unlock:
 	mutex_unlock(&private->io_mutex);
 	return ret;
 }
@@ -48,6 +58,12 @@ static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
 	if (!mutex_trylock(&private->io_mutex))
 		return -EAGAIN;
 
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_from_user((void *)region + pos, buf, count)) {
 		ret = -EFAULT;
diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index 38c176cf6295..7708eb4d6de0 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/vfio.h>
 #include "vfio_ccw_private.h"
 
@@ -26,6 +27,13 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
 	if (cio_update_schib(sch)) {
@@ -85,19 +93,30 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_crw_region *region;
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 	int ret;
 
 	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
+	mutex_lock(&private->io_mutex);
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
+	region = private->region[i].data;
+
+	spin_lock_irqsave(&private->crw_lock, flags);
 	crw = list_first_entry_or_null(&private->crw,
 				       struct vfio_ccw_crw, next);
 
 	if (crw)
 		list_del(&crw->next);
 
-	mutex_lock(&private->io_mutex);
-	region = private->region[i].data;
+	/* Drop CRW lock while copying to userspace */
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 
 	if (crw)
 		memcpy(&region->crw, &crw->crw, sizeof(region->crw));
@@ -108,14 +127,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 		ret = count;
 
 	region->crw = 0;
-
-	mutex_unlock(&private->io_mutex);
-
 	kfree(crw);
 
 	/* Notify the guest if more CRWs are on our queue */
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+
+out:
+	mutex_unlock(&private->io_mutex);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 7561aa7d3e01..58722c4baa25 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -233,6 +233,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
 }
 
 #define idal_is_2k(_cp) (!(_cp)->orb.cmd.c64 || (_cp)->orb.cmd.i2k)
+#define get_idaw_size(_cp) ((_cp)->orb.cmd.c64 ? sizeof(u64) : sizeof(u32))
 
 /*
  * Helpers to operate ccwchain.
@@ -332,6 +333,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 		goto out_err;
 
 	list_add_tail(&chain->next, &cp->ccwchain_list);
+	cp->ccwchain_count++;
 
 	return chain;
 
@@ -376,11 +378,9 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
 static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 {
 	struct ccw1 *ccw = cp->guest_cp;
-	int cnt = 0;
-
-	do {
-		cnt++;
+	int cnt;
 
+	for (cnt = 1; cnt <= CCWCHAIN_LEN_MAX; cnt++, ccw++) {
 		/*
 		 * We want to keep counting if the current CCW has the
 		 * command-chaining flag enabled, or if it is a TIC CCW
@@ -390,15 +390,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 		 * after the TIC, depending on the results of its operation.
 		 */
 		if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
-			break;
-
-		ccw++;
-	} while (cnt < CCWCHAIN_LEN_MAX + 1);
-
-	if (cnt == CCWCHAIN_LEN_MAX + 1)
-		cnt = -EINVAL;
+			return cnt;
+	}
 
-	return cnt;
+	return -EINVAL;
 }
 
 static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
@@ -441,6 +436,10 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	if (len < 0)
 		return len;
 
+	/* Limit number of chains in a single channel program */
+	if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX)
+		return -EINVAL;
+
 	/* Need alloc a new chain for this one. */
 	chain = ccwchain_alloc(cp, len);
 	if (!chain)
@@ -455,9 +454,6 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	/* Loop for tics on this new chain. */
 	ret = ccwchain_loop_tic(chain, cp);
 
-	if (ret)
-		ccwchain_free(chain);
-
 	return ret;
 }
 
@@ -486,6 +482,23 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
 	return 0;
 }
 
+static int ccwchain_build_ccws(dma32_t cda, struct channel_program *cp)
+{
+	struct ccwchain *chain, *temp;
+	int ret;
+
+	ret = ccwchain_handle_ccw(cda, cp);
+
+	if (ret) {
+		/* Cleanup if an error occurred */
+		list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+			ccwchain_free(chain);
+		}
+	}
+
+	return ret;
+}
+
 static int ccwchain_fetch_tic(struct ccw1 *ccw,
 			      struct channel_program *cp)
 {
@@ -511,7 +524,8 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	dma64_t *idaws;
 	dma32_t *idaws_f1;
-	int idal_len = idaw_nr * sizeof(*idaws);
+	u64 first_idaw;
+	int idal_len = idaw_nr * get_idaw_size(cp);
 	int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
 	int idaw_mask = ~(idaw_size - 1);
 	int i, ret;
@@ -527,6 +541,18 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 			kfree(idaws);
 			return ERR_PTR(ret);
 		}
+
+		idaws_f1 = (dma32_t *)idaws;
+		if (cp->orb.cmd.c64)
+			first_idaw = dma64_to_u64(idaws[0]);
+		else
+			first_idaw = dma32_to_u32(idaws_f1[0]);
+
+		/* Unexpected mismatch from earlier read */
+		if (first_idaw != cp->guest_iova) {
+			kfree(idaws);
+			return ERR_PTR(-EINVAL);
+		}
 	} else {
 		/* Fabricate an IDAL based off CCW data address */
 		if (cp->orb.cmd.c64) {
@@ -568,7 +594,7 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 	struct vfio_device *vdev =
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	u64 iova;
-	int size = cp->orb.cmd.c64 ? sizeof(u64) : sizeof(u32);
+	int size = get_idaw_size(cp);
 	int ret;
 	int bytes = 1;
 
@@ -592,6 +618,9 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 		iova = dma32_to_u32(ccw->cda);
 	}
 
+	/* Save the read address for later */
+	cp->guest_iova = iova;
+
 	/* Format-1 IDAWs operate on 2K each */
 	if (!cp->orb.cmd.c64)
 		return idal_2k_nr_words((void *)iova, bytes);
@@ -731,11 +760,12 @@ int cp_init(struct channel_program *cp, union orb *orb)
 			vdev->dev,
 			"Prefetching channel program even though prefetch not specified in ORB");
 
+	cp->ccwchain_count = 0;
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
 
 	/* Build a ccwchain for the first CCW segment */
-	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
+	ret = ccwchain_build_ccws(orb->cmd.cpa, cp);
 
 	if (!ret)
 		cp->initialized = true;
@@ -947,17 +977,23 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
  */
 bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	int i;
 
 	if (!cp->initialized)
 		return false;
 
+	mutex_lock(&private->io_mutex);
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++)
-			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length))
+			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length)) {
+				mutex_unlock(&private->io_mutex);
 				return true;
+			}
 	}
+	mutex_unlock(&private->io_mutex);
 
 	return false;
 }
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index fc31eb699807..9af98ff12d67 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -23,11 +23,19 @@
  */
 #define CCWCHAIN_LEN_MAX	256
 
+/*
+ * Maximum number of chains
+ */
+#define CCWCHAIN_COUNT_MAX	16
+
 /**
  * struct channel_program - manage information for channel program
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @initialized: whether this instance is actually initialized
+ * @guest_cp: copy of guest channel program
+ * @ccwchain_count: number of channel program segments (linked by TIC)
+ * @guest_iova: first data address of a guest channel program
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -38,6 +46,8 @@ struct channel_program {
 	union orb orb;
 	bool initialized;
 	struct ccw1 *guest_cp;
+	unsigned int ccwchain_count;
+	u64 guest_iova;
 };
 
 int cp_init(struct channel_program *cp, union orb *orb);
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 1a095085bc72..ab6b518cc353 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -91,6 +91,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 
 	is_final = !(scsw_actl(&irb->scsw) &
 		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
+	mutex_lock(&private->io_mutex);
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
 		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
@@ -98,9 +99,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 			cp_is_finished = true;
 		}
 	}
-	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
-	mutex_unlock(&private->io_mutex);
 
 	/*
 	 * Reset to IDLE only if processing of a channel program
@@ -110,6 +109,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 	 */
 	if (cp_is_finished)
 		private->state = VFIO_CCW_STATE_IDLE;
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger);
@@ -118,11 +118,25 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 void vfio_ccw_crw_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
+	unsigned long flags;
 
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+}
+
+void vfio_ccw_notoper_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+
+	private = container_of(work, struct vfio_ccw_private, notoper_work);
+
+	mutex_lock(&private->io_mutex);
+	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
 }
 
 /*
@@ -275,6 +289,7 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 			       unsigned int rsid)
 {
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 
 	/*
 	 * If unable to allocate a CRW, just drop the event and
@@ -292,7 +307,9 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 	crw->crw.erc = erc;
 	crw->crw.rsid = rsid;
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_add_tail(&crw->next, &private->crw);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 	queue_work(vfio_ccw_work_q, &private->crw_work);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4d7988ea47ef..5fd94e9d5c61 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -170,8 +170,8 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
 
-	/* This is usually handled during CLOSE event */
-	cp_free(&private->cp);
+	/* This routine could be called from IRQ context, so defer */
+	queue_work(vfio_ccw_work_q, &private->notoper_work);
 }
 
 /*
@@ -410,7 +410,11 @@ static void fsm_close(struct vfio_ccw_private *private,
 
 	private->state = VFIO_CCW_STATE_STANDBY;
 	spin_unlock_irq(&sch->lock);
+
+	mutex_lock(&private->io_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
+
 	return;
 
 err_unlock:
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 45ec722d25ea..5ce91285c7d5 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -54,6 +54,8 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
+	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
+	spin_lock_init(&private->crw_lock);
 
 	private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
 	if (!private->cp.guest_cp)
@@ -130,11 +132,28 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 	struct vfio_ccw_crw *crw, *temp;
+	unsigned long flags;
 
+	/*
+	 * Ensure these work items are fully drained, so none can
+	 * fire after being released.
+	 *
+	 * notoper_work should have nothing to do here, because only
+	 * open devices could have channel_program resources in use
+	 * and those would be released during close. Nevertheless,
+	 * call flush here as well to be certain anything that was
+	 * allocated is freed.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
+
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_for_each_entry_safe(crw, temp, &private->crw, next) {
 		list_del(&crw->next);
 		kfree(crw);
 	}
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 
 	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
 	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
@@ -202,6 +221,19 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+
+	/*
+	 * Ensure these work items are drained, in the event the
+	 * device is re-opened instead of released.
+	 *
+	 * notoper_work needs to be given a chance to run if it
+	 * is queued, so any memory associated with the channel
+	 * program can be returned.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
+
 	vfio_ccw_unregister_dev_regions(private);
 }
 
@@ -243,6 +275,7 @@ static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev,
 		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->read(private, buf, count,
 							ppos);
 	}
@@ -295,6 +328,7 @@ static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev,
 		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->write(private, buf, count,
 							 ppos);
 	}
@@ -338,11 +372,8 @@ static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev,
 		    VFIO_CCW_NUM_REGIONS + private->num_regions)
 			return -EINVAL;
 
-		info->index = array_index_nospec(info->index,
-						 VFIO_CCW_NUM_REGIONS +
-						 private->num_regions);
-
 		i = info->index - VFIO_CCW_NUM_REGIONS;
+		i = array_index_nospec(i, private->num_regions);
 
 		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
 		info->size = private->region[i].size;
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 0501d4bbcdbd..3bd0171d38d0 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -88,7 +88,8 @@ struct vfio_ccw_parent {
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
  * @io_region: MMIO region to input/output I/O arguments/results
- * @io_mutex: protect against concurrent update of I/O regions
+ * @io_mutex: protect against concurrent update of I/O resources
+ *            and @cp lifecycle
  * @region: additional regions for other subchannel operations
  * @cmd_region: MMIO region for asynchronous I/O commands other than START
  * @schib_region: MMIO region for SCHIB information
@@ -97,11 +98,14 @@ struct vfio_ccw_parent {
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
+ * @crw_lock: serialization of CRW list information
+ * @crw: list of Channel Report Word elements
  * @io_trigger: eventfd ctx for signaling userspace I/O results
  * @crw_trigger: eventfd ctx for signaling userspace CRW information
  * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
  * @crw_work: work for deferral process of CRW handling
+ * @notoper_work: work for deferred processing in not-operational state
  */
 struct vfio_ccw_private {
 	struct vfio_device vdev;
@@ -118,6 +122,8 @@ struct vfio_ccw_private {
 	struct channel_program	cp;
 	struct irb		irb;
 	union scsw		scsw;
+
+	spinlock_t		crw_lock;
 	struct list_head	crw;
 
 	struct eventfd_ctx	*io_trigger;
@@ -125,11 +131,13 @@ struct vfio_ccw_private {
 	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
+	struct work_struct	notoper_work;
 } __aligned(8);
 
 int vfio_ccw_sch_quiesce(struct subchannel *sch);
 void vfio_ccw_sch_io_todo(struct work_struct *work);
 void vfio_ccw_crw_todo(struct work_struct *work);
+void vfio_ccw_notoper_todo(struct work_struct *work);
 
 extern struct mdev_driver vfio_ccw_mdev_driver;