Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:
 "The main bulk of the s390 patches for the 4.10 merge window:

   - Add support for the contiguous memory allocator.

   - The recovery for I/O errors in the dasd device driver is improved,
     the driver will now remove channel paths that are not working
     properly.

   - Additional fields are added to /proc/sysinfo, the extended
     partition name and the partition UUID.

   - New naming for PCI devices with system defined UIDs.

   - The last few remaining alloc_bootmem calls are converted to
     memblock.

   - The thread_info structure is stripped down and moved to the
     task_struct. The only field left in thread_info is the flags field.

   - Rework of the arch topology code to fix a fake numa issue.

   - Refactoring of the atomic primitives and add a new preempt_count
     implementation.

   - Clocksource steering for the STP sync check offsets.

   - The s390 specific headers are changed to make them usable with
     CLANG.

   - Bug fixes and cleanup"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (70 commits)
  s390/cpumf: Use configuration level indication for sampling data
  s390: provide memmove implementation
  s390: cleanup arch/s390/kernel Makefile
  s390: fix initrd corruptions with gcov/kcov instrumented kernels
  s390: exclude early C code from gcov profiling
  s390/dasd: channel path aware error recovery
  s390/dasd: extend dasd path handling
  s390: remove unused labels from entry.S
  s390/vmlogrdr: fix IUCV buffer allocation
  s390/crypto: unlock on error in prng_tdes_read()
  s390/sysinfo: show partition extended name and UUID if available
  s390/numa: pin all possible cpus to nodes early
  s390/numa: establish cpu to node mapping early
  s390/topology: use cpu_topology array instead of per cpu variable
  s390/smp: initialize cpu_present_mask in setup_arch
  s390/topology: always use s390 specific sched_domain_topology_level
  s390/smp: use smp_get_base_cpu() helper function
  s390/numa: always use logical cpu and core ids
  s390: Remove VLAIS in ptff() and clear_table()
  s390: fix machine check panic stack switch
  ...

68 files changed, 1069 insertions, 745 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 028f97be5bae..c6722112527d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -136,6 +136,7 @@ config S390
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -169,6 +170,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_HAS_SCALED_CPUTIME
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index 28c4f96a2d9c..11f6254c561e 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -46,7 +46,7 @@ mover_end:
 
 	.align	8
 .Lstack:
-	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
+	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
 .Loffset:
 	.quad	0x11000
 .Lmvsize:
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 45968686f918..e659daffe368 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -66,6 +66,8 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
 CONFIG_CMA=y
+CONFIG_CMA_DEBUG=y
+CONFIG_CMA_DEBUGFS=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZPOOL=m
 CONFIG_ZBUD=m
@@ -366,6 +368,8 @@ CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 CONFIG_NET_TCPPROBE=m
 CONFIG_DEVTMPFS=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -438,7 +442,6 @@ CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
 CONFIG_NLMON=m
-CONFIG_VHOST_NET=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -693,3 +696,4 @@ CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
+CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 1dd05e345c4d..95ceac50bc65 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -362,6 +362,8 @@ CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 CONFIG_NET_TCPPROBE=m
 CONFIG_DEVTMPFS=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -434,7 +436,6 @@ CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
 CONFIG_NLMON=m
-CONFIG_VHOST_NET=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -633,3 +634,4 @@ CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
+CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 29d1178666f0..bc7b176f5795 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -362,6 +362,8 @@ CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 CONFIG_NET_TCPPROBE=m
 CONFIG_DEVTMPFS=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -434,7 +436,6 @@ CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
 CONFIG_NLMON=m
-CONFIG_VHOST_NET=m
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -632,3 +633,4 @@ CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
+CONFIG_VHOST_NET=m
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 9cc050f9536c..1113389d0a39 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -507,8 +507,10 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf,
 		prng_data->prngws.byte_counter += n;
 		prng_data->prngws.reseed_counter += n;
 
-		if (copy_to_user(ubuf, prng_data->buf, chunk))
-			return -EFAULT;
+		if (copy_to_user(ubuf, prng_data->buf, chunk)) {
+			ret = -EFAULT;
+			break;
+		}
 
 		nbytes -= chunk;
 		ret += chunk;
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 09bccb224d03..cf8a2d92467f 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -3,6 +3,7 @@
  *
  *    Copyright IBM Corp. 2006, 2008
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ *    License: GPL
  */
 
 #define KMSG_COMPONENT "hypfs"
@@ -18,7 +19,8 @@
 #include <linux/time.h>
 #include <linux/parser.h>
 #include <linux/sysfs.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/uio.h>
@@ -443,7 +445,6 @@ static struct file_system_type hypfs_type = {
 	.mount		= hypfs_mount,
 	.kill_sb	= hypfs_kill_super
 };
-MODULE_ALIAS_FS("s390_hypfs");
 
 static const struct super_operations hypfs_s_ops = {
 	.statfs		= simple_statfs,
@@ -497,21 +498,4 @@ fail_dbfs_exit:
 	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
-
-static void __exit hypfs_exit(void)
-{
-	unregister_filesystem(&hypfs_type);
-	sysfs_remove_mount_point(hypervisor_kobj, "s390");
-	hypfs_diag0c_exit();
-	hypfs_sprp_exit();
-	hypfs_vm_exit();
-	hypfs_diag_exit();
-	hypfs_dbfs_exit();
-}
-
-module_init(hypfs_init)
-module_exit(hypfs_exit)
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Michael Holzheu <holzheu@de.ibm.com>");
-MODULE_DESCRIPTION("s390 Hypervisor Filesystem");
+device_initcall(hypfs_init)
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 20f196b82a6e..8aea32fe8bd2 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,6 +1,6 @@
-
-
+generic-y += asm-offsets.h
 generic-y += clkdev.h
+generic-y += dma-contiguous.h
 generic-y += export.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
diff --git a/arch/s390/include/asm/asm-offsets.h b/arch/s390/include/asm/asm-offsets.h
deleted file mode 100644
index d370ee36a182..000000000000
--- a/arch/s390/include/asm/asm-offsets.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <generated/asm-offsets.h>
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index d28cc2f5b7b2..f7f69dfd2db2 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -1,13 +1,8 @@
 /*
- * Copyright IBM Corp. 1999, 2009
+ * Copyright IBM Corp. 1999, 2016
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
  *	      Denis Joseph Barrow,
- *	      Arnd Bergmann <arndb@de.ibm.com>,
- *
- * Atomic operations that C can't guarantee us.
- * Useful for resource counting etc.
- * s390 uses 'Compare And Swap' for atomicity in SMP environment.
- *
+ *	      Arnd Bergmann,
  */
 
 #ifndef __ARCH_S390_ATOMIC__
@@ -15,62 +10,12 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <asm/atomic_ops.h>
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define __ATOMIC_NO_BARRIER	"\n"
-
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-
-#define __ATOMIC_OR	"lao"
-#define __ATOMIC_AND	"lan"
-#define __ATOMIC_ADD	"laa"
-#define __ATOMIC_XOR	"lax"
-#define __ATOMIC_BARRIER "bcr	14,0\n"
-
-#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
-({									\
-	int old_val;							\
-									\
-	typecheck(atomic_t *, ptr);					\
-	asm volatile(							\
-		op_string "	%0,%2,%1\n"				\
-		__barrier						\
-		: "=d" (old_val), "+Q" ((ptr)->counter)			\
-		: "d" (op_val)						\
-		: "cc", "memory");					\
-	old_val;							\
-})
-
-#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
-#define __ATOMIC_OR	"or"
-#define __ATOMIC_AND	"nr"
-#define __ATOMIC_ADD	"ar"
-#define __ATOMIC_XOR	"xr"
-#define __ATOMIC_BARRIER "\n"
-
-#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
-({									\
-	int old_val, new_val;						\
-									\
-	typecheck(atomic_t *, ptr);					\
-	asm volatile(							\
-		"	l	%0,%2\n"				\
-		"0:	lr	%1,%0\n"				\
-		op_string "	%1,%3\n"				\
-		"	cs	%0,%1,%2\n"				\
-		"	jl	0b"					\
-		: "=&d" (old_val), "=&d" (new_val), "+Q" ((ptr)->counter)\
-		: "d" (op_val)						\
-		: "cc", "memory");					\
-	old_val;							\
-})
-
-#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
 static inline int atomic_read(const atomic_t *v)
 {
 	int c;
@@ -90,27 +35,23 @@ static inline void atomic_set(atomic_t *v, int i)
 
 static inline int atomic_add_return(int i, atomic_t *v)
 {
-	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
+	return __atomic_add_barrier(i, &v->counter) + i;
 }
 
 static inline int atomic_fetch_add(int i, atomic_t *v)
 {
-	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER);
+	return __atomic_add_barrier(i, &v->counter);
 }
 
 static inline void atomic_add(int i, atomic_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
-		asm volatile(
-			"asi	%0,%1\n"
-			: "+Q" (v->counter)
-			: "i" (i)
-			: "cc", "memory");
+		__atomic_add_const(i, &v->counter);
 		return;
 	}
 #endif
-	__ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER);
+	__atomic_add(i, &v->counter);
 }
 
 #define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
@@ -125,19 +66,19 @@ static inline void atomic_add(int i, atomic_t *v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-#define ATOMIC_OPS(op, OP)						\
+#define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
+	__atomic_##op(i, &v->counter);					\
 }									\
 static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 {									\
-	return __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_BARRIER);	\
+	return __atomic_##op##_barrier(i, &v->counter);			\
 }
 
-ATOMIC_OPS(and, AND)
-ATOMIC_OPS(or, OR)
-ATOMIC_OPS(xor, XOR)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
 
@@ -145,12 +86,7 @@ ATOMIC_OPS(xor, XOR)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-	asm volatile(
-		"	cs	%0,%2,%1"
-		: "+d" (old), "+Q" (v->counter)
-		: "d" (new)
-		: "cc", "memory");
-	return old;
+	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
@@ -168,65 +104,11 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-#undef __ATOMIC_LOOP
-
 #define ATOMIC64_INIT(i)  { (i) }
 
-#define __ATOMIC64_NO_BARRIER	"\n"
-
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-
-#define __ATOMIC64_OR	"laog"
-#define __ATOMIC64_AND	"lang"
-#define __ATOMIC64_ADD	"laag"
-#define __ATOMIC64_XOR	"laxg"
-#define __ATOMIC64_BARRIER "bcr	14,0\n"
-
-#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
-({									\
-	long long old_val;						\
-									\
-	typecheck(atomic64_t *, ptr);					\
-	asm volatile(							\
-		op_string "	%0,%2,%1\n"				\
-		__barrier						\
-		: "=d" (old_val), "+Q" ((ptr)->counter)			\
-		: "d" (op_val)						\
-		: "cc", "memory");					\
-	old_val;							\
-})
-
-#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
-#define __ATOMIC64_OR	"ogr"
-#define __ATOMIC64_AND	"ngr"
-#define __ATOMIC64_ADD	"agr"
-#define __ATOMIC64_XOR	"xgr"
-#define __ATOMIC64_BARRIER "\n"
-
-#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
-({									\
-	long long old_val, new_val;					\
-									\
-	typecheck(atomic64_t *, ptr);					\
-	asm volatile(							\
-		"	lg	%0,%2\n"				\
-		"0:	lgr	%1,%0\n"				\
-		op_string "	%1,%3\n"				\
-		"	csg	%0,%1,%2\n"				\
-		"	jl	0b"					\
-		: "=&d" (old_val), "=&d" (new_val), "+Q" ((ptr)->counter)\
-		: "d" (op_val)						\
-		: "cc", "memory");					\
-	old_val;							\
-})
-
-#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
-static inline long long atomic64_read(const atomic64_t *v)
+static inline long atomic64_read(const atomic64_t *v)
 {
-	long long c;
+	long c;
 
 	asm volatile(
 		"	lg	%0,%1\n"
@@ -234,71 +116,60 @@ static inline long long atomic64_read(const atomic64_t *v)
 	return c;
 }
 
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void atomic64_set(atomic64_t *v, long i)
 {
 	asm volatile(
 		"	stg	%1,%0\n"
 		: "=Q" (v->counter) : "d" (i));
 }
 
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
+static inline long atomic64_add_return(long i, atomic64_t *v)
 {
-	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
+	return __atomic64_add_barrier(i, &v->counter) + i;
 }
 
-static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+static inline long atomic64_fetch_add(long i, atomic64_t *v)
 {
-	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER);
+	return __atomic64_add_barrier(i, &v->counter);
 }
 
-static inline void atomic64_add(long long i, atomic64_t *v)
+static inline void atomic64_add(long i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
-		asm volatile(
-			"agsi	%0,%1\n"
-			: "+Q" (v->counter)
-			: "i" (i)
-			: "cc", "memory");
+		__atomic64_add_const(i, &v->counter);
 		return;
 	}
 #endif
-	__ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
+	__atomic64_add(i, &v->counter);
 }
 
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long long atomic64_cmpxchg(atomic64_t *v,
-					     long long old, long long new)
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
-	asm volatile(
-		"	csg	%0,%2,%1"
-		: "+d" (old), "+Q" (v->counter)
-		: "d" (new)
-		: "cc", "memory");
-	return old;
+	return __atomic64_cmpxchg(&v->counter, old, new);
 }
 
-#define ATOMIC64_OPS(op, OP)						\
+#define ATOMIC64_OPS(op)						\
 static inline void atomic64_##op(long i, atomic64_t *v)			\
 {									\
-	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+	__atomic64_##op(i, &v->counter);				\
 }									\
 static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
 {									\
-	return __ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_BARRIER); \
+	return __atomic64_##op##_barrier(i, &v->counter);		\
 }
 
-ATOMIC64_OPS(and, AND)
-ATOMIC64_OPS(or, OR)
-ATOMIC64_OPS(xor, XOR)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
-#undef __ATOMIC64_LOOP
 
-static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
 {
-	long long c, old;
+	long c, old;
 
 	c = atomic64_read(v);
 	for (;;) {
@@ -312,9 +183,9 @@ static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
 	return c != u;
 }
 
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long c, old, dec;
+	long c, old, dec;
 
 	c = atomic64_read(v);
 	for (;;) {
@@ -333,9 +204,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_inc(_v)		atomic64_add(1, _v)
 #define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
 #define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
-#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long long)(_i), _v)
-#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long long)(_i), _v)
-#define atomic64_sub(_i, _v)		atomic64_add(-(long long)(_i), _v)
+#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
+#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
+#define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
 #define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
 #define atomic64_dec(_v)		atomic64_sub(1, _v)
 #define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
new file mode 100644
index 000000000000..ac9e2b939d04
--- /dev/null
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -0,0 +1,130 @@
+/*
+ * Low level function for atomic operations
+ *
+ * Copyright IBM Corp. 1999, 2016
+ */
+
+#ifndef __ARCH_S390_ATOMIC_OPS__
+#define __ARCH_S390_ATOMIC_OPS__
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+#define __ATOMIC_OP(op_name, op_type, op_string, op_barrier)		\
+static inline op_type op_name(op_type val, op_type *ptr)		\
+{									\
+	op_type old;							\
+									\
+	asm volatile(							\
+		op_string "	%[old],%[val],%[ptr]\n"			\
+		op_barrier						\
+		: [old] "=d" (old), [ptr] "+Q" (*ptr)			\
+		: [val] "d" (val) : "cc", "memory");			\
+	return old;							\
+}									\
+
+#define __ATOMIC_OPS(op_name, op_type, op_string)			\
+	__ATOMIC_OP(op_name, op_type, op_string, "\n")			\
+	__ATOMIC_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
+
+__ATOMIC_OPS(__atomic_add, int, "laa")
+__ATOMIC_OPS(__atomic_and, int, "lan")
+__ATOMIC_OPS(__atomic_or,  int, "lao")
+__ATOMIC_OPS(__atomic_xor, int, "lax")
+
+__ATOMIC_OPS(__atomic64_add, long, "laag")
+__ATOMIC_OPS(__atomic64_and, long, "lang")
+__ATOMIC_OPS(__atomic64_or,  long, "laog")
+__ATOMIC_OPS(__atomic64_xor, long, "laxg")
+
+#undef __ATOMIC_OPS
+#undef __ATOMIC_OP
+
+static inline void __atomic_add_const(int val, int *ptr)
+{
+	asm volatile(
+		"	asi	%[ptr],%[val]\n"
+		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
+}
+
+static inline void __atomic64_add_const(long val, long *ptr)
+{
+	asm volatile(
+		"	agsi	%[ptr],%[val]\n"
+		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
+}
+
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+#define __ATOMIC_OP(op_name, op_string)					\
+static inline int op_name(int val, int *ptr)				\
+{									\
+	int old, new;							\
+									\
+	asm volatile(							\
+		"0:	lr	%[new],%[old]\n"			\
+		op_string "	%[new],%[val]\n"			\
+		"	cs	%[old],%[new],%[ptr]\n"			\
+		"	jl	0b"					\
+		: [old] "=d" (old), [new] "=&d" (new), [ptr] "+Q" (*ptr)\
+		: [val] "d" (val), "0" (*ptr) : "cc", "memory");	\
+	return old;							\
+}
+
+#define __ATOMIC_OPS(op_name, op_string)				\
+	__ATOMIC_OP(op_name, op_string)					\
+	__ATOMIC_OP(op_name##_barrier, op_string)
+
+__ATOMIC_OPS(__atomic_add, "ar")
+__ATOMIC_OPS(__atomic_and, "nr")
+__ATOMIC_OPS(__atomic_or,  "or")
+__ATOMIC_OPS(__atomic_xor, "xr")
+
+#undef __ATOMIC_OPS
+
+#define __ATOMIC64_OP(op_name, op_string)				\
+static inline long op_name(long val, long *ptr)				\
+{									\
+	long old, new;							\
+									\
+	asm volatile(							\
+		"0:	lgr	%[new],%[old]\n"			\
+		op_string "	%[new],%[val]\n"			\
+		"	csg	%[old],%[new],%[ptr]\n"			\
+		"	jl	0b"					\
+		: [old] "=d" (old), [new] "=&d" (new), [ptr] "+Q" (*ptr)\
+		: [val] "d" (val), "0" (*ptr) : "cc", "memory");	\
+	return old;							\
+}
+
+#define __ATOMIC64_OPS(op_name, op_string)				\
+	__ATOMIC64_OP(op_name, op_string)				\
+	__ATOMIC64_OP(op_name##_barrier, op_string)
+
+__ATOMIC64_OPS(__atomic64_add, "agr")
+__ATOMIC64_OPS(__atomic64_and, "ngr")
+__ATOMIC64_OPS(__atomic64_or,  "ogr")
+__ATOMIC64_OPS(__atomic64_xor, "xgr")
+
+#undef __ATOMIC64_OPS
+
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+static inline int __atomic_cmpxchg(int *ptr, int old, int new)
+{
+	asm volatile(
+		"	cs	%[old],%[new],%[ptr]"
+		: [old] "+d" (old), [ptr] "+Q" (*ptr)
+		: [new] "d" (new) : "cc", "memory");
+	return old;
+}
+
+static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
+{
+	asm volatile(
+		"	csg	%[old],%[new],%[ptr]"
+		: [old] "+d" (old), [ptr] "+Q" (*ptr)
+		: [new] "d" (new) : "cc", "memory");
+	return old;
+}
+
+#endif /* __ARCH_S390_ATOMIC_OPS__  */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 8043f10da6b5..d92047da5ccb 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -42,57 +42,9 @@
 
 #include <linux/typecheck.h>
 #include <linux/compiler.h>
+#include <asm/atomic_ops.h>
 #include <asm/barrier.h>
 
-#define __BITOPS_NO_BARRIER	"\n"
-
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-
-#define __BITOPS_OR		"laog"
-#define __BITOPS_AND		"lang"
-#define __BITOPS_XOR		"laxg"
-#define __BITOPS_BARRIER	"bcr	14,0\n"
-
-#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier)	\
-({								\
-	unsigned long __old;					\
-								\
-	typecheck(unsigned long *, (__addr));			\
-	asm volatile(						\
-		__op_string "	%0,%2,%1\n"			\
-		__barrier					\
-		: "=d" (__old),	"+Q" (*(__addr))		\
-		: "d" (__val)					\
-		: "cc", "memory");				\
-	__old;							\
-})
-
-#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
-#define __BITOPS_OR		"ogr"
-#define __BITOPS_AND		"ngr"
-#define __BITOPS_XOR		"xgr"
-#define __BITOPS_BARRIER	"\n"
-
-#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier)	\
-({								\
-	unsigned long __old, __new;				\
-								\
-	typecheck(unsigned long *, (__addr));			\
-	asm volatile(						\
-		"	lg	%0,%2\n"			\
-		"0:	lgr	%1,%0\n"			\
-		__op_string "	%1,%3\n"			\
-		"	csg	%0,%1,%2\n"			\
-		"	jl	0b"				\
-		: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
-		: "d" (__val)					\
-		: "cc", "memory");				\
-	__old;							\
-})
-
-#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
 #define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG)
 
 static inline unsigned long *
@@ -128,7 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER);
+	__atomic64_or(mask, addr);
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -149,7 +101,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	__BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER);
+	__atomic64_and(mask, addr);
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -170,7 +122,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER);
+	__atomic64_xor(mask, addr);
 }
 
 static inline int
@@ -180,7 +132,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER);
+	old = __atomic64_or_barrier(mask, addr);
 	return (old & mask) != 0;
 }
 
@@ -191,7 +143,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER);
+	old = __atomic64_and_barrier(mask, addr);
 	return (old & ~mask) != 0;
 }
 
@@ -202,7 +154,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER);
+	old = __atomic64_xor_barrier(mask, addr);
 	return (old & mask) != 0;
 }
 
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 03516476127b..b69d8bc231a5 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -104,7 +104,8 @@ struct hws_basic_entry {
 	unsigned int P:1;	    /* 28 PSW Problem state		 */
 	unsigned int AS:2;	    /* 29-30 PSW address-space control	 */
 	unsigned int I:1;	    /* 31 entry valid or invalid	 */
-	unsigned int:16;
+	unsigned int CL:2;	    /* 32-33 Configuration Level	 */
+	unsigned int:14;
 	unsigned int prim_asn:16;   /* primary ASN			 */
 	unsigned long long ia;	    /* Instruction Address		 */
 	unsigned long long gpp;     /* Guest Program Parameter		 */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1736c7d3c94c..f4381e1fb19e 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -193,7 +193,7 @@ extern char elf_platform[];
 do {								\
 	set_personality(PER_LINUX |				\
 		(current->personality & (~PER_MASK)));		\
-	current_thread_info()->sys_call_table = 		\
+	current->thread.sys_call_table =			\
 		(unsigned long) &sys_call_table;		\
 } while (0)
 #else /* CONFIG_COMPAT */
@@ -204,11 +204,11 @@ do {								\
 			(current->personality & ~PER_MASK));	\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32) {		\
 		set_thread_flag(TIF_31BIT);			\
-		current_thread_info()->sys_call_table =		\
+		current->thread.sys_call_table =		\
 			(unsigned long)	&sys_call_table_emu;	\
 	} else {						\
 		clear_thread_flag(TIF_31BIT);			\
-		current_thread_info()->sys_call_table =		\
+		current->thread.sys_call_table =		\
 			(unsigned long) &sys_call_table;	\
 	}							\
 } while (0)
diff --git a/arch/s390/include/asm/facilities_src.h b/arch/s390/include/asm/facilities_src.h
deleted file mode 100644
index 3b758f66e48b..000000000000
--- a/arch/s390/include/asm/facilities_src.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- *    Copyright IBM Corp. 2015
- */
-
-#ifndef S390_GEN_FACILITIES_C
-#error "This file can only be included by gen_facilities.c"
-#endif
-
-#include <linux/kconfig.h>
-
-struct facility_def {
-	char *name;
-	int *bits;
-};
-
-static struct facility_def facility_defs[] = {
-	{
-		/*
-		 * FACILITIES_ALS contains the list of facilities that are
-		 * required to run a kernel that is compiled e.g. with
-		 * -march=<machine>.
-		 */
-		.name = "FACILITIES_ALS",
-		.bits = (int[]){
-#ifdef CONFIG_HAVE_MARCH_Z900_FEATURES
-			0,  /* N3 instructions */
-			1,  /* z/Arch mode installed */
-#endif
-#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
-			18, /* long displacement facility */
-#endif
-#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
-			7,  /* stfle */
-			17, /* message security assist */
-			21, /* extended-immediate facility */
-			25, /* store clock fast */
-#endif
-#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
-			27, /* mvcos */
-			32, /* compare and swap and store */
-			33, /* compare and swap and store 2 */
-			34, /* general extension facility */
-			35, /* execute extensions */
-#endif
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-			45, /* fast-BCR, etc. */
-#endif
-#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
-			49, /* misc-instruction-extensions */
-			52, /* interlocked facility 2 */
-#endif
-#ifdef CONFIG_HAVE_MARCH_Z13_FEATURES
-			53, /* load-and-zero-rightmost-byte, etc. */
-#endif
-			-1 /* END */
-		}
-	},
-	{
-		.name = "FACILITIES_KVM",
-		.bits = (int[]){
-			0,  /* N3 instructions */
-			1,  /* z/Arch mode installed */
-			2,  /* z/Arch mode active */
-			3,  /* DAT-enhancement */
-			4,  /* idte segment table */
-			5,  /* idte region table */
-			6,  /* ASN-and-LX reuse */
-			7,  /* stfle */
-			8,  /* enhanced-DAT 1 */
-			9,  /* sense-running-status */
-			10, /* conditional sske */
-			13, /* ipte-range */
-			14, /* nonquiescing key-setting */
-			73, /* transactional execution */
-			75, /* access-exception-fetch/store indication */
-			76, /* msa extension 3 */
-			77, /* msa extension 4 */
-			78, /* enhanced-DAT 2 */
-			-1  /* END */
-		}
-	},
-};
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 4da22b2f0521..edb5161df7e2 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -97,7 +97,7 @@ void __init save_area_add_vxrs(struct save_area *, __vector128 *vxrs);
 extern void do_reipl(void);
 extern void do_halt(void);
 extern void do_poff(void);
-extern void ipl_save_parameters(void);
+extern void ipl_verify_parameters(void);
 extern void ipl_update_parameters(void);
 extern size_t append_ipl_vmparm(char *, size_t);
 extern size_t append_ipl_scpdata(char *, size_t);
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 7b93b78f423c..9bfad2ad6312 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -95,7 +95,7 @@ struct lowcore {
 
 	/* Current process. */
 	__u64	current_task;			/* 0x0310 */
-	__u64	thread_info;			/* 0x0318 */
+	__u8	pad_0x318[0x320-0x318];		/* 0x0318 */
 	__u64	kernel_stack;			/* 0x0320 */
 
 	/* Interrupt, panic and restart stack. */
@@ -126,7 +126,8 @@ struct lowcore {
 	__u64	percpu_offset;			/* 0x0378 */
 	__u64	vdso_per_cpu_data;		/* 0x0380 */
 	__u64	machine_flags;			/* 0x0388 */
-	__u8	pad_0x0390[0x0398-0x0390];	/* 0x0390 */
+	__u32	preempt_count;			/* 0x0390 */
+	__u8	pad_0x0394[0x0398-0x0394];	/* 0x0394 */
 	__u64	gmap;				/* 0x0398 */
 	__u32	spinlock_lockval;		/* 0x03a0 */
 	__u32	fpu_flags;			/* 0x03a4 */
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index e75c64cbcf08..c232ef9711f5 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -46,6 +46,8 @@ struct clp_fh_list_entry {
 #define CLP_UTIL_STR_LEN	64
 #define CLP_PFIP_NR_SEGMENTS	4
 
+extern bool zpci_unique_uid;
+
 /* List PCI functions request */
 struct clp_req_list_pci {
 	struct clp_req_hdr hdr;
@@ -59,7 +61,8 @@ struct clp_rsp_list_pci {
 	u64 resume_token;
 	u32 reserved2;
 	u16 max_fn;
-	u8 reserved3;
+	u8			: 7;
+	u8 uid_checking		: 1;
 	u8 entry_size;
 	struct clp_fh_list_entry fh_list[CLP_FH_LIST_NR_ENTRIES];
 } __packed;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f4eb9843eed4..166f703dad7c 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -27,17 +27,17 @@ extern int page_table_allocate_pgste;
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
-	typedef struct { char _[n]; } addrtype;
-
-	*s = val;
-	n = (n / 256) - 1;
-	asm volatile(
-		"	mvc	8(248,%0),0(%0)\n"
-		"0:	mvc	256(256,%0),0(%0)\n"
-		"	la	%0,256(%0)\n"
-		"	brct	%1,0b\n"
-		: "+a" (s), "+d" (n), "=m" (*(addrtype *) s)
-		: "m" (*(addrtype *) s));
+	struct addrtype { char _[256]; };
+	int i;
+
+	for (i = 0; i < n; i += 256) {
+		*s = val;
+		asm volatile(
+			"mvc	8(248,%[s]),0(%[s])\n"
+			: "+m" (*(struct addrtype *) s)
+			: [s] "a" (s));
+		s += 256 / sizeof(long);
+	}
 }
 
 static inline void crst_table_init(unsigned long *crst, unsigned long entry)
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
new file mode 100644
index 000000000000..b0776b2c8dcf
--- /dev/null
+++ b/arch/s390/include/asm/preempt.h
@@ -0,0 +1,137 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <asm/current.h>
+#include <linux/thread_info.h>
+#include <asm/atomic_ops.h>
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+#define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
+
+static inline int preempt_count(void)
+{
+	return READ_ONCE(S390_lowcore.preempt_count) & ~PREEMPT_NEED_RESCHED;
+}
+
+static inline void preempt_count_set(int pc)
+{
+	int old, new;
+
+	do {
+		old = READ_ONCE(S390_lowcore.preempt_count);
+		new = (old & PREEMPT_NEED_RESCHED) |
+			(pc & ~PREEMPT_NEED_RESCHED);
+	} while (__atomic_cmpxchg(&S390_lowcore.preempt_count,
+				  old, new) != old);
+}
+
+#define init_task_preempt_count(p)	do { } while (0)
+
+#define init_idle_preempt_count(p, cpu)	do { \
+	S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+} while (0)
+
+static inline void set_preempt_need_resched(void)
+{
+	__atomic_and(~PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
+}
+
+static inline void clear_preempt_need_resched(void)
+{
+	__atomic_or(PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
+}
+
+static inline bool test_preempt_need_resched(void)
+{
+	return !(READ_ONCE(S390_lowcore.preempt_count) & PREEMPT_NEED_RESCHED);
+}
+
+static inline void __preempt_count_add(int val)
+{
+	if (__builtin_constant_p(val) && (val >= -128) && (val <= 127))
+		__atomic_add_const(val, &S390_lowcore.preempt_count);
+	else
+		__atomic_add(val, &S390_lowcore.preempt_count);
+}
+
+static inline void __preempt_count_sub(int val)
+{
+	__preempt_count_add(-val);
+}
+
+static inline bool __preempt_count_dec_and_test(void)
+{
+	return __atomic_add(-1, &S390_lowcore.preempt_count) == 1;
+}
+
+static inline bool should_resched(int preempt_offset)
+{
+	return unlikely(READ_ONCE(S390_lowcore.preempt_count) ==
+			preempt_offset);
+}
+
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+#define PREEMPT_ENABLED	(0)
+
+static inline int preempt_count(void)
+{
+	return READ_ONCE(S390_lowcore.preempt_count);
+}
+
+static inline void preempt_count_set(int pc)
+{
+	S390_lowcore.preempt_count = pc;
+}
+
+#define init_task_preempt_count(p)	do { } while (0)
+
+#define init_idle_preempt_count(p, cpu)	do { \
+	S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+} while (0)
+
+static inline void set_preempt_need_resched(void)
+{
+}
+
+static inline void clear_preempt_need_resched(void)
+{
+}
+
+static inline bool test_preempt_need_resched(void)
+{
+	return false;
+}
+
+static inline void __preempt_count_add(int val)
+{
+	S390_lowcore.preempt_count += val;
+}
+
+static inline void __preempt_count_sub(int val)
+{
+	S390_lowcore.preempt_count -= val;
+}
+
+static inline bool __preempt_count_dec_and_test(void)
+{
+	return !--S390_lowcore.preempt_count && tif_need_resched();
+}
+
+static inline bool should_resched(int preempt_offset)
+{
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
+}
+
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+#ifdef CONFIG_PREEMPT
+extern asmlinkage void preempt_schedule(void);
+#define __preempt_schedule() preempt_schedule()
+extern asmlinkage void preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
+#endif /* CONFIG_PREEMPT */
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 9d3a21aedc97..6bca916a5ba0 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -110,14 +110,20 @@ typedef struct {
 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 system_timer;	/* task cputime in kernel space */
+	unsigned long sys_call_table;	/* system call table address */
 	mm_segment_t mm_segment;
 	unsigned long gmap_addr;	/* address of last gmap fault. */
 	unsigned int gmap_write_flag;	/* gmap fault write indication */
 	unsigned int gmap_int_code;	/* int code of last gmap fault */
 	unsigned int gmap_pfault;	/* signal of a pending guest pfault */
+	/* Per-thread information related to debugging */
 	struct per_regs per_user;	/* User specified PER registers */
 	struct per_event per_event;	/* Cause of the last PER trap */
 	unsigned long per_flags;	/* Flags to control debug behavior */
+	unsigned int system_call;	/* system call number in signal */
+	unsigned long last_break;	/* last breaking-event-address. */
         /* pfault_wait is used to block the process on a pfault event */
 	unsigned long pfault_wait;
 	struct list_head list;
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 2ad9c204b1a2..8db92a5b3bf1 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -101,7 +101,8 @@ struct zpci_report_error_header {
 	u8 data[0];	/* Subsequent Data passed verbatim to SCLP ET 24 */
 } __packed;
 
-int sclp_get_core_info(struct sclp_core_info *info);
+int _sclp_get_core_info_early(struct sclp_core_info *info);
+int _sclp_get_core_info(struct sclp_core_info *info);
 int sclp_core_configure(u8 core);
 int sclp_core_deconfigure(u8 core);
 int sclp_sdias_blk_count(void);
@@ -119,4 +120,11 @@ 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_get_core_info(info);
+}
+
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h
index 4af99cdaddf5..17a7904f001a 100644
--- a/arch/s390/include/asm/scsw.h
+++ b/arch/s390/include/asm/scsw.h
@@ -96,7 +96,8 @@ struct tm_scsw {
 	u32 dstat:8;
 	u32 cstat:8;
 	u32 fcxs:8;
-	u32 schxs:8;
+	u32 ifob:1;
+	u32 sesq:7;
 } __attribute__ ((packed));
 
 /**
@@ -177,6 +178,9 @@ union scsw {
 #define SCHN_STAT_INTF_CTRL_CHK	 0x02
 #define SCHN_STAT_CHAIN_CHECK	 0x01
 
+#define SCSW_SESQ_DEV_NOFCX	 3
+#define SCSW_SESQ_PATH_NOFCX	 4
+
 /*
  * architectured values for first sense byte
  */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 0cc383b9be7f..3deb134587b7 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -36,6 +36,7 @@ extern void smp_yield_cpu(int cpu);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
 extern void smp_fill_possible_mask(void);
+extern void smp_detect_cpus(void);
 
 #else /* CONFIG_SMP */
 
@@ -56,6 +57,7 @@ static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_fill_possible_mask(void) { }
+static inline void smp_detect_cpus(void) { }
 
 #endif /* CONFIG_SMP */
 
@@ -69,6 +71,12 @@ static inline void smp_stop_cpu(void)
 	}
 }
 
+/* Return thread 0 CPU number as base CPU */
+static inline int smp_get_base_cpu(int cpu)
+{
+	return cpu - (cpu % (smp_cpu_mtid + 1));
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern int smp_rescan_cpus(void);
 extern void __noreturn cpu_die(void);
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 8662f5c8e17f..15a3c005c274 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -14,6 +14,7 @@
 #define __HAVE_ARCH_MEMCHR	/* inline & arch function */
 #define __HAVE_ARCH_MEMCMP	/* arch function */
 #define __HAVE_ARCH_MEMCPY	/* gcc builtin & arch function */
+#define __HAVE_ARCH_MEMMOVE	/* gcc builtin & arch function */
 #define __HAVE_ARCH_MEMSCAN	/* inline & arch function */
 #define __HAVE_ARCH_MEMSET	/* gcc builtin & arch function */
 #define __HAVE_ARCH_STRCAT	/* inline & arch function */
@@ -32,6 +33,7 @@
 extern int memcmp(const void *, const void *, size_t);
 extern void *memcpy(void *, const void *, size_t);
 extern void *memset(void *, int, size_t);
+extern void *memmove(void *, const void *, size_t);
 extern int strcmp(const char *,const char *);
 extern size_t strlcat(char *, const char *, size_t);
 extern size_t strlcpy(char *, const char *, size_t);
@@ -40,7 +42,6 @@ extern char *strncpy(char *, const char *, size_t);
 extern char *strrchr(const char *, int);
 extern char *strstr(const char *, const char *);
 
-#undef __HAVE_ARCH_MEMMOVE
 #undef __HAVE_ARCH_STRCHR
 #undef __HAVE_ARCH_STRNCHR
 #undef __HAVE_ARCH_STRNCMP
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 2728114d5484..229326c942c7 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -107,6 +107,11 @@ struct sysinfo_2_2_2 {
 	char reserved_3[5];
 	unsigned short cpus_dedicated;
 	unsigned short cpus_shared;
+	char reserved_4[3];
+	unsigned char vsne;
+	uuid_be uuid;
+	char reserved_5[160];
+	char ext_name[256];
 };
 
 #define LPAR_CHAR_DEDICATED	(1 << 7)
@@ -127,7 +132,7 @@ struct sysinfo_3_2_2 {
 		unsigned int caf;
 		char cpi[16];
 		char reserved_1[3];
-		char ext_name_encoding;
+		unsigned char evmne;
 		unsigned int reserved_2;
 		uuid_be uuid;
 	} vm[8];
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index f15c0398c363..a5b54a445eb8 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -12,10 +12,10 @@
 /*
  * Size of kernel stack for each process
  */
-#define THREAD_ORDER 2
+#define THREAD_SIZE_ORDER 2
 #define ASYNC_ORDER  2
 
-#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
+#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
 #define ASYNC_SIZE  (PAGE_SIZE << ASYNC_ORDER)
 
 #ifndef __ASSEMBLY__
@@ -30,15 +30,7 @@
  * - if the contents of this structure are changed, the assembly constants must also be changed
  */
 struct thread_info {
-	struct task_struct	*task;		/* main task structure */
 	unsigned long		flags;		/* low level flags */
-	unsigned long		sys_call_table;	/* System call table address */
-	unsigned int		cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-	unsigned int		system_call;
-	__u64			user_timer;
-	__u64			system_timer;
-	unsigned long		last_break;	/* last breaking-event-address. */
 };
 
 /*
@@ -46,26 +38,14 @@ struct thread_info {
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
-	.task		= &tsk,			\
 	.flags		= 0,			\
-	.cpu		= 0,			\
-	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *) S390_lowcore.thread_info;
-}
-
 void arch_release_task_struct(struct task_struct *tsk);
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
-#define THREAD_SIZE_ORDER THREAD_ORDER
-
 #endif
 
 /*
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 0bb08f341c09..de8298800722 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -52,11 +52,9 @@ static inline void store_clock_comparator(__u64 *time)
 
 void clock_comparator_work(void);
 
-void __init ptff_init(void);
+void __init time_early_init(void);
 
 extern unsigned char ptff_function_mask[16];
-extern unsigned long lpar_offset;
-extern unsigned long initial_leap_seconds;
 
 /* Function codes for the ptff instruction. */
 #define PTFF_QAF	0x00	/* query available functions */
@@ -100,21 +98,28 @@ struct ptff_qui {
 	unsigned int pad_0x5c[41];
 } __packed;
 
-static inline int ptff(void *ptff_block, size_t len, unsigned int func)
-{
-	typedef struct { char _[len]; } addrtype;
-	register unsigned int reg0 asm("0") = func;
-	register unsigned long reg1 asm("1") = (unsigned long) ptff_block;
-	int rc;
-
-	asm volatile(
-		"	.word	0x0104\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (rc), "+m" (*(addrtype *) ptff_block)
-		: "d" (reg0), "d" (reg1) : "cc");
-	return rc;
-}
+/*
+ * ptff - Perform timing facility function
+ * @ptff_block: Pointer to ptff parameter block
+ * @len: Length of parameter block
+ * @func: Function code
+ * Returns: Condition code (0 on success)
+ */
+#define ptff(ptff_block, len, func)					\
+({									\
+	struct addrtype { char _[len]; };				\
+	register unsigned int reg0 asm("0") = func;			\
+	register unsigned long reg1 asm("1") = (unsigned long) (ptff_block);\
+	int rc;								\
+									\
+	asm volatile(							\
+		"	.word	0x0104\n"				\
+		"	ipm	%0\n"					\
+		"	srl	%0,28\n"				\
+		: "=d" (rc), "+m" (*(struct addrtype *) reg1)		\
+		: "d" (reg0), "d" (reg1) : "cc");			\
+	rc;								\
+})
 
 static inline unsigned long long local_tick_disable(void)
 {
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index f15f5571ca2b..fa1bfce10370 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -22,21 +22,22 @@ struct cpu_topology_s390 {
 	cpumask_t drawer_mask;
 };
 
-DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
-
-#define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)
-#define topology_thread_id(cpu)		  (per_cpu(cpu_topology, cpu).thread_id)
-#define topology_sibling_cpumask(cpu) \
-		(&per_cpu(cpu_topology, cpu).thread_mask)
-#define topology_core_id(cpu)		  (per_cpu(cpu_topology, cpu).core_id)
-#define topology_core_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).core_mask)
-#define topology_book_id(cpu)		  (per_cpu(cpu_topology, cpu).book_id)
-#define topology_book_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).book_mask)
-#define topology_drawer_id(cpu)		  (per_cpu(cpu_topology, cpu).drawer_id)
-#define topology_drawer_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).drawer_mask)
+extern struct cpu_topology_s390 cpu_topology[NR_CPUS];
+extern cpumask_t cpus_with_topology;
+
+#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id)
+#define topology_thread_id(cpu)		  (cpu_topology[cpu].thread_id)
+#define topology_sibling_cpumask(cpu)	  (&cpu_topology[cpu].thread_mask)
+#define topology_core_id(cpu)		  (cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	  (&cpu_topology[cpu].core_mask)
+#define topology_book_id(cpu)		  (cpu_topology[cpu].book_id)
+#define topology_book_cpumask(cpu)	  (&cpu_topology[cpu].book_mask)
+#define topology_drawer_id(cpu)		  (cpu_topology[cpu].drawer_id)
+#define topology_drawer_cpumask(cpu)	  (&cpu_topology[cpu].drawer_mask)
 
 #define mc_capable() 1
 
+void topology_init_early(void);
 int topology_cpu_init(struct cpu *);
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -46,6 +47,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #else /* CONFIG_SCHED_TOPOLOGY */
 
+static inline void topology_init_early(void) { }
 static inline void topology_schedule_update(void) { }
 static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
 static inline void topology_expect_change(void) { }
@@ -65,7 +67,7 @@ static inline void topology_expect_change(void) { }
 #define cpu_to_node cpu_to_node
 static inline int cpu_to_node(int cpu)
 {
-	return per_cpu(cpu_topology, cpu).node_id;
+	return cpu_topology[cpu].node_id;
 }
 
 /* Returns a pointer to the cpumask of CPUs on node 'node'. */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 52d7c8709279..f82b04e85a21 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -37,14 +37,14 @@
 #define get_ds()        (KERNEL_DS)
 #define get_fs()        (current->thread.mm_segment)
 
-#define set_fs(x) \
-({									\
+#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);					\
-})
+}
 
 #define segment_eq(a,b) ((a).ar4 == (b).ar4)
 
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index d0a2dbf2433d..88bdc477a843 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -33,6 +33,8 @@ struct vdso_data {
 	__u32 ectg_available;		/* ECTG instruction present	0x58 */
 	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x5c */
 	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
+	__u32 ts_dir;			/* TOD steering direction	0x64 */
+	__u64 ts_end;			/* TOD steering end		0x68 */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index cc44b09c25fc..bf736e764cb4 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += dasd.h
 header-y += debug.h
 header-y += errno.h
 header-y += fcntl.h
+header-y += hypfs.h
 header-y += ioctl.h
 header-y += ioctls.h
 header-y += ipcbuf.h
@@ -29,16 +30,16 @@ header-y += ptrace.h
 header-y += qeth.h
 header-y += resource.h
 header-y += schid.h
+header-y += sclp_ctl.h
 header-y += sembuf.h
 header-y += setup.h
 header-y += shmbuf.h
+header-y += sie.h
 header-y += sigcontext.h
 header-y += siginfo.h
 header-y += signal.h
 header-y += socket.h
 header-y += sockios.h
-header-y += sclp_ctl.h
-header-y += sie.h
 header-y += stat.h
 header-y += statfs.h
 header-y += swab.h
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 1f0fe98f6db9..36b5101c8606 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -2,20 +2,47 @@
 # Makefile for the linux kernel.
 #
 
-KCOV_INSTRUMENT_early.o := n
-KCOV_INSTRUMENT_sclp.o := n
-KCOV_INSTRUMENT_als.o := n
-
 ifdef CONFIG_FUNCTION_TRACER
-# Don't trace early setup code and tracing code
-CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+
+# Do not trace tracer code
+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	= $(CC_FLAGS_FTRACE)
+
+endif
+
+GCOV_PROFILE_als.o	:= n
+GCOV_PROFILE_early.o	:= n
+GCOV_PROFILE_sclp.o	:= n
+
+KCOV_INSTRUMENT_als.o	:= n
+KCOV_INSTRUMENT_early.o	:= n
+KCOV_INSTRUMENT_sclp.o	:= n
+
+UBSAN_SANITIZE_als.o	:= n
+UBSAN_SANITIZE_early.o	:= n
+UBSAN_SANITIZE_sclp.o	:= n
+
+#
+# Use -march=z900 for sclp.c and als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
+#
+ifneq ($(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
 
 #
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
-CFLAGS_smp.o	:= -Wno-nonnull
+CFLAGS_smp.o		:= -Wno-nonnull
 
 #
 # Disable tailcall optimizations for stack / callchain walking functions
@@ -30,27 +57,7 @@ CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
 #
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-CFLAGS_sysinfo.o += -w
-
-#
-# Use -march=z900 for sclp.c and als.c to be able to print an error
-# message if the kernel is started on a machine which is too old
-#
-CFLAGS_REMOVE_sclp.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE)
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp.o		+= -march=z900
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_als.o		+= -march=z900
-AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o		+= -march=z900
-endif
-GCOV_PROFILE_sclp.o := n
-GCOV_PROFILE_als.o := n
-UBSAN_SANITIZE_als.o := n
-UBSAN_SANITIZE_early.o := n
-UBSAN_SANITIZE_sclp.o := n
+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
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index f3df9e0a5dec..c4b3570ded5b 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -25,12 +25,14 @@
 int main(void)
 {
 	/* task struct offsets */
-	OFFSET(__TASK_thread_info, task_struct, stack);
+	OFFSET(__TASK_stack, task_struct, stack);
 	OFFSET(__TASK_thread, task_struct, thread);
 	OFFSET(__TASK_pid, task_struct, pid);
 	BLANK();
 	/* thread struct offsets */
 	OFFSET(__THREAD_ksp, thread_struct, ksp);
+	OFFSET(__THREAD_sysc_table,  thread_struct, sys_call_table);
+	OFFSET(__THREAD_last_break, thread_struct, last_break);
 	OFFSET(__THREAD_FPU_fpc, thread_struct, fpu.fpc);
 	OFFSET(__THREAD_FPU_regs, thread_struct, fpu.regs);
 	OFFSET(__THREAD_per_cause, thread_struct, per_event.cause);
@@ -39,14 +41,7 @@ int main(void)
 	OFFSET(__THREAD_trap_tdb, thread_struct, trap_tdb);
 	BLANK();
 	/* thread info offsets */
-	OFFSET(__TI_task, thread_info, task);
-	OFFSET(__TI_flags, thread_info, flags);
-	OFFSET(__TI_sysc_table, thread_info, sys_call_table);
-	OFFSET(__TI_cpu, thread_info, cpu);
-	OFFSET(__TI_precount, thread_info, preempt_count);
-	OFFSET(__TI_user_timer, thread_info, user_timer);
-	OFFSET(__TI_system_timer, thread_info, system_timer);
-	OFFSET(__TI_last_break, thread_info, last_break);
+	OFFSET(__TI_flags, task_struct, thread_info.flags);
 	BLANK();
 	/* pt_regs offsets */
 	OFFSET(__PT_ARGS, pt_regs, args);
@@ -79,6 +74,8 @@ int main(void)
 	OFFSET(__VDSO_ECTG_OK, vdso_data, ectg_available);
 	OFFSET(__VDSO_TK_MULT, vdso_data, tk_mult);
 	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
+	OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
+	OFFSET(__VDSO_TS_END, vdso_data, ts_end);
 	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
 	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
 	OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr);
@@ -159,7 +156,6 @@ int main(void)
 	OFFSET(__LC_INT_CLOCK, lowcore, int_clock);
 	OFFSET(__LC_MCCK_CLOCK, lowcore, mcck_clock);
 	OFFSET(__LC_CURRENT, lowcore, current_task);
-	OFFSET(__LC_THREAD_INFO, lowcore, thread_info);
 	OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
 	OFFSET(__LC_ASYNC_STACK, lowcore, async_stack);
 	OFFSET(__LC_PANIC_STACK, lowcore, panic_stack);
@@ -173,6 +169,7 @@ int main(void)
 	OFFSET(__LC_PERCPU_OFFSET, lowcore, percpu_offset);
 	OFFSET(__LC_VDSO_PER_CPU, lowcore, vdso_per_cpu_data);
 	OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
+	OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
 	OFFSET(__LC_GMAP, lowcore, gmap);
 	OFFSET(__LC_PASTE, lowcore, paste);
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 4af60374eba0..6f2a6ab13cb5 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -446,7 +446,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		/* set extra registers only for synchronous signals */
 		regs->gprs[4] = regs->int_code & 127;
 		regs->gprs[5] = regs->int_parm_long;
-		regs->gprs[6] = task_thread_info(current)->last_break;
+		regs->gprs[6] = current->thread.last_break;
 	}
 
 	return 0;
@@ -523,7 +523,7 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 	regs->gprs[2] = ksig->sig;
 	regs->gprs[3] = (__force __u64) &frame->info;
 	regs->gprs[4] = (__force __u64) &frame->uc;
-	regs->gprs[5] = task_thread_info(current)->last_break;
+	regs->gprs[5] = current->thread.last_break;
 	return 0;
 }
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2374c5b46bbc..d038c8cea6cb 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -293,6 +293,7 @@ static noinline __init void setup_lowcore_early(void)
 	psw.addr = (unsigned long) s390_base_pgm_handler;
 	S390_lowcore.program_new_psw = psw;
 	s390_base_pgm_handler_fn = early_pgm_check_handler;
+	S390_lowcore.preempt_count = INIT_PREEMPT_COUNT;
 }
 
 static noinline __init void setup_facility_list(void)
@@ -391,7 +392,49 @@ static int __init cad_init(void)
 }
 early_initcall(cad_init);
 
-static __init void rescue_initrd(void)
+static __init void memmove_early(void *dst, const void *src, size_t n)
+{
+	unsigned long addr;
+	long incr;
+	psw_t old;
+
+	if (!n)
+		return;
+	incr = 1;
+	if (dst > src) {
+		incr = -incr;
+		dst += n - 1;
+		src += n - 1;
+	}
+	old = S390_lowcore.program_new_psw;
+	S390_lowcore.program_new_psw.mask = __extract_psw();
+	asm volatile(
+		"	larl	%[addr],1f\n"
+		"	stg	%[addr],%[psw_pgm_addr]\n"
+		"0:     mvc	0(1,%[dst]),0(%[src])\n"
+		"	agr	%[dst],%[incr]\n"
+		"	agr	%[src],%[incr]\n"
+		"	brctg	%[n],0b\n"
+		"1:\n"
+		: [addr] "=&d" (addr),
+		  [psw_pgm_addr] "=&Q" (S390_lowcore.program_new_psw.addr),
+		  [dst] "+&a" (dst), [src] "+&a" (src),  [n] "+d" (n)
+		: [incr] "d" (incr)
+		: "cc", "memory");
+	S390_lowcore.program_new_psw = old;
+}
+
+static __init noinline void ipl_save_parameters(void)
+{
+	void *src, *dst;
+
+	src = (void *)(unsigned long) S390_lowcore.ipl_parmblock_ptr;
+	dst = (void *) IPL_PARMBLOCK_ORIGIN;
+	memmove_early(dst, src, PAGE_SIZE);
+	S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN;
+}
+
+static __init noinline void rescue_initrd(void)
 {
 #ifdef CONFIG_BLK_DEV_INITRD
 	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
@@ -405,7 +448,7 @@ static __init void rescue_initrd(void)
 		return;
 	if (INITRD_START >= min_initrd_addr)
 		return;
-	memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
+	memmove_early((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
 	INITRD_START = min_initrd_addr;
 #endif
 }
@@ -467,7 +510,8 @@ void __init startup_init(void)
 	ipl_save_parameters();
 	rescue_initrd();
 	clear_bss_section();
-	ptff_init();
+	ipl_verify_parameters();
+	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
 	setup_lowcore_early();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 49a30737adde..97298c58b2be 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -42,7 +42,7 @@ __PT_R13     =	__PT_GPRS + 104
 __PT_R14     =	__PT_GPRS + 112
 __PT_R15     =	__PT_GPRS + 120
 
-STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
+STACK_SHIFT = PAGE_SHIFT + THREAD_SIZE_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
@@ -123,8 +123,14 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 
 	.macro	LAST_BREAK scratch
 	srag	\scratch,%r10,23
+#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
 	jz	.+10
-	stg	%r10,__TI_last_break(%r12)
+	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
@@ -186,14 +192,13 @@ ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	lgr	%r1,%r2
 	aghi	%r1,__TASK_thread		# thread_struct of prev task
-	lg	%r5,__TASK_thread_info(%r3)	# get thread_info of next
+	lg	%r5,__TASK_stack(%r3)		# start of kernel stack of next
 	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
 	lgr	%r1,%r3
 	aghi	%r1,__TASK_thread		# thread_struct of next task
 	lgr	%r15,%r5
 	aghi	%r15,STACK_INIT			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
-	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
 	/* c4 is used in guest detection: arch/s390/kernel/perf_cpum_sf.c */
@@ -274,7 +279,7 @@ ENTRY(system_call)
 .Lsysc_stmg:
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
-	lg	%r12,__LC_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	lghi	%r14,_PIF_SYSCALL
 .Lsysc_per:
 	lg	%r15,__LC_KERNEL_STACK
@@ -288,7 +293,13 @@ ENTRY(system_call)
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
 	stg	%r14,__PT_FLAGS(%r11)
 .Lsysc_do_svc:
-	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
+	# 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
@@ -389,7 +400,6 @@ ENTRY(system_call)
 	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL
 	jno	.Lsysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
-	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	lghi	%r8,0			# svc 0 returns -ENOSYS
 	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
@@ -457,7 +467,7 @@ ENTRY(system_call)
 #
 ENTRY(ret_from_fork)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	lg	%r12,__LC_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	brasl	%r14,schedule_tail
 	TRACE_IRQS_ON
 	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
@@ -478,7 +488,7 @@ ENTRY(pgm_check_handler)
 	stpt	__LC_SYNC_ENTER_TIMER
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
-	lg	%r12,__LC_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_PGM_OLD_PSW
 	tmhh	%r8,0x0001		# test problem state bit
@@ -501,7 +511,7 @@ ENTRY(pgm_check_handler)
 2:	LAST_BREAK %r14
 	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	lg	%r15,__LC_KERNEL_STACK
-	lg	%r14,__TI_task(%r12)
+	lgr	%r14,%r12
 	aghi	%r14,__TASK_thread	# pointer to thread_struct
 	lghi	%r13,__LC_PGM_TDB
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
@@ -567,7 +577,7 @@ ENTRY(io_int_handler)
 	stpt	__LC_ASYNC_ENTER_TIMER
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r10,__LC_LAST_BREAK
-	lg	%r12,__LC_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
@@ -626,7 +636,7 @@ ENTRY(io_int_handler)
 	jo	.Lio_work_user		# yes -> do resched & signal
 #ifdef CONFIG_PREEMPT
 	# check for preemptive scheduling
-	icm	%r0,15,__TI_precount(%r12)
+	icm	%r0,15,__LC_PREEMPT_COUNT
 	jnz	.Lio_restore		# preemption is disabled
 	TSTMSK	__TI_flags(%r12),_TIF_NEED_RESCHED
 	jno	.Lio_restore
@@ -741,7 +751,7 @@ ENTRY(ext_int_handler)
 	stpt	__LC_ASYNC_ENTER_TIMER
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r10,__LC_LAST_BREAK
-	lg	%r12,__LC_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
@@ -798,13 +808,10 @@ ENTRY(save_fpu_regs)
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	bor	%r14
 	stfpc	__THREAD_FPU_fpc(%r2)
-.Lsave_fpu_regs_fpc_end:
 	lg	%r3,__THREAD_FPU_regs(%r2)
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
 	jz	.Lsave_fpu_regs_fp	  # no -> store FP regs
-.Lsave_fpu_regs_vx_low:
 	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
-.Lsave_fpu_regs_vx_high:
 	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
 	j	.Lsave_fpu_regs_done	  # -> set CIF_FPU flag
 .Lsave_fpu_regs_fp:
@@ -851,9 +858,7 @@ load_fpu_regs:
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
 	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
 	jz	.Lload_fpu_regs_fp		# -> no VX, load FP regs
-.Lload_fpu_regs_vx:
 	VLM	%v0,%v15,0,%r4
-.Lload_fpu_regs_vx_high:
 	VLM	%v16,%v31,256,%r4
 	j	.Lload_fpu_regs_done
 .Lload_fpu_regs_fp:
@@ -889,7 +894,7 @@ ENTRY(mcck_int_handler)
 	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_THREAD_INFO
+	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
 	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE
@@ -948,7 +953,7 @@ ENTRY(mcck_int_handler)
 
 .Lmcck_panic:
 	lg	%r15,__LC_PANIC_STACK
-	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	j	.Lmcck_skip
 
 #
@@ -1085,7 +1090,7 @@ cleanup_critical:
 	jhe	0f
 	# set up saved registers r10 and r12
 	stg	%r10,16(%r11)		# r10 last break
-	stg	%r12,32(%r11)		# r12 thread-info pointer
+	stg	%r12,32(%r11)		# r12 task struct pointer
 0:	# check if the user time update has been done
 	clg	%r9,BASED(.Lcleanup_system_call_insn+24)
 	jh	0f
@@ -1106,7 +1111,9 @@ cleanup_critical:
 	lg	%r9,16(%r11)
 	srag	%r9,%r9,23
 	jz	0f
-	mvc	__TI_last_break(8,%r12),16(%r11)
+	lgr	%r9,%r12
+	aghi	%r9,__TASK_thread
+	mvc	__THREAD_last_break(8,%r9),16(%r11)
 0:	# set up saved register r11
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r9,STACK_FRAME_OVERHEAD(%r15)
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 4431905f8cfa..0b5ebf8a3d30 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -315,7 +315,7 @@ ENTRY(startup_kdump)
 	jg	startup_continue
 
 .Lstack:
-	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
 	.align	8
 6:	.long	0x7fffffff,0xffffffff
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 03c2b469c472..482d3526e32b 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -32,11 +32,10 @@ ENTRY(startup_continue)
 #
 # Setup stack
 #
-	larl	%r15,init_thread_union
-	stg	%r15,__LC_THREAD_INFO	# cache thread info in lowcore
-	lg	%r14,__TI_task(%r15)	# cache current in lowcore
+	larl	%r14,init_task
 	stg	%r14,__LC_CURRENT
-	aghi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE
+	larl	%r15,init_thread_union
+	aghi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER) # init_task_union + THREAD_SIZE
 	stg	%r15,__LC_KERNEL_STACK	# set end of kernel stack
 	aghi	%r15,-160
 #
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 295bfb7124bc..ff3364a067ff 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1991,10 +1991,9 @@ void __init ipl_update_parameters(void)
 		diag308_set_works = 1;
 }
 
-void __init ipl_save_parameters(void)
+void __init ipl_verify_parameters(void)
 {
 	struct cio_iplinfo iplinfo;
-	void *src, *dst;
 
 	if (cio_get_iplinfo(&iplinfo))
 		return;
@@ -2005,10 +2004,6 @@ void __init ipl_save_parameters(void)
 	if (!iplinfo.is_qdio)
 		return;
 	ipl_flags |= IPL_PARMBLOCK_VALID;
-	src = (void *)(unsigned long)S390_lowcore.ipl_parmblock_ptr;
-	dst = (void *)IPL_PARMBLOCK_ORIGIN;
-	memmove(dst, src, PAGE_SIZE);
-	S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN;
 }
 
 static LIST_HEAD(rcall);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 285d6561076d..ef60f4177331 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -168,7 +168,7 @@ void do_softirq_own_stack(void)
 	old = current_stack_pointer();
 	/* Check against async. stack address range. */
 	new = S390_lowcore.async_stack;
-	if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {
+	if (((new - old) >> (PAGE_SHIFT + THREAD_SIZE_ORDER)) != 0) {
 		/* Need to switch to the async. stack. */
 		new -= STACK_FRAME_OVERHEAD;
 		((struct stack_frame *) new)->back_chain = old;
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index 6ea6d69339b5..ae7dff110054 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -5,7 +5,8 @@
  * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
 #include <asm/facility.h>
@@ -183,4 +184,4 @@ static int __init lgr_init(void)
 	lgr_timer_set();
 	return 0;
 }
-module_init(lgr_init);
+device_initcall(lgr_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index fcc634c1479a..763dec18edcd 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -995,39 +995,36 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	regs.int_parm = CPU_MF_INT_SF_PRA;
 	sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
 
-	regs.psw.addr = sfr->basic.ia;
-	if (sfr->basic.T)
-		regs.psw.mask |= PSW_MASK_DAT;
-	if (sfr->basic.W)
-		regs.psw.mask |= PSW_MASK_WAIT;
-	if (sfr->basic.P)
-		regs.psw.mask |= PSW_MASK_PSTATE;
-	switch (sfr->basic.AS) {
-	case 0x0:
-		regs.psw.mask |= PSW_ASC_PRIMARY;
-		break;
-	case 0x1:
-		regs.psw.mask |= PSW_ASC_ACCREG;
-		break;
-	case 0x2:
-		regs.psw.mask |= PSW_ASC_SECONDARY;
-		break;
-	case 0x3:
-		regs.psw.mask |= PSW_ASC_HOME;
-		break;
-	}
+	psw_bits(regs.psw).ia = sfr->basic.ia;
+	psw_bits(regs.psw).t  = sfr->basic.T;
+	psw_bits(regs.psw).w  = sfr->basic.W;
+	psw_bits(regs.psw).p  = sfr->basic.P;
+	psw_bits(regs.psw).as = sfr->basic.AS;
 
 	/*
-	 * A non-zero guest program parameter indicates a guest
-	 * sample.
-	 * Note that some early samples or samples from guests without
+	 * Use the hardware provided configuration level to decide if the
+	 * sample belongs to a guest or host. If that is not available,
+	 * fall back to the following heuristics:
+	 * A non-zero guest program parameter always indicates a guest
+	 * sample. Some early samples or samples from guests without
 	 * lpp usage would be misaccounted to the host. We use the asn
-	 * value as a heuristic to detect most of these guest samples.
-	 * If the value differs from the host hpp value, we assume
-	 * it to be a KVM guest.
+	 * value as an addon heuristic to detect most of these guest samples.
+	 * If the value differs from the host hpp value, we assume to be a
+	 * KVM guest.
 	 */
-	if (sfr->basic.gpp || sfr->basic.prim_asn != (u16) sfr->basic.hpp)
+	switch (sfr->basic.CL) {
+	case 1: /* logical partition */
+		sde_regs->in_guest = 0;
+		break;
+	case 2: /* virtual machine */
 		sde_regs->in_guest = 1;
+		break;
+	default: /* old machine, use heuristics */
+		if (sfr->basic.gpp ||
+		    sfr->basic.prim_asn != (u16)sfr->basic.hpp)
+			sde_regs->in_guest = 1;
+		break;
+	}
 
 	overflow = 0;
 	if (perf_exclude_event(event, &regs, sde_regs))
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index bba4fa74b321..400d14f0b9f5 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -103,7 +103,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 		unsigned long arg, struct task_struct *p)
 {
-	struct thread_info *ti;
 	struct fake_frame
 	{
 		struct stack_frame sf;
@@ -121,9 +120,8 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
 	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
 	/* Initialize per thread user and system timer values */
-	ti = task_thread_info(p);
-	ti->user_timer = 0;
-	ti->system_timer = 0;
+	p->thread.user_timer = 0;
+	p->thread.system_timer = 0;
 
 	frame->sf.back_chain = 0;
 	/* new return point is ret_from_fork */
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 9336e824e2db..b81ab8882e2e 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -461,7 +461,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		}
 		return 0;
 	case PTRACE_GET_LAST_BREAK:
-		put_user(task_thread_info(child)->last_break,
+		put_user(child->thread.last_break,
 			 (unsigned long __user *) data);
 		return 0;
 	case PTRACE_ENABLE_TE:
@@ -811,7 +811,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		}
 		return 0;
 	case PTRACE_GET_LAST_BREAK:
-		put_user(task_thread_info(child)->last_break,
+		put_user(child->thread.last_break,
 			 (unsigned int __user *) data);
 		return 0;
 	}
@@ -997,10 +997,10 @@ static int s390_last_break_get(struct task_struct *target,
 	if (count > 0) {
 		if (kbuf) {
 			unsigned long *k = kbuf;
-			*k = task_thread_info(target)->last_break;
+			*k = target->thread.last_break;
 		} else {
 			unsigned long  __user *u = ubuf;
-			if (__put_user(task_thread_info(target)->last_break, u))
+			if (__put_user(target->thread.last_break, u))
 				return -EFAULT;
 		}
 	}
@@ -1113,7 +1113,7 @@ static int s390_system_call_get(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				void *kbuf, void __user *ubuf)
 {
-	unsigned int *data = &task_thread_info(target)->system_call;
+	unsigned int *data = &target->thread.system_call;
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   data, 0, sizeof(unsigned int));
 }
@@ -1123,7 +1123,7 @@ static int s390_system_call_set(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				const void *kbuf, const void __user *ubuf)
 {
-	unsigned int *data = &task_thread_info(target)->system_call;
+	unsigned int *data = &target->thread.system_call;
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  data, 0, sizeof(unsigned int));
 }
@@ -1327,7 +1327,7 @@ static int s390_compat_last_break_get(struct task_struct *target,
 	compat_ulong_t last_break;
 
 	if (count > 0) {
-		last_break = task_thread_info(target)->last_break;
+		last_break = target->thread.last_break;
 		if (kbuf) {
 			unsigned long *k = kbuf;
 			*k = last_break;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 7f7ba5f23f13..adfac9f0a89f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -35,6 +35,7 @@
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/kernel_stat.h>
+#include <linux/dma-contiguous.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pfn.h>
@@ -303,7 +304,7 @@ static void __init setup_lowcore(void)
 	 * Setup lowcore for boot cpu
 	 */
 	BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096);
-	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
+	lc = memblock_virt_alloc_low(sizeof(*lc), sizeof(*lc));
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
 	lc->restart_psw.addr = (unsigned long) restart_int_handler;
 	lc->external_new_psw.mask = PSW_KERNEL_BITS |
@@ -324,15 +325,15 @@ static void __init setup_lowcore(void)
 	lc->kernel_stack = ((unsigned long) &init_thread_union)
 		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->async_stack = (unsigned long)
-		__alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0)
+		memblock_virt_alloc(ASYNC_SIZE, ASYNC_SIZE)
 		+ ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->panic_stack = (unsigned long)
-		__alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0)
+		memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE)
 		+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
-	lc->current_task = (unsigned long) init_thread_union.thread_info.task;
-	lc->thread_info = (unsigned long) &init_thread_union;
+	lc->current_task = (unsigned long)&init_task;
 	lc->lpp = LPP_MAGIC;
 	lc->machine_flags = S390_lowcore.machine_flags;
+	lc->preempt_count = S390_lowcore.preempt_count;
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
 	       MAX_FACILITY_BIT/8);
@@ -349,7 +350,7 @@ static void __init setup_lowcore(void)
 	lc->last_update_timer = S390_lowcore.last_update_timer;
 	lc->last_update_clock = S390_lowcore.last_update_clock;
 
-	restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0);
+	restart_stack = memblock_virt_alloc(ASYNC_SIZE, ASYNC_SIZE);
 	restart_stack += ASYNC_SIZE;
 
 	/*
@@ -412,7 +413,7 @@ static void __init setup_resources(void)
 	bss_resource.end = (unsigned long) &__bss_stop - 1;
 
 	for_each_memblock(memory, reg) {
-		res = alloc_bootmem_low(sizeof(*res));
+		res = memblock_virt_alloc(sizeof(*res), 8);
 		res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 
 		res->name = "System RAM";
@@ -426,7 +427,7 @@ static void __init setup_resources(void)
 			    std_res->start > res->end)
 				continue;
 			if (std_res->end > res->end) {
-				sub_res = alloc_bootmem_low(sizeof(*sub_res));
+				sub_res = memblock_virt_alloc(sizeof(*sub_res), 8);
 				*sub_res = *std_res;
 				sub_res->end = res->end;
 				std_res->start = res->end + 1;
@@ -445,7 +446,7 @@ static void __init setup_resources(void)
 	 * part of the System RAM resource.
 	 */
 	if (crashk_res.end) {
-		memblock_add(crashk_res.start, resource_size(&crashk_res));
+		memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0);
 		memblock_reserve(crashk_res.start, resource_size(&crashk_res));
 		insert_resource(&iomem_resource, &crashk_res);
 	}
@@ -903,6 +904,7 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_memory_end();
 	setup_memory();
+	dma_contiguous_reserve(memory_end);
 
 	check_initrd();
 	reserve_crashkernel();
@@ -921,6 +923,8 @@ void __init setup_arch(char **cmdline_p)
 	cpu_detect_mhz_feature();
         cpu_init();
 	numa_setup();
+	smp_detect_cpus();
+	topology_init_early();
 
 	/*
 	 * Create kernel page tables and switch to virtual addressing.
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index d82562cf0a0e..9f241d1efeda 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -359,7 +359,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 		/* set extra registers only for synchronous signals */
 		regs->gprs[4] = regs->int_code & 127;
 		regs->gprs[5] = regs->int_parm_long;
-		regs->gprs[6] = task_thread_info(current)->last_break;
+		regs->gprs[6] = current->thread.last_break;
 	}
 	return 0;
 }
@@ -430,7 +430,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->gprs[2] = ksig->sig;
 	regs->gprs[3] = (unsigned long) &frame->info;
 	regs->gprs[4] = (unsigned long) &frame->uc;
-	regs->gprs[5] = task_thread_info(current)->last_break;
+	regs->gprs[5] = current->thread.last_break;
 	return 0;
 }
 
@@ -467,13 +467,13 @@ void do_signal(struct pt_regs *regs)
 	 * the debugger may change all our registers, including the system
 	 * call information.
 	 */
-	current_thread_info()->system_call =
+	current->thread.system_call =
 		test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0;
 
 	if (get_signal(&ksig)) {
 		/* Whee!  Actually deliver the signal.  */
-		if (current_thread_info()->system_call) {
-			regs->int_code = current_thread_info()->system_call;
+		if (current->thread.system_call) {
+			regs->int_code = current->thread.system_call;
 			/* Check for system call restarting. */
 			switch (regs->gprs[2]) {
 			case -ERESTART_RESTARTBLOCK:
@@ -506,8 +506,8 @@ void do_signal(struct pt_regs *regs)
 
 	/* No handlers present - check for system call restart */
 	clear_pt_regs_flag(regs, PIF_SYSCALL);
-	if (current_thread_info()->system_call) {
-		regs->int_code = current_thread_info()->system_call;
+	if (current->thread.system_call) {
+		regs->int_code = current->thread.system_call;
 		switch (regs->gprs[2]) {
 		case -ERESTART_RESTARTBLOCK:
 			/* Restart with sys_restart_syscall */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index df4a508ff35c..e49f61aadaf9 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/workqueue.h>
+#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mm.h>
@@ -259,16 +260,14 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
 {
 	struct lowcore *lc = pcpu->lowcore;
-	struct thread_info *ti = task_thread_info(tsk);
 
 	lc->kernel_stack = (unsigned long) task_stack_page(tsk)
 		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
-	lc->thread_info = (unsigned long) task_thread_info(tsk);
 	lc->current_task = (unsigned long) tsk;
 	lc->lpp = LPP_MAGIC;
 	lc->current_pid = tsk->pid;
-	lc->user_timer = ti->user_timer;
-	lc->system_timer = ti->system_timer;
+	lc->user_timer = tsk->thread.user_timer;
+	lc->system_timer = tsk->thread.system_timer;
 	lc->steal_timer = 0;
 }
 
@@ -662,14 +661,12 @@ int smp_cpu_get_polarization(int cpu)
 	return pcpu_devices[cpu].polarization;
 }
 
-static struct sclp_core_info *smp_get_core_info(void)
+static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 {
 	static int use_sigp_detection;
-	struct sclp_core_info *info;
 	int address;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (info && (use_sigp_detection || sclp_get_core_info(info))) {
+	if (use_sigp_detection || sclp_get_core_info(info, early)) {
 		use_sigp_detection = 1;
 		for (address = 0;
 		     address < (SCLP_MAX_CORES << smp_cpu_mt_shift);
@@ -683,7 +680,6 @@ static struct sclp_core_info *smp_get_core_info(void)
 		}
 		info->combined = info->configured;
 	}
-	return info;
 }
 
 static int smp_add_present_cpu(int cpu);
@@ -724,17 +720,15 @@ static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
 	return nr;
 }
 
-static void __init smp_detect_cpus(void)
+void __init smp_detect_cpus(void)
 {
 	unsigned int cpu, mtid, c_cpus, s_cpus;
 	struct sclp_core_info *info;
 	u16 address;
 
 	/* Get CPU information */
-	info = smp_get_core_info();
-	if (!info)
-		panic("smp_detect_cpus failed to allocate memory\n");
-
+	info = memblock_virt_alloc(sizeof(*info), 8);
+	smp_get_core_info(info, 1);
 	/* Find boot CPU type */
 	if (sclp.has_core_type) {
 		address = stap();
@@ -770,7 +764,7 @@ static void __init smp_detect_cpus(void)
 	get_online_cpus();
 	__smp_rescan_cpus(info, 0);
 	put_online_cpus();
-	kfree(info);
+	memblock_free_early((unsigned long)info, sizeof(*info));
 }
 
 /*
@@ -807,7 +801,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	pcpu = pcpu_devices + cpu;
 	if (pcpu->state != CPU_STATE_CONFIGURED)
 		return -EIO;
-	base = cpu - (cpu % (smp_cpu_mtid + 1));
+	base = smp_get_base_cpu(cpu);
 	for (i = 0; i <= smp_cpu_mtid; i++) {
 		if (base + i < nr_cpu_ids)
 			if (cpu_online(base + i))
@@ -907,7 +901,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	/* request the 0x1202 external call external interrupt */
 	if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt))
 		panic("Couldn't request external interrupt 0x1202");
-	smp_detect_cpus();
 }
 
 void __init smp_prepare_boot_cpu(void)
@@ -973,7 +966,7 @@ static ssize_t cpu_configure_store(struct device *dev,
 	rc = -EBUSY;
 	/* disallow configuration changes of online cpus and cpu 0 */
 	cpu = dev->id;
-	cpu -= cpu % (smp_cpu_mtid + 1);
+	cpu = smp_get_base_cpu(cpu);
 	if (cpu == 0)
 		goto out;
 	for (i = 0; i <= smp_cpu_mtid; i++)
@@ -1106,9 +1099,10 @@ int __ref smp_rescan_cpus(void)
 	struct sclp_core_info *info;
 	int nr;
 
-	info = smp_get_core_info();
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
+	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
 	nr = __smp_rescan_cpus(info, 1);
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index 2d6b6e81f812..1ff21f05d7dd 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -194,7 +194,7 @@ pgm_check_entry:
 
 	/* Suspend CPU not available -> panic */
 	larl	%r15,init_thread_union
-	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER)
+	ahi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
 	larl	%r2,.Lpanic_string
 	larl	%r3,_sclp_print_early
 	lghi	%r1,0
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index bfda6aa40280..24021c1e3ecb 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -56,6 +56,20 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2)
 }
 EXPORT_SYMBOL(stsi);
 
+static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
+{
+	switch (encoding) {
+	case 1: /* EBCDIC */
+		EBCASC(name, len);
+		break;
+	case 2:	/* UTF-8 */
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
 static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
 {
 	int i;
@@ -207,24 +221,19 @@ static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info)
 		seq_printf(m, "LPAR CPUs S-MTID:     %d\n", info->mt_stid);
 		seq_printf(m, "LPAR CPUs PS-MTID:    %d\n", info->mt_psmtid);
 	}
+	if (convert_ext_name(info->vsne, info->ext_name, sizeof(info->ext_name))) {
+		seq_printf(m, "LPAR Extended Name:   %-.256s\n", info->ext_name);
+		seq_printf(m, "LPAR UUID:            %pUb\n", &info->uuid);
+	}
 }
 
 static void print_ext_name(struct seq_file *m, int lvl,
 			   struct sysinfo_3_2_2 *info)
 {
-	if (info->vm[lvl].ext_name_encoding == 0)
-		return;
-	if (info->ext_names[lvl][0] == 0)
-		return;
-	switch (info->vm[lvl].ext_name_encoding) {
-	case 1: /* EBCDIC */
-		EBCASC(info->ext_names[lvl], sizeof(info->ext_names[lvl]));
-		break;
-	case 2:	/* UTF-8 */
-		break;
-	default:
+	size_t len = sizeof(info->ext_names[lvl]);
+
+	if (!convert_ext_name(info->vm[lvl].evmne, info->ext_names[lvl], len))
 		return;
-	}
 	seq_printf(m, "VM%02d Extended Name:   %-.256s\n", lvl,
 		   info->ext_names[lvl]);
 }
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 0bfcc492987e..867d0a057046 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -59,19 +59,27 @@ ATOMIC_NOTIFIER_HEAD(s390_epoch_delta_notifier);
 EXPORT_SYMBOL(s390_epoch_delta_notifier);
 
 unsigned char ptff_function_mask[16];
-unsigned long lpar_offset;
-unsigned long initial_leap_seconds;
+
+static unsigned long long lpar_offset;
+static unsigned long long initial_leap_seconds;
+static unsigned long long tod_steering_end;
+static long long tod_steering_delta;
 
 /*
  * Get time offsets with PTFF
  */
-void __init ptff_init(void)
+void __init time_early_init(void)
 {
 	struct ptff_qto qto;
 	struct ptff_qui qui;
 
+	/* Initialize TOD steering parameters */
+	tod_steering_end = sched_clock_base_cc;
+	vdso_data->ts_end = tod_steering_end;
+
 	if (!test_facility(28))
 		return;
+
 	ptff(&ptff_function_mask, sizeof(ptff_function_mask), PTFF_QAF);
 
 	/* get LPAR offset */
@@ -80,7 +88,7 @@ void __init ptff_init(void)
 
 	/* get initial leap seconds */
 	if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
-		initial_leap_seconds = (unsigned long)
+		initial_leap_seconds = (unsigned long long)
 			((long) qui.old_leap * 4096000000L);
 }
 
@@ -123,18 +131,6 @@ void clock_comparator_work(void)
 	cd->event_handler(cd);
 }
 
-/*
- * Fixup the clock comparator.
- */
-static void fixup_clock_comparator(unsigned long long delta)
-{
-	/* If nobody is waiting there's nothing to fix. */
-	if (S390_lowcore.clock_comparator == -1ULL)
-		return;
-	S390_lowcore.clock_comparator += delta;
-	set_clock_comparator(S390_lowcore.clock_comparator);
-}
-
 static int s390_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
@@ -215,7 +211,21 @@ void read_boot_clock64(struct timespec64 *ts)
 
 static cycle_t read_tod_clock(struct clocksource *cs)
 {
-	return get_tod_clock();
+	unsigned long long now, adj;
+
+	preempt_disable(); /* protect from changes to steering parameters */
+	now = get_tod_clock();
+	adj = tod_steering_end - now;
+	if (unlikely((s64) adj >= 0))
+		/*
+		 * manually steer by 1 cycle every 2^16 cycles. This
+		 * corresponds to shifting the tod delta by 15. 1s is
+		 * therefore steered in ~9h. The adjust will decrease
+		 * over time, until it finally reaches 0.
+		 */
+		now += (tod_steering_delta < 0) ? (adj >> 15) : -(adj >> 15);
+	preempt_enable();
+	return now;
 }
 
 static struct clocksource clocksource_tod = {
@@ -384,6 +394,55 @@ static inline int check_sync_clock(void)
 	return rc;
 }
 
+/*
+ * Apply clock delta to the global data structures.
+ * This is called once on the CPU that performed the clock sync.
+ */
+static void clock_sync_global(unsigned long long delta)
+{
+	unsigned long now, adj;
+	struct ptff_qto qto;
+
+	/* Fixup the monotonic sched clock. */
+	sched_clock_base_cc += delta;
+	/* Adjust TOD steering parameters. */
+	vdso_data->tb_update_count++;
+	now = get_tod_clock();
+	adj = tod_steering_end - now;
+	if (unlikely((s64) adj >= 0))
+		/* Calculate how much of the old adjustment is left. */
+		tod_steering_delta = (tod_steering_delta < 0) ?
+			-(adj >> 15) : (adj >> 15);
+	tod_steering_delta += delta;
+	if ((abs(tod_steering_delta) >> 48) != 0)
+		panic("TOD clock sync offset %lli is too large to drift\n",
+		      tod_steering_delta);
+	tod_steering_end = now + (abs(tod_steering_delta) << 15);
+	vdso_data->ts_dir = (tod_steering_delta < 0) ? 0 : 1;
+	vdso_data->ts_end = tod_steering_end;
+	vdso_data->tb_update_count++;
+	/* Update LPAR offset. */
+	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
+		lpar_offset = qto.tod_epoch_difference;
+	/* Call the TOD clock change notifier. */
+	atomic_notifier_call_chain(&s390_epoch_delta_notifier, 0, &delta);
+}
+
+/*
+ * Apply clock delta to the per-CPU data structures of this CPU.
+ * This is called for each online CPU after the call to clock_sync_global.
+ */
+static void clock_sync_local(unsigned long long delta)
+{
+	/* Add the delta to the clock comparator. */
+	if (S390_lowcore.clock_comparator != -1ULL) {
+		S390_lowcore.clock_comparator += delta;
+		set_clock_comparator(S390_lowcore.clock_comparator);
+	}
+	/* Adjust the last_update_clock time-stamp. */
+	S390_lowcore.last_update_clock += delta;
+}
+
 /* Single threaded workqueue used for stp sync events */
 static struct workqueue_struct *time_sync_wq;
 
@@ -397,31 +456,9 @@ static void __init time_init_wq(void)
 struct clock_sync_data {
 	atomic_t cpus;
 	int in_sync;
-	unsigned long long fixup_cc;
+	unsigned long long clock_delta;
 };
 
-static void clock_sync_cpu(struct clock_sync_data *sync)
-{
-	atomic_dec(&sync->cpus);
-	enable_sync_clock();
-	while (sync->in_sync == 0) {
-		__udelay(1);
-		/*
-		 * A different cpu changes *in_sync. Therefore use
-		 * barrier() to force memory access.
-		 */
-		barrier();
-	}
-	if (sync->in_sync != 1)
-		/* Didn't work. Clear per-cpu in sync bit again. */
-		disable_sync_clock(NULL);
-	/*
-	 * This round of TOD syncing is done. Set the clock comparator
-	 * to the next tick and let the processor continue.
-	 */
-	fixup_clock_comparator(sync->fixup_cc);
-}
-
 /*
  * Server Time Protocol (STP) code.
  */
@@ -523,54 +560,46 @@ void stp_queue_work(void)
 
 static int stp_sync_clock(void *data)
 {
-	static int first;
+	struct clock_sync_data *sync = data;
 	unsigned long long clock_delta;
-	struct clock_sync_data *stp_sync;
-	struct ptff_qto qto;
+	static int first;
 	int rc;
 
-	stp_sync = data;
-
-	if (xchg(&first, 1) == 1) {
-		/* Slave */
-		clock_sync_cpu(stp_sync);
-		return 0;
-	}
-
-	/* Wait until all other cpus entered the sync function. */
-	while (atomic_read(&stp_sync->cpus) != 0)
-		cpu_relax();
-
 	enable_sync_clock();
-
-	rc = 0;
-	if (stp_info.todoff[0] || stp_info.todoff[1] ||
-	    stp_info.todoff[2] || stp_info.todoff[3] ||
-	    stp_info.tmd != 2) {
-		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0, &clock_delta);
-		if (rc == 0) {
-			/* fixup the monotonic sched clock */
-			sched_clock_base_cc += clock_delta;
-			if (ptff_query(PTFF_QTO) &&
-			    ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
-				/* Update LPAR offset */
-				lpar_offset = qto.tod_epoch_difference;
-			atomic_notifier_call_chain(&s390_epoch_delta_notifier,
-						   0, &clock_delta);
-			stp_sync->fixup_cc = clock_delta;
-			fixup_clock_comparator(clock_delta);
-			rc = chsc_sstpi(stp_page, &stp_info,
-					sizeof(struct stp_sstpi));
-			if (rc == 0 && stp_info.tmd != 2)
-				rc = -EAGAIN;
+	if (xchg(&first, 1) == 0) {
+		/* Wait until all other cpus entered the sync function. */
+		while (atomic_read(&sync->cpus) != 0)
+			cpu_relax();
+		rc = 0;
+		if (stp_info.todoff[0] || stp_info.todoff[1] ||
+		    stp_info.todoff[2] || stp_info.todoff[3] ||
+		    stp_info.tmd != 2) {
+			rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0,
+					&clock_delta);
+			if (rc == 0) {
+				sync->clock_delta = clock_delta;
+				clock_sync_global(clock_delta);
+				rc = chsc_sstpi(stp_page, &stp_info,
+						sizeof(struct stp_sstpi));
+				if (rc == 0 && stp_info.tmd != 2)
+					rc = -EAGAIN;
+			}
 		}
+		sync->in_sync = rc ? -EAGAIN : 1;
+		xchg(&first, 0);
+	} else {
+		/* Slave */
+		atomic_dec(&sync->cpus);
+		/* Wait for in_sync to be set. */
+		while (READ_ONCE(sync->in_sync) == 0)
+			__udelay(1);
 	}
-	if (rc) {
+	if (sync->in_sync != 1)
+		/* Didn't work. Clear per-cpu in sync bit again. */
 		disable_sync_clock(NULL);
-		stp_sync->in_sync = -EAGAIN;
-	} else
-		stp_sync->in_sync = 1;
-	xchg(&first, 0);
+	/* Apply clock delta to per-CPU fields of this CPU. */
+	clock_sync_local(sync->clock_delta);
+
 	return 0;
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index e959c02e0cac..93dcbae1e98d 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -7,6 +7,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/workqueue.h>
+#include <linux/bootmem.h>
 #include <linux/cpuset.h>
 #include <linux/device.h>
 #include <linux/export.h>
@@ -41,15 +42,17 @@ static bool topology_enabled = true;
 static DECLARE_WORK(topology_work, topology_work_fn);
 
 /*
- * Socket/Book linked lists and per_cpu(cpu_topology) updates are
+ * Socket/Book linked lists and cpu_topology updates are
  * protected by "sched_domains_mutex".
  */
 static struct mask_info socket_info;
 static struct mask_info book_info;
 static struct mask_info drawer_info;
 
-DEFINE_PER_CPU(struct cpu_topology_s390, cpu_topology);
-EXPORT_PER_CPU_SYMBOL_GPL(cpu_topology);
+struct cpu_topology_s390 cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+cpumask_t cpus_with_topology;
 
 static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
@@ -97,7 +100,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core,
 		if (lcpu < 0)
 			continue;
 		for (i = 0; i <= smp_cpu_mtid; i++) {
-			topo = &per_cpu(cpu_topology, lcpu + i);
+			topo = &cpu_topology[lcpu + i];
 			topo->drawer_id = drawer->id;
 			topo->book_id = book->id;
 			topo->socket_id = socket->id;
@@ -106,6 +109,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core,
 			cpumask_set_cpu(lcpu + i, &drawer->mask);
 			cpumask_set_cpu(lcpu + i, &book->mask);
 			cpumask_set_cpu(lcpu + i, &socket->mask);
+			cpumask_set_cpu(lcpu + i, &cpus_with_topology);
 			smp_cpu_set_polarization(lcpu + i, tl_core->pp);
 		}
 	}
@@ -220,7 +224,7 @@ static void update_cpu_masks(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		topo = &per_cpu(cpu_topology, cpu);
+		topo = &cpu_topology[cpu];
 		topo->thread_mask = cpu_thread_map(cpu);
 		topo->core_mask = cpu_group_map(&socket_info, cpu);
 		topo->book_mask = cpu_group_map(&book_info, cpu);
@@ -231,6 +235,8 @@ static void update_cpu_masks(void)
 			topo->socket_id = cpu;
 			topo->book_id = cpu;
 			topo->drawer_id = cpu;
+			if (cpu_present(cpu))
+				cpumask_set_cpu(cpu, &cpus_with_topology);
 		}
 	}
 	numa_update_cpu_topology();
@@ -241,12 +247,12 @@ void store_topology(struct sysinfo_15_1_x *info)
 	stsi(info, 15, 1, min(topology_max_mnest, 4));
 }
 
-int arch_update_cpu_topology(void)
+static int __arch_update_cpu_topology(void)
 {
 	struct sysinfo_15_1_x *info = tl_info;
-	struct device *dev;
-	int cpu, rc = 0;
+	int rc = 0;
 
+	cpumask_clear(&cpus_with_topology);
 	if (MACHINE_HAS_TOPOLOGY) {
 		rc = 1;
 		store_topology(info);
@@ -255,6 +261,15 @@ int arch_update_cpu_topology(void)
 	update_cpu_masks();
 	if (!MACHINE_HAS_TOPOLOGY)
 		topology_update_polarization_simple();
+	return rc;
+}
+
+int arch_update_cpu_topology(void)
+{
+	struct device *dev;
+	int cpu, rc;
+
+	rc = __arch_update_cpu_topology();
 	for_each_online_cpu(cpu) {
 		dev = get_cpu_device(cpu);
 		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
@@ -394,23 +409,23 @@ int topology_cpu_init(struct cpu *cpu)
 
 static const struct cpumask *cpu_thread_mask(int cpu)
 {
-	return &per_cpu(cpu_topology, cpu).thread_mask;
+	return &cpu_topology[cpu].thread_mask;
 }
 
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	return &per_cpu(cpu_topology, cpu).core_mask;
+	return &cpu_topology[cpu].core_mask;
 }
 
 static const struct cpumask *cpu_book_mask(int cpu)
 {
-	return &per_cpu(cpu_topology, cpu).book_mask;
+	return &cpu_topology[cpu].book_mask;
 }
 
 static const struct cpumask *cpu_drawer_mask(int cpu)
 {
-	return &per_cpu(cpu_topology, cpu).drawer_mask;
+	return &cpu_topology[cpu].drawer_mask;
 }
 
 static int __init early_parse_topology(char *p)
@@ -438,19 +453,20 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
 		nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
 	nr_masks = max(nr_masks, 1);
 	for (i = 0; i < nr_masks; i++) {
-		mask->next = kzalloc(sizeof(*mask->next), GFP_KERNEL);
+		mask->next = memblock_virt_alloc(sizeof(*mask->next), 8);
 		mask = mask->next;
 	}
 }
 
-static int __init s390_topology_init(void)
+void __init topology_init_early(void)
 {
 	struct sysinfo_15_1_x *info;
 	int i;
 
+	set_sched_topology(s390_topology);
 	if (!MACHINE_HAS_TOPOLOGY)
-		return 0;
-	tl_info = (struct sysinfo_15_1_x *)__get_free_page(GFP_KERNEL);
+		goto out;
+	tl_info = memblock_virt_alloc(sizeof(*tl_info), PAGE_SIZE);
 	info = tl_info;
 	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
@@ -460,10 +476,9 @@ static int __init s390_topology_init(void)
 	alloc_masks(info, &socket_info, 1);
 	alloc_masks(info, &book_info, 2);
 	alloc_masks(info, &drawer_info, 3);
-	set_sched_topology(s390_topology);
-	return 0;
+out:
+	__arch_update_cpu_topology();
 }
-early_initcall(s390_topology_init);
 
 static int __init topology_init(void)
 {
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index 5eec9afbb5b5..a5769b83d90e 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -99,8 +99,27 @@ __kernel_clock_gettime:
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	11b
 	stcke	0(%r15)				/* Store TOD clock */
-	lm	%r0,%r1,1(%r15)
-	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	lm	%r0,%r1,__VDSO_TS_END(%r5)	/* TOD steering end time */
+	s	%r0,1(%r15)			/* no - ts_steering_end */
+	sl	%r1,5(%r15)
+	brc	3,22f
+	ahi	%r0,-1
+22:	ltr	%r0,%r0				/* past end of steering? */
+	jm	24f
+	srdl	%r0,15				/* 1 per 2^16 */
+	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
+	jz	23f
+	lcr	%r0,%r0				/* negative TOD offset */
+	lcr	%r1,%r1
+	je	23f
+	ahi	%r0,-1
+23:	a	%r0,1(%r15)			/* add TOD timestamp */
+	al	%r1,5(%r15)
+	brc	12,25f
+	ahi	%r0,1
+	j	25f
+24:	lm	%r0,%r1,1(%r15)			/* load TOD timestamp */
+25:	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
 	ahi	%r0,-1
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index 719de6186b20..63b86dceb0bf 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -31,8 +31,27 @@ __kernel_gettimeofday:
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	1b
 	stcke	0(%r15)				/* Store TOD clock */
-	lm	%r0,%r1,1(%r15)
-	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	lm	%r0,%r1,__VDSO_TS_END(%r5)	/* TOD steering end time */
+	s	%r0,1(%r15)
+	sl	%r1,5(%r15)
+	brc	3,14f
+	ahi	%r0,-1
+14:	ltr	%r0,%r0				/* past end of steering? */
+	jm	16f
+	srdl	%r0,15				/* 1 per 2^16 */
+	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
+	jz	15f
+	lcr	%r0,%r0				/* negative TOD offset */
+	lcr	%r1,%r1
+	je	15f
+	ahi	%r0,-1
+15:	a	%r0,1(%r15)			/* add TOD timestamp */
+	al	%r1,5(%r15)
+	brc	12,17f
+	ahi	%r0,1
+	j	17f
+16:	lm	%r0,%r1,1(%r15)			/* load TOD timestamp */
+17:	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
 	ahi	%r0,-1
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 61541fb93dc6..9c3b12626dba 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -83,8 +83,17 @@ __kernel_clock_gettime:
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	5b
 	stcke	0(%r15)				/* Store TOD clock */
-	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
 	lg	%r1,1(%r15)
+	lg	%r0,__VDSO_TS_END(%r5)		/* TOD steering end time */
+	slgr	%r0,%r1				/* now - ts_steering_end */
+	ltgr	%r0,%r0				/* past end of steering ? */
+	jm	17f
+	srlg	%r0,%r0,15			/* 1 per 2^16 */
+	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
+	jz	18f
+	lcgr	%r0,%r0				/* negative TOD offset */
+18:	algr	%r1,%r0				/* add steering offset */
+17:	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index 6ce46707663c..b02e62f3bc12 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -31,7 +31,16 @@ __kernel_gettimeofday:
 	jnz	0b
 	stcke	0(%r15)				/* Store TOD clock */
 	lg	%r1,1(%r15)
-	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	lg	%r0,__VDSO_TS_END(%r5)		/* TOD steering end time */
+	slgr	%r0,%r1				/* now - ts_steering_end */
+	ltgr	%r0,%r0				/* past end of steering ? */
+	jm	6f
+	srlg	%r0,%r0,15			/* 1 per 2^16 */
+	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
+	jz	7f
+	lcgr	%r0,%r0				/* negative TOD offset */
+7:	algr	%r1,%r0				/* add steering offset */
+6:	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 1bd5dde2d5a9..6b246aadf311 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -96,7 +96,6 @@ static void update_mt_scaling(void)
  */
 static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 {
-	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, clock, user, system, steal;
 	u64 user_scaled, system_scaled;
 
@@ -119,13 +118,13 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
-	user = S390_lowcore.user_timer - ti->user_timer;
+	user = S390_lowcore.user_timer - tsk->thread.user_timer;
 	S390_lowcore.steal_timer -= user;
-	ti->user_timer = S390_lowcore.user_timer;
+	tsk->thread.user_timer = S390_lowcore.user_timer;
 
-	system = S390_lowcore.system_timer - ti->system_timer;
+	system = S390_lowcore.system_timer - tsk->thread.system_timer;
 	S390_lowcore.steal_timer -= system;
-	ti->system_timer = S390_lowcore.system_timer;
+	tsk->thread.system_timer = S390_lowcore.system_timer;
 
 	user_scaled = user;
 	system_scaled = system;
@@ -153,15 +152,11 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 
 void vtime_task_switch(struct task_struct *prev)
 {
-	struct thread_info *ti;
-
 	do_account_vtime(prev, 0);
-	ti = task_thread_info(prev);
-	ti->user_timer = S390_lowcore.user_timer;
-	ti->system_timer = S390_lowcore.system_timer;
-	ti = task_thread_info(current);
-	S390_lowcore.user_timer = ti->user_timer;
-	S390_lowcore.system_timer = ti->system_timer;
+	prev->thread.user_timer = S390_lowcore.user_timer;
+	prev->thread.system_timer = S390_lowcore.system_timer;
+	S390_lowcore.user_timer = current->thread.user_timer;
+	S390_lowcore.system_timer = current->thread.system_timer;
 }
 
 /*
@@ -181,7 +176,6 @@ void vtime_account_user(struct task_struct *tsk)
  */
 void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, system, system_scaled;
 
 	timer = S390_lowcore.last_update_timer;
@@ -193,9 +187,9 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
-	system = S390_lowcore.system_timer - ti->system_timer;
+	system = S390_lowcore.system_timer - tsk->thread.system_timer;
 	S390_lowcore.steal_timer -= system;
-	ti->system_timer = S390_lowcore.system_timer;
+	tsk->thread.system_timer = S390_lowcore.system_timer;
 	system_scaled = system;
 	/* Do MT utilization scaling */
 	if (smp_cpu_mtid) {
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index be9fa65bfac4..7422a706f310 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -8,6 +8,45 @@
 #include <asm/export.h>
 
 /*
+ * void *memmove(void *dest, const void *src, size_t n)
+ */
+ENTRY(memmove)
+	ltgr	%r4,%r4
+	lgr	%r1,%r2
+	bzr	%r14
+	clgr	%r2,%r3
+	jnh	.Lmemmove_forward
+	la	%r5,0(%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:
+	mvc	0(256,%r1),0(%r3)
+	la	%r1,256(%r1)
+	la	%r3,256(%r3)
+	brctg	%r0,.Lmemmove_loop
+.Lmemmove_rest:
+	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
+	ic	%r0,0(%r4,%r3)
+	stc	%r0,0(%r4,%r1)
+	br	%r14
+.Lmemmove_mvc:
+	mvc	0(1,%r1),0(%r3)
+EXPORT_SYMBOL(memmove)
+
+/*
  * memset implementation
  *
  * This code corresponds to the C construct below. We do distinguish
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 661d9fe63c43..d1faae5cdd12 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -733,6 +733,7 @@ block:
 			 * return to userspace schedule() to block. */
 			__set_current_state(TASK_UNINTERRUPTIBLE);
 			set_tsk_need_resched(tsk);
+			set_preempt_need_resched();
 		}
 	}
 out:
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 1848292766ef..45becc8a44ec 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -34,7 +34,7 @@ static void __ref *vmem_alloc_pages(unsigned int order)
 
 	if (slab_is_available())
 		return (void *)__get_free_pages(GFP_KERNEL, order);
-	return alloc_bootmem_align(size, size);
+	return (void *) memblock_alloc(size, size);
 }
 
 static inline pud_t *vmem_pud_alloc(void)
@@ -61,17 +61,16 @@ pmd_t *vmem_pmd_alloc(void)
 
 pte_t __ref *vmem_pte_alloc(void)
 {
+	unsigned long size = PTRS_PER_PTE * sizeof(pte_t);
 	pte_t *pte;
 
 	if (slab_is_available())
 		pte = (pte_t *) page_table_alloc(&init_mm);
 	else
-		pte = alloc_bootmem_align(PTRS_PER_PTE * sizeof(pte_t),
-					  PTRS_PER_PTE * sizeof(pte_t));
+		pte = (pte_t *) memblock_alloc(size, size);
 	if (!pte)
 		return NULL;
-	clear_table((unsigned long *) pte, _PAGE_INVALID,
-		    PTRS_PER_PTE * sizeof(pte_t));
+	clear_table((unsigned long *) pte, _PAGE_INVALID, size);
 	return pte;
 }
 
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 37e0bb835516..cfd08384f0ab 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/cpumask.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 #include <linux/node.h>
 #include <linux/memory.h>
 #include <linux/slab.h>
@@ -307,13 +308,11 @@ fail:
 /*
  * Allocate and initialize core to node mapping
  */
-static void create_core_to_node_map(void)
+static void __ref create_core_to_node_map(void)
 {
 	int i;
 
-	emu_cores = kzalloc(sizeof(*emu_cores), GFP_KERNEL);
-	if (emu_cores == NULL)
-		panic("Could not allocate cores to node memory");
+	emu_cores = memblock_virt_alloc(sizeof(*emu_cores), 8);
 	for (i = 0; i < ARRAY_SIZE(emu_cores->to_node_id); i++)
 		emu_cores->to_node_id[i] = NODE_ID_FREE;
 }
@@ -354,13 +353,13 @@ static struct toptree *toptree_from_topology(void)
 
 	phys = toptree_new(TOPTREE_ID_PHYS, 1);
 
-	for_each_online_cpu(cpu) {
-		top = &per_cpu(cpu_topology, cpu);
+	for_each_cpu(cpu, &cpus_with_topology) {
+		top = &cpu_topology[cpu];
 		node = toptree_get_child(phys, 0);
 		drawer = toptree_get_child(node, top->drawer_id);
 		book = toptree_get_child(drawer, top->book_id);
 		mc = toptree_get_child(book, top->socket_id);
-		core = toptree_get_child(mc, top->core_id);
+		core = toptree_get_child(mc, smp_get_base_cpu(cpu));
 		if (!drawer || !book || !mc || !core)
 			panic("NUMA emulation could not allocate memory");
 		cpumask_set_cpu(cpu, &core->mask);
@@ -378,7 +377,7 @@ static void topology_add_core(struct toptree *core)
 	int cpu;
 
 	for_each_cpu(cpu, &core->mask) {
-		top = &per_cpu(cpu_topology, cpu);
+		top = &cpu_topology[cpu];
 		cpumask_copy(&top->thread_mask, &core->mask);
 		cpumask_copy(&top->core_mask, &core_mc(core)->mask);
 		cpumask_copy(&top->book_mask, &core_book(core)->mask);
@@ -425,6 +424,27 @@ static void print_node_to_core_map(void)
 	}
 }
 
+static void pin_all_possible_cpus(void)
+{
+	int core_id, node_id, cpu;
+	static int initialized;
+
+	if (initialized)
+		return;
+	print_node_to_core_map();
+	node_id = 0;
+	for_each_possible_cpu(cpu) {
+		core_id = smp_get_base_cpu(cpu);
+		if (emu_cores->to_node_id[core_id] != NODE_ID_FREE)
+			continue;
+		pin_core_to_node(core_id, node_id);
+		cpu_topology[cpu].node_id = node_id;
+		node_id = (node_id + 1) % emu_nodes;
+	}
+	print_node_to_core_map();
+	initialized = 1;
+}
+
 /*
  * Transfer physical topology into a NUMA topology and modify CPU masks
  * according to the NUMA topology.
@@ -442,7 +462,7 @@ static void emu_update_cpu_topology(void)
 	toptree_free(phys);
 	toptree_to_topology(numa);
 	toptree_free(numa);
-	print_node_to_core_map();
+	pin_all_possible_cpus();
 }
 
 /*
diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c
index 902d350d859a..26f622b1cd11 100644
--- a/arch/s390/numa/toptree.c
+++ b/arch/s390/numa/toptree.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/bootmem.h>
 #include <linux/cpumask.h>
 #include <linux/list.h>
 #include <linux/list_sort.h>
@@ -25,10 +26,14 @@
  * RETURNS:
  * Pointer to the new tree node or NULL on error
  */
-struct toptree *toptree_alloc(int level, int id)
+struct toptree __ref *toptree_alloc(int level, int id)
 {
-	struct toptree *res = kzalloc(sizeof(struct toptree), GFP_KERNEL);
+	struct toptree *res;
 
+	if (slab_is_available())
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+	else
+		res = memblock_virt_alloc(sizeof(*res), 8);
 	if (!res)
 		return res;
 
@@ -65,7 +70,7 @@ static void toptree_remove(struct toptree *cand)
  * cleanly using toptree_remove. Possible children are freed
  * recursively. In the end @cand itself is freed.
  */
-void toptree_free(struct toptree *cand)
+void __ref toptree_free(struct toptree *cand)
 {
 	struct toptree *child, *tmp;
 
@@ -73,7 +78,10 @@ void toptree_free(struct toptree *cand)
 		toptree_remove(cand);
 	toptree_for_each_child_safe(child, tmp, cand)
 		toptree_free(child);
-	kfree(cand);
+	if (slab_is_available())
+		kfree(cand);
+	else
+		memblock_free_early((unsigned long)cand, sizeof(*cand));
 }
 
 /**
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 15ffc19c8c0c..64e1734bebb7 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -722,6 +722,11 @@ struct dev_pm_ops pcibios_pm_ops = {
 
 static int zpci_alloc_domain(struct zpci_dev *zdev)
 {
+	if (zpci_unique_uid) {
+		zdev->domain = (u16) zdev->uid;
+		return 0;
+	}
+
 	spin_lock(&zpci_domain_lock);
 	zdev->domain = find_first_zero_bit(zpci_domain, ZPCI_NR_DEVICES);
 	if (zdev->domain == ZPCI_NR_DEVICES) {
@@ -735,6 +740,9 @@ static int zpci_alloc_domain(struct zpci_dev *zdev)
 
 static void zpci_free_domain(struct zpci_dev *zdev)
 {
+	if (zpci_unique_uid)
+		return;
+
 	spin_lock(&zpci_domain_lock);
 	clear_bit(zdev->domain, zpci_domain);
 	spin_unlock(&zpci_domain_lock);
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 1a4512c8544a..e3ef63b36b5a 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -22,6 +22,8 @@
 #include <asm/clp.h>
 #include <uapi/asm/clp.h>
 
+bool zpci_unique_uid;
+
 static inline void zpci_err_clp(unsigned int rsp, int rc)
 {
 	struct {
@@ -315,6 +317,7 @@ static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
 			goto out;
 		}
 
+		zpci_unique_uid = rrb->response.uid_checking;
 		WARN_ON_ONCE(rrb->response.entry_size !=
 			sizeof(struct clp_fh_list_entry));
 
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 38993b156924..c2f786f0ea06 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -69,7 +69,7 @@ static void pci_sw_counter_show(struct seq_file *m)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
-		seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
+		seq_printf(m, "%26s:\t%lu\n", pci_sw_names[i],
 			   atomic64_read(counter));
 }
 
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 6b2f72f523b9..1d7a9c71944a 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -181,14 +181,17 @@ static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 	/*
 	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
 	 * translations when previously invalid translation-table entries are
-	 * validated. With lazy unmap, it also is skipped for previously valid
+	 * validated. With lazy unmap, rpcit is skipped for previously valid
 	 * entries, but a global rpcit is then required before any address can
 	 * be re-used, i.e. after each iommu bitmap wrap-around.
 	 */
-	if (!zdev->tlb_refresh &&
-			(!s390_iommu_strict ||
-			((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)))
-		return 0;
+	if ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID) {
+		if (!zdev->tlb_refresh)
+			return 0;
+	} else {
+		if (!s390_iommu_strict)
+			return 0;
+	}
 
 	return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
 				  PAGE_ALIGN(size));
@@ -257,7 +260,7 @@ static dma_addr_t dma_alloc_address(struct device *dev, int size)
 	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
 	offset = __dma_alloc_iommu(dev, zdev->next_bit, size);
 	if (offset == -1) {
-		if (!zdev->tlb_refresh && !s390_iommu_strict) {
+		if (!s390_iommu_strict) {
 			/* global flush before DMA addresses are reused */
 			if (zpci_refresh_global(zdev))
 				goto out_error;
@@ -292,7 +295,7 @@ static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
 	if (!zdev->iommu_bitmap)
 		goto out;
 
-	if (zdev->tlb_refresh || s390_iommu_strict)
+	if (s390_iommu_strict)
 		bitmap_clear(zdev->iommu_bitmap, offset, size);
 	else
 		bitmap_set(zdev->lazy_bitmap, offset, size);
@@ -388,8 +391,6 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 		return NULL;
 
 	pa = page_to_phys(page);
-	memset((void *) pa, 0, size);
-
 	map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, 0);
 	if (dma_mapping_error(dev, map)) {
 		free_pages(pa, get_order(size));
@@ -419,6 +420,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 			     size_t size, dma_addr_t *handle,
 			     enum dma_data_direction dir)
 {
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	dma_addr_t dma_addr_base, dma_addr;
 	int flags = ZPCI_PTE_VALID;
@@ -426,8 +428,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long pa = 0;
 	int ret;
 
-	size = PAGE_ALIGN(size);
-	dma_addr_base = dma_alloc_address(dev, size >> PAGE_SHIFT);
+	dma_addr_base = dma_alloc_address(dev, nr_pages);
 	if (dma_addr_base == DMA_ERROR_CODE)
 		return -ENOMEM;
 
@@ -436,26 +437,27 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		flags |= ZPCI_TABLE_PROTECTED;
 
 	for (s = sg; dma_addr < dma_addr_base + size; s = sg_next(s)) {
-		pa = page_to_phys(sg_page(s)) + s->offset;
-		ret = __dma_update_trans(zdev, pa, dma_addr, s->length, flags);
+		pa = page_to_phys(sg_page(s));
+		ret = __dma_update_trans(zdev, pa, dma_addr,
+					 s->offset + s->length, flags);
 		if (ret)
 			goto unmap;
 
-		dma_addr += s->length;
+		dma_addr += s->offset + s->length;
 	}
 	ret = __dma_purge_tlb(zdev, dma_addr_base, size, flags);
 	if (ret)
 		goto unmap;
 
 	*handle = dma_addr_base;
-	atomic64_add(size >> PAGE_SHIFT, &zdev->mapped_pages);
+	atomic64_add(nr_pages, &zdev->mapped_pages);
 
 	return ret;
 
 unmap:
 	dma_update_trans(zdev, 0, dma_addr_base, dma_addr - dma_addr_base,
 			 ZPCI_PTE_INVALID);
-	dma_free_address(dev, dma_addr_base, size >> PAGE_SHIFT);
+	dma_free_address(dev, dma_addr_base, nr_pages);
 	zpci_err("map error:\n");
 	zpci_err_dma(ret, pa);
 	return ret;
@@ -564,7 +566,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		rc = -ENOMEM;
 		goto free_dma_table;
 	}
-	if (!zdev->tlb_refresh && !s390_iommu_strict) {
+	if (!s390_iommu_strict) {
 		zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8);
 		if (!zdev->lazy_bitmap) {
 			rc = -ENOMEM;
diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile
index 6d9814c9df2b..4b5e1e499527 100644
--- a/arch/s390/tools/Makefile
+++ b/arch/s390/tools/Makefile
@@ -9,7 +9,5 @@ define filechk_facilities.h
 	$(obj)/gen_facilities
 endef
 
-$(obj)/gen_facilities.o: $(srctree)/arch/s390/tools/gen_facilities.c
-
 include/generated/facilities.h: $(obj)/gen_facilities FORCE
 	$(call filechk,facilities.h)
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index fe4e6c910dd7..8cc53b1e6d03 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -7,13 +7,83 @@
  *
  */
 
-#define S390_GEN_FACILITIES_C
-
 #include <strings.h>
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
-#include <asm/facilities_src.h>
+
+struct facility_def {
+	char *name;
+	int *bits;
+};
+
+static struct facility_def facility_defs[] = {
+	{
+		/*
+		 * FACILITIES_ALS contains the list of facilities that are
+		 * required to run a kernel that is compiled e.g. with
+		 * -march=<machine>.
+		 */
+		.name = "FACILITIES_ALS",
+		.bits = (int[]){
+#ifdef CONFIG_HAVE_MARCH_Z900_FEATURES
+			0,  /* N3 instructions */
+			1,  /* z/Arch mode installed */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
+			18, /* long displacement facility */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
+			7,  /* stfle */
+			17, /* message security assist */
+			21, /* extended-immediate facility */
+			25, /* store clock fast */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+			27, /* mvcos */
+			32, /* compare and swap and store */
+			33, /* compare and swap and store 2 */
+			34, /* general extension facility */
+			35, /* execute extensions */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+			45, /* fast-BCR, etc. */
+#endif
+#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
+			49, /* misc-instruction-extensions */
+			52, /* interlocked facility 2 */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z13_FEATURES
+			53, /* load-and-zero-rightmost-byte, etc. */
+#endif
+			-1 /* END */
+		}
+	},
+	{
+		.name = "FACILITIES_KVM",
+		.bits = (int[]){
+			0,  /* N3 instructions */
+			1,  /* z/Arch mode installed */
+			2,  /* z/Arch mode active */
+			3,  /* DAT-enhancement */
+			4,  /* idte segment table */
+			5,  /* idte region table */
+			6,  /* ASN-and-LX reuse */
+			7,  /* stfle */
+			8,  /* enhanced-DAT 1 */
+			9,  /* sense-running-status */
+			10, /* conditional sske */
+			13, /* ipte-range */
+			14, /* nonquiescing key-setting */
+			73, /* transactional execution */
+			75, /* access-exception-fetch/store indication */
+			76, /* msa extension 3 */
+			77, /* msa extension 4 */
+			78, /* enhanced-DAT 2 */
+			-1  /* END */
+		}
+	},
+};
 
 static void print_facility_list(struct facility_def *def)
 {