Merge branch 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6

* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (21 commits)
  [S390] use siginfo for sigtrap signals
  [S390] dasd: add enhanced DASD statistics interface
  [S390] kvm: make sigp emerg smp capable
  [S390] disable cpu measurement alerts on a dying cpu
  [S390] initial cr0 bits
  [S390] iucv cr0 enablement bit
  [S390] race safe external interrupt registration
  [S390] remove tape block docu
  [S390] ap: toleration support for ap device type 10
  [S390] cleanup program check handler prototypes
  [S390] remove kvm mmu reload on s390
  [S390] Use gmap translation for accessing guest memory
  [S390] use gmap address spaces for kvm guest images
  [S390] kvm guest address space mapping
  [S390] fix s390 assembler code alignments
  [S390] move sie code to entry.S
  [S390] kvm: handle tprot intercepts
  [S390] qdio: clear shared DSCI before scheduling the queue handler
  [S390] reference bit testing for unmapped pages
  [S390] irqs: Do not trace arch_local_{*,irq_*} functions
  ...

60 files changed, 2091 insertions, 1280 deletions

diff --git a/Documentation/s390/TAPE b/Documentation/s390/TAPE
deleted file mode 100644
index c639aa5603f..00000000000
--- a/Documentation/s390/TAPE
+++ /dev/null
@@ -1,122 +0,0 @@
-Channel attached Tape device driver 
-
------------------------------WARNING-----------------------------------------
-This driver is considered to be EXPERIMENTAL. Do NOT use it in 
-production environments. Feel free to test it and report problems back to us. 
------------------------------------------------------------------------------
-
-The LINUX for zSeries tape device driver manages channel attached tape drives 
-which are compatible to IBM 3480 or IBM 3490 magnetic tape subsystems. This 
-includes various models of these devices (for example the 3490E). 
-
-
-Tape driver features 
-
-The device driver supports a maximum of 128 tape devices. 
-No official LINUX device major number is assigned to the zSeries tape device 
-driver. It allocates major numbers dynamically and reports them on system 
-startup. 
-Typically it will get major number 254 for both the character device front-end 
-and the block device front-end. 
-
-The tape device driver needs no kernel parameters. All supported devices 
-present are detected on driver initialization at system startup or module load.
-The devices detected are ordered by their subchannel numbers. The device with 
-the lowest subchannel number becomes device 0, the next one will be device 1 
-and so on. 
-
-
-Tape character device front-end 
-
-The usual way to read or write to the tape device is through the character 
-device front-end. The zSeries tape device driver provides two character devices
-for each physical device -- the first of these will rewind automatically when 
-it is closed, the second will not rewind automatically. 
-
-The character device nodes are named /dev/rtibm0 (rewinding) and /dev/ntibm0 
-(non-rewinding) for the first device, /dev/rtibm1 and /dev/ntibm1 for the 
-second, and so on. 
-
-The character device front-end can be used as any other LINUX tape device. You 
-can write to it and read from it using LINUX facilities such as GNU tar. The 
-tool mt can be used to perform control operations, such as rewinding the tape 
-or skipping a file. 
-
-Most LINUX tape software should work with either tape character device. 
-
-
-Tape block device front-end 
-
-The tape device may also be accessed as a block device in read-only mode. 
-This could be used for software installation in the same way as it is used with 
-other operation systems on the zSeries platform (and most LINUX 
-distributions are shipped on compact disk using ISO9660 filesystems). 
-
-One block device node is provided for each physical device. These are named 
-/dev/btibm0 for the first device, /dev/btibm1 for the second and so on. 
-You should only use the ISO9660 filesystem on LINUX for zSeries tapes because 
-the physical tape devices cannot perform fast seeks and the ISO9660 system is 
-optimized for this situation. 
-
-
-Tape block device example 
-
-In this example a tape with an ISO9660 filesystem is created using the first 
-tape device. ISO9660 filesystem support must be built into your system kernel
-for this. 
-The mt command is used to issue tape commands and the mkisofs command to 
-create an ISO9660 filesystem: 
-
-- create a LINUX directory (somedir) with the contents of the filesystem 
-     mkdir somedir
-     cp contents somedir 
-
-- insert a tape 
-
-- ensure the tape is at the beginning 
-     mt -f /dev/ntibm0 rewind 
-
-- set the blocksize of the character driver. The blocksize 2048 bytes
-  is commonly used on ISO9660 CD-Roms
-     mt -f /dev/ntibm0 setblk 2048 
-
-- write the filesystem to the character device driver 
-     mkisofs -o /dev/ntibm0 somedir 
-
-- rewind the tape again 
-     mt -f /dev/ntibm0 rewind 
-
-- Now you can mount your new filesystem as a block device: 
-     mount -t iso9660 -o ro,block=2048 /dev/btibm0 /mnt 
-
-TODO List 
-
-   - Driver has to be stabilized still
-
-BUGS 
-
-This driver is considered BETA, which means some weaknesses may still
-be in it.
-If an error occurs which cannot be handled by the code you will get a 
-sense-data dump.In that case please do the following: 
-
-1. set the tape driver debug level to maximum: 
-     echo 6 >/proc/s390dbf/tape/level 
-
-2. re-perform the actions which produced the bug. (Hopefully the bug will 
-   reappear.) 
-
-3. get a snapshot from the debug-feature: 
-     cat /proc/s390dbf/tape/hex_ascii >somefile 
-
-4. Now put the snapshot together with a detailed description of the situation 
-   that led to the bug: 
- - Which tool did you use? 
- - Which hardware do you have? 
- - Was your tape unit online? 
- - Is it a shared tape unit? 
-
-5. Send an email with your bug report to: 
-     mailto:Linux390@de.ibm.com 
-
-
diff --git a/arch/s390/boot/compressed/head31.S b/arch/s390/boot/compressed/head31.S
index 2a5523a32bc..e8c9e18b803 100644
--- a/arch/s390/boot/compressed/head31.S
+++ b/arch/s390/boot/compressed/head31.S
@@ -7,14 +7,14 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 #include "sizes.h"
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack
diff --git a/arch/s390/boot/compressed/head64.S b/arch/s390/boot/compressed/head64.S
index 2982cb14055..f86a4eef28a 100644
--- a/arch/s390/boot/compressed/head64.S
+++ b/arch/s390/boot/compressed/head64.S
@@ -7,14 +7,14 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 #include "sizes.h"
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 865d6d891ac..38fdf451feb 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -29,42 +29,42 @@
 })
 
 /* set system mask. */
-static inline void __arch_local_irq_ssm(unsigned long flags)
+static inline notrace void __arch_local_irq_ssm(unsigned long flags)
 {
 	asm volatile("ssm   %0" : : "Q" (flags) : "memory");
 }
 
-static inline unsigned long arch_local_save_flags(void)
+static inline notrace unsigned long arch_local_save_flags(void)
 {
 	return __arch_local_irq_stosm(0x00);
 }
 
-static inline unsigned long arch_local_irq_save(void)
+static inline notrace unsigned long arch_local_irq_save(void)
 {
 	return __arch_local_irq_stnsm(0xfc);
 }
 
-static inline void arch_local_irq_disable(void)
+static inline notrace void arch_local_irq_disable(void)
 {
 	arch_local_irq_save();
 }
 
-static inline void arch_local_irq_enable(void)
+static inline notrace void arch_local_irq_enable(void)
 {
 	__arch_local_irq_stosm(0x03);
 }
 
-static inline void arch_local_irq_restore(unsigned long flags)
+static inline notrace void arch_local_irq_restore(unsigned long flags)
 {
 	__arch_local_irq_ssm(flags);
 }
 
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
+static inline notrace bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & (3UL << (BITS_PER_LONG - 8)));
 }
 
-static inline bool arch_irqs_disabled(void)
+static inline notrace bool arch_irqs_disabled(void)
 {
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index cef7dbf69df..00ff00dfb24 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -93,9 +93,7 @@ struct kvm_s390_sie_block {
 	__u32	scaol;			/* 0x0064 */
 	__u8	reserved68[4];		/* 0x0068 */
 	__u32	todpr;			/* 0x006c */
-	__u8	reserved70[16];		/* 0x0070 */
-	__u64	gmsor;			/* 0x0080 */
-	__u64	gmslm;			/* 0x0088 */
+	__u8	reserved70[32];		/* 0x0070 */
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
@@ -138,6 +136,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_chsc;
 	u32 instruction_stsi;
 	u32 instruction_stfl;
+	u32 instruction_tprot;
 	u32 instruction_sigp_sense;
 	u32 instruction_sigp_emergency;
 	u32 instruction_sigp_stop;
@@ -175,6 +174,10 @@ struct kvm_s390_prefix_info {
 	__u32 address;
 };
 
+struct kvm_s390_emerg_info {
+	__u16 code;
+};
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -182,6 +185,7 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_io_info io;
 		struct kvm_s390_ext_info ext;
 		struct kvm_s390_pgm_info pgm;
+		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_prefix_info prefix;
 	};
 };
@@ -226,6 +230,7 @@ struct kvm_vcpu_arch {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
+	struct gmap *gmap;
 };
 
 struct kvm_vm_stat {
@@ -236,6 +241,7 @@ struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
+	struct gmap *gmap;
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, unsigned long *);
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 291c2d01c44..fc8a8284778 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -1,6 +1,9 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
-/* Nothing to see here... */
+#include <linux/stringify.h>
+
+#define __ALIGN .align 4, 0x07
+#define __ALIGN_STR __stringify(__ALIGN)
 
 #endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 228cf0b295d..f26280d9e88 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -268,7 +268,7 @@ struct _lowcore {
 	__u64	vdso_per_cpu_data;		/* 0x0358 */
 	__u64	machine_flags;			/* 0x0360 */
 	__u64	ftrace_func;			/* 0x0368 */
-	__u64	sie_hook;			/* 0x0370 */
+	__u64	gmap;				/* 0x0370 */
 	__u64	cmf_hpp;			/* 0x0378 */
 
 	/* Interrupt response block. */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 82d0847896a..4506791adcd 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -6,6 +6,7 @@ typedef struct {
 	unsigned int flush_mm;
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
+	struct list_head gmap_list;
 	unsigned long asce_bits;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
@@ -17,6 +18,7 @@ typedef struct {
 
 #define INIT_MM_CONTEXT(name)						      \
 	.context.list_lock    = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
-	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),
+	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
+	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
 
 #endif
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 38e71ebcd3c..8eef9b5b3cf 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -20,7 +20,7 @@
 unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
 
-unsigned long *page_table_alloc(struct mm_struct *);
+unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
@@ -115,6 +115,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	spin_lock_init(&mm->context.list_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	INIT_LIST_HEAD(&mm->context.gmap_list);
 	return (pgd_t *) crst_table_alloc(mm);
 }
 #define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
@@ -133,8 +134,8 @@ static inline void pmd_populate(struct mm_struct *mm,
 /*
  * page table entry allocation/free routines.
  */
-#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
-#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
+#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
 
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 801fbe1d837..519eb5f187e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -654,6 +654,48 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
+/**
+ * struct gmap_struct - guest address space
+ * @mm: pointer to the parent mm_struct
+ * @table: pointer to the page directory
+ * @crst_list: list of all crst tables used in the guest address space
+ */
+struct gmap {
+	struct list_head list;
+	struct mm_struct *mm;
+	unsigned long *table;
+	struct list_head crst_list;
+};
+
+/**
+ * struct gmap_rmap - reverse mapping for segment table entries
+ * @next: pointer to the next gmap_rmap structure in the list
+ * @entry: pointer to a segment table entry
+ */
+struct gmap_rmap {
+	struct list_head list;
+	unsigned long *entry;
+};
+
+/**
+ * struct gmap_pgtable - gmap information attached to a page table
+ * @vmaddr: address of the 1MB segment in the process virtual memory
+ * @mapper: list of segment table entries maping a page table
+ */
+struct gmap_pgtable {
+	unsigned long vmaddr;
+	struct list_head mapper;
+};
+
+struct gmap *gmap_alloc(struct mm_struct *mm);
+void gmap_free(struct gmap *gmap);
+void gmap_enable(struct gmap *gmap);
+void gmap_disable(struct gmap *gmap);
+int gmap_map_segment(struct gmap *gmap, unsigned long from,
+		     unsigned long to, unsigned long length);
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
+unsigned long gmap_fault(unsigned long address, struct gmap *);
+
 /*
  * Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 1300c302533..55dfcc8bdc0 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -80,6 +80,7 @@ struct thread_struct {
 	mm_segment_t mm_segment;
         unsigned long prot_addr;        /* address of protection-excep.     */
         unsigned int trap_no;
+	unsigned long gmap_addr;	/* address of last gmap fault. */
 	struct per_regs per_user;	/* User specified PER registers */
 	struct per_event per_event;	/* Cause of the last PER trap */
         /* pfault_wait is used to block the process on a pfault event */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index ad1382f7932..1a5dbb6f149 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -94,6 +94,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing active */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
+#define TIF_SIE			12	/* guest execution active */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling
 					   TIF_NEED_RESCHED */
 #define TIF_31BIT		17	/* 32bit process */
@@ -113,6 +114,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SIE		(1<<TIF_SIE)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_FREEZE)
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index b7a4f2eb005..30444538238 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -80,7 +80,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * on all cpus instead of doing a local flush if the mm
 	 * only ran on the local cpu.
 	 */
-	if (MACHINE_HAS_IDTE)
+	if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
 		__tlb_flush_idte((unsigned long) mm->pgd |
 				 mm->context.asce_bits);
 	else
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index edfbd17d708..05d8f38734e 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -151,7 +151,7 @@ int main(void)
 	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
 	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
-	DEFINE(__LC_SIE_HOOK, offsetof(struct _lowcore, sie_hook));
+	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
 #endif /* CONFIG_32BIT */
 	return 0;
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index 15e46ca9433..209938c1dfc 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -6,13 +6,13 @@
  *		 Michael Holzheu <holzheu@de.ibm.com>
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_64BIT
 
-	.globl	s390_base_mcck_handler
-s390_base_mcck_handler:
+ENTRY(s390_base_mcck_handler)
 	basr	%r13,0
 0:	lg	%r15,__LC_PANIC_STACK	# load panic stack
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -26,13 +26,13 @@ s390_base_mcck_handler:
 	lpswe	__LC_MCK_OLD_PSW
 
 	.section .bss
+	.align 8
 	.globl	s390_base_mcck_handler_fn
 s390_base_mcck_handler_fn:
 	.quad	0
 	.previous
 
-	.globl	s390_base_ext_handler
-s390_base_ext_handler:
+ENTRY(s390_base_ext_handler)
 	stmg	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -46,13 +46,13 @@ s390_base_ext_handler:
 	lpswe	__LC_EXT_OLD_PSW
 
 	.section .bss
+	.align 8
 	.globl s390_base_ext_handler_fn
 s390_base_ext_handler_fn:
 	.quad	0
 	.previous
 
-	.globl	s390_base_pgm_handler
-s390_base_pgm_handler:
+ENTRY(s390_base_pgm_handler)
 	stmg	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -70,6 +70,7 @@ disabled_wait_psw:
 	.quad	0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler
 
 	.section .bss
+	.align 8
 	.globl s390_base_pgm_handler_fn
 s390_base_pgm_handler_fn:
 	.quad	0
@@ -77,8 +78,7 @@ s390_base_pgm_handler_fn:
 
 #else /* CONFIG_64BIT */
 
-	.globl	s390_base_mcck_handler
-s390_base_mcck_handler:
+ENTRY(s390_base_mcck_handler)
 	basr	%r13,0
 0:	l	%r15,__LC_PANIC_STACK	# load panic stack
 	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -93,13 +93,13 @@ s390_base_mcck_handler:
 2:	.long	s390_base_mcck_handler_fn
 
 	.section .bss
+	.align 4
 	.globl	s390_base_mcck_handler_fn
 s390_base_mcck_handler_fn:
 	.long	0
 	.previous
 
-	.globl	s390_base_ext_handler
-s390_base_ext_handler:
+ENTRY(s390_base_ext_handler)
 	stm	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -115,13 +115,13 @@ s390_base_ext_handler:
 2:	.long	s390_base_ext_handler_fn
 
 	.section .bss
+	.align 4
 	.globl	s390_base_ext_handler_fn
 s390_base_ext_handler_fn:
 	.long	0
 	.previous
 
-	.globl	s390_base_pgm_handler
-s390_base_pgm_handler:
+ENTRY(s390_base_pgm_handler)
 	stm	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -142,6 +142,7 @@ disabled_wait_psw:
 	.long	0x000a0000,0x00000000 + s390_base_pgm_handler
 
 	.section .bss
+	.align 4
 	.globl	s390_base_pgm_handler_fn
 s390_base_pgm_handler_fn:
 	.long	0
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 1f5eb789c3a..08ab9aa6a0d 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -7,86 +7,74 @@
 *		Thomas Spatzier (tspat@de.ibm.com)
 */
 
-	.globl	sys32_exit_wrapper
-sys32_exit_wrapper:
+#include <linux/linkage.h>
+
+ENTRY(sys32_exit_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_exit		# branch to sys_exit
 
-	.globl	sys32_read_wrapper
-sys32_read_wrapper:
+ENTRY(sys32_read_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
 	jg	sys32_read		# branch to sys_read
 
-	.globl	sys32_write_wrapper
-sys32_write_wrapper:
+ENTRY(sys32_write_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# size_t
 	jg	sys32_write		# branch to system call
 
-	.globl	sys32_open_wrapper
-sys32_open_wrapper:
+ENTRY(sys32_open_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
 	jg	sys_open		# branch to system call
 
-	.globl	sys32_close_wrapper
-sys32_close_wrapper:
+ENTRY(sys32_close_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_close		# branch to system call
 
-	.globl	sys32_creat_wrapper
-sys32_creat_wrapper:
+ENTRY(sys32_creat_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	jg	sys_creat		# branch to system call
 
-	.globl	sys32_link_wrapper
-sys32_link_wrapper:
+ENTRY(sys32_link_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	jg	sys_link		# branch to system call
 
-	.globl	sys32_unlink_wrapper
-sys32_unlink_wrapper:
+ENTRY(sys32_unlink_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_unlink		# branch to system call
 
-	.globl	sys32_chdir_wrapper
-sys32_chdir_wrapper:
+ENTRY(sys32_chdir_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_chdir		# branch to system call
 
-	.globl	sys32_time_wrapper
-sys32_time_wrapper:
+ENTRY(sys32_time_wrapper)
 	llgtr	%r2,%r2			# int *
 	jg	compat_sys_time		# branch to system call
 
-	.globl	sys32_mknod_wrapper
-sys32_mknod_wrapper:
+ENTRY(sys32_mknod_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	llgfr	%r4,%r4			# dev
 	jg	sys_mknod		# branch to system call
 
-	.globl	sys32_chmod_wrapper
-sys32_chmod_wrapper:
+ENTRY(sys32_chmod_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# mode_t
 	jg	sys_chmod		# branch to system call
 
-	.globl	sys32_lchown16_wrapper
-sys32_lchown16_wrapper:
+ENTRY(sys32_lchown16_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
 	llgfr	%r4,%r4			# __kernel_old_uid_emu31_t
 	jg	sys32_lchown16		# branch to system call
 
-	.globl	sys32_lseek_wrapper
-sys32_lseek_wrapper:
+ENTRY(sys32_lseek_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	lgfr	%r3,%r3			# off_t
 	llgfr	%r4,%r4			# unsigned int
@@ -94,8 +82,7 @@ sys32_lseek_wrapper:
 
 #sys32_getpid_wrapper				# void
 
-	.globl	sys32_mount_wrapper
-sys32_mount_wrapper:
+ENTRY(sys32_mount_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# char *
@@ -103,102 +90,85 @@ sys32_mount_wrapper:
 	llgtr	%r6,%r6			# void *
 	jg	compat_sys_mount	# branch to system call
 
-	.globl	sys32_oldumount_wrapper
-sys32_oldumount_wrapper:
+ENTRY(sys32_oldumount_wrapper)
 	llgtr	%r2,%r2			# char *
 	jg	sys_oldumount		# branch to system call
 
-	.globl	sys32_setuid16_wrapper
-sys32_setuid16_wrapper:
+ENTRY(sys32_setuid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
 	jg	sys32_setuid16		# branch to system call
 
 #sys32_getuid16_wrapper			# void
 
-	.globl	sys32_ptrace_wrapper
-sys32_ptrace_wrapper:
+ENTRY(sys32_ptrace_wrapper)
 	lgfr	%r2,%r2			# long
 	lgfr	%r3,%r3			# long
 	llgtr	%r4,%r4			# long
 	llgfr	%r5,%r5			# long
 	jg	compat_sys_ptrace	# branch to system call
 
-	.globl	sys32_alarm_wrapper
-sys32_alarm_wrapper:
+ENTRY(sys32_alarm_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_alarm		# branch to system call
 
-	.globl	compat_sys_utime_wrapper
-compat_sys_utime_wrapper:
+ENTRY(compat_sys_utime_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct compat_utimbuf *
 	jg	compat_sys_utime	# branch to system call
 
-	.globl	sys32_access_wrapper
-sys32_access_wrapper:
+ENTRY(sys32_access_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	jg	sys_access		# branch to system call
 
-	.globl	sys32_nice_wrapper
-sys32_nice_wrapper:
+ENTRY(sys32_nice_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_nice		# branch to system call
 
 #sys32_sync_wrapper			# void
 
-	.globl	sys32_kill_wrapper
-sys32_kill_wrapper:
+ENTRY(sys32_kill_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	jg	sys_kill		# branch to system call
 
-	.globl	sys32_rename_wrapper
-sys32_rename_wrapper:
+ENTRY(sys32_rename_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	jg	sys_rename		# branch to system call
 
-	.globl	sys32_mkdir_wrapper
-sys32_mkdir_wrapper:
+ENTRY(sys32_mkdir_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	jg	sys_mkdir		# branch to system call
 
-	.globl	sys32_rmdir_wrapper
-sys32_rmdir_wrapper:
+ENTRY(sys32_rmdir_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_rmdir		# branch to system call
 
-	.globl	sys32_dup_wrapper
-sys32_dup_wrapper:
+ENTRY(sys32_dup_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_dup			# branch to system call
 
-	.globl	sys32_pipe_wrapper
-sys32_pipe_wrapper:
+ENTRY(sys32_pipe_wrapper)
 	llgtr	%r2,%r2			# u32 *
 	jg	sys_pipe		# branch to system call
 
-	.globl	compat_sys_times_wrapper
-compat_sys_times_wrapper:
+ENTRY(compat_sys_times_wrapper)
 	llgtr	%r2,%r2			# struct compat_tms *
 	jg	compat_sys_times	# branch to system call
 
-	.globl	sys32_brk_wrapper
-sys32_brk_wrapper:
+ENTRY(sys32_brk_wrapper)
 	llgtr	%r2,%r2			# unsigned long
 	jg	sys_brk			# branch to system call
 
-	.globl	sys32_setgid16_wrapper
-sys32_setgid16_wrapper:
+ENTRY(sys32_setgid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
 	jg	sys32_setgid16		# branch to system call
 
 #sys32_getgid16_wrapper			# void
 
-	.globl sys32_signal_wrapper
-sys32_signal_wrapper:
+ENTRY(sys32_signal_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# __sighandler_t
 	jg	sys_signal
@@ -207,55 +177,46 @@ sys32_signal_wrapper:
 
 #sys32_getegid16_wrapper		# void
 
-	.globl	sys32_acct_wrapper
-sys32_acct_wrapper:
+ENTRY(sys32_acct_wrapper)
 	llgtr	%r2,%r2			# char *
 	jg	sys_acct		# branch to system call
 
-	.globl	sys32_umount_wrapper
-sys32_umount_wrapper:
+ENTRY(sys32_umount_wrapper)
 	llgtr	%r2,%r2			# char *
 	lgfr	%r3,%r3			# int
 	jg	sys_umount		# branch to system call
 
-	.globl	compat_sys_ioctl_wrapper
-compat_sys_ioctl_wrapper:
+ENTRY(compat_sys_ioctl_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	llgfr	%r4,%r4			# unsigned int
 	jg	compat_sys_ioctl	# branch to system call
 
-	.globl	compat_sys_fcntl_wrapper
-compat_sys_fcntl_wrapper:
+ENTRY(compat_sys_fcntl_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	llgfr	%r4,%r4			# unsigned long
 	jg	compat_sys_fcntl	# branch to system call
 
-	.globl	sys32_setpgid_wrapper
-sys32_setpgid_wrapper:
+ENTRY(sys32_setpgid_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	lgfr	%r3,%r3			# pid_t
 	jg	sys_setpgid		# branch to system call
 
-	.globl	sys32_umask_wrapper
-sys32_umask_wrapper:
+ENTRY(sys32_umask_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_umask		# branch to system call
 
-	.globl	sys32_chroot_wrapper
-sys32_chroot_wrapper:
+ENTRY(sys32_chroot_wrapper)
 	llgtr	%r2,%r2			# char *
 	jg	sys_chroot		# branch to system call
 
-	.globl sys32_ustat_wrapper
-sys32_ustat_wrapper:
+ENTRY(sys32_ustat_wrapper)
 	llgfr	%r2,%r2			# dev_t
 	llgtr	%r3,%r3			# struct ustat *
 	jg	compat_sys_ustat
 
-	.globl	sys32_dup2_wrapper
-sys32_dup2_wrapper:
+ENTRY(sys32_dup2_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	jg	sys_dup2		# branch to system call
@@ -266,262 +227,220 @@ sys32_dup2_wrapper:
 
 #sys32_setsid_wrapper			# void
 
-	.globl	sys32_sigaction_wrapper
-sys32_sigaction_wrapper:
+ENTRY(sys32_sigaction_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const struct old_sigaction *
 	llgtr	%r4,%r4			# struct old_sigaction32 *
 	jg	sys32_sigaction		# branch to system call
 
-	.globl	sys32_setreuid16_wrapper
-sys32_setreuid16_wrapper:
+ENTRY(sys32_setreuid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
 	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
 	jg	sys32_setreuid16	# branch to system call
 
-	.globl	sys32_setregid16_wrapper
-sys32_setregid16_wrapper:
+ENTRY(sys32_setregid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
 	llgfr	%r3,%r3			# __kernel_old_gid_emu31_t
 	jg	sys32_setregid16	# branch to system call
 
-	.globl sys_sigsuspend_wrapper
-sys_sigsuspend_wrapper:
+ENTRY(sys_sigsuspend_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgfr	%r4,%r4			# old_sigset_t
 	jg	sys_sigsuspend
 
-	.globl	compat_sys_sigpending_wrapper
-compat_sys_sigpending_wrapper:
+ENTRY(compat_sys_sigpending_wrapper)
 	llgtr	%r2,%r2			# compat_old_sigset_t *
 	jg	compat_sys_sigpending	# branch to system call
 
-	.globl	sys32_sethostname_wrapper
-sys32_sethostname_wrapper:
+ENTRY(sys32_sethostname_wrapper)
 	llgtr	%r2,%r2			# char *
 	lgfr	%r3,%r3			# int
 	jg	sys_sethostname		# branch to system call
 
-	.globl	compat_sys_setrlimit_wrapper
-compat_sys_setrlimit_wrapper:
+ENTRY(compat_sys_setrlimit_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# struct rlimit_emu31 *
 	jg	compat_sys_setrlimit	# branch to system call
 
-	.globl	compat_sys_old_getrlimit_wrapper
-compat_sys_old_getrlimit_wrapper:
+ENTRY(compat_sys_old_getrlimit_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# struct rlimit_emu31 *
 	jg	compat_sys_old_getrlimit # branch to system call
 
-	.globl	compat_sys_getrlimit_wrapper
-compat_sys_getrlimit_wrapper:
+ENTRY(compat_sys_getrlimit_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# struct rlimit_emu31 *
 	jg	compat_sys_getrlimit	# branch to system call
 
-	.globl	sys32_mmap2_wrapper
-sys32_mmap2_wrapper:
+ENTRY(sys32_mmap2_wrapper)
 	llgtr	%r2,%r2			# struct mmap_arg_struct_emu31 *
 	jg	sys32_mmap2			# branch to system call
 
-	.globl	compat_sys_getrusage_wrapper
-compat_sys_getrusage_wrapper:
+ENTRY(compat_sys_getrusage_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct rusage_emu31 *
 	jg	compat_sys_getrusage	# branch to system call
 
-	.globl	compat_sys_gettimeofday_wrapper
-compat_sys_gettimeofday_wrapper:
+ENTRY(compat_sys_gettimeofday_wrapper)
 	llgtr	%r2,%r2			# struct timeval_emu31 *
 	llgtr	%r3,%r3			# struct timezone *
 	jg	compat_sys_gettimeofday	# branch to system call
 
-	.globl	compat_sys_settimeofday_wrapper
-compat_sys_settimeofday_wrapper:
+ENTRY(compat_sys_settimeofday_wrapper)
 	llgtr	%r2,%r2			# struct timeval_emu31 *
 	llgtr	%r3,%r3			# struct timezone *
 	jg	compat_sys_settimeofday	# branch to system call
 
-	.globl	sys32_getgroups16_wrapper
-sys32_getgroups16_wrapper:
+ENTRY(sys32_getgroups16_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
 	jg	sys32_getgroups16	# branch to system call
 
-	.globl	sys32_setgroups16_wrapper
-sys32_setgroups16_wrapper:
+ENTRY(sys32_setgroups16_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
 	jg	sys32_setgroups16	# branch to system call
 
-	.globl	sys32_symlink_wrapper
-sys32_symlink_wrapper:
+ENTRY(sys32_symlink_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	jg	sys_symlink		# branch to system call
 
-	.globl	sys32_readlink_wrapper
-sys32_readlink_wrapper:
+ENTRY(sys32_readlink_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# char *
 	lgfr	%r4,%r4			# int
 	jg	sys_readlink		# branch to system call
 
-	.globl	sys32_uselib_wrapper
-sys32_uselib_wrapper:
+ENTRY(sys32_uselib_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_uselib		# branch to system call
 
-	.globl	sys32_swapon_wrapper
-sys32_swapon_wrapper:
+ENTRY(sys32_swapon_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	jg	sys_swapon		# branch to system call
 
-	.globl	sys32_reboot_wrapper
-sys32_reboot_wrapper:
+ENTRY(sys32_reboot_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgfr	%r4,%r4			# unsigned int
 	llgtr	%r5,%r5			# void *
 	jg	sys_reboot		# branch to system call
 
-	.globl	old32_readdir_wrapper
-old32_readdir_wrapper:
+ENTRY(old32_readdir_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# void *
 	llgfr	%r4,%r4			# unsigned int
 	jg	compat_sys_old_readdir	# branch to system call
 
-	.globl	old32_mmap_wrapper
-old32_mmap_wrapper:
+ENTRY(old32_mmap_wrapper)
 	llgtr	%r2,%r2			# struct mmap_arg_struct_emu31 *
 	jg	old32_mmap		# branch to system call
 
-	.globl	sys32_munmap_wrapper
-sys32_munmap_wrapper:
+ENTRY(sys32_munmap_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	jg	sys_munmap		# branch to system call
 
-	.globl	sys32_truncate_wrapper
-sys32_truncate_wrapper:
+ENTRY(sys32_truncate_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# long
 	jg	sys_truncate		# branch to system call
 
-	.globl	sys32_ftruncate_wrapper
-sys32_ftruncate_wrapper:
+ENTRY(sys32_ftruncate_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned long
 	jg	sys_ftruncate		# branch to system call
 
-	.globl	sys32_fchmod_wrapper
-sys32_fchmod_wrapper:
+ENTRY(sys32_fchmod_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# mode_t
 	jg	sys_fchmod		# branch to system call
 
-	.globl	sys32_fchown16_wrapper
-sys32_fchown16_wrapper:
+ENTRY(sys32_fchown16_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# compat_uid_t
 	llgfr	%r4,%r4			# compat_uid_t
 	jg	sys32_fchown16		# branch to system call
 
-	.globl	sys32_getpriority_wrapper
-sys32_getpriority_wrapper:
+ENTRY(sys32_getpriority_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	jg	sys_getpriority		# branch to system call
 
-	.globl	sys32_setpriority_wrapper
-sys32_setpriority_wrapper:
+ENTRY(sys32_setpriority_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
 	jg	sys_setpriority		# branch to system call
 
-	.globl	compat_sys_statfs_wrapper
-compat_sys_statfs_wrapper:
+ENTRY(compat_sys_statfs_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct compat_statfs *
 	jg	compat_sys_statfs	# branch to system call
 
-	.globl	compat_sys_fstatfs_wrapper
-compat_sys_fstatfs_wrapper:
+ENTRY(compat_sys_fstatfs_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# struct compat_statfs *
 	jg	compat_sys_fstatfs	# branch to system call
 
-	.globl	compat_sys_socketcall_wrapper
-compat_sys_socketcall_wrapper:
+ENTRY(compat_sys_socketcall_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# u32 *
 	jg	compat_sys_socketcall	# branch to system call
 
-	.globl	sys32_syslog_wrapper
-sys32_syslog_wrapper:
+ENTRY(sys32_syslog_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# char *
 	lgfr	%r4,%r4			# int
 	jg	sys_syslog		# branch to system call
 
-	.globl	compat_sys_setitimer_wrapper
-compat_sys_setitimer_wrapper:
+ENTRY(compat_sys_setitimer_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct itimerval_emu31 *
 	llgtr	%r4,%r4			# struct itimerval_emu31 *
 	jg	compat_sys_setitimer	# branch to system call
 
-	.globl	compat_sys_getitimer_wrapper
-compat_sys_getitimer_wrapper:
+ENTRY(compat_sys_getitimer_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct itimerval_emu31 *
 	jg	compat_sys_getitimer	# branch to system call
 
-	.globl	compat_sys_newstat_wrapper
-compat_sys_newstat_wrapper:
+ENTRY(compat_sys_newstat_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct stat_emu31 *
 	jg	compat_sys_newstat	# branch to system call
 
-	.globl	compat_sys_newlstat_wrapper
-compat_sys_newlstat_wrapper:
+ENTRY(compat_sys_newlstat_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct stat_emu31 *
 	jg	compat_sys_newlstat	# branch to system call
 
-	.globl	compat_sys_newfstat_wrapper
-compat_sys_newfstat_wrapper:
+ENTRY(compat_sys_newfstat_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# struct stat_emu31 *
 	jg	compat_sys_newfstat	# branch to system call
 
 #sys32_vhangup_wrapper			# void
 
-	.globl	compat_sys_wait4_wrapper
-compat_sys_wait4_wrapper:
+ENTRY(compat_sys_wait4_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# unsigned int *
 	lgfr	%r4,%r4			# int
 	llgtr	%r5,%r5			# struct rusage *
 	jg	compat_sys_wait4	# branch to system call
 
-	.globl	sys32_swapoff_wrapper
-sys32_swapoff_wrapper:
+ENTRY(sys32_swapoff_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_swapoff		# branch to system call
 
-	.globl	compat_sys_sysinfo_wrapper
-compat_sys_sysinfo_wrapper:
+ENTRY(compat_sys_sysinfo_wrapper)
 	llgtr	%r2,%r2			# struct sysinfo_emu31 *
 	jg	compat_sys_sysinfo	# branch to system call
 
-	.globl	sys32_ipc_wrapper
-sys32_ipc_wrapper:
+ENTRY(sys32_ipc_wrapper)
 	llgfr	%r2,%r2			# uint
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
@@ -529,8 +448,7 @@ sys32_ipc_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	sys32_ipc		# branch to system call
 
-	.globl	sys32_fsync_wrapper
-sys32_fsync_wrapper:
+ENTRY(sys32_fsync_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_fsync		# branch to system call
 
@@ -538,97 +456,81 @@ sys32_fsync_wrapper:
 
 #sys32_clone_wrapper			# done in clone_glue
 
-	.globl	sys32_setdomainname_wrapper
-sys32_setdomainname_wrapper:
+ENTRY(sys32_setdomainname_wrapper)
 	llgtr	%r2,%r2			# char *
 	lgfr	%r3,%r3			# int
 	jg	sys_setdomainname	# branch to system call
 
-	.globl	sys32_newuname_wrapper
-sys32_newuname_wrapper:
+ENTRY(sys32_newuname_wrapper)
 	llgtr	%r2,%r2			# struct new_utsname *
 	jg	sys_newuname		# branch to system call
 
-	.globl	compat_sys_adjtimex_wrapper
-compat_sys_adjtimex_wrapper:
+ENTRY(compat_sys_adjtimex_wrapper)
 	llgtr	%r2,%r2			# struct compat_timex *
 	jg	compat_sys_adjtimex	# branch to system call
 
-	.globl	sys32_mprotect_wrapper
-sys32_mprotect_wrapper:
+ENTRY(sys32_mprotect_wrapper)
 	llgtr	%r2,%r2			# unsigned long (actually pointer
 	llgfr	%r3,%r3			# size_t
 	llgfr	%r4,%r4			# unsigned long
 	jg	sys_mprotect		# branch to system call
 
-	.globl	compat_sys_sigprocmask_wrapper
-compat_sys_sigprocmask_wrapper:
+ENTRY(compat_sys_sigprocmask_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_old_sigset_t *
 	llgtr	%r4,%r4			# compat_old_sigset_t *
 	jg	compat_sys_sigprocmask		# branch to system call
 
-	.globl	sys_init_module_wrapper
-sys_init_module_wrapper:
+ENTRY(sys_init_module_wrapper)
 	llgtr	%r2,%r2			# void *
 	llgfr	%r3,%r3			# unsigned long
 	llgtr	%r4,%r4			# char *
 	jg	sys_init_module		# branch to system call
 
-	.globl	sys_delete_module_wrapper
-sys_delete_module_wrapper:
+ENTRY(sys_delete_module_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# unsigned int
 	jg	sys_delete_module	# branch to system call
 
-	.globl	sys32_quotactl_wrapper
-sys32_quotactl_wrapper:
+ENTRY(sys32_quotactl_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# qid_t
 	llgtr	%r5,%r5			# caddr_t
 	jg	sys_quotactl		# branch to system call
 
-	.globl	sys32_getpgid_wrapper
-sys32_getpgid_wrapper:
+ENTRY(sys32_getpgid_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	jg	sys_getpgid		# branch to system call
 
-	.globl	sys32_fchdir_wrapper
-sys32_fchdir_wrapper:
+ENTRY(sys32_fchdir_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_fchdir		# branch to system call
 
-	.globl	sys32_bdflush_wrapper
-sys32_bdflush_wrapper:
+ENTRY(sys32_bdflush_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# long
 	jg	sys_bdflush		# branch to system call
 
-	.globl	sys32_sysfs_wrapper
-sys32_sysfs_wrapper:
+ENTRY(sys32_sysfs_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
 	jg	sys_sysfs		# branch to system call
 
-	.globl	sys32_personality_wrapper
-sys32_personality_wrapper:
+ENTRY(sys32_personality_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_s390_personality	# branch to system call
 
-	.globl	sys32_setfsuid16_wrapper
-sys32_setfsuid16_wrapper:
+ENTRY(sys32_setfsuid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
 	jg	sys32_setfsuid16	# branch to system call
 
-	.globl	sys32_setfsgid16_wrapper
-sys32_setfsgid16_wrapper:
+ENTRY(sys32_setfsgid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
 	jg	sys32_setfsgid16	# branch to system call
 
-	.globl	sys32_llseek_wrapper
-sys32_llseek_wrapper:
+ENTRY(sys32_llseek_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
@@ -636,15 +538,13 @@ sys32_llseek_wrapper:
 	llgfr	%r6,%r6			# unsigned int
 	jg	sys_llseek		# branch to system call
 
-	.globl	sys32_getdents_wrapper
-sys32_getdents_wrapper:
+ENTRY(sys32_getdents_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# void *
 	llgfr	%r4,%r4			# unsigned int
 	jg	compat_sys_getdents	# branch to system call
 
-	.globl	compat_sys_select_wrapper
-compat_sys_select_wrapper:
+ENTRY(compat_sys_select_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_fd_set *
 	llgtr	%r4,%r4			# compat_fd_set *
@@ -652,112 +552,94 @@ compat_sys_select_wrapper:
 	llgtr	%r6,%r6			# struct compat_timeval *
 	jg	compat_sys_select	# branch to system call
 
-	.globl	sys32_flock_wrapper
-sys32_flock_wrapper:
+ENTRY(sys32_flock_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	jg	sys_flock		# branch to system call
 
-	.globl	sys32_msync_wrapper
-sys32_msync_wrapper:
+ENTRY(sys32_msync_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	lgfr	%r4,%r4			# int
 	jg	sys_msync		# branch to system call
 
-	.globl	compat_sys_readv_wrapper
-compat_sys_readv_wrapper:
+ENTRY(compat_sys_readv_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const struct compat_iovec *
 	llgfr	%r4,%r4			# unsigned long
 	jg	compat_sys_readv	# branch to system call
 
-	.globl	compat_sys_writev_wrapper
-compat_sys_writev_wrapper:
+ENTRY(compat_sys_writev_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const struct compat_iovec *
 	llgfr	%r4,%r4			# unsigned long
 	jg	compat_sys_writev	# branch to system call
 
-	.globl	sys32_getsid_wrapper
-sys32_getsid_wrapper:
+ENTRY(sys32_getsid_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	jg	sys_getsid		# branch to system call
 
-	.globl	sys32_fdatasync_wrapper
-sys32_fdatasync_wrapper:
+ENTRY(sys32_fdatasync_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_fdatasync		# branch to system call
 
-	.globl	sys32_mlock_wrapper
-sys32_mlock_wrapper:
+ENTRY(sys32_mlock_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	jg	sys_mlock		# branch to system call
 
-	.globl	sys32_munlock_wrapper
-sys32_munlock_wrapper:
+ENTRY(sys32_munlock_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	jg	sys_munlock		# branch to system call
 
-	.globl	sys32_mlockall_wrapper
-sys32_mlockall_wrapper:
+ENTRY(sys32_mlockall_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_mlockall		# branch to system call
 
 #sys32_munlockall_wrapper		# void
 
-	.globl	sys32_sched_setparam_wrapper
-sys32_sched_setparam_wrapper:
+ENTRY(sys32_sched_setparam_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# struct sched_param *
 	jg	sys_sched_setparam	# branch to system call
 
-	.globl	sys32_sched_getparam_wrapper
-sys32_sched_getparam_wrapper:
+ENTRY(sys32_sched_getparam_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# struct sched_param *
 	jg	sys_sched_getparam	# branch to system call
 
-	.globl	sys32_sched_setscheduler_wrapper
-sys32_sched_setscheduler_wrapper:
+ENTRY(sys32_sched_setscheduler_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# struct sched_param *
 	jg	sys_sched_setscheduler	# branch to system call
 
-	.globl	sys32_sched_getscheduler_wrapper
-sys32_sched_getscheduler_wrapper:
+ENTRY(sys32_sched_getscheduler_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	jg	sys_sched_getscheduler	# branch to system call
 
 #sys32_sched_yield_wrapper		# void
 
-	.globl	sys32_sched_get_priority_max_wrapper
-sys32_sched_get_priority_max_wrapper:
+ENTRY(sys32_sched_get_priority_max_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_sched_get_priority_max	# branch to system call
 
-	.globl	sys32_sched_get_priority_min_wrapper
-sys32_sched_get_priority_min_wrapper:
+ENTRY(sys32_sched_get_priority_min_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_sched_get_priority_min	# branch to system call
 
-	.globl	sys32_sched_rr_get_interval_wrapper
-sys32_sched_rr_get_interval_wrapper:
+ENTRY(sys32_sched_rr_get_interval_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# struct compat_timespec *
 	jg	sys32_sched_rr_get_interval	# branch to system call
 
-	.globl	compat_sys_nanosleep_wrapper
-compat_sys_nanosleep_wrapper:
+ENTRY(compat_sys_nanosleep_wrapper)
 	llgtr	%r2,%r2			# struct compat_timespec *
 	llgtr	%r3,%r3			# struct compat_timespec *
 	jg	compat_sys_nanosleep		# branch to system call
 
-	.globl	sys32_mremap_wrapper
-sys32_mremap_wrapper:
+ENTRY(sys32_mremap_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
@@ -765,50 +647,43 @@ sys32_mremap_wrapper:
 	llgfr	%r6,%r6			# unsigned long
 	jg	sys_mremap		# branch to system call
 
-	.globl	sys32_setresuid16_wrapper
-sys32_setresuid16_wrapper:
+ENTRY(sys32_setresuid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
 	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
 	llgfr	%r4,%r4			# __kernel_old_uid_emu31_t
 	jg	sys32_setresuid16	# branch to system call
 
-	.globl	sys32_getresuid16_wrapper
-sys32_getresuid16_wrapper:
+ENTRY(sys32_getresuid16_wrapper)
 	llgtr	%r2,%r2			# __kernel_old_uid_emu31_t *
 	llgtr	%r3,%r3			# __kernel_old_uid_emu31_t *
 	llgtr	%r4,%r4			# __kernel_old_uid_emu31_t *
 	jg	sys32_getresuid16	# branch to system call
 
-	.globl	sys32_poll_wrapper
-sys32_poll_wrapper:
+ENTRY(sys32_poll_wrapper)
 	llgtr	%r2,%r2			# struct pollfd *
 	llgfr	%r3,%r3			# unsigned int
 	lgfr	%r4,%r4			# long
 	jg	sys_poll		# branch to system call
 
-	.globl	compat_sys_nfsservctl_wrapper
-compat_sys_nfsservctl_wrapper:
+ENTRY(compat_sys_nfsservctl_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct compat_nfsctl_arg*
 	llgtr	%r4,%r4			# union compat_nfsctl_res*
 	jg	compat_sys_nfsservctl	# branch to system call
 
-	.globl	sys32_setresgid16_wrapper
-sys32_setresgid16_wrapper:
+ENTRY(sys32_setresgid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
 	llgfr	%r3,%r3			# __kernel_old_gid_emu31_t
 	llgfr	%r4,%r4			# __kernel_old_gid_emu31_t
 	jg	sys32_setresgid16	# branch to system call
 
-	.globl	sys32_getresgid16_wrapper
-sys32_getresgid16_wrapper:
+ENTRY(sys32_getresgid16_wrapper)
 	llgtr	%r2,%r2			# __kernel_old_gid_emu31_t *
 	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
 	llgtr	%r4,%r4			# __kernel_old_gid_emu31_t *
 	jg	sys32_getresgid16	# branch to system call
 
-	.globl	sys32_prctl_wrapper
-sys32_prctl_wrapper:
+ENTRY(sys32_prctl_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
@@ -818,51 +693,44 @@ sys32_prctl_wrapper:
 
 #sys32_rt_sigreturn_wrapper		# done in rt_sigreturn_glue
 
-	.globl	sys32_rt_sigaction_wrapper
-sys32_rt_sigaction_wrapper:
+ENTRY(sys32_rt_sigaction_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const struct sigaction_emu31 *
 	llgtr	%r4,%r4			# const struct sigaction_emu31 *
 	llgfr	%r5,%r5			# size_t
 	jg	sys32_rt_sigaction	# branch to system call
 
-	.globl	sys32_rt_sigprocmask_wrapper
-sys32_rt_sigprocmask_wrapper:
+ENTRY(sys32_rt_sigprocmask_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# old_sigset_emu31 *
 	llgtr	%r4,%r4			# old_sigset_emu31 *
 	llgfr	%r5,%r5			# size_t
 	jg	sys32_rt_sigprocmask	# branch to system call
 
-	.globl	sys32_rt_sigpending_wrapper
-sys32_rt_sigpending_wrapper:
+ENTRY(sys32_rt_sigpending_wrapper)
 	llgtr	%r2,%r2			# sigset_emu31 *
 	llgfr	%r3,%r3			# size_t
 	jg	sys32_rt_sigpending	# branch to system call
 
-	.globl	compat_sys_rt_sigtimedwait_wrapper
-compat_sys_rt_sigtimedwait_wrapper:
+ENTRY(compat_sys_rt_sigtimedwait_wrapper)
 	llgtr	%r2,%r2			# const sigset_emu31_t *
 	llgtr	%r3,%r3			# siginfo_emu31_t *
 	llgtr	%r4,%r4			# const struct compat_timespec *
 	llgfr	%r5,%r5			# size_t
 	jg	compat_sys_rt_sigtimedwait	# branch to system call
 
-	.globl	sys32_rt_sigqueueinfo_wrapper
-sys32_rt_sigqueueinfo_wrapper:
+ENTRY(sys32_rt_sigqueueinfo_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# siginfo_emu31_t *
 	jg	sys32_rt_sigqueueinfo	# branch to system call
 
-	.globl compat_sys_rt_sigsuspend_wrapper
-compat_sys_rt_sigsuspend_wrapper:
+ENTRY(compat_sys_rt_sigsuspend_wrapper)
 	llgtr	%r2,%r2			# compat_sigset_t *
 	llgfr	%r3,%r3			# compat_size_t
 	jg	compat_sys_rt_sigsuspend
 
-	.globl	sys32_pread64_wrapper
-sys32_pread64_wrapper:
+ENTRY(sys32_pread64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
@@ -870,8 +738,7 @@ sys32_pread64_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	sys32_pread64		# branch to system call
 
-	.globl	sys32_pwrite64_wrapper
-sys32_pwrite64_wrapper:
+ENTRY(sys32_pwrite64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# size_t
@@ -879,39 +746,33 @@ sys32_pwrite64_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	sys32_pwrite64		# branch to system call
 
-	.globl	sys32_chown16_wrapper
-sys32_chown16_wrapper:
+ENTRY(sys32_chown16_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
 	llgfr	%r4,%r4			# __kernel_old_gid_emu31_t
 	jg	sys32_chown16		# branch to system call
 
-	.globl	sys32_getcwd_wrapper
-sys32_getcwd_wrapper:
+ENTRY(sys32_getcwd_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgfr	%r3,%r3			# unsigned long
 	jg	sys_getcwd		# branch to system call
 
-	.globl	sys32_capget_wrapper
-sys32_capget_wrapper:
+ENTRY(sys32_capget_wrapper)
 	llgtr	%r2,%r2			# cap_user_header_t
 	llgtr	%r3,%r3			# cap_user_data_t
 	jg	sys_capget		# branch to system call
 
-	.globl	sys32_capset_wrapper
-sys32_capset_wrapper:
+ENTRY(sys32_capset_wrapper)
 	llgtr	%r2,%r2			# cap_user_header_t
 	llgtr	%r3,%r3			# const cap_user_data_t
 	jg	sys_capset		# branch to system call
 
-	.globl sys32_sigaltstack_wrapper
-sys32_sigaltstack_wrapper:
+ENTRY(sys32_sigaltstack_wrapper)
 	llgtr	%r2,%r2			# const stack_emu31_t *
 	llgtr	%r3,%r3			# stack_emu31_t *
 	jg	sys32_sigaltstack
 
-	.globl	sys32_sendfile_wrapper
-sys32_sendfile_wrapper:
+ENTRY(sys32_sendfile_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# __kernel_off_emu31_t *
@@ -920,22 +781,19 @@ sys32_sendfile_wrapper:
 
 #sys32_vfork_wrapper			# done in vfork_glue
 
-	.globl	sys32_truncate64_wrapper
-sys32_truncate64_wrapper:
+ENTRY(sys32_truncate64_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
 	jg	sys32_truncate64	# branch to system call
 
-	.globl	sys32_ftruncate64_wrapper
-sys32_ftruncate64_wrapper:
+ENTRY(sys32_ftruncate64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
 	jg	sys32_ftruncate64	# branch to system call
 
-	.globl sys32_lchown_wrapper
-sys32_lchown_wrapper:
+ENTRY(sys32_lchown_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# uid_t
 	llgfr	%r4,%r4			# gid_t
@@ -946,156 +804,131 @@ sys32_lchown_wrapper:
 #sys32_geteuid_wrapper			# void
 #sys32_getegid_wrapper			# void
 
-	.globl sys32_setreuid_wrapper
-sys32_setreuid_wrapper:
+ENTRY(sys32_setreuid_wrapper)
 	llgfr	%r2,%r2			# uid_t
 	llgfr	%r3,%r3			# uid_t
 	jg	sys_setreuid		# branch to system call
 
-	.globl sys32_setregid_wrapper
-sys32_setregid_wrapper:
+ENTRY(sys32_setregid_wrapper)
 	llgfr	%r2,%r2			# gid_t
 	llgfr	%r3,%r3			# gid_t
 	jg	sys_setregid		# branch to system call
 
-	.globl	sys32_getgroups_wrapper
-sys32_getgroups_wrapper:
+ENTRY(sys32_getgroups_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# gid_t *
 	jg	sys_getgroups		# branch to system call
 
-	.globl	sys32_setgroups_wrapper
-sys32_setgroups_wrapper:
+ENTRY(sys32_setgroups_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# gid_t *
 	jg	sys_setgroups		# branch to system call
 
-	.globl sys32_fchown_wrapper
-sys32_fchown_wrapper:
+ENTRY(sys32_fchown_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# uid_t
 	llgfr	%r4,%r4			# gid_t
 	jg	sys_fchown		# branch to system call
 
-	.globl sys32_setresuid_wrapper
-sys32_setresuid_wrapper:
+ENTRY(sys32_setresuid_wrapper)
 	llgfr	%r2,%r2			# uid_t
 	llgfr	%r3,%r3			# uid_t
 	llgfr	%r4,%r4			# uid_t
 	jg	sys_setresuid		# branch to system call
 
-	.globl sys32_getresuid_wrapper
-sys32_getresuid_wrapper:
+ENTRY(sys32_getresuid_wrapper)
 	llgtr	%r2,%r2			# uid_t *
 	llgtr	%r3,%r3			# uid_t *
 	llgtr	%r4,%r4			# uid_t *
 	jg	sys_getresuid		# branch to system call
 
-	.globl sys32_setresgid_wrapper
-sys32_setresgid_wrapper:
+ENTRY(sys32_setresgid_wrapper)
 	llgfr	%r2,%r2			# gid_t
 	llgfr	%r3,%r3			# gid_t
 	llgfr	%r4,%r4			# gid_t
 	jg	sys_setresgid		# branch to system call
 
-	.globl sys32_getresgid_wrapper
-sys32_getresgid_wrapper:
+ENTRY(sys32_getresgid_wrapper)
 	llgtr	%r2,%r2			# gid_t *
 	llgtr	%r3,%r3			# gid_t *
 	llgtr	%r4,%r4			# gid_t *
 	jg	sys_getresgid		# branch to system call
 
-	.globl sys32_chown_wrapper
-sys32_chown_wrapper:
+ENTRY(sys32_chown_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# uid_t
 	llgfr	%r4,%r4			# gid_t
 	jg	sys_chown		# branch to system call
 
-	.globl sys32_setuid_wrapper
-sys32_setuid_wrapper:
+ENTRY(sys32_setuid_wrapper)
 	llgfr	%r2,%r2			# uid_t
 	jg	sys_setuid		# branch to system call
 
-	.globl sys32_setgid_wrapper
-sys32_setgid_wrapper:
+ENTRY(sys32_setgid_wrapper)
 	llgfr	%r2,%r2			# gid_t
 	jg	sys_setgid		# branch to system call
 
-	.globl sys32_setfsuid_wrapper
-sys32_setfsuid_wrapper:
+ENTRY(sys32_setfsuid_wrapper)
 	llgfr	%r2,%r2			# uid_t
 	jg	sys_setfsuid		# branch to system call
 
-	.globl sys32_setfsgid_wrapper
-sys32_setfsgid_wrapper:
+ENTRY(sys32_setfsgid_wrapper)
 	llgfr	%r2,%r2			# gid_t
 	jg	sys_setfsgid		# branch to system call
 
-	.globl	sys32_pivot_root_wrapper
-sys32_pivot_root_wrapper:
+ENTRY(sys32_pivot_root_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	jg	sys_pivot_root		# branch to system call
 
-	.globl	sys32_mincore_wrapper
-sys32_mincore_wrapper:
+ENTRY(sys32_mincore_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	llgtr	%r4,%r4			# unsigned char *
 	jg	sys_mincore		# branch to system call
 
-	.globl	sys32_madvise_wrapper
-sys32_madvise_wrapper:
+ENTRY(sys32_madvise_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# size_t
 	lgfr	%r4,%r4			# int
 	jg	sys_madvise		# branch to system call
 
-	.globl	sys32_getdents64_wrapper
-sys32_getdents64_wrapper:
+ENTRY(sys32_getdents64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# void *
 	llgfr	%r4,%r4			# unsigned int
 	jg	sys_getdents64		# branch to system call
 
-	.globl	compat_sys_fcntl64_wrapper
-compat_sys_fcntl64_wrapper:
+ENTRY(compat_sys_fcntl64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	llgfr	%r4,%r4			# unsigned long
 	jg	compat_sys_fcntl64	# branch to system call
 
-	.globl	sys32_stat64_wrapper
-sys32_stat64_wrapper:
+ENTRY(sys32_stat64_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct stat64 *
 	jg	sys32_stat64		# branch to system call
 
-	.globl	sys32_lstat64_wrapper
-sys32_lstat64_wrapper:
+ENTRY(sys32_lstat64_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct stat64 *
 	jg	sys32_lstat64		# branch to system call
 
-	.globl	sys32_stime_wrapper
-sys32_stime_wrapper:
+ENTRY(sys32_stime_wrapper)
 	llgtr	%r2,%r2			# long *
 	jg	compat_sys_stime	# branch to system call
 
-	.globl	sys32_sysctl_wrapper
-sys32_sysctl_wrapper:
+ENTRY(sys32_sysctl_wrapper)
 	llgtr	%r2,%r2 		# struct compat_sysctl_args *
 	jg	compat_sys_sysctl
 
-	.globl	sys32_fstat64_wrapper
-sys32_fstat64_wrapper:
+ENTRY(sys32_fstat64_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgtr	%r3,%r3			# struct stat64 *
 	jg	sys32_fstat64		# branch to system call
 
-	.globl	compat_sys_futex_wrapper
-compat_sys_futex_wrapper:
+ENTRY(compat_sys_futex_wrapper)
 	llgtr	%r2,%r2			# u32 *
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
@@ -1105,8 +938,7 @@ compat_sys_futex_wrapper:
 	stg	%r0,160(%r15)
 	jg	compat_sys_futex	# branch to system call
 
-	.globl	sys32_setxattr_wrapper
-sys32_setxattr_wrapper:
+ENTRY(sys32_setxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
@@ -1114,8 +946,7 @@ sys32_setxattr_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_setxattr
 
-	.globl	sys32_lsetxattr_wrapper
-sys32_lsetxattr_wrapper:
+ENTRY(sys32_lsetxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
@@ -1123,8 +954,7 @@ sys32_lsetxattr_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_lsetxattr
 
-	.globl	sys32_fsetxattr_wrapper
-sys32_fsetxattr_wrapper:
+ENTRY(sys32_fsetxattr_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
@@ -1132,124 +962,106 @@ sys32_fsetxattr_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_fsetxattr
 
-	.globl	sys32_getxattr_wrapper
-sys32_getxattr_wrapper:
+ENTRY(sys32_getxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
 	llgfr	%r5,%r5			# size_t
 	jg	sys_getxattr
 
-	.globl	sys32_lgetxattr_wrapper
-sys32_lgetxattr_wrapper:
+ENTRY(sys32_lgetxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
 	llgfr	%r5,%r5			# size_t
 	jg	sys_lgetxattr
 
-	.globl	sys32_fgetxattr_wrapper
-sys32_fgetxattr_wrapper:
+ENTRY(sys32_fgetxattr_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# void *
 	llgfr	%r5,%r5			# size_t
 	jg	sys_fgetxattr
 
-	.globl	sys32_listxattr_wrapper
-sys32_listxattr_wrapper:
+ENTRY(sys32_listxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
 	jg	sys_listxattr
 
-	.globl	sys32_llistxattr_wrapper
-sys32_llistxattr_wrapper:
+ENTRY(sys32_llistxattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
 	jg	sys_llistxattr
 
-	.globl	sys32_flistxattr_wrapper
-sys32_flistxattr_wrapper:
+ENTRY(sys32_flistxattr_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
 	jg	sys_flistxattr
 
-	.globl	sys32_removexattr_wrapper
-sys32_removexattr_wrapper:
+ENTRY(sys32_removexattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	jg	sys_removexattr
 
-	.globl	sys32_lremovexattr_wrapper
-sys32_lremovexattr_wrapper:
+ENTRY(sys32_lremovexattr_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# char *
 	jg	sys_lremovexattr
 
-	.globl	sys32_fremovexattr_wrapper
-sys32_fremovexattr_wrapper:
+ENTRY(sys32_fremovexattr_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# char *
 	jg	sys_fremovexattr
 
-	.globl	sys32_sched_setaffinity_wrapper
-sys32_sched_setaffinity_wrapper:
+ENTRY(sys32_sched_setaffinity_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# unsigned int
 	llgtr	%r4,%r4			# unsigned long *
 	jg	compat_sys_sched_setaffinity
 
-	.globl	sys32_sched_getaffinity_wrapper
-sys32_sched_getaffinity_wrapper:
+ENTRY(sys32_sched_getaffinity_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# unsigned int
 	llgtr	%r4,%r4			# unsigned long *
 	jg	compat_sys_sched_getaffinity
 
-	.globl	sys32_exit_group_wrapper
-sys32_exit_group_wrapper:
+ENTRY(sys32_exit_group_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_exit_group		# branch to system call
 
-	.globl	sys32_set_tid_address_wrapper
-sys32_set_tid_address_wrapper:
+ENTRY(sys32_set_tid_address_wrapper)
 	llgtr	%r2,%r2			# int *
 	jg	sys_set_tid_address	# branch to system call
 
-	.globl	sys_epoll_create_wrapper
-sys_epoll_create_wrapper:
+ENTRY(sys_epoll_create_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_epoll_create	# branch to system call
 
-	.globl	sys_epoll_ctl_wrapper
-sys_epoll_ctl_wrapper:
+ENTRY(sys_epoll_ctl_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
 	llgtr	%r5,%r5			# struct epoll_event *
 	jg	sys_epoll_ctl		# branch to system call
 
-	.globl	sys_epoll_wait_wrapper
-sys_epoll_wait_wrapper:
+ENTRY(sys_epoll_wait_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct epoll_event *
 	lgfr	%r4,%r4			# int
 	lgfr	%r5,%r5			# int
 	jg	sys_epoll_wait		# branch to system call
 
-	.globl	sys32_lookup_dcookie_wrapper
-sys32_lookup_dcookie_wrapper:
+ENTRY(sys32_lookup_dcookie_wrapper)
 	sllg	%r2,%r2,32		# get high word of 64bit dcookie
 	or	%r2,%r3			# get low word of 64bit dcookie
 	llgtr	%r3,%r4			# char *
 	llgfr	%r4,%r5			# size_t
 	jg	sys_lookup_dcookie
 
-	.globl	sys32_fadvise64_wrapper
-sys32_fadvise64_wrapper:
+ENTRY(sys32_fadvise64_wrapper)
 	lgfr	%r2,%r2			# int
 	sllg	%r3,%r3,32		# get high word of 64bit loff_t
 	or	%r3,%r4			# get low word of 64bit loff_t
@@ -1257,81 +1069,68 @@ sys32_fadvise64_wrapper:
 	lgfr	%r5,%r6			# int
 	jg	sys32_fadvise64
 
-	.globl	sys32_fadvise64_64_wrapper
-sys32_fadvise64_64_wrapper:
+ENTRY(sys32_fadvise64_64_wrapper)
 	llgtr	%r2,%r2			# struct fadvise64_64_args *
 	jg	sys32_fadvise64_64
 
-	.globl	sys32_clock_settime_wrapper
-sys32_clock_settime_wrapper:
+ENTRY(sys32_clock_settime_wrapper)
 	lgfr	%r2,%r2			# clockid_t (int)
 	llgtr	%r3,%r3			# struct compat_timespec *
 	jg	compat_sys_clock_settime
 
-	.globl	sys32_clock_gettime_wrapper
-sys32_clock_gettime_wrapper:
+ENTRY(sys32_clock_gettime_wrapper)
 	lgfr	%r2,%r2			# clockid_t (int)
 	llgtr	%r3,%r3			# struct compat_timespec *
 	jg	compat_sys_clock_gettime
 
-	.globl	sys32_clock_getres_wrapper
-sys32_clock_getres_wrapper:
+ENTRY(sys32_clock_getres_wrapper)
 	lgfr	%r2,%r2			# clockid_t (int)
 	llgtr	%r3,%r3			# struct compat_timespec *
 	jg	compat_sys_clock_getres
 
-	.globl	sys32_clock_nanosleep_wrapper
-sys32_clock_nanosleep_wrapper:
+ENTRY(sys32_clock_nanosleep_wrapper)
 	lgfr	%r2,%r2			# clockid_t (int)
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# struct compat_timespec *
 	llgtr	%r5,%r5			# struct compat_timespec *
 	jg	compat_sys_clock_nanosleep
 
-	.globl	sys32_timer_create_wrapper
-sys32_timer_create_wrapper:
+ENTRY(sys32_timer_create_wrapper)
 	lgfr	%r2,%r2			# timer_t (int)
 	llgtr	%r3,%r3			# struct compat_sigevent *
 	llgtr	%r4,%r4			# timer_t *
 	jg	compat_sys_timer_create
 
-	.globl	sys32_timer_settime_wrapper
-sys32_timer_settime_wrapper:
+ENTRY(sys32_timer_settime_wrapper)
 	lgfr	%r2,%r2			# timer_t (int)
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# struct compat_itimerspec *
 	llgtr	%r5,%r5			# struct compat_itimerspec *
 	jg	compat_sys_timer_settime
 
-	.globl	sys32_timer_gettime_wrapper
-sys32_timer_gettime_wrapper:
+ENTRY(sys32_timer_gettime_wrapper)
 	lgfr	%r2,%r2			# timer_t (int)
 	llgtr	%r3,%r3			# struct compat_itimerspec *
 	jg	compat_sys_timer_gettime
 
-	.globl	sys32_timer_getoverrun_wrapper
-sys32_timer_getoverrun_wrapper:
+ENTRY(sys32_timer_getoverrun_wrapper)
 	lgfr	%r2,%r2			# timer_t (int)
 	jg	sys_timer_getoverrun
 
-	.globl	sys32_timer_delete_wrapper
-sys32_timer_delete_wrapper:
+ENTRY(sys32_timer_delete_wrapper)
 	lgfr	%r2,%r2			# timer_t (int)
 	jg	sys_timer_delete
 
-	.globl	sys32_io_setup_wrapper
-sys32_io_setup_wrapper:
+ENTRY(sys32_io_setup_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# u32 *
 	jg	compat_sys_io_setup
 
-	.globl	sys32_io_destroy_wrapper
-sys32_io_destroy_wrapper:
+ENTRY(sys32_io_destroy_wrapper)
 	llgfr	%r2,%r2			# (aio_context_t) u32
 	jg	sys_io_destroy
 
-	.globl	sys32_io_getevents_wrapper
-sys32_io_getevents_wrapper:
+ENTRY(sys32_io_getevents_wrapper)
 	llgfr	%r2,%r2			# (aio_context_t) u32
 	lgfr	%r3,%r3			# long
 	lgfr	%r4,%r4			# long
@@ -1339,49 +1138,42 @@ sys32_io_getevents_wrapper:
 	llgtr	%r6,%r6			# struct compat_timespec *
 	jg	compat_sys_io_getevents
 
-	.globl	sys32_io_submit_wrapper
-sys32_io_submit_wrapper:
+ENTRY(sys32_io_submit_wrapper)
 	llgfr	%r2,%r2			# (aio_context_t) u32
 	lgfr	%r3,%r3			# long
 	llgtr	%r4,%r4			# struct iocb **
 	jg	compat_sys_io_submit
 
-	.globl	sys32_io_cancel_wrapper
-sys32_io_cancel_wrapper:
+ENTRY(sys32_io_cancel_wrapper)
 	llgfr	%r2,%r2			# (aio_context_t) u32
 	llgtr	%r3,%r3			# struct iocb *
 	llgtr	%r4,%r4			# struct io_event *
 	jg	sys_io_cancel
 
-	.globl compat_sys_statfs64_wrapper
-compat_sys_statfs64_wrapper:
+ENTRY(compat_sys_statfs64_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgfr	%r3,%r3			# compat_size_t
 	llgtr	%r4,%r4			# struct compat_statfs64 *
 	jg	compat_sys_statfs64
 
-	.globl compat_sys_fstatfs64_wrapper
-compat_sys_fstatfs64_wrapper:
+ENTRY(compat_sys_fstatfs64_wrapper)
 	llgfr	%r2,%r2			# unsigned int fd
 	llgfr	%r3,%r3			# compat_size_t
 	llgtr	%r4,%r4			# struct compat_statfs64 *
 	jg	compat_sys_fstatfs64
 
-	.globl	compat_sys_mq_open_wrapper
-compat_sys_mq_open_wrapper:
+ENTRY(compat_sys_mq_open_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	llgfr	%r4,%r4			# mode_t
 	llgtr	%r5,%r5			# struct compat_mq_attr *
 	jg	compat_sys_mq_open
 
-	.globl	sys32_mq_unlink_wrapper
-sys32_mq_unlink_wrapper:
+ENTRY(sys32_mq_unlink_wrapper)
 	llgtr	%r2,%r2			# const char *
 	jg	sys_mq_unlink
 
-	.globl	compat_sys_mq_timedsend_wrapper
-compat_sys_mq_timedsend_wrapper:
+ENTRY(compat_sys_mq_timedsend_wrapper)
 	lgfr	%r2,%r2			# mqd_t
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# size_t
@@ -1389,8 +1181,7 @@ compat_sys_mq_timedsend_wrapper:
 	llgtr	%r6,%r6			# const struct compat_timespec *
 	jg	compat_sys_mq_timedsend
 
-	.globl	compat_sys_mq_timedreceive_wrapper
-compat_sys_mq_timedreceive_wrapper:
+ENTRY(compat_sys_mq_timedreceive_wrapper)
 	lgfr	%r2,%r2			# mqd_t
 	llgtr	%r3,%r3			# char *
 	llgfr	%r4,%r4			# size_t
@@ -1398,21 +1189,18 @@ compat_sys_mq_timedreceive_wrapper:
 	llgtr	%r6,%r6			# const struct compat_timespec *
 	jg	compat_sys_mq_timedreceive
 
-	.globl	compat_sys_mq_notify_wrapper
-compat_sys_mq_notify_wrapper:
+ENTRY(compat_sys_mq_notify_wrapper)
 	lgfr	%r2,%r2			# mqd_t
 	llgtr	%r3,%r3			# struct compat_sigevent *
 	jg	compat_sys_mq_notify
 
-	.globl	compat_sys_mq_getsetattr_wrapper
-compat_sys_mq_getsetattr_wrapper:
+ENTRY(compat_sys_mq_getsetattr_wrapper)
 	lgfr	%r2,%r2			# mqd_t
 	llgtr	%r3,%r3			# struct compat_mq_attr *
 	llgtr	%r4,%r4			# struct compat_mq_attr *
 	jg	compat_sys_mq_getsetattr
 
-	.globl	compat_sys_add_key_wrapper
-compat_sys_add_key_wrapper:
+ENTRY(compat_sys_add_key_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	llgtr	%r4,%r4			# const void *
@@ -1420,16 +1208,14 @@ compat_sys_add_key_wrapper:
 	llgfr	%r6,%r6			# (key_serial_t) u32
 	jg	sys_add_key
 
-	.globl	compat_sys_request_key_wrapper
-compat_sys_request_key_wrapper:
+ENTRY(compat_sys_request_key_wrapper)
 	llgtr	%r2,%r2			# const char *
 	llgtr	%r3,%r3			# const char *
 	llgtr	%r4,%r4			# const void *
 	llgfr	%r5,%r5			# (key_serial_t) u32
 	jg	sys_request_key
 
-	.globl	sys32_remap_file_pages_wrapper
-sys32_remap_file_pages_wrapper:
+ENTRY(sys32_remap_file_pages_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# unsigned long
 	llgfr	%r4,%r4			# unsigned long
@@ -1437,8 +1223,7 @@ sys32_remap_file_pages_wrapper:
 	llgfr	%r6,%r6			# unsigned long
 	jg	sys_remap_file_pages
 
-	.globl	compat_sys_waitid_wrapper
-compat_sys_waitid_wrapper:
+ENTRY(compat_sys_waitid_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# pid_t
 	llgtr	%r4,%r4			# siginfo_emu31_t *
@@ -1446,65 +1231,56 @@ compat_sys_waitid_wrapper:
 	llgtr	%r6,%r6			# struct rusage_emu31 *
 	jg	compat_sys_waitid
 
-	.globl	compat_sys_kexec_load_wrapper
-compat_sys_kexec_load_wrapper:
+ENTRY(compat_sys_kexec_load_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# unsigned long
 	llgtr	%r4,%r4			# struct kexec_segment *
 	llgfr	%r5,%r5			# unsigned long
 	jg	compat_sys_kexec_load
 
-	.globl	sys_ioprio_set_wrapper
-sys_ioprio_set_wrapper:
+ENTRY(sys_ioprio_set_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
 	jg	sys_ioprio_set
 
-	.globl	sys_ioprio_get_wrapper
-sys_ioprio_get_wrapper:
+ENTRY(sys_ioprio_get_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	jg	sys_ioprio_get
 
-	.globl	sys_inotify_add_watch_wrapper
-sys_inotify_add_watch_wrapper:
+ENTRY(sys_inotify_add_watch_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# u32
 	jg	sys_inotify_add_watch
 
-	.globl	sys_inotify_rm_watch_wrapper
-sys_inotify_rm_watch_wrapper:
+ENTRY(sys_inotify_rm_watch_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# u32
 	jg	sys_inotify_rm_watch
 
-	.globl compat_sys_openat_wrapper
-compat_sys_openat_wrapper:
+ENTRY(compat_sys_openat_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	lgfr	%r5,%r5			# int
 	jg	compat_sys_openat
 
-	.globl sys_mkdirat_wrapper
-sys_mkdirat_wrapper:
+ENTRY(sys_mkdirat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	jg	sys_mkdirat
 
-	.globl sys_mknodat_wrapper
-sys_mknodat_wrapper:
+ENTRY(sys_mknodat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	llgfr	%r5,%r5			# unsigned int
 	jg	sys_mknodat
 
-	.globl sys_fchownat_wrapper
-sys_fchownat_wrapper:
+ENTRY(sys_fchownat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# uid_t
@@ -1512,38 +1288,33 @@ sys_fchownat_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_fchownat
 
-	.globl compat_sys_futimesat_wrapper
-compat_sys_futimesat_wrapper:
+ENTRY(compat_sys_futimesat_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# struct timeval *
 	jg	compat_sys_futimesat
 
-	.globl sys32_fstatat64_wrapper
-sys32_fstatat64_wrapper:
+ENTRY(sys32_fstatat64_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# struct stat64 *
 	lgfr	%r5,%r5			# int
 	jg	sys32_fstatat64
 
-	.globl sys_unlinkat_wrapper
-sys_unlinkat_wrapper:
+ENTRY(sys_unlinkat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	jg	sys_unlinkat
 
-	.globl sys_renameat_wrapper
-sys_renameat_wrapper:
+ENTRY(sys_renameat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	llgtr	%r5,%r5			# const char *
 	jg	sys_renameat
 
-	.globl sys_linkat_wrapper
-sys_linkat_wrapper:
+ENTRY(sys_linkat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
@@ -1551,37 +1322,32 @@ sys_linkat_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_linkat
 
-	.globl sys_symlinkat_wrapper
-sys_symlinkat_wrapper:
+ENTRY(sys_symlinkat_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# const char *
 	jg	sys_symlinkat
 
-	.globl sys_readlinkat_wrapper
-sys_readlinkat_wrapper:
+ENTRY(sys_readlinkat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	llgtr	%r4,%r4			# char *
 	lgfr	%r5,%r5			# int
 	jg	sys_readlinkat
 
-	.globl sys_fchmodat_wrapper
-sys_fchmodat_wrapper:
+ENTRY(sys_fchmodat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	llgfr	%r4,%r4			# mode_t
 	jg	sys_fchmodat
 
-	.globl sys_faccessat_wrapper
-sys_faccessat_wrapper:
+ENTRY(sys_faccessat_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char *
 	lgfr	%r4,%r4			# int
 	jg	sys_faccessat
 
-	.globl compat_sys_pselect6_wrapper
-compat_sys_pselect6_wrapper:
+ENTRY(compat_sys_pselect6_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# fd_set *
 	llgtr	%r4,%r4			# fd_set *
@@ -1591,8 +1357,7 @@ compat_sys_pselect6_wrapper:
 	stg	%r0,160(%r15)
 	jg	compat_sys_pselect6
 
-	.globl compat_sys_ppoll_wrapper
-compat_sys_ppoll_wrapper:
+ENTRY(compat_sys_ppoll_wrapper)
 	llgtr	%r2,%r2			# struct pollfd *
 	llgfr	%r3,%r3			# unsigned int
 	llgtr	%r4,%r4			# struct timespec *
@@ -1600,26 +1365,22 @@ compat_sys_ppoll_wrapper:
 	llgfr	%r6,%r6			# size_t
 	jg	compat_sys_ppoll
 
-	.globl sys_unshare_wrapper
-sys_unshare_wrapper:
+ENTRY(sys_unshare_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	jg	sys_unshare
 
-	.globl compat_sys_set_robust_list_wrapper
-compat_sys_set_robust_list_wrapper:
+ENTRY(compat_sys_set_robust_list_wrapper)
 	llgtr	%r2,%r2			# struct compat_robust_list_head *
 	llgfr	%r3,%r3			# size_t
 	jg	compat_sys_set_robust_list
 
-	.globl compat_sys_get_robust_list_wrapper
-compat_sys_get_robust_list_wrapper:
+ENTRY(compat_sys_get_robust_list_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_uptr_t_t *
 	llgtr	%r4,%r4			# compat_size_t *
 	jg	compat_sys_get_robust_list
 
-	.globl sys_splice_wrapper
-sys_splice_wrapper:
+ENTRY(sys_splice_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# loff_t *
 	lgfr	%r4,%r4			# int
@@ -1629,8 +1390,7 @@ sys_splice_wrapper:
 	stg	%r0,160(%r15)
 	jg	sys_splice
 
-	.globl	sys_sync_file_range_wrapper
-sys_sync_file_range_wrapper:
+ENTRY(sys_sync_file_range_wrapper)
 	lgfr	%r2,%r2			# int
 	sllg	%r3,%r3,32		# get high word of 64bit loff_t
 	or	%r3,%r4			# get low word of 64bit loff_t
@@ -1639,31 +1399,27 @@ sys_sync_file_range_wrapper:
 	llgf	%r5,164(%r15)		# unsigned int
 	jg	sys_sync_file_range
 
-	.globl	sys_tee_wrapper
-sys_tee_wrapper:
+ENTRY(sys_tee_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgfr	%r4,%r4			# size_t
 	llgfr	%r5,%r5			# unsigned int
 	jg	sys_tee
 
-	.globl compat_sys_vmsplice_wrapper
-compat_sys_vmsplice_wrapper:
+ENTRY(compat_sys_vmsplice_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_iovec *
 	llgfr	%r4,%r4			# unsigned int
 	llgfr	%r5,%r5			# unsigned int
 	jg	compat_sys_vmsplice
 
-	.globl	sys_getcpu_wrapper
-sys_getcpu_wrapper:
+ENTRY(sys_getcpu_wrapper)
 	llgtr	%r2,%r2			# unsigned *
 	llgtr	%r3,%r3			# unsigned *
 	llgtr	%r4,%r4			# struct getcpu_cache *
 	jg	sys_getcpu
 
-	.globl	compat_sys_epoll_pwait_wrapper
-compat_sys_epoll_pwait_wrapper:
+ENTRY(compat_sys_epoll_pwait_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct compat_epoll_event *
 	lgfr	%r4,%r4			# int
@@ -1673,34 +1429,29 @@ compat_sys_epoll_pwait_wrapper:
 	stg	%r0,160(%r15)
 	jg	compat_sys_epoll_pwait
 
-	.globl	compat_sys_utimes_wrapper
-compat_sys_utimes_wrapper:
+ENTRY(compat_sys_utimes_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# struct compat_timeval *
 	jg	compat_sys_utimes
 
-	.globl	compat_sys_utimensat_wrapper
-compat_sys_utimensat_wrapper:
+ENTRY(compat_sys_utimensat_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgtr	%r3,%r3			# char *
 	llgtr	%r4,%r4			# struct compat_timespec *
 	lgfr	%r5,%r5			# int
 	jg	compat_sys_utimensat
 
-	.globl	compat_sys_signalfd_wrapper
-compat_sys_signalfd_wrapper:
+ENTRY(compat_sys_signalfd_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_sigset_t *
 	llgfr	%r4,%r4			# compat_size_t
 	jg	compat_sys_signalfd
 
-	.globl	sys_eventfd_wrapper
-sys_eventfd_wrapper:
+ENTRY(sys_eventfd_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	jg	sys_eventfd
 
-	.globl	sys_fallocate_wrapper
-sys_fallocate_wrapper:
+ENTRY(sys_fallocate_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	sllg	%r4,%r4,32		# get high word of 64bit loff_t
@@ -1709,94 +1460,80 @@ sys_fallocate_wrapper:
 	l	%r5,164(%r15)		# get low word of 64bit loff_t
 	jg	sys_fallocate
 
-	.globl	sys_timerfd_create_wrapper
-sys_timerfd_create_wrapper:
+ENTRY(sys_timerfd_create_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	jg	sys_timerfd_create
 
-	.globl	compat_sys_timerfd_settime_wrapper
-compat_sys_timerfd_settime_wrapper:
+ENTRY(compat_sys_timerfd_settime_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# struct compat_itimerspec *
 	llgtr	%r5,%r5			# struct compat_itimerspec *
 	jg	compat_sys_timerfd_settime
 
-	.globl	compat_sys_timerfd_gettime_wrapper
-compat_sys_timerfd_gettime_wrapper:
+ENTRY(compat_sys_timerfd_gettime_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct compat_itimerspec *
 	jg	compat_sys_timerfd_gettime
 
-	.globl compat_sys_signalfd4_wrapper
-compat_sys_signalfd4_wrapper:
+ENTRY(compat_sys_signalfd4_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# compat_sigset_t *
 	llgfr	%r4,%r4			# compat_size_t
 	lgfr	%r5,%r5			# int
 	jg	compat_sys_signalfd4
 
-	.globl sys_eventfd2_wrapper
-sys_eventfd2_wrapper:
+ENTRY(sys_eventfd2_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	lgfr	%r3,%r3			# int
 	jg	sys_eventfd2
 
-	.globl	sys_inotify_init1_wrapper
-sys_inotify_init1_wrapper:
+ENTRY(sys_inotify_init1_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_inotify_init1
 
-	.globl	sys_pipe2_wrapper
-sys_pipe2_wrapper:
+ENTRY(sys_pipe2_wrapper)
 	llgtr	%r2,%r2			# u32 *
 	lgfr	%r3,%r3			# int
 	jg	sys_pipe2		# branch to system call
 
-	.globl	sys_dup3_wrapper
-sys_dup3_wrapper:
+ENTRY(sys_dup3_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	lgfr	%r4,%r4			# int
 	jg	sys_dup3		# branch to system call
 
-	.globl	sys_epoll_create1_wrapper
-sys_epoll_create1_wrapper:
+ENTRY(sys_epoll_create1_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_epoll_create1	# branch to system call
 
-	.globl	sys32_readahead_wrapper
-sys32_readahead_wrapper:
+ENTRY(sys32_readahead_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# u32
 	llgfr	%r4,%r4			# u32
 	lgfr	%r5,%r5			# s32
 	jg	sys32_readahead		# branch to system call
 
-	.globl	sys32_sendfile64_wrapper
-sys32_sendfile64_wrapper:
+ENTRY(sys32_sendfile64_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	llgtr	%r4,%r4			# compat_loff_t *
 	lgfr	%r5,%r5			# s32
 	jg	sys32_sendfile64	# branch to system call
 
-	.globl	sys_tkill_wrapper
-sys_tkill_wrapper:
+ENTRY(sys_tkill_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	lgfr	%r3,%r3			# int
 	jg	sys_tkill		# branch to system call
 
-	.globl	sys_tgkill_wrapper
-sys_tgkill_wrapper:
+ENTRY(sys_tgkill_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	lgfr	%r3,%r3			# pid_t
 	lgfr	%r4,%r4			# int
 	jg	sys_tgkill		# branch to system call
 
-	.globl	compat_sys_keyctl_wrapper
-compat_sys_keyctl_wrapper:
+ENTRY(compat_sys_keyctl_wrapper)
 	llgfr	%r2,%r2			# u32
 	llgfr	%r3,%r3			# u32
 	llgfr	%r4,%r4			# u32
@@ -1804,8 +1541,7 @@ compat_sys_keyctl_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	compat_sys_keyctl	# branch to system call
 
-	.globl	compat_sys_preadv_wrapper
-compat_sys_preadv_wrapper:
+ENTRY(compat_sys_preadv_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgtr	%r3,%r3			# compat_iovec *
 	llgfr	%r4,%r4			# unsigned long
@@ -1813,8 +1549,7 @@ compat_sys_preadv_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	compat_sys_preadv	# branch to system call
 
-	.globl	compat_sys_pwritev_wrapper
-compat_sys_pwritev_wrapper:
+ENTRY(compat_sys_pwritev_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgtr	%r3,%r3			# compat_iovec *
 	llgfr	%r4,%r4			# unsigned long
@@ -1822,16 +1557,14 @@ compat_sys_pwritev_wrapper:
 	llgfr	%r6,%r6			# u32
 	jg	compat_sys_pwritev	# branch to system call
 
-	.globl	compat_sys_rt_tgsigqueueinfo_wrapper
-compat_sys_rt_tgsigqueueinfo_wrapper:
+ENTRY(compat_sys_rt_tgsigqueueinfo_wrapper)
 	lgfr	%r2,%r2			# compat_pid_t
 	lgfr	%r3,%r3			# compat_pid_t
 	lgfr	%r4,%r4			# int
 	llgtr	%r5,%r5			# struct compat_siginfo *
 	jg	compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call
 
-	.globl	sys_perf_event_open_wrapper
-sys_perf_event_open_wrapper:
+ENTRY(sys_perf_event_open_wrapper)
 	llgtr	%r2,%r2			# const struct perf_event_attr *
 	lgfr	%r3,%r3			# pid_t
 	lgfr	%r4,%r4			# int
@@ -1839,29 +1572,25 @@ sys_perf_event_open_wrapper:
 	llgfr	%r6,%r6			# unsigned long
 	jg	sys_perf_event_open	# branch to system call
 
-	.globl	sys_clone_wrapper
-sys_clone_wrapper:
+ENTRY(sys_clone_wrapper)
 	llgfr	%r2,%r2			# unsigned long
 	llgfr	%r3,%r3			# unsigned long
 	llgtr	%r4,%r4			# int *
 	llgtr	%r5,%r5			# int *
 	jg	sys_clone		# branch to system call
 
-	.globl	sys32_execve_wrapper
-sys32_execve_wrapper:
+ENTRY(sys32_execve_wrapper)
 	llgtr	%r2,%r2			# char *
 	llgtr	%r3,%r3			# compat_uptr_t *
 	llgtr	%r4,%r4			# compat_uptr_t *
 	jg	sys32_execve		# branch to system call
 
-	.globl	sys_fanotify_init_wrapper
-sys_fanotify_init_wrapper:
+ENTRY(sys_fanotify_init_wrapper)
 	llgfr	%r2,%r2			# unsigned int
 	llgfr	%r3,%r3			# unsigned int
 	jg	sys_fanotify_init	# branch to system call
 
-	.globl	sys_fanotify_mark_wrapper
-sys_fanotify_mark_wrapper:
+ENTRY(sys_fanotify_mark_wrapper)
 	lgfr	%r2,%r2			# int
 	llgfr	%r3,%r3			# unsigned int
 	sllg	%r4,%r4,32		# get high word of 64bit mask
@@ -1870,16 +1599,14 @@ sys_fanotify_mark_wrapper:
 	llgt	%r6,164(%r15)		# char *
 	jg	sys_fanotify_mark	# branch to system call
 
-	.globl	sys_prlimit64_wrapper
-sys_prlimit64_wrapper:
+ENTRY(sys_prlimit64_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgfr	%r3,%r3			# unsigned int
 	llgtr	%r4,%r4			# const struct rlimit64 __user *
 	llgtr	%r5,%r5			# struct rlimit64 __user *
 	jg	sys_prlimit64		# branch to system call
 
-	.globl	sys_name_to_handle_at_wrapper
-sys_name_to_handle_at_wrapper:
+ENTRY(sys_name_to_handle_at_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# const char __user *
 	llgtr	%r4,%r4			# struct file_handle __user *
@@ -1887,21 +1614,18 @@ sys_name_to_handle_at_wrapper:
 	lgfr	%r6,%r6			# int
 	jg	sys_name_to_handle_at
 
-	.globl	compat_sys_open_by_handle_at_wrapper
-compat_sys_open_by_handle_at_wrapper:
+ENTRY(compat_sys_open_by_handle_at_wrapper)
 	lgfr	%r2,%r2			# int
 	llgtr	%r3,%r3			# struct file_handle __user *
 	lgfr	%r4,%r4			# int
 	jg	compat_sys_open_by_handle_at
 
-	.globl	compat_sys_clock_adjtime_wrapper
-compat_sys_clock_adjtime_wrapper:
+ENTRY(compat_sys_clock_adjtime_wrapper)
 	lgfr	%r2,%r2			# clockid_t (int)
 	llgtr	%r3,%r3			# struct compat_timex __user *
 	jg	compat_sys_clock_adjtime
 
-	.globl	sys_syncfs_wrapper
-sys_syncfs_wrapper:
+ENTRY(sys_syncfs_wrapper)
 	lgfr	%r2,%r2			# int
 	jg	sys_syncfs
 
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 0476174dfff..3eab7cfab07 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -9,8 +9,8 @@
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
-#include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -197,8 +197,7 @@ STACK_SIZE  = 1 << STACK_SHIFT
  * Returns:
  *  gpr2 = prev
  */
-	.globl	__switch_to
-__switch_to:
+ENTRY(__switch_to)
 	basr	%r1,0
 0:	l	%r4,__THREAD_info(%r2)		# get thread_info of prev
 	l	%r5,__THREAD_info(%r3)		# get thread_info of next
@@ -224,8 +223,7 @@ __critical_start:
  * are executed with interrupts enabled.
  */
 
-	.globl	system_call
-system_call:
+ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
 sysc_saveall:
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
@@ -388,8 +386,7 @@ sysc_tracenogo:
 #
 # a new process exits the kernel with ret_from_fork
 #
-	.globl	ret_from_fork
-ret_from_fork:
+ENTRY(ret_from_fork)
 	l	%r13,__LC_SVC_NEW_PSW+4
 	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
@@ -405,8 +402,7 @@ ret_from_fork:
 # kernel_execve function needs to deal with pt_regs that is not
 # at the usual place
 #
-	.globl	kernel_execve
-kernel_execve:
+ENTRY(kernel_execve)
 	stm	%r12,%r15,48(%r15)
 	lr	%r14,%r15
 	l	%r13,__LC_SVC_NEW_PSW+4
@@ -438,8 +434,7 @@ kernel_execve:
  * Program check handler routine
  */
 
-	.globl	pgm_check_handler
-pgm_check_handler:
+ENTRY(pgm_check_handler)
 /*
  * First we need to check for a special case:
  * Single stepping an instruction that disables the PER event mask will
@@ -565,8 +560,7 @@ kernel_per:
  * IO interrupt handler routine
  */
 
-	.globl io_int_handler
-io_int_handler:
+ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+16
@@ -703,8 +697,7 @@ io_notify_resume:
  * External interrupt handler routine
  */
 
-	.globl	ext_int_handler
-ext_int_handler:
+ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+16
@@ -731,8 +724,7 @@ __critical_end:
  * Machine check handler routines
  */
 
-	.globl mcck_int_handler
-mcck_int_handler:
+ENTRY(mcck_int_handler)
 	stck	__LC_MCCK_CLOCK
 	spt	__LC_CPU_TIMER_SAVE_AREA	# revalidate cpu timer
 	lm	%r0,%r15,__LC_GPREGS_SAVE_AREA	# revalidate gprs
@@ -818,8 +810,7 @@ mcck_return:
  */
 #ifdef CONFIG_SMP
 	__CPUINIT
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	spt	restart_vtime-restart_base(%r1)
@@ -848,8 +839,7 @@ restart_vtime:
 /*
  * If we do not run with SMP enabled, let the new CPU crash ...
  */
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	lpsw	restart_crash-restart_base(%r1)
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 17a6f83a2d6..66729eb7bbc 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -5,10 +5,9 @@
 #include <linux/signal.h>
 #include <asm/ptrace.h>
 
-typedef void pgm_check_handler_t(struct pt_regs *, long, unsigned long);
-extern pgm_check_handler_t *pgm_check_table[128];
-pgm_check_handler_t do_protection_exception;
-pgm_check_handler_t do_dat_exception;
+void do_protection_exception(struct pt_regs *, long, unsigned long);
+void do_dat_exception(struct pt_regs *, long, unsigned long);
+void do_asce_exception(struct pt_regs *, long, unsigned long);
 
 extern int sysctl_userprocess_debug;
 
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index d61967e2eab..7a0fd426ca9 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -9,8 +9,8 @@
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
-#include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -56,15 +56,28 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING)
 _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
 		_TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8)
+_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 
 #define BASED(name) name-system_call(%r13)
 
+	.macro SPP newpp
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
+	jz	.+8
+	.insn	s,0xb2800000,\newpp
+#endif
+	.endm
+
 	.macro	HANDLE_SIE_INTERCEPT
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	lg	%r3,__LC_SIE_HOOK
-	ltgr	%r3,%r3
+	tm	__TI_flags+6(%r12),_TIF_SIE>>8
 	jz	0f
-	basr	%r14,%r3
+	SPP	__LC_CMF_HPP			# set host id
+	clc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
+	jl	0f
+	clc	SP_PSW+8(8,%r15),BASED(.Lsie_done)
+	jhe	0f
+	mvc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
 0:
 #endif
 	.endm
@@ -206,8 +219,7 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
  * Returns:
  *  gpr2 = prev
  */
-	.globl	__switch_to
-__switch_to:
+ENTRY(__switch_to)
 	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
 	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
 	tm	__TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending?
@@ -232,8 +244,7 @@ __critical_start:
  * are executed with interrupts enabled.
  */
 
-	.globl	system_call
-system_call:
+ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
 sysc_saveall:
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
@@ -395,8 +406,7 @@ sysc_tracenogo:
 #
 # a new process exits the kernel with ret_from_fork
 #
-	.globl	ret_from_fork
-ret_from_fork:
+ENTRY(ret_from_fork)
 	lg	%r13,__LC_SVC_NEW_PSW+8
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
@@ -411,8 +421,7 @@ ret_from_fork:
 # kernel_execve function needs to deal with pt_regs that is not
 # at the usual place
 #
-	.globl	kernel_execve
-kernel_execve:
+ENTRY(kernel_execve)
 	stmg	%r12,%r15,96(%r15)
 	lgr	%r14,%r15
 	aghi	%r15,-SP_SIZE
@@ -442,8 +451,7 @@ kernel_execve:
  * Program check handler routine
  */
 
-	.globl	pgm_check_handler
-pgm_check_handler:
+ENTRY(pgm_check_handler)
 /*
  * First we need to check for a special case:
  * Single stepping an instruction that disables the PER event mask will
@@ -465,6 +473,7 @@ pgm_check_handler:
 	xc	SP_ILC(4,%r15),SP_ILC(%r15)
 	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	pgm_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -472,7 +481,6 @@ pgm_check_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
 	LAST_BREAK
 pgm_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	stg	%r11,SP_ARGS(%r15)
 	lgf	%r3,__LC_PGM_ILC	# load program interruption code
 	lg	%r4,__LC_TRANS_EXC_CODE
@@ -507,6 +515,7 @@ pgm_per_std:
 	CREATE_STACK_FRAME __LC_SAVE_AREA
 	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	pgm_no_vtime2
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -514,7 +523,6 @@ pgm_per_std:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
 	LAST_BREAK
 pgm_no_vtime2:
-	HANDLE_SIE_INTERCEPT
 	lg	%r1,__TI_task(%r12)
 	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
 	jz	kernel_per
@@ -571,14 +579,14 @@ kernel_per:
 /*
  * IO interrupt handler routine
  */
-	.globl io_int_handler
-io_int_handler:
+ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+40
 	CREATE_STACK_FRAME __LC_SAVE_AREA+40
 	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	io_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -586,7 +594,6 @@ io_int_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
 	LAST_BREAK
 io_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	brasl	%r14,do_IRQ		# call standard irq handler
@@ -706,14 +713,14 @@ io_notify_resume:
 /*
  * External interrupt handler routine
  */
-	.globl	ext_int_handler
-ext_int_handler:
+ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+40
 	CREATE_STACK_FRAME __LC_SAVE_AREA+40
 	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	ext_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -721,7 +728,6 @@ ext_int_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
 	LAST_BREAK
 ext_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	lghi	%r1,4096
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
@@ -736,8 +742,7 @@ __critical_end:
 /*
  * Machine check handler routines
  */
-	.globl mcck_int_handler
-mcck_int_handler:
+ENTRY(mcck_int_handler)
 	stck	__LC_MCCK_CLOCK
 	la	%r1,4095		# revalidate r1
 	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
@@ -785,6 +790,7 @@ mcck_int_main:
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	__LC_MCCK_CODE+2,0x08	# mwp of old psw valid?
 	jno	mcck_no_vtime		# no -> no timer update
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	mcck_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_MCCK_ENTER_TIMER,__LC_USER_TIMER
@@ -804,7 +810,6 @@ mcck_no_vtime:
 	stosm	__SF_EMPTY(%r15),0x04	# turn dat on
 	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jno	mcck_return
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
@@ -823,8 +828,7 @@ mcck_done:
  */
 #ifdef CONFIG_SMP
 	__CPUINIT
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	spt	restart_vtime-restart_base(%r1)
@@ -851,8 +855,7 @@ restart_vtime:
 /*
  * If we do not run with SMP enabled, let the new CPU crash ...
  */
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	lpswe	restart_crash-restart_base(%r1)
@@ -1036,6 +1039,56 @@ cleanup_io_restore_insn:
 .Lcritical_end:
 		.quad	__critical_end
 
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+ENTRY(sie64a)
+	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
+	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
+	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
+	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	oi	__TI_flags+6(%r14),_TIF_SIE>>8
+sie_loop:
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
+	jnz	sie_exit
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	SPP	__SF_EMPTY(%r15)		# set guest id
+	sie	0(%r14)
+sie_done:
+	SPP	__LC_CMF_HPP			# set host id
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+sie_exit:
+	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lghi	%r2,0
+	br	%r14
+sie_fault:
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lghi	%r2,-EFAULT
+	br	%r14
+
+	.align	8
+.Lsie_loop:
+	.quad	sie_loop
+.Lsie_done:
+	.quad	sie_done
+
+	.section __ex_table,"a"
+	.quad	sie_loop,sie_fault
+	.previous
+#endif
+
 		.section .rodata, "a"
 #define SYSCALL(esa,esame,emu)	.long esame
 	.globl	sys_call_table
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index fb317bf2c37..2d781bab37b 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -22,6 +22,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
@@ -383,8 +384,7 @@ iplstart:
 # doesn't need a builtin ipl record.
 #
 	.org	0x800
-	.globl	start
-start:
+ENTRY(start)
 	stm	%r0,%r15,0x07b0		# store registers
 	basr	%r12,%r0
 .base:
@@ -448,8 +448,7 @@ start:
 # or linload or SALIPL
 #
 	.org	0x10000
-	.globl	startup
-startup:
+ENTRY(startup)
 	basr	%r13,0			# get base
 .LPG0:
 	xc	0x200(256),0x200	# partially clear lowcore
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index b8f8dc12610..f21954b44dc 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -11,13 +11,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 
@@ -45,7 +45,7 @@ startup_continue:
 					# virtual and never return ...
 	.align	8
 .Lentry:.long	0x00080000,0x80000000 + _stext
-.Lctl:	.long	0x04b50002		# cr0: various things
+.Lctl:	.long	0x04b50000		# cr0: various things
 	.long	0			# cr1: primary space segment table
 	.long	.Lduct			# cr2: dispatchable unit control table
 	.long	0			# cr3: instruction authorization
@@ -78,8 +78,7 @@ startup_continue:
 .Lbase_cc:
 	.long	sched_clock_base_cc
 
-	.globl	_ehead
-_ehead:
+ENTRY(_ehead)
 
 #ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
@@ -88,8 +87,8 @@ _ehead:
 #
 # startup-code, running in absolute addressing mode
 #
-	.globl	_stext
-_stext:	basr	%r13,0			# get base
+ENTRY(_stext)
+	basr	%r13,0			# get base
 .LPG3:
 # check control registers
 	stctl	%c0,%c15,0(%r15)
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index cdef6871741..ae5d492b069 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -11,13 +11,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	larl	%r1,sched_clock_base_cc
 	mvc	0(8,%r1),__LC_LAST_UPDATE_CLOCK
 	larl	%r13,.LPG1		# get base
@@ -46,7 +46,7 @@ startup_continue:
 	.align	16
 .LPG1:
 .Lentry:.quad	0x0000000180000000,_stext
-.Lctl:	.quad	0x04350002		# cr0: various things
+.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
 	.quad	0			# cr3: instruction authorization
@@ -76,8 +76,7 @@ startup_continue:
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
 
-	.globl	_ehead
-_ehead:
+ENTRY(_ehead)
 
 #ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
@@ -86,8 +85,8 @@ _ehead:
 #
 # startup-code, running in absolute addressing mode
 #
-	.globl	_stext
-_stext:	basr	%r13,0			# get base
+ENTRY(_stext)
+	basr	%r13,0			# get base
 .LPG3:
 # check control registers
 	stctg	%c0,%c15,0(%r15)
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index e3264f6a972..1f4050d45f7 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -88,15 +88,6 @@ int show_interrupts(struct seq_file *p, void *v)
 }
 
 /*
- * For compatibilty only. S/390 specific setup of interrupts et al. is done
- * much later in init_channel_subsystem().
- */
-void __init init_IRQ(void)
-{
-	/* nothing... */
-}
-
-/*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
 asmlinkage void do_softirq(void)
@@ -144,28 +135,45 @@ void init_irq_proc(void)
 #endif
 
 /*
- * ext_int_hash[index] is the start of the list for all external interrupts
- * that hash to this index. With the current set of external interrupts
- * (0x1202 external call, 0x1004 cpu timer, 0x2401 hwc console, 0x4000
- * iucv and 0x2603 pfault) this is always the first element.
+ * ext_int_hash[index] is the list head for all external interrupts that hash
+ * to this index.
  */
+static struct list_head ext_int_hash[256];
 
 struct ext_int_info {
-	struct ext_int_info *next;
 	ext_int_handler_t handler;
 	u16 code;
+	struct list_head entry;
+	struct rcu_head rcu;
 };
 
-static struct ext_int_info *ext_int_hash[256];
+/* ext_int_hash_lock protects the handler lists for external interrupts */
+DEFINE_SPINLOCK(ext_int_hash_lock);
+
+static void __init init_external_interrupts(void)
+{
+	int idx;
+
+	for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
+		INIT_LIST_HEAD(&ext_int_hash[idx]);
+}
 
 static inline int ext_hash(u16 code)
 {
 	return (code + (code >> 9)) & 0xff;
 }
 
+static void ext_int_hash_update(struct rcu_head *head)
+{
+	struct ext_int_info *p = container_of(head, struct ext_int_info, rcu);
+
+	kfree(p);
+}
+
 int register_external_interrupt(u16 code, ext_int_handler_t handler)
 {
 	struct ext_int_info *p;
+	unsigned long flags;
 	int index;
 
 	p = kmalloc(sizeof(*p), GFP_ATOMIC);
@@ -174,33 +182,27 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler)
 	p->code = code;
 	p->handler = handler;
 	index = ext_hash(code);
-	p->next = ext_int_hash[index];
-	ext_int_hash[index] = p;
+
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	list_add_rcu(&p->entry, &ext_int_hash[index]);
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(register_external_interrupt);
 
 int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 {
-	struct ext_int_info *p, *q;
-	int index;
+	struct ext_int_info *p;
+	unsigned long flags;
+	int index = ext_hash(code);
 
-	index = ext_hash(code);
-	q = NULL;
-	p = ext_int_hash[index];
-	while (p) {
-		if (p->code == code && p->handler == handler)
-			break;
-		q = p;
-		p = p->next;
-	}
-	if (!p)
-		return -ENOENT;
-	if (q)
-		q->next = p->next;
-	else
-		ext_int_hash[index] = p->next;
-	kfree(p);
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
+		if (p->code == code && p->handler == handler) {
+			list_del_rcu(&p->entry);
+			call_rcu(&p->rcu, ext_int_hash_update);
+		}
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(unregister_external_interrupt);
@@ -224,15 +226,22 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code,
 	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
 	if (code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
+
 	index = ext_hash(code);
-	for (p = ext_int_hash[index]; p; p = p->next) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
 		if (likely(p->code == code))
 			p->handler(ext_int_code, param32, param64);
-	}
+	rcu_read_unlock();
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 
+void __init init_IRQ(void)
+{
+	init_external_interrupts();
+}
+
 static DEFINE_SPINLOCK(sc_irq_lock);
 static int sc_irq_refcount;
 
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 1e6a5579562..7e2c38ba137 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -5,21 +5,19 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 	.section .kprobes.text, "ax"
 
-	.globl ftrace_stub
-ftrace_stub:
+ENTRY(ftrace_stub)
 	br	%r14
 
-	.globl _mcount
-_mcount:
+ENTRY(_mcount)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
-	.globl ftrace_caller
-ftrace_caller:
+ENTRY(ftrace_caller)
 #endif
 	stm	%r2,%r5,16(%r15)
 	bras	%r1,2f
@@ -41,8 +39,7 @@ ftrace_caller:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	l	%r2,100(%r15)
 	l	%r3,152(%r15)
-	.globl	ftrace_graph_caller
-ftrace_graph_caller:
+ENTRY(ftrace_graph_caller)
 # The bras instruction gets runtime patched to call prepare_ftrace_return.
 # See ftrace_enable_ftrace_graph_caller. The patched instruction is:
 #	bras	%r14,prepare_ftrace_return
@@ -56,8 +53,7 @@ ftrace_graph_caller:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-	.globl	return_to_handler
-return_to_handler:
+ENTRY(return_to_handler)
 	stm	%r2,%r5,16(%r15)
 	st	%r14,56(%r15)
 	lr	%r0,%r15
diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S
index e73667286ac..f70cadec68f 100644
--- a/arch/s390/kernel/mcount64.S
+++ b/arch/s390/kernel/mcount64.S
@@ -5,21 +5,19 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 	.section .kprobes.text, "ax"
 
-	.globl ftrace_stub
-ftrace_stub:
+ENTRY(ftrace_stub)
 	br	%r14
 
-	.globl _mcount
-_mcount:
+ENTRY(_mcount)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
-	.globl ftrace_caller
-ftrace_caller:
+ENTRY(ftrace_caller)
 #endif
 	larl	%r1,function_trace_stop
 	icm	%r1,0xf,0(%r1)
@@ -37,8 +35,7 @@ ftrace_caller:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	lg	%r2,168(%r15)
 	lg	%r3,272(%r15)
-	.globl	ftrace_graph_caller
-ftrace_graph_caller:
+ENTRY(ftrace_graph_caller)
 # The bras instruction gets runtime patched to call prepare_ftrace_return.
 # See ftrace_enable_ftrace_graph_caller. The patched instruction is:
 #	bras	%r14,prepare_ftrace_return
@@ -52,8 +49,7 @@ ftrace_graph_caller:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-	.globl	return_to_handler
-return_to_handler:
+ENTRY(return_to_handler)
 	stmg	%r2,%r5,32(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-160
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index cb899d9f850..303d961c3bb 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -6,14 +6,15 @@
  *    Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com)
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #
 # do_reipl_asm
 # Parameter: r2 = schid of reipl device
 #
-		.globl	do_reipl_asm
-do_reipl_asm:	basr	%r13,0
+ENTRY(do_reipl_asm)
+		basr	%r13,0
 .Lpg0:		lpsw	.Lnewpsw-.Lpg0(%r13)
 .Lpg1:		# do store status of all registers
 
diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S
index 9eabbc90795..78eb7cfbd3d 100644
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@@ -4,6 +4,7 @@
  *		 Denis Joseph Barrow,
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #
@@ -11,8 +12,8 @@
 # Parameter: r2 = schid of reipl device
 #
 
-		.globl	do_reipl_asm
-do_reipl_asm:	basr	%r13,0
+ENTRY(do_reipl_asm)
+		basr	%r13,0
 .Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
 .Lpg1:		# do store status of all registers
 
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
index 3b456b80bce..c91d70aede9 100644
--- a/arch/s390/kernel/relocate_kernel.S
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 /*
  * moves the new kernel to its destination...
  * %r2 = pointer to first kimage_entry_t
@@ -22,8 +24,7 @@
  */
 
 	.text
-	.globl		relocate_kernel
-	relocate_kernel:
+ENTRY(relocate_kernel)
 		basr	%r13,0		# base address
 	.base:
 		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
@@ -112,6 +113,7 @@
 		.byte	0
 		.align	8
 	relocate_kernel_end:
+	.align 8
 	.globl	relocate_kernel_len
 	relocate_kernel_len:
 		.quad	relocate_kernel_end - relocate_kernel
diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S
index 1f9ea2067b5..7c3ce589a7f 100644
--- a/arch/s390/kernel/relocate_kernel64.S
+++ b/arch/s390/kernel/relocate_kernel64.S
@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 /*
  * moves the new kernel to its destination...
  * %r2 = pointer to first kimage_entry_t
@@ -23,8 +25,7 @@
  */
 
 	.text
-	.globl		relocate_kernel
-	relocate_kernel:
+ENTRY(relocate_kernel)
 		basr	%r13,0		# base address
 	.base:
 		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
@@ -115,6 +116,7 @@
 		.byte	0
 		.align	8
 	relocate_kernel_end:
+	.align 8
 	.globl	relocate_kernel_len
 	relocate_kernel_len:
 		.quad	relocate_kernel_end - relocate_kernel
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 656fcbb9bd8..57b536649b0 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -1,6 +1,10 @@
 #include <linux/module.h>
+#include <linux/kvm_host.h>
 #include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+EXPORT_SYMBOL(sie64a);
+#endif
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index 2e82fdd8932..95792d846bb 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 LC_EXT_NEW_PSW		= 0x58			# addr of ext int handler
 LC_EXT_NEW_PSW_64	= 0x1b0			# addr of ext int handler 64 bit
 LC_EXT_INT_PARAM	= 0x80			# addr of ext int parameter
@@ -260,8 +262,7 @@ _sclp_print:
 #   R2	= 0 on success, 1 on failure
 #
 
-	.globl _sclp_print_early
-_sclp_print_early:
+ENTRY(_sclp_print_early)
 	stm	%r6,%r15,24(%r15)		# save registers
 	ahi	%r15,-96			# create stack frame
 #ifdef CONFIG_64BIT
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 1d55c95f617..a6d85c0a7f2 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -654,7 +654,8 @@ int __cpu_disable(void)
 	/* disable all external interrupts */
 	cr_parms.orvals[0] = 0;
 	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 11 |
-				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  4);
+				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  5 |
+				1 <<  4);
 	/* disable all I/O interrupts */
 	cr_parms.orvals[6] = 0;
 	cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 |
diff --git a/arch/s390/kernel/switch_cpu.S b/arch/s390/kernel/switch_cpu.S
index 20530dd2eab..bfe070bc765 100644
--- a/arch/s390/kernel/switch_cpu.S
+++ b/arch/s390/kernel/switch_cpu.S
@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
@@ -16,9 +17,7 @@
 #	     %r6 - destination cpu
 
 	.section .text
-	.align 4
-	.globl smp_switch_to_cpu
-smp_switch_to_cpu:
+ENTRY(smp_switch_to_cpu)
 	stm	%r6,%r15,__SF_GPRS(%r15)
 	lr	%r1,%r15
 	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -33,8 +32,7 @@ smp_switch_to_cpu:
 	brc	2,2b			/* busy, try again */
 3:	j	3b
 
-	.globl	smp_restart_cpu
-smp_restart_cpu:
+ENTRY(smp_restart_cpu)
 	basr	%r13,0
 0:	la	%r1,.gprregs_addr-0b(%r13)
 	l	%r1,0(%r1)
diff --git a/arch/s390/kernel/switch_cpu64.S b/arch/s390/kernel/switch_cpu64.S
index 5be3f43898f..fcc42d799e4 100644
--- a/arch/s390/kernel/switch_cpu64.S
+++ b/arch/s390/kernel/switch_cpu64.S
@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
@@ -16,9 +17,7 @@
 #	     %r6 - destination cpu
 
 	.section .text
-	.align 4
-	.globl smp_switch_to_cpu
-smp_switch_to_cpu:
+ENTRY(smp_switch_to_cpu)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -31,8 +30,7 @@ smp_switch_to_cpu:
 	brc	2,2b			/* busy, try again */
 3:	j	3b
 
-	.globl	smp_restart_cpu
-smp_restart_cpu:
+ENTRY(smp_restart_cpu)
 	larl	%r1,.gprregs
 	lmg	%r0,%r15,0(%r1)
 1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index 1f066e46e83..51bcdb50a23 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -7,6 +7,7 @@
  *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
  */
 
+#include <linux/linkage.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -22,9 +23,7 @@
  * This function runs with disabled interrupts.
  */
 	.section .text
-	.align	4
-	.globl swsusp_arch_suspend
-swsusp_arch_suspend:
+ENTRY(swsusp_arch_suspend)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -112,8 +111,7 @@ swsusp_arch_suspend:
  * Then we return to the function that called swsusp_arch_suspend().
  * swsusp_arch_resume() runs with disabled interrupts.
  */
-	.globl swsusp_arch_resume
-swsusp_arch_resume:
+ENTRY(swsusp_arch_resume)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index a63d34c3611..e9372c77cce 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
-#include <linux/tracehook.h>
+#include <linux/ptrace.h>
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
@@ -43,14 +43,10 @@
 #include <asm/debug.h>
 #include "entry.h"
 
-pgm_check_handler_t *pgm_check_table[128];
+void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long);
 
 int show_unhandled_signals;
 
-extern pgm_check_handler_t do_protection_exception;
-extern pgm_check_handler_t do_dat_exception;
-extern pgm_check_handler_t do_asce_exception;
-
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
 
 #ifndef CONFIG_64BIT
@@ -329,10 +325,17 @@ static inline void __user *get_psw_address(struct pt_regs *regs,
 
 void __kprobes do_per_trap(struct pt_regs *regs)
 {
+	siginfo_t info;
+
 	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
 		return;
-	if (current->ptrace)
-		force_sig(SIGTRAP, current);
+	if (!current->ptrace)
+		return;
+	info.si_signo = SIGTRAP;
+	info.si_errno = 0;
+	info.si_code = TRAP_HWBKPT;
+	info.si_addr = (void *) current->thread.per_event.address;
+	force_sig_info(SIGTRAP, &info, current);
 }
 
 static void default_trap_handler(struct pt_regs *regs, long pgm_int_code,
@@ -425,9 +428,13 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
 			return;
 		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
-			if (current->ptrace)
-				force_sig(SIGTRAP, current);
-			else
+			if (current->ptrace) {
+				info.si_signo = SIGTRAP;
+				info.si_errno = 0;
+				info.si_code = TRAP_BRKPT;
+				info.si_addr = location;
+				force_sig_info(SIGTRAP, &info, current);
+			} else
 				signal = SIGILL;
 #ifdef CONFIG_MATHEMU
 		} else if (opcode[0] == 0xb3) {
@@ -489,9 +496,8 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 
 
 #ifdef CONFIG_MATHEMU
-asmlinkage void specification_exception(struct pt_regs *regs,
-					long pgm_int_code,
-					unsigned long trans_exc_code)
+void specification_exception(struct pt_regs *regs, long pgm_int_code,
+			     unsigned long trans_exc_code)
 {
         __u8 opcode[6];
 	__u16 __user *location = NULL;
@@ -648,7 +654,7 @@ static void space_switch_exception(struct pt_regs *regs, long pgm_int_code,
 	do_trap(pgm_int_code, SIGILL, "space switch event", regs, &info);
 }
 
-asmlinkage void __kprobes kernel_stack_overflow(struct pt_regs * regs)
+void __kprobes kernel_stack_overflow(struct pt_regs * regs)
 {
 	bust_spinlocks(1);
 	printk("Kernel stack overflow.\n");
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 860d26514c0..3975722bb19 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -10,5 +10,5 @@ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
-kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 03c716a0f01..c86f6ae43f7 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -1,5 +1,5 @@
 /*
- * gaccess.h -  access guest memory
+ * access.h -  access guest memory
  *
  * Copyright IBM Corp. 2008,2009
  *
@@ -22,20 +22,13 @@ static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
 					       unsigned long guestaddr)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestaddr < 2 * PAGE_SIZE)
 		guestaddr += prefix;
 	else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE))
 		guestaddr -= prefix;
 
-	if (guestaddr > memsize)
-		return (void __user __force *) ERR_PTR(-EFAULT);
-
-	guestaddr += origin;
-
-	return (void __user *) guestaddr;
+	return (void __user *) gmap_fault(guestaddr, vcpu->arch.gmap);
 }
 
 static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr,
@@ -141,11 +134,11 @@ static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr,
 
 static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu,
 				       unsigned long guestdest,
-				       const void *from, unsigned long n)
+				       void *from, unsigned long n)
 {
 	int rc;
 	unsigned long i;
-	const u8 *data = from;
+	u8 *data = from;
 
 	for (i = 0; i < n; i++) {
 		rc = put_guest_u8(vcpu, guestdest++, *(data++));
@@ -155,12 +148,95 @@ static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static inline int __copy_to_guest_fast(struct kvm_vcpu *vcpu,
+				       unsigned long guestdest,
+				       void *from, unsigned long n)
+{
+	int r;
+	void __user *uptr;
+	unsigned long size;
+
+	if (guestdest + n < guestdest)
+		return -EFAULT;
+
+	/* simple case: all within one segment table entry? */
+	if ((guestdest & PMD_MASK) == ((guestdest+n) & PMD_MASK)) {
+		uptr = (void __user *) gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, n);
+
+		if (r)
+			r = -EFAULT;
+
+		goto out;
+	}
+
+	/* copy first segment */
+	uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	size = PMD_SIZE - (guestdest & ~PMD_MASK);
+
+	r = copy_to_user(uptr, from, size);
+
+	if (r) {
+		r = -EFAULT;
+		goto out;
+	}
+	from += size;
+	n -= size;
+	guestdest += size;
+
+	/* copy full segments */
+	while (n >= PMD_SIZE) {
+		uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, PMD_SIZE);
+
+		if (r) {
+			r = -EFAULT;
+			goto out;
+		}
+		from += PMD_SIZE;
+		n -= PMD_SIZE;
+		guestdest += PMD_SIZE;
+	}
+
+	/* copy the tail segment */
+	if (n) {
+		uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, n);
+
+		if (r)
+			r = -EFAULT;
+	}
+out:
+	return r;
+}
+
+static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
+					 unsigned long guestdest,
+					 void *from, unsigned long n)
+{
+	return __copy_to_guest_fast(vcpu, guestdest, from, n);
+}
+
 static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
-				const void *from, unsigned long n)
+				void *from, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -177,15 +253,7 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
 	else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE))
 		guestdest -= prefix;
 
-	if (guestdest + n > memsize)
-		return -EFAULT;
-
-	if (guestdest + n < guestdest)
-		return -EFAULT;
-
-	guestdest += origin;
-
-	return copy_to_user((void __user *) guestdest, from, n);
+	return __copy_to_guest_fast(vcpu, guestdest, from, n);
 slowpath:
 	return __copy_to_guest_slow(vcpu, guestdest, from, n);
 }
@@ -206,74 +274,113 @@ static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to,
 	return 0;
 }
 
-static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
-				  unsigned long guestsrc, unsigned long n)
+static inline int __copy_from_guest_fast(struct kvm_vcpu *vcpu, void *to,
+					 unsigned long guestsrc,
+					 unsigned long n)
 {
-	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	int r;
+	void __user *uptr;
+	unsigned long size;
 
-	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
-		goto slowpath;
+	if (guestsrc + n < guestsrc)
+		return -EFAULT;
 
-	if ((guestsrc < prefix) && (guestsrc + n > prefix))
-		goto slowpath;
+	/* simple case: all within one segment table entry? */
+	if ((guestsrc & PMD_MASK) == ((guestsrc+n) & PMD_MASK)) {
+		uptr = (void __user *) gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	if ((guestsrc < prefix + 2 * PAGE_SIZE)
-	    && (guestsrc + n > prefix + 2 * PAGE_SIZE))
-		goto slowpath;
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
 
-	if (guestsrc < 2 * PAGE_SIZE)
-		guestsrc += prefix;
-	else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
-		guestsrc -= prefix;
+		r = copy_from_user(to, uptr, n);
 
-	if (guestsrc + n > memsize)
-		return -EFAULT;
+		if (r)
+			r = -EFAULT;
 
-	if (guestsrc + n < guestsrc)
-		return -EFAULT;
+		goto out;
+	}
 
-	guestsrc += origin;
+	/* copy first segment */
+	uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	return copy_from_user(to, (void __user *) guestsrc, n);
-slowpath:
-	return __copy_from_guest_slow(vcpu, to, guestsrc, n);
-}
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
 
-static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
-					 unsigned long guestdest,
-					 const void *from, unsigned long n)
-{
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	size = PMD_SIZE - (guestsrc & ~PMD_MASK);
 
-	if (guestdest + n > memsize)
-		return -EFAULT;
+	r = copy_from_user(to, uptr, size);
 
-	if (guestdest + n < guestdest)
-		return -EFAULT;
+	if (r) {
+		r = -EFAULT;
+		goto out;
+	}
+	to += size;
+	n -= size;
+	guestsrc += size;
+
+	/* copy full segments */
+	while (n >= PMD_SIZE) {
+		uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_from_user(to, uptr, PMD_SIZE);
+
+		if (r) {
+			r = -EFAULT;
+			goto out;
+		}
+		to += PMD_SIZE;
+		n -= PMD_SIZE;
+		guestsrc += PMD_SIZE;
+	}
+
+	/* copy the tail segment */
+	if (n) {
+		uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	guestdest += origin;
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
 
-	return copy_to_user((void __user *) guestdest, from, n);
+		r = copy_from_user(to, uptr, n);
+
+		if (r)
+			r = -EFAULT;
+	}
+out:
+	return r;
 }
 
 static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
 					   unsigned long guestsrc,
 					   unsigned long n)
 {
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+}
 
-	if (guestsrc + n > memsize)
-		return -EFAULT;
+static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
+				  unsigned long guestsrc, unsigned long n)
+{
+	unsigned long prefix  = vcpu->arch.sie_block->prefix;
 
-	if (guestsrc + n < guestsrc)
-		return -EFAULT;
+	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
+		goto slowpath;
 
-	guestsrc += origin;
+	if ((guestsrc < prefix) && (guestsrc + n > prefix))
+		goto slowpath;
+
+	if ((guestsrc < prefix + 2 * PAGE_SIZE)
+	    && (guestsrc + n > prefix + 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if (guestsrc < 2 * PAGE_SIZE)
+		guestsrc += prefix;
+	else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
+		guestsrc -= prefix;
 
-	return copy_from_user(to, (void __user *) guestsrc, n);
+	return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+slowpath:
+	return __copy_from_guest_slow(vcpu, to, guestsrc, n);
 }
 #endif
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index f7b6df45d8b..c7c51898984 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -105,6 +105,7 @@ static intercept_handler_t instruction_handlers[256] = {
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xe5] = kvm_s390_handle_e5,
 	[0xeb] = handle_lctlg,
 };
 
@@ -159,22 +160,42 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 static int handle_validity(struct kvm_vcpu *vcpu)
 {
+	unsigned long vmaddr;
 	int viwhy = vcpu->arch.sie_block->ipb >> 16;
 	int rc;
 
 	vcpu->stat.exit_validity++;
-	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
-		<= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) {
-		rc = fault_in_pages_writeable((char __user *)
-			 vcpu->arch.sie_block->gmsor +
-			 vcpu->arch.sie_block->prefix,
-			 2*PAGE_SIZE);
-		if (rc)
+	if (viwhy == 0x37) {
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
+			/* user will receive sigsegv, exit to user */
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
 			/* user will receive sigsegv, exit to user */
 			rc = -EOPNOTSUPP;
+			goto out;
+		}
 	} else
 		rc = -EOPNOTSUPP;
 
+out:
 	if (rc)
 		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
 			   viwhy);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 35c21bf910c..c9aeb4b4d0b 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -128,6 +128,10 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
+		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->emerg.code);
+		if (rc == -EFAULT)
+			exception = 1;
+
 		rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
 			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
 		if (rc == -EFAULT)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 67345ae7ce8..f17296e4fc8 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -62,6 +62,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
 	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
 	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
@@ -189,7 +190,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
+	kvm->arch.gmap = gmap_alloc(current->mm);
+	if (!kvm->arch.gmap)
+		goto out_nogmap;
+
 	return 0;
+out_nogmap:
+	debug_unregister(kvm->arch.dbf);
 out_nodbf:
 	free_page((unsigned long)(kvm->arch.sca));
 out_err:
@@ -234,11 +241,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
+	gmap_free(kvm->arch.gmap);
 }
 
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
 	return 0;
 }
 
@@ -284,8 +293,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
-	set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
 	vcpu->arch.sie_block->ecb   = 6;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -453,6 +461,7 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
+	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -461,6 +470,7 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
+	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
@@ -474,17 +484,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	sigset_t sigsaved;
 
 rerun_vcpu:
-	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
-			kvm_s390_vcpu_set_mem(vcpu);
-
-	/* verify, that memory has been registered */
-	if (!vcpu->arch.sie_block->gmslm) {
-		vcpu_put(vcpu);
-		VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
-		return -EINVAL;
-	}
-
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -545,7 +544,7 @@ rerun_vcpu:
 	return rc;
 }
 
-static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
+static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
 		       unsigned long n, int prefix)
 {
 	if (prefix)
@@ -562,7 +561,7 @@ static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
  */
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 {
-	const unsigned char archmode = 1;
+	unsigned char archmode = 1;
 	int prefix;
 
 	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
@@ -680,10 +679,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr)
 		return -EINVAL;
 
-	if (mem->userspace_addr & (PAGE_SIZE - 1))
+	if (mem->userspace_addr & 0xffffful)
 		return -EINVAL;
 
-	if (mem->memory_size & (PAGE_SIZE - 1))
+	if (mem->memory_size & 0xffffful)
 		return -EINVAL;
 
 	if (!user_alloc)
@@ -697,15 +696,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot old,
 				int user_alloc)
 {
-	int i;
-	struct kvm_vcpu *vcpu;
+	int rc;
 
-	/* request update of sie control block for all available vcpus */
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
-			continue;
-		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
-	}
+
+	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
+		mem->guest_phys_addr, mem->memory_size);
+	if (rc)
+		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
+	return;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a7b7586626d..99b0b759711 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -58,35 +58,9 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
-static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.sie_block->gmslm
-		- vcpu->arch.sie_block->gmsor
-		- VIRTIODESCSPACE + 1ul;
-}
-
-static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
-{
-	int idx;
-	struct kvm_memory_slot *mem;
-	struct kvm_memslots *memslots;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	memslots = kvm_memslots(vcpu->kvm);
-
-	mem = &memslots->memslots[0];
-
-	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
-	vcpu->arch.sie_block->gmslm =
-		mem->userspace_addr +
-		(mem->npages << PAGE_SHIFT) +
-		VIRTIODESCSPACE - 1ul;
-
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 73c47bd95db..39162636108 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -326,3 +326,52 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	}
 	return -EOPNOTSUPP;
 }
+
+static int handle_tprot(struct kvm_vcpu *vcpu)
+{
+	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	struct vm_area_struct *vma;
+
+	vcpu->stat.instruction_tprot++;
+
+	/* we only handle the Linux memory detection case:
+	 * access key == 0
+	 * guest DAT == off
+	 * everything else goes to userspace. */
+	if (address2 & 0xf0)
+		return -EOPNOTSUPP;
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
+		return -EOPNOTSUPP;
+
+
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm,
+			(unsigned long) __guestaddr_to_user(vcpu, address1));
+	if (!vma) {
+		up_read(&current->mm->mmap_sem);
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	}
+
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (1ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (2ul << 44);
+
+	up_read(&current->mm->mmap_sem);
+	return 0;
+}
+
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
+{
+	/* For e5xx... instructions we only handle TPROT */
+	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+		return handle_tprot(vcpu);
+	return -EOPNOTSUPP;
+}
+
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
deleted file mode 100644
index 5faa1b1b23f..00000000000
--- a/arch/s390/kvm/sie64a.S
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * sie64a.S - low level sie call
- *
- * Copyright IBM Corp. 2008,2010
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
- *		 Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
- */
-
-#include <linux/errno.h>
-#include <asm/asm-offsets.h>
-#include <asm/setup.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-#include <asm/thread_info.h>
-
-_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
-
-/*
- * offsets into stackframe
- * SP_	= offsets into stack sie64 is called with
- * SPI_ = offsets into irq stack
- */
-SP_GREGS = __SF_EMPTY
-SP_HOOK  = __SF_EMPTY+8
-SP_GPP	 = __SF_EMPTY+16
-SPI_PSW  = STACK_FRAME_OVERHEAD + __PT_PSW
-
-
-	.macro SPP newpp
-	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
-	jz	0f
-	.insn	s,0xb2800000,\newpp
-0:
-	.endm
-
-sie_irq_handler:
-	SPP	__LC_CMF_HPP			# set host id
-	larl	%r2,sie_inst
-	clg	%r2,SPI_PSW+8(0,%r15)		# intercepted sie
-	jne	1f
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	lg	%r2,__LC_THREAD_INFO		# pointer thread_info struct
-	tm	__TI_flags+7(%r2),_TIF_EXIT_SIE
-	jz	0f
-	larl	%r2,sie_exit			# work pending, leave sie
-	stg	%r2,SPI_PSW+8(0,%r15)
-	br	%r14
-0:	larl	%r2,sie_reenter			# re-enter with guest id
-	stg	%r2,SPI_PSW+8(0,%r15)
-1:	br	%r14
-
-/*
- * sie64a calling convention:
- * %r2 pointer to sie control block
- * %r3 guest register save area
- */
-	.globl	sie64a
-sie64a:
-	stg	%r3,SP_GREGS(%r15)		# save guest register save area
-	stmg	%r6,%r14,__SF_GPRS(%r15)	# save registers on entry
-	lgr	%r14,%r2			# pointer to sie control block
-	larl	%r5,sie_irq_handler
-	stg	%r2,SP_GPP(%r15)
-	stg	%r5,SP_HOOK(%r15)		# save hook target
-	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
-sie_reenter:
-	mvc	__LC_SIE_HOOK(8),SP_HOOK(%r15)
-	SPP	SP_GPP(%r15)			# set guest id
-sie_inst:
-	sie	0(%r14)
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	SPP	__LC_CMF_HPP			# set host id
-sie_exit:
-	lg	%r14,SP_GREGS(%r15)
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lghi	%r2,0
-	lmg	%r6,%r14,__SF_GPRS(%r15)
-	br	%r14
-
-sie_err:
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	SPP	__LC_CMF_HPP			# set host id
-	lg	%r14,SP_GREGS(%r15)
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lghi	%r2,-EFAULT
-	lmg	%r6,%r14,__SF_GPRS(%r15)
-	br	%r14
-
-	.section __ex_table,"a"
-	.quad	sie_inst,sie_err
-	.quad	sie_exit,sie_err
-	.quad	sie_reenter,sie_err
-	.previous
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 702276f5e2f..d6a50c1fb2e 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -189,10 +189,8 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
-	if ((copy_from_user(&tmp, (void __user *)
-		(address + vcpu->arch.sie_block->gmsor) , 1)) ||
-	   (copy_from_user(&tmp, (void __user *)(address +
-			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
+	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+	   copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */
 	}
diff --git a/arch/s390/lib/qrnnd.S b/arch/s390/lib/qrnnd.S
index eb1df632e74..d321329130e 100644
--- a/arch/s390/lib/qrnnd.S
+++ b/arch/s390/lib/qrnnd.S
@@ -1,5 +1,7 @@
 # S/390 __udiv_qrnnd
 
+#include <linux/linkage.h>
+
 # r2 : &__r
 # r3 : upper half of 64 bit word n
 # r4 : lower half of 64 bit word n
@@ -8,8 +10,7 @@
 # the quotient q is to be returned
 
 	.text
-	.globl __udiv_qrnnd
-__udiv_qrnnd:
+ENTRY(__udiv_qrnnd)
 	st    %r2,24(%r15)	  # store pointer to reminder for later
 	lr    %r0,%r3		  # reload n
 	lr    %r1,%r4
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 095f782a551..9564fc779b2 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -303,9 +303,24 @@ static inline int do_exception(struct pt_regs *regs, int access,
 	flags = FAULT_FLAG_ALLOW_RETRY;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
-retry:
 	down_read(&mm->mmap_sem);
 
+#ifdef CONFIG_PGSTE
+	if (test_tsk_thread_flag(current, TIF_SIE) && S390_lowcore.gmap) {
+		address = gmap_fault(address,
+				     (struct gmap *) S390_lowcore.gmap);
+		if (address == -EFAULT) {
+			fault = VM_FAULT_BADMAP;
+			goto out_up;
+		}
+		if (address == -ENOMEM) {
+			fault = VM_FAULT_OOM;
+			goto out_up;
+		}
+	}
+#endif
+
+retry:
 	fault = VM_FAULT_BADMAP;
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -356,6 +371,7 @@ retry:
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			down_read(&mm->mmap_sem);
 			goto retry;
 		}
 	}
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index a4d856db915..597bb2d27c3 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -35,7 +35,7 @@ int arch_prepare_hugepage(struct page *page)
 	if (MACHINE_HAS_HPAGE)
 		return 0;
 
-	ptep = (pte_t *) pte_alloc_one(&init_mm, address);
+	ptep = (pte_t *) pte_alloc_one(&init_mm, addr);
 	if (!ptep)
 		return -ENOMEM;
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 37a23c22370..2adb23938a7 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/quicklist.h>
 #include <linux/rcupdate.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/pgtable.h>
@@ -133,30 +134,374 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 }
 #endif
 
-static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+#ifdef CONFIG_PGSTE
+
+/**
+ * gmap_alloc - allocate a guest address space
+ * @mm: pointer to the parent mm_struct
+ *
+ * Returns a guest address space structure.
+ */
+struct gmap *gmap_alloc(struct mm_struct *mm)
 {
-	unsigned int old, new;
+	struct gmap *gmap;
+	struct page *page;
+	unsigned long *table;
 
-	do {
-		old = atomic_read(v);
-		new = old ^ bits;
-	} while (atomic_cmpxchg(v, old, new) != old);
-	return new;
+	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL);
+	if (!gmap)
+		goto out;
+	INIT_LIST_HEAD(&gmap->crst_list);
+	gmap->mm = mm;
+	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	if (!page)
+		goto out_free;
+	list_add(&page->lru, &gmap->crst_list);
+	table = (unsigned long *) page_to_phys(page);
+	crst_table_init(table, _REGION1_ENTRY_EMPTY);
+	gmap->table = table;
+	list_add(&gmap->list, &mm->context.gmap_list);
+	return gmap;
+
+out_free:
+	kfree(gmap);
+out:
+	return NULL;
 }
+EXPORT_SYMBOL_GPL(gmap_alloc);
 
-/*
- * page table entry allocation/free routines.
+static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
+{
+	struct gmap_pgtable *mp;
+	struct gmap_rmap *rmap;
+	struct page *page;
+
+	if (*table & _SEGMENT_ENTRY_INV)
+		return 0;
+	page = pfn_to_page(*table >> PAGE_SHIFT);
+	mp = (struct gmap_pgtable *) page->index;
+	list_for_each_entry(rmap, &mp->mapper, list) {
+		if (rmap->entry != table)
+			continue;
+		list_del(&rmap->list);
+		kfree(rmap);
+		break;
+	}
+	*table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+	return 1;
+}
+
+static void gmap_flush_tlb(struct gmap *gmap)
+{
+	if (MACHINE_HAS_IDTE)
+		__tlb_flush_idte((unsigned long) gmap->table |
+				 _ASCE_TYPE_REGION1);
+	else
+		__tlb_flush_global();
+}
+
+/**
+ * gmap_free - free a guest address space
+ * @gmap: pointer to the guest address space structure
  */
-#ifdef CONFIG_PGSTE
-static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
+void gmap_free(struct gmap *gmap)
+{
+	struct page *page, *next;
+	unsigned long *table;
+	int i;
+
+
+	/* Flush tlb. */
+	if (MACHINE_HAS_IDTE)
+		__tlb_flush_idte((unsigned long) gmap->table |
+				 _ASCE_TYPE_REGION1);
+	else
+		__tlb_flush_global();
+
+	/* Free all segment & region tables. */
+	down_read(&gmap->mm->mmap_sem);
+	list_for_each_entry_safe(page, next, &gmap->crst_list, lru) {
+		table = (unsigned long *) page_to_phys(page);
+		if ((*table & _REGION_ENTRY_TYPE_MASK) == 0)
+			/* Remove gmap rmap structures for segment table. */
+			for (i = 0; i < PTRS_PER_PMD; i++, table++)
+				gmap_unlink_segment(gmap, table);
+		__free_pages(page, ALLOC_ORDER);
+	}
+	up_read(&gmap->mm->mmap_sem);
+	list_del(&gmap->list);
+	kfree(gmap);
+}
+EXPORT_SYMBOL_GPL(gmap_free);
+
+/**
+ * gmap_enable - switch primary space to the guest address space
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_enable(struct gmap *gmap)
+{
+	/* Load primary space page table origin. */
+	S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
+				 _ASCE_USER_BITS | __pa(gmap->table);
+	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
+	S390_lowcore.gmap = (unsigned long) gmap;
+}
+EXPORT_SYMBOL_GPL(gmap_enable);
+
+/**
+ * gmap_disable - switch back to the standard primary address space
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_disable(struct gmap *gmap)
+{
+	/* Load primary space page table origin. */
+	S390_lowcore.user_asce =
+		gmap->mm->context.asce_bits | __pa(gmap->mm->pgd);
+	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
+	S390_lowcore.gmap = 0UL;
+}
+EXPORT_SYMBOL_GPL(gmap_disable);
+
+static int gmap_alloc_table(struct gmap *gmap,
+			       unsigned long *table, unsigned long init)
+{
+	struct page *page;
+	unsigned long *new;
+
+	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	if (!page)
+		return -ENOMEM;
+	new = (unsigned long *) page_to_phys(page);
+	crst_table_init(new, init);
+	down_read(&gmap->mm->mmap_sem);
+	if (*table & _REGION_ENTRY_INV) {
+		list_add(&page->lru, &gmap->crst_list);
+		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
+			(*table & _REGION_ENTRY_TYPE_MASK);
+	} else
+		__free_pages(page, ALLOC_ORDER);
+	up_read(&gmap->mm->mmap_sem);
+	return 0;
+}
+
+/**
+ * gmap_unmap_segment - unmap segment from the guest address space
+ * @gmap: pointer to the guest address space structure
+ * @addr: address in the guest address space
+ * @len: length of the memory area to unmap
+ *
+ * Returns 0 if the unmap succeded, -EINVAL if not.
+ */
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
+{
+	unsigned long *table;
+	unsigned long off;
+	int flush;
+
+	if ((to | len) & (PMD_SIZE - 1))
+		return -EINVAL;
+	if (len == 0 || to + len < to)
+		return -EINVAL;
+
+	flush = 0;
+	down_read(&gmap->mm->mmap_sem);
+	for (off = 0; off < len; off += PMD_SIZE) {
+		/* Walk the guest addr space page table */
+		table = gmap->table + (((to + off) >> 53) & 0x7ff);
+		if (*table & _REGION_ENTRY_INV)
+			return 0;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 42) & 0x7ff);
+		if (*table & _REGION_ENTRY_INV)
+			return 0;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 31) & 0x7ff);
+		if (*table & _REGION_ENTRY_INV)
+			return 0;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 20) & 0x7ff);
+
+		/* Clear segment table entry in guest address space. */
+		flush |= gmap_unlink_segment(gmap, table);
+		*table = _SEGMENT_ENTRY_INV;
+	}
+	up_read(&gmap->mm->mmap_sem);
+	if (flush)
+		gmap_flush_tlb(gmap);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gmap_unmap_segment);
+
+/**
+ * gmap_mmap_segment - map a segment to the guest address space
+ * @gmap: pointer to the guest address space structure
+ * @from: source address in the parent address space
+ * @to: target address in the guest address space
+ *
+ * Returns 0 if the mmap succeded, -EINVAL or -ENOMEM if not.
+ */
+int gmap_map_segment(struct gmap *gmap, unsigned long from,
+		     unsigned long to, unsigned long len)
+{
+	unsigned long *table;
+	unsigned long off;
+	int flush;
+
+	if ((from | to | len) & (PMD_SIZE - 1))
+		return -EINVAL;
+	if (len == 0 || from + len > PGDIR_SIZE ||
+	    from + len < from || to + len < to)
+		return -EINVAL;
+
+	flush = 0;
+	down_read(&gmap->mm->mmap_sem);
+	for (off = 0; off < len; off += PMD_SIZE) {
+		/* Walk the gmap address space page table */
+		table = gmap->table + (((to + off) >> 53) & 0x7ff);
+		if ((*table & _REGION_ENTRY_INV) &&
+		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY))
+			goto out_unmap;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 42) & 0x7ff);
+		if ((*table & _REGION_ENTRY_INV) &&
+		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY))
+			goto out_unmap;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 31) & 0x7ff);
+		if ((*table & _REGION_ENTRY_INV) &&
+		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY))
+			goto out_unmap;
+		table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN);
+		table = table + (((to + off) >> 20) & 0x7ff);
+
+		/* Store 'from' address in an invalid segment table entry. */
+		flush |= gmap_unlink_segment(gmap, table);
+		*table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off);
+	}
+	up_read(&gmap->mm->mmap_sem);
+	if (flush)
+		gmap_flush_tlb(gmap);
+	return 0;
+
+out_unmap:
+	up_read(&gmap->mm->mmap_sem);
+	gmap_unmap_segment(gmap, to, len);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(gmap_map_segment);
+
+unsigned long gmap_fault(unsigned long address, struct gmap *gmap)
+{
+	unsigned long *table, vmaddr, segment;
+	struct mm_struct *mm;
+	struct gmap_pgtable *mp;
+	struct gmap_rmap *rmap;
+	struct vm_area_struct *vma;
+	struct page *page;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	current->thread.gmap_addr = address;
+	mm = gmap->mm;
+	/* Walk the gmap address space page table */
+	table = gmap->table + ((address >> 53) & 0x7ff);
+	if (unlikely(*table & _REGION_ENTRY_INV))
+		return -EFAULT;
+	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	table = table + ((address >> 42) & 0x7ff);
+	if (unlikely(*table & _REGION_ENTRY_INV))
+		return -EFAULT;
+	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	table = table + ((address >> 31) & 0x7ff);
+	if (unlikely(*table & _REGION_ENTRY_INV))
+		return -EFAULT;
+	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	table = table + ((address >> 20) & 0x7ff);
+
+	/* Convert the gmap address to an mm address. */
+	segment = *table;
+	if (likely(!(segment & _SEGMENT_ENTRY_INV))) {
+		page = pfn_to_page(segment >> PAGE_SHIFT);
+		mp = (struct gmap_pgtable *) page->index;
+		return mp->vmaddr | (address & ~PMD_MASK);
+	} else if (segment & _SEGMENT_ENTRY_RO) {
+		vmaddr = segment & _SEGMENT_ENTRY_ORIGIN;
+		vma = find_vma(mm, vmaddr);
+		if (!vma || vma->vm_start > vmaddr)
+			return -EFAULT;
+
+		/* Walk the parent mm page table */
+		pgd = pgd_offset(mm, vmaddr);
+		pud = pud_alloc(mm, pgd, vmaddr);
+		if (!pud)
+			return -ENOMEM;
+		pmd = pmd_alloc(mm, pud, vmaddr);
+		if (!pmd)
+			return -ENOMEM;
+		if (!pmd_present(*pmd) &&
+		    __pte_alloc(mm, vma, pmd, vmaddr))
+			return -ENOMEM;
+		/* pmd now points to a valid segment table entry. */
+		rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT);
+		if (!rmap)
+			return -ENOMEM;
+		/* Link gmap segment table entry location to page table. */
+		page = pmd_page(*pmd);
+		mp = (struct gmap_pgtable *) page->index;
+		rmap->entry = table;
+		list_add(&rmap->list, &mp->mapper);
+		/* Set gmap segment table entry to page table. */
+		*table = pmd_val(*pmd) & PAGE_MASK;
+		return vmaddr | (address & ~PMD_MASK);
+	}
+	return -EFAULT;
+
+}
+EXPORT_SYMBOL_GPL(gmap_fault);
+
+void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table)
+{
+	struct gmap_rmap *rmap, *next;
+	struct gmap_pgtable *mp;
+	struct page *page;
+	int flush;
+
+	flush = 0;
+	spin_lock(&mm->page_table_lock);
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	mp = (struct gmap_pgtable *) page->index;
+	list_for_each_entry_safe(rmap, next, &mp->mapper, list) {
+		*rmap->entry =
+			_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+		list_del(&rmap->list);
+		kfree(rmap);
+		flush = 1;
+	}
+	spin_unlock(&mm->page_table_lock);
+	if (flush)
+		__tlb_flush_global();
+}
+
+static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
+						    unsigned long vmaddr)
 {
 	struct page *page;
 	unsigned long *table;
+	struct gmap_pgtable *mp;
 
 	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
 	if (!page)
 		return NULL;
+	mp = kmalloc(sizeof(*mp), GFP_KERNEL|__GFP_REPEAT);
+	if (!mp) {
+		__free_page(page);
+		return NULL;
+	}
 	pgtable_page_ctor(page);
+	mp->vmaddr = vmaddr & PMD_MASK;
+	INIT_LIST_HEAD(&mp->mapper);
+	page->index = (unsigned long) mp;
 	atomic_set(&page->_mapcount, 3);
 	table = (unsigned long *) page_to_phys(page);
 	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
@@ -167,24 +512,57 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
 static inline void page_table_free_pgste(unsigned long *table)
 {
 	struct page *page;
+	struct gmap_pgtable *mp;
 
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	mp = (struct gmap_pgtable *) page->index;
+	BUG_ON(!list_empty(&mp->mapper));
 	pgtable_page_ctor(page);
 	atomic_set(&page->_mapcount, -1);
+	kfree(mp);
 	__free_page(page);
 }
-#endif
 
-unsigned long *page_table_alloc(struct mm_struct *mm)
+#else /* CONFIG_PGSTE */
+
+static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
+						    unsigned long vmaddr)
+{
+}
+
+static inline void page_table_free_pgste(unsigned long *table)
+{
+}
+
+static inline void gmap_unmap_notifier(struct mm_struct *mm,
+					  unsigned long *table)
+{
+}
+
+#endif /* CONFIG_PGSTE */
+
+static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+{
+	unsigned int old, new;
+
+	do {
+		old = atomic_read(v);
+		new = old ^ bits;
+	} while (atomic_cmpxchg(v, old, new) != old);
+	return new;
+}
+
+/*
+ * page table entry allocation/free routines.
+ */
+unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr)
 {
 	struct page *page;
 	unsigned long *table;
 	unsigned int mask, bit;
 
-#ifdef CONFIG_PGSTE
 	if (mm_has_pgste(mm))
-		return page_table_alloc_pgste(mm);
-#endif
+		return page_table_alloc_pgste(mm, vmaddr);
 	/* Allocate fragments of a 4K page as 1K/2K page table */
 	spin_lock_bh(&mm->context.list_lock);
 	mask = FRAG_MASK;
@@ -222,10 +600,10 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	struct page *page;
 	unsigned int bit, mask;
 
-#ifdef CONFIG_PGSTE
-	if (mm_has_pgste(mm))
+	if (mm_has_pgste(mm)) {
+		gmap_unmap_notifier(mm, table);
 		return page_table_free_pgste(table);
-#endif
+	}
 	/* Free 1K/2K page table fragment of a 4K page */
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
@@ -249,10 +627,8 @@ static void __page_table_free_rcu(void *table, unsigned bit)
 {
 	struct page *page;
 
-#ifdef CONFIG_PGSTE
 	if (bit == FRAG_MASK)
 		return page_table_free_pgste(table);
-#endif
 	/* Free 1K/2K page table fragment of a 4K page */
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	if (atomic_xor_bits(&page->_mapcount, bit) == 0) {
@@ -269,13 +645,12 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 	unsigned int bit, mask;
 
 	mm = tlb->mm;
-#ifdef CONFIG_PGSTE
 	if (mm_has_pgste(mm)) {
+		gmap_unmap_notifier(mm, table);
 		table = (unsigned long *) (__pa(table) | FRAG_MASK);
 		tlb_remove_table(tlb, table);
 		return;
 	}
-#endif
 	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 8c1970d1dd9..781ff516956 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -61,12 +61,12 @@ static inline pmd_t *vmem_pmd_alloc(void)
 	return pmd;
 }
 
-static pte_t __ref *vmem_pte_alloc(void)
+static pte_t __ref *vmem_pte_alloc(unsigned long address)
 {
 	pte_t *pte;
 
 	if (slab_is_available())
-		pte = (pte_t *) page_table_alloc(&init_mm);
+		pte = (pte_t *) page_table_alloc(&init_mm, address);
 	else
 		pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
 	if (!pte)
@@ -120,7 +120,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		}
 #endif
 		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc();
+			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
@@ -205,7 +205,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 
 		pm_dir = pmd_offset(pu_dir, address);
 		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc();
+			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 86b6f1cc1b1..432444af7ee 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -22,6 +22,8 @@
 #include <linux/hdreg.h>
 #include <linux/async.h>
 #include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 
 #include <asm/ccwdev.h>
 #include <asm/ebcdic.h>
@@ -45,6 +47,7 @@
  * SECTION: exported variables of dasd.c
  */
 debug_info_t *dasd_debug_area;
+static struct dentry *dasd_debugfs_root_entry;
 struct dasd_discipline *dasd_diag_discipline_pointer;
 void dasd_int_handler(struct ccw_device *, unsigned long, struct irb *);
 
@@ -71,6 +74,8 @@ static void dasd_return_cqr_cb(struct dasd_ccw_req *, void *);
 static void dasd_device_timeout(unsigned long);
 static void dasd_block_timeout(unsigned long);
 static void __dasd_process_erp(struct dasd_device *, struct dasd_ccw_req *);
+static void dasd_profile_init(struct dasd_profile *, struct dentry *);
+static void dasd_profile_exit(struct dasd_profile *);
 
 /*
  * SECTION: Operations on the device structure.
@@ -121,7 +126,7 @@ struct dasd_device *dasd_alloc_device(void)
 	device->state = DASD_STATE_NEW;
 	device->target = DASD_STATE_NEW;
 	mutex_init(&device->state_mutex);
-
+	spin_lock_init(&device->profile.lock);
 	return device;
 }
 
@@ -159,6 +164,7 @@ struct dasd_block *dasd_alloc_block(void)
 	init_timer(&block->timer);
 	block->timer.function = dasd_block_timeout;
 	block->timer.data = (unsigned long) block;
+	spin_lock_init(&block->profile.lock);
 
 	return block;
 }
@@ -222,19 +228,44 @@ static int dasd_state_known_to_new(struct dasd_device *device)
 	return 0;
 }
 
+static struct dentry *dasd_debugfs_setup(const char *name,
+					 struct dentry *base_dentry)
+{
+	struct dentry *pde;
+
+	if (!base_dentry)
+		return NULL;
+	pde = debugfs_create_dir(name, base_dentry);
+	if (!pde || IS_ERR(pde))
+		return NULL;
+	return pde;
+}
+
 /*
  * Request the irq line for the device.
  */
 static int dasd_state_known_to_basic(struct dasd_device *device)
 {
+	struct dasd_block *block = device->block;
 	int rc;
 
 	/* Allocate and register gendisk structure. */
-	if (device->block) {
-		rc = dasd_gendisk_alloc(device->block);
+	if (block) {
+		rc = dasd_gendisk_alloc(block);
 		if (rc)
 			return rc;
-	}
+		block->debugfs_dentry =
+			dasd_debugfs_setup(block->gdp->disk_name,
+					   dasd_debugfs_root_entry);
+		dasd_profile_init(&block->profile, block->debugfs_dentry);
+		if (dasd_global_profile_level == DASD_PROFILE_ON)
+			dasd_profile_on(&device->block->profile);
+	}
+	device->debugfs_dentry =
+		dasd_debugfs_setup(dev_name(&device->cdev->dev),
+				   dasd_debugfs_root_entry);
+	dasd_profile_init(&device->profile, device->debugfs_dentry);
+
 	/* register 'device' debug area, used for all DBF_DEV_XXX calls */
 	device->debug_area = debug_register(dev_name(&device->cdev->dev), 4, 1,
 					    8 * sizeof(long));
@@ -253,6 +284,9 @@ static int dasd_state_basic_to_known(struct dasd_device *device)
 {
 	int rc;
 	if (device->block) {
+		dasd_profile_exit(&device->block->profile);
+		if (device->block->debugfs_dentry)
+			debugfs_remove(device->block->debugfs_dentry);
 		dasd_gendisk_free(device->block);
 		dasd_block_clear_timer(device->block);
 	}
@@ -260,6 +294,9 @@ static int dasd_state_basic_to_known(struct dasd_device *device)
 	if (rc)
 		return rc;
 	dasd_device_clear_timer(device);
+	dasd_profile_exit(&device->profile);
+	if (device->debugfs_dentry)
+		debugfs_remove(device->debugfs_dentry);
 
 	DBF_DEV_EVENT(DBF_EMERG, device, "%p debug area deleted", device);
 	if (device->debug_area != NULL) {
@@ -609,21 +646,13 @@ void dasd_enable_device(struct dasd_device *device)
 /*
  * SECTION: device operation (interrupt handler, start i/o, term i/o ...)
  */
-#ifdef CONFIG_DASD_PROFILE
 
-struct dasd_profile_info_t dasd_global_profile;
-unsigned int dasd_profile_level = DASD_PROFILE_OFF;
+unsigned int dasd_global_profile_level = DASD_PROFILE_OFF;
 
-/*
- * Increments counter in global and local profiling structures.
- */
-#define dasd_profile_counter(value, counter, block) \
-{ \
-	int index; \
-	for (index = 0; index < 31 && value >> (2+index); index++); \
-	dasd_global_profile.counter[index]++; \
-	block->profile.counter[index]++; \
-}
+#ifdef CONFIG_DASD_PROFILE
+struct dasd_profile_info dasd_global_profile_data;
+static struct dentry *dasd_global_profile_dentry;
+static struct dentry *dasd_debugfs_global_entry;
 
 /*
  * Add profiling information for cqr before execution.
@@ -634,30 +663,121 @@ static void dasd_profile_start(struct dasd_block *block,
 {
 	struct list_head *l;
 	unsigned int counter;
-
-	if (dasd_profile_level != DASD_PROFILE_ON)
-		return;
+	struct dasd_device *device;
 
 	/* count the length of the chanq for statistics */
 	counter = 0;
-	list_for_each(l, &block->ccw_queue)
-		if (++counter >= 31)
-			break;
-	dasd_global_profile.dasd_io_nr_req[counter]++;
-	block->profile.dasd_io_nr_req[counter]++;
+	if (dasd_global_profile_level || block->profile.data)
+		list_for_each(l, &block->ccw_queue)
+			if (++counter >= 31)
+				break;
+
+	if (dasd_global_profile_level) {
+		dasd_global_profile_data.dasd_io_nr_req[counter]++;
+		if (rq_data_dir(req) == READ)
+			dasd_global_profile_data.dasd_read_nr_req[counter]++;
+	}
+
+	spin_lock(&block->profile.lock);
+	if (block->profile.data)
+		block->profile.data->dasd_io_nr_req[counter]++;
+		if (rq_data_dir(req) == READ)
+			block->profile.data->dasd_read_nr_req[counter]++;
+	spin_unlock(&block->profile.lock);
+
+	/*
+	 * We count the request for the start device, even though it may run on
+	 * some other device due to error recovery. This way we make sure that
+	 * we count each request only once.
+	 */
+	device = cqr->startdev;
+	if (device->profile.data) {
+		counter = 1; /* request is not yet queued on the start device */
+		list_for_each(l, &device->ccw_queue)
+			if (++counter >= 31)
+				break;
+	}
+	spin_lock(&device->profile.lock);
+	if (device->profile.data) {
+		device->profile.data->dasd_io_nr_req[counter]++;
+		if (rq_data_dir(req) == READ)
+			device->profile.data->dasd_read_nr_req[counter]++;
+	}
+	spin_unlock(&device->profile.lock);
 }
 
 /*
  * Add profiling information for cqr after execution.
  */
+
+#define dasd_profile_counter(value, index)			   \
+{								   \
+	for (index = 0; index < 31 && value >> (2+index); index++) \
+		;						   \
+}
+
+static void dasd_profile_end_add_data(struct dasd_profile_info *data,
+				      int is_alias,
+				      int is_tpm,
+				      int is_read,
+				      long sectors,
+				      int sectors_ind,
+				      int tottime_ind,
+				      int tottimeps_ind,
+				      int strtime_ind,
+				      int irqtime_ind,
+				      int irqtimeps_ind,
+				      int endtime_ind)
+{
+	/* in case of an overflow, reset the whole profile */
+	if (data->dasd_io_reqs == UINT_MAX) {
+			memset(data, 0, sizeof(*data));
+			getnstimeofday(&data->starttod);
+	}
+	data->dasd_io_reqs++;
+	data->dasd_io_sects += sectors;
+	if (is_alias)
+		data->dasd_io_alias++;
+	if (is_tpm)
+		data->dasd_io_tpm++;
+
+	data->dasd_io_secs[sectors_ind]++;
+	data->dasd_io_times[tottime_ind]++;
+	data->dasd_io_timps[tottimeps_ind]++;
+	data->dasd_io_time1[strtime_ind]++;
+	data->dasd_io_time2[irqtime_ind]++;
+	data->dasd_io_time2ps[irqtimeps_ind]++;
+	data->dasd_io_time3[endtime_ind]++;
+
+	if (is_read) {
+		data->dasd_read_reqs++;
+		data->dasd_read_sects += sectors;
+		if (is_alias)
+			data->dasd_read_alias++;
+		if (is_tpm)
+			data->dasd_read_tpm++;
+		data->dasd_read_secs[sectors_ind]++;
+		data->dasd_read_times[tottime_ind]++;
+		data->dasd_read_time1[strtime_ind]++;
+		data->dasd_read_time2[irqtime_ind]++;
+		data->dasd_read_time3[endtime_ind]++;
+	}
+}
+
 static void dasd_profile_end(struct dasd_block *block,
 			     struct dasd_ccw_req *cqr,
 			     struct request *req)
 {
 	long strtime, irqtime, endtime, tottime;	/* in microseconds */
 	long tottimeps, sectors;
+	struct dasd_device *device;
+	int sectors_ind, tottime_ind, tottimeps_ind, strtime_ind;
+	int irqtime_ind, irqtimeps_ind, endtime_ind;
 
-	if (dasd_profile_level != DASD_PROFILE_ON)
+	device = cqr->startdev;
+	if (!(dasd_global_profile_level ||
+	      block->profile.data ||
+	      device->profile.data))
 		return;
 
 	sectors = blk_rq_sectors(req);
@@ -672,29 +792,392 @@ static void dasd_profile_end(struct dasd_block *block,
 	tottime = ((cqr->endclk - cqr->buildclk) >> 12);
 	tottimeps = tottime / sectors;
 
-	if (!dasd_global_profile.dasd_io_reqs)
-		memset(&dasd_global_profile, 0,
-		       sizeof(struct dasd_profile_info_t));
-	dasd_global_profile.dasd_io_reqs++;
-	dasd_global_profile.dasd_io_sects += sectors;
-
-	if (!block->profile.dasd_io_reqs)
-		memset(&block->profile, 0,
-		       sizeof(struct dasd_profile_info_t));
-	block->profile.dasd_io_reqs++;
-	block->profile.dasd_io_sects += sectors;
-
-	dasd_profile_counter(sectors, dasd_io_secs, block);
-	dasd_profile_counter(tottime, dasd_io_times, block);
-	dasd_profile_counter(tottimeps, dasd_io_timps, block);
-	dasd_profile_counter(strtime, dasd_io_time1, block);
-	dasd_profile_counter(irqtime, dasd_io_time2, block);
-	dasd_profile_counter(irqtime / sectors, dasd_io_time2ps, block);
-	dasd_profile_counter(endtime, dasd_io_time3, block);
+	dasd_profile_counter(sectors, sectors_ind);
+	dasd_profile_counter(tottime, tottime_ind);
+	dasd_profile_counter(tottimeps, tottimeps_ind);
+	dasd_profile_counter(strtime, strtime_ind);
+	dasd_profile_counter(irqtime, irqtime_ind);
+	dasd_profile_counter(irqtime / sectors, irqtimeps_ind);
+	dasd_profile_counter(endtime, endtime_ind);
+
+	if (dasd_global_profile_level) {
+		dasd_profile_end_add_data(&dasd_global_profile_data,
+					  cqr->startdev != block->base,
+					  cqr->cpmode == 1,
+					  rq_data_dir(req) == READ,
+					  sectors, sectors_ind, tottime_ind,
+					  tottimeps_ind, strtime_ind,
+					  irqtime_ind, irqtimeps_ind,
+					  endtime_ind);
+	}
+
+	spin_lock(&block->profile.lock);
+	if (block->profile.data)
+		dasd_profile_end_add_data(block->profile.data,
+					  cqr->startdev != block->base,
+					  cqr->cpmode == 1,
+					  rq_data_dir(req) == READ,
+					  sectors, sectors_ind, tottime_ind,
+					  tottimeps_ind, strtime_ind,
+					  irqtime_ind, irqtimeps_ind,
+					  endtime_ind);
+	spin_unlock(&block->profile.lock);
+
+	spin_lock(&device->profile.lock);
+	if (device->profile.data)
+		dasd_profile_end_add_data(device->profile.data,
+					  cqr->startdev != block->base,
+					  cqr->cpmode == 1,
+					  rq_data_dir(req) == READ,
+					  sectors, sectors_ind, tottime_ind,
+					  tottimeps_ind, strtime_ind,
+					  irqtime_ind, irqtimeps_ind,
+					  endtime_ind);
+	spin_unlock(&device->profile.lock);
+}
+
+void dasd_profile_reset(struct dasd_profile *profile)
+{
+	struct dasd_profile_info *data;
+
+	spin_lock_bh(&profile->lock);
+	data = profile->data;
+	if (!data) {
+		spin_unlock_bh(&profile->lock);
+		return;
+	}
+	memset(data, 0, sizeof(*data));
+	getnstimeofday(&data->starttod);
+	spin_unlock_bh(&profile->lock);
+}
+
+void dasd_global_profile_reset(void)
+{
+	memset(&dasd_global_profile_data, 0, sizeof(dasd_global_profile_data));
+	getnstimeofday(&dasd_global_profile_data.starttod);
+}
+
+int dasd_profile_on(struct dasd_profile *profile)
+{
+	struct dasd_profile_info *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	spin_lock_bh(&profile->lock);
+	if (profile->data) {
+		spin_unlock_bh(&profile->lock);
+		kfree(data);
+		return 0;
+	}
+	getnstimeofday(&data->starttod);
+	profile->data = data;
+	spin_unlock_bh(&profile->lock);
+	return 0;
+}
+
+void dasd_profile_off(struct dasd_profile *profile)
+{
+	spin_lock_bh(&profile->lock);
+	kfree(profile->data);
+	profile->data = NULL;
+	spin_unlock_bh(&profile->lock);
+}
+
+char *dasd_get_user_string(const char __user *user_buf, size_t user_len)
+{
+	char *buffer;
+
+	buffer = kmalloc(user_len + 1, GFP_KERNEL);
+	if (buffer == NULL)
+		return ERR_PTR(-ENOMEM);
+	if (copy_from_user(buffer, user_buf, user_len) != 0) {
+		kfree(buffer);
+		return ERR_PTR(-EFAULT);
+	}
+	/* got the string, now strip linefeed. */
+	if (buffer[user_len - 1] == '\n')
+		buffer[user_len - 1] = 0;
+	else
+		buffer[user_len] = 0;
+	return buffer;
 }
+
+static ssize_t dasd_stats_write(struct file *file,
+				const char __user *user_buf,
+				size_t user_len, loff_t *pos)
+{
+	char *buffer, *str;
+	int rc;
+	struct seq_file *m = (struct seq_file *)file->private_data;
+	struct dasd_profile *prof = m->private;
+
+	if (user_len > 65536)
+		user_len = 65536;
+	buffer = dasd_get_user_string(user_buf, user_len);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+
+	str = skip_spaces(buffer);
+	rc = user_len;
+	if (strncmp(str, "reset", 5) == 0) {
+		dasd_profile_reset(prof);
+	} else if (strncmp(str, "on", 2) == 0) {
+		rc = dasd_profile_on(prof);
+		if (!rc)
+			rc = user_len;
+	} else if (strncmp(str, "off", 3) == 0) {
+		dasd_profile_off(prof);
+	} else
+		rc = -EINVAL;
+	kfree(buffer);
+	return rc;
+}
+
+static void dasd_stats_array(struct seq_file *m, unsigned int *array)
+{
+	int i;
+
+	for (i = 0; i < 32; i++)
+		seq_printf(m, "%u ", array[i]);
+	seq_putc(m, '\n');
+}
+
+static void dasd_stats_seq_print(struct seq_file *m,
+				 struct dasd_profile_info *data)
+{
+	seq_printf(m, "start_time %ld.%09ld\n",
+		   data->starttod.tv_sec, data->starttod.tv_nsec);
+	seq_printf(m, "total_requests %u\n", data->dasd_io_reqs);
+	seq_printf(m, "total_sectors %u\n", data->dasd_io_sects);
+	seq_printf(m, "total_pav %u\n", data->dasd_io_alias);
+	seq_printf(m, "total_hpf %u\n", data->dasd_io_tpm);
+	seq_printf(m, "histogram_sectors ");
+	dasd_stats_array(m, data->dasd_io_secs);
+	seq_printf(m, "histogram_io_times ");
+	dasd_stats_array(m, data->dasd_io_times);
+	seq_printf(m, "histogram_io_times_weighted ");
+	dasd_stats_array(m, data->dasd_io_timps);
+	seq_printf(m, "histogram_time_build_to_ssch ");
+	dasd_stats_array(m, data->dasd_io_time1);
+	seq_printf(m, "histogram_time_ssch_to_irq ");
+	dasd_stats_array(m, data->dasd_io_time2);
+	seq_printf(m, "histogram_time_ssch_to_irq_weighted ");
+	dasd_stats_array(m, data->dasd_io_time2ps);
+	seq_printf(m, "histogram_time_irq_to_end ");
+	dasd_stats_array(m, data->dasd_io_time3);
+	seq_printf(m, "histogram_ccw_queue_length ");
+	dasd_stats_array(m, data->dasd_io_nr_req);
+	seq_printf(m, "total_read_requests %u\n", data->dasd_read_reqs);
+	seq_printf(m, "total_read_sectors %u\n", data->dasd_read_sects);
+	seq_printf(m, "total_read_pav %u\n", data->dasd_read_alias);
+	seq_printf(m, "total_read_hpf %u\n", data->dasd_read_tpm);
+	seq_printf(m, "histogram_read_sectors ");
+	dasd_stats_array(m, data->dasd_read_secs);
+	seq_printf(m, "histogram_read_times ");
+	dasd_stats_array(m, data->dasd_read_times);
+	seq_printf(m, "histogram_read_time_build_to_ssch ");
+	dasd_stats_array(m, data->dasd_read_time1);
+	seq_printf(m, "histogram_read_time_ssch_to_irq ");
+	dasd_stats_array(m, data->dasd_read_time2);
+	seq_printf(m, "histogram_read_time_irq_to_end ");
+	dasd_stats_array(m, data->dasd_read_time3);
+	seq_printf(m, "histogram_read_ccw_queue_length ");
+	dasd_stats_array(m, data->dasd_read_nr_req);
+}
+
+static int dasd_stats_show(struct seq_file *m, void *v)
+{
+	struct dasd_profile *profile;
+	struct dasd_profile_info *data;
+
+	profile = m->private;
+	spin_lock_bh(&profile->lock);
+	data = profile->data;
+	if (!data) {
+		spin_unlock_bh(&profile->lock);
+		seq_printf(m, "disabled\n");
+		return 0;
+	}
+	dasd_stats_seq_print(m, data);
+	spin_unlock_bh(&profile->lock);
+	return 0;
+}
+
+static int dasd_stats_open(struct inode *inode, struct file *file)
+{
+	struct dasd_profile *profile = inode->i_private;
+	return single_open(file, dasd_stats_show, profile);
+}
+
+static const struct file_operations dasd_stats_raw_fops = {
+	.owner		= THIS_MODULE,
+	.open		= dasd_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= dasd_stats_write,
+};
+
+static ssize_t dasd_stats_global_write(struct file *file,
+				       const char __user *user_buf,
+				       size_t user_len, loff_t *pos)
+{
+	char *buffer, *str;
+	ssize_t rc;
+
+	if (user_len > 65536)
+		user_len = 65536;
+	buffer = dasd_get_user_string(user_buf, user_len);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+	str = skip_spaces(buffer);
+	rc = user_len;
+	if (strncmp(str, "reset", 5) == 0) {
+		dasd_global_profile_reset();
+	} else if (strncmp(str, "on", 2) == 0) {
+		dasd_global_profile_reset();
+		dasd_global_profile_level = DASD_PROFILE_GLOBAL_ONLY;
+	} else if (strncmp(str, "off", 3) == 0) {
+		dasd_global_profile_level = DASD_PROFILE_OFF;
+	} else
+		rc = -EINVAL;
+	kfree(buffer);
+	return rc;
+}
+
+static int dasd_stats_global_show(struct seq_file *m, void *v)
+{
+	if (!dasd_global_profile_level) {
+		seq_printf(m, "disabled\n");
+		return 0;
+	}
+	dasd_stats_seq_print(m, &dasd_global_profile_data);
+	return 0;
+}
+
+static int dasd_stats_global_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dasd_stats_global_show, NULL);
+}
+
+static const struct file_operations dasd_stats_global_fops = {
+	.owner		= THIS_MODULE,
+	.open		= dasd_stats_global_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= dasd_stats_global_write,
+};
+
+static void dasd_profile_init(struct dasd_profile *profile,
+			      struct dentry *base_dentry)
+{
+	mode_t mode;
+	struct dentry *pde;
+
+	if (!base_dentry)
+		return;
+	profile->dentry = NULL;
+	profile->data = NULL;
+	mode = (S_IRUSR | S_IWUSR | S_IFREG);
+	pde = debugfs_create_file("statistics", mode, base_dentry,
+				  profile, &dasd_stats_raw_fops);
+	if (pde && !IS_ERR(pde))
+		profile->dentry = pde;
+	return;
+}
+
+static void dasd_profile_exit(struct dasd_profile *profile)
+{
+	dasd_profile_off(profile);
+	if (profile->dentry) {
+		debugfs_remove(profile->dentry);
+		profile->dentry = NULL;
+	}
+}
+
+static void dasd_statistics_removeroot(void)
+{
+	dasd_global_profile_level = DASD_PROFILE_OFF;
+	if (dasd_global_profile_dentry) {
+		debugfs_remove(dasd_global_profile_dentry);
+		dasd_global_profile_dentry = NULL;
+	}
+	if (dasd_debugfs_global_entry)
+		debugfs_remove(dasd_debugfs_global_entry);
+	if (dasd_debugfs_root_entry)
+		debugfs_remove(dasd_debugfs_root_entry);
+}
+
+static void dasd_statistics_createroot(void)
+{
+	mode_t mode;
+	struct dentry *pde;
+
+	dasd_debugfs_root_entry = NULL;
+	dasd_debugfs_global_entry = NULL;
+	dasd_global_profile_dentry = NULL;
+	pde = debugfs_create_dir("dasd", NULL);
+	if (!pde || IS_ERR(pde))
+		goto error;
+	dasd_debugfs_root_entry = pde;
+	pde = debugfs_create_dir("global", dasd_debugfs_root_entry);
+	if (!pde || IS_ERR(pde))
+		goto error;
+	dasd_debugfs_global_entry = pde;
+
+	mode = (S_IRUSR | S_IWUSR | S_IFREG);
+	pde = debugfs_create_file("statistics", mode, dasd_debugfs_global_entry,
+				  NULL, &dasd_stats_global_fops);
+	if (!pde || IS_ERR(pde))
+		goto error;
+	dasd_global_profile_dentry = pde;
+	return;
+
+error:
+	DBF_EVENT(DBF_ERR, "%s",
+		  "Creation of the dasd debugfs interface failed");
+	dasd_statistics_removeroot();
+	return;
+}
+
 #else
 #define dasd_profile_start(block, cqr, req) do {} while (0)
 #define dasd_profile_end(block, cqr, req) do {} while (0)
+
+static void dasd_statistics_createroot(void)
+{
+	return;
+}
+
+static void dasd_statistics_removeroot(void)
+{
+	return;
+}
+
+int dasd_stats_generic_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "Statistics are not activated in this kernel\n");
+	return 0;
+}
+
+static void dasd_profile_init(struct dasd_profile *profile,
+			      struct dentry *base_dentry)
+{
+	return;
+}
+
+static void dasd_profile_exit(struct dasd_profile *profile)
+{
+	return;
+}
+
+int dasd_profile_on(struct dasd_profile *profile)
+{
+	return 0;
+}
+
 #endif				/* CONFIG_DASD_PROFILE */
 
 /*
@@ -2441,6 +2924,7 @@ dasd_exit(void)
 		debug_unregister(dasd_debug_area);
 		dasd_debug_area = NULL;
 	}
+	dasd_statistics_removeroot();
 }
 
 /*
@@ -2992,6 +3476,8 @@ static int __init dasd_init(void)
 
 	dasd_diag_discipline_pointer = NULL;
 
+	dasd_statistics_createroot();
+
 	rc = dasd_devmap_init();
 	if (rc)
 		goto failed;
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index d1e4f2c1264..1dd12bd85a6 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -382,6 +382,41 @@ struct dasd_path {
 	__u8 npm;
 };
 
+struct dasd_profile_info {
+	/* legacy part of profile data, as in dasd_profile_info_t */
+	unsigned int dasd_io_reqs;	 /* number of requests processed */
+	unsigned int dasd_io_sects;	 /* number of sectors processed */
+	unsigned int dasd_io_secs[32];	 /* histogram of request's sizes */
+	unsigned int dasd_io_times[32];	 /* histogram of requests's times */
+	unsigned int dasd_io_timps[32];	 /* h. of requests's times per sector */
+	unsigned int dasd_io_time1[32];	 /* hist. of time from build to start */
+	unsigned int dasd_io_time2[32];	 /* hist. of time from start to irq */
+	unsigned int dasd_io_time2ps[32]; /* hist. of time from start to irq */
+	unsigned int dasd_io_time3[32];	 /* hist. of time from irq to end */
+	unsigned int dasd_io_nr_req[32]; /* hist. of # of requests in chanq */
+
+	/* new data */
+	struct timespec starttod;	   /* time of start or last reset */
+	unsigned int dasd_io_alias;	   /* requests using an alias */
+	unsigned int dasd_io_tpm;	   /* requests using transport mode */
+	unsigned int dasd_read_reqs;	   /* total number of read  requests */
+	unsigned int dasd_read_sects;	   /* total number read sectors */
+	unsigned int dasd_read_alias;	   /* read request using an alias */
+	unsigned int dasd_read_tpm;	   /* read requests in transport mode */
+	unsigned int dasd_read_secs[32];   /* histogram of request's sizes */
+	unsigned int dasd_read_times[32];  /* histogram of requests's times */
+	unsigned int dasd_read_time1[32];  /* hist. time from build to start */
+	unsigned int dasd_read_time2[32];  /* hist. of time from start to irq */
+	unsigned int dasd_read_time3[32];  /* hist. of time from irq to end */
+	unsigned int dasd_read_nr_req[32]; /* hist. of # of requests in chanq */
+};
+
+struct dasd_profile {
+	struct dentry *dentry;
+	struct dasd_profile_info *data;
+	spinlock_t lock;
+};
+
 struct dasd_device {
 	/* Block device stuff. */
 	struct dasd_block *block;
@@ -431,6 +466,9 @@ struct dasd_device {
 
 	/* default expiration time in s */
 	unsigned long default_expires;
+
+	struct dentry *debugfs_dentry;
+	struct dasd_profile profile;
 };
 
 struct dasd_block {
@@ -453,9 +491,8 @@ struct dasd_block {
 	struct tasklet_struct tasklet;
 	struct timer_list timer;
 
-#ifdef CONFIG_DASD_PROFILE
-	struct dasd_profile_info_t profile;
-#endif
+	struct dentry *debugfs_dentry;
+	struct dasd_profile profile;
 };
 
 
@@ -589,12 +626,13 @@ dasd_check_blocksize(int bsize)
 }
 
 /* externals in dasd.c */
-#define DASD_PROFILE_ON	 1
-#define DASD_PROFILE_OFF 0
+#define DASD_PROFILE_OFF	 0
+#define DASD_PROFILE_ON 	 1
+#define DASD_PROFILE_GLOBAL_ONLY 2
 
 extern debug_info_t *dasd_debug_area;
-extern struct dasd_profile_info_t dasd_global_profile;
-extern unsigned int dasd_profile_level;
+extern struct dasd_profile_info dasd_global_profile_data;
+extern unsigned int dasd_global_profile_level;
 extern const struct block_device_operations dasd_device_operations;
 
 extern struct kmem_cache *dasd_page_cache;
@@ -662,6 +700,11 @@ void dasd_device_remove_stop_bits(struct dasd_device *, int);
 
 int dasd_device_is_ro(struct dasd_device *);
 
+void dasd_profile_reset(struct dasd_profile *);
+int dasd_profile_on(struct dasd_profile *);
+void dasd_profile_off(struct dasd_profile *);
+void dasd_global_profile_reset(void);
+char *dasd_get_user_string(const char __user *, size_t);
 
 /* externals in dasd_devmap.c */
 extern int dasd_max_devindex;
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 72261e4c516..eb4e034378c 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -239,7 +239,7 @@ dasd_ioctl_format(struct block_device *bdev, void __user *argp)
  */
 static int dasd_ioctl_reset_profile(struct dasd_block *block)
 {
-	memset(&block->profile, 0, sizeof(struct dasd_profile_info_t));
+	dasd_profile_reset(&block->profile);
 	return 0;
 }
 
@@ -248,10 +248,40 @@ static int dasd_ioctl_reset_profile(struct dasd_block *block)
  */
 static int dasd_ioctl_read_profile(struct dasd_block *block, void __user *argp)
 {
-	if (dasd_profile_level == DASD_PROFILE_OFF)
+	struct dasd_profile_info_t *data;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	spin_lock_bh(&block->profile.lock);
+	if (block->profile.data) {
+		data->dasd_io_reqs = block->profile.data->dasd_io_reqs;
+		data->dasd_io_sects = block->profile.data->dasd_io_sects;
+		memcpy(data->dasd_io_secs, block->profile.data->dasd_io_secs,
+		       sizeof(data->dasd_io_secs));
+		memcpy(data->dasd_io_times, block->profile.data->dasd_io_times,
+		       sizeof(data->dasd_io_times));
+		memcpy(data->dasd_io_timps, block->profile.data->dasd_io_timps,
+		       sizeof(data->dasd_io_timps));
+		memcpy(data->dasd_io_time1, block->profile.data->dasd_io_time1,
+		       sizeof(data->dasd_io_time1));
+		memcpy(data->dasd_io_time2, block->profile.data->dasd_io_time2,
+		       sizeof(data->dasd_io_time2));
+		memcpy(data->dasd_io_time2ps,
+		       block->profile.data->dasd_io_time2ps,
+		       sizeof(data->dasd_io_time2ps));
+		memcpy(data->dasd_io_time3, block->profile.data->dasd_io_time3,
+		       sizeof(data->dasd_io_time3));
+		memcpy(data->dasd_io_nr_req,
+		       block->profile.data->dasd_io_nr_req,
+		       sizeof(data->dasd_io_nr_req));
+		spin_unlock_bh(&block->profile.lock);
+	} else {
+		spin_unlock_bh(&block->profile.lock);
 		return -EIO;
-	if (copy_to_user(argp, &block->profile,
-			 sizeof(struct dasd_profile_info_t)))
+	}
+	if (copy_to_user(argp, data, sizeof(*data)))
 		return -EFAULT;
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index c4a6a31bd9c..6c3c5364d08 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -32,28 +32,6 @@ static struct proc_dir_entry *dasd_proc_root_entry = NULL;
 static struct proc_dir_entry *dasd_devices_entry = NULL;
 static struct proc_dir_entry *dasd_statistics_entry = NULL;
 
-#ifdef CONFIG_DASD_PROFILE
-static char *
-dasd_get_user_string(const char __user *user_buf, size_t user_len)
-{
-	char *buffer;
-
-	buffer = kmalloc(user_len + 1, GFP_KERNEL);
-	if (buffer == NULL)
-		return ERR_PTR(-ENOMEM);
-	if (copy_from_user(buffer, user_buf, user_len) != 0) {
-		kfree(buffer);
-		return ERR_PTR(-EFAULT);
-	}
-	/* got the string, now strip linefeed. */
-	if (buffer[user_len - 1] == '\n')
-		buffer[user_len - 1] = 0;
-	else
-		buffer[user_len] = 0;
-	return buffer;
-}
-#endif /* CONFIG_DASD_PROFILE */
-
 static int
 dasd_devices_show(struct seq_file *m, void *v)
 {
@@ -167,6 +145,55 @@ static const struct file_operations dasd_devices_file_ops = {
 };
 
 #ifdef CONFIG_DASD_PROFILE
+static int dasd_stats_all_block_on(void)
+{
+	int i, rc;
+	struct dasd_device *device;
+
+	rc = 0;
+	for (i = 0; i < dasd_max_devindex; ++i) {
+		device = dasd_device_from_devindex(i);
+		if (IS_ERR(device))
+			continue;
+		if (device->block)
+			rc = dasd_profile_on(&device->block->profile);
+		dasd_put_device(device);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static void dasd_stats_all_block_off(void)
+{
+	int i;
+	struct dasd_device *device;
+
+	for (i = 0; i < dasd_max_devindex; ++i) {
+		device = dasd_device_from_devindex(i);
+		if (IS_ERR(device))
+			continue;
+		if (device->block)
+			dasd_profile_off(&device->block->profile);
+		dasd_put_device(device);
+	}
+}
+
+static void dasd_stats_all_block_reset(void)
+{
+	int i;
+	struct dasd_device *device;
+
+	for (i = 0; i < dasd_max_devindex; ++i) {
+		device = dasd_device_from_devindex(i);
+		if (IS_ERR(device))
+			continue;
+		if (device->block)
+			dasd_profile_reset(&device->block->profile);
+		dasd_put_device(device);
+	}
+}
+
 static void dasd_statistics_array(struct seq_file *m, unsigned int *array, int factor)
 {
 	int i;
@@ -183,18 +210,18 @@ static void dasd_statistics_array(struct seq_file *m, unsigned int *array, int f
 static int dasd_stats_proc_show(struct seq_file *m, void *v)
 {
 #ifdef CONFIG_DASD_PROFILE
-	struct dasd_profile_info_t *prof;
+	struct dasd_profile_info *prof;
 	int factor;
 
 	/* check for active profiling */
-	if (dasd_profile_level == DASD_PROFILE_OFF) {
+	if (!dasd_global_profile_level) {
 		seq_printf(m, "Statistics are off - they might be "
 				    "switched on using 'echo set on > "
 				    "/proc/dasd/statistics'\n");
 		return 0;
 	}
+	prof = &dasd_global_profile_data;
 
-	prof = &dasd_global_profile;
 	/* prevent counter 'overflow' on output */
 	for (factor = 1; (prof->dasd_io_reqs / factor) > 9999999;
 	     factor *= 10);
@@ -245,6 +272,7 @@ static ssize_t dasd_stats_proc_write(struct file *file,
 {
 #ifdef CONFIG_DASD_PROFILE
 	char *buffer, *str;
+	int rc;
 
 	if (user_len > 65536)
 		user_len = 65536;
@@ -259,32 +287,40 @@ static ssize_t dasd_stats_proc_write(struct file *file,
 		str = skip_spaces(str + 4);
 		if (strcmp(str, "on") == 0) {
 			/* switch on statistics profiling */
-			dasd_profile_level = DASD_PROFILE_ON;
+			rc = dasd_stats_all_block_on();
+			if (rc) {
+				dasd_stats_all_block_off();
+				goto out_error;
+			}
+			dasd_global_profile_reset();
+			dasd_global_profile_level = DASD_PROFILE_ON;
 			pr_info("The statistics feature has been switched "
 				"on\n");
 		} else if (strcmp(str, "off") == 0) {
 			/* switch off and reset statistics profiling */
-			memset(&dasd_global_profile,
-			       0, sizeof (struct dasd_profile_info_t));
-			dasd_profile_level = DASD_PROFILE_OFF;
+			dasd_global_profile_level = DASD_PROFILE_OFF;
+			dasd_global_profile_reset();
+			dasd_stats_all_block_off();
 			pr_info("The statistics feature has been switched "
 				"off\n");
 		} else
-			goto out_error;
+			goto out_parse_error;
 	} else if (strncmp(str, "reset", 5) == 0) {
 		/* reset the statistics */
-		memset(&dasd_global_profile, 0,
-		       sizeof (struct dasd_profile_info_t));
+		dasd_global_profile_reset();
+		dasd_stats_all_block_reset();
 		pr_info("The statistics have been reset\n");
 	} else
-		goto out_error;
+		goto out_parse_error;
 	kfree(buffer);
 	return user_len;
-out_error:
+out_parse_error:
+	rc = -EINVAL;
 	pr_warning("%s is not a supported value for /proc/dasd/statistics\n",
 		str);
+out_error:
 	kfree(buffer);
-	return -EINVAL;
+	return rc;
 #else
 	pr_warning("/proc/dasd/statistics: is not activated in this kernel\n");
 	return user_len;
diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig
index a4f117d9fdc..2c9a776bd63 100644
--- a/drivers/s390/char/Kconfig
+++ b/drivers/s390/char/Kconfig
@@ -116,9 +116,6 @@ config S390_TAPE
 	  called tape390 and include all selected interfaces and
 	  hardware drivers.
 
-comment "S/390 tape interface support"
-	depends on S390_TAPE
-
 comment "S/390 tape hardware support"
 	depends on S390_TAPE
 
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 5c4e741d822..68be6e15712 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -95,9 +95,11 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 	}
 }
 
-static inline u32 shared_ind_set(void)
+static inline u32 clear_shared_ind(void)
 {
-	return q_indicators[TIQDIO_SHARED_IND].ind;
+	if (!atomic_read(&q_indicators[TIQDIO_SHARED_IND].count))
+		return 0;
+	return xchg(&q_indicators[TIQDIO_SHARED_IND].ind, 0);
 }
 
 /**
@@ -107,7 +109,7 @@ static inline u32 shared_ind_set(void)
  */
 static void tiqdio_thinint_handler(void *alsi, void *data)
 {
-	u32 si_used = shared_ind_set();
+	u32 si_used = clear_shared_ind();
 	struct qdio_q *q;
 
 	last_ai_time = S390_lowcore.int_clock;
@@ -150,13 +152,6 @@ static void tiqdio_thinint_handler(void *alsi, void *data)
 		qperf_inc(q, adapter_int);
 	}
 	rcu_read_unlock();
-
-	/*
-	 * If the shared indicator was used clear it now after all queues
-	 * were processed.
-	 */
-	if (si_used && shared_ind_set())
-		xchg(&q_indicators[TIQDIO_SHARED_IND].ind, 0);
 }
 
 static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 16e4a25596e..f8134a44cef 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -6,6 +6,7 @@
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Ralph Wuerthner <rwuerthn@de.ibm.com>
  *	      Felix Beck <felix.beck@de.ibm.com>
+ *	      Holger Dengler <hd@linux.vnet.ibm.com>
  *
  * Adjunct processor bus.
  *
@@ -222,47 +223,52 @@ ap_queue_interruption_control(ap_qid_t qid, void *ind)
 }
 #endif
 
-static inline struct ap_queue_status __ap_4096_commands_available(ap_qid_t qid,
-								  int *support)
+#ifdef CONFIG_64BIT
+static inline struct ap_queue_status
+__ap_query_functions(ap_qid_t qid, unsigned int *functions)
 {
 	register unsigned long reg0 asm ("0") = 0UL | qid | (1UL << 23);
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
+	register struct ap_queue_status reg1 asm ("1") = AP_QUEUE_STATUS_INVALID;
+	register unsigned long reg2 asm ("2");
 
 	asm volatile(
 		".long 0xb2af0000\n"
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "=d" (reg1), "=d" (reg2)
+		"0:\n"
+		EX_TABLE(0b, 0b)
+		: "+d" (reg0), "+d" (reg1), "=d" (reg2)
 		:
 		: "cc");
 
-	if (reg2 & 0x6000000000000000ULL)
-		*support = 1;
-	else
-		*support = 0;
-
+	*functions = (unsigned int)(reg2 >> 32);
 	return reg1;
 }
+#endif
 
 /**
- * ap_4096_commands_availablen(): Check for availability of 4096 bit RSA
- * support.
+ * ap_query_functions(): Query supported functions.
  * @qid: The AP queue number
+ * @functions: Pointer to functions field.
  *
- * Returns 1 if 4096 bit RSA keys are support fo the AP, returns 0 if not.
+ * Returns
+ *   0	     on success.
+ *   -ENODEV  if queue not valid.
+ *   -EBUSY   if device busy.
+ *   -EINVAL  if query function is not supported
  */
-int ap_4096_commands_available(ap_qid_t qid)
+static int ap_query_functions(ap_qid_t qid, unsigned int *functions)
 {
+#ifdef CONFIG_64BIT
 	struct ap_queue_status status;
-	int i, support = 0;
-	status = __ap_4096_commands_available(qid, &support);
+	int i;
+	status = __ap_query_functions(qid, functions);
 
 	for (i = 0; i < AP_MAX_RESET; i++) {
+		if (ap_queue_status_invalid_test(&status))
+			return -ENODEV;
+
 		switch (status.response_code) {
 		case AP_RESPONSE_NORMAL:
-			return support;
+			return 0;
 		case AP_RESPONSE_RESET_IN_PROGRESS:
 		case AP_RESPONSE_BUSY:
 			break;
@@ -270,7 +276,7 @@ int ap_4096_commands_available(ap_qid_t qid)
 		case AP_RESPONSE_DECONFIGURED:
 		case AP_RESPONSE_CHECKSTOPPED:
 		case AP_RESPONSE_INVALID_ADDRESS:
-			return 0;
+			return -ENODEV;
 		case AP_RESPONSE_OTHERWISE_CHANGED:
 			break;
 		default:
@@ -278,10 +284,31 @@ int ap_4096_commands_available(ap_qid_t qid)
 		}
 		if (i < AP_MAX_RESET - 1) {
 			udelay(5);
-			status = __ap_4096_commands_available(qid, &support);
+			status = __ap_query_functions(qid, functions);
 		}
 	}
-	return support;
+	return -EBUSY;
+#else
+	return -EINVAL;
+#endif
+}
+
+/**
+ * ap_4096_commands_availablen(): Check for availability of 4096 bit RSA
+ * support.
+ * @qid: The AP queue number
+ *
+ * Returns 1 if 4096 bit RSA keys are support fo the AP, returns 0 if not.
+ */
+int ap_4096_commands_available(ap_qid_t qid)
+{
+	unsigned int functions;
+
+	if (ap_query_functions(qid, &functions))
+		return 0;
+
+	return test_ap_facility(functions, 1) &&
+	       test_ap_facility(functions, 2);
 }
 EXPORT_SYMBOL(ap_4096_commands_available);
 
@@ -1135,6 +1162,7 @@ static void ap_scan_bus(struct work_struct *unused)
 	struct device *dev;
 	ap_qid_t qid;
 	int queue_depth, device_type;
+	unsigned int device_functions;
 	int rc, i;
 
 	if (ap_select_domain() != 0)
@@ -1183,14 +1211,30 @@ static void ap_scan_bus(struct work_struct *unused)
 		INIT_LIST_HEAD(&ap_dev->list);
 		setup_timer(&ap_dev->timeout, ap_request_timeout,
 			    (unsigned long) ap_dev);
-		if (device_type == 0) {
+		switch (device_type) {
+		case 0:
 			if (ap_probe_device_type(ap_dev)) {
 				kfree(ap_dev);
 				continue;
 			}
-		}
-		else
+			break;
+		case 10:
+			if (ap_query_functions(qid, &device_functions)) {
+				kfree(ap_dev);
+				continue;
+			}
+			if (test_ap_facility(device_functions, 3))
+				ap_dev->device_type = AP_DEVICE_TYPE_CEX3C;
+			else if (test_ap_facility(device_functions, 4))
+				ap_dev->device_type = AP_DEVICE_TYPE_CEX3A;
+			else {
+				kfree(ap_dev);
+				continue;
+			}
+			break;
+		default:
 			ap_dev->device_type = device_type;
+		}
 
 		ap_dev->device.bus = &ap_bus_type;
 		ap_dev->device.parent = ap_root_device;
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 08b9738285b..d960a6309ee 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -6,6 +6,7 @@
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Ralph Wuerthner <rwuerthn@de.ibm.com>
  *	      Felix Beck <felix.beck@de.ibm.com>
+ *	      Holger Dengler <hd@linux.vnet.ibm.com>
  *
  * Adjunct processor bus header file.
  *
@@ -72,7 +73,26 @@ struct ap_queue_status {
 	unsigned int int_enabled	: 1;
 	unsigned int response_code	: 8;
 	unsigned int pad2		: 16;
-};
+} __packed;
+
+#define AP_QUEUE_STATUS_INVALID \
+		{ 1, 1, 1, 0xF, 1, 0xFF, 0xFFFF }
+
+static inline
+int ap_queue_status_invalid_test(struct ap_queue_status *status)
+{
+	struct ap_queue_status invalid = AP_QUEUE_STATUS_INVALID;
+	return !(memcmp(status, &invalid, sizeof(struct ap_queue_status)));
+}
+
+#define MAX_AP_FACILITY 31
+
+static inline int test_ap_facility(unsigned int function, unsigned int nr)
+{
+	if (nr > MAX_AP_FACILITY)
+		return 0;
+	return function & (unsigned int)(0x80000000 >> nr);
+}
 
 #define AP_RESPONSE_NORMAL		0x00
 #define AP_RESPONSE_Q_NOT_AVAIL		0x01
diff --git a/mm/rmap.c b/mm/rmap.c
index 2540a39eea4..9701574bb67 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -869,11 +869,11 @@ int page_referenced(struct page *page,
 								vm_flags);
 		if (we_locked)
 			unlock_page(page);
+
+		if (page_test_and_clear_young(page_to_pfn(page)))
+			referenced++;
 	}
 out:
-	if (page_test_and_clear_young(page_to_pfn(page)))
-		referenced++;
-
 	return referenced;
 }
 
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 7f9124914b1..f2b713847b4 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -1988,12 +1988,13 @@ static int __init iucv_init(void)
 		rc = -EPROTONOSUPPORT;
 		goto out;
 	}
+	ctl_set_bit(0, 1);
 	rc = iucv_query_maxconn();
 	if (rc)
-		goto out;
+		goto out_ctl;
 	rc = register_external_interrupt(0x4000, iucv_external_interrupt);
 	if (rc)
-		goto out;
+		goto out_ctl;
 	iucv_root = root_device_register("iucv");
 	if (IS_ERR(iucv_root)) {
 		rc = PTR_ERR(iucv_root);
@@ -2055,6 +2056,8 @@ out_free:
 	root_device_unregister(iucv_root);
 out_int:
 	unregister_external_interrupt(0x4000, iucv_external_interrupt);
+out_ctl:
+	ctl_clear_bit(0, 1);
 out:
 	return rc;
 }