25 files changed, 332 insertions, 112 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d72989591223..b4c7c34069f8 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,6 +140,7 @@ config S390
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_VMALLOC
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6422618a4f75..86afcc6b56bf 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -387,6 +387,7 @@ CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 CONFIG_PCI=y
+CONFIG_PCI_IOV=y
 # CONFIG_PCIEASPM is not set
 CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
@@ -548,7 +549,7 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_RAW_DRIVER=m
 CONFIG_HANGCHECK_TIMER=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 371a529546aa..71b49ea5b058 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -377,6 +377,7 @@ CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 CONFIG_PCI=y
+CONFIG_PCI_IOV=y
 # CONFIG_PCIEASPM is not set
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
@@ -540,7 +541,7 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_RAW_DRIVER=m
 CONFIG_HANGCHECK_TIMER=m
diff --git a/arch/s390/include/asm/cpu_mcf.h b/arch/s390/include/asm/cpu_mcf.h
index 649b9fc60685..3e4cbcb7c4cc 100644
--- a/arch/s390/include/asm/cpu_mcf.h
+++ b/arch/s390/include/asm/cpu_mcf.h
@@ -123,4 +123,6 @@ static inline int stccm_avail(void)
 	return test_facility(142);
 }
 
+size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset,
+			   struct cpumf_ctr_info *info);
 #endif /* _ASM_S390_CPU_MCF_H */
diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h
index 9cceb26ed63f..baa8005090c3 100644
--- a/arch/s390/include/asm/entry-common.h
+++ b/arch/s390/include/asm/entry-common.h
@@ -4,9 +4,11 @@
 
 #include <linux/sched.h>
 #include <linux/audit.h>
+#include <linux/randomize_kstack.h>
 #include <linux/tracehook.h>
 #include <linux/processor.h>
 #include <linux/uaccess.h>
+#include <asm/timex.h>
 #include <asm/fpu/api.h>
 
 #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_GUARDED_STORAGE | _TIF_PER_TRAP)
@@ -48,6 +50,14 @@ static __always_inline void arch_exit_to_user_mode(void)
 
 #define arch_exit_to_user_mode arch_exit_to_user_mode
 
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	choose_random_kstack_offset(get_tod_clock_fast() & 0xff);
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
+
 static inline bool on_thread_stack(void)
 {
 	return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1));
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 6bcfc5614bbc..8925f3969478 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -454,6 +454,7 @@ struct kvm_vcpu_stat {
 	u64 diagnose_44;
 	u64 diagnose_9c;
 	u64 diagnose_9c_ignored;
+	u64 diagnose_9c_forward;
 	u64 diagnose_258;
 	u64 diagnose_308;
 	u64 diagnose_500;
@@ -700,6 +701,10 @@ struct kvm_hw_bp_info_arch {
 #define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \
 		(vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING))
 
+#define KVM_GUESTDBG_VALID_MASK \
+		(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP |\
+		KVM_GUESTDBG_USE_HW_BP | KVM_GUESTDBG_EXIT_PENDING)
+
 struct kvm_guestdbg_info_arch {
 	unsigned long cr0;
 	unsigned long cr9;
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 35c2af9371a9..10b67f8aab99 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -204,7 +204,7 @@ extern unsigned int s390_pci_no_rid;
 struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
 int zpci_enable_device(struct zpci_dev *);
 int zpci_disable_device(struct zpci_dev *);
-int zpci_configure_device(struct zpci_dev *zdev, u32 fh);
+int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh);
 int zpci_deconfigure_device(struct zpci_dev *zdev);
 
 int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 01e360004481..e317fd4866c1 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -63,5 +63,6 @@ extern void __noreturn cpu_die(void);
 extern void __cpu_die(unsigned int cpu);
 extern int __cpu_disable(void);
 extern void schedule_mcck_handler(void);
+void notrace smp_yield_cpu(int cpu);
 
 #endif /* __ASM_SMP_H */
diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h
index ed89ef742530..383c53c3dddd 100644
--- a/arch/s390/include/asm/vdso/gettimeofday.h
+++ b/arch/s390/include/asm/vdso/gettimeofday.h
@@ -68,7 +68,8 @@ long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
 }
 
 #ifdef CONFIG_TIME_NS
-static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
 {
 	return _timens_data;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index b3beef64d3d4..31a605bcbc6e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -230,9 +230,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 		/* No support for kernel space counters only */
 		} else if (!attr->exclude_kernel && attr->exclude_user) {
 			return -EOPNOTSUPP;
-
-		/* Count user and kernel space */
-		} else {
+		} else {	/* Count user and kernel space */
 			if (ev >= ARRAY_SIZE(cpumf_generic_events_basic))
 				return -EOPNOTSUPP;
 			ev = cpumf_generic_events_basic[ev];
@@ -402,12 +400,12 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 		 */
 		if (!atomic_dec_return(&cpuhw->ctr_set[hwc->config_base]))
 			ctr_set_stop(&cpuhw->state, hwc->config_base);
-		event->hw.state |= PERF_HES_STOPPED;
+		hwc->state |= PERF_HES_STOPPED;
 	}
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
 		hw_perf_event_update(event);
-		event->hw.state |= PERF_HES_UPTODATE;
+		hwc->state |= PERF_HES_UPTODATE;
 	}
 }
 
@@ -430,8 +428,6 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
 	if (flags & PERF_EF_START)
 		cpumf_pmu_start(event, PERF_EF_RELOAD);
 
-	perf_event_update_userpage(event);
-
 	return 0;
 }
 
@@ -451,8 +447,6 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
 	 */
 	if (!atomic_read(&cpuhw->ctr_set[event->hw.config_base]))
 		ctr_set_disable(&cpuhw->state, event->hw.config_base);
-
-	perf_event_update_userpage(event);
 }
 
 /*
diff --git a/arch/s390/kernel/perf_cpum_cf_common.c b/arch/s390/kernel/perf_cpum_cf_common.c
index 3bced89caffb..6d53215c8484 100644
--- a/arch/s390/kernel/perf_cpum_cf_common.c
+++ b/arch/s390/kernel/perf_cpum_cf_common.c
@@ -170,6 +170,52 @@ static int cpum_cf_offline_cpu(unsigned int cpu)
 	return cpum_cf_setup(cpu, PMC_RELEASE);
 }
 
+/* Return the maximum possible counter set size (in number of 8 byte counters)
+ * depending on type and model number.
+ */
+size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset,
+			   struct cpumf_ctr_info *info)
+{
+	size_t ctrset_size = 0;
+
+	switch (ctrset) {
+	case CPUMF_CTR_SET_BASIC:
+		if (info->cfvn >= 1)
+			ctrset_size = 6;
+		break;
+	case CPUMF_CTR_SET_USER:
+		if (info->cfvn == 1)
+			ctrset_size = 6;
+		else if (info->cfvn >= 3)
+			ctrset_size = 2;
+		break;
+	case CPUMF_CTR_SET_CRYPTO:
+		if (info->csvn >= 1 && info->csvn <= 5)
+			ctrset_size = 16;
+		else if (info->csvn == 6)
+			ctrset_size = 20;
+		break;
+	case CPUMF_CTR_SET_EXT:
+		if (info->csvn == 1)
+			ctrset_size = 32;
+		else if (info->csvn == 2)
+			ctrset_size = 48;
+		else if (info->csvn >= 3 && info->csvn <= 5)
+			ctrset_size = 128;
+		else if (info->csvn == 6)
+			ctrset_size = 160;
+		break;
+	case CPUMF_CTR_SET_MT_DIAG:
+		if (info->csvn > 3)
+			ctrset_size = 48;
+		break;
+	case CPUMF_CTR_SET_MAX:
+		break;
+	}
+
+	return ctrset_size;
+}
+
 static int __init cpum_cf_init(void)
 {
 	int rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2e3e7edbe3a0..08c985c1097c 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -316,52 +316,6 @@ static void cf_diag_read(struct perf_event *event)
 	debug_sprintf_event(cf_diag_dbg, 5, "%s event %p\n", __func__, event);
 }
 
-/* Return the maximum possible counter set size (in number of 8 byte counters)
- * depending on type and model number.
- */
-static size_t cf_diag_ctrset_size(enum cpumf_ctr_set ctrset,
-				 struct cpumf_ctr_info *info)
-{
-	size_t ctrset_size = 0;
-
-	switch (ctrset) {
-	case CPUMF_CTR_SET_BASIC:
-		if (info->cfvn >= 1)
-			ctrset_size = 6;
-		break;
-	case CPUMF_CTR_SET_USER:
-		if (info->cfvn == 1)
-			ctrset_size = 6;
-		else if (info->cfvn >= 3)
-			ctrset_size = 2;
-		break;
-	case CPUMF_CTR_SET_CRYPTO:
-		if (info->csvn >= 1 && info->csvn <= 5)
-			ctrset_size = 16;
-		else if (info->csvn == 6)
-			ctrset_size = 20;
-		break;
-	case CPUMF_CTR_SET_EXT:
-		if (info->csvn == 1)
-			ctrset_size = 32;
-		else if (info->csvn == 2)
-			ctrset_size = 48;
-		else if (info->csvn >= 3 && info->csvn <= 5)
-			ctrset_size = 128;
-		else if (info->csvn == 6)
-			ctrset_size = 160;
-		break;
-	case CPUMF_CTR_SET_MT_DIAG:
-		if (info->csvn > 3)
-			ctrset_size = 48;
-		break;
-	case CPUMF_CTR_SET_MAX:
-		break;
-	}
-
-	return ctrset_size;
-}
-
 /* Calculate memory needed to store all counter sets together with header and
  * trailer data. This is independend of the counter set authorization which
  * can vary depending on the configuration.
@@ -372,7 +326,7 @@ static size_t cf_diag_ctrset_maxsize(struct cpumf_ctr_info *info)
 	enum cpumf_ctr_set i;
 
 	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
-		size_t size = cf_diag_ctrset_size(i, info);
+		size_t size = cpum_cf_ctrset_size(i, info);
 
 		if (size)
 			max_size += size * sizeof(u64) +
@@ -405,7 +359,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset,
 	ctrdata->def = CF_DIAG_CTRSET_DEF;
 	ctrdata->set = ctrset;
 	ctrdata->res1 = 0;
-	ctrset_size = cf_diag_ctrset_size(ctrset, &cpuhw->info);
+	ctrset_size = cpum_cf_ctrset_size(ctrset, &cpuhw->info);
 
 	if (ctrset_size) {			/* Save data */
 		need = ctrset_size * sizeof(u64) + sizeof(*ctrdata);
@@ -845,7 +799,7 @@ static void cf_diag_cpu_read(void *parm)
 
 		if (!(p->sets & cpumf_ctr_ctl[set]))
 			continue;	/* Counter set not in list */
-		set_size = cf_diag_ctrset_size(set, &cpuhw->info);
+		set_size = cpum_cf_ctrset_size(set, &cpuhw->info);
 		space = sizeof(csd->data) - csd->used;
 		space = cf_diag_cpuset_read(sp, set, set_size, space);
 		if (space) {
@@ -975,7 +929,7 @@ static size_t cf_diag_needspace(unsigned int sets)
 	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
 		if (!(sets & cpumf_ctr_ctl[i]))
 			continue;
-		bytes += cf_diag_ctrset_size(i, &cpuhw->info) * sizeof(u64) +
+		bytes += cpum_cf_ctrset_size(i, &cpuhw->info) * sizeof(u64) +
 			 sizeof(((struct s390_ctrset_setdata *)0)->set) +
 			 sizeof(((struct s390_ctrset_setdata *)0)->no_cnts);
 	}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 72134f9f6ff5..5aab59ad5688 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -937,9 +937,9 @@ static int __init setup_hwcaps(void)
 	if (MACHINE_HAS_VX) {
 		elf_hwcap |= HWCAP_S390_VXRS;
 		if (test_facility(134))
-			elf_hwcap |= HWCAP_S390_VXRS_EXT;
-		if (test_facility(135))
 			elf_hwcap |= HWCAP_S390_VXRS_BCD;
+		if (test_facility(135))
+			elf_hwcap |= HWCAP_S390_VXRS_EXT;
 		if (test_facility(148))
 			elf_hwcap |= HWCAP_S390_VXRS_EXT2;
 		if (test_facility(152))
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 58c8afa3da65..2fec2b80d35d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -429,6 +429,7 @@ void notrace smp_yield_cpu(int cpu)
 	asm volatile("diag %0,0,0x9c"
 		     : : "d" (pcpu_devices[cpu].address));
 }
+EXPORT_SYMBOL_GPL(smp_yield_cpu);
 
 /*
  * Send cpus emergency shutdown signal. This gives the cpus the
diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c
index bc8e650e377d..4e5cc7d2364e 100644
--- a/arch/s390/kernel/syscall.c
+++ b/arch/s390/kernel/syscall.c
@@ -142,6 +142,7 @@ void do_syscall(struct pt_regs *regs)
 
 void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
 {
+	add_random_kstack_offset();
 	enter_from_user_mode(regs);
 
 	memcpy(&regs->gprs[8], S390_lowcore.save_area_sync, 8 * sizeof(unsigned long));
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index a421905c36e8..7e4a2aba366d 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -446,3 +446,6 @@
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
 442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
 443  common	quotactl_path		sys_quotactl_path		sys_quotactl_path
+444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
+445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
+446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 63021d484626..8dd23c703718 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -17,6 +17,7 @@
 #include "asm/ptrace.h"
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/randomize_kstack.h>
 #include <linux/extable.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -301,6 +302,7 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 	unsigned int trapnr, syscall_redirect = 0;
 	irqentry_state_t state;
 
+	add_random_kstack_offset();
 	regs->int_code = *(u32 *)&S390_lowcore.pgm_ilc;
 	regs->int_parm_long = S390_lowcore.trans_exc_code;
 
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5b8ec1c447e1..02c146f9e5cd 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -150,6 +150,19 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int forward_cnt;
+static unsigned long cur_slice;
+
+static int diag9c_forwarding_overrun(void)
+{
+	/* Reset the count on a new slice */
+	if (time_after(jiffies, cur_slice)) {
+		cur_slice = jiffies;
+		forward_cnt = diag9c_forwarding_hz / HZ;
+	}
+	return forward_cnt-- <= 0 ? 1 : 0;
+}
+
 static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu *tcpu;
@@ -167,9 +180,21 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 	if (!tcpu)
 		goto no_yield;
 
-	/* target already running */
-	if (READ_ONCE(tcpu->cpu) >= 0)
-		goto no_yield;
+	/* target guest VCPU already running */
+	if (READ_ONCE(tcpu->cpu) >= 0) {
+		if (!diag9c_forwarding_hz || diag9c_forwarding_overrun())
+			goto no_yield;
+
+		/* target host CPU already running */
+		if (!vcpu_is_preempted(tcpu->cpu))
+			goto no_yield;
+		smp_yield_cpu(tcpu->cpu);
+		VCPU_EVENT(vcpu, 5,
+			   "diag time slice end directed to %d: yield forwarded",
+			   tid);
+		vcpu->stat.diagnose_9c_forward++;
+		return 0;
+	}
 
 	if (kvm_vcpu_yield_to(tcpu) <= 0)
 		goto no_yield;
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 6d6b57059493..b9f85b2dc053 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -976,7 +976,9 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
  * kvm_s390_shadow_tables - walk the guest page table and create shadow tables
  * @sg: pointer to the shadow guest address space structure
  * @saddr: faulting address in the shadow gmap
- * @pgt: pointer to the page table address result
+ * @pgt: pointer to the beginning of the page table for the given address if
+ *	 successful (return value 0), or to the first invalid DAT entry in
+ *	 case of exceptions (return value > 0)
  * @fake: pgt references contiguous guest memory block, not a pgtable
  */
 static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
@@ -1034,6 +1036,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
 			rfte.val = ptr;
 			goto shadow_r2t;
 		}
+		*pgt = ptr + vaddr.rfx * 8;
 		rc = gmap_read_table(parent, ptr + vaddr.rfx * 8, &rfte.val);
 		if (rc)
 			return rc;
@@ -1060,6 +1063,7 @@ shadow_r2t:
 			rste.val = ptr;
 			goto shadow_r3t;
 		}
+		*pgt = ptr + vaddr.rsx * 8;
 		rc = gmap_read_table(parent, ptr + vaddr.rsx * 8, &rste.val);
 		if (rc)
 			return rc;
@@ -1087,6 +1091,7 @@ shadow_r3t:
 			rtte.val = ptr;
 			goto shadow_sgt;
 		}
+		*pgt = ptr + vaddr.rtx * 8;
 		rc = gmap_read_table(parent, ptr + vaddr.rtx * 8, &rtte.val);
 		if (rc)
 			return rc;
@@ -1123,6 +1128,7 @@ shadow_sgt:
 			ste.val = ptr;
 			goto shadow_pgt;
 		}
+		*pgt = ptr + vaddr.sx * 8;
 		rc = gmap_read_table(parent, ptr + vaddr.sx * 8, &ste.val);
 		if (rc)
 			return rc;
@@ -1157,6 +1163,8 @@ shadow_pgt:
  * @vcpu: virtual cpu
  * @sg: pointer to the shadow guest address space structure
  * @saddr: faulting address in the shadow gmap
+ * @datptr: will contain the address of the faulting DAT table entry, or of
+ *	    the valid leaf, plus some flags
  *
  * Returns: - 0 if the shadow fault was successfully resolved
  *	    - > 0 (pgm exception code) on exceptions while faulting
@@ -1165,11 +1173,11 @@ shadow_pgt:
  *	    - -ENOMEM if out of memory
  */
 int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
-			  unsigned long saddr)
+			  unsigned long saddr, unsigned long *datptr)
 {
 	union vaddress vaddr;
 	union page_table_entry pte;
-	unsigned long pgt;
+	unsigned long pgt = 0;
 	int dat_protection, fake;
 	int rc;
 
@@ -1191,8 +1199,20 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 		pte.val = pgt + vaddr.px * PAGE_SIZE;
 		goto shadow_page;
 	}
-	if (!rc)
-		rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
+
+	switch (rc) {
+	case PGM_SEGMENT_TRANSLATION:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_FIRST_TRANS:
+		pgt |= PEI_NOT_PTE;
+		break;
+	case 0:
+		pgt += vaddr.px * 8;
+		rc = gmap_read_table(sg->parent, pgt, &pte.val);
+	}
+	if (datptr)
+		*datptr = pgt | dat_protection * PEI_DAT_PROT;
 	if (!rc && pte.i)
 		rc = PGM_PAGE_TRANSLATION;
 	if (!rc && pte.z)
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index f4c51756c462..7c72a5e3449f 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -18,17 +18,14 @@
 
 /**
  * kvm_s390_real_to_abs - convert guest real address to guest absolute address
- * @vcpu - guest virtual cpu
+ * @prefix - guest prefix
  * @gra - guest real address
  *
  * Returns the guest absolute address that corresponds to the passed guest real
- * address @gra of a virtual guest cpu by applying its prefix.
+ * address @gra of by applying the given prefix.
  */
-static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
-						 unsigned long gra)
+static inline unsigned long _kvm_s390_real_to_abs(u32 prefix, unsigned long gra)
 {
-	unsigned long prefix  = kvm_s390_get_prefix(vcpu);
-
 	if (gra < 2 * PAGE_SIZE)
 		gra += prefix;
 	else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE)
@@ -37,6 +34,43 @@ static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
 }
 
 /**
+ * kvm_s390_real_to_abs - convert guest real address to guest absolute address
+ * @vcpu - guest virtual cpu
+ * @gra - guest real address
+ *
+ * Returns the guest absolute address that corresponds to the passed guest real
+ * address @gra of a virtual guest cpu by applying its prefix.
+ */
+static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
+						 unsigned long gra)
+{
+	return _kvm_s390_real_to_abs(kvm_s390_get_prefix(vcpu), gra);
+}
+
+/**
+ * _kvm_s390_logical_to_effective - convert guest logical to effective address
+ * @psw: psw of the guest
+ * @ga: guest logical address
+ *
+ * Convert a guest logical address to an effective address by applying the
+ * rules of the addressing mode defined by bits 31 and 32 of the given PSW
+ * (extendended/basic addressing mode).
+ *
+ * Depending on the addressing mode, the upper 40 bits (24 bit addressing
+ * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing
+ * mode) of @ga will be zeroed and the remaining bits will be returned.
+ */
+static inline unsigned long _kvm_s390_logical_to_effective(psw_t *psw,
+							   unsigned long ga)
+{
+	if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT)
+		return ga;
+	if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT)
+		return ga & ((1UL << 31) - 1);
+	return ga & ((1UL << 24) - 1);
+}
+
+/**
  * kvm_s390_logical_to_effective - convert guest logical to effective address
  * @vcpu: guest virtual cpu
  * @ga: guest logical address
@@ -52,13 +86,7 @@ static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
 static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu,
 							  unsigned long ga)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-
-	if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT)
-		return ga;
-	if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT)
-		return ga & ((1UL << 31) - 1);
-	return ga & ((1UL << 24) - 1);
+	return _kvm_s390_logical_to_effective(&vcpu->arch.sie_block->gpsw, ga);
 }
 
 /*
@@ -359,7 +387,11 @@ void ipte_unlock(struct kvm_vcpu *vcpu);
 int ipte_lock_held(struct kvm_vcpu *vcpu);
 int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra);
 
+/* MVPG PEI indication bits */
+#define PEI_DAT_PROT 2
+#define PEI_NOT_PTE 4
+
 int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *shadow,
-			  unsigned long saddr);
+			  unsigned long saddr, unsigned long *datptr);
 
 #endif /* __KVM_S390_GACCESS_H */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2f09e9d7dc95..1296fc10f80c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -158,6 +158,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("instruction_diag_44", diagnose_44),
 	VCPU_STAT("instruction_diag_9c", diagnose_9c),
 	VCPU_STAT("diag_9c_ignored", diagnose_9c_ignored),
+	VCPU_STAT("diag_9c_forward", diagnose_9c_forward),
 	VCPU_STAT("instruction_diag_258", diagnose_258),
 	VCPU_STAT("instruction_diag_308", diagnose_308),
 	VCPU_STAT("instruction_diag_500", diagnose_500),
@@ -185,6 +186,11 @@ static bool use_gisa  = true;
 module_param(use_gisa, bool, 0644);
 MODULE_PARM_DESC(use_gisa, "Use the GISA if the host supports it.");
 
+/* maximum diag9c forwarding per second */
+unsigned int diag9c_forwarding_hz;
+module_param(diag9c_forwarding_hz, uint, 0644);
+MODULE_PARM_DESC(diag9c_forwarding_hz, "Maximum diag9c forwarding per second, 0 to turn off");
+
 /*
  * For now we handle at most 16 double words as this is what the s390 base
  * kernel handles and stores in the prefix page. If we ever need to go beyond
@@ -544,6 +550,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_DIAG318:
 		r = 1;
 		break;
+	case KVM_CAP_SET_GUEST_DEBUG2:
+		r = KVM_GUESTDBG_VALID_MASK;
+		break;
 	case KVM_CAP_S390_HPAGE_1M:
 		r = 0;
 		if (hpage && !kvm_is_ucontrol(kvm))
@@ -4307,16 +4316,16 @@ static void store_regs_fmt2(struct kvm_vcpu *vcpu)
 	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	kvm_run->s.regs.diag318 = vcpu->arch.diag318_info.val;
 	if (MACHINE_HAS_GS) {
+		preempt_disable();
 		__ctl_set_bit(2, 4);
 		if (vcpu->arch.gs_enabled)
 			save_gs_cb(current->thread.gs_cb);
-		preempt_disable();
 		current->thread.gs_cb = vcpu->arch.host_gscb;
 		restore_gs_cb(vcpu->arch.host_gscb);
-		preempt_enable();
 		if (!vcpu->arch.host_gscb)
 			__ctl_clear_bit(2, 4);
 		vcpu->arch.host_gscb = NULL;
+		preempt_enable();
 	}
 	/* SIE will save etoken directly into SDNX and therefore kvm_run */
 }
@@ -4542,7 +4551,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 		/*
 		 * As we are starting a second VCPU, we have to disable
 		 * the IBS facility on all VCPUs to remove potentially
-		 * oustanding ENABLE requests.
+		 * outstanding ENABLE requests.
 		 */
 		__disable_ibs_on_all_vcpus(vcpu->kvm);
 	}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 79dcd647b378..9fad25109b0d 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -471,4 +471,12 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
  * @kvm: the KVM guest
  */
 void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm);
+
+/**
+ * diag9c_forwarding_hz
+ *
+ * Set the maximum number of diag9c forwarding per second
+ */
+extern unsigned int diag9c_forwarding_hz;
+
 #endif
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index bd803e091918..4002a24bc43a 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -417,11 +417,6 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		memcpy((void *)((u64)scb_o + 0xc0),
 		       (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0);
 		break;
-	case ICPT_PARTEXEC:
-		/* MVPG only */
-		memcpy((void *)((u64)scb_o + 0xc0),
-		       (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0);
-		break;
 	}
 
 	if (scb_s->ihcpu != 0xffffU)
@@ -620,10 +615,10 @@ static int map_prefix(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* with mso/msl, the prefix lies at offset *mso* */
 	prefix += scb_s->mso;
 
-	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix);
+	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix, NULL);
 	if (!rc && (scb_s->ecb & ECB_TE))
 		rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-					   prefix + PAGE_SIZE);
+					   prefix + PAGE_SIZE, NULL);
 	/*
 	 * We don't have to mprotect, we will be called for all unshadows.
 	 * SIE will detect if protection applies and trigger a validity.
@@ -914,7 +909,7 @@ static int handle_fault(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 				    current->thread.gmap_addr, 1);
 
 	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-				   current->thread.gmap_addr);
+				   current->thread.gmap_addr, NULL);
 	if (rc > 0) {
 		rc = inject_fault(vcpu, rc,
 				  current->thread.gmap_addr,
@@ -936,7 +931,7 @@ static void handle_last_fault(struct kvm_vcpu *vcpu,
 {
 	if (vsie_page->fault_addr)
 		kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-				      vsie_page->fault_addr);
+				      vsie_page->fault_addr, NULL);
 	vsie_page->fault_addr = 0;
 }
 
@@ -984,6 +979,98 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 }
 
 /*
+ * Get a register for a nested guest.
+ * @vcpu the vcpu of the guest
+ * @vsie_page the vsie_page for the nested guest
+ * @reg the register number, the upper 4 bits are ignored.
+ * returns: the value of the register.
+ */
+static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, u8 reg)
+{
+	/* no need to validate the parameter and/or perform error handling */
+	reg &= 0xf;
+	switch (reg) {
+	case 15:
+		return vsie_page->scb_s.gg15;
+	case 14:
+		return vsie_page->scb_s.gg14;
+	default:
+		return vcpu->run->s.regs.gprs[reg];
+	}
+}
+
+static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	unsigned long pei_dest, pei_src, src, dest, mask, prefix;
+	u64 *pei_block = &vsie_page->scb_o->mcic;
+	int edat, rc_dest, rc_src;
+	union ctlreg0 cr0;
+
+	cr0.val = vcpu->arch.sie_block->gcr[0];
+	edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8);
+	mask = _kvm_s390_logical_to_effective(&scb_s->gpsw, PAGE_MASK);
+	prefix = scb_s->prefix << GUEST_PREFIX_SHIFT;
+
+	dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & mask;
+	dest = _kvm_s390_real_to_abs(prefix, dest) + scb_s->mso;
+	src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) & mask;
+	src = _kvm_s390_real_to_abs(prefix, src) + scb_s->mso;
+
+	rc_dest = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, &pei_dest);
+	rc_src = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, &pei_src);
+	/*
+	 * Either everything went well, or something non-critical went wrong
+	 * e.g. because of a race. In either case, simply retry.
+	 */
+	if (rc_dest == -EAGAIN || rc_src == -EAGAIN || (!rc_dest && !rc_src)) {
+		retry_vsie_icpt(vsie_page);
+		return -EAGAIN;
+	}
+	/* Something more serious went wrong, propagate the error */
+	if (rc_dest < 0)
+		return rc_dest;
+	if (rc_src < 0)
+		return rc_src;
+
+	/* The only possible suppressing exception: just deliver it */
+	if (rc_dest == PGM_TRANSLATION_SPEC || rc_src == PGM_TRANSLATION_SPEC) {
+		clear_vsie_icpt(vsie_page);
+		rc_dest = kvm_s390_inject_program_int(vcpu, PGM_TRANSLATION_SPEC);
+		WARN_ON_ONCE(rc_dest);
+		return 1;
+	}
+
+	/*
+	 * Forward the PEI intercept to the guest if it was a page fault, or
+	 * also for segment and region table faults if EDAT applies.
+	 */
+	if (edat) {
+		rc_dest = rc_dest == PGM_ASCE_TYPE ? rc_dest : 0;
+		rc_src = rc_src == PGM_ASCE_TYPE ? rc_src : 0;
+	} else {
+		rc_dest = rc_dest != PGM_PAGE_TRANSLATION ? rc_dest : 0;
+		rc_src = rc_src != PGM_PAGE_TRANSLATION ? rc_src : 0;
+	}
+	if (!rc_dest && !rc_src) {
+		pei_block[0] = pei_dest;
+		pei_block[1] = pei_src;
+		return 1;
+	}
+
+	retry_vsie_icpt(vsie_page);
+
+	/*
+	 * The host has edat, and the guest does not, or it was an ASCE type
+	 * exception. The host needs to inject the appropriate DAT interrupts
+	 * into the guest.
+	 */
+	if (rc_dest)
+		return inject_fault(vcpu, rc_dest, dest, 1);
+	return inject_fault(vcpu, rc_src, src, 0);
+}
+
+/*
  * Run the vsie on a shadow scb and a shadow gmap, without any further
  * sanity checks, handling SIE faults.
  *
@@ -1071,6 +1158,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		if ((scb_s->ipa & 0xf000) != 0xf000)
 			scb_s->ipa += 0x1000;
 		break;
+	case ICPT_PARTEXEC:
+		if (scb_s->ipa == 0xb254)
+			rc = vsie_handle_mvpg(vcpu, vsie_page);
+		break;
 	}
 	return rc;
 }
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index c01b6dbac7cf..b0993e05affe 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -738,17 +738,19 @@ error:
 }
 
 /**
- * zpci_configure_device() - Configure a zpci_dev
+ * zpci_scan_configured_device() - Scan a freshly configured zpci_dev
  * @zdev: The zpci_dev to be configured
  * @fh: The general function handle supplied by the platform
  *
  * Given a device in the configuration state Configured, enables, scans and
- * adds it to the common code PCI subsystem. If any failure occurs, the
- * zpci_dev is left disabled.
+ * adds it to the common code PCI subsystem if possible. If the PCI device is
+ * parked because we can not yet create a PCI bus because we have not seen
+ * function 0, it is ignored but will be scanned once function 0 appears.
+ * If any failure occurs, the zpci_dev is left disabled.
  *
  * Return: 0 on success, or an error code otherwise
  */
-int zpci_configure_device(struct zpci_dev *zdev, u32 fh)
+int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh)
 {
 	int rc;
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 1178b48a66df..cd447b96b4b1 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -76,8 +76,6 @@ void zpci_event_error(void *data)
 
 static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 {
-	enum zpci_state state;
-
 	zdev->fh = fh;
 	/* Give the driver a hint that the function is
 	 * already unusable.
@@ -88,15 +86,12 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 	 */
 	zpci_disable_device(zdev);
 	zdev->state = ZPCI_FN_STATE_STANDBY;
-	if (!clp_get_state(zdev->fid, &state) &&
-	    state == ZPCI_FN_STATE_RESERVED) {
-		zpci_zdev_put(zdev);
-	}
 }
 
 static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+	enum zpci_state state;
 
 	zpci_err("avail CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
@@ -113,7 +108,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 				break;
 			zdev->state = ZPCI_FN_STATE_CONFIGURED;
 		}
-		zpci_configure_device(zdev, ccdf->fh);
+		zpci_scan_configured_device(zdev, ccdf->fh);
 		break;
 	case 0x0302: /* Reserved -> Standby */
 		if (!zdev)
@@ -123,13 +118,28 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (zdev) {
+			/* The event may have been queued before we confirgured
+			 * the device.
+			 */
+			if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+				break;
 			zdev->fh = ccdf->fh;
 			zpci_deconfigure_device(zdev);
 		}
 		break;
 	case 0x0304: /* Configured -> Standby|Reserved */
-		if (zdev)
-			zpci_event_hard_deconfigured(zdev, ccdf->fh);
+		if (zdev) {
+			/* The event may have been queued before we confirgured
+			 * the device.:
+			 */
+			if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
+				zpci_event_hard_deconfigured(zdev, ccdf->fh);
+			/* The 0x0304 event may immediately reserve the device */
+			if (!clp_get_state(zdev->fid, &state) &&
+			    state == ZPCI_FN_STATE_RESERVED) {
+				zpci_zdev_put(zdev);
+			}
+		}
 		break;
 	case 0x0306: /* 0x308 or 0x302 for multiple devices */
 		zpci_remove_reserved_devices();