Merge tag 'kvm-s390-next-20150306' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into queue

KVM: s390: Features and Fixes for 4.1 (kvm/next)

1. Several Fixes and enhancements
---------------------------------
- These 3 patches have cc stable:
b75f4c9 KVM: s390: Zero out current VMDB of STSI before including level3 data.
261520d KVM: s390: fix handling of write errors in the tpi handler
15462e3 KVM: s390: reinjection of irqs can fail in the tpi handler

2. SIMD support the kernel part (introduced with z13)
-----------------------------------------------------
- two KVM-generic changes in kvm.h:
1. New capability that can be enabled: KVM_CAP_S390_VECTOR_REGISTERS
2. increased padding size for sync regs in struct kvm_run to clarify that
   sync regs can be larger than 1k. This is fine as this is the last
   element in the structure.

12 files changed, 195 insertions, 53 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f407bbf5ee94..347a3333d618 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -172,7 +172,9 @@ struct kvm_s390_sie_block {
 	__u32	fac;			/* 0x01a0 */
 	__u8	reserved1a4[20];	/* 0x01a4 */
 	__u64	cbrlo;			/* 0x01b8 */
-	__u8	reserved1c0[30];	/* 0x01c0 */
+	__u8	reserved1c0[8];		/* 0x01c0 */
+	__u32	ecd;			/* 0x01c8 */
+	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
 	__u8	reserved1e6[2];		/* 0x01e6 */
 	__u64	itdba;			/* 0x01e8 */
@@ -183,11 +185,17 @@ struct kvm_s390_itdb {
 	__u8	data[256];
 } __packed;
 
+struct kvm_s390_vregs {
+	__vector128 vrs[32];
+	__u8	reserved200[512];	/* for future vector expansion */
+} __packed;
+
 struct sie_page {
 	struct kvm_s390_sie_block sie_block;
 	__u8 reserved200[1024];		/* 0x0200 */
 	struct kvm_s390_itdb itdb;	/* 0x0600 */
-	__u8 reserved700[2304];		/* 0x0700 */
+	__u8 reserved700[1280];		/* 0x0700 */
+	struct kvm_s390_vregs vregs;	/* 0x0c00 */
 } __packed;
 
 struct kvm_vcpu_stat {
@@ -238,6 +246,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_sigp_stop;
 	u32 instruction_sigp_stop_store_status;
 	u32 instruction_sigp_store_status;
+	u32 instruction_sigp_store_adtl_status;
 	u32 instruction_sigp_arch;
 	u32 instruction_sigp_prefix;
 	u32 instruction_sigp_restart;
@@ -270,6 +279,7 @@ struct kvm_vcpu_stat {
 #define PGM_SPECIAL_OPERATION		0x13
 #define PGM_OPERAND			0x15
 #define PGM_TRACE_TABEL			0x16
+#define PGM_VECTOR_PROCESSING		0x1b
 #define PGM_SPACE_SWITCH		0x1c
 #define PGM_HFP_SQUARE_ROOT		0x1d
 #define PGM_PC_TRANSLATION_SPEC		0x1f
@@ -465,6 +475,7 @@ struct kvm_vcpu_arch {
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
+	struct kvm_s390_vregs	*host_vregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
@@ -551,6 +562,7 @@ struct kvm_arch{
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
+	int use_vectors;
 	int user_cpu_state_ctrl;
 	int user_sigp;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 9c77e60b9a26..ef1a5fcc6c66 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -150,6 +150,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_CRS    (1UL << 3)
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
+#define KVM_SYNC_VRS    (1UL << 6)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -164,6 +165,9 @@ struct kvm_sync_regs {
 	__u64 pft;	/* pfault token [PFAULT] */
 	__u64 pfs;	/* pfault select [PFAULT] */
 	__u64 pfc;	/* pfault compare [PFAULT] */
+	__u64 vrs[32][2];	/* vector registers */
+	__u8  reserved[512];	/* for future vector expansion */
+	__u32 fpc;	/* only valid with vector registers */
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h
index d4096fdfc6ab..ee69c0854c88 100644
--- a/arch/s390/include/uapi/asm/sie.h
+++ b/arch/s390/include/uapi/asm/sie.h
@@ -230,7 +230,7 @@
  * and returns a key, which can be used to find a mnemonic name
  * of the instruction in the icpt_insn_codes table.
  */
-#define icpt_insn_decoder(insn)			\
+#define icpt_insn_decoder(insn) (		\
 	INSN_DECODE_IPA0(0x01, insn, 48, 0xff)	\
 	INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f)	\
 	INSN_DECODE_IPA0(0xb2, insn, 48, 0xff)	\
@@ -239,6 +239,6 @@
 	INSN_DECODE_IPA0(0xe5, insn, 48, 0xff)	\
 	INSN_DECODE_IPA0(0xeb, insn, 16, 0xff)	\
 	INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f)	\
-	INSN_DECODE(insn)
+	INSN_DECODE(insn))
 
 #endif /* _UAPI_ASM_S390_SIE_H */
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index e07e91605353..8dc4db10d160 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -171,6 +171,7 @@ int main(void)
 #else /* CONFIG_32BIT */
 	DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code));
 	DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address));
+	DEFINE(__LC_VX_SAVE_AREA_ADDR, offsetof(struct _lowcore, vector_save_area_addr));
 	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 267523cac6de..633fe9bd75a9 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -333,7 +333,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
  * @write: indicates if access is a write access
  *
  * Translate a guest virtual address into a guest absolute address by means
- * of dynamic address translation as specified by the architecuture.
+ * of dynamic address translation as specified by the architecture.
  * If the resulting absolute address is not available in the configuration
  * an addressing exception is indicated and @gpa will not be changed.
  *
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 3e8d4092ce30..e97b3455d7e6 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -191,8 +191,8 @@ static int __import_wp_info(struct kvm_vcpu *vcpu,
 	if (!wp_info->old_data)
 		return -ENOMEM;
 	/* try to backup the original value */
-	ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data,
-			 wp_info->len);
+	ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data,
+			     wp_info->len);
 	if (ret) {
 		kfree(wp_info->old_data);
 		wp_info->old_data = NULL;
@@ -362,8 +362,8 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu)
 			continue;
 
 		/* refetch the wp data and compare it to the old value */
-		if (!read_guest(vcpu, wp_info->phys_addr, temp,
-				wp_info->len)) {
+		if (!read_guest_abs(vcpu, wp_info->phys_addr, temp,
+				    wp_info->len)) {
 			if (memcmp(temp, wp_info->old_data, wp_info->len)) {
 				kfree(temp);
 				return wp_info;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index bebd2157edd0..08ae10a3b406 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -165,6 +165,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 		pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
 		pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
 		break;
+	case PGM_VECTOR_PROCESSING:
 	case PGM_DATA:
 		pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
 		break;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 073b5f387d1d..2afec6006def 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,7 +1,7 @@
 /*
  * handling kvm guest interrupts
  *
- * Copyright IBM Corp. 2008,2014
+ * Copyright IBM Corp. 2008, 2015
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/bitmap.h>
 #include <asm/asm-offsets.h>
+#include <asm/dis.h>
 #include <asm/uaccess.h>
 #include <asm/sclp.h>
 #include "kvm-s390.h"
@@ -265,8 +266,6 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 
 static u16 get_ilc(struct kvm_vcpu *vcpu)
 {
-	const unsigned short table[] = { 2, 4, 4, 6 };
-
 	switch (vcpu->arch.sie_block->icptcode) {
 	case ICPT_INST:
 	case ICPT_INSTPROGI:
@@ -274,7 +273,7 @@ static u16 get_ilc(struct kvm_vcpu *vcpu)
 	case ICPT_PARTEXEC:
 	case ICPT_IOINST:
 		/* last instruction only stored for these icptcodes */
-		return table[vcpu->arch.sie_block->ipa >> 14];
+		return insn_length(vcpu->arch.sie_block->ipa >> 8);
 	case ICPT_PROGI:
 		return vcpu->arch.sie_block->pgmilc;
 	default:
@@ -352,6 +351,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_mchk_info mchk;
+	unsigned long adtl_status_addr;
 	int rc;
 
 	spin_lock(&li->lock);
@@ -372,6 +372,9 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
 					 mchk.cr14, mchk.mcic);
 
 	rc  = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);
+	rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR,
+			    &adtl_status_addr, sizeof(unsigned long));
+	rc |= kvm_s390_vcpu_store_adtl_status(vcpu, adtl_status_addr);
 	rc |= put_guest_lc(vcpu, mchk.mcic,
 			   (u64 __user *) __LC_MCCK_CODE);
 	rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
@@ -484,7 +487,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_pgm_info pgm_info;
-	int rc = 0;
+	int rc = 0, nullifying = false;
 	u16 ilc = get_ilc(vcpu);
 
 	spin_lock(&li->lock);
@@ -509,6 +512,8 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	case PGM_LX_TRANSLATION:
 	case PGM_PRIMARY_AUTHORITY:
 	case PGM_SECONDARY_AUTHORITY:
+		nullifying = true;
+		/* fall through */
 	case PGM_SPACE_SWITCH:
 		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
 				  (u64 *)__LC_TRANS_EXC_CODE);
@@ -521,6 +526,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	case PGM_EXTENDED_AUTHORITY:
 		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
 				  (u8 *)__LC_EXC_ACCESS_ID);
+		nullifying = true;
 		break;
 	case PGM_ASCE_TYPE:
 	case PGM_PAGE_TRANSLATION:
@@ -534,6 +540,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 				   (u8 *)__LC_EXC_ACCESS_ID);
 		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
 				   (u8 *)__LC_OP_ACCESS_ID);
+		nullifying = true;
 		break;
 	case PGM_MONITOR:
 		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
@@ -541,6 +548,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
 				   (u64 *)__LC_MON_CODE);
 		break;
+	case PGM_VECTOR_PROCESSING:
 	case PGM_DATA:
 		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
 				  (u32 *)__LC_DATA_EXC_CODE);
@@ -551,6 +559,15 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
 				   (u8 *)__LC_EXC_ACCESS_ID);
 		break;
+	case PGM_STACK_FULL:
+	case PGM_STACK_EMPTY:
+	case PGM_STACK_SPECIFICATION:
+	case PGM_STACK_TYPE:
+	case PGM_STACK_OPERATION:
+	case PGM_TRACE_TABEL:
+	case PGM_CRYPTO_OPERATION:
+		nullifying = true;
+		break;
 	}
 
 	if (pgm_info.code & PGM_PER) {
@@ -564,6 +581,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 				   (u8 *) __LC_PER_ACCESS_ID);
 	}
 
+	if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
+		kvm_s390_rewind_psw(vcpu, ilc);
+
 	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
 	rc |= put_guest_lc(vcpu, pgm_info.code,
 			   (u16 *)__LC_PGM_INT_CODE);
@@ -1332,10 +1352,10 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	return rc;
 }
 
-void kvm_s390_reinject_io_int(struct kvm *kvm,
+int kvm_s390_reinject_io_int(struct kvm *kvm,
 			      struct kvm_s390_interrupt_info *inti)
 {
-	__inject_vm(kvm, inti);
+	return __inject_vm(kvm, inti);
 }
 
 int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f6579cfde2df..02e03c862a60 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -87,6 +87,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
 	{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
 	{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
+	{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
 	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
 	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
 	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
@@ -103,6 +104,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 unsigned long kvm_s390_fac_list_mask[] = {
 	0xff82fffbf4fc2000UL,
 	0x005c000000000000UL,
+	0x4000000000000000UL,
 };
 
 unsigned long kvm_s390_fac_list_mask_size(void)
@@ -185,6 +187,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;
 		break;
+	case KVM_CAP_S390_VECTOR_REGISTERS:
+		r = MACHINE_HAS_VX;
+		break;
 	default:
 		r = 0;
 	}
@@ -265,6 +270,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		kvm->arch.user_sigp = 1;
 		r = 0;
 		break;
+	case KVM_CAP_S390_VECTOR_REGISTERS:
+		kvm->arch.use_vectors = MACHINE_HAS_VX;
+		r = MACHINE_HAS_VX ? 0 : -EINVAL;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -942,6 +951,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm->arch.css_support = 0;
 	kvm->arch.use_irqchip = 0;
+	kvm->arch.use_vectors = 0;
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
@@ -1035,6 +1045,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	if (test_kvm_facility(vcpu->kvm, 129))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		return __kvm_ucontrol_vcpu_init(vcpu);
@@ -1045,10 +1057,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
-	save_fp_regs(vcpu->arch.host_fpregs.fprs);
+	if (vcpu->kvm->arch.use_vectors)
+		save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
+	else
+		save_fp_regs(vcpu->arch.host_fpregs.fprs);
 	save_access_regs(vcpu->arch.host_acrs);
-	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	if (vcpu->kvm->arch.use_vectors) {
+		restore_fp_ctl(&vcpu->run->s.regs.fpc);
+		restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+	} else {
+		restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+		restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	}
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
@@ -1058,11 +1078,19 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
-	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	if (vcpu->kvm->arch.use_vectors) {
+		save_fp_ctl(&vcpu->run->s.regs.fpc);
+		save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+	} else {
+		save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+		save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	}
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
-	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
+	if (vcpu->kvm->arch.use_vectors)
+		restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
+	else
+		restore_fp_regs(vcpu->arch.host_fpregs.fprs);
 	restore_access_regs(vcpu->arch.host_acrs);
 }
 
@@ -1130,6 +1158,15 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model;
+
+	vcpu->arch.cpu_id = model->cpu_id;
+	vcpu->arch.sie_block->ibc = model->ibc;
+	vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+}
+
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
@@ -1138,6 +1175,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 						    CPUSTAT_SM |
 						    CPUSTAT_STOPPED |
 						    CPUSTAT_GED);
+	kvm_s390_vcpu_setup_model(vcpu);
+
 	vcpu->arch.sie_block->ecb   = 6;
 	if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
 		vcpu->arch.sie_block->ecb |= 0x10;
@@ -1148,8 +1187,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->eca |= 1;
 	if (sclp_has_sigpif())
 		vcpu->arch.sie_block->eca |= 0x10000000U;
-	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
-				      ICTL_TPROT;
+	if (vcpu->kvm->arch.use_vectors) {
+		vcpu->arch.sie_block->eca |= 0x00020000;
+		vcpu->arch.sie_block->ecd |= 0x20000000;
+	}
+	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
 	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
 		rc = kvm_s390_vcpu_setup_cmma(vcpu);
@@ -1159,11 +1201,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 
-	mutex_lock(&vcpu->kvm->lock);
-	vcpu->arch.cpu_id = vcpu->kvm->arch.model.cpu_id;
-	vcpu->arch.sie_block->ibc = vcpu->kvm->arch.model.ibc;
-	mutex_unlock(&vcpu->kvm->lock);
-
 	kvm_s390_vcpu_crypto_setup(vcpu);
 
 	return rc;
@@ -1191,6 +1228,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
+	vcpu->arch.host_vregs = &sie_page->vregs;
 
 	vcpu->arch.sie_block->icpua = id;
 	if (!kvm_is_ucontrol(kvm)) {
@@ -1206,7 +1244,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
 		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
 	}
-	vcpu->arch.sie_block->fac = (int) (long) kvm->arch.model.fac->list;
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
@@ -1726,6 +1763,31 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
+{
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	u8 opcode;
+	int rc;
+
+	VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+	trace_kvm_s390_sie_fault(vcpu);
+
+	/*
+	 * We want to inject an addressing exception, which is defined as a
+	 * suppressing or terminating exception. However, since we came here
+	 * by a DAT access exception, the PSW still points to the faulting
+	 * instruction since DAT exceptions are nullifying. So we've got
+	 * to look up the current opcode to get the length of the instruction
+	 * to be able to forward the PSW.
+	 */
+	rc = read_guest(vcpu, psw->addr, &opcode, 1);
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
+	psw->addr = __rewind_psw(*psw, -insn_length(opcode));
+
+	return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+}
+
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 {
 	int rc = -1;
@@ -1757,11 +1819,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 		}
 	}
 
-	if (rc == -1) {
-		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
-		trace_kvm_s390_sie_fault(vcpu);
-		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-	}
+	if (rc == -1)
+		rc = vcpu_post_run_fault_in_sie(vcpu);
 
 	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 
@@ -1977,6 +2036,35 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return kvm_s390_store_status_unloaded(vcpu, addr);
 }
 
+/*
+ * store additional status at address
+ */
+int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
+					unsigned long gpa)
+{
+	/* Only bits 0-53 are used for address formation */
+	if (!(gpa & ~0x3ff))
+		return 0;
+
+	return write_guest_abs(vcpu, gpa & ~0x3ff,
+			       (void *)&vcpu->run->s.regs.vrs, 512);
+}
+
+int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	if (!test_kvm_facility(vcpu->kvm, 129))
+		return 0;
+
+	/*
+	 * The guest VXRS are in the host VXRs due to the lazy
+	 * copying in vcpu load/put. Let's update our copies before we save
+	 * it into the save area.
+	 */
+	save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+
+	return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
+}
+
 static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index c34109aa552d..fda3f3146eb6 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -151,8 +151,8 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 cr6, u64 schid);
-void kvm_s390_reinject_io_int(struct kvm *kvm,
-			      struct kvm_s390_interrupt_info *inti);
+int kvm_s390_reinject_io_int(struct kvm *kvm,
+			     struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in intercept.c */
@@ -177,7 +177,10 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 /* implemented in kvm-s390.c */
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
+					unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
 void s390_vcpu_block(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 351116939ea2..b982fbca34df 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -229,18 +229,19 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	struct kvm_s390_interrupt_info *inti;
 	unsigned long len;
 	u32 tpi_data[3];
-	int cc, rc;
+	int rc;
 	u64 addr;
 
-	rc = 0;
 	addr = kvm_s390_get_base_disp_s(vcpu);
 	if (addr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	cc = 0;
+
 	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0);
-	if (!inti)
-		goto no_interrupt;
-	cc = 1;
+	if (!inti) {
+		kvm_s390_set_psw_cc(vcpu, 0);
+		return 0;
+	}
+
 	tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr;
 	tpi_data[1] = inti->io.io_int_parm;
 	tpi_data[2] = inti->io.io_int_word;
@@ -251,30 +252,38 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 		 */
 		len = sizeof(tpi_data) - 4;
 		rc = write_guest(vcpu, addr, &tpi_data, len);
-		if (rc)
-			return kvm_s390_inject_prog_cond(vcpu, rc);
+		if (rc) {
+			rc = kvm_s390_inject_prog_cond(vcpu, rc);
+			goto reinject_interrupt;
+		}
 	} else {
 		/*
 		 * Store the three-word I/O interruption code into
 		 * the appropriate lowcore area.
 		 */
 		len = sizeof(tpi_data);
-		if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len))
+		if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) {
+			/* failed writes to the low core are not recoverable */
 			rc = -EFAULT;
+			goto reinject_interrupt;
+		}
 	}
+
+	/* irq was successfully handed to the guest */
+	kfree(inti);
+	kvm_s390_set_psw_cc(vcpu, 1);
+	return 0;
+reinject_interrupt:
 	/*
 	 * If we encounter a problem storing the interruption code, the
 	 * instruction is suppressed from the guest's view: reinject the
 	 * interrupt.
 	 */
-	if (!rc)
+	if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) {
 		kfree(inti);
-	else
-		kvm_s390_reinject_io_int(vcpu->kvm, inti);
-no_interrupt:
-	/* Set condition code and we're done. */
-	if (!rc)
-		kvm_s390_set_psw_cc(vcpu, cc);
+		rc = -EFAULT;
+	}
+	/* don't set the cc, a pgm irq was injected or we drop to user space */
 	return rc ? -EFAULT : 0;
 }
 
@@ -467,6 +476,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 	for (n = mem->count - 1; n > 0 ; n--)
 		memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
 
+	memset(&mem->vm[0], 0, sizeof(mem->vm[0]));
 	mem->vm[0].cpus_total = cpus;
 	mem->vm[0].cpus_configured = cpus;
 	mem->vm[0].cpus_standby = 0;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 23b1e86b2122..755a7330d361 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -393,6 +393,9 @@ static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
 	case SIGP_STORE_STATUS_AT_ADDRESS:
 		vcpu->stat.instruction_sigp_store_status++;
 		break;
+	case SIGP_STORE_ADDITIONAL_STATUS:
+		vcpu->stat.instruction_sigp_store_adtl_status++;
+		break;
 	case SIGP_SET_PREFIX:
 		vcpu->stat.instruction_sigp_prefix++;
 		break;