Merge tag 'kvm-s390-next-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and features for kvm/next (4.6)

1. also provide the floating point registers via sync regs
2. Separate out intruction vs. data accesses
3. Fix program interrupts in some cases
4. Documentation fixes
5. dirty log improvements for huge guests

12 files changed, 254 insertions, 122 deletions

diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index d1ad9d5cae46..e3e314cb83e8 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -88,6 +88,8 @@ struct kvm_s390_io_adapter_req {
       perform a gmap translation for the guest address provided in addr,
       pin a userspace page for the translated address and add it to the
       list of mappings
+      Note: A new mapping will be created unconditionally; therefore,
+            the calling code should avoid making duplicate mappings.
 
     KVM_S390_IO_ADAPTER_UNMAP
       release a userspace page for the translated address specified in addr
diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt
index f083a168eb35..a9ea8774a45f 100644
--- a/Documentation/virtual/kvm/devices/vm.txt
+++ b/Documentation/virtual/kvm/devices/vm.txt
@@ -84,3 +84,55 @@ Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write
 	    -EFAULT if the given address is not accessible from kernel space
 	    -ENOMEM if not enough memory is available to process the ioctl
 	    0 in case of success
+
+3. GROUP: KVM_S390_VM_TOD
+Architectures: s390
+
+3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
+
+Allows user space to set/get the TOD clock extension (u8).
+
+Parameters: address of a buffer in user space to store the data (u8) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
+3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
+
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64).
+
+Parameters: address of a buffer in user space to store the data (u64) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+
+4. GROUP: KVM_S390_VM_CRYPTO
+Architectures: s390
+
+4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o)
+
+Allows user space to enable aes key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o)
+
+Allows user space to enable dea key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o)
+
+Allows user space to disable aes key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o)
+
+Allows user space to disable dea key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns:    0
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 8959ebb6d2c9..727e7f7b33fd 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -229,17 +229,11 @@ 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[1280];		/* 0x0700 */
-	struct kvm_s390_vregs vregs;	/* 0x0c00 */
+	__u8 reserved700[2304];		/* 0x0700 */
 } __packed;
 
 struct kvm_vcpu_stat {
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index fe84bd5fe7ce..347fe5afa419 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -154,6 +154,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
 #define KVM_SYNC_RICCB  (1UL << 7)
+#define KVM_SYNC_FPRS   (1UL << 8)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -168,9 +169,12 @@ 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 */
+	union {
+		__u64 vrs[32][2];	/* vector registers (KVM_SYNC_VRS) */
+		__u64 fprs[16];		/* fp registers (KVM_SYNC_FPRS) */
+	};
 	__u8  reserved[512];	/* for future vector expansion */
-	__u32 fpc;	/* only valid with vector registers */
+	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
 	__u8 padding[52];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 };
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d30db40437dc..66938d283b77 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
 }
 
 static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
-			  int write)
+			  enum gacc_mode mode)
 {
 	union alet alet;
 	struct ale ale;
@@ -454,7 +454,7 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
 		}
 	}
 
-	if (ale.fo == 1 && write)
+	if (ale.fo == 1 && mode == GACC_STORE)
 		return PGM_PROTECTION;
 
 	asce->val = aste.asce;
@@ -477,25 +477,28 @@ enum {
 };
 
 static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
-			 ar_t ar, int write)
+			 ar_t ar, enum gacc_mode mode)
 {
 	int rc;
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	struct trans_exc_code_bits *tec_bits;
 
 	memset(pgm, 0, sizeof(*pgm));
 	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	tec_bits->fsi = write ? FSI_STORE : FSI_FETCH;
-	tec_bits->as = psw_bits(*psw).as;
+	tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+	tec_bits->as = psw.as;
 
-	if (!psw_bits(*psw).t) {
+	if (!psw.t) {
 		asce->val = 0;
 		asce->r = 1;
 		return 0;
 	}
 
-	switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
+	if (mode == GACC_IFETCH)
+		psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY;
+
+	switch (psw.as) {
 	case PSW_AS_PRIMARY:
 		asce->val = vcpu->arch.sie_block->gcr[1];
 		return 0;
@@ -506,7 +509,7 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
 		asce->val = vcpu->arch.sie_block->gcr[13];
 		return 0;
 	case PSW_AS_ACCREG:
-		rc = ar_translation(vcpu, asce, ar, write);
+		rc = ar_translation(vcpu, asce, ar, mode);
 		switch (rc) {
 		case PGM_ALEN_TRANSLATION:
 		case PGM_ALE_SEQUENCE:
@@ -538,7 +541,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
  * @gva: guest virtual address
  * @gpa: points to where guest physical (absolute) address should be stored
  * @asce: effective asce
- * @write: indicates if access is a write access
+ * @mode: indicates the access mode to be used
  *
  * Translate a guest virtual address into a guest absolute address by means
  * of dynamic address translation as specified by the architecture.
@@ -554,7 +557,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
  */
 static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 				     unsigned long *gpa, const union asce asce,
-				     int write)
+				     enum gacc_mode mode)
 {
 	union vaddress vaddr = {.addr = gva};
 	union raddress raddr = {.addr = gva};
@@ -699,7 +702,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 real_address:
 	raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
 absolute_address:
-	if (write && dat_protection)
+	if (mode == GACC_STORE && dat_protection)
 		return PGM_PROTECTION;
 	if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
 		return PGM_ADDRESSING;
@@ -728,7 +731,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 
 static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 			    unsigned long *pages, unsigned long nr_pages,
-			    const union asce asce, int write)
+			    const union asce asce, enum gacc_mode mode)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -740,13 +743,13 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 	while (nr_pages) {
 		ga = kvm_s390_logical_to_effective(vcpu, ga);
 		tec_bits->addr = ga >> PAGE_SHIFT;
-		if (write && lap_enabled && is_low_address(ga)) {
+		if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) {
 			pgm->code = PGM_PROTECTION;
 			return pgm->code;
 		}
 		ga &= PAGE_MASK;
 		if (psw_bits(*psw).t) {
-			rc = guest_translate(vcpu, ga, pages, asce, write);
+			rc = guest_translate(vcpu, ga, pages, asce, mode);
 			if (rc < 0)
 				return rc;
 			if (rc == PGM_PROTECTION)
@@ -768,7 +771,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 }
 
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
-		 unsigned long len, int write)
+		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
 	unsigned long _len, nr_pages, gpa, idx;
@@ -780,7 +783,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 
 	if (!len)
 		return 0;
-	rc = get_vcpu_asce(vcpu, &asce, ar, write);
+	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
 	if (rc)
 		return rc;
 	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
@@ -792,11 +795,11 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	need_ipte_lock = psw_bits(*psw).t && !asce.r;
 	if (need_ipte_lock)
 		ipte_lock(vcpu);
-	rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write);
+	rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode);
 	for (idx = 0; idx < nr_pages && !rc; idx++) {
 		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
 		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (write)
+		if (mode == GACC_STORE)
 			rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
 		else
 			rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
@@ -812,7 +815,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 }
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
-		      void *data, unsigned long len, int write)
+		      void *data, unsigned long len, enum gacc_mode mode)
 {
 	unsigned long _len, gpa;
 	int rc = 0;
@@ -820,7 +823,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 	while (len && !rc) {
 		gpa = kvm_s390_real_to_abs(vcpu, gra);
 		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (write)
+		if (mode)
 			rc = write_guest_abs(vcpu, gpa, data, _len);
 		else
 			rc = read_guest_abs(vcpu, gpa, data, _len);
@@ -841,7 +844,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * has to take care of this.
  */
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-			    unsigned long *gpa, int write)
+			    unsigned long *gpa, enum gacc_mode mode)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -851,19 +854,19 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 
 	gva = kvm_s390_logical_to_effective(vcpu, gva);
 	tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	rc = get_vcpu_asce(vcpu, &asce, ar, write);
+	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
 	tec->addr = gva >> PAGE_SHIFT;
 	if (rc)
 		return rc;
 	if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
-		if (write) {
+		if (mode == GACC_STORE) {
 			rc = pgm->code = PGM_PROTECTION;
 			return rc;
 		}
 	}
 
 	if (psw_bits(*psw).t && !asce.r) {	/* Use DAT? */
-		rc = guest_translate(vcpu, gva, gpa, asce, write);
+		rc = guest_translate(vcpu, gva, gpa, asce, mode);
 		if (rc > 0) {
 			if (rc == PGM_PROTECTION)
 				tec->b61 = 1;
@@ -883,7 +886,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
  * check_gva_range - test a range of guest virtual addresses for accessibility
  */
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-		    unsigned long length, int is_write)
+		    unsigned long length, enum gacc_mode mode)
 {
 	unsigned long gpa;
 	unsigned long currlen;
@@ -892,7 +895,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 	ipte_lock(vcpu);
 	while (length > 0 && !rc) {
 		currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
-		rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write);
+		rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
 		gva += currlen;
 		length -= currlen;
 	}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index ef03726cc661..df0a79dd8159 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -155,16 +155,22 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
 	return kvm_read_guest(vcpu->kvm, gpa, data, len);
 }
 
+enum gacc_mode {
+	GACC_FETCH,
+	GACC_STORE,
+	GACC_IFETCH,
+};
+
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
-			    ar_t ar, unsigned long *gpa, int write);
+			    ar_t ar, unsigned long *gpa, enum gacc_mode mode);
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-		    unsigned long length, int is_write);
+		    unsigned long length, enum gacc_mode mode);
 
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
-		 unsigned long len, int write);
+		 unsigned long len, enum gacc_mode mode);
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
-		      void *data, unsigned long len, int write);
+		      void *data, unsigned long len, enum gacc_mode mode);
 
 /**
  * write_guest - copy data from kernel space to guest space
@@ -215,7 +221,7 @@ static inline __must_check
 int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 		unsigned long len)
 {
-	return access_guest(vcpu, ga, ar, data, len, 1);
+	return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
 }
 
 /**
@@ -235,7 +241,27 @@ static inline __must_check
 int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	       unsigned long len)
 {
-	return access_guest(vcpu, ga, ar, data, len, 0);
+	return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
+}
+
+/**
+ * read_guest_instr - copy instruction data from guest space to kernel space
+ * @vcpu: virtual cpu
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from the current psw address (guest space) to @data (kernel
+ * space).
+ *
+ * The behaviour of read_guest_instr is identical to read_guest, except that
+ * instruction data will be read from primary space when in home-space or
+ * address-space mode.
+ */
+static inline __must_check
+int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+{
+	return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
+			    GACC_IFETCH);
 }
 
 /**
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index d53c10753c46..2e6b54e4d3f9 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -38,17 +38,32 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0xeb] = kvm_s390_handle_eb,
 };
 
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+	u8 ilen = 0;
 
-	/* Use the length of the EXECUTE instruction if necessary */
-	if (sie_block->icptstatus & 1) {
-		ilc = (sie_block->icptstatus >> 4) & 0x6;
-		if (!ilc)
-			ilc = 4;
+	switch (vcpu->arch.sie_block->icptcode) {
+	case ICPT_INST:
+	case ICPT_INSTPROGI:
+	case ICPT_OPEREXC:
+	case ICPT_PARTEXEC:
+	case ICPT_IOINST:
+		/* instruction only stored for these icptcodes */
+		ilen = insn_length(vcpu->arch.sie_block->ipa >> 8);
+		/* Use the length of the EXECUTE instruction if necessary */
+		if (sie_block->icptstatus & 1) {
+			ilen = (sie_block->icptstatus >> 4) & 0x6;
+			if (!ilen)
+				ilen = 4;
+		}
+		break;
+	case ICPT_PROGI:
+		/* bit 1+2 of pgmilc are the ilc, so we directly get ilen */
+		ilen = vcpu->arch.sie_block->pgmilc & 0x6;
+		break;
 	}
-	sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+	return ilen;
 }
 
 static int handle_noop(struct kvm_vcpu *vcpu)
@@ -121,11 +136,13 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
-static void __extract_prog_irq(struct kvm_vcpu *vcpu,
-			       struct kvm_s390_pgm_info *pgm_info)
+static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
 {
-	memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
-	pgm_info->code = vcpu->arch.sie_block->iprcc;
+	struct kvm_s390_pgm_info pgm_info = {
+		.code = vcpu->arch.sie_block->iprcc,
+		/* the PSW has already been rewound */
+		.flags = KVM_S390_PGM_FLAGS_NO_REWIND,
+	};
 
 	switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
 	case PGM_AFX_TRANSLATION:
@@ -138,7 +155,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_PRIMARY_AUTHORITY:
 	case PGM_SECONDARY_AUTHORITY:
 	case PGM_SPACE_SWITCH:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
 		break;
 	case PGM_ALEN_TRANSLATION:
 	case PGM_ALE_SEQUENCE:
@@ -146,7 +163,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_ASTE_SEQUENCE:
 	case PGM_ASTE_VALIDITY:
 	case PGM_EXTENDED_AUTHORITY:
-		pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+		pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
 		break;
 	case PGM_ASCE_TYPE:
 	case PGM_PAGE_TRANSLATION:
@@ -154,32 +171,33 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_REGION_SECOND_TRANS:
 	case PGM_REGION_THIRD_TRANS:
 	case PGM_SEGMENT_TRANSLATION:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
-		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
-		pgm_info->op_access_id  = vcpu->arch.sie_block->oai;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info.op_access_id  = vcpu->arch.sie_block->oai;
 		break;
 	case PGM_MONITOR:
-		pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
-		pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+		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;
+		pgm_info.data_exc_code = vcpu->arch.sie_block->dxc;
 		break;
 	case PGM_PROTECTION:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
-		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
 		break;
 	default:
 		break;
 	}
 
 	if (vcpu->arch.sie_block->iprcc & PGM_PER) {
-		pgm_info->per_code = vcpu->arch.sie_block->perc;
-		pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
-		pgm_info->per_address = vcpu->arch.sie_block->peraddr;
-		pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+		pgm_info.per_code = vcpu->arch.sie_block->perc;
+		pgm_info.per_atmid = vcpu->arch.sie_block->peratmid;
+		pgm_info.per_address = vcpu->arch.sie_block->peraddr;
+		pgm_info.per_access_id = vcpu->arch.sie_block->peraid;
 	}
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 /*
@@ -208,7 +226,6 @@ static int handle_itdb(struct kvm_vcpu *vcpu)
 
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
-	struct kvm_s390_pgm_info pgm_info;
 	psw_t psw;
 	int rc;
 
@@ -234,8 +251,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	if (rc)
 		return rc;
 
-	__extract_prog_irq(vcpu, &pgm_info);
-	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	return inject_prog_on_prog_intercept(vcpu);
 }
 
 /**
@@ -302,7 +318,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the source is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
-				     reg2, &srcaddr, 0);
+				     reg2, &srcaddr, GACC_FETCH);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@@ -311,14 +327,14 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the destination is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
-				     reg1, &dstaddr, 1);
+				     reg1, &dstaddr, GACC_STORE);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
 	if (rc != 0)
 		return rc;
 
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 
 	return 0;
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f88ca72c3a77..87e2d1a89d74 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -335,23 +335,6 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
 	set_intercept_indicators_stop(vcpu);
 }
 
-static u16 get_ilc(struct kvm_vcpu *vcpu)
-{
-	switch (vcpu->arch.sie_block->icptcode) {
-	case ICPT_INST:
-	case ICPT_INSTPROGI:
-	case ICPT_OPEREXC:
-	case ICPT_PARTEXEC:
-	case ICPT_IOINST:
-		/* last instruction only stored for these icptcodes */
-		return insn_length(vcpu->arch.sie_block->ipa >> 8);
-	case ICPT_PROGI:
-		return vcpu->arch.sie_block->pgmilc;
-	default:
-		return 0;
-	}
-}
-
 static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -588,7 +571,7 @@ 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, nullifying = false;
-	u16 ilc = get_ilc(vcpu);
+	u16 ilen;
 
 	spin_lock(&li->lock);
 	pgm_info = li->irq.pgm;
@@ -596,8 +579,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	memset(&li->irq.pgm, 0, sizeof(pgm_info));
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
-		   pgm_info.code, ilc);
+	ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
+	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
+		   pgm_info.code, ilen);
 	vcpu->stat.deliver_program_int++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 					 pgm_info.code, 0);
@@ -681,10 +665,11 @@ 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);
+	if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+		kvm_s390_rewind_psw(vcpu, ilen);
 
-	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+	/* bit 1+2 of the target are the ilc, so we can directly use ilen */
+	rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
 	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
 				 (u64 *) __LC_LAST_BREAK);
 	rc |= put_guest_lc(vcpu, pgm_info.code,
@@ -1059,8 +1044,16 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 				   irq->u.pgm.code, 0);
 
+	if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+		/* auto detection if no valid ILC was given */
+		irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+		irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+		irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+	}
+
 	if (irq->u.pgm.code == PGM_PER) {
 		li->irq.pgm.code |= PGM_PER;
+		li->irq.pgm.flags = irq->u.pgm.flags;
 		/* only modify PER related information */
 		li->irq.pgm.per_address = irq->u.pgm.per_address;
 		li->irq.pgm.per_code = irq->u.pgm.per_code;
@@ -1069,6 +1062,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	} else if (!(irq->u.pgm.code & PGM_PER)) {
 		li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
 				   irq->u.pgm.code;
+		li->irq.pgm.flags = irq->u.pgm.flags;
 		/* only modify non-PER information */
 		li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
 		li->irq.pgm.mon_code = irq->u.pgm.mon_code;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4af21c771f9b..28bd5ea1b08f 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -274,7 +274,6 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 	unsigned long address;
 	struct gmap *gmap = kvm->arch.gmap;
 
-	down_read(&gmap->mm->mmap_sem);
 	/* Loop over all guest pages */
 	last_gfn = memslot->base_gfn + memslot->npages;
 	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
@@ -282,8 +281,10 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 
 		if (gmap_test_and_clear_dirty(address, gmap))
 			mark_page_dirty(kvm, cur_gfn);
+		if (fatal_signal_pending(current))
+			return;
+		cond_resched();
 	}
-	up_read(&gmap->mm->mmap_sem);
 }
 
 /* Section: vm related */
@@ -1414,8 +1415,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_PFAULT;
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
-	if (test_kvm_facility(vcpu->kvm, 129))
+	/* fprs can be synchronized via vrs, even if the guest has no vx. With
+	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+	 */
+	if (MACHINE_HAS_VX)
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+	else
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		return __kvm_ucontrol_vcpu_init(vcpu);
@@ -1430,10 +1436,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
 	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
-	/* Depending on MACHINE_HAS_VX, data stored to vrs either
-	 * has vector register or floating point register format.
-	 */
-	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	if (MACHINE_HAS_VX)
+		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	else
+		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
 	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
@@ -2158,8 +2164,10 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 
 static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	u8 opcode;
+	struct kvm_s390_pgm_info pgm_info = {
+		.code = PGM_ADDRESSING,
+	};
+	u8 opcode, ilen;
 	int rc;
 
 	VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
@@ -2173,12 +2181,21 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 	 * 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, 0, &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);
+	rc = read_guest_instr(vcpu, &opcode, 1);
+	ilen = insn_length(opcode);
+	if (rc < 0) {
+		return rc;
+	} else if (rc) {
+		/* Instruction-Fetching Exceptions - we can't detect the ilen.
+		 * Forward by arbitrary ilc, injection will take care of
+		 * nullification if necessary.
+		 */
+		pgm_info = vcpu->arch.pgm;
+		ilen = 4;
+	}
+	pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
+	kvm_s390_forward_psw(vcpu, ilen);
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -2386,7 +2403,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 				     fprs, 128);
 	} else {
 		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
-				     vcpu->run->s.regs.vrs, 128);
+				     vcpu->run->s.regs.fprs, 128);
 	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
@@ -2605,7 +2622,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 	switch (mop->op) {
 	case KVM_S390_MEMOP_LOGICAL_READ:
 		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false);
+			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+					    mop->size, GACC_FETCH);
 			break;
 		}
 		r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
@@ -2616,7 +2634,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_S390_MEMOP_LOGICAL_WRITE:
 		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true);
+			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+					    mop->size, GACC_STORE);
 			break;
 		}
 		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index df1abada1f36..1c756c7dd0c2 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,6 +19,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <asm/facility.h>
+#include <asm/processor.h>
 
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
@@ -212,8 +213,22 @@ int kvm_s390_reinject_io_int(struct kvm *kvm,
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in intercept.c */
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc);
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu);
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+static inline void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+	sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilen);
+}
+static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+	kvm_s390_rewind_psw(vcpu, -ilen);
+}
+static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
+{
+	kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu));
+}
 
 /* implemented in priv.c */
 int is_valid_psw(psw_t *psw);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ed74e86d9b9e..add990945986 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -173,7 +173,7 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
 	return 0;
 }
@@ -184,7 +184,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
 	if (psw_bits(vcpu->arch.sie_block->gpsw).p)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
 	return 0;
 }
@@ -759,8 +759,8 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 	if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	/* Rewind PSW to repeat the ESSA instruction */
-	kvm_s390_rewind_psw(vcpu, 4);
+	/* Retry the ESSA instruction */
+	kvm_s390_retry_instr(vcpu);
 	vcpu->arch.sie_block->cbrlo &= PAGE_MASK;	/* reset nceo */
 	cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
 	down_read(&gmap->mm->mmap_sem);
@@ -981,11 +981,12 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
 		ipte_lock(vcpu);
-	ret = guest_translate_address(vcpu, address1, ar, &gpa, 1);
+	ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE);
 	if (ret == PGM_PROTECTION) {
 		/* Write protected? Try again with read-only... */
 		cc = 1;
-		ret = guest_translate_address(vcpu, address1, ar, &gpa, 0);
+		ret = guest_translate_address(vcpu, address1, ar, &gpa,
+					      GACC_FETCH);
 	}
 	if (ret) {
 		if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 9da905157cee..a2fe0ac1d61a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -541,7 +541,13 @@ struct kvm_s390_pgm_info {
 	__u8 exc_access_id;
 	__u8 per_access_id;
 	__u8 op_access_id;
-	__u8 pad[3];
+#define KVM_S390_PGM_FLAGS_ILC_VALID	0x01
+#define KVM_S390_PGM_FLAGS_ILC_0	0x02
+#define KVM_S390_PGM_FLAGS_ILC_1	0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK	0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND	0x08
+	__u8 flags;
+	__u8 pad[2];
 };
 
 struct kvm_s390_prefix_info {