Merge branch 'linus' into WIP.x86/boot, to fix up conflicts and to pick up updates

Conflicts: arch/x86/xen/setup.c Signed-off-by: Ingo Molnar <mingo@kernel.org>
author: Ingo Molnar <mingo@kernel.org> 2017-03-01 11:02:26 +0300
committer: Ingo Molnar <mingo@kernel.org> 2017-03-01 11:02:26 +0300
commit: 0871d5a66da5c41151e0896a90298b163e42f2e0 (patch)
tree: 1ba71fab9016cb28bb9d18ffd62b6b744f2f761c /arch/s390
parent: e22af0be2cf654bb225f19750c6b9aab1627dc9e (diff)
parent: 2d6be4abf514fc26c83d239c7f31da1f95e4a31d (diff)
download: linux-0871d5a66da5c41151e0896a90298b163e42f2e0.tar.xz
101 files changed, 1894 insertions, 907 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c6722112527d..a2dcef0aacc7 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -62,9 +62,6 @@ config PCI_QUIRKS
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
-config DEBUG_RODATA
-	def_bool y
-
 config S390
 	def_bool y
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
@@ -72,7 +69,10 @@ config S390
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
@@ -134,9 +134,11 @@ config S390
 	select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
+	select DMA_NOOP_OPS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 26c5d5beb4be..ba5f878a295c 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -17,7 +17,7 @@ config S390_PTDUMP
 	  kernel.
 	  If in doubt, say "N"
 
-config DEBUG_SET_MODULE_RONX
+config EARLY_PRINTK
 	def_bool y
-	depends on MODULES
+
 endmenu
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 69b23b25ac34..08b9e942a262 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -113,21 +113,21 @@ static void appldata_get_os_data(void *data)
 	j = 0;
 	for_each_online_cpu(i) {
 		os_data->os_cpu[j].per_cpu_user =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 6bd2c9022be3..f7e4c834ea24 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -19,7 +19,8 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 GCOV_PROFILE := n
 UBSAN_SANITIZE := n
 
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o sclp.o ebcdic.o als.o)
+OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
+OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
 OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 8515dd5a5663..fa95041fa9f6 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -66,7 +66,7 @@ static unsigned long free_mem_end_ptr;
 
 static int puts(const char *s)
 {
-	_sclp_print_early(s);
+	sclp_early_printk(s);
 	return 0;
 }
 
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index e00975361fec..143b1e00b818 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -678,6 +678,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2cf87343b590..2358bf33c5ef 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -628,6 +628,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index d1033de4c4ee..402c530c6da5 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
-obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
+obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o paes_s390.o
 obj-$(CONFIG_S390_PRNG) += prng.o
 obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
 obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 303d28eb03a2..591cbdf615af 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -28,6 +28,7 @@
 #include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <linux/fips.h>
 #include <crypto/xts.h>
 #include <asm/cpacf.h>
 
@@ -501,6 +502,12 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	if (err)
 		return err;
 
+	/* In fips mode only 128 bit or 256 bit keys are valid */
+	if (fips_enabled && key_len != 32 && key_len != 64) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
 	/* Pick the correct function code based on the key length */
 	fc = (key_len == 32) ? CPACF_KM_XTS_128 :
 	     (key_len == 64) ? CPACF_KM_XTS_256 : 0;
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 8b83144206eb..0d296662bbf0 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
+#include <linux/fips.h>
 #include <crypto/algapi.h>
 #include <crypto/des.h>
 #include <asm/cpacf.h>
@@ -221,6 +222,8 @@ static struct crypto_alg cbc_des_alg = {
  *   same as DES.  Implementers MUST reject keys that exhibit this
  *   property.
  *
+ *   In fips mode additinally check for all 3 keys are unique.
+ *
  */
 static int des3_setkey(struct crypto_tfm *tfm, const u8 *key,
 		       unsigned int key_len)
@@ -234,6 +237,17 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key,
 		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
 		return -EINVAL;
 	}
+
+	/* in fips mode, ensure k1 != k2 and k2 != k3 and k1 != k3 */
+	if (fips_enabled &&
+	    !(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
+	      crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
+			    DES_KEY_SIZE) &&
+	      crypto_memneq(key, &key[DES_KEY_SIZE * 2], DES_KEY_SIZE))) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
 	memcpy(ctx->key, key, key_len);
 	return 0;
 }
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
new file mode 100644
index 000000000000..d69ea495c4d7
--- /dev/null
+++ b/arch/s390/crypto/paes_s390.c
@@ -0,0 +1,619 @@
+/*
+ * Cryptographic API.
+ *
+ * s390 implementation of the AES Cipher Algorithm with protected keys.
+ *
+ * s390 Version:
+ *   Copyright IBM Corp. 2017
+ *   Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		Harald Freudenberger <freude@de.ibm.com>
+ *
+ * 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)
+ * as published by the Free Software Foundation.
+ *
+ */
+
+#define KMSG_COMPONENT "paes_s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <crypto/xts.h>
+#include <asm/cpacf.h>
+#include <asm/pkey.h>
+
+static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
+
+static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
+
+struct s390_paes_ctx {
+	struct pkey_seckey sk;
+	struct pkey_protkey pk;
+	unsigned long fc;
+};
+
+struct s390_pxts_ctx {
+	struct pkey_seckey sk[2];
+	struct pkey_protkey pk[2];
+	unsigned long fc;
+};
+
+static inline int __paes_convert_key(struct pkey_seckey *sk,
+				     struct pkey_protkey *pk)
+{
+	int i, ret;
+
+	/* try three times in case of failure */
+	for (i = 0; i < 3; i++) {
+		ret = pkey_skey2pkey(sk, pk);
+		if (ret == 0)
+			break;
+	}
+
+	return ret;
+}
+
+static int __paes_set_key(struct s390_paes_ctx *ctx)
+{
+	unsigned long fc;
+
+	if (__paes_convert_key(&ctx->sk, &ctx->pk))
+		return -EINVAL;
+
+	/* Pick the correct function code based on the protected key type */
+	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KM_PAES_128 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KM_PAES_192 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KM_PAES_256 : 0;
+
+	/* Check if the function code is available */
+	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+
+	return ctx->fc ? 0 : -EINVAL;
+}
+
+static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (key_len != SECKEYBLOBSIZE)
+		return -EINVAL;
+
+	memcpy(ctx->sk.seckey, in_key, SECKEYBLOBSIZE);
+	if (__paes_set_key(ctx)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int ecb_paes_crypt(struct blkcipher_desc *desc,
+			  unsigned long modifier,
+			  struct blkcipher_walk *walk)
+{
+	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int nbytes, n, k;
+	int ret;
+
+	ret = blkcipher_walk_virt(desc, walk);
+	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+		/* only use complete blocks */
+		n = nbytes & ~(AES_BLOCK_SIZE - 1);
+		k = cpacf_km(ctx->fc | modifier, ctx->pk.protkey,
+			     walk->dst.virt.addr, walk->src.virt.addr, n);
+		if (k)
+			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+		if (k < n) {
+			if (__paes_set_key(ctx) != 0)
+				return blkcipher_walk_done(desc, walk, -EIO);
+		}
+	}
+	return ret;
+}
+
+static int ecb_paes_encrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_paes_crypt(desc, CPACF_ENCRYPT, &walk);
+}
+
+static int ecb_paes_decrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_paes_crypt(desc, CPACF_DECRYPT, &walk);
+}
+
+static struct crypto_alg ecb_paes_alg = {
+	.cra_name		=	"ecb(paes)",
+	.cra_driver_name	=	"ecb-paes-s390",
+	.cra_priority		=	400,	/* combo: aes + ecb */
+	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		=	AES_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
+	.cra_type		=	&crypto_blkcipher_type,
+	.cra_module		=	THIS_MODULE,
+	.cra_list		=	LIST_HEAD_INIT(ecb_paes_alg.cra_list),
+	.cra_u			=	{
+		.blkcipher = {
+			.min_keysize		=	SECKEYBLOBSIZE,
+			.max_keysize		=	SECKEYBLOBSIZE,
+			.setkey			=	ecb_paes_set_key,
+			.encrypt		=	ecb_paes_encrypt,
+			.decrypt		=	ecb_paes_decrypt,
+		}
+	}
+};
+
+static int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
+{
+	unsigned long fc;
+
+	if (__paes_convert_key(&ctx->sk, &ctx->pk))
+		return -EINVAL;
+
+	/* Pick the correct function code based on the protected key type */
+	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KMC_PAES_128 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KMC_PAES_192 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KMC_PAES_256 : 0;
+
+	/* Check if the function code is available */
+	ctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0;
+
+	return ctx->fc ? 0 : -EINVAL;
+}
+
+static int cbc_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	memcpy(ctx->sk.seckey, in_key, SECKEYBLOBSIZE);
+	if (__cbc_paes_set_key(ctx)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
+			  struct blkcipher_walk *walk)
+{
+	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int nbytes, n, k;
+	int ret;
+	struct {
+		u8 iv[AES_BLOCK_SIZE];
+		u8 key[MAXPROTKEYSIZE];
+	} param;
+
+	ret = blkcipher_walk_virt(desc, walk);
+	memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+	memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+		/* only use complete blocks */
+		n = nbytes & ~(AES_BLOCK_SIZE - 1);
+		k = cpacf_kmc(ctx->fc | modifier, &param,
+			      walk->dst.virt.addr, walk->src.virt.addr, n);
+		if (k)
+			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+		if (n < k) {
+			if (__cbc_paes_set_key(ctx) != 0)
+				return blkcipher_walk_done(desc, walk, -EIO);
+			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+		}
+	}
+	memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
+	return ret;
+}
+
+static int cbc_paes_encrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return cbc_paes_crypt(desc, 0, &walk);
+}
+
+static int cbc_paes_decrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return cbc_paes_crypt(desc, CPACF_DECRYPT, &walk);
+}
+
+static struct crypto_alg cbc_paes_alg = {
+	.cra_name		=	"cbc(paes)",
+	.cra_driver_name	=	"cbc-paes-s390",
+	.cra_priority		=	400,	/* combo: aes + cbc */
+	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		=	AES_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
+	.cra_type		=	&crypto_blkcipher_type,
+	.cra_module		=	THIS_MODULE,
+	.cra_list		=	LIST_HEAD_INIT(cbc_paes_alg.cra_list),
+	.cra_u			=	{
+		.blkcipher = {
+			.min_keysize		=	SECKEYBLOBSIZE,
+			.max_keysize		=	SECKEYBLOBSIZE,
+			.ivsize			=	AES_BLOCK_SIZE,
+			.setkey			=	cbc_paes_set_key,
+			.encrypt		=	cbc_paes_encrypt,
+			.decrypt		=	cbc_paes_decrypt,
+		}
+	}
+};
+
+static int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
+{
+	unsigned long fc;
+
+	if (__paes_convert_key(&ctx->sk[0], &ctx->pk[0]) ||
+	    __paes_convert_key(&ctx->sk[1], &ctx->pk[1]))
+		return -EINVAL;
+
+	if (ctx->pk[0].type != ctx->pk[1].type)
+		return -EINVAL;
+
+	/* Pick the correct function code based on the protected key type */
+	fc = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? CPACF_KM_PXTS_128 :
+		(ctx->pk[0].type == PKEY_KEYTYPE_AES_256) ?
+		CPACF_KM_PXTS_256 : 0;
+
+	/* Check if the function code is available */
+	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+
+	return ctx->fc ? 0 : -EINVAL;
+}
+
+static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+	u8 ckey[2 * AES_MAX_KEY_SIZE];
+	unsigned int ckey_len;
+
+	memcpy(ctx->sk[0].seckey, in_key, SECKEYBLOBSIZE);
+	memcpy(ctx->sk[1].seckey, in_key + SECKEYBLOBSIZE, SECKEYBLOBSIZE);
+	if (__xts_paes_set_key(ctx)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
+	/*
+	 * xts_check_key verifies the key length is not odd and makes
+	 * sure that the two keys are not the same. This can be done
+	 * on the two protected keys as well
+	 */
+	ckey_len = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ?
+		AES_KEYSIZE_128 : AES_KEYSIZE_256;
+	memcpy(ckey, ctx->pk[0].protkey, ckey_len);
+	memcpy(ckey + ckey_len, ctx->pk[1].protkey, ckey_len);
+	return xts_check_key(tfm, ckey, 2*ckey_len);
+}
+
+static int xts_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
+			  struct blkcipher_walk *walk)
+{
+	struct s390_pxts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int keylen, offset, nbytes, n, k;
+	int ret;
+	struct {
+		u8 key[MAXPROTKEYSIZE];	/* key + verification pattern */
+		u8 tweak[16];
+		u8 block[16];
+		u8 bit[16];
+		u8 xts[16];
+	} pcc_param;
+	struct {
+		u8 key[MAXPROTKEYSIZE];	/* key + verification pattern */
+		u8 init[16];
+	} xts_param;
+
+	ret = blkcipher_walk_virt(desc, walk);
+	keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 48 : 64;
+	offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 16 : 0;
+retry:
+	memset(&pcc_param, 0, sizeof(pcc_param));
+	memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+	memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen);
+	cpacf_pcc(ctx->fc, pcc_param.key + offset);
+
+	memcpy(xts_param.key + offset, ctx->pk[0].protkey, keylen);
+	memcpy(xts_param.init, pcc_param.xts, 16);
+
+	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+		/* only use complete blocks */
+		n = nbytes & ~(AES_BLOCK_SIZE - 1);
+		k = cpacf_km(ctx->fc | modifier, xts_param.key + offset,
+			     walk->dst.virt.addr, walk->src.virt.addr, n);
+		if (k)
+			ret = blkcipher_walk_done(desc, walk, nbytes - k);
+		if (k < n) {
+			if (__xts_paes_set_key(ctx) != 0)
+				return blkcipher_walk_done(desc, walk, -EIO);
+			goto retry;
+		}
+	}
+	return ret;
+}
+
+static int xts_paes_encrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return xts_paes_crypt(desc, 0, &walk);
+}
+
+static int xts_paes_decrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return xts_paes_crypt(desc, CPACF_DECRYPT, &walk);
+}
+
+static struct crypto_alg xts_paes_alg = {
+	.cra_name		=	"xts(paes)",
+	.cra_driver_name	=	"xts-paes-s390",
+	.cra_priority		=	400,	/* combo: aes + xts */
+	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		=	AES_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct s390_pxts_ctx),
+	.cra_type		=	&crypto_blkcipher_type,
+	.cra_module		=	THIS_MODULE,
+	.cra_list		=	LIST_HEAD_INIT(xts_paes_alg.cra_list),
+	.cra_u			=	{
+		.blkcipher = {
+			.min_keysize		=	2 * SECKEYBLOBSIZE,
+			.max_keysize		=	2 * SECKEYBLOBSIZE,
+			.ivsize			=	AES_BLOCK_SIZE,
+			.setkey			=	xts_paes_set_key,
+			.encrypt		=	xts_paes_encrypt,
+			.decrypt		=	xts_paes_decrypt,
+		}
+	}
+};
+
+static int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
+{
+	unsigned long fc;
+
+	if (__paes_convert_key(&ctx->sk, &ctx->pk))
+		return -EINVAL;
+
+	/* Pick the correct function code based on the protected key type */
+	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KMCTR_PAES_128 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KMCTR_PAES_192 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ?
+		CPACF_KMCTR_PAES_256 : 0;
+
+	/* Check if the function code is available */
+	ctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0;
+
+	return ctx->fc ? 0 : -EINVAL;
+}
+
+static int ctr_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	memcpy(ctx->sk.seckey, in_key, key_len);
+	if (__ctr_paes_set_key(ctx)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	memcpy(ctrptr, iv, AES_BLOCK_SIZE);
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = (n / AES_BLOCK_SIZE) - 1; i > 0; i--) {
+		memcpy(ctrptr + AES_BLOCK_SIZE, ctrptr, AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + AES_BLOCK_SIZE, AES_BLOCK_SIZE);
+		ctrptr += AES_BLOCK_SIZE;
+	}
+	return n;
+}
+
+static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
+			  struct blkcipher_walk *walk)
+{
+	struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	u8 buf[AES_BLOCK_SIZE], *ctrptr;
+	unsigned int nbytes, n, k;
+	int ret, locked;
+
+	locked = spin_trylock(&ctrblk_lock);
+
+	ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
+	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+		n = AES_BLOCK_SIZE;
+		if (nbytes >= 2*AES_BLOCK_SIZE && locked)
+			n = __ctrblk_init(ctrblk, walk->iv, nbytes);
+		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv;
+		k = cpacf_kmctr(ctx->fc | modifier, ctx->pk.protkey,
+				walk->dst.virt.addr, walk->src.virt.addr,
+				n, ctrptr);
+		if (k) {
+			if (ctrptr == ctrblk)
+				memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE,
+				       AES_BLOCK_SIZE);
+			crypto_inc(walk->iv, AES_BLOCK_SIZE);
+			ret = blkcipher_walk_done(desc, walk, nbytes - n);
+		}
+		if (k < n) {
+			if (__ctr_paes_set_key(ctx) != 0)
+				return blkcipher_walk_done(desc, walk, -EIO);
+		}
+	}
+	if (locked)
+		spin_unlock(&ctrblk_lock);
+	/*
+	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
+	 */
+	if (nbytes) {
+		while (1) {
+			if (cpacf_kmctr(ctx->fc | modifier,
+					ctx->pk.protkey, buf,
+					walk->src.virt.addr, AES_BLOCK_SIZE,
+					walk->iv) == AES_BLOCK_SIZE)
+				break;
+			if (__ctr_paes_set_key(ctx) != 0)
+				return blkcipher_walk_done(desc, walk, -EIO);
+		}
+		memcpy(walk->dst.virt.addr, buf, nbytes);
+		crypto_inc(walk->iv, AES_BLOCK_SIZE);
+		ret = blkcipher_walk_done(desc, walk, 0);
+	}
+
+	return ret;
+}
+
+static int ctr_paes_encrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ctr_paes_crypt(desc, 0, &walk);
+}
+
+static int ctr_paes_decrypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst, struct scatterlist *src,
+			    unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ctr_paes_crypt(desc, CPACF_DECRYPT, &walk);
+}
+
+static struct crypto_alg ctr_paes_alg = {
+	.cra_name		=	"ctr(paes)",
+	.cra_driver_name	=	"ctr-paes-s390",
+	.cra_priority		=	400,	/* combo: aes + ctr */
+	.cra_flags		=	CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		=	1,
+	.cra_ctxsize		=	sizeof(struct s390_paes_ctx),
+	.cra_type		=	&crypto_blkcipher_type,
+	.cra_module		=	THIS_MODULE,
+	.cra_list		=	LIST_HEAD_INIT(ctr_paes_alg.cra_list),
+	.cra_u			=	{
+		.blkcipher = {
+			.min_keysize		=	SECKEYBLOBSIZE,
+			.max_keysize		=	SECKEYBLOBSIZE,
+			.ivsize			=	AES_BLOCK_SIZE,
+			.setkey			=	ctr_paes_set_key,
+			.encrypt		=	ctr_paes_encrypt,
+			.decrypt		=	ctr_paes_decrypt,
+		}
+	}
+};
+
+static inline void __crypto_unregister_alg(struct crypto_alg *alg)
+{
+	if (!list_empty(&alg->cra_list))
+		crypto_unregister_alg(alg);
+}
+
+static void paes_s390_fini(void)
+{
+	if (ctrblk)
+		free_page((unsigned long) ctrblk);
+	__crypto_unregister_alg(&ctr_paes_alg);
+	__crypto_unregister_alg(&xts_paes_alg);
+	__crypto_unregister_alg(&cbc_paes_alg);
+	__crypto_unregister_alg(&ecb_paes_alg);
+}
+
+static int __init paes_s390_init(void)
+{
+	int ret;
+
+	/* Query available functions for KM, KMC and KMCTR */
+	cpacf_query(CPACF_KM, &km_functions);
+	cpacf_query(CPACF_KMC, &kmc_functions);
+	cpacf_query(CPACF_KMCTR, &kmctr_functions);
+
+	if (cpacf_test_func(&km_functions, CPACF_KM_PAES_128) ||
+	    cpacf_test_func(&km_functions, CPACF_KM_PAES_192) ||
+	    cpacf_test_func(&km_functions, CPACF_KM_PAES_256)) {
+		ret = crypto_register_alg(&ecb_paes_alg);
+		if (ret)
+			goto out_err;
+	}
+
+	if (cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
+	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
+	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) {
+		ret = crypto_register_alg(&cbc_paes_alg);
+		if (ret)
+			goto out_err;
+	}
+
+	if (cpacf_test_func(&km_functions, CPACF_KM_PXTS_128) ||
+	    cpacf_test_func(&km_functions, CPACF_KM_PXTS_256)) {
+		ret = crypto_register_alg(&xts_paes_alg);
+		if (ret)
+			goto out_err;
+	}
+
+	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_128) ||
+	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_192) ||
+	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_256)) {
+		ret = crypto_register_alg(&ctr_paes_alg);
+		if (ret)
+			goto out_err;
+		ctrblk = (u8 *) __get_free_page(GFP_KERNEL);
+		if (!ctrblk) {
+			ret = -ENOMEM;
+			goto out_err;
+		}
+	}
+
+	return 0;
+out_err:
+	paes_s390_fini();
+	return ret;
+}
+
+module_init(paes_s390_init);
+module_exit(paes_s390_fini);
+
+MODULE_ALIAS_CRYPTO("aes-all");
+
+MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm with protected keys");
+MODULE_LICENSE("GPL");
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index daf9bb063aaa..85b7f5efe06a 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -110,22 +110,30 @@ static const u8 initial_parm_block[32] __initconst = {
 
 /*** helper functions ***/
 
+/*
+ * generate_entropy:
+ * This algorithm produces 64 bytes of entropy data based on 1024
+ * individual stckf() invocations assuming that each stckf() value
+ * contributes 0.25 bits of entropy. So the caller gets 256 bit
+ * entropy per 64 byte or 4 bits entropy per byte.
+ */
 static int generate_entropy(u8 *ebuf, size_t nbytes)
 {
 	int n, ret = 0;
-	u8 *pg, *h, hash[32];
+	u8 *pg, *h, hash[64];
 
-	pg = (u8 *) __get_free_page(GFP_KERNEL);
+	/* allocate 2 pages */
+	pg = (u8 *) __get_free_pages(GFP_KERNEL, 1);
 	if (!pg) {
 		prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
 		return -ENOMEM;
 	}
 
 	while (nbytes) {
-		/* fill page with urandom bytes */
-		get_random_bytes(pg, PAGE_SIZE);
-		/* exor page with stckf values */
-		for (n = 0; n < PAGE_SIZE / sizeof(u64); n++) {
+		/* fill pages with urandom bytes */
+		get_random_bytes(pg, 2*PAGE_SIZE);
+		/* exor pages with 1024 stckf values */
+		for (n = 0; n < 2 * PAGE_SIZE / sizeof(u64); n++) {
 			u64 *p = ((u64 *)pg) + n;
 			*p ^= get_tod_clock_fast();
 		}
@@ -134,8 +142,8 @@ static int generate_entropy(u8 *ebuf, size_t nbytes)
 			h = hash;
 		else
 			h = ebuf;
-		/* generate sha256 from this page */
-		cpacf_kimd(CPACF_KIMD_SHA_256, h, pg, PAGE_SIZE);
+		/* hash over the filled pages */
+		cpacf_kimd(CPACF_KIMD_SHA_512, h, pg, 2*PAGE_SIZE);
 		if (n < sizeof(hash))
 			memcpy(ebuf, hash, n);
 		ret += n;
@@ -143,7 +151,7 @@ static int generate_entropy(u8 *ebuf, size_t nbytes)
 		nbytes -= n;
 	}
 
-	free_page((unsigned long)pg);
+	free_pages((unsigned long)pg, 1);
 	return ret;
 }
 
@@ -334,7 +342,7 @@ static int __init prng_sha512_selftest(void)
 static int __init prng_sha512_instantiate(void)
 {
 	int ret, datalen;
-	u8 seed[64];
+	u8 seed[64 + 32 + 16];
 
 	pr_debug("prng runs in SHA-512 mode "
 		 "with chunksize=%d and reseed_limit=%u\n",
@@ -357,12 +365,12 @@ static int __init prng_sha512_instantiate(void)
 	if (ret)
 		goto outfree;
 
-	/* generate initial seed bytestring, first 48 bytes of entropy */
-	ret = generate_entropy(seed, 48);
-	if (ret != 48)
+	/* generate initial seed bytestring, with 256 + 128 bits entropy */
+	ret = generate_entropy(seed, 64 + 32);
+	if (ret != 64 + 32)
 		goto outfree;
 	/* followed by 16 bytes of unique nonce */
-	get_tod_clock_ext(seed + 48);
+	get_tod_clock_ext(seed + 64 + 32);
 
 	/* initial seed of the ppno drng */
 	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED,
@@ -395,9 +403,9 @@ static void prng_sha512_deinstantiate(void)
 static int prng_sha512_reseed(void)
 {
 	int ret;
-	u8 seed[32];
+	u8 seed[64];
 
-	/* generate 32 bytes of fresh entropy */
+	/* fetch 256 bits of fresh entropy */
 	ret = generate_entropy(seed, sizeof(seed));
 	if (ret != sizeof(seed))
 		return ret;
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index d00e368fb5e6..68bfd09f1b02 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -229,6 +229,7 @@ CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h
index 58fae7d098cf..0499334f9473 100644
--- a/arch/s390/include/asm/cacheflush.h
+++ b/arch/s390/include/asm/cacheflush.h
@@ -4,9 +4,31 @@
 /* Caches aren't brain-dead on the s390. */
 #include <asm-generic/cacheflush.h>
 
-int set_memory_ro(unsigned long addr, int numpages);
-int set_memory_rw(unsigned long addr, int numpages);
-int set_memory_nx(unsigned long addr, int numpages);
-int set_memory_x(unsigned long addr, int numpages);
+#define SET_MEMORY_RO	1UL
+#define SET_MEMORY_RW	2UL
+#define SET_MEMORY_NX	4UL
+#define SET_MEMORY_X	8UL
+
+int __set_memory(unsigned long addr, int numpages, unsigned long flags);
+
+static inline int set_memory_ro(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_RO);
+}
+
+static inline int set_memory_rw(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_RW);
+}
+
+static inline int set_memory_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_NX);
+}
+
+static inline int set_memory_x(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_X);
+}
 
 #endif /* _S390_CACHEFLUSH_H */
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index 2c680db7e5c1..e2dfbf280d12 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -28,8 +28,9 @@
 #define CPACF_PPNO		0xb93c		/* MSA5 */
 
 /*
- * Decryption modifier bit
+ * En/decryption modifier bits
  */
+#define CPACF_ENCRYPT		0x00
 #define CPACF_DECRYPT		0x80
 
 /*
@@ -42,8 +43,13 @@
 #define CPACF_KM_AES_128	0x12
 #define CPACF_KM_AES_192	0x13
 #define CPACF_KM_AES_256	0x14
+#define CPACF_KM_PAES_128	0x1a
+#define CPACF_KM_PAES_192	0x1b
+#define CPACF_KM_PAES_256	0x1c
 #define CPACF_KM_XTS_128	0x32
 #define CPACF_KM_XTS_256	0x34
+#define CPACF_KM_PXTS_128	0x3a
+#define CPACF_KM_PXTS_256	0x3c
 
 /*
  * Function codes for the KMC (CIPHER MESSAGE WITH CHAINING)
@@ -56,6 +62,9 @@
 #define CPACF_KMC_AES_128	0x12
 #define CPACF_KMC_AES_192	0x13
 #define CPACF_KMC_AES_256	0x14
+#define CPACF_KMC_PAES_128	0x1a
+#define CPACF_KMC_PAES_192	0x1b
+#define CPACF_KMC_PAES_256	0x1c
 #define CPACF_KMC_PRNG		0x43
 
 /*
@@ -69,6 +78,9 @@
 #define CPACF_KMCTR_AES_128	0x12
 #define CPACF_KMCTR_AES_192	0x13
 #define CPACF_KMCTR_AES_256	0x14
+#define CPACF_KMCTR_PAES_128	0x1a
+#define CPACF_KMCTR_PAES_192	0x1b
+#define CPACF_KMCTR_PAES_256	0x1c
 
 /*
  * Function codes for the KIMD (COMPUTE INTERMEDIATE MESSAGE DIGEST)
@@ -99,6 +111,18 @@
 #define CPACF_KMAC_TDEA_192	0x03
 
 /*
+ * Function codes for the PCKMO (PERFORM CRYPTOGRAPHIC KEY MANAGEMENT)
+ * instruction
+ */
+#define CPACF_PCKMO_QUERY		0x00
+#define CPACF_PCKMO_ENC_DES_KEY		0x01
+#define CPACF_PCKMO_ENC_TDES_128_KEY	0x02
+#define CPACF_PCKMO_ENC_TDES_192_KEY	0x03
+#define CPACF_PCKMO_ENC_AES_128_KEY	0x12
+#define CPACF_PCKMO_ENC_AES_192_KEY	0x13
+#define CPACF_PCKMO_ENC_AES_256_KEY	0x14
+
+/*
  * Function codes for the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION)
  * instruction
  */
@@ -397,4 +421,24 @@ static inline void cpacf_pcc(unsigned long func, void *param)
 		: "cc", "memory");
 }
 
+/**
+ * cpacf_pckmo() - executes the PCKMO (PERFORM CRYPTOGRAPHIC KEY
+ *		  MANAGEMENT) instruction
+ * @func: the function code passed to PCKMO; see CPACF_PCKMO_xxx defines
+ * @param: address of parameter block; see POP for details on each func
+ *
+ * Returns 0.
+ */
+static inline void cpacf_pckmo(long func, void *param)
+{
+	register unsigned long r0 asm("0") = (unsigned long) func;
+	register unsigned long r1 asm("1") = (unsigned long) param;
+
+	asm volatile(
+		"       .insn   rre,%[opc] << 16,0,0\n" /* PCKMO opcode */
+		:
+		: [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_PCKMO)
+		: "cc", "memory");
+}
+
 #endif	/* _ASM_S390_CPACF_H */
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 428c41239a49..d1e0707310fd 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -199,14 +199,15 @@ static inline int ecctr(u64 ctr, u64 *val)
 /* Store CPU counter multiple for the MT utilization counter set */
 static inline int stcctm5(u64 num, u64 *val)
 {
-	typedef struct { u64 _[num]; } addrtype;
 	int cc;
 
 	asm volatile (
 		"	.insn	rsy,0xeb0000000017,%2,5,%1\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
-		: "=d" (cc), "=Q" (*(addrtype *) val)  : "d" (num) : "cc");
+		: "=d" (cc)
+		: "Q" (*val), "d" (num)
+		: "cc", "memory");
 	return cc;
 }
 
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 221b454c734a..d1c407ddf703 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -25,33 +25,6 @@ static inline unsigned long __div(unsigned long long n, unsigned long base)
 	return n / base;
 }
 
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-/*
- * Convert cputime to jiffies and back.
- */
-static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned int jif)
-{
-	return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
-static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
-{
-	unsigned long long jif = (__force unsigned long long) cputime;
-	do_div(jif, CPUTIME_PER_SEC / HZ);
-	return jif;
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
-	return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
 /*
  * Convert cputime to microseconds and back.
  */
@@ -60,88 +33,8 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime)
 	return (__force unsigned long long) cputime >> 12;
 }
 
-static inline cputime_t usecs_to_cputime(const unsigned int m)
-{
-	return (__force cputime_t)(m * CPUTIME_PER_USEC);
-}
-
-#define usecs_to_cputime64(m)		usecs_to_cputime(m)
-
-/*
- * Convert cputime to milliseconds and back.
- */
-static inline unsigned int cputime_to_secs(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1;
-}
-
-static inline cputime_t secs_to_cputime(const unsigned int s)
-{
-	return (__force cputime_t)(s * CPUTIME_PER_SEC);
-}
-
-/*
- * Convert cputime to timespec and back.
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC));
-}
-
-static inline void cputime_to_timespec(const cputime_t cputime,
-				       struct timespec *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to timeval and back.
- * Since cputime and timeval have the same resolution (microseconds)
- * this is easy.
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC);
-}
-
-static inline void cputime_to_timeval(const cputime_t cputime,
-				      struct timeval *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to clock and back.
- */
-static inline clock_t cputime_to_clock_t(cputime_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
-
-static inline cputime_t clock_t_to_cputime(unsigned long x)
-{
-	return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ));
-}
-
-/*
- * Convert cputime64 to clock.
- */
-static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
 
-cputime64_t arch_cpu_idle_time(int cpu);
+u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 8e136b88cdf4..d0441ad2a990 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -9,7 +9,7 @@
 
 #include <linux/bug.h>
 
-#define __ctl_load(array, low, high) {					\
+#define __ctl_load(array, low, high) do {				\
 	typedef struct { char _[sizeof(array)]; } addrtype;		\
 									\
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
@@ -18,9 +18,9 @@
 		:							\
 		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
 		: "memory");						\
-}
+} while (0)
 
-#define __ctl_store(array, low, high) {					\
+#define __ctl_store(array, low, high) do {				\
 	typedef struct { char _[sizeof(array)]; } addrtype;		\
 									\
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
@@ -28,7 +28,7 @@
 		"	stctg	%1,%2,%0\n"				\
 		: "=Q" (*(addrtype *)(&array))				\
 		: "i" (low), "i" (high));				\
-}
+} while (0)
 
 static inline void __ctl_set_bit(unsigned int cr, unsigned int bit)
 {
@@ -62,7 +62,9 @@ union ctlreg0 {
 		unsigned long	   : 4;
 		unsigned long afp  : 1; /* AFP-register control */
 		unsigned long vx   : 1; /* Vector enablement control */
-		unsigned long	   : 17;
+		unsigned long	   : 7;
+		unsigned long sssm : 1; /* Service signal subclass mask */
+		unsigned long	   : 9;
 	};
 };
 
diff --git a/arch/s390/include/asm/device.h b/arch/s390/include/asm/device.h
index 4a9f35e0973f..5203fc87f080 100644
--- a/arch/s390/include/asm/device.h
+++ b/arch/s390/include/asm/device.h
@@ -4,7 +4,6 @@
  * This file is released under the GPLv2
  */
 struct dev_archdata {
-	struct dma_map_ops *dma_ops;
 };
 
 struct pdev_archdata {
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index ffaba07f50ab..3108b8dbe266 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -10,12 +10,10 @@
 
 #define DMA_ERROR_CODE		(~(dma_addr_t) 0x0)
 
-extern struct dma_map_ops s390_pci_dma_ops;
+extern const struct dma_map_ops s390_pci_dma_ops;
 
-static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	if (dev && dev->archdata.dma_ops)
-		return dev->archdata.dma_ops;
 	return &dma_noop_ops;
 }
 
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index f4381e1fb19e..83aaefed2a7b 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -103,6 +103,8 @@
 #define HWCAP_S390_HIGH_GPRS	512
 #define HWCAP_S390_TE		1024
 #define HWCAP_S390_VXRS		2048
+#define HWCAP_S390_VXRS_BCD	4096
+#define HWCAP_S390_VXRS_EXT	8192
 
 /* Internal bits, not exposed via elf */
 #define HWCAP_INT_SIE		1UL
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 4c7fac75090e..cd546a245c68 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -14,7 +14,7 @@
 
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range			free_pgd_range
-#define hugepages_supported()			(MACHINE_HAS_HPAGE)
+#define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 591e5a5279b0..84c0f9086483 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -27,6 +27,11 @@
  * 2005-Dec	Used as a template for s390 by Mike Grundy
  *		<grundym@us.ibm.com>
  */
+#include <asm-generic/kprobes.h>
+
+#define BREAKPOINT_INSTRUCTION	0x0002
+
+#ifdef CONFIG_KPROBES
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
@@ -37,7 +42,6 @@ struct pt_regs;
 struct kprobe;
 
 typedef u16 kprobe_opcode_t;
-#define BREAKPOINT_INSTRUCTION	0x0002
 
 /* Maximum instruction size is 3 (16bit) halfwords: */
 #define MAX_INSN_SIZE		0x0003
@@ -91,4 +95,5 @@ int probe_is_insn_relative_long(u16 *insn);
 
 #define flush_insn_slot(p)	do { } while (0)
 
+#endif /* CONFIG_KPROBES */
 #endif	/* _ASM_S390_KPROBES_H */
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 2c1213785892..6de5c6cb0061 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -17,7 +17,7 @@
 #ifndef ASM_LIVEPATCH_H
 #define ASM_LIVEPATCH_H
 
-#include <linux/module.h>
+#include <asm/ptrace.h>
 
 static inline int klp_check_compiler_support(void)
 {
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9bfad2ad6312..61261e0e95c0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -85,53 +85,56 @@ struct lowcore {
 	__u64	mcck_enter_timer;		/* 0x02c0 */
 	__u64	exit_timer;			/* 0x02c8 */
 	__u64	user_timer;			/* 0x02d0 */
-	__u64	system_timer;			/* 0x02d8 */
-	__u64	steal_timer;			/* 0x02e0 */
-	__u64	last_update_timer;		/* 0x02e8 */
-	__u64	last_update_clock;		/* 0x02f0 */
-	__u64	int_clock;			/* 0x02f8 */
-	__u64	mcck_clock;			/* 0x0300 */
-	__u64	clock_comparator;		/* 0x0308 */
+	__u64	guest_timer;			/* 0x02d8 */
+	__u64	system_timer;			/* 0x02e0 */
+	__u64	hardirq_timer;			/* 0x02e8 */
+	__u64	softirq_timer;			/* 0x02f0 */
+	__u64	steal_timer;			/* 0x02f8 */
+	__u64	last_update_timer;		/* 0x0300 */
+	__u64	last_update_clock;		/* 0x0308 */
+	__u64	int_clock;			/* 0x0310 */
+	__u64	mcck_clock;			/* 0x0318 */
+	__u64	clock_comparator;		/* 0x0320 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0310 */
-	__u8	pad_0x318[0x320-0x318];		/* 0x0318 */
-	__u64	kernel_stack;			/* 0x0320 */
+	__u64	current_task;			/* 0x0328 */
+	__u8	pad_0x318[0x320-0x318];		/* 0x0330 */
+	__u64	kernel_stack;			/* 0x0338 */
 
 	/* Interrupt, panic and restart stack. */
-	__u64	async_stack;			/* 0x0328 */
-	__u64	panic_stack;			/* 0x0330 */
-	__u64	restart_stack;			/* 0x0338 */
+	__u64	async_stack;			/* 0x0340 */
+	__u64	panic_stack;			/* 0x0348 */
+	__u64	restart_stack;			/* 0x0350 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0340 */
-	__u64	restart_data;			/* 0x0348 */
-	__u64	restart_source;			/* 0x0350 */
+	__u64	restart_fn;			/* 0x0358 */
+	__u64	restart_data;			/* 0x0360 */
+	__u64	restart_source;			/* 0x0368 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0358 */
-	__u64	user_asce;			/* 0x0360 */
+	__u64	kernel_asce;			/* 0x0370 */
+	__u64	user_asce;			/* 0x0378 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0368 */
-	__u32	current_pid;			/* 0x036c */
+	__u32	lpp;				/* 0x0380 */
+	__u32	current_pid;			/* 0x0384 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0370 */
-	__u32	softirq_pending;		/* 0x0374 */
-	__u64	percpu_offset;			/* 0x0378 */
-	__u64	vdso_per_cpu_data;		/* 0x0380 */
-	__u64	machine_flags;			/* 0x0388 */
-	__u32	preempt_count;			/* 0x0390 */
-	__u8	pad_0x0394[0x0398-0x0394];	/* 0x0394 */
-	__u64	gmap;				/* 0x0398 */
-	__u32	spinlock_lockval;		/* 0x03a0 */
-	__u32	fpu_flags;			/* 0x03a4 */
-	__u8	pad_0x03a8[0x0400-0x03a8];	/* 0x03a8 */
+	__u32	cpu_nr;				/* 0x0388 */
+	__u32	softirq_pending;		/* 0x038c */
+	__u64	percpu_offset;			/* 0x0390 */
+	__u64	vdso_per_cpu_data;		/* 0x0398 */
+	__u64	machine_flags;			/* 0x03a0 */
+	__u32	preempt_count;			/* 0x03a8 */
+	__u8	pad_0x03ac[0x03b0-0x03ac];	/* 0x03ac */
+	__u64	gmap;				/* 0x03b0 */
+	__u32	spinlock_lockval;		/* 0x03b8 */
+	__u32	fpu_flags;			/* 0x03bc */
+	__u8	pad_0x03c0[0x0400-0x03c0];	/* 0x03c0 */
 
 	/* Per cpu primary space access list */
 	__u32	paste[16];			/* 0x0400 */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 67f7a991c929..9b828c073176 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -63,7 +63,7 @@ static inline void set_user_asce(struct mm_struct *mm)
 	S390_lowcore.user_asce = mm->context.asce;
 	if (current->thread.mm_segment.ar4)
 		__ctl_load(S390_lowcore.user_asce, 7, 7);
-	set_cpu_flag(CIF_ASCE);
+	set_cpu_flag(CIF_ASCE_PRIMARY);
 }
 
 static inline void clear_user_asce(void)
@@ -81,7 +81,7 @@ static inline void load_kernel_asce(void)
 	__ctl_store(asce, 1, 1);
 	if (asce != S390_lowcore.kernel_asce)
 		__ctl_load(S390_lowcore.kernel_asce, 1, 1);
-	set_cpu_flag(CIF_ASCE);
+	set_cpu_flag(CIF_ASCE_PRIMARY);
 }
 
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index d6f1b1d94352..938b8cc19fc6 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -85,7 +85,7 @@ struct clp_rsp_query_pci {
 	u32 fid;			/* pci function id */
 	u8 bar_size[PCI_BAR_COUNT];
 	u16 pchid;
-	u32 bar[PCI_BAR_COUNT];
+	__le32 bar[PCI_BAR_COUNT];
 	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
 	u32			: 16;
 	u8 fmb_len;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 0362cd5fa187..7ed1972b1920 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -200,6 +200,7 @@ static inline int is_module_addr(void *addr)
  */
 
 /* Hardware bits in the page table entry */
+#define _PAGE_NOEXEC	0x100		/* HW no-execute bit  */
 #define _PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define _PAGE_INVALID	0x400		/* HW invalid bit    */
 #define _PAGE_LARGE	0x800		/* Bit to mark a large pte */
@@ -277,6 +278,7 @@ static inline int is_module_addr(void *addr)
 /* Bits in the region table entry */
 #define _REGION_ENTRY_ORIGIN	~0xfffUL/* region/segment table origin	    */
 #define _REGION_ENTRY_PROTECT	0x200	/* region protection bit	    */
+#define _REGION_ENTRY_NOEXEC	0x100	/* region no-execute bit	    */
 #define _REGION_ENTRY_OFFSET	0xc0	/* region table offset		    */
 #define _REGION_ENTRY_INVALID	0x20	/* invalid region table entry	    */
 #define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
@@ -316,6 +318,7 @@ static inline int is_module_addr(void *addr)
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* segment table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* page protection bit		    */
+#define _SEGMENT_ENTRY_NOEXEC	0x100	/* region no-execute bit	    */
 #define _SEGMENT_ENTRY_INVALID	0x20	/* invalid segment table entry	    */
 
 #define _SEGMENT_ENTRY		(0)
@@ -385,17 +388,23 @@ static inline int is_module_addr(void *addr)
  * Page protection definitions.
  */
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_READ	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+#define PAGE_RO		__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+				 _PAGE_NOEXEC  | _PAGE_INVALID | _PAGE_PROTECT)
+#define PAGE_RX		__pgprot(_PAGE_PRESENT | _PAGE_READ | \
 				 _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_WRITE	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define PAGE_RW		__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_NOEXEC  | _PAGE_INVALID | _PAGE_PROTECT)
+#define PAGE_RWX	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 				 _PAGE_INVALID | _PAGE_PROTECT)
 
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
-				 _PAGE_YOUNG | _PAGE_DIRTY)
+				 _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC)
 #define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
-				 _PAGE_YOUNG | _PAGE_DIRTY)
+				 _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC)
 #define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \
-				 _PAGE_PROTECT)
+				 _PAGE_PROTECT | _PAGE_NOEXEC)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				  _PAGE_YOUNG |	_PAGE_DIRTY)
 
 /*
  * On s390 the page table entry has an invalid bit and a read-only bit.
@@ -404,43 +413,51 @@ static inline int is_module_addr(void *addr)
  */
          /*xwr*/
 #define __P000	PAGE_NONE
-#define __P001	PAGE_READ
-#define __P010	PAGE_READ
-#define __P011	PAGE_READ
-#define __P100	PAGE_READ
-#define __P101	PAGE_READ
-#define __P110	PAGE_READ
-#define __P111	PAGE_READ
+#define __P001	PAGE_RO
+#define __P010	PAGE_RO
+#define __P011	PAGE_RO
+#define __P100	PAGE_RX
+#define __P101	PAGE_RX
+#define __P110	PAGE_RX
+#define __P111	PAGE_RX
 
 #define __S000	PAGE_NONE
-#define __S001	PAGE_READ
-#define __S010	PAGE_WRITE
-#define __S011	PAGE_WRITE
-#define __S100	PAGE_READ
-#define __S101	PAGE_READ
-#define __S110	PAGE_WRITE
-#define __S111	PAGE_WRITE
+#define __S001	PAGE_RO
+#define __S010	PAGE_RW
+#define __S011	PAGE_RW
+#define __S100	PAGE_RX
+#define __S101	PAGE_RX
+#define __S110	PAGE_RWX
+#define __S111	PAGE_RWX
 
 /*
  * Segment entry (large page) protection definitions.
  */
 #define SEGMENT_NONE	__pgprot(_SEGMENT_ENTRY_INVALID | \
 				 _SEGMENT_ENTRY_PROTECT)
-#define SEGMENT_READ	__pgprot(_SEGMENT_ENTRY_PROTECT | \
+#define SEGMENT_RO	__pgprot(_SEGMENT_ENTRY_PROTECT | \
+				 _SEGMENT_ENTRY_READ | \
+				 _SEGMENT_ENTRY_NOEXEC)
+#define SEGMENT_RX	__pgprot(_SEGMENT_ENTRY_PROTECT | \
 				 _SEGMENT_ENTRY_READ)
-#define SEGMENT_WRITE	__pgprot(_SEGMENT_ENTRY_READ | \
+#define SEGMENT_RW	__pgprot(_SEGMENT_ENTRY_READ | \
+				 _SEGMENT_ENTRY_WRITE | \
+				 _SEGMENT_ENTRY_NOEXEC)
+#define SEGMENT_RWX	__pgprot(_SEGMENT_ENTRY_READ | \
 				 _SEGMENT_ENTRY_WRITE)
 #define SEGMENT_KERNEL	__pgprot(_SEGMENT_ENTRY |	\
 				 _SEGMENT_ENTRY_LARGE |	\
 				 _SEGMENT_ENTRY_READ |	\
 				 _SEGMENT_ENTRY_WRITE | \
 				 _SEGMENT_ENTRY_YOUNG | \
-				 _SEGMENT_ENTRY_DIRTY)
+				 _SEGMENT_ENTRY_DIRTY | \
+				 _SEGMENT_ENTRY_NOEXEC)
 #define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY |	\
 				 _SEGMENT_ENTRY_LARGE |	\
 				 _SEGMENT_ENTRY_READ |	\
 				 _SEGMENT_ENTRY_YOUNG |	\
-				 _SEGMENT_ENTRY_PROTECT)
+				 _SEGMENT_ENTRY_PROTECT | \
+				 _SEGMENT_ENTRY_NOEXEC)
 
 /*
  * Region3 entry (large page) protection definitions.
@@ -451,12 +468,14 @@ static inline int is_module_addr(void *addr)
 				 _REGION3_ENTRY_READ |	 \
 				 _REGION3_ENTRY_WRITE |	 \
 				 _REGION3_ENTRY_YOUNG |	 \
-				 _REGION3_ENTRY_DIRTY)
+				 _REGION3_ENTRY_DIRTY | \
+				 _REGION_ENTRY_NOEXEC)
 #define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \
 				   _REGION3_ENTRY_LARGE |  \
 				   _REGION3_ENTRY_READ |   \
 				   _REGION3_ENTRY_YOUNG |  \
-				   _REGION_ENTRY_PROTECT)
+				   _REGION_ENTRY_PROTECT | \
+				   _REGION_ENTRY_NOEXEC)
 
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
@@ -621,12 +640,12 @@ static inline int pud_bad(pud_t pud)
 
 static inline int pmd_present(pmd_t pmd)
 {
-	return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID;
+	return pmd_val(pmd) != _SEGMENT_ENTRY_EMPTY;
 }
 
 static inline int pmd_none(pmd_t pmd)
 {
-	return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID;
+	return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
@@ -784,7 +803,7 @@ static inline void pud_clear(pud_t *pud)
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID;
+	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -801,14 +820,14 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	pte_val(pte) &= _PAGE_CHG_MASK;
 	pte_val(pte) |= pgprot_val(newprot);
 	/*
-	 * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the
-	 * invalid bit set, clear it again for readable, young pages
+	 * newprot for PAGE_NONE, PAGE_RO, PAGE_RX, PAGE_RW and PAGE_RWX
+	 * has the invalid bit set, clear it again for readable, young pages
 	 */
 	if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ))
 		pte_val(pte) &= ~_PAGE_INVALID;
 	/*
-	 * newprot for PAGE_READ and PAGE_WRITE has the page protection
-	 * bit set, clear it again for writable, dirty pages
+	 * newprot for PAGE_RO, PAGE_RX, PAGE_RW and PAGE_RWX has the page
+	 * protection bit set, clear it again for writable, dirty pages
 	 */
 	if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE))
 		pte_val(pte) &= ~_PAGE_PROTECT;
@@ -1029,6 +1048,8 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
+	if (!MACHINE_HAS_NX)
+		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (mm_has_pgste(mm))
 		ptep_set_pte_at(mm, addr, ptep, entry);
 	else
@@ -1173,14 +1194,18 @@ static inline pud_t pud_mkdirty(pud_t pud)
 static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 {
 	/*
-	 * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
-	 * Convert to segment table entry format.
+	 * pgprot is PAGE_NONE, PAGE_RO, PAGE_RX, PAGE_RW or PAGE_RWX
+	 * (see __Pxxx / __Sxxx). Convert to segment table entry format.
 	 */
 	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
 		return pgprot_val(SEGMENT_NONE);
-	if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
-		return pgprot_val(SEGMENT_READ);
-	return pgprot_val(SEGMENT_WRITE);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_RO))
+		return pgprot_val(SEGMENT_RO);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_RX))
+		return pgprot_val(SEGMENT_RX);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_RW))
+		return pgprot_val(SEGMENT_RW);
+	return pgprot_val(SEGMENT_RWX);
 }
 
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
@@ -1315,6 +1340,8 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t entry)
 {
+	if (!MACHINE_HAS_NX)
+		pmd_val(entry) &= ~_SEGMENT_ENTRY_NOEXEC;
 	*pmdp = entry;
 }
 
@@ -1330,7 +1357,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pmd_t *pmdp)
 {
-	return pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
+	return pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
 }
 
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
@@ -1340,10 +1367,10 @@ static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
 {
 	if (full) {
 		pmd_t pmd = *pmdp;
-		*pmdp = __pmd(_SEGMENT_ENTRY_INVALID);
+		*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		return pmd;
 	}
-	return pmdp_xchg_lazy(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
+	return pmdp_xchg_lazy(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
 }
 
 #define __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
@@ -1357,7 +1384,7 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 static inline void pmdp_invalidate(struct vm_area_struct *vma,
 				   unsigned long addr, pmd_t *pmdp)
 {
-	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
+	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
@@ -1389,7 +1416,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 #define has_transparent_hugepage has_transparent_hugepage
 static inline int has_transparent_hugepage(void)
 {
-	return MACHINE_HAS_HPAGE ? 1 : 0;
+	return MACHINE_HAS_EDAT1 ? 1 : 0;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
diff --git a/arch/s390/include/asm/pkey.h b/arch/s390/include/asm/pkey.h
new file mode 100644
index 000000000000..b48aef4188f6
--- /dev/null
+++ b/arch/s390/include/asm/pkey.h
@@ -0,0 +1,90 @@
+/*
+ * Kernelspace interface to the pkey device driver
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author: Harald Freudenberger <freude@de.ibm.com>
+ *
+ */
+
+#ifndef _KAPI_PKEY_H
+#define _KAPI_PKEY_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+#include <uapi/asm/pkey.h>
+
+/*
+ * Generate (AES) random secure key.
+ * @param cardnr may be -1 (use default card)
+ * @param domain may be -1 (use default domain)
+ * @param keytype one of the PKEY_KEYTYPE values
+ * @param seckey pointer to buffer receiving the secure key
+ * @return 0 on success, negative errno value on failure
+ */
+int pkey_genseckey(__u16 cardnr, __u16 domain,
+		   __u32 keytype, struct pkey_seckey *seckey);
+
+/*
+ * Generate (AES) secure key with given key value.
+ * @param cardnr may be -1 (use default card)
+ * @param domain may be -1 (use default domain)
+ * @param keytype one of the PKEY_KEYTYPE values
+ * @param clrkey pointer to buffer with clear key data
+ * @param seckey pointer to buffer receiving the secure key
+ * @return 0 on success, negative errno value on failure
+ */
+int pkey_clr2seckey(__u16 cardnr, __u16 domain, __u32 keytype,
+		    const struct pkey_clrkey *clrkey,
+		    struct pkey_seckey *seckey);
+
+/*
+ * Derive (AES) proteced key from the (AES) secure key blob.
+ * @param cardnr may be -1 (use default card)
+ * @param domain may be -1 (use default domain)
+ * @param seckey pointer to buffer with the input secure key
+ * @param protkey pointer to buffer receiving the protected key and
+ *	  additional info (type, length)
+ * @return 0 on success, negative errno value on failure
+ */
+int pkey_sec2protkey(__u16 cardnr, __u16 domain,
+		     const struct pkey_seckey *seckey,
+		     struct pkey_protkey *protkey);
+
+/*
+ * Derive (AES) protected key from a given clear key value.
+ * @param keytype one of the PKEY_KEYTYPE values
+ * @param clrkey pointer to buffer with clear key data
+ * @param protkey pointer to buffer receiving the protected key and
+ *	  additional info (type, length)
+ * @return 0 on success, negative errno value on failure
+ */
+int pkey_clr2protkey(__u32 keytype,
+		     const struct pkey_clrkey *clrkey,
+		     struct pkey_protkey *protkey);
+
+/*
+ * Search for a matching crypto card based on the Master Key
+ * Verification Pattern provided inside a secure key.
+ * @param seckey pointer to buffer with the input secure key
+ * @param cardnr pointer to cardnr, receives the card number on success
+ * @param domain pointer to domain, receives the domain number on success
+ * @param verify if set, always verify by fetching verification pattern
+ *	  from card
+ * @return 0 on success, negative errno value on failure. If no card could be
+ *	   found, -ENODEV is returned.
+ */
+int pkey_findcard(const struct pkey_seckey *seckey,
+		  __u16 *cardnr, __u16 *domain, int verify);
+
+/*
+ * Find card and transform secure key to protected key.
+ * @param seckey pointer to buffer with the input secure key
+ * @param protkey pointer to buffer receiving the protected key and
+ *	  additional info (type, length)
+ * @return 0 on success, negative errno value on failure
+ */
+int pkey_skey2pkey(const struct pkey_seckey *seckey,
+		   struct pkey_protkey *protkey);
+
+#endif /* _KAPI_PKEY_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6bca916a5ba0..e4988710aa86 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,14 +14,16 @@
 #include <linux/const.h>
 
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
-#define CIF_ASCE		1	/* user asce needs fixup / uaccess */
-#define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
-#define CIF_FPU			3	/* restore FPU registers */
-#define CIF_IGNORE_IRQ		4	/* ignore interrupt (for udelay) */
-#define CIF_ENABLED_WAIT	5	/* in enabled wait state */
+#define CIF_ASCE_PRIMARY	1	/* primary asce needs fixup / uaccess */
+#define CIF_ASCE_SECONDARY	2	/* secondary asce needs fixup / uaccess */
+#define CIF_NOHZ_DELAY		3	/* delay HZ disable for a tick */
+#define CIF_FPU			4	/* restore FPU registers */
+#define CIF_IGNORE_IRQ		5	/* ignore interrupt (for udelay) */
+#define CIF_ENABLED_WAIT	6	/* in enabled wait state */
 
 #define _CIF_MCCK_PENDING	_BITUL(CIF_MCCK_PENDING)
-#define _CIF_ASCE		_BITUL(CIF_ASCE)
+#define _CIF_ASCE_PRIMARY	_BITUL(CIF_ASCE_PRIMARY)
+#define _CIF_ASCE_SECONDARY	_BITUL(CIF_ASCE_SECONDARY)
 #define _CIF_NOHZ_DELAY		_BITUL(CIF_NOHZ_DELAY)
 #define _CIF_FPU		_BITUL(CIF_FPU)
 #define _CIF_IGNORE_IRQ		_BITUL(CIF_IGNORE_IRQ)
@@ -89,7 +91,8 @@ extern void execve_tail(void);
  * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
  */
 
-#define TASK_SIZE_OF(tsk)	((tsk)->mm->context.asce_limit)
+#define TASK_SIZE_OF(tsk)	((tsk)->mm ? \
+				 (tsk)->mm->context.asce_limit : TASK_MAX_SIZE)
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
 					(1UL << 30) : (1UL << 41))
 #define TASK_SIZE		TASK_SIZE_OF(current)
@@ -111,7 +114,10 @@ struct thread_struct {
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	unsigned long user_timer;	/* task cputime in user space */
+	unsigned long guest_timer;	/* task cputime in kvm guest */
 	unsigned long system_timer;	/* task cputime in kernel space */
+	unsigned long hardirq_timer;	/* task cputime in hardirq context */
+	unsigned long softirq_timer;	/* task cputime in softirq context */
 	unsigned long sys_call_table;	/* system call table address */
 	mm_segment_t mm_segment;
 	unsigned long gmap_addr;	/* address of last gmap fault. */
@@ -197,10 +203,12 @@ struct stack_frame {
 struct task_struct;
 struct mm_struct;
 struct seq_file;
+struct pt_regs;
 
 typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
 void dump_trace(dump_trace_func_t func, void *data,
 		struct task_struct *task, unsigned long sp);
+void show_registers(struct pt_regs *regs);
 
 void show_cacheinfo(struct seq_file *m);
 
@@ -358,12 +366,12 @@ extern void (*s390_base_ext_handler_fn)(void);
 extern int memcpy_real(void *, void *, size_t);
 extern void memcpy_absolute(void *, void *, size_t);
 
-#define mem_assign_absolute(dest, val) {			\
+#define mem_assign_absolute(dest, val) do {			\
 	__typeof__(dest) __tmp = (val);				\
 								\
 	BUILD_BUG_ON(sizeof(__tmp) != sizeof(val));		\
 	memcpy_absolute(&(dest), &__tmp, sizeof(__tmp));	\
-}
+} while (0)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 8db92a5b3bf1..ace3bd315438 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -101,7 +101,12 @@ struct zpci_report_error_header {
 	u8 data[0];	/* Subsequent Data passed verbatim to SCLP ET 24 */
 } __packed;
 
-int _sclp_get_core_info_early(struct sclp_core_info *info);
+int sclp_early_get_core_info(struct sclp_core_info *info);
+void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
+void sclp_early_detect(void);
+void sclp_early_printk(const char *s);
+void __sclp_early_printk(const char *s, unsigned int len);
+
 int _sclp_get_core_info(struct sclp_core_info *info);
 int sclp_core_configure(u8 core);
 int sclp_core_deconfigure(u8 core);
@@ -110,20 +115,17 @@ int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
 int sclp_chp_deconfigure(struct chp_id chpid);
 int sclp_chp_read_info(struct sclp_chp_info *info);
-void sclp_get_ipl_info(struct sclp_ipl_info *info);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
 int sclp_pci_report(struct zpci_report_error_header *report, u32 fh, u32 fid);
 int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count);
 int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count);
-void sclp_early_detect(void);
-void _sclp_print_early(const char *);
 void sclp_ocf_cpc_name_copy(char *dst);
 
 static inline int sclp_get_core_info(struct sclp_core_info *info, int early)
 {
 	if (early)
-		return _sclp_get_core_info_early(info);
+		return sclp_early_get_core_info(info);
 	return _sclp_get_core_info(info);
 }
 
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 5e8d57e1cc5e..30bdb5a027f3 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -30,6 +30,7 @@
 #define MACHINE_FLAG_TLB_LC	_BITUL(12)
 #define MACHINE_FLAG_VX		_BITUL(13)
 #define MACHINE_FLAG_CAD	_BITUL(14)
+#define MACHINE_FLAG_NX		_BITUL(15)
 
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
@@ -58,9 +59,6 @@ extern void detect_memory_memblock(void);
 
 #define MACHINE_HAS_DIAG9C	(S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C)
 #define MACHINE_HAS_ESOP	(S390_lowcore.machine_flags & MACHINE_FLAG_ESOP)
-#define MACHINE_HAS_PFMF	MACHINE_HAS_EDAT1
-#define MACHINE_HAS_HPAGE	MACHINE_HAS_EDAT1
-
 #define MACHINE_HAS_IDTE	(S390_lowcore.machine_flags & MACHINE_FLAG_IDTE)
 #define MACHINE_HAS_DIAG44	(S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44)
 #define MACHINE_HAS_EDAT1	(S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1)
@@ -71,6 +69,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
 #define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
 #define MACHINE_HAS_CAD		(S390_lowcore.machine_flags & MACHINE_FLAG_CAD)
+#define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
 
 /*
  * Console mode. Override with conmode=
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 7ecd8902a5c3..ffc45048ea7d 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -63,7 +63,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lp)
 {
-	return ACCESS_ONCE(lp->lock) != 0;
+	return READ_ONCE(lp->lock) != 0;
 }
 
 static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index de8298800722..354344dcc198 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -178,14 +178,6 @@ int get_phys_clock(unsigned long long *clock);
 void init_cpu_timer(void);
 unsigned long long monotonic_clock(void);
 
-void tod_to_timeval(__u64 todval, struct timespec64 *xt);
-
-static inline
-void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
-{
-	tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
-}
-
 extern u64 sched_clock_base_cc;
 
 /**
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index f82b04e85a21..136932ff4250 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -14,6 +14,7 @@
  */
 #include <linux/sched.h>
 #include <linux/errno.h>
+#include <asm/processor.h>
 #include <asm/ctl_reg.h>
 
 #define VERIFY_READ     0
@@ -36,18 +37,20 @@
 
 #define get_ds()        (KERNEL_DS)
 #define get_fs()        (current->thread.mm_segment)
+#define segment_eq(a,b) ((a).ar4 == (b).ar4)
 
-#define set_fs(x)							\
-{									\
-	unsigned long __pto;						\
-	current->thread.mm_segment = (x);				\
-	__pto = current->thread.mm_segment.ar4 ?			\
-		S390_lowcore.user_asce : S390_lowcore.kernel_asce;	\
-	__ctl_load(__pto, 7, 7);					\
+static inline void set_fs(mm_segment_t fs)
+{
+	current->thread.mm_segment = fs;
+	if (segment_eq(fs, KERNEL_DS)) {
+		set_cpu_flag(CIF_ASCE_SECONDARY);
+		__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	} else {
+		clear_cpu_flag(CIF_ASCE_SECONDARY);
+		__ctl_load(S390_lowcore.user_asce, 7, 7);
+	}
 }
 
-#define segment_eq(a,b) ((a).ar4 == (b).ar4)
-
 static inline int __range_ok(unsigned long addr, unsigned long size)
 {
 	return 1;
@@ -177,7 +180,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 					(unsigned long *)x,
 					size, spec);
 		break;
-	};
+	}
 	return rc;
 }
 
@@ -207,7 +210,7 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 					(unsigned long __user *)ptr,
 					size, spec);
 		break;
-	};
+	}
 	return rc;
 }
 
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index bf736e764cb4..6848ba5c1454 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -24,6 +24,7 @@ header-y += mman.h
 header-y += monwriter.h
 header-y += msgbuf.h
 header-y += param.h
+header-y += pkey.h
 header-y += poll.h
 header-y += posix_types.h
 header-y += ptrace.h
diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h
new file mode 100644
index 000000000000..ed7f19c27ce5
--- /dev/null
+++ b/arch/s390/include/uapi/asm/pkey.h
@@ -0,0 +1,112 @@
+/*
+ * Userspace interface to the pkey device driver
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author: Harald Freudenberger <freude@de.ibm.com>
+ *
+ */
+
+#ifndef _UAPI_PKEY_H
+#define _UAPI_PKEY_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * Ioctl calls supported by the pkey device driver
+ */
+
+#define PKEY_IOCTL_MAGIC 'p'
+
+#define SECKEYBLOBSIZE	64     /* secure key blob size is always 64 bytes */
+#define MAXPROTKEYSIZE	64  /* a protected key blob may be up to 64 bytes */
+#define MAXCLRKEYSIZE	32     /* a clear key value may be up to 32 bytes */
+
+/* defines for the type field within the pkey_protkey struct */
+#define PKEY_KEYTYPE_AES_128  1
+#define PKEY_KEYTYPE_AES_192  2
+#define PKEY_KEYTYPE_AES_256  3
+
+/* Struct to hold a secure key blob */
+struct pkey_seckey {
+	__u8  seckey[SECKEYBLOBSIZE];		  /* the secure key blob */
+};
+
+/* Struct to hold protected key and length info */
+struct pkey_protkey {
+	__u32 type;	     /* key type, one of the PKEY_KEYTYPE values */
+	__u32 len;		/* bytes actually stored in protkey[]	 */
+	__u8  protkey[MAXPROTKEYSIZE];	       /* the protected key blob */
+};
+
+/* Struct to hold a clear key value */
+struct pkey_clrkey {
+	__u8  clrkey[MAXCLRKEYSIZE]; /* 16, 24, or 32 byte clear key value */
+};
+
+/*
+ * Generate secure key
+ */
+struct pkey_genseck {
+	__u16 cardnr;		    /* in: card to use or FFFF for any	 */
+	__u16 domain;		    /* in: domain or FFFF for any	 */
+	__u32 keytype;		    /* in: key type to generate		 */
+	struct pkey_seckey seckey;  /* out: the secure key blob		 */
+};
+#define PKEY_GENSECK _IOWR(PKEY_IOCTL_MAGIC, 0x01, struct pkey_genseck)
+
+/*
+ * Construct secure key from clear key value
+ */
+struct pkey_clr2seck {
+	__u16 cardnr;		    /* in: card to use or FFFF for any	 */
+	__u16 domain;		    /* in: domain or FFFF for any	 */
+	__u32 keytype;		    /* in: key type to generate		 */
+	struct pkey_clrkey clrkey;  /* in: the clear key value		 */
+	struct pkey_seckey seckey;  /* out: the secure key blob		 */
+};
+#define PKEY_CLR2SECK _IOWR(PKEY_IOCTL_MAGIC, 0x02, struct pkey_clr2seck)
+
+/*
+ * Fabricate protected key from a secure key
+ */
+struct pkey_sec2protk {
+	__u16 cardnr;		     /* in: card to use or FFFF for any   */
+	__u16 domain;		     /* in: domain or FFFF for any	  */
+	struct pkey_seckey seckey;   /* in: the secure key blob		  */
+	struct pkey_protkey protkey; /* out: the protected key		  */
+};
+#define PKEY_SEC2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x03, struct pkey_sec2protk)
+
+/*
+ * Fabricate protected key from an clear key value
+ */
+struct pkey_clr2protk {
+	__u32 keytype;		     /* in: key type to generate	  */
+	struct pkey_clrkey clrkey;   /* in: the clear key value		  */
+	struct pkey_protkey protkey; /* out: the protected key		  */
+};
+#define PKEY_CLR2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x04, struct pkey_clr2protk)
+
+/*
+ * Search for matching crypto card based on the Master Key
+ * Verification Pattern provided inside a secure key.
+ */
+struct pkey_findcard {
+	struct pkey_seckey seckey;	       /* in: the secure key blob */
+	__u16  cardnr;			       /* out: card number	  */
+	__u16  domain;			       /* out: domain number	  */
+};
+#define PKEY_FINDCARD _IOWR(PKEY_IOCTL_MAGIC, 0x05, struct pkey_findcard)
+
+/*
+ * Combined together: findcard + sec2prot
+ */
+struct pkey_skey2pkey {
+	struct pkey_seckey seckey;   /* in: the secure key blob		  */
+	struct pkey_protkey protkey; /* out: the protected key		  */
+};
+#define PKEY_SKEY2PKEY _IOWR(PKEY_IOCTL_MAGIC, 0x06, struct pkey_skey2pkey)
+
+#endif /* _UAPI_PKEY_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 36b5101c8606..060ce548fe8b 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -10,31 +10,25 @@ CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
 # Do not trace early setup code
 CFLAGS_REMOVE_als.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_sclp.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
 GCOV_PROFILE_als.o	:= n
 GCOV_PROFILE_early.o	:= n
-GCOV_PROFILE_sclp.o	:= n
 
 KCOV_INSTRUMENT_als.o	:= n
 KCOV_INSTRUMENT_early.o	:= n
-KCOV_INSTRUMENT_sclp.o	:= n
 
 UBSAN_SANITIZE_als.o	:= n
 UBSAN_SANITIZE_early.o	:= n
-UBSAN_SANITIZE_sclp.o	:= n
 
 #
-# Use -march=z900 for sclp.c and als.c to be able to print an error
+# Use -march=z900 for als.c to be able to print an error
 # message if the kernel is started on a machine which is too old
 #
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
 CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
 CFLAGS_als.o		+= -march=z900
-CFLAGS_REMOVE_sclp.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp.o		+= -march=z900
 AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
 AFLAGS_head.o		+= -march=z900
 endif
@@ -61,7 +55,7 @@ CFLAGS_sysinfo.o	+= -w
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o als.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o
 obj-y	+= entry.o reipl.o relocate_kernel.o
@@ -76,7 +70,7 @@ obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
 obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o
 obj-$(CONFIG_COMPAT)		+= compat_wrapper.o $(compat-obj-y)
-
+obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
diff --git a/arch/s390/kernel/als.c b/arch/s390/kernel/als.c
index a16e9d1bf9e3..14769eb52a33 100644
--- a/arch/s390/kernel/als.c
+++ b/arch/s390/kernel/als.c
@@ -41,7 +41,8 @@ static void __init print_machine_type(void)
 	get_cpu_id(&id);
 	u16_to_hex(type_str, id.machine);
 	strcat(mach_str, type_str);
-	_sclp_print_early(mach_str);
+	strcat(mach_str, "\n");
+	sclp_early_printk(mach_str);
 }
 
 static void __init u16_to_decimal(char *str, u16 val)
@@ -79,7 +80,8 @@ static void __init print_missing_facilities(void)
 			 * z/VM adds a four character prefix.
 			 */
 			if (strlen(als_str) > 70) {
-				_sclp_print_early(als_str);
+				strcat(als_str, "\n");
+				sclp_early_printk(als_str);
 				*als_str = '\0';
 			}
 			u16_to_decimal(val_str, i * BITS_PER_LONG + j);
@@ -87,13 +89,14 @@ static void __init print_missing_facilities(void)
 			first = 0;
 		}
 	}
-	_sclp_print_early(als_str);
-	_sclp_print_early("See Principles of Operations for facility bits");
+	strcat(als_str, "\n");
+	sclp_early_printk(als_str);
+	sclp_early_printk("See Principles of Operations for facility bits\n");
 }
 
 static void __init facility_mismatch(void)
 {
-	_sclp_print_early("The Linux kernel requires more recent processor hardware");
+	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
 	print_machine_type();
 	print_missing_facilities();
 	disabled_wait(0x8badcccc);
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 96df4547377a..a3d14161abcb 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -28,7 +28,6 @@
 #include <linux/shm.h>
 #include <linux/uio.h>
 #include <linux/quota.h>
-#include <linux/module.h>
 #include <linux/poll.h>
 #include <linux/personality.h>
 #include <linux/stat.h>
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 7f48e568ac64..9f0e4a2785f7 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -9,7 +9,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index f9293bfefb7f..dd1d5c62c374 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -8,7 +8,8 @@
 #include <linux/crash_dump.h>
 #include <asm/lowcore.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
@@ -31,6 +32,7 @@ static struct memblock_type oldmem_type = {
 	.max = 1,
 	.total_size = 0,
 	.regions = &oldmem_region,
+	.name = "oldmem",
 };
 
 struct save_area {
@@ -329,7 +331,11 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
 
 static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
 {
-	return nt_init_name(buf, type, desc, d_len, KEXEC_CORE_NOTE_NAME);
+	const char *note_name = "LINUX";
+
+	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
+		note_name = KEXEC_CORE_NOTE_NAME;
+	return nt_init_name(buf, type, desc, d_len, note_name);
 }
 
 /*
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 79f8ae933520..530226b6cb19 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -20,7 +20,7 @@
 #include <linux/string.h>
 #include <linux/sysctl.h>
 #include <linux/uaccess.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/debugfs.h>
@@ -866,7 +866,7 @@ static inline void
 debug_finish_entry(debug_info_t * id, debug_entry_t* active, int level,
 			int exception)
 {
-	active->id.stck = get_tod_clock_fast();
+	active->id.stck = get_tod_clock_fast() - sched_clock_base_cc;
 	active->id.fields.cpuid = smp_processor_id();
 	active->caller = __builtin_return_address(0);
 	active->id.fields.exception = exception;
@@ -1455,23 +1455,24 @@ int
 debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 			 int area, debug_entry_t * entry, char *out_buf)
 {
-	struct timespec64 time_spec;
+	unsigned long sec, usec;
 	char *except_str;
 	unsigned long caller;
 	int rc = 0;
 	unsigned int level;
 
 	level = entry->id.fields.level;
-	stck_to_timespec64(entry->id.stck, &time_spec);
+	sec = (entry->id.stck >> 12) + (sched_clock_base_cc >> 12);
+	sec = sec - (TOD_UNIX_EPOCH >> 12);
+	usec = do_div(sec, USEC_PER_SEC);
 
 	if (entry->id.fields.exception)
 		except_str = "*";
 	else
 		except_str = "-";
 	caller = (unsigned long) entry->caller;
-	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
-		      area, (long long)time_spec.tv_sec,
-		      time_spec.tv_nsec / 1000, level, except_str,
+	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %p  ",
+		      area, sec, usec, level, except_str,
 		      entry->id.fields.cpuid, (void *)caller);
 	return rc;
 }
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index a97354c8c667..ac6abcd3fe6a 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -5,7 +5,8 @@
  * Author(s): Michael Holzheu <holzheu@de.ibm.com>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 9f017cf417f6..f7e82302a71e 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -16,7 +16,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/reboot.h>
 #include <linux/kprobes.h>
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 324f1c147a41..4e65c79cc5f2 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -354,6 +354,10 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
+	if (test_facility(130)) {
+		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
+		__ctl_set_bit(0, 20);
+	}
 }
 
 static inline void save_vector_registers(void)
@@ -364,6 +368,18 @@ static inline void save_vector_registers(void)
 #endif
 }
 
+static int __init topology_setup(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (!rc && !enabled)
+		S390_lowcore.machine_flags &= ~MACHINE_HAS_TOPOLOGY;
+	return rc;
+}
+early_param("topology", topology_setup);
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
@@ -372,6 +388,21 @@ static int __init disable_vector_extension(char *str)
 }
 early_param("novx", disable_vector_extension);
 
+static int __init noexec_setup(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (!rc && !enabled) {
+		/* Disable no-execute support */
+		S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX;
+		__ctl_clear_bit(0, 20);
+	}
+	return rc;
+}
+early_param("noexec", noexec_setup);
+
 static int __init cad_setup(char *str)
 {
 	int val;
diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c
new file mode 100644
index 000000000000..819cb15c67e8
--- /dev/null
+++ b/arch/s390/kernel/early_printk.c
@@ -0,0 +1,35 @@
+/*
+ *    Copyright IBM Corp. 2017
+ */
+
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/sclp.h>
+
+static void sclp_early_write(struct console *con, const char *s, unsigned int len)
+{
+	__sclp_early_printk(s, len);
+}
+
+static struct console sclp_early_console = {
+	.name  = "earlysclp",
+	.write = sclp_early_write,
+	.flags = CON_PRINTBUFFER | CON_BOOT,
+	.index = -1,
+};
+
+static int __init setup_early_printk(char *buf)
+{
+	if (early_console)
+		return 0;
+	/* Accept only "earlyprintk" and "earlyprintk=sclp" */
+	if (buf && strncmp(buf, "sclp", 4))
+		return 0;
+	if (!sclp.has_linemode && !sclp.has_vt220)
+		return 0;
+	early_console = &sclp_early_console;
+	register_console(early_console);
+	return 0;
+}
+early_param("earlyprintk", setup_early_printk);
diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c
index b971c6be6298..1d5392b36ad8 100644
--- a/arch/s390/kernel/ebcdic.c
+++ b/arch/s390/kernel/ebcdic.c
@@ -8,8 +8,8 @@
  *               Martin Peschke <peschke@fh-brandenburg.de>
  */
 
-#include <linux/module.h>
-#include <asm/types.h>
+#include <linux/types.h>
+#include <linux/export.h>
 #include <asm/ebcdic.h>
 
 /*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 97298c58b2be..dff2152350a7 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -50,7 +50,8 @@ _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		   _TIF_UPROBE)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
-_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE | _CIF_FPU)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
+		   _CIF_ASCE_SECONDARY | _CIF_FPU)
 _PIF_WORK	= (_PIF_PER_TRAP)
 
 #define BASED(name) name-cleanup_critical(%r13)
@@ -103,8 +104,7 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 	CHECK_STACK 1<<STACK_SHIFT,\savearea
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	3f
-1:	LAST_BREAK %r14
-	UPDATE_VTIME %r14,%r15,\timer
+1:	UPDATE_VTIME %r14,%r15,\timer
 2:	lg	%r15,__LC_ASYNC_STACK	# load async stack
 3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	.endm
@@ -121,18 +121,6 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 	mvc	__LC_LAST_UPDATE_TIMER(8),\enter_timer
 	.endm
 
-	.macro	LAST_BREAK scratch
-	srag	\scratch,%r10,23
-#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
-	jz	.+10
-	stg	%r10,__TASK_thread+__THREAD_last_break(%r12)
-#else
-	jz	.+14
-	lghi	\scratch,__TASK_thread
-	stg	%r10,__THREAD_last_break(\scratch,%r12)
-#endif
-	.endm
-
 	.macro REENABLE_IRQS
 	stg	%r8,__LC_RETURN_PSW
 	ni	__LC_RETURN_PSW,0xbf
@@ -278,15 +266,14 @@ ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
 .Lsysc_stmg:
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
-	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_CURRENT
+	lghi	%r13,__TASK_thread
 	lghi	%r14,_PIF_SYSCALL
 .Lsysc_per:
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
-	LAST_BREAK %r13
 .Lsysc_vtime:
-	UPDATE_VTIME %r10,%r13,__LC_SYNC_ENTER_TIMER
+	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
@@ -294,12 +281,7 @@ ENTRY(system_call)
 	stg	%r14,__PT_FLAGS(%r11)
 .Lsysc_do_svc:
 	# load address of system call table
-#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
-	lg	%r10,__TASK_thread+__THREAD_sysc_table(%r12)
-#else
-	lghi	%r13,__TASK_thread
 	lg	%r10,__THREAD_sysc_table(%r13,%r12)
-#endif
 	llgh	%r8,__PT_INT_CODE+2(%r11)
 	slag	%r8,%r8,2			# shift and test for svc 0
 	jnz	.Lsysc_nr_ok
@@ -358,8 +340,8 @@ ENTRY(system_call)
 	jo	.Lsysc_notify_resume
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lsysc_vxrs
-	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE
-	jo	.Lsysc_uaccess
+	TSTMSK	__LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
+	jnz	.Lsysc_asce
 	j	.Lsysc_return		# beware of critical section cleanup
 
 #
@@ -377,12 +359,15 @@ ENTRY(system_call)
 	jg	s390_handle_mcck	# TIF bit will be cleared by handler
 
 #
-# _CIF_ASCE is set, load user space asce
+# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
 #
-.Lsysc_uaccess:
-	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
+.Lsysc_asce:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	j	.Lsysc_return
+	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_SECONDARY
+	jz	.Lsysc_return
+	larl	%r14,.Lsysc_return
+	jg	set_fs_fixup
 
 #
 # CIF_FPU is set, restore floating-point controls and floating-point registers.
@@ -399,13 +384,11 @@ ENTRY(system_call)
 	brasl	%r14,do_signal
 	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL
 	jno	.Lsysc_return
+.Lsysc_do_syscall:
+	lghi	%r13,__TASK_thread
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
-	lghi	%r8,0			# svc 0 returns -ENOSYS
-	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
-	cghi	%r1,NR_syscalls
-	jnl	.Lsysc_nr_ok		# invalid svc number -> do svc 0
-	slag	%r8,%r1,2
-	j	.Lsysc_nr_ok		# restart svc
+	lghi	%r1,0			# svc 0 returns -ENOSYS
+	j	.Lsysc_do_svc
 
 #
 # _TIF_NOTIFY_RESUME is set, call do_notify_resume
@@ -508,8 +491,7 @@ ENTRY(pgm_check_handler)
 1:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	3f
-2:	LAST_BREAK %r14
-	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+2:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	lg	%r15,__LC_KERNEL_STACK
 	lgr	%r14,%r12
 	aghi	%r14,__TASK_thread	# pointer to thread_struct
@@ -518,6 +500,7 @@ ENTRY(pgm_check_handler)
 	jz	3f
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
 3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	stg	%r10,__THREAD_last_break(%r14)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -547,6 +530,8 @@ ENTRY(pgm_check_handler)
 	LOCKDEP_SYS_EXIT
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jno	.Lsysc_restore
+	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL
+	jo	.Lsysc_do_syscall
 	j	.Lsysc_tif
 
 #
@@ -564,6 +549,7 @@ ENTRY(pgm_check_handler)
 #
 .Lpgm_svcper:
 	mvc	__LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
+	lghi	%r13,__TASK_thread
 	larl	%r14,.Lsysc_per
 	stg	%r14,__LC_RETURN_PSW+8
 	lghi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
@@ -576,7 +562,6 @@ ENTRY(io_int_handler)
 	STCK	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
-	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
@@ -680,8 +665,8 @@ ENTRY(io_int_handler)
 	jo	.Lio_notify_resume
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lio_vxrs
-	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE
-	jo	.Lio_uaccess
+	TSTMSK	__LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
+	jnz	.Lio_asce
 	j	.Lio_return		# beware of critical section cleanup
 
 #
@@ -694,12 +679,15 @@ ENTRY(io_int_handler)
 	j	.Lio_return
 
 #
-# _CIF_ASCE is set, load user space asce
+# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
 #
-.Lio_uaccess:
-	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
+.Lio_asce:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	j	.Lio_return
+	TSTMSK	__LC_CPU_FLAGS,_CIF_ASCE_SECONDARY
+	jz	.Lio_return
+	larl	%r14,.Lio_return
+	jg	set_fs_fixup
 
 #
 # CIF_FPU is set, restore floating-point controls and floating-point registers.
@@ -750,7 +738,6 @@ ENTRY(ext_int_handler)
 	STCK	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
-	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
@@ -893,7 +880,6 @@ ENTRY(mcck_int_handler)
 	la	%r1,4095		# revalidate r1
 	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs
-	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
@@ -1088,9 +1074,10 @@ cleanup_critical:
 0:	# check if base register setup + TIF bit load has been done
 	clg	%r9,BASED(.Lcleanup_system_call_insn+16)
 	jhe	0f
-	# set up saved registers r10 and r12
-	stg	%r10,16(%r11)		# r10 last break
-	stg	%r12,32(%r11)		# r12 task struct pointer
+	# set up saved register r12 task struct pointer
+	stg	%r12,32(%r11)
+	# set up saved register r13 __TASK_thread offset
+	mvc	40(8,%r11),BASED(.Lcleanup_system_call_const)
 0:	# check if the user time update has been done
 	clg	%r9,BASED(.Lcleanup_system_call_insn+24)
 	jh	0f
@@ -1107,14 +1094,7 @@ cleanup_critical:
 	stg	%r15,__LC_SYSTEM_TIMER
 0:	# update accounting time stamp
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	# do LAST_BREAK
-	lg	%r9,16(%r11)
-	srag	%r9,%r9,23
-	jz	0f
-	lgr	%r9,%r12
-	aghi	%r9,__TASK_thread
-	mvc	__THREAD_last_break(8,%r9),16(%r11)
-0:	# set up saved register r11
+	# set up saved register r11
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r9,STACK_FRAME_OVERHEAD(%r15)
 	stg	%r9,24(%r11)		# r11 pt_regs pointer
@@ -1136,6 +1116,8 @@ cleanup_critical:
 	.quad	.Lsysc_per
 	.quad	.Lsysc_vtime+36
 	.quad	.Lsysc_vtime+42
+.Lcleanup_system_call_const:
+	.quad	__TASK_thread
 
 .Lcleanup_sysc_tif:
 	larl	%r9,.Lsysc_tif
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index e79f030dd276..33f901865326 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -80,5 +80,6 @@ long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
 void verify_facilities(void);
+void set_fs_fixup(void);
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 7a55c29b0b33..fb07a70820af 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -12,7 +12,7 @@
 #include <linux/notifier.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
@@ -43,7 +43,7 @@ void enabled_wait(void)
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
 	idle->idle_time += idle_time;
 	idle->idle_count++;
-	account_idle_time(idle_time);
+	account_idle_time(cputime_to_nsecs(idle_time));
 	write_seqcount_end(&idle->seqcount);
 }
 NOKPROBE_SYMBOL(enabled_wait);
@@ -57,8 +57,8 @@ static ssize_t show_idle_count(struct device *dev,
 
 	do {
 		seq = read_seqcount_begin(&idle->seqcount);
-		idle_count = ACCESS_ONCE(idle->idle_count);
-		if (ACCESS_ONCE(idle->clock_idle_enter))
+		idle_count = READ_ONCE(idle->idle_count);
+		if (READ_ONCE(idle->clock_idle_enter))
 			idle_count++;
 	} while (read_seqcount_retry(&idle->seqcount, seq));
 	return sprintf(buf, "%llu\n", idle_count);
@@ -75,16 +75,16 @@ static ssize_t show_idle_time(struct device *dev,
 	do {
 		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
-		idle_time = ACCESS_ONCE(idle->idle_time);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+		idle_time = READ_ONCE(idle->idle_time);
+		idle_enter = READ_ONCE(idle->clock_idle_enter);
+		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
 	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
-cputime64_t arch_cpu_idle_time(int cpu)
+u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
 	unsigned long long now, idle_enter, idle_exit;
@@ -93,10 +93,11 @@ cputime64_t arch_cpu_idle_time(int cpu)
 	do {
 		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+		idle_enter = READ_ONCE(idle->clock_idle_enter);
+		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+
+	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
 }
 
 void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index ff3364a067ff..b67dafb7b7cf 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -8,7 +8,8 @@
  */
 
 #include <linux/types.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
@@ -1546,7 +1547,8 @@ static void dump_reipl_run(struct shutdown_trigger *trigger)
 	unsigned long ipib = (unsigned long) reipl_block_actual;
 	unsigned int csum;
 
-	csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
+	csum = (__force unsigned int)
+	       csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
 	mem_assign_absolute(S390_lowcore.ipib, ipib);
 	mem_assign_absolute(S390_lowcore.ipib_checksum, csum);
 	dump_run(trigger);
@@ -1863,7 +1865,7 @@ static int __init s390_ipl_init(void)
 {
 	char str[8] = {0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40};
 
-	sclp_get_ipl_info(&sclp_ipl_info);
+	sclp_early_get_ipl_info(&sclp_ipl_info);
 	/*
 	 * Fix loadparm: There are systems where the (SCSI) LOADPARM
 	 * returned by read SCP info is invalid (contains EBCDIC blanks)
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index ef60f4177331..6dca93b29bed 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -12,11 +12,12 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/profile.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/irq.h>
 #include <asm/irq_regs.h>
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 083b05f5f5ab..6aa630a8d24f 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -4,7 +4,6 @@
  * Copyright IBM Corp. 2011
  * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
  */
-#include <linux/module.h>
 #include <linux/uaccess.h>
 #include <linux/stop_machine.h>
 #include <linux/jump_label.h>
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 84e0557b16fe..76f9eda1d7c0 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -45,11 +45,17 @@ DEFINE_INSN_CACHE_OPS(dmainsn);
 
 static void *alloc_dmainsn_page(void)
 {
-	return (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+	void *page;
+
+	page = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
+	if (page)
+		set_memory_x((unsigned long) page, 1);
+	return page;
 }
 
 static void free_dmainsn_page(void *page)
 {
+	set_memory_nx((unsigned long) page, 1);
 	free_page((unsigned long)page);
 }
 
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index fbc07891f9e7..1a27f307a920 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -45,7 +45,8 @@ void *module_alloc(unsigned long size)
 	if (PAGE_ALIGN(size) > MODULES_LEN)
 		return NULL;
 	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-				    GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    GFP_KERNEL, PAGE_KERNEL_EXEC,
+				    0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 9862196b4b89..80c093e0c6f1 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -13,7 +13,7 @@
 #include <linux/errno.h>
 #include <linux/hardirq.h>
 #include <linux/time.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/lowcore.h>
 #include <asm/smp.h>
 #include <asm/stp.h>
@@ -116,6 +116,19 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 			s390_handle_damage();
 		kill_task = 1;
 	}
+	/* Validate control registers */
+	if (!mci.cr) {
+		/*
+		 * Control registers have unknown contents.
+		 * Can't recover and therefore stopping machine.
+		 */
+		s390_handle_damage();
+	} else {
+		asm volatile(
+			"	lctlg	0,15,0(%0)\n"
+			"	ptlb\n"
+			: : "a" (&S390_lowcore.cregs_save_area) : "memory");
+	}
 	if (!mci.fp) {
 		/*
 		 * Floating point registers can't be restored. If the
@@ -208,18 +221,6 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 		 */
 		kill_task = 1;
 	}
-	/* Validate control registers */
-	if (!mci.cr) {
-		/*
-		 * Control registers have unknown contents.
-		 * Can't recover and therefore stopping machine.
-		 */
-		s390_handle_damage();
-	} else {
-		asm volatile(
-			"	lctlg	0,15,0(%0)"
-			: : "a" (&S390_lowcore.cregs_save_area) : "memory");
-	}
 	/*
 	 * We don't even try to validate the TOD register, since we simply
 	 * can't write something sensible into that register.
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index 87f05e475ae8..753ba63182b9 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -26,7 +26,7 @@ static struct os_info os_info __page_aligned_data;
 u32 os_info_csum(struct os_info *os_info)
 {
 	int size = sizeof(*os_info) - offsetof(struct os_info, version_major);
-	return csum_partial(&os_info->version_major, size, 0);
+	return (__force u32)csum_partial(&os_info->version_major, size, 0);
 }
 
 /*
@@ -46,7 +46,7 @@ void os_info_entry_add(int nr, void *ptr, u64 size)
 {
 	os_info.entry[nr].addr = (u64)(unsigned long)ptr;
 	os_info.entry[nr].size = size;
-	os_info.entry[nr].csum = csum_partial(ptr, size, 0);
+	os_info.entry[nr].csum = (__force u32)csum_partial(ptr, size, 0);
 	os_info.csum = os_info_csum(&os_info);
 }
 
@@ -93,7 +93,7 @@ static void os_info_old_alloc(int nr, int align)
 		msg = "copy failed";
 		goto fail_free;
 	}
-	csum = csum_partial(buf_align, size, 0);
+	csum = (__force u32)csum_partial(buf_align, size, 0);
 	if (csum != os_info_old->entry[nr].csum) {
 		msg = "checksum failed";
 		goto fail_free;
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 4554a4bae39e..c343ac2cf6c5 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -309,7 +309,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	default:
 		model = NULL;
 		break;
-	};
+	}
 
 	if (!model)
 		goto out;
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 400d14f0b9f5..54281660582c 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -23,7 +23,7 @@
 #include <linux/compat.h>
 #include <linux/kprobes.h>
 #include <linux/random.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init_task.h>
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -100,8 +100,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
-		unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
+		    unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct fake_frame
 	{
@@ -156,7 +156,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {
-		unsigned long tls = frame->childregs.gprs[6];
 		if (is_compat_task()) {
 			p->thread.acrs[0] = (unsigned int)tls;
 		} else {
@@ -234,3 +233,16 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	ret = PAGE_ALIGN(mm->brk + brk_rnd());
 	return (ret > mm->brk) ? ret : mm->brk;
 }
+
+void set_fs_fixup(void)
+{
+	struct pt_regs *regs = current_pt_regs();
+	static bool warned;
+
+	set_fs(USER_DS);
+	if (warned)
+		return;
+	WARN(1, "Unbalanced set_fs - int code: 0x%x\n", regs->int_code);
+	show_registers(regs);
+	warned = true;
+}
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 9e60ef144d03..bc2b60dcb178 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -32,7 +32,7 @@ static bool machine_has_cpu_mhz;
 void __init cpu_detect_mhz_feature(void)
 {
 	if (test_facility(34) && __ecag(ECAG_CPU_ATTRIBUTE, 0) != -1UL)
-		machine_has_cpu_mhz = 1;
+		machine_has_cpu_mhz = true;
 }
 
 static void update_cpu_mhz(void *arg)
@@ -73,7 +73,7 @@ void cpu_init(void)
 	get_cpu_id(id);
 	if (machine_has_cpu_mhz)
 		update_cpu_mhz(NULL);
-	atomic_inc(&init_mm.mm_count);
+	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
@@ -92,7 +92,7 @@ static void show_cpu_summary(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te", "vx"
+		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe"
 	};
 	static const char * const int_hwcap_str[] = {
 		"sie"
diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c
deleted file mode 100644
index f08af675f36f..000000000000
--- a/arch/s390/kernel/sclp.c
+++ /dev/null
@@ -1,196 +0,0 @@
-/*
- *    Copyright IBM Corp. 2015
- *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/kernel.h>
-#include <asm/ebcdic.h>
-#include <asm/irq.h>
-#include <asm/lowcore.h>
-#include <asm/processor.h>
-#include <asm/sclp.h>
-
-#define EVTYP_VT220MSG_MASK	0x00000040
-#define EVTYP_MSG_MASK		0x40000000
-
-static char _sclp_work_area[4096] __aligned(PAGE_SIZE) __section(data);
-static bool have_vt220 __section(data);
-static bool have_linemode __section(data);
-
-static void _sclp_wait_int(void)
-{
-	unsigned long cr0, cr0_new, psw_mask, addr;
-	psw_t psw_ext_save, psw_wait;
-
-	__ctl_store(cr0, 0, 0);
-	cr0_new = cr0 | 0x200;
-	__ctl_load(cr0_new, 0, 0);
-
-	psw_ext_save = S390_lowcore.external_new_psw;
-	psw_mask = __extract_psw();
-	S390_lowcore.external_new_psw.mask = psw_mask;
-	psw_wait.mask = psw_mask | PSW_MASK_EXT | PSW_MASK_WAIT;
-	S390_lowcore.ext_int_code = 0;
-
-	do {
-		asm volatile(
-			"	larl	%[addr],0f\n"
-			"	stg	%[addr],%[psw_wait_addr]\n"
-			"	stg	%[addr],%[psw_ext_addr]\n"
-			"	lpswe	%[psw_wait]\n"
-			"0:\n"
-			: [addr] "=&d" (addr),
-			  [psw_wait_addr] "=Q" (psw_wait.addr),
-			  [psw_ext_addr] "=Q" (S390_lowcore.external_new_psw.addr)
-			: [psw_wait] "Q" (psw_wait)
-			: "cc", "memory");
-	} while (S390_lowcore.ext_int_code != EXT_IRQ_SERVICE_SIG);
-
-	__ctl_load(cr0, 0, 0);
-	S390_lowcore.external_new_psw = psw_ext_save;
-}
-
-static int _sclp_servc(unsigned int cmd, char *sccb)
-{
-	unsigned int cc;
-
-	do {
-		asm volatile(
-			"	.insn	rre,0xb2200000,%1,%2\n"
-			"	ipm	%0\n"
-			: "=d" (cc) : "d" (cmd), "a" (sccb)
-			: "cc", "memory");
-		cc >>= 28;
-		if (cc == 3)
-			return -EINVAL;
-		_sclp_wait_int();
-	} while (cc != 0);
-	return (*(unsigned short *)(sccb + 6) == 0x20) ? 0 : -EIO;
-}
-
-static int _sclp_setup(int disable)
-{
-	static unsigned char init_sccb[] = {
-		0x00, 0x1c,
-		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00,
-		0x00, 0x04,
-		0x80, 0x00, 0x00, 0x00,	0x40, 0x00, 0x00, 0x40,
-		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00
-	};
-	unsigned int *masks;
-	int rc;
-
-	memcpy(_sclp_work_area, init_sccb, 28);
-	masks = (unsigned int *)(_sclp_work_area + 12);
-	if (disable)
-		memset(masks, 0, 16);
-	/* SCLP write mask */
-	rc = _sclp_servc(0x00780005, _sclp_work_area);
-	if (rc)
-		return rc;
-	have_vt220 = masks[2] & EVTYP_VT220MSG_MASK;
-	have_linemode = masks[2] & EVTYP_MSG_MASK;
-	return 0;
-}
-
-/* Output multi-line text using SCLP Message interface. */
-static void _sclp_print_lm(const char *str)
-{
-	static unsigned char write_head[] = {
-		/* sccb header */
-		0x00, 0x52,					/* 0 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00,		/* 2 */
-		/* evbuf */
-		0x00, 0x4a,					/* 8 */
-		0x02, 0x00, 0x00, 0x00,				/* 10 */
-		/* mdb */
-		0x00, 0x44,					/* 14 */
-		0x00, 0x01,					/* 16 */
-		0xd4, 0xc4, 0xc2, 0x40,				/* 18 */
-		0x00, 0x00, 0x00, 0x01,				/* 22 */
-		/* go */
-		0x00, 0x38,					/* 26 */
-		0x00, 0x01,					/* 28 */
-		0x00, 0x00, 0x00, 0x00,				/* 30 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 34 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 42 */
-		0x00, 0x00, 0x00, 0x00,				/* 50 */
-		0x00, 0x00,					/* 54 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 56 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 64 */
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 72 */
-		0x00, 0x00,					/* 80 */
-	};
-	static unsigned char write_mto[] = {
-		/* mto	*/
-		0x00, 0x0a,					/* 0 */
-		0x00, 0x04,					/* 2 */
-		0x10, 0x00,					/* 4 */
-		0x00, 0x00, 0x00, 0x00				/* 6 */
-	};
-	unsigned char *ptr, ch;
-	unsigned int count;
-
-	memcpy(_sclp_work_area, write_head, sizeof(write_head));
-	ptr = _sclp_work_area + sizeof(write_head);
-	do {
-		memcpy(ptr, write_mto, sizeof(write_mto));
-		for (count = sizeof(write_mto); (ch = *str++) != 0; count++) {
-			if (ch == 0x0a)
-				break;
-			ptr[count] = _ascebc[ch];
-		}
-		/* Update length fields in mto, mdb, evbuf and sccb */
-		*(unsigned short *) ptr = count;
-		*(unsigned short *)(_sclp_work_area + 14) += count;
-		*(unsigned short *)(_sclp_work_area + 8) += count;
-		*(unsigned short *)(_sclp_work_area + 0) += count;
-		ptr += count;
-	} while (ch != 0);
-
-	/* SCLP write data */
-	_sclp_servc(0x00760005, _sclp_work_area);
-}
-
-/* Output multi-line text (plus a newline) using SCLP VT220
- * interface.
- */
-static void _sclp_print_vt220(const char *str)
-{
-	static unsigned char const write_head[] = {
-		/* sccb header */
-		0x00, 0x0e,
-		0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-		/* evbuf header */
-		0x00, 0x06,
-		0x1a, 0x00, 0x00, 0x00,
-	};
-	size_t len = strlen(str);
-
-	if (sizeof(write_head) + len >= sizeof(_sclp_work_area))
-		len = sizeof(_sclp_work_area) - sizeof(write_head) - 1;
-
-	memcpy(_sclp_work_area, write_head, sizeof(write_head));
-	memcpy(_sclp_work_area + sizeof(write_head), str, len);
-	_sclp_work_area[sizeof(write_head) + len] = '\n';
-
-	/* Update length fields in evbuf and sccb headers */
-	*(unsigned short *)(_sclp_work_area + 8) += len + 1;
-	*(unsigned short *)(_sclp_work_area + 0) += len + 1;
-
-	/* SCLP write data */
-	(void)_sclp_servc(0x00760005, _sclp_work_area);
-}
-
-/* Output one or more lines of text on the SCLP console (VT220 and /
- * or line-mode). All lines get terminated; no need for a trailing LF.
- */
-void _sclp_print_early(const char *str)
-{
-	if (_sclp_setup(0) != 0)
-		return;
-	if (have_linemode)
-		_sclp_print_lm(str);
-	if (have_vt220)
-		_sclp_print_vt220(str);
-	_sclp_setup(1);
-}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 865a48871ca4..e4d811f17971 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -636,6 +636,8 @@ static void __init reserve_crashkernel(void)
 static void __init reserve_initrd(void)
 {
 #ifdef CONFIG_BLK_DEV_INITRD
+	if (!INITRD_START || !INITRD_SIZE)
+		return;
 	initrd_start = INITRD_START;
 	initrd_end = initrd_start + INITRD_SIZE;
 	memblock_reserve(INITRD_START, INITRD_SIZE);
@@ -747,7 +749,7 @@ static int __init setup_hwcaps(void)
 	/*
 	 * Huge page support HWCAP_S390_HPAGE is bit 7.
 	 */
-	if (MACHINE_HAS_HPAGE)
+	if (MACHINE_HAS_EDAT1)
 		elf_hwcap |= HWCAP_S390_HPAGE;
 
 	/*
@@ -767,8 +769,14 @@ static int __init setup_hwcaps(void)
 	 * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX
 	 * instead of facility bit 129.
 	 */
-	if (MACHINE_HAS_VX)
+	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;
+	}
+
 	get_cpu_id(&cpu_id);
 	add_device_randomness(&cpu_id, sizeof(cpu_id));
 	switch (cpu_id.machine) {
@@ -820,10 +828,10 @@ static void __init setup_randomness(void)
 {
 	struct sysinfo_3_2_2 *vmms;
 
-	vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL);
-	if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count)
-		add_device_randomness(&vmms, vmms->count);
-	free_page((unsigned long) vmms);
+	vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
+		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
+	memblock_free((unsigned long) vmms, PAGE_SIZE);
 }
 
 /*
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index e49f61aadaf9..d0a74d7ce433 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -20,7 +20,7 @@
 
 #include <linux/workqueue.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/err.h>
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 355db9db8210..0085b2d8ed7d 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -8,7 +8,7 @@
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 static int __save_address(void *data, unsigned long address, int nosched)
 {
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index 1ff21f05d7dd..6bebc935e9c2 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -196,7 +196,7 @@ pgm_check_entry:
 	larl	%r15,init_thread_union
 	ahi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
 	larl	%r2,.Lpanic_string
-	larl	%r3,_sclp_print_early
+	larl	%r3,sclp_early_printk
 	lghi	%r1,0
 	sam31
 	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
@@ -273,7 +273,7 @@ restore_registers:
 .Ldisabled_wait_31:
 	.long  0x000a0000,0x00000000
 .Lpanic_string:
-	.asciz	"Resume not possible because suspend CPU is no longer available"
+	.asciz	"Resume not possible because suspend CPU is no longer available\n"
 	.align	8
 .Lrestart_diag308_psw:
 	.long	0x00080000,0x80000000
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 24021c1e3ecb..12b6b138e354 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -10,7 +10,7 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 52949df88529..de66abb479c9 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -16,7 +16,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
@@ -110,7 +110,7 @@ unsigned long long monotonic_clock(void)
 }
 EXPORT_SYMBOL(monotonic_clock);
 
-void tod_to_timeval(__u64 todval, struct timespec64 *xt)
+static void tod_to_timeval(__u64 todval, struct timespec64 *xt)
 {
 	unsigned long long sec;
 
@@ -120,7 +120,6 @@ void tod_to_timeval(__u64 todval, struct timespec64 *xt)
 	todval -= (sec * 1000000) << 12;
 	xt->tv_nsec = ((todval * 1000) >> 12);
 }
-EXPORT_SYMBOL(tod_to_timeval);
 
 void clock_comparator_work(void)
 {
@@ -492,7 +491,7 @@ static void __init stp_reset(void)
 		pr_warn("The real or virtual hardware system does not provide an STP interface\n");
 		free_page((unsigned long) stp_page);
 		stp_page = NULL;
-		stp_online = 0;
+		stp_online = false;
 	}
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 93dcbae1e98d..2cd5f4f1013c 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -38,7 +38,6 @@ static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
 
-static bool topology_enabled = true;
 static DECLARE_WORK(topology_work, topology_work_fn);
 
 /*
@@ -59,7 +58,7 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 	cpumask_t mask;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+	if (!MACHINE_HAS_TOPOLOGY)
 		return mask;
 	for (; info; info = info->next) {
 		if (cpumask_test_cpu(cpu, &info->mask))
@@ -74,7 +73,7 @@ static cpumask_t cpu_thread_map(unsigned int cpu)
 	int i;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+	if (!MACHINE_HAS_TOPOLOGY)
 		return mask;
 	cpu -= cpu % (smp_cpu_mtid + 1);
 	for (i = 0; i <= smp_cpu_mtid; i++)
@@ -428,12 +427,6 @@ static const struct cpumask *cpu_drawer_mask(int cpu)
 	return &cpu_topology[cpu].drawer_mask;
 }
 
-static int __init early_parse_topology(char *p)
-{
-	return kstrtobool(p, &topology_enabled);
-}
-early_param("topology", early_parse_topology);
-
 static struct sched_domain_topology_level s390_topology[] = {
 	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
@@ -461,18 +454,16 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
 void __init topology_init_early(void)
 {
 	struct sysinfo_15_1_x *info;
-	int i;
 
 	set_sched_topology(s390_topology);
 	if (!MACHINE_HAS_TOPOLOGY)
 		goto out;
-	tl_info = memblock_virt_alloc(sizeof(*tl_info), PAGE_SIZE);
+	tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE);
 	info = tl_info;
 	store_topology(info);
-	pr_info("The CPU configuration topology of the machine is:");
-	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
-		printk(KERN_CONT " %d", info->mag[i]);
-	printk(KERN_CONT " / %d\n", info->mnest);
+	pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n",
+		info->mag[0], info->mag[1], info->mag[2], info->mag[3],
+		info->mag[4], info->mag[5], info->mnest);
 	alloc_masks(info, &socket_info, 1);
 	alloc_masks(info, &book_info, 2);
 	alloc_masks(info, &drawer_info, 3);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 5904abf6b1ae..10516ae3b55e 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -9,7 +9,7 @@
  * as published by the Free Software Foundation.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 3667d20e997f..5ccf95396251 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -44,6 +44,7 @@ SECTIONS
 		*(.gnu.warning)
 	} :text = 0x0700
 
+	. = ALIGN(PAGE_SIZE);
 	_etext = .;		/* End of text section */
 
 	NOTES :text :note
@@ -79,7 +80,13 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);	/* Init code and data */
 	__init_begin = .;
 
-	INIT_TEXT_SECTION(PAGE_SIZE)
+	. = ALIGN(PAGE_SIZE);
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+		VMLINUX_SYMBOL(_sinittext) = . ;
+		INIT_TEXT
+		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(_einittext) = . ;
+	}
 
 	/*
 	 * .exit.text is discarded at runtime, not link time,
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 1b5c5ee9fc1b..31bd96e81167 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,13 +6,13 @@
  */
 
 #include <linux/kernel_stat.h>
+#include <linux/cputime.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
 
-#include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
 #include <asm/cpu_mf.h>
@@ -90,14 +90,41 @@ static void update_mt_scaling(void)
 	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
 }
 
+static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
+{
+	u64 delta;
+
+	delta = new - *tsk_vtime;
+	*tsk_vtime = new;
+	return delta;
+}
+
+
+static inline u64 scale_vtime(u64 vtime)
+{
+	u64 mult = __this_cpu_read(mt_scaling_mult);
+	u64 div = __this_cpu_read(mt_scaling_div);
+
+	if (smp_cpu_mtid)
+		return vtime * mult / div;
+	return vtime;
+}
+
+static void account_system_index_scaled(struct task_struct *p,
+					cputime_t cputime, cputime_t scaled,
+					enum cpu_usage_stat index)
+{
+	p->stimescaled += cputime_to_nsecs(scaled);
+	account_system_index_time(p, cputime_to_nsecs(cputime), index);
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, system, steal;
-	u64 user_scaled, system_scaled;
+	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -110,53 +137,76 @@ static int do_account_vtime(struct task_struct *tsk)
 #endif
 		: "=m" (S390_lowcore.last_update_timer),
 		  "=m" (S390_lowcore.last_update_clock));
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+	clock = S390_lowcore.last_update_clock - clock;
+	timer -= S390_lowcore.last_update_timer;
+
+	if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
 
 	/* Update MT utilization calculation */
 	if (smp_cpu_mtid &&
 	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
-	user = S390_lowcore.user_timer - tsk->thread.user_timer;
-	S390_lowcore.steal_timer -= user;
-	tsk->thread.user_timer = S390_lowcore.user_timer;
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-
-	user_scaled = user;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
+	/* Calculate cputime delta */
+	user = update_tsk_timer(&tsk->thread.user_timer,
+				READ_ONCE(S390_lowcore.user_timer));
+	guest = update_tsk_timer(&tsk->thread.guest_timer,
+				 READ_ONCE(S390_lowcore.guest_timer));
+	system = update_tsk_timer(&tsk->thread.system_timer,
+				  READ_ONCE(S390_lowcore.system_timer));
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
+				   READ_ONCE(S390_lowcore.hardirq_timer));
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
+				   READ_ONCE(S390_lowcore.softirq_timer));
+	S390_lowcore.steal_timer +=
+		clock - user - guest - system - hardirq - softirq;
+
+	/* Push account value */
+	if (user) {
+		account_user_time(tsk, cputime_to_nsecs(user));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(user));
+	}
 
-		user_scaled = (user_scaled * mult) / div;
-		system_scaled = (system_scaled * mult) / div;
+	if (guest) {
+		account_guest_time(tsk, cputime_to_nsecs(guest));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest));
 	}
-	account_user_time(tsk, user);
-	tsk->utimescaled += user_scaled;
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
+
+	if (system)
+		account_system_index_scaled(tsk, system, scale_vtime(system),
+					    CPUTIME_SYSTEM);
+	if (hardirq)
+		account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
+					    CPUTIME_IRQ);
+	if (softirq)
+		account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
+					    CPUTIME_SOFTIRQ);
 
 	steal = S390_lowcore.steal_timer;
 	if ((s64) steal > 0) {
 		S390_lowcore.steal_timer = 0;
-		account_steal_time(steal);
+		account_steal_time(cputime_to_nsecs(steal));
 	}
 
-	return virt_timer_forward(user + system);
+	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
 void vtime_task_switch(struct task_struct *prev)
 {
 	do_account_vtime(prev);
 	prev->thread.user_timer = S390_lowcore.user_timer;
+	prev->thread.guest_timer = S390_lowcore.guest_timer;
 	prev->thread.system_timer = S390_lowcore.system_timer;
+	prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
+	prev->thread.softirq_timer = S390_lowcore.softirq_timer;
 	S390_lowcore.user_timer = current->thread.user_timer;
+	S390_lowcore.guest_timer = current->thread.guest_timer;
 	S390_lowcore.system_timer = current->thread.system_timer;
+	S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
+	S390_lowcore.softirq_timer = current->thread.softirq_timer;
 }
 
 /*
@@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev)
  * accounting system time in order to correctly compute
  * the stolen time accounting.
  */
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
@@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk)
  */
 void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	u64 timer, system, system_scaled;
+	u64 timer;
 
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-
-	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
-		update_mt_scaling();
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
-
-		system_scaled = (system_scaled * mult) / div;
-	}
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
-
-	virt_timer_forward(system);
+	timer -= S390_lowcore.last_update_timer;
+
+	if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
+		S390_lowcore.guest_timer += timer;
+	else if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else if (in_serving_softirq())
+		S390_lowcore.softirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
+
+	virt_timer_forward(timer);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 
@@ -310,7 +350,7 @@ static void __add_vtimer(struct vtimer_list *timer, int periodic)
 }
 
 /*
- * add_virt_timer - add an oneshot virtual CPU timer
+ * add_virt_timer - add a oneshot virtual CPU timer
  */
 void add_virt_timer(struct vtimer_list *timer)
 {
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4aa8a7e2a1da..4492c9363178 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
 		ipte_unlock_simple(vcpu);
 }
 
-static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
+static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar,
 			  enum gacc_mode mode)
 {
 	union alet alet;
@@ -465,7 +465,9 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
 struct trans_exc_code_bits {
 	unsigned long addr : 52; /* Translation-exception Address */
 	unsigned long fsi  : 2;  /* Access Exception Fetch/Store Indication */
-	unsigned long	   : 6;
+	unsigned long	   : 2;
+	unsigned long b56  : 1;
+	unsigned long	   : 3;
 	unsigned long b60  : 1;
 	unsigned long b61  : 1;
 	unsigned long as   : 2;  /* ASCE Identifier */
@@ -485,7 +487,7 @@ enum prot_type {
 };
 
 static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
-		     ar_t ar, enum gacc_mode mode, enum prot_type prot)
+		     u8 ar, enum gacc_mode mode, enum prot_type prot)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	struct trans_exc_code_bits *tec;
@@ -497,14 +499,18 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 	switch (code) {
 	case PGM_PROTECTION:
 		switch (prot) {
+		case PROT_TYPE_LA:
+			tec->b56 = 1;
+			break;
+		case PROT_TYPE_KEYC:
+			tec->b60 = 1;
+			break;
 		case PROT_TYPE_ALC:
 			tec->b60 = 1;
 			/* FALL THROUGH */
 		case PROT_TYPE_DAT:
 			tec->b61 = 1;
 			break;
-		default: /* LA and KEYC set b61 to 0, other params undefined */
-			return code;
 		}
 		/* FALL THROUGH */
 	case PGM_ASCE_TYPE:
@@ -539,7 +545,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 }
 
 static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
-			 unsigned long ga, ar_t ar, enum gacc_mode mode)
+			 unsigned long ga, u8 ar, enum gacc_mode mode)
 {
 	int rc;
 	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
@@ -771,7 +777,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar,
+static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 			    unsigned long *pages, unsigned long nr_pages,
 			    const union asce asce, enum gacc_mode mode)
 {
@@ -803,7 +809,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar,
 	return 0;
 }
 
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -877,7 +883,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * Note: The IPTE lock is not taken during this function, so the caller
  * has to take care of this.
  */
-int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 			    unsigned long *gpa, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -910,7 +916,7 @@ 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,
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
 {
 	unsigned long gpa;
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 8756569ad938..7ce47fd36f28 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -162,11 +162,11 @@ enum gacc_mode {
 };
 
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
-			    ar_t ar, unsigned long *gpa, enum gacc_mode mode);
-int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+			    u8 ar, unsigned long *gpa, enum gacc_mode mode);
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode);
 
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode);
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
@@ -218,7 +218,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  *	 if data has been changed in guest space in case of an exception.
  */
 static inline __must_check
-int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		unsigned long len)
 {
 	return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
@@ -238,7 +238,7 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
  * data will be copied from guest space to kernel space.
  */
 static inline __must_check
-int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 	       unsigned long len)
 {
 	return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
@@ -247,10 +247,11 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 /**
  * read_guest_instr - copy instruction data from guest space to kernel space
  * @vcpu: virtual cpu
+ * @ga: guest address
  * @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
+ * Copy @len bytes from the given address (guest space) to @data (kernel
  * space).
  *
  * The behaviour of read_guest_instr is identical to read_guest, except that
@@ -258,10 +259,10 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
  * address-space mode.
  */
 static inline __must_check
-int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+int read_guest_instr(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+		     unsigned long len)
 {
-	return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
-			    GACC_IFETCH);
+	return access_guest(vcpu, ga, 0, data, len, GACC_IFETCH);
 }
 
 /**
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index d7c6a7f53ced..23d9a4e12da1 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -388,14 +388,13 @@ void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu)
 #define per_write_wp_event(code) \
 			(code & (PER_CODE_STORE | PER_CODE_STORE_REAL))
 
-static int debug_exit_required(struct kvm_vcpu *vcpu)
+static int debug_exit_required(struct kvm_vcpu *vcpu, u8 perc,
+			       unsigned long peraddr)
 {
-	u8 perc = vcpu->arch.sie_block->perc;
 	struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch;
 	struct kvm_hw_wp_info_arch *wp_info = NULL;
 	struct kvm_hw_bp_info_arch *bp_info = NULL;
 	unsigned long addr = vcpu->arch.sie_block->gpsw.addr;
-	unsigned long peraddr = vcpu->arch.sie_block->peraddr;
 
 	if (guestdbg_hw_bp_enabled(vcpu)) {
 		if (per_write_wp_event(perc) &&
@@ -437,36 +436,118 @@ exit_required:
 	return 1;
 }
 
+static int per_fetched_addr(struct kvm_vcpu *vcpu, unsigned long *addr)
+{
+	u8 exec_ilen = 0;
+	u16 opcode[3];
+	int rc;
+
+	if (vcpu->arch.sie_block->icptcode == ICPT_PROGI) {
+		/* PER address references the fetched or the execute instr */
+		*addr = vcpu->arch.sie_block->peraddr;
+		/*
+		 * Manually detect if we have an EXECUTE instruction. As
+		 * instructions are always 2 byte aligned we can read the
+		 * first two bytes unconditionally
+		 */
+		rc = read_guest_instr(vcpu, *addr, &opcode, 2);
+		if (rc)
+			return rc;
+		if (opcode[0] >> 8 == 0x44)
+			exec_ilen = 4;
+		if ((opcode[0] & 0xff0f) == 0xc600)
+			exec_ilen = 6;
+	} else {
+		/* instr was suppressed, calculate the responsible instr */
+		*addr = __rewind_psw(vcpu->arch.sie_block->gpsw,
+				     kvm_s390_get_ilen(vcpu));
+		if (vcpu->arch.sie_block->icptstatus & 0x01) {
+			exec_ilen = (vcpu->arch.sie_block->icptstatus & 0x60) >> 4;
+			if (!exec_ilen)
+				exec_ilen = 4;
+		}
+	}
+
+	if (exec_ilen) {
+		/* read the complete EXECUTE instr to detect the fetched addr */
+		rc = read_guest_instr(vcpu, *addr, &opcode, exec_ilen);
+		if (rc)
+			return rc;
+		if (exec_ilen == 6) {
+			/* EXECUTE RELATIVE LONG - RIL-b format */
+			s32 rl = *((s32 *) (opcode + 1));
+
+			/* rl is a _signed_ 32 bit value specifying halfwords */
+			*addr += (u64)(s64) rl * 2;
+		} else {
+			/* EXECUTE - RX-a format */
+			u32 base = (opcode[1] & 0xf000) >> 12;
+			u32 disp = opcode[1] & 0x0fff;
+			u32 index = opcode[0] & 0x000f;
+
+			*addr = base ? vcpu->run->s.regs.gprs[base] : 0;
+			*addr += index ? vcpu->run->s.regs.gprs[index] : 0;
+			*addr += disp;
+		}
+		*addr = kvm_s390_logical_to_effective(vcpu, *addr);
+	}
+	return 0;
+}
+
 #define guest_per_enabled(vcpu) \
 			     (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER)
 
 int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu)
 {
+	const u64 cr10 = vcpu->arch.sie_block->gcr[10];
+	const u64 cr11 = vcpu->arch.sie_block->gcr[11];
 	const u8 ilen = kvm_s390_get_ilen(vcpu);
 	struct kvm_s390_pgm_info pgm_info = {
 		.code = PGM_PER,
 		.per_code = PER_CODE_IFETCH,
 		.per_address = __rewind_psw(vcpu->arch.sie_block->gpsw, ilen),
 	};
+	unsigned long fetched_addr;
+	int rc;
 
 	/*
 	 * The PSW points to the next instruction, therefore the intercepted
 	 * instruction generated a PER i-fetch event. PER address therefore
 	 * points at the previous PSW address (could be an EXECUTE function).
 	 */
-	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	if (!guestdbg_enabled(vcpu))
+		return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+
+	if (debug_exit_required(vcpu, pgm_info.per_code, pgm_info.per_address))
+		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
+
+	if (!guest_per_enabled(vcpu) ||
+	    !(vcpu->arch.sie_block->gcr[9] & PER_EVENT_IFETCH))
+		return 0;
+
+	rc = per_fetched_addr(vcpu, &fetched_addr);
+	if (rc < 0)
+		return rc;
+	if (rc)
+		/* instruction-fetching exceptions */
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	if (in_addr_range(fetched_addr, cr10, cr11))
+		return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	return 0;
 }
 
-static void filter_guest_per_event(struct kvm_vcpu *vcpu)
+static int filter_guest_per_event(struct kvm_vcpu *vcpu)
 {
 	const u8 perc = vcpu->arch.sie_block->perc;
-	u64 peraddr = vcpu->arch.sie_block->peraddr;
 	u64 addr = vcpu->arch.sie_block->gpsw.addr;
 	u64 cr9 = vcpu->arch.sie_block->gcr[9];
 	u64 cr10 = vcpu->arch.sie_block->gcr[10];
 	u64 cr11 = vcpu->arch.sie_block->gcr[11];
 	/* filter all events, demanded by the guest */
 	u8 guest_perc = perc & (cr9 >> 24) & PER_CODE_MASK;
+	unsigned long fetched_addr;
+	int rc;
 
 	if (!guest_per_enabled(vcpu))
 		guest_perc = 0;
@@ -478,9 +559,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 		guest_perc &= ~PER_CODE_BRANCH;
 
 	/* filter "instruction-fetching" events */
-	if (guest_perc & PER_CODE_IFETCH &&
-	    !in_addr_range(peraddr, cr10, cr11))
-		guest_perc &= ~PER_CODE_IFETCH;
+	if (guest_perc & PER_CODE_IFETCH) {
+		rc = per_fetched_addr(vcpu, &fetched_addr);
+		if (rc < 0)
+			return rc;
+		/*
+		 * Don't inject an irq on exceptions. This would make handling
+		 * on icpt code 8 very complex (as PSW was already rewound).
+		 */
+		if (rc || !in_addr_range(fetched_addr, cr10, cr11))
+			guest_perc &= ~PER_CODE_IFETCH;
+	}
 
 	/* All other PER events will be given to the guest */
 	/* TODO: Check altered address/address space */
@@ -489,6 +578,7 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 
 	if (!guest_perc)
 		vcpu->arch.sie_block->iprcc &= ~PGM_PER;
+	return 0;
 }
 
 #define pssec(vcpu) (vcpu->arch.sie_block->gcr[1] & _ASCE_SPACE_SWITCH)
@@ -496,14 +586,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 #define old_ssec(vcpu) ((vcpu->arch.sie_block->tecmc >> 31) & 0x1)
 #define old_as_is_home(vcpu) !(vcpu->arch.sie_block->tecmc & 0xffff)
 
-void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
+int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 {
-	int new_as;
+	int rc, new_as;
 
-	if (debug_exit_required(vcpu))
+	if (debug_exit_required(vcpu, vcpu->arch.sie_block->perc,
+				vcpu->arch.sie_block->peraddr))
 		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
 
-	filter_guest_per_event(vcpu);
+	rc = filter_guest_per_event(vcpu);
+	if (rc)
+		return rc;
 
 	/*
 	 * Only RP, SAC, SACF, PT, PTI, PR, PC instructions can trigger
@@ -532,4 +625,5 @@ void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 		    (pssec(vcpu) || old_ssec(vcpu)))
 			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
 	}
+	return 0;
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 7a27eebab28a..59920f96ebc0 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -238,7 +238,9 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	vcpu->stat.exit_program_interruption++;
 
 	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
-		kvm_s390_handle_per_event(vcpu);
+		rc = kvm_s390_handle_per_event(vcpu);
+		if (rc)
+			return rc;
 		/* the interrupt might have been filtered out completely */
 		if (vcpu->arch.sie_block->iprcc == 0)
 			return 0;
@@ -359,6 +361,9 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
 
 static int handle_operexc(struct kvm_vcpu *vcpu)
 {
+	psw_t oldpsw, newpsw;
+	int rc;
+
 	vcpu->stat.exit_operation_exception++;
 	trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa,
 				      vcpu->arch.sie_block->ipb);
@@ -369,6 +374,24 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
 		return -EOPNOTSUPP;
+	rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t));
+	if (rc)
+		return rc;
+	/*
+	 * Avoid endless loops of operation exceptions, if the pgm new
+	 * PSW will cause a new operation exception.
+	 * The heuristic checks if the pgm new psw is within 6 bytes before
+	 * the faulting psw address (with same DAT, AS settings) and the
+	 * new psw is not a wait psw and the fault was not triggered by
+	 * problem state.
+	 */
+	oldpsw = vcpu->arch.sie_block->gpsw;
+	if (oldpsw.addr - newpsw.addr <= 6 &&
+	    !(newpsw.mask & PSW_MASK_WAIT) &&
+	    !(oldpsw.mask & PSW_MASK_PSTATE) &&
+	    (newpsw.mask & PSW_MASK_ASC) == (oldpsw.mask & PSW_MASK_ASC) &&
+	    (newpsw.mask & PSW_MASK_DAT) == (oldpsw.mask & PSW_MASK_DAT))
+		return -EOPNOTSUPP;
 
 	return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6484a250021e..f5694838234d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -23,6 +23,7 @@
 #include <linux/kvm_host.h>
 #include <linux/mman.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
@@ -217,7 +218,7 @@ static void allow_cpu_feat(unsigned long nr)
 static inline int plo_test_bit(unsigned char nr)
 {
 	register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
-	int cc = 3; /* subfunction not available */
+	int cc;
 
 	asm volatile(
 		/* Parameter registers are ignored for "test bit" */
@@ -370,6 +371,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
 	case KVM_CAP_MP_STATE:
+	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_S390_INJECT_IRQ:
 	case KVM_CAP_S390_USER_SIGP:
 	case KVM_CAP_S390_USER_STSI:
@@ -442,6 +444,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return -EINVAL;
+
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
@@ -505,6 +510,14 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		} else if (MACHINE_HAS_VX) {
 			set_kvm_facility(kvm->arch.model.fac_mask, 129);
 			set_kvm_facility(kvm->arch.model.fac_list, 129);
+			if (test_facility(134)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 134);
+				set_kvm_facility(kvm->arch.model.fac_list, 134);
+			}
+			if (test_facility(135)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 135);
+				set_kvm_facility(kvm->arch.model.fac_list, 135);
+			}
 			r = 0;
 		} else
 			r = -EINVAL;
@@ -821,6 +834,13 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		}
 		memcpy(kvm->arch.model.fac_list, proc->fac_list,
 		       S390_ARCH_FAC_LIST_SIZE_BYTE);
+		VM_EVENT(kvm, 3, "SET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
+			 kvm->arch.model.ibc,
+			 kvm->arch.model.cpuid);
+		VM_EVENT(kvm, 3, "SET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
+			 kvm->arch.model.fac_list[0],
+			 kvm->arch.model.fac_list[1],
+			 kvm->arch.model.fac_list[2]);
 	} else
 		ret = -EFAULT;
 	kfree(proc);
@@ -894,6 +914,13 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	proc->ibc = kvm->arch.model.ibc;
 	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+	VM_EVENT(kvm, 3, "GET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
+		 kvm->arch.model.ibc,
+		 kvm->arch.model.cpuid);
+	VM_EVENT(kvm, 3, "GET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
+		 kvm->arch.model.fac_list[0],
+		 kvm->arch.model.fac_list[1],
+		 kvm->arch.model.fac_list[2]);
 	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
 		ret = -EFAULT;
 	kfree(proc);
@@ -917,6 +944,17 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
 	       sizeof(S390_lowcore.stfle_fac_list));
+	VM_EVENT(kvm, 3, "GET: host ibc:  0x%4.4x, host cpuid:  0x%16.16llx",
+		 kvm->arch.model.ibc,
+		 kvm->arch.model.cpuid);
+	VM_EVENT(kvm, 3, "GET: host facmask:  0x%16.16llx.%16.16llx.%16.16llx",
+		 mach->fac_mask[0],
+		 mach->fac_mask[1],
+		 mach->fac_mask[2]);
+	VM_EVENT(kvm, 3, "GET: host faclist:  0x%16.16llx.%16.16llx.%16.16llx",
+		 mach->fac_list[0],
+		 mach->fac_list[1],
+		 mach->fac_list[2]);
 	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
 		ret = -EFAULT;
 	kfree(mach);
@@ -1938,6 +1976,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
 		vcpu->arch.sie_block->ecb2 |= 0x08;
+	if (test_kvm_facility(vcpu->kvm, 130))
+		vcpu->arch.sie_block->ecb2 |= 0x20;
 	vcpu->arch.sie_block->eca = 0x1002000U;
 	if (sclp.has_cei)
 		vcpu->arch.sie_block->eca |= 0x80000000U;
@@ -2578,7 +2618,7 @@ 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_instr(vcpu, &opcode, 1);
+	rc = read_guest_instr(vcpu, vcpu->arch.sie_block->gpsw.addr, &opcode, 1);
 	ilen = insn_length(opcode);
 	if (rc < 0) {
 		return rc;
@@ -2760,6 +2800,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int rc;
 	sigset_t sigsaved;
 
+	if (kvm_run->immediate_exit)
+		return -EINTR;
+
 	if (guestdbg_exit_pending(vcpu)) {
 		kvm_s390_prepare_debug_exit(vcpu);
 		return 0;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 3a4e97f1a9e6..af9fa91a0c91 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -86,9 +86,7 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 }
 
-typedef u8 __bitwise ar_t;
-
-static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
@@ -101,7 +99,7 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
 
 static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
 					      u64 *address1, u64 *address2,
-					      ar_t *ar_b1, ar_t *ar_b2)
+					      u8 *ar_b1, u8 *ar_b2)
 {
 	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
 	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
@@ -125,7 +123,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2
 		*r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
 }
 
-static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
@@ -140,7 +138,7 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
 }
 
-static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
@@ -379,7 +377,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu);
-void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
 /* support for Basic/Extended SCA handling */
 static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index e18435355c16..fb4b494cde9b 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -54,7 +54,7 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu)
 static int handle_set_clock(struct kvm_vcpu *vcpu)
 {
 	int rc;
-	ar_t ar;
+	u8 ar;
 	u64 op2, val;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
@@ -79,7 +79,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 	u64 operand2;
 	u32 address;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_spx++;
 
@@ -117,7 +117,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	u64 operand2;
 	u32 address;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stpx++;
 
@@ -147,7 +147,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	u16 vcpu_id = vcpu->vcpu_id;
 	u64 ga;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stap++;
 
@@ -311,7 +311,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 		if (rc < 0)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		start += PAGE_SIZE;
-	};
+	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
 		if (m3 & SSKE_MB) {
@@ -380,7 +380,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	u32 tpi_data[3];
 	int rc;
 	u64 addr;
-	ar_t ar;
+	u8 ar;
 
 	addr = kvm_s390_get_base_disp_s(vcpu, &ar);
 	if (addr & 3)
@@ -548,7 +548,7 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
 	psw_compat_t new_psw;
 	u64 addr;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	if (gpsw->mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -575,7 +575,7 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
 	psw_t new_psw;
 	u64 addr;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -597,7 +597,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	u64 stidp_data = vcpu->kvm->arch.model.cpuid;
 	u64 operand2;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stidp++;
 
@@ -644,7 +644,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 	ASCEBC(mem->vm[0].cpi, 16);
 }
 
-static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar,
+static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, u8 ar,
 				 u8 fc, u8 sel1, u16 sel2)
 {
 	vcpu->run->exit_reason = KVM_EXIT_S390_STSI;
@@ -663,7 +663,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	unsigned long mem = 0;
 	u64 operand2;
 	int rc = 0;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stsi++;
 	VCPU_EVENT(vcpu, 3, "STSI: fc: %u sel1: %u sel2: %u", fc, sel1, sel2);
@@ -970,7 +970,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u32 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_lctl++;
 
@@ -1009,7 +1009,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u32 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stctl++;
 
@@ -1043,7 +1043,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u64 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_lctlg++;
 
@@ -1081,7 +1081,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u64 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stctg++;
 
@@ -1132,7 +1132,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	unsigned long hva, gpa;
 	int ret = 0, cc = 0;
 	bool writable;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_tprot++;
 
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index d8673e243f13..38556e395915 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -324,6 +324,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* Run-time-Instrumentation */
 	if (test_kvm_facility(vcpu->kvm, 64))
 		scb_s->ecb3 |= scb_o->ecb3 & 0x01U;
+	/* Instruction Execution Prevention */
+	if (test_kvm_facility(vcpu->kvm, 130))
+		scb_s->ecb2 |= scb_o->ecb2 & 0x20U;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIIF))
 		scb_s->eca |= scb_o->eca & 0x00000001U;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IB))
@@ -899,7 +902,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		if (rc || scb_s->icptcode || signal_pending(current) ||
 		    kvm_s390_vcpu_has_irq(vcpu, 0))
 			break;
-	};
+	}
 
 	if (rc == -EFAULT) {
 		/*
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 501dcd4ca4a0..92e90e40b6fb 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -9,7 +9,7 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/timex.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 7422a706f310..7ff79a4ff00c 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -14,31 +14,29 @@ ENTRY(memmove)
 	ltgr	%r4,%r4
 	lgr	%r1,%r2
 	bzr	%r14
+	aghi	%r4,-1
 	clgr	%r2,%r3
 	jnh	.Lmemmove_forward
-	la	%r5,0(%r4,%r3)
+	la	%r5,1(%r4,%r3)
 	clgr	%r2,%r5
 	jl	.Lmemmove_reverse
 .Lmemmove_forward:
-	aghi	%r4,-1
 	srlg	%r0,%r4,8
 	ltgr	%r0,%r0
-	jz	.Lmemmove_rest
-.Lmemmove_loop:
+	jz	.Lmemmove_forward_remainder
+.Lmemmove_forward_loop:
 	mvc	0(256,%r1),0(%r3)
 	la	%r1,256(%r1)
 	la	%r3,256(%r3)
-	brctg	%r0,.Lmemmove_loop
-.Lmemmove_rest:
+	brctg	%r0,.Lmemmove_forward_loop
+.Lmemmove_forward_remainder:
 	larl	%r5,.Lmemmove_mvc
 	ex	%r4,0(%r5)
 	br	%r14
 .Lmemmove_reverse:
-	aghi	%r4,-1
-.Lmemmove_reverse_loop:
 	ic	%r0,0(%r4,%r3)
 	stc	%r0,0(%r4,%r1)
-	brctg	%r4,.Lmemmove_reverse_loop
+	brctg	%r4,.Lmemmove_reverse
 	ic	%r0,0(%r4,%r3)
 	stc	%r0,0(%r4,%r1)
 	br	%r14
@@ -70,12 +68,12 @@ ENTRY(memset)
 	srlg	%r3,%r4,8
 	ltgr	%r3,%r3
 	lgr	%r1,%r2
-	jz	.Lmemset_clear_rest
+	jz	.Lmemset_clear_remainder
 .Lmemset_clear_loop:
 	xc	0(256,%r1),0(%r1)
 	la	%r1,256(%r1)
 	brctg	%r3,.Lmemset_clear_loop
-.Lmemset_clear_rest:
+.Lmemset_clear_remainder:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
 	br	%r14
@@ -87,12 +85,12 @@ ENTRY(memset)
 	aghi	%r4,-2
 	srlg	%r3,%r4,8
 	ltgr	%r3,%r3
-	jz	.Lmemset_fill_rest
+	jz	.Lmemset_fill_remainder
 .Lmemset_fill_loop:
 	mvc	1(256,%r1),0(%r1)
 	la	%r1,256(%r1)
 	brctg	%r3,.Lmemset_fill_loop
-.Lmemset_fill_rest:
+.Lmemset_fill_remainder:
 	larl	%r3,.Lmemset_mvc
 	ex	%r4,0(%r3)
 	br	%r14
@@ -115,7 +113,7 @@ ENTRY(memcpy)
 	ltgr	%r5,%r5
 	lgr	%r1,%r2
 	jnz	.Lmemcpy_loop
-.Lmemcpy_rest:
+.Lmemcpy_remainder:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
 	br	%r14
@@ -124,7 +122,7 @@ ENTRY(memcpy)
 	la	%r1,256(%r1)
 	la	%r3,256(%r3)
 	brctg	%r5,.Lmemcpy_loop
-	j	.Lmemcpy_rest
+	j	.Lmemcpy_remainder
 .Lmemcpy_mvc:
 	mvc	0(1,%r1),0(%r3)
 EXPORT_SYMBOL(memcpy)
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index e48a48ec24bc..ba427eb6f14c 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -6,7 +6,7 @@
  */
 
 #include <linux/types.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
 #include <linux/smp.h>
@@ -133,7 +133,7 @@ int arch_spin_trylock_retry(arch_spinlock_t *lp)
 	int count;
 
 	for (count = spin_retry; count > 0; count--) {
-		owner = ACCESS_ONCE(lp->lock);
+		owner = READ_ONCE(lp->lock);
 		/* Try to get the lock if it is free. */
 		if (!owner) {
 			if (_raw_compare_and_swap(&lp->lock, 0, cpu))
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index f71d9f655970..4ee27339c792 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -9,7 +9,8 @@
 #define IN_ARCH_STRING_C 1
 
 #include <linux/types.h>
-#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/export.h>
 
 /*
  * Helper functions to find the end of a string
diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 7d94e3ec34a9..b4fd05c36151 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -6,7 +6,7 @@
  */
 
 #include <linux/types.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/raid/xor.h>
 
 static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 79ddd580d605..829c63dbc81a 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sysctl.h>
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 861880df12c7..1b553d847140 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -1,6 +1,6 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
-#include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -49,8 +49,8 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level)
 		seq_printf(m, "I\n");
 		return;
 	}
-	seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW ");
-	seq_putc(m, '\n');
+	seq_puts(m, (pr & _PAGE_PROTECT) ? "RO " : "RW ");
+	seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n");
 }
 
 static void note_page(struct seq_file *m, struct pg_state *st,
@@ -117,7 +117,8 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st,
 	for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) {
 		st->current_address = addr;
 		pte = pte_offset_kernel(pmd, addr);
-		prot = pte_val(*pte) & (_PAGE_PROTECT | _PAGE_INVALID);
+		prot = pte_val(*pte) &
+			(_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC);
 		note_page(m, st, prot, 4);
 		addr += PAGE_SIZE;
 	}
@@ -135,7 +136,9 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
 		pmd = pmd_offset(pud, addr);
 		if (!pmd_none(*pmd)) {
 			if (pmd_large(*pmd)) {
-				prot = pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT;
+				prot = pmd_val(*pmd) &
+					(_SEGMENT_ENTRY_PROTECT |
+					 _SEGMENT_ENTRY_NOEXEC);
 				note_page(m, st, prot, 3);
 			} else
 				walk_pte_level(m, st, pmd, addr);
@@ -157,7 +160,9 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st,
 		pud = pud_offset(pgd, addr);
 		if (!pud_none(*pud))
 			if (pud_large(*pud)) {
-				prot = pud_val(*pud) & _REGION_ENTRY_PROTECT;
+				prot = pud_val(*pud) &
+					(_REGION_ENTRY_PROTECT |
+					 _REGION_ENTRY_NOEXEC);
 				note_page(m, st, prot, 2);
 			} else
 				walk_pmd_level(m, st, pud, addr);
@@ -183,6 +188,7 @@ static void walk_pgd_level(struct seq_file *m)
 		else
 			note_page(m, &st, _PAGE_INVALID, 1);
 		addr += PGDIR_SIZE;
+		cond_resched();
 	}
 	/* Flush out the last page */
 	st.current_address = max_addr;
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 362237203144..9f118629b55f 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -14,7 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bootmem.h>
 #include <linux/ctype.h>
 #include <linux/ioport.h>
@@ -154,7 +154,7 @@ dcss_mkname(char *name, char *dcss_name)
 		if (name[i] == '\0')
 			break;
 		dcss_name[i] = toupper(name[i]);
-	};
+	}
 	for (; i < 8; i++)
 		dcss_name[i] = ' ';
 	ASCEBC(dcss_name, 8);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index d1faae5cdd12..bb5560eb2435 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -311,12 +311,34 @@ static noinline void do_sigbus(struct pt_regs *regs)
 	force_sig_info(SIGBUS, &si, tsk);
 }
 
-static noinline void do_fault_error(struct pt_regs *regs, int fault)
+static noinline int signal_return(struct pt_regs *regs)
+{
+	u16 instruction;
+	int rc;
+
+	rc = __get_user(instruction, (u16 __user *) regs->psw.addr);
+	if (rc)
+		return rc;
+	if (instruction == 0x0a77) {
+		set_pt_regs_flag(regs, PIF_SYSCALL);
+		regs->int_code = 0x00040077;
+		return 0;
+	} else if (instruction == 0x0aad) {
+		set_pt_regs_flag(regs, PIF_SYSCALL);
+		regs->int_code = 0x000400ad;
+		return 0;
+	}
+	return -EACCES;
+}
+
+static noinline void do_fault_error(struct pt_regs *regs, int access, int fault)
 {
 	int si_code;
 
 	switch (fault) {
 	case VM_FAULT_BADACCESS:
+		if (access == VM_EXEC && signal_return(regs) == 0)
+			break;
 	case VM_FAULT_BADMAP:
 		/* Bad memory access. Check if it is kernel or user space. */
 		if (user_mode(regs)) {
@@ -324,7 +346,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 			si_code = (fault == VM_FAULT_BADMAP) ?
 				SEGV_MAPERR : SEGV_ACCERR;
 			do_sigsegv(regs, si_code);
-			return;
+			break;
 		}
 	case VM_FAULT_BADCONTEXT:
 	case VM_FAULT_PFAULT:
@@ -525,7 +547,7 @@ out:
 void do_protection_exception(struct pt_regs *regs)
 {
 	unsigned long trans_exc_code;
-	int fault;
+	int access, fault;
 
 	trans_exc_code = regs->int_parm_long;
 	/*
@@ -544,9 +566,17 @@ void do_protection_exception(struct pt_regs *regs)
 		do_low_address(regs);
 		return;
 	}
-	fault = do_exception(regs, VM_WRITE);
+	if (unlikely(MACHINE_HAS_NX && (trans_exc_code & 0x80))) {
+		regs->int_parm_long = (trans_exc_code & ~PAGE_MASK) |
+					(regs->psw.addr & PAGE_MASK);
+		access = VM_EXEC;
+		fault = VM_FAULT_BADACCESS;
+	} else {
+		access = VM_WRITE;
+		fault = do_exception(regs, access);
+	}
 	if (unlikely(fault))
-		do_fault_error(regs, fault);
+		do_fault_error(regs, access, fault);
 }
 NOKPROBE_SYMBOL(do_protection_exception);
 
@@ -557,7 +587,7 @@ void do_dat_exception(struct pt_regs *regs)
 	access = VM_READ | VM_EXEC | VM_WRITE;
 	fault = do_exception(regs, access);
 	if (unlikely(fault))
-		do_fault_error(regs, fault);
+		do_fault_error(regs, access, fault);
 }
 NOKPROBE_SYMBOL(do_dat_exception);
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index ec1f0dedb948..a07b1ec1391d 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -359,8 +359,8 @@ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
 	spin_lock(&gmap->guest_table_lock);
 	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
 	if (entry) {
-		flush = (*entry != _SEGMENT_ENTRY_INVALID);
-		*entry = _SEGMENT_ENTRY_INVALID;
+		flush = (*entry != _SEGMENT_ENTRY_EMPTY);
+		*entry = _SEGMENT_ENTRY_EMPTY;
 	}
 	spin_unlock(&gmap->guest_table_lock);
 	return flush;
@@ -589,7 +589,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 		return rc;
 	ptl = pmd_lock(mm, pmd);
 	spin_lock(&gmap->guest_table_lock);
-	if (*table == _SEGMENT_ENTRY_INVALID) {
+	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
 				       vmaddr >> PMD_SHIFT, table);
 		if (!rc)
@@ -687,7 +687,7 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
-		zap_page_range(vma, vmaddr, size, NULL);
+		zap_page_range(vma, vmaddr, size);
 	}
 	up_read(&gmap->mm->mmap_sem);
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 4a0c5bce3552..9b4050caa4e9 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -59,8 +59,10 @@ static inline unsigned long __pte_to_rste(pte_t pte)
 		rste |= move_set_bit(pte_val(pte), _PAGE_SOFT_DIRTY,
 				     _SEGMENT_ENTRY_SOFT_DIRTY);
 #endif
+		rste |= move_set_bit(pte_val(pte), _PAGE_NOEXEC,
+				     _SEGMENT_ENTRY_NOEXEC);
 	} else
-		rste = _SEGMENT_ENTRY_INVALID;
+		rste = _SEGMENT_ENTRY_EMPTY;
 	return rste;
 }
 
@@ -113,6 +115,8 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
 					     _PAGE_DIRTY);
 #endif
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
+					     _PAGE_NOEXEC);
 	} else
 		pte_val(pte) = _PAGE_INVALID;
 	return pte;
@@ -121,7 +125,11 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
-	unsigned long rste = __pte_to_rste(pte);
+	unsigned long rste;
+
+	rste = __pte_to_rste(pte);
+	if (!MACHINE_HAS_NX)
+		rste &= ~_SEGMENT_ENTRY_NOEXEC;
 
 	/* Set correct table type for 2G hugepages */
 	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index b67454ad8408..ee5066718b21 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -137,6 +137,9 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
+	__set_memory((unsigned long) _sinittext,
+		     (_einittext - _sinittext) >> PAGE_SHIFT,
+		     SET_MEMORY_RW | SET_MEMORY_NX);
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
@@ -148,6 +151,15 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+unsigned long memory_block_size_bytes(void)
+{
+	/*
+	 * Make sure the memory block size is always greater
+	 * or equal than the memory increment size.
+	 */
+	return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
@@ -191,15 +203,6 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 	return rc;
 }
 
-unsigned long memory_block_size_bytes(void)
-{
-	/*
-	 * Make sure the memory block size is always greater
-	 * or equal than the memory increment size.
-	 */
-	return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
-}
-
 #ifdef CONFIG_MEMORY_HOTREMOVE
 int arch_remove_memory(u64 start, u64 size)
 {
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
index d612cc3eec6a..e58dca05b962 100644
--- a/arch/s390/mm/mem_detect.c
+++ b/arch/s390/mm/mem_detect.c
@@ -5,7 +5,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/debugfs.h>
@@ -19,6 +18,8 @@
 
 static inline void memblock_physmem_add(phys_addr_t start, phys_addr_t size)
 {
+	memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n",
+		     start, start + size - 1);
 	memblock_add_range(&memblock.memory, start, size, 0, 0);
 	memblock_add_range(&memblock.physmem, start, size, 0, 0);
 }
@@ -39,7 +40,8 @@ void __init detect_memory_memblock(void)
 	memblock_set_bottom_up(true);
 	do {
 		size = 0;
-		type = tprot(addr);
+		/* assume lowcore is writable */
+		type = addr ? tprot(addr) : CHUNK_READ_WRITE;
 		do {
 			size += rzm;
 			if (max_physmem_end && addr + size >= max_physmem_end)
@@ -55,4 +57,5 @@ void __init detect_memory_memblock(void)
 	memblock_set_bottom_up(false);
 	if (!max_physmem_end)
 		max_physmem_end = memblock_end_of_DRAM();
+	memblock_dump_all();
 }
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index eb9df2822da1..7ae1282d5be9 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -26,11 +26,11 @@
 #include <linux/personality.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/module.h>
 #include <linux/random.h>
 #include <linux/compat.h>
 #include <linux/security.h>
 #include <asm/pgalloc.h>
+#include <asm/elf.h>
 
 static unsigned long stack_maxrandom_size(void)
 {
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 44f150312a16..fc5dc33bb141 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -3,7 +3,6 @@
  * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
  */
 #include <linux/hugetlb.h>
-#include <linux/module.h>
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
 #include <asm/facility.h>
@@ -81,24 +80,24 @@ static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr,
 	}
 }
 
-struct cpa {
-	unsigned int set_ro	: 1;
-	unsigned int clear_ro	: 1;
-};
-
 static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
-			  struct cpa cpa)
+			  unsigned long flags)
 {
 	pte_t *ptep, new;
 
 	ptep = pte_offset(pmdp, addr);
 	do {
-		if (pte_none(*ptep))
+		new = *ptep;
+		if (pte_none(new))
 			return -EINVAL;
-		if (cpa.set_ro)
-			new = pte_wrprotect(*ptep);
-		else if (cpa.clear_ro)
-			new = pte_mkwrite(pte_mkdirty(*ptep));
+		if (flags & SET_MEMORY_RO)
+			new = pte_wrprotect(new);
+		else if (flags & SET_MEMORY_RW)
+			new = pte_mkwrite(pte_mkdirty(new));
+		if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+			pte_val(new) |= _PAGE_NOEXEC;
+		else if (flags & SET_MEMORY_X)
+			pte_val(new) &= ~_PAGE_NOEXEC;
 		pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE);
 		ptep++;
 		addr += PAGE_SIZE;
@@ -112,14 +111,17 @@ static int split_pmd_page(pmd_t *pmdp, unsigned long addr)
 	unsigned long pte_addr, prot;
 	pte_t *pt_dir, *ptep;
 	pmd_t new;
-	int i, ro;
+	int i, ro, nx;
 
 	pt_dir = vmem_pte_alloc();
 	if (!pt_dir)
 		return -ENOMEM;
 	pte_addr = pmd_pfn(*pmdp) << PAGE_SHIFT;
 	ro = !!(pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT);
+	nx = !!(pmd_val(*pmdp) & _SEGMENT_ENTRY_NOEXEC);
 	prot = pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
+	if (!nx)
+		prot &= ~_PAGE_NOEXEC;
 	ptep = pt_dir;
 	for (i = 0; i < PTRS_PER_PTE; i++) {
 		pte_val(*ptep) = pte_addr | prot;
@@ -133,19 +135,24 @@ static int split_pmd_page(pmd_t *pmdp, unsigned long addr)
 	return 0;
 }
 
-static void modify_pmd_page(pmd_t *pmdp, unsigned long addr, struct cpa cpa)
+static void modify_pmd_page(pmd_t *pmdp, unsigned long addr,
+			    unsigned long flags)
 {
-	pmd_t new;
-
-	if (cpa.set_ro)
-		new = pmd_wrprotect(*pmdp);
-	else if (cpa.clear_ro)
-		new = pmd_mkwrite(pmd_mkdirty(*pmdp));
+	pmd_t new = *pmdp;
+
+	if (flags & SET_MEMORY_RO)
+		new = pmd_wrprotect(new);
+	else if (flags & SET_MEMORY_RW)
+		new = pmd_mkwrite(pmd_mkdirty(new));
+	if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+		pmd_val(new) |= _SEGMENT_ENTRY_NOEXEC;
+	else if (flags & SET_MEMORY_X)
+		pmd_val(new) &= ~_SEGMENT_ENTRY_NOEXEC;
 	pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT);
 }
 
 static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
-			  struct cpa cpa)
+			  unsigned long flags)
 {
 	unsigned long next;
 	pmd_t *pmdp;
@@ -163,9 +170,9 @@ static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
 					return rc;
 				continue;
 			}
-			modify_pmd_page(pmdp, addr, cpa);
+			modify_pmd_page(pmdp, addr, flags);
 		} else {
-			rc = walk_pte_level(pmdp, addr, next, cpa);
+			rc = walk_pte_level(pmdp, addr, next, flags);
 			if (rc)
 				return rc;
 		}
@@ -181,14 +188,17 @@ static int split_pud_page(pud_t *pudp, unsigned long addr)
 	unsigned long pmd_addr, prot;
 	pmd_t *pm_dir, *pmdp;
 	pud_t new;
-	int i, ro;
+	int i, ro, nx;
 
 	pm_dir = vmem_pmd_alloc();
 	if (!pm_dir)
 		return -ENOMEM;
 	pmd_addr = pud_pfn(*pudp) << PAGE_SHIFT;
 	ro = !!(pud_val(*pudp) & _REGION_ENTRY_PROTECT);
+	nx = !!(pud_val(*pudp) & _REGION_ENTRY_NOEXEC);
 	prot = pgprot_val(ro ? SEGMENT_KERNEL_RO : SEGMENT_KERNEL);
+	if (!nx)
+		prot &= ~_SEGMENT_ENTRY_NOEXEC;
 	pmdp = pm_dir;
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		pmd_val(*pmdp) = pmd_addr | prot;
@@ -202,19 +212,24 @@ static int split_pud_page(pud_t *pudp, unsigned long addr)
 	return 0;
 }
 
-static void modify_pud_page(pud_t *pudp, unsigned long addr, struct cpa cpa)
+static void modify_pud_page(pud_t *pudp, unsigned long addr,
+			    unsigned long flags)
 {
-	pud_t new;
-
-	if (cpa.set_ro)
-		new = pud_wrprotect(*pudp);
-	else if (cpa.clear_ro)
-		new = pud_mkwrite(pud_mkdirty(*pudp));
+	pud_t new = *pudp;
+
+	if (flags & SET_MEMORY_RO)
+		new = pud_wrprotect(new);
+	else if (flags & SET_MEMORY_RW)
+		new = pud_mkwrite(pud_mkdirty(new));
+	if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+		pud_val(new) |= _REGION_ENTRY_NOEXEC;
+	else if (flags & SET_MEMORY_X)
+		pud_val(new) &= ~_REGION_ENTRY_NOEXEC;
 	pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
 }
 
 static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
-			  struct cpa cpa)
+			  unsigned long flags)
 {
 	unsigned long next;
 	pud_t *pudp;
@@ -232,9 +247,9 @@ static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
 					break;
 				continue;
 			}
-			modify_pud_page(pudp, addr, cpa);
+			modify_pud_page(pudp, addr, flags);
 		} else {
-			rc = walk_pmd_level(pudp, addr, next, cpa);
+			rc = walk_pmd_level(pudp, addr, next, flags);
 		}
 		pudp++;
 		addr = next;
@@ -246,7 +261,7 @@ static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
 static DEFINE_MUTEX(cpa_mutex);
 
 static int change_page_attr(unsigned long addr, unsigned long end,
-			    struct cpa cpa)
+			    unsigned long flags)
 {
 	unsigned long next;
 	int rc = -EINVAL;
@@ -262,7 +277,7 @@ static int change_page_attr(unsigned long addr, unsigned long end,
 		if (pgd_none(*pgdp))
 			break;
 		next = pgd_addr_end(addr, end);
-		rc = walk_pud_level(pgdp, addr, next, cpa);
+		rc = walk_pud_level(pgdp, addr, next, flags);
 		if (rc)
 			break;
 		cond_resched();
@@ -271,35 +286,10 @@ static int change_page_attr(unsigned long addr, unsigned long end,
 	return rc;
 }
 
-int set_memory_ro(unsigned long addr, int numpages)
+int __set_memory(unsigned long addr, int numpages, unsigned long flags)
 {
-	struct cpa cpa = {
-		.set_ro = 1,
-	};
-
 	addr &= PAGE_MASK;
-	return change_page_attr(addr, addr + numpages * PAGE_SIZE, cpa);
-}
-
-int set_memory_rw(unsigned long addr, int numpages)
-{
-	struct cpa cpa = {
-		.clear_ro = 1,
-	};
-
-	addr &= PAGE_MASK;
-	return change_page_attr(addr, addr + numpages * PAGE_SIZE, cpa);
-}
-
-/* not possible */
-int set_memory_nx(unsigned long addr, int numpages)
-{
-	return 0;
-}
-
-int set_memory_x(unsigned long addr, int numpages)
-{
-	return 0;
+	return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -339,7 +329,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 		nr = min(numpages - i, nr);
 		if (enable) {
 			for (j = 0; j < nr; j++) {
-				pte_val(*pte) = address | pgprot_val(PAGE_KERNEL);
+				pte_val(*pte) &= ~_PAGE_INVALID;
 				address += PAGE_SIZE;
 				pte++;
 			}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index d56ef26d4681..b48dc5f1900b 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -275,6 +275,8 @@ void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 
+	if (!MACHINE_HAS_NX)
+		pte_val(pte) &= ~_PAGE_NOEXEC;
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get(ptep);
 		pgste_set_key(ptep, pgste, pte, mm);
@@ -742,7 +744,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(ptep, ptl);
-	return 0;
+	return cc;
 }
 EXPORT_SYMBOL(reset_guest_reference_bit);
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 45becc8a44ec..60d38993f232 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -6,7 +6,7 @@
 #include <linux/bootmem.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/list.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
@@ -79,6 +79,7 @@ pte_t __ref *vmem_pte_alloc(void)
  */
 static int vmem_add_mem(unsigned long start, unsigned long size)
 {
+	unsigned long pgt_prot, sgt_prot, r3_prot;
 	unsigned long pages4k, pages1m, pages2g;
 	unsigned long end = start + size;
 	unsigned long address = start;
@@ -88,6 +89,14 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
 	pte_t *pt_dir;
 	int ret = -ENOMEM;
 
+	pgt_prot = pgprot_val(PAGE_KERNEL);
+	sgt_prot = pgprot_val(SEGMENT_KERNEL);
+	r3_prot = pgprot_val(REGION3_KERNEL);
+	if (!MACHINE_HAS_NX) {
+		pgt_prot &= ~_PAGE_NOEXEC;
+		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
+		r3_prot &= ~_REGION_ENTRY_NOEXEC;
+	}
 	pages4k = pages1m = pages2g = 0;
 	while (address < end) {
 		pg_dir = pgd_offset_k(address);
@@ -101,7 +110,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
 		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
 		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
 		     !debug_pagealloc_enabled()) {
-			pud_val(*pu_dir) = address | pgprot_val(REGION3_KERNEL);
+			pud_val(*pu_dir) = address | r3_prot;
 			address += PUD_SIZE;
 			pages2g++;
 			continue;
@@ -116,7 +125,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
 		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
 		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
 		    !debug_pagealloc_enabled()) {
-			pmd_val(*pm_dir) = address | pgprot_val(SEGMENT_KERNEL);
+			pmd_val(*pm_dir) = address | sgt_prot;
 			address += PMD_SIZE;
 			pages1m++;
 			continue;
@@ -129,7 +138,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
-		pte_val(*pt_dir) = address |  pgprot_val(PAGE_KERNEL);
+		pte_val(*pt_dir) = address | pgt_prot;
 		address += PAGE_SIZE;
 		pages4k++;
 	}
@@ -200,6 +209,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
  */
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
+	unsigned long pgt_prot, sgt_prot;
 	unsigned long address = start;
 	pgd_t *pg_dir;
 	pud_t *pu_dir;
@@ -207,6 +217,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	pte_t *pt_dir;
 	int ret = -ENOMEM;
 
+	pgt_prot = pgprot_val(PAGE_KERNEL);
+	sgt_prot = pgprot_val(SEGMENT_KERNEL);
+	if (!MACHINE_HAS_NX) {
+		pgt_prot &= ~_PAGE_NOEXEC;
+		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
+	}
 	for (address = start; address < end;) {
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
@@ -238,8 +254,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 				new_page = vmemmap_alloc_block(PMD_SIZE, node);
 				if (!new_page)
 					goto out;
-				pmd_val(*pm_dir) = __pa(new_page) |
-					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE;
+				pmd_val(*pm_dir) = __pa(new_page) | sgt_prot;
 				address = (address + PMD_SIZE) & PMD_MASK;
 				continue;
 			}
@@ -259,8 +274,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 			new_page = vmemmap_alloc_block(PAGE_SIZE, node);
 			if (!new_page)
 				goto out;
-			pte_val(*pt_dir) =
-				__pa(new_page) | pgprot_val(PAGE_KERNEL);
+			pte_val(*pt_dir) = __pa(new_page) | pgt_prot;
 		}
 		address += PAGE_SIZE;
 	}
@@ -372,13 +386,21 @@ out:
  */
 void __init vmem_map_init(void)
 {
-	unsigned long size = _eshared - _stext;
 	struct memblock_region *reg;
 
 	for_each_memblock(memory, reg)
 		vmem_add_mem(reg->base, reg->size);
-	set_memory_ro((unsigned long)_stext, size >> PAGE_SHIFT);
-	pr_info("Write protected kernel read-only data: %luk\n", size >> 10);
+	__set_memory((unsigned long) _stext,
+		     (_etext - _stext) >> PAGE_SHIFT,
+		     SET_MEMORY_RO | SET_MEMORY_X);
+	__set_memory((unsigned long) _etext,
+		     (_eshared - _etext) >> PAGE_SHIFT,
+		     SET_MEMORY_RO);
+	__set_memory((unsigned long) _sinittext,
+		     (_einittext - _sinittext) >> PAGE_SHIFT,
+		     SET_MEMORY_RO | SET_MEMORY_X);
+	pr_info("Write protected kernel read-only data: %luk\n",
+		(_eshared - _stext) >> 10);
 }
 
 /*
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 167b31b186c1..4ecf6d687509 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1263,14 +1263,6 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 }
 
 /*
- * Classic BPF function stub. BPF programs will be converted into
- * eBPF and then bpf_int_jit_compile() will be called.
- */
-void bpf_jit_compile(struct bpf_prog *fp)
-{
-}
-
-/*
  * Compile eBPF program "fp"
  */
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
@@ -1331,14 +1323,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 	if (bpf_jit_enable > 1) {
 		bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf);
-		if (jit.prg_buf)
-			print_fn_code(jit.prg_buf, jit.size_prg);
-	}
-	if (jit.prg_buf) {
-		set_memory_ro((unsigned long)header, header->pages);
-		fp->bpf_func = (void *) jit.prg_buf;
-		fp->jited = 1;
+		print_fn_code(jit.prg_buf, jit.size_prg);
 	}
+	bpf_jit_binary_lock_ro(header);
+	fp->bpf_func = (void *) jit.prg_buf;
+	fp->jited = 1;
 free_addrs:
 	kfree(jit.addrs);
 out:
@@ -1347,21 +1336,3 @@ out:
 					   tmp : orig_fp);
 	return fp;
 }
-
-/*
- * Free eBPF program
- */
-void bpf_jit_free(struct bpf_prog *fp)
-{
-	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
-	struct bpf_binary_header *header = (void *)addr;
-
-	if (!fp->jited)
-		goto free_filter;
-
-	set_memory_rw(addr, header->pages);
-	bpf_jit_binary_free(header);
-
-free_filter:
-	bpf_prog_unlock_free(fp);
-}
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 38e17d4d9884..364b9d824be3 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -224,8 +224,8 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 
 	rc = zpci_load(&data, req, offset);
 	if (!rc) {
-		data = data << ((8 - len) * 8);
-		data = le64_to_cpu(data);
+		data = le64_to_cpu((__force __le64) data);
+		data >>= (8 - len) * 8;
 		*val = (u32) data;
 	} else
 		*val = 0xffffffff;
@@ -238,8 +238,8 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	u64 data = val;
 	int rc;
 
-	data = cpu_to_le64(data);
-	data = data >> ((8 - len) * 8);
+	data <<= (8 - len) * 8;
+	data = (__force u64) cpu_to_le64(data);
 	rc = zpci_store(data, req, offset);
 	return rc;
 }
@@ -641,7 +641,7 @@ int pcibios_add_device(struct pci_dev *pdev)
 	int i;
 
 	pdev->dev.groups = zpci_attr_groups;
-	pdev->dev.archdata.dma_ops = &s390_pci_dma_ops;
+	pdev->dev.dma_ops = &s390_pci_dma_ops;
 	zpci_map_resources(pdev);
 
 	for (i = 0; i < PCI_BAR_COUNT; i++) {
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 1d7a9c71944a..9081a57fa340 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -650,7 +650,7 @@ static int __init dma_debug_do_init(void)
 }
 fs_initcall(dma_debug_do_init);
 
-struct dma_map_ops s390_pci_dma_ops = {
+const struct dma_map_ops s390_pci_dma_ops = {
 	.alloc		= s390_dma_alloc,
 	.free		= s390_dma_free,
 	.map_sg		= s390_dma_map_sg,
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 8cc53b1e6d03..0cf802de52a1 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -80,6 +80,8 @@ static struct facility_def facility_defs[] = {
 			76, /* msa extension 3 */
 			77, /* msa extension 4 */
 			78, /* enhanced-DAT 2 */
+			130, /* instruction-execution-protection */
+			131, /* enhanced-SOP 2 and side-effect */
 			-1  /* END */
 		}
 	},
author	Ingo Molnar <mingo@kernel.org>	2017-03-01 11:02:26 +0300
committer	Ingo Molnar <mingo@kernel.org>	2017-03-01 11:02:26 +0300
commit	0871d5a66da5c41151e0896a90298b163e42f2e0 (patch)
tree	1ba71fab9016cb28bb9d18ffd62b6b744f2f761c /arch/s390
parent	e22af0be2cf654bb225f19750c6b9aab1627dc9e (diff)
parent	2d6be4abf514fc26c83d239c7f31da1f95e4a31d (diff)
download	linux-0871d5a66da5c41151e0896a90298b163e42f2e0.tar.xz