18 files changed, 225 insertions, 235 deletions

diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index 8df8d8a19c9..64b24650e4f 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -59,8 +59,8 @@ enum {
 
 enum {
 	CACHE_TI_UNIFIED = 0,
-	CACHE_TI_INSTRUCTION = 0,
-	CACHE_TI_DATA,
+	CACHE_TI_DATA = 0,
+	CACHE_TI_INSTRUCTION,
 };
 
 struct cache_info {
@@ -121,7 +121,10 @@ static int __init cache_add(int level, int private, int type)
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (!cache)
 		return -ENOMEM;
-	ti = type == CACHE_TYPE_DATA ? CACHE_TI_DATA : CACHE_TI_UNIFIED;
+	if (type == CACHE_TYPE_INSTRUCTION)
+		ti = CACHE_TI_INSTRUCTION;
+	else
+		ti = CACHE_TI_UNIFIED;
 	cache->size = ecag(EXTRACT_SIZE, level, ti);
 	cache->line_size = ecag(EXTRACT_LINE_SIZE, level, ti);
 	cache->associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti);
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 189963c90c6..65cca95843e 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -432,32 +432,6 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo)
 	return ret;
 }
 
-/*
- * sys32_execve() executes a new program after the asm stub has set
- * things up for us.  This should basically do what I want it to.
- */
-asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
-			     compat_uptr_t __user *envp)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	char *filename;
-	long rc;
-
-	filename = getname(name);
-	rc = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		return rc;
-	rc = compat_do_execve(filename, argv, envp, regs);
-	if (rc)
-		goto out;
-	current->thread.fp_regs.fpc=0;
-	asm volatile("sfpc %0,0" : : "d" (0));
-	rc = regs->gprs[2];
-out:
-	putname(filename);
-	return rc;
-}
-
 asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf,
 				size_t count, u32 poshi, u32 poslo)
 {
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 90887bd98cf..d4d0239970a 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -125,8 +125,6 @@ long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
 			  compat_sigset_t __user *oset, size_t sigsetsize);
 long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize);
 long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo);
-long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
-		  compat_uptr_t __user *envp);
 long sys32_init_module(void __user *umod, unsigned long len,
 		       const char __user *uargs);
 long sys32_delete_module(const char __user *name_user, unsigned int flags);
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 3afba804fe9..ad79b846535 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1576,7 +1576,7 @@ 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
+	jg	compat_sys_execve	# branch to system call
 
 ENTRY(sys_fanotify_init_wrapper)
 	llgfr	%r2,%r2			# unsigned int
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 00d11444506..1f0eee9e7da 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -283,14 +283,6 @@ static noinline __init void setup_facility_list(void)
 	      ARRAY_SIZE(S390_lowcore.stfle_fac_list));
 }
 
-static noinline __init void setup_hpage(void)
-{
-	if (!test_facility(2) || !test_facility(8))
-		return;
-	S390_lowcore.machine_flags |= MACHINE_FLAG_HPAGE;
-	__ctl_set_bit(0, 23);
-}
-
 static __init void detect_mvpg(void)
 {
 #ifndef CONFIG_64BIT
@@ -378,10 +370,14 @@ static __init void detect_diag44(void)
 static __init void detect_machine_facilities(void)
 {
 #ifdef CONFIG_64BIT
+	if (test_facility(8)) {
+		S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT1;
+		__ctl_set_bit(0, 23);
+	}
+	if (test_facility(78))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2;
 	if (test_facility(3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
-	if (test_facility(8))
-		S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF;
 	if (test_facility(27))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
 	if (test_facility(40))
@@ -484,7 +480,6 @@ void __init startup_init(void)
 	detect_diag9c();
 	detect_diag44();
 	detect_machine_facilities();
-	setup_hpage();
 	setup_topology();
 	sclp_facilities_detect();
 	detect_memory_layout(memory_chunk);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 870bad6d56f..ef46f66bc0d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -331,45 +331,38 @@ ENTRY(ret_from_fork)
 	l	%r12,__LC_THREAD_INFO
 	l	%r13,__LC_SVC_NEW_PSW+4
 	tm	__PT_PSW+1(%r11),0x01	# forking a kernel thread ?
-	jo	0f
-	st	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
-0:	l	%r1,BASED(.Lschedule_tail)
+	je	1f
+	l	%r1,BASED(.Lschedule_tail)
 	basr	%r14,%r1		# call schedule_tail
 	TRACE_IRQS_ON
 	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	j	sysc_tracenogo
 
+1:	# it's a kernel thread
+	st	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
+	l	%r1,BASED(.Lschedule_tail)
+	basr	%r14,%r1		# call schedule_tail
+	TRACE_IRQS_ON
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lm	%r9,%r11,__PT_R9(%r11)	# load gprs
+ENTRY(kernel_thread_starter)
+	la	%r2,0(%r10)
+	basr	%r14,%r9
+	la	%r2,0
+	br	%r11			# do_exit
+
 #
 # kernel_execve function needs to deal with pt_regs that is not
 # at the usual place
 #
-ENTRY(kernel_execve)
-	stm	%r12,%r15,48(%r15)
-	lr	%r14,%r15
-	l	%r13,__LC_SVC_NEW_PSW+4
-	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	st	%r14,__SF_BACKCHAIN(%r15)
-	la	%r12,STACK_FRAME_OVERHEAD(%r15)
-	xc	0(__PT_SIZE,%r12),0(%r12)
-	l	%r1,BASED(.Ldo_execve)
-	lr	%r5,%r12
-	basr	%r14,%r1		# call do_execve
-	ltr	%r2,%r2
-	je	0f
-	ahi	%r15,(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	lm	%r12,%r15,48(%r15)
-	br	%r14
-	# execve succeeded.
-0:	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
-	l	%r15,__LC_KERNEL_STACK	# load ksp
-	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	mvc	0(__PT_SIZE,%r11),0(%r12)	# copy pt_regs
-	l	%r12,__LC_THREAD_INFO
+ENTRY(ret_from_kernel_execve)
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	lr	%r15,%r2
+	lr	%r11,%r2
+	ahi	%r15,-STACK_FRAME_OVERHEAD
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	l	%r12,__LC_THREAD_INFO
 	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
-	l	%r1,BASED(.Lexecve_tail)
-	basr	%r14,%r1		# call execve_tail
 	j	sysc_return
 
 /*
@@ -931,8 +924,6 @@ cleanup_idle_wait:
 .Ldo_signal:		.long	do_signal
 .Ldo_notify_resume:	.long	do_notify_resume
 .Ldo_per_trap:		.long	do_per_trap
-.Ldo_execve:		.long	do_execve
-.Lexecve_tail:		.long	execve_tail
 .Ljump_table:		.long	pgm_check_table
 .Lschedule:		.long	schedule
 #ifdef CONFIG_PREEMPT
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index a5f4dc42a5d..d0d3f69a734 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -58,9 +58,6 @@ long sys_fork(void);
 long sys_clone(unsigned long newsp, unsigned long clone_flags,
 	       int __user *parent_tidptr, int __user *child_tidptr);
 long sys_vfork(void);
-void execve_tail(void);
-long sys_execve(const char __user *name, const char __user *const __user *argv,
-		const char __user *const __user *envp);
 long sys_sigsuspend(int history0, int history1, old_sigset_t mask);
 long sys_sigaction(int sig, const struct old_sigaction __user *act,
 		   struct old_sigaction __user *oact);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 7549985402f..07d8de35398 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -295,7 +295,7 @@ sysc_sigpending:
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
 	lghi	%r8,0			# svc 0 returns -ENOSYS
-	lh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
+	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
 	slag	%r8,%r1,2
@@ -353,41 +353,31 @@ ENTRY(ret_from_fork)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	lg	%r12,__LC_THREAD_INFO
 	tm	__PT_PSW+1(%r11),0x01	# forking a kernel thread ?
-	jo	0f
-	stg	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
-0:	brasl	%r14,schedule_tail
+	je	1f
+	brasl	%r14,schedule_tail
 	TRACE_IRQS_ON
 	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	j	sysc_tracenogo
-
-#
-# kernel_execve function needs to deal with pt_regs that is not
-# at the usual place
-#
-ENTRY(kernel_execve)
-	stmg	%r12,%r15,96(%r15)
-	lgr	%r14,%r15
-	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	stg	%r14,__SF_BACKCHAIN(%r15)
-	la	%r12,STACK_FRAME_OVERHEAD(%r15)
-	xc	0(__PT_SIZE,%r12),0(%r12)
-	lgr	%r5,%r12
-	brasl	%r14,do_execve
-	ltgfr	%r2,%r2
-	je	0f
-	aghi	%r15,(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	lmg	%r12,%r15,96(%r15)
-	br	%r14
-	# execve succeeded.
-0:	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
-	lg	%r15,__LC_KERNEL_STACK	# load ksp
-	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	mvc	0(__PT_SIZE,%r11),0(%r12)	# copy pt_regs
-	lg	%r12,__LC_THREAD_INFO
+1:	# it's a kernel thread
+	stg	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
+	brasl	%r14,schedule_tail
+	TRACE_IRQS_ON
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lmg	%r9,%r11,__PT_R9(%r11)	# load gprs
+ENTRY(kernel_thread_starter)
+	la	%r2,0(%r10)
+	basr	%r14,%r9
+	la	%r2,0
+	br	%r11			# do_exit
+
+ENTRY(ret_from_kernel_execve)
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	lgr	%r15,%r2
+	lgr	%r11,%r2
+	aghi	%r15,-STACK_FRAME_OVERHEAD
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lg	%r12,__LC_THREAD_INFO
 	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
-	brasl	%r14,execve_tail
 	j	sysc_return
 
 /*
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 805b6686b64..984726cbce1 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -52,7 +52,7 @@ __HEAD
 	.long	0x02000370,0x60000050		# the channel program the PSW
 	.long	0x020003c0,0x60000050		# at location 0 is loaded.
 	.long	0x02000410,0x60000050		# Initial processing starts
-	.long	0x02000460,0x60000050		# at 0xf0 = iplstart.
+	.long	0x02000460,0x60000050		# at 0x200 = iplstart.
 	.long	0x020004b0,0x60000050
 	.long	0x02000500,0x60000050
 	.long	0x02000550,0x60000050
@@ -62,11 +62,54 @@ __HEAD
 	.long	0x02000690,0x60000050
 	.long	0x020006e0,0x20000050
 
-	.org	0xf0
+	.org	0x200
+#
+# subroutine to set architecture mode
+#
+.Lsetmode:
+#ifdef CONFIG_64BIT
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam31				# switch to 31 bit addressing mode
+#else
+	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
+#endif
+	br	%r14
+
+#
+# subroutine to wait for end I/O
+#
+.Lirqwait:
+#ifdef CONFIG_64BIT
+	mvc	0x1f0(16),.Lnewpsw	# set up IO interrupt psw
+	lpsw	.Lwaitpsw
+.Lioint:
+	br	%r14
+	.align	8
+.Lnewpsw:
+	.quad	0x0000000080000000,.Lioint
+#else
+	mvc	0x78(8),.Lnewpsw	# set up IO interrupt psw
+	lpsw	.Lwaitpsw
+.Lioint:
+	br	%r14
+	.align	8
+.Lnewpsw:
+	.long	0x00080000,0x80000000+.Lioint
+#endif
+.Lwaitpsw:
+	.long	0x020a0000,0x80000000+.Lioint
+
 #
 # subroutine for loading cards from the reader
 #
 .Lloader:
+	la	%r4,0(%r14)
 	la	%r3,.Lorb		# r2 = address of orb into r2
 	la	%r5,.Lirb		# r4 = address of irb
 	la	%r6,.Lccws
@@ -83,9 +126,7 @@ __HEAD
 	ssch	0(%r3)			# load chunk of 1600 bytes
 	bnz	.Llderr
 .Lwait4irq:
-	mvc	0x78(8),.Lnewpsw	# set up IO interrupt psw
-	lpsw	.Lwaitpsw
-.Lioint:
+	bas	%r14,.Lirqwait
 	c	%r1,0xb8		# compare subchannel number
 	bne	.Lwait4irq
 	tsch	0(%r5)
@@ -104,7 +145,7 @@ __HEAD
 	sr	%r0,%r3 		# #ccws*80-residual=#bytes read
 	ar	%r2,%r0
 
-	br	%r14			# r2 contains the total size
+	br	%r4			# r2 contains the total size
 
 .Lcont:
 	ahi	%r2,0x640		# add 0x640 to total size
@@ -128,10 +169,6 @@ __HEAD
 .Lloadp:.long	0,0
 	.align	8
 .Lcrash:.long	0x000a0000,0x00000000
-.Lnewpsw:
-	.long	0x00080000,0x80000000+.Lioint
-.Lwaitpsw:
-	.long	0x020a0000,0x80000000+.Lioint
 
 	.align	8
 .Lccws: .rept	19
@@ -140,6 +177,7 @@ __HEAD
 	.long	0x02200050,0x00000000
 
 iplstart:
+	bas	%r14,.Lsetmode		# Immediately switch to 64 bit mode
 	lh	%r1,0xb8		# test if subchannel number
 	bct	%r1,.Lnoload		#  is valid
 	l	%r1,0xb8		# load ipl subchannel number
@@ -209,8 +247,8 @@ iplstart:
 #
 # reset files in VM reader
 #
-	stidp	__LC_SAVE_AREA_SYNC	# store cpuid
-	tm	__LC_SAVE_AREA_SYNC,0xff# running VM ?
+	stidp	.Lcpuid			# store cpuid
+	tm	.Lcpuid,0xff		# running VM ?
 	bno	.Lnoreset
 	la	%r2,.Lreset
 	lhi	%r3,26
@@ -222,23 +260,14 @@ iplstart:
 	tm	31(%r5),0xff		# bits is set in the schib
 	bz	.Lnoreset
 .Lwaitforirq:
-	mvc	0x78(8),.Lrdrnewpsw	# set up IO interrupt psw
-.Lwaitrdrirq:
-	lpsw	.Lrdrwaitpsw
-.Lrdrint:
+	bas	%r14,.Lirqwait		# wait for IO interrupt
 	c	%r1,0xb8		# compare subchannel number
-	bne	.Lwaitrdrirq
+	bne	.Lwaitforirq
 	la	%r5,.Lirb
 	tsch	0(%r5)
 .Lnoreset:
 	b	.Lnoload
 
-	.align	8
-.Lrdrnewpsw:
-	.long	0x00080000,0x80000000+.Lrdrint
-.Lrdrwaitpsw:
-	.long	0x020a0000,0x80000000+.Lrdrint
-
 #
 # everything loaded, go for it
 #
@@ -254,6 +283,8 @@ iplstart:
 	.byte	0xc8,0xd6,0xd3,0xc4	# "change rdr all keep nohold"
 .L_eof: .long	0xc5d6c600	 /* C'EOF' */
 .L_hdr: .long	0xc8c4d900	 /* C'HDR' */
+	.align	8
+.Lcpuid:.fill	8,1,0
 
 #
 # SALIPL loader support. Based on a patch by Rob van der Heij.
@@ -263,6 +294,7 @@ iplstart:
 	.org	0x800
 ENTRY(start)
 	stm	%r0,%r15,0x07b0		# store registers
+	bas	%r14,.Lsetmode		# Immediately switch to 64 bit mode
 	basr	%r12,%r0
 .base:
 	l	%r11,.parm
@@ -343,6 +375,18 @@ ENTRY(startup)
 ENTRY(startup_kdump)
 	j	.Lep_startup_kdump
 .Lep_startup_normal:
+#ifdef CONFIG_64BIT
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam31				# switch to 31 bit addressing mode
+#else
+	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
+#endif
 	basr	%r13,0			# get base
 .LPG0:
 	xc	0x200(256),0x200	# partially clear lowcore
@@ -410,22 +454,17 @@ ENTRY(startup_kdump)
 #endif
 
 #ifdef CONFIG_64BIT
-	mvi	__LC_AR_MODE_ID,1	# set esame flag
-	slr	%r0,%r0 		# set cpuid to zero
-	lhi	%r1,2			# mode 2 = esame (dump)
-	sigp	%r1,%r0,0x12		# switch to esame mode
+	/* Continue with 64bit startup code in head64.S */
 	sam64				# switch to 64 bit mode
-	larl	%r13,4f
-	lmh	%r0,%r15,0(%r13)	# clear high-order half
 	jg	startup_continue
-4:	.fill	16,4,0x0
 #else
-	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
+	/* Continue with 31bit startup code in head31.S */
 	l	%r13,4f-.LPG0(%r13)
 	b	0(%r13)
 	.align	8
 4:	.long	startup_continue
 #endif
+
 	.align	8
 5:	.long	0x7fffffff,0xffffffff
 
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index a1372ae24ae..9a99856df1c 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -78,10 +78,7 @@ ENTRY(startup_continue)
 
 ENTRY(_ehead)
 
-#ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
-#endif
-
 #
 # startup-code, running in absolute addressing mode
 #
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index c108af28bbe..b9e25ae2579 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -76,10 +76,7 @@ ENTRY(startup_continue)
 
 ENTRY(_ehead)
 
-#ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
-#endif
-
 #
 # startup-code, running in absolute addressing mode
 #
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S
index acaaaf4b705..085a95eb315 100644
--- a/arch/s390/kernel/head_kdump.S
+++ b/arch/s390/kernel/head_kdump.S
@@ -85,16 +85,10 @@
 .align 2
 startup_kdump_relocated:
 	basr	%r13,0
-0:
-	mvc	0(8,%r0),.Lrestart_psw-0b(%r13)	# Setup restart PSW
-	sam31					# Switch to 31 bit addr mode
-	sr	%r1,%r1				# Erase register r1
-	sr	%r2,%r2				# Erase register r2
-	sigp	%r1,%r2,SIGP_SET_ARCHITECTURE	# Switch to 31 bit arch mode
-	lpsw	0				# Start new kernel...
+0:	lpswe	.Lrestart_psw-0b(%r13)		# Start new kernel...
 .align	8
 .Lrestart_psw:
-	.long	0x00080000,0x80000000 + startup
+	.quad	0x0000000080000000,0x0000000000000000 + startup
 #else
 .align 2
 .Lep_startup_kdump:
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 46412b1d7e1..4610deafd95 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -44,6 +44,17 @@
 #define PLT_ENTRY_SIZE 20
 #endif /* CONFIG_64BIT */
 
+#ifdef CONFIG_64BIT
+void *module_alloc(unsigned long size)
+{
+	if (PAGE_ALIGN(size) > MODULES_LEN)
+		return NULL;
+	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				    GFP_KERNEL, PAGE_KERNEL, -1,
+				    __builtin_return_address(0));
+}
+#endif
+
 /* Free memory returned from module_alloc */
 void module_free(struct module *mod, void *module_region)
 {
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 9871b1971ed..c4e7269d4a0 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -94,7 +94,7 @@ static int get_counter_set(u64 event)
 		set = CPUMF_CTR_SET_USER;
 	else if (event < 128)
 		set = CPUMF_CTR_SET_CRYPTO;
-	else if (event < 160)
+	else if (event < 256)
 		set = CPUMF_CTR_SET_EXT;
 
 	return set;
@@ -138,6 +138,10 @@ static int validate_ctr_version(const struct hw_perf_event *hwc)
 	case CPUMF_CTR_SET_EXT:
 		if (cpuhw->info.csvn < 1)
 			err = -EOPNOTSUPP;
+		if ((cpuhw->info.csvn == 1 && hwc->config > 159) ||
+		    (cpuhw->info.csvn == 2 && hwc->config > 175) ||
+		    (cpuhw->info.csvn  > 2 && hwc->config > 255))
+			err = -EOPNOTSUPP;
 		break;
 	}
 
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 5024be27df4..cd31ad457a9 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -100,35 +100,6 @@ void cpu_idle(void)
 
 extern void __kprobes kernel_thread_starter(void);
 
-asm(
-	".section .kprobes.text, \"ax\"\n"
-	".global kernel_thread_starter\n"
-	"kernel_thread_starter:\n"
-	"    la    2,0(10)\n"
-	"    basr  14,9\n"
-	"    la    2,0\n"
-	"    br    11\n"
-	".previous\n");
-
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-	regs.psw.mask = psw_kernel_bits |
-		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE;
-	regs.gprs[9] = (unsigned long) fn;
-	regs.gprs[10] = (unsigned long) arg;
-	regs.gprs[11] = (unsigned long) do_exit;
-	regs.orig_gpr2 = -1;
-
-	/* Ok, create the new process.. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED,
-		       0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 /*
  * Free current thread data structures etc..
  */
@@ -146,7 +117,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
-		unsigned long unused,
+		unsigned long arg,
 		struct task_struct *p, struct pt_regs *regs)
 {
 	struct thread_info *ti;
@@ -158,20 +129,44 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 
 	frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
 	p->thread.ksp = (unsigned long) frame;
-	/* Store access registers to kernel stack of new process. */
-	frame->childregs = *regs;
-	frame->childregs.gprs[2] = 0;	/* child returns 0 on fork. */
-	frame->childregs.gprs[15] = new_stackp;
-	frame->sf.back_chain = 0;
+	/* Save access registers to new thread structure. */
+	save_access_regs(&p->thread.acrs[0]);
+	/* start new process with ar4 pointing to the correct address space */
+	p->thread.mm_segment = get_fs();
+	/* Don't copy debug registers */
+	memset(&p->thread.per_user, 0, sizeof(p->thread.per_user));
+	memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
+	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
+	clear_tsk_thread_flag(p, TIF_PER_TRAP);
+	/* Initialize per thread user and system timer values */
+	ti = task_thread_info(p);
+	ti->user_timer = 0;
+	ti->system_timer = 0;
 
+	frame->sf.back_chain = 0;
 	/* new return point is ret_from_fork */
 	frame->sf.gprs[8] = (unsigned long) ret_from_fork;
-
 	/* fake return stack for resume(), don't go back to schedule */
 	frame->sf.gprs[9] = (unsigned long) frame;
 
-	/* Save access registers to new thread structure. */
-	save_access_regs(&p->thread.acrs[0]);
+	/* Store access registers to kernel stack of new process. */
+	if (unlikely(!regs)) {
+		/* kernel thread */
+		memset(&frame->childregs, 0, sizeof(struct pt_regs));
+		frame->childregs.psw.mask = psw_kernel_bits | PSW_MASK_DAT |
+				PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+		frame->childregs.psw.addr = PSW_ADDR_AMODE |
+				(unsigned long) kernel_thread_starter;
+		frame->childregs.gprs[9] = new_stackp; /* function */
+		frame->childregs.gprs[10] = arg;
+		frame->childregs.gprs[11] = (unsigned long) do_exit;
+		frame->childregs.orig_gpr2 = -1;
+
+		return 0;
+	}
+	frame->childregs = *regs;
+	frame->childregs.gprs[2] = 0;	/* child returns 0 on fork. */
+	frame->childregs.gprs[15] = new_stackp;
 
 	/* Don't copy runtime instrumentation info */
 	p->thread.ri_cb = NULL;
@@ -202,17 +197,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 		}
 	}
 #endif /* CONFIG_64BIT */
-	/* start new process with ar4 pointing to the correct address space */
-	p->thread.mm_segment = get_fs();
-	/* Don't copy debug registers */
-	memset(&p->thread.per_user, 0, sizeof(p->thread.per_user));
-	memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
-	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
-	clear_tsk_thread_flag(p, TIF_PER_TRAP);
-	/* Initialize per thread user and system timer values */
-	ti = task_thread_info(p);
-	ti->user_timer = 0;
-	ti->system_timer = 0;
 	return 0;
 }
 
@@ -258,31 +242,6 @@ asmlinkage void execve_tail(void)
 }
 
 /*
- * sys_execve() executes a new program.
- */
-SYSCALL_DEFINE3(execve, const char __user *, name,
-		const char __user *const __user *, argv,
-		const char __user *const __user *, envp)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	char *filename;
-	long rc;
-
-	filename = getname(name);
-	rc = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		return rc;
-	rc = do_execve(filename, argv, envp, regs);
-	if (rc)
-		goto out;
-	execve_tail();
-	rc = regs->gprs[2];
-out:
-	putname(filename);
-	return rc;
-}
-
-/*
  * fill in the FPU structure for a core dump.
  */
 int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index afa9fdba200..b1f2be9aaaa 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -105,6 +105,11 @@ EXPORT_SYMBOL(VMALLOC_END);
 struct page *vmemmap;
 EXPORT_SYMBOL(vmemmap);
 
+#ifdef CONFIG_64BIT
+unsigned long MODULES_VADDR;
+unsigned long MODULES_END;
+#endif
+
 /* An array with a pointer to the lowcore of every CPU. */
 struct _lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
@@ -544,19 +549,23 @@ static void __init setup_memory_end(void)
 
 	/* Choose kernel address space layout: 2, 3, or 4 levels. */
 #ifdef CONFIG_64BIT
-	vmalloc_size = VMALLOC_END ?: 128UL << 30;
+	vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
 	tmp = (memory_end ?: real_memory_size) / PAGE_SIZE;
 	tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size;
 	if (tmp <= (1UL << 42))
 		vmax = 1UL << 42;	/* 3-level kernel page table */
 	else
 		vmax = 1UL << 53;	/* 4-level kernel page table */
+	/* module area is at the end of the kernel address space. */
+	MODULES_END = vmax;
+	MODULES_VADDR = MODULES_END - MODULES_LEN;
+	VMALLOC_END = MODULES_VADDR;
 #else
 	vmalloc_size = VMALLOC_END ?: 96UL << 20;
 	vmax = 1UL << 31;		/* 2-level kernel page table */
-#endif
 	/* vmalloc area is at the end of the kernel address space. */
 	VMALLOC_END = vmax;
+#endif
 	VMALLOC_START = vmax - vmalloc_size;
 
 	/* Split remaining virtual space between 1:1 mapping & vmemmap array */
@@ -768,6 +777,40 @@ static void __init reserve_crashkernel(void)
 #endif
 }
 
+static void __init init_storage_keys(unsigned long start, unsigned long end)
+{
+	unsigned long boundary, function, size;
+
+	while (start < end) {
+		if (MACHINE_HAS_EDAT2) {
+			/* set storage keys for a 2GB frame */
+			function = 0x22000 | PAGE_DEFAULT_KEY;
+			size = 1UL << 31;
+			boundary = (start + size) & ~(size - 1);
+			if (boundary <= end) {
+				do {
+					start = pfmf(function, start);
+				} while (start < boundary);
+				continue;
+			}
+		}
+		if (MACHINE_HAS_EDAT1) {
+			/* set storage keys for a 1MB frame */
+			function = 0x21000 | PAGE_DEFAULT_KEY;
+			size = 1UL << 20;
+			boundary = (start + size) & ~(size - 1);
+			if (boundary <= end) {
+				do {
+					start = pfmf(function, start);
+				} while (start < boundary);
+				continue;
+			}
+		}
+		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+		start += PAGE_SIZE;
+	}
+}
+
 static void __init setup_memory(void)
 {
         unsigned long bootmap_size;
@@ -846,9 +889,7 @@ static void __init setup_memory(void)
 		memblock_add_node(PFN_PHYS(start_chunk),
 				  PFN_PHYS(end_chunk - start_chunk), 0);
 		pfn = max(start_chunk, start_pfn);
-		for (; pfn < end_chunk; pfn++)
-			page_set_storage_key(PFN_PHYS(pfn),
-					     PAGE_DEFAULT_KEY, 0);
+		init_storage_keys(PFN_PHYS(pfn), PFN_PHYS(end_chunk));
 	}
 
 	psw_set_key(PAGE_DEFAULT_KEY);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 2db1011b8b1..7fcd690d42c 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -34,7 +34,7 @@
 #include <linux/profile.h>
 #include <linux/timex.h>
 #include <linux/notifier.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/clockchips.h>
 #include <linux/gfp.h>
 #include <linux/kprobes.h>
@@ -219,7 +219,7 @@ struct clocksource * __init clocksource_default_clock(void)
 	return &clocksource_tod;
 }
 
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
+void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
 	if (clock != &clocksource_tod)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index de8fa9bbd35..79cb51adc74 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -8,7 +8,7 @@
 
 #ifndef CONFIG_64BIT
 OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
-OUTPUT_ARCH(s390)
+OUTPUT_ARCH(s390:31-bit)
 ENTRY(startup)
 jiffies = jiffies_64 + 4;
 #else