Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

17 files changed, 367 insertions, 467 deletions

diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index cc10cdd4d6a2..afe1715a4eb7 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -50,6 +50,7 @@ int main(void)
 	DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code));
 	DEFINE(__PT_INT_PARM, offsetof(struct pt_regs, int_parm));
 	DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long));
+	DEFINE(__PT_FLAGS, offsetof(struct pt_regs, flags));
 	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
 	BLANK();
 	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain));
@@ -89,16 +90,22 @@ int main(void)
 	DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc));
 	DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code));
 	DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code));
-	DEFINE(__LC_PER_CAUSE, offsetof(struct _lowcore, per_perc_atmid));
+	DEFINE(__LC_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num));
+	DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code));
+	DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_atmid));
 	DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address));
-	DEFINE(__LC_PER_PAID, offsetof(struct _lowcore, per_access_id));
-	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id));
+	DEFINE(__LC_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id));
+	DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id));
+	DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id));
+	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id));
+	DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code));
 	DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id));
 	DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr));
 	DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm));
 	DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word));
 	DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list));
 	DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code));
+	DEFINE(__LC_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_code));
 	DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw));
 	DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw));
 	DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw));
@@ -115,6 +122,7 @@ int main(void)
 	DEFINE(__LC_SAVE_AREA_SYNC, offsetof(struct _lowcore, save_area_sync));
 	DEFINE(__LC_SAVE_AREA_ASYNC, offsetof(struct _lowcore, save_area_async));
 	DEFINE(__LC_SAVE_AREA_RESTART, offsetof(struct _lowcore, save_area_restart));
+	DEFINE(__LC_CPU_FLAGS, offsetof(struct _lowcore, cpu_flags));
 	DEFINE(__LC_RETURN_PSW, offsetof(struct _lowcore, return_psw));
 	DEFINE(__LC_RETURN_MCCK_PSW, offsetof(struct _lowcore, return_mcck_psw));
 	DEFINE(__LC_SYNC_ENTER_TIMER, offsetof(struct _lowcore, sync_enter_timer));
@@ -142,7 +150,6 @@ int main(void)
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
 	DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func));
-	DEFINE(__LC_IRB, offsetof(struct _lowcore, irb));
 	DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib));
 	BLANK();
 	DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area));
@@ -156,6 +163,8 @@ int main(void)
 #ifdef CONFIG_32BIT
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr));
 #else /* CONFIG_32BIT */
+	DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code));
+	DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address));
 	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 7df5ed9f44d7..f204d6920368 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -213,7 +213,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	       sizeof(current->thread.fp_regs));
 
 	restore_fp_regs(current->thread.fp_regs.fprs);
-	clear_thread_flag(TIF_SYSCALL);	/* No longer in a system call */
+	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d7658c4b2ed5..a3b9150e6802 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
+#include <linux/memblock.h>
 #include <asm/os_info.h>
 #include <asm/elf.h>
 #include <asm/ipl.h>
@@ -22,6 +23,24 @@
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
 #define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y))))
 
+static struct memblock_region oldmem_region;
+
+static struct memblock_type oldmem_type = {
+	.cnt = 1,
+	.max = 1,
+	.total_size = 0,
+	.regions = &oldmem_region,
+};
+
+#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\
+	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\
+				     &oldmem_type, p_start,		\
+				     p_end, p_nid);			\
+	     i != (u64)ULLONG_MAX;					\
+	     __next_mem_range(&i, nid, &memblock.physmem,		\
+			      &oldmem_type,				\
+			      p_start, p_end, p_nid))
+
 struct dump_save_areas dump_save_areas;
 
 /*
@@ -264,19 +283,6 @@ static void *kzalloc_panic(int len)
 }
 
 /*
- * Get memory layout and create hole for oldmem
- */
-static struct mem_chunk *get_memory_layout(void)
-{
-	struct mem_chunk *chunk_array;
-
-	chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk));
-	detect_memory_layout(chunk_array, 0);
-	create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE);
-	return chunk_array;
-}
-
-/*
  * Initialize ELF note
  */
 static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
@@ -490,52 +496,33 @@ static int get_cpu_cnt(void)
  */
 static int get_mem_chunk_cnt(void)
 {
-	struct mem_chunk *chunk_array, *mem_chunk;
-	int i, cnt = 0;
+	int cnt = 0;
+	u64 idx;
 
-	chunk_array = get_memory_layout();
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		mem_chunk = &chunk_array[i];
-		if (chunk_array[i].type != CHUNK_READ_WRITE &&
-		    chunk_array[i].type != CHUNK_READ_ONLY)
-			continue;
-		if (mem_chunk->size == 0)
-			continue;
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, NULL, NULL, NULL)
 		cnt++;
-	}
-	kfree(chunk_array);
 	return cnt;
 }
 
 /*
  * Initialize ELF loads (new kernel)
  */
-static int loads_init(Elf64_Phdr *phdr, u64 loads_offset)
+static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
 {
-	struct mem_chunk *chunk_array, *mem_chunk;
-	int i;
+	phys_addr_t start, end;
+	u64 idx;
 
-	chunk_array = get_memory_layout();
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		mem_chunk = &chunk_array[i];
-		if (mem_chunk->size == 0)
-			continue;
-		if (chunk_array[i].type != CHUNK_READ_WRITE &&
-		    chunk_array[i].type != CHUNK_READ_ONLY)
-			continue;
-		else
-			phdr->p_filesz = mem_chunk->size;
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, &start, &end, NULL) {
+		phdr->p_filesz = end - start;
 		phdr->p_type = PT_LOAD;
-		phdr->p_offset = mem_chunk->addr;
-		phdr->p_vaddr = mem_chunk->addr;
-		phdr->p_paddr = mem_chunk->addr;
-		phdr->p_memsz = mem_chunk->size;
+		phdr->p_offset = start;
+		phdr->p_vaddr = start;
+		phdr->p_paddr = start;
+		phdr->p_memsz = end - start;
 		phdr->p_flags = PF_R | PF_W | PF_X;
 		phdr->p_align = PAGE_SIZE;
 		phdr++;
 	}
-	kfree(chunk_array);
-	return i;
 }
 
 /*
@@ -584,6 +571,14 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	/* If we cannot get HSA size for zfcpdump return error */
 	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size())
 		return -ENODEV;
+
+	/* For kdump, exclude previous crashkernel memory */
+	if (OLDMEM_BASE) {
+		oldmem_region.base = OLDMEM_BASE;
+		oldmem_region.size = OLDMEM_SIZE;
+		oldmem_type.total_size = OLDMEM_SIZE;
+	}
+
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
 	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index a734f3585ceb..0dff972a169c 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -258,13 +258,19 @@ static __init void setup_topology(void)
 static void early_pgm_check_handler(void)
 {
 	const struct exception_table_entry *fixup;
+	unsigned long cr0, cr0_new;
 	unsigned long addr;
 
 	addr = S390_lowcore.program_old_psw.addr;
 	fixup = search_exception_tables(addr & PSW_ADDR_INSN);
 	if (!fixup)
 		disabled_wait(0);
+	/* Disable low address protection before storing into lowcore. */
+	__ctl_store(cr0, 0, 0);
+	cr0_new = cr0 & ~(1UL << 28);
+	__ctl_load(cr0_new, 0, 0);
 	S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE;
+	__ctl_load(cr0, 0, 0);
 }
 
 static noinline __init void setup_lowcore_early(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 1662038516c0..70203265196f 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -37,18 +38,16 @@ __PT_R13     =	__PT_GPRS + 524
 __PT_R14     =	__PT_GPRS + 56
 __PT_R15     =	__PT_GPRS + 60
 
-_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		 _TIF_MCCK_PENDING | _TIF_PER_TRAP | _TIF_ASCE)
-_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		 _TIF_MCCK_PENDING | _TIF_ASCE)
-_TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
-		 _TIF_SYSCALL_TRACEPOINT)
-_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
-
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT  = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
+_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+_TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
+		   _TIF_SYSCALL_TRACEPOINT)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
+_PIF_WORK	= (_PIF_PER_TRAP)
+
 #define BASED(name) name-system_call(%r13)
 
 	.macro	TRACE_IRQS_ON
@@ -160,13 +159,7 @@ ENTRY(__switch_to)
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3)	# store pid of next
 	l	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
-	lhi	%r6,_TIF_TRANSFER		# transfer TIF bits
-	n	%r6,__TI_flags(%r4)		# isolate TIF bits
-	jz	0f
-	o	%r6,__TI_flags(%r5)		# set TIF bits of next
-	st	%r6,__TI_flags(%r5)
-	ni	__TI_flags+3(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
-0:	lm	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
+	lm	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
 __critical_start:
@@ -181,6 +174,7 @@ sysc_stm:
 	stm	%r8,%r15,__LC_SAVE_AREA_SYNC
 	l	%r12,__LC_THREAD_INFO
 	l	%r13,__LC_SVC_NEW_PSW+4
+	lhi	%r14,_PIF_SYSCALL
 sysc_per:
 	l	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
@@ -190,8 +184,8 @@ sysc_vtime:
 	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(8,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
+	st	%r14,__PT_FLAGS(%r11)
 sysc_do_svc:
-	oi	__TI_flags+3(%r12),_TIF_SYSCALL
 	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
 	lh	%r8,__PT_INT_CODE+2(%r11)
 	sla	%r8,2				# shift and test for svc0
@@ -207,7 +201,7 @@ sysc_nr_ok:
 	st	%r2,__PT_ORIG_GPR2(%r11)
 	st	%r7,STACK_FRAME_OVERHEAD(%r15)
 	l	%r9,0(%r8,%r10)			# get system call addr.
-	tm	__TI_flags+2(%r12),_TIF_TRACE >> 8
+	tm	__TI_flags+3(%r12),_TIF_TRACE
 	jnz	sysc_tracesys
 	basr	%r14,%r9			# call sys_xxxx
 	st	%r2,__PT_R2(%r11)		# store return value
@@ -217,9 +211,12 @@ sysc_return:
 sysc_tif:
 	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
 	jno	sysc_restore
-	tm	__TI_flags+3(%r12),_TIF_WORK_SVC
-	jnz	sysc_work			# check for work
-	ni	__TI_flags+3(%r12),255-_TIF_SYSCALL
+	tm	__PT_FLAGS+3(%r11),_PIF_WORK
+	jnz	sysc_work
+	tm	__TI_flags+3(%r12),_TIF_WORK
+	jnz	sysc_work			# check for thread work
+	tm	__LC_CPU_FLAGS+3,_CIF_WORK
+	jnz	sysc_work
 sysc_restore:
 	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r11)
 	stpt	__LC_EXIT_TIMER
@@ -231,17 +228,17 @@ sysc_done:
 # One of the work bits is on. Find out which one.
 #
 sysc_work:
-	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+3,_CIF_MCCK_PENDING
 	jo	sysc_mcck_pending
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
-	tm	__TI_flags+3(%r12),_TIF_PER_TRAP
+	tm	__PT_FLAGS+3(%r11),_PIF_PER_TRAP
 	jo	sysc_singlestep
 	tm	__TI_flags+3(%r12),_TIF_SIGPENDING
 	jo	sysc_sigpending
 	tm	__TI_flags+3(%r12),_TIF_NOTIFY_RESUME
 	jo	sysc_notify_resume
-	tm	__TI_flags+3(%r12),_TIF_ASCE
+	tm	__LC_CPU_FLAGS+3,_CIF_ASCE
 	jo	sysc_uaccess
 	j	sysc_return		# beware of critical section cleanup
 
@@ -254,7 +251,7 @@ sysc_reschedule:
 	br	%r1			# call schedule
 
 #
-# _TIF_MCCK_PENDING is set, call handler
+# _CIF_MCCK_PENDING is set, call handler
 #
 sysc_mcck_pending:
 	l	%r1,BASED(.Lhandle_mcck)
@@ -262,10 +259,10 @@ sysc_mcck_pending:
 	br	%r1			# TIF bit will be cleared by handler
 
 #
-# _TIF_ASCE is set, load user space asce
+# _CIF_ASCE is set, load user space asce
 #
 sysc_uaccess:
-	ni	__TI_flags+3(%r12),255-_TIF_ASCE
+	ni	__LC_CPU_FLAGS+3,255-_CIF_ASCE
 	lctl	%c1,%c1,__LC_USER_ASCE	# load primary asce
 	j	sysc_return
 
@@ -276,7 +273,7 @@ sysc_sigpending:
 	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_signal)
 	basr	%r14,%r1		# call do_signal
-	tm	__TI_flags+3(%r12),_TIF_SYSCALL
+	tm	__PT_FLAGS+3(%r11),_PIF_SYSCALL
 	jno	sysc_return
 	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
 	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
@@ -297,10 +294,10 @@ sysc_notify_resume:
 	br	%r1			# call do_notify_resume
 
 #
-# _TIF_PER_TRAP is set, call do_per_trap
+# _PIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
-	ni	__TI_flags+3(%r12),255-_TIF_PER_TRAP
+	ni	__PT_FLAGS+3(%r11),255-_PIF_PER_TRAP
 	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_per_trap)
 	la	%r14,BASED(sysc_return)
@@ -330,7 +327,7 @@ sysc_tracego:
 	basr	%r14,%r9		# call sys_xxx
 	st	%r2,__PT_R2(%r11)	# store return value
 sysc_tracenogo:
-	tm	__TI_flags+2(%r12),_TIF_TRACE >> 8
+	tm	__TI_flags+3(%r12),_TIF_TRACE
 	jz	sysc_return
 	l	%r1,BASED(.Ltrace_exit)
 	lr	%r2,%r11		# pass pointer to pt_regs
@@ -384,15 +381,16 @@ ENTRY(pgm_check_handler)
 	stm	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(4,%r11),__LC_PGM_ILC
 	mvc	__PT_INT_PARM_LONG(4,%r11),__LC_TRANS_EXC_CODE
+	xc	__PT_FLAGS(4,%r11),__PT_FLAGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
 	jz	0f
 	l	%r1,__TI_task(%r12)
 	tmh	%r8,0x0001		# kernel per event ?
 	jz	pgm_kprobe
-	oi	__TI_flags+3(%r12),_TIF_PER_TRAP
+	oi	__PT_FLAGS+3(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(4,%r1),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r1),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	l	%r1,BASED(.Ljump_table)
@@ -420,9 +418,9 @@ pgm_kprobe:
 # single stepped system call
 #
 pgm_svcper:
-	oi	__TI_flags+3(%r12),_TIF_PER_TRAP
 	mvc	__LC_RETURN_PSW(4),__LC_SVC_NEW_PSW
 	mvc	__LC_RETURN_PSW+4(4),BASED(.Lsysc_per)
+	lhi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
 	lpsw	__LC_RETURN_PSW		# branch to sysc_per and enable irqs
 
 /*
@@ -445,6 +443,7 @@ io_skip:
 	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC
 	stm	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
+	xc	__PT_FLAGS(4,%r11),__PT_FLAGS(%r11)
 	TRACE_IRQS_OFF
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 io_loop:
@@ -466,8 +465,10 @@ io_return:
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON
 io_tif:
-	tm	__TI_flags+3(%r12),_TIF_WORK_INT
+	tm	__TI_flags+3(%r12),_TIF_WORK
 	jnz	io_work			# there is work to do (signals etc.)
+	tm	__LC_CPU_FLAGS+3,_CIF_WORK
+	jnz	io_work
 io_restore:
 	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r11)
 	stpt	__LC_EXIT_TIMER
@@ -477,7 +478,7 @@ io_done:
 
 #
 # There is work todo, find out in which context we have been interrupted:
-# 1) if we return to user space we can do all _TIF_WORK_INT work
+# 1) if we return to user space we can do all _TIF_WORK work
 # 2) if we return to kernel code and preemptive scheduling is enabled check
 #    the preemption counter and if it is zero call preempt_schedule_irq
 # Before any work can be done, a switch to the kernel stack is required.
@@ -520,11 +521,9 @@ io_work_user:
 
 #
 # One of the work bits is on. Find out which one.
-# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED
-#		and _TIF_MCCK_PENDING
 #
 io_work_tif:
-	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+3(%r12),_CIF_MCCK_PENDING
 	jo	io_mcck_pending
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
 	jo	io_reschedule
@@ -532,12 +531,12 @@ io_work_tif:
 	jo	io_sigpending
 	tm	__TI_flags+3(%r12),_TIF_NOTIFY_RESUME
 	jo	io_notify_resume
-	tm	__TI_flags+3(%r12),_TIF_ASCE
+	tm	__LC_CPU_FLAGS+3,_CIF_ASCE
 	jo	io_uaccess
 	j	io_return		# beware of critical section cleanup
 
 #
-# _TIF_MCCK_PENDING is set, call handler
+# _CIF_MCCK_PENDING is set, call handler
 #
 io_mcck_pending:
 	# TRACE_IRQS_ON already done at io_return
@@ -547,10 +546,10 @@ io_mcck_pending:
 	j	io_return
 
 #
-# _TIF_ASCE is set, load user space asce
+# _CIF_ASCE is set, load user space asce
 #
 io_uaccess:
-	ni	__TI_flags+3(%r12),255-_TIF_ASCE
+	ni	__LC_CPU_FLAGS+3,255-_CIF_ASCE
 	lctl	%c1,%c1,__LC_USER_ASCE	# load primary asce
 	j	io_return
 
@@ -613,6 +612,7 @@ ext_skip:
 	stm	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
 	mvc	__PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
+	xc	__PT_FLAGS(4,%r11),__PT_FLAGS(%r11)
 	TRACE_IRQS_OFF
 	l	%r1,BASED(.Ldo_IRQ)
 	lr	%r2,%r11		# pass pointer to pt_regs
@@ -677,6 +677,7 @@ mcck_skip:
 	stm	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32
 	stm	%r8,%r9,__PT_PSW(%r11)
+	xc	__PT_FLAGS(4,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	l	%r1,BASED(.Ldo_machine_check)
 	lr	%r2,%r11		# pass pointer to pt_regs
@@ -689,7 +690,7 @@ mcck_skip:
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	lr	%r15,%r1
 	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
-	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+3,_CIF_MCCK_PENDING
 	jno	mcck_return
 	TRACE_IRQS_OFF
 	l	%r1,BASED(.Lhandle_mcck)
@@ -842,6 +843,8 @@ cleanup_system_call:
 	stm	%r0,%r7,__PT_R0(%r9)
 	mvc	__PT_PSW(8,%r9),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r9),__LC_SVC_ILC
+	xc	__PT_FLAGS(4,%r9),__PT_FLAGS(%r9)
+	mvi	__PT_FLAGS+3(%r9),_PIF_SYSCALL
 	# setup saved register 15
 	st	%r15,28(%r11)		# r15 stack pointer
 	# set new psw address and exit
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 5963e43618bb..f2e674c702e1 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -42,13 +42,11 @@ STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
-_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		 _TIF_MCCK_PENDING | _TIF_PER_TRAP | _TIF_ASCE)
-_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		 _TIF_MCCK_PENDING | _TIF_ASCE)
-_TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
-		 _TIF_SYSCALL_TRACEPOINT)
-_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
+_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+_TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
+		   _TIF_SYSCALL_TRACEPOINT)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
+_PIF_WORK	= (_PIF_PER_TRAP)
 
 #define BASED(name) name-system_call(%r13)
 
@@ -190,13 +188,7 @@ ENTRY(__switch_to)
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
 	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
-	llill	%r6,_TIF_TRANSFER		# transfer TIF bits
-	ng	%r6,__TI_flags(%r4)		# isolate TIF bits
-	jz	0f
-	og	%r6,__TI_flags(%r5)		# set TIF bits of next
-	stg	%r6,__TI_flags(%r5)
-	ni	__TI_flags+7(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
-0:	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
+	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
 __critical_start:
@@ -211,6 +203,7 @@ sysc_stmg:
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_THREAD_INFO
+	lghi	%r14,_PIF_SYSCALL
 sysc_per:
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
@@ -221,8 +214,8 @@ sysc_vtime:
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
+	stg	%r14,__PT_FLAGS(%r11)
 sysc_do_svc:
-	oi	__TI_flags+7(%r12),_TIF_SYSCALL
 	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	llgh	%r8,__PT_INT_CODE+2(%r11)
 	slag	%r8,%r8,2			# shift and test for svc 0
@@ -238,7 +231,7 @@ sysc_nr_ok:
 	stg	%r2,__PT_ORIG_GPR2(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
 	lgf	%r9,0(%r8,%r10)			# get system call add.
-	tm	__TI_flags+6(%r12),_TIF_TRACE >> 8
+	tm	__TI_flags+7(%r12),_TIF_TRACE
 	jnz	sysc_tracesys
 	basr	%r14,%r9			# call sys_xxxx
 	stg	%r2,__PT_R2(%r11)		# store return value
@@ -248,9 +241,12 @@ sysc_return:
 sysc_tif:
 	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
 	jno	sysc_restore
-	tm	__TI_flags+7(%r12),_TIF_WORK_SVC
+	tm	__PT_FLAGS+7(%r11),_PIF_WORK
+	jnz	sysc_work
+	tm	__TI_flags+7(%r12),_TIF_WORK
 	jnz	sysc_work			# check for work
-	ni	__TI_flags+7(%r12),255-_TIF_SYSCALL
+	tm	__LC_CPU_FLAGS+7,_CIF_WORK
+	jnz	sysc_work
 sysc_restore:
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
@@ -265,17 +261,17 @@ sysc_done:
 # One of the work bits is on. Find out which one.
 #
 sysc_work:
-	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
 	jo	sysc_mcck_pending
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
-	tm	__TI_flags+7(%r12),_TIF_PER_TRAP
+	tm	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	jo	sysc_singlestep
 	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
 	jo	sysc_sigpending
 	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
 	jo	sysc_notify_resume
-	tm	__TI_flags+7(%r12),_TIF_ASCE
+	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
 	jo	sysc_uaccess
 	j	sysc_return		# beware of critical section cleanup
 
@@ -287,17 +283,17 @@ sysc_reschedule:
 	jg	schedule
 
 #
-# _TIF_MCCK_PENDING is set, call handler
+# _CIF_MCCK_PENDING is set, call handler
 #
 sysc_mcck_pending:
 	larl	%r14,sysc_return
 	jg	s390_handle_mcck	# TIF bit will be cleared by handler
 
 #
-# _TIF_ASCE is set, load user space asce
+# _CIF_ASCE is set, load user space asce
 #
 sysc_uaccess:
-	ni	__TI_flags+7(%r12),255-_TIF_ASCE
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	j	sysc_return
 
@@ -307,7 +303,7 @@ sysc_uaccess:
 sysc_sigpending:
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,do_signal
-	tm	__TI_flags+7(%r12),_TIF_SYSCALL
+	tm	__PT_FLAGS+7(%r11),_PIF_SYSCALL
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
 	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
@@ -327,10 +323,10 @@ sysc_notify_resume:
 	jg	do_notify_resume
 
 #
-# _TIF_PER_TRAP is set, call do_per_trap
+# _PIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
-	ni	__TI_flags+7(%r12),255-_TIF_PER_TRAP
+	ni	__PT_FLAGS+7(%r11),255-_PIF_PER_TRAP
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,sysc_return
 	jg	do_per_trap
@@ -357,7 +353,7 @@ sysc_tracego:
 	basr	%r14,%r9		# call sys_xxx
 	stg	%r2,__PT_R2(%r11)	# store return value
 sysc_tracenogo:
-	tm	__TI_flags+6(%r12),_TIF_TRACE >> 8
+	tm	__TI_flags+7(%r12),_TIF_TRACE
 	jz	sysc_return
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,sysc_return
@@ -416,15 +412,16 @@ ENTRY(pgm_check_handler)
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(4,%r11),__LC_PGM_ILC
 	mvc	__PT_INT_PARM_LONG(8,%r11),__LC_TRANS_EXC_CODE
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	stg	%r10,__PT_ARGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
 	jz	0f
 	tmhh	%r8,0x0001		# kernel per event ?
 	jz	pgm_kprobe
-	oi	__TI_flags+7(%r12),_TIF_PER_TRAP
+	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r14),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
@@ -451,10 +448,10 @@ pgm_kprobe:
 # single stepped system call
 #
 pgm_svcper:
-	oi	__TI_flags+7(%r12),_TIF_PER_TRAP
 	mvc	__LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
 	larl	%r14,sysc_per
 	stg	%r14,__LC_RETURN_PSW+8
+	lghi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
 	lpswe	__LC_RETURN_PSW		# branch to sysc_per and enable irqs
 
 /*
@@ -479,6 +476,7 @@ io_skip:
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	TRACE_IRQS_OFF
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 io_loop:
@@ -499,8 +497,10 @@ io_return:
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON
 io_tif:
-	tm	__TI_flags+7(%r12),_TIF_WORK_INT
+	tm	__TI_flags+7(%r12),_TIF_WORK
 	jnz	io_work 		# there is work to do (signals etc.)
+	tm	__LC_CPU_FLAGS+7,_CIF_WORK
+	jnz	io_work
 io_restore:
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
@@ -513,7 +513,7 @@ io_done:
 
 #
 # There is work todo, find out in which context we have been interrupted:
-# 1) if we return to user space we can do all _TIF_WORK_INT work
+# 1) if we return to user space we can do all _TIF_WORK work
 # 2) if we return to kernel code and kvm is enabled check if we need to
 #    modify the psw to leave SIE
 # 3) if we return to kernel code and preemptive scheduling is enabled check
@@ -557,11 +557,9 @@ io_work_user:
 
 #
 # One of the work bits is on. Find out which one.
-# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED
-#	       and _TIF_MCCK_PENDING
 #
 io_work_tif:
-	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
 	jo	io_mcck_pending
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	io_reschedule
@@ -569,12 +567,12 @@ io_work_tif:
 	jo	io_sigpending
 	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
 	jo	io_notify_resume
-	tm	__TI_flags+7(%r12),_TIF_ASCE
+	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
 	jo	io_uaccess
 	j	io_return		# beware of critical section cleanup
 
 #
-# _TIF_MCCK_PENDING is set, call handler
+# _CIF_MCCK_PENDING is set, call handler
 #
 io_mcck_pending:
 	# TRACE_IRQS_ON already done at io_return
@@ -583,10 +581,10 @@ io_mcck_pending:
 	j	io_return
 
 #
-# _TIF_ASCE is set, load user space asce
+# _CIF_ASCE is set, load user space asce
 #
 io_uaccess:
-	ni	__TI_flags+7(%r12),255-_TIF_ASCE
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	j	io_return
 
@@ -650,6 +648,7 @@ ext_skip:
 	mvc	__PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
 	mvc	__PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
 	mvc	__PT_INT_PARM_LONG(8,%r11),0(%r1)
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	TRACE_IRQS_OFF
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
@@ -716,6 +715,7 @@ mcck_skip:
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),0(%r14)
 	stmg	%r8,%r9,__PT_PSW(%r11)
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,s390_do_machine_check
@@ -727,7 +727,7 @@ mcck_skip:
 	la	%r11,STACK_FRAME_OVERHEAD(%r1)
 	lgr	%r15,%r1
 	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
-	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
 	jno	mcck_return
 	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck
@@ -884,6 +884,8 @@ cleanup_system_call:
 	stmg	%r0,%r7,__PT_R0(%r9)
 	mvc	__PT_PSW(16,%r9),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r9),__LC_SVC_ILC
+	xc	__PT_FLAGS(8,%r9),__PT_FLAGS(%r9)
+	mvi	__PT_FLAGS+7(%r9),_PIF_SYSCALL
 	# setup saved register r15
 	stg	%r15,56(%r11)		# r15 stack pointer
 	# set new psw address and exit
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 429afcc480cb..7ba7d6784510 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -437,13 +437,13 @@ ENTRY(startup_kdump)
 
 #if defined(CONFIG_64BIT)
 #if defined(CONFIG_MARCH_ZEC12)
-	.long 3, 0xc100efe3, 0xf46ce800, 0x00400000
+	.long 3, 0xc100efea, 0xf46ce800, 0x00400000
 #elif defined(CONFIG_MARCH_Z196)
-	.long 2, 0xc100efe3, 0xf46c0000
+	.long 2, 0xc100efea, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
-	.long 2, 0xc100efe3, 0xf0680000
+	.long 2, 0xc100efea, 0xf0680000
 #elif defined(CONFIG_MARCH_Z9_109)
-	.long 1, 0xc100efc3
+	.long 1, 0xc100efc2
 #elif defined(CONFIG_MARCH_Z990)
 	.long 1, 0xc0002000
 #elif defined(CONFIG_MARCH_Z900)
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index 9a99856df1c9..6dbe80983a24 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -59,7 +59,6 @@ ENTRY(startup_continue)
 	.long	0			# cr13: home space segment table
 	.long	0xc0000000		# cr14: machine check handling off
 	.long	0			# cr15: linkage stack operations
-.Lmchunk:.long	memory_chunk
 .Lbss_bgn:  .long __bss_start
 .Lbss_end:  .long _end
 .Lparmaddr: .long PARMAREA
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index c7463aa0014b..99b0b09646ca 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -92,7 +92,6 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 
 void __init init_IRQ(void)
 {
-	irq_reserve_irqs(0, THIN_INTERRUPT);
 	init_cio_interrupts();
 	init_airq_interrupts();
 	init_ext_interrupts();
@@ -151,9 +150,9 @@ out:
 	return 0;
 }
 
-int arch_show_interrupts(struct seq_file *p, int prec)
+unsigned int arch_dynirq_lower_bound(unsigned int from)
 {
-	return 0;
+	return from < THIN_INTERRUPT ? THIN_INTERRUPT : from;
 }
 
 /*
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index c4c033819879..210e1285f75a 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -55,7 +55,7 @@ void s390_handle_mcck(void)
 	local_mcck_disable();
 	mcck = __get_cpu_var(cpu_mcck);
 	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
-	clear_thread_flag(TIF_MCCK_PENDING);
+	clear_cpu_flag(CIF_MCCK_PENDING);
 	local_mcck_enable();
 	local_irq_restore(flags);
 
@@ -313,7 +313,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 			 */
 			mcck->kill_task = 1;
 			mcck->mcck_code = *(unsigned long long *) mci;
-			set_thread_flag(TIF_MCCK_PENDING);
+			set_cpu_flag(CIF_MCCK_PENDING);
 		} else {
 			/*
 			 * Couldn't restore all register contents while in
@@ -352,12 +352,12 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	if (mci->cp) {
 		/* Channel report word pending */
 		mcck->channel_report = 1;
-		set_thread_flag(TIF_MCCK_PENDING);
+		set_cpu_flag(CIF_MCCK_PENDING);
 	}
 	if (mci->w) {
 		/* Warning pending */
 		mcck->warning = 1;
-		set_thread_flag(TIF_MCCK_PENDING);
+		set_cpu_flag(CIF_MCCK_PENDING);
 	}
 	nmi_exit();
 }
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index dd145321d215..93b9ca42e5c0 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -64,7 +64,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 void arch_cpu_idle(void)
 {
 	local_mcck_disable();
-	if (test_thread_flag(TIF_MCCK_PENDING)) {
+	if (test_cpu_flag(CIF_MCCK_PENDING)) {
 		local_mcck_enable();
 		local_irq_enable();
 		return;
@@ -76,7 +76,7 @@ void arch_cpu_idle(void)
 
 void arch_cpu_idle_exit(void)
 {
-	if (test_thread_flag(TIF_MCCK_PENDING))
+	if (test_cpu_flag(CIF_MCCK_PENDING))
 		s390_handle_mcck();
 }
 
@@ -123,7 +123,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	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;
@@ -152,6 +151,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	}
 	frame->childregs = *current_pt_regs();
 	frame->childregs.gprs[2] = 0;	/* child returns 0 on fork. */
+	frame->childregs.flags = 0;
 	if (new_stackp)
 		frame->childregs.gprs[15] = new_stackp;
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 1c82619eb4f7..2d716734b5b1 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -136,7 +136,7 @@ void ptrace_disable(struct task_struct *task)
 	memset(&task->thread.per_user, 0, sizeof(task->thread.per_user));
 	memset(&task->thread.per_event, 0, sizeof(task->thread.per_event));
 	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
-	clear_tsk_thread_flag(task, TIF_PER_TRAP);
+	clear_pt_regs_flag(task_pt_regs(task), PIF_PER_TRAP);
 	task->thread.per_flags = 0;
 }
 
@@ -813,7 +813,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 * debugger stored an invalid system call number. Skip
 		 * the system call and the system call restart handling.
 		 */
-		clear_thread_flag(TIF_SYSCALL);
+		clear_pt_regs_flag(regs, PIF_SYSCALL);
 		ret = -1;
 	}
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 88d1ca81e2dd..1e2264b46e4c 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -78,10 +78,9 @@ EXPORT_SYMBOL(console_irq);
 unsigned long elf_hwcap = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
-struct mem_chunk __initdata memory_chunk[MEMORY_CHUNKS];
-
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
+unsigned long __initdata max_physmem_end;
 
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
@@ -212,7 +211,7 @@ static void __init conmode_default(void)
 	}
 }
 
-#ifdef CONFIG_ZFCPDUMP
+#ifdef CONFIG_CRASH_DUMP
 static void __init setup_zfcpdump(void)
 {
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
@@ -224,7 +223,7 @@ static void __init setup_zfcpdump(void)
 }
 #else
 static inline void setup_zfcpdump(void) {}
-#endif /* CONFIG_ZFCPDUMP */
+#endif /* CONFIG_CRASH_DUMP */
 
  /*
  * Reboot, halt and power_off stubs. They just call _machine_restart,
@@ -273,6 +272,7 @@ EXPORT_SYMBOL_GPL(pm_power_off);
 static int __init early_parse_mem(char *p)
 {
 	memory_end = memparse(p, &p);
+	memory_end &= PAGE_MASK;
 	memory_end_set = 1;
 	return 0;
 }
@@ -373,6 +373,10 @@ static void __init setup_lowcore(void)
 	mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source);
 	mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw);
 
+#ifdef CONFIG_SMP
+	lc->spinlock_lockval = arch_spin_lockval(0);
+#endif
+
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;
 }
@@ -401,7 +405,8 @@ static struct resource __initdata *standard_resources[] = {
 static void __init setup_resources(void)
 {
 	struct resource *res, *std_res, *sub_res;
-	int i, j;
+	struct memblock_region *reg;
+	int j;
 
 	code_resource.start = (unsigned long) &_text;
 	code_resource.end = (unsigned long) &_etext - 1;
@@ -410,24 +415,13 @@ static void __init setup_resources(void)
 	bss_resource.start = (unsigned long) &__bss_start;
 	bss_resource.end = (unsigned long) &__bss_stop - 1;
 
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		if (!memory_chunk[i].size)
-			continue;
+	for_each_memblock(memory, reg) {
 		res = alloc_bootmem_low(sizeof(*res));
 		res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
-		switch (memory_chunk[i].type) {
-		case CHUNK_READ_WRITE:
-			res->name = "System RAM";
-			break;
-		case CHUNK_READ_ONLY:
-			res->name = "System ROM";
-			res->flags |= IORESOURCE_READONLY;
-			break;
-		default:
-			res->name = "reserved";
-		}
-		res->start = memory_chunk[i].addr;
-		res->end = res->start + memory_chunk[i].size - 1;
+
+		res->name = "System RAM";
+		res->start = reg->base;
+		res->end = reg->base + reg->size - 1;
 		request_resource(&iomem_resource, res);
 
 		for (j = 0; j < ARRAY_SIZE(standard_resources); j++) {
@@ -451,48 +445,11 @@ static void __init setup_resources(void)
 static void __init setup_memory_end(void)
 {
 	unsigned long vmax, vmalloc_size, tmp;
-	unsigned long real_memory_size = 0;
-	int i;
-
-
-#ifdef CONFIG_ZFCPDUMP
-	if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
-	    !OLDMEM_BASE && sclp_get_hsa_size()) {
-		memory_end = sclp_get_hsa_size();
-		memory_end_set = 1;
-	}
-#endif
-	memory_end &= PAGE_MASK;
-
-	/*
-	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
-	 * extra checks that HOLES_IN_ZONE would require.
-	 */
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		unsigned long start, end;
-		struct mem_chunk *chunk;
-		unsigned long align;
-
-		chunk = &memory_chunk[i];
-		if (!chunk->size)
-			continue;
-		align = 1UL << (MAX_ORDER + PAGE_SHIFT - 1);
-		start = (chunk->addr + align - 1) & ~(align - 1);
-		end = (chunk->addr + chunk->size) & ~(align - 1);
-		if (start >= end)
-			memset(chunk, 0, sizeof(*chunk));
-		else {
-			chunk->addr = start;
-			chunk->size = end - start;
-		}
-		real_memory_size = max(real_memory_size,
-				       chunk->addr + chunk->size);
-	}
 
 	/* Choose kernel address space layout: 2, 3, or 4 levels. */
 #ifdef CONFIG_64BIT
 	vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
-	tmp = (memory_end ?: real_memory_size) / PAGE_SIZE;
+	tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
 	tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size;
 	if (tmp <= (1UL << 42))
 		vmax = 1UL << 42;	/* 3-level kernel page table */
@@ -520,21 +477,11 @@ static void __init setup_memory_end(void)
 	vmemmap = (struct page *) tmp;
 
 	/* Take care that memory_end is set and <= vmemmap */
-	memory_end = min(memory_end ?: real_memory_size, tmp);
-
-	/* Fixup memory chunk array to fit into 0..memory_end */
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		struct mem_chunk *chunk = &memory_chunk[i];
+	memory_end = min(memory_end ?: max_physmem_end, tmp);
+	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
+	memblock_remove(memory_end, ULONG_MAX);
 
-		if (!chunk->size)
-			continue;
-		if (chunk->addr >= memory_end) {
-			memset(chunk, 0, sizeof(*chunk));
-			continue;
-		}
-		if (chunk->addr + chunk->size > memory_end)
-			chunk->size = memory_end - chunk->addr;
-	}
+	pr_notice("Max memory size: %luMB\n", memory_end >> 20);
 }
 
 static void __init setup_vmcoreinfo(void)
@@ -545,89 +492,6 @@ static void __init setup_vmcoreinfo(void)
 #ifdef CONFIG_CRASH_DUMP
 
 /*
- * Find suitable location for crashkernel memory
- */
-static unsigned long __init find_crash_base(unsigned long crash_size,
-					    char **msg)
-{
-	unsigned long crash_base;
-	struct mem_chunk *chunk;
-	int i;
-
-	if (memory_chunk[0].size < crash_size) {
-		*msg = "first memory chunk must be at least crashkernel size";
-		return 0;
-	}
-	if (OLDMEM_BASE && crash_size == OLDMEM_SIZE)
-		return OLDMEM_BASE;
-
-	for (i = MEMORY_CHUNKS - 1; i >= 0; i--) {
-		chunk = &memory_chunk[i];
-		if (chunk->size == 0)
-			continue;
-		if (chunk->type != CHUNK_READ_WRITE)
-			continue;
-		if (chunk->size < crash_size)
-			continue;
-		crash_base = (chunk->addr + chunk->size) - crash_size;
-		if (crash_base < crash_size)
-			continue;
-		if (crash_base < sclp_get_hsa_size())
-			continue;
-		if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE)
-			continue;
-		return crash_base;
-	}
-	*msg = "no suitable area found";
-	return 0;
-}
-
-/*
- * Check if crash_base and crash_size is valid
- */
-static int __init verify_crash_base(unsigned long crash_base,
-				    unsigned long crash_size,
-				    char **msg)
-{
-	struct mem_chunk *chunk;
-	int i;
-
-	/*
-	 * Because we do the swap to zero, we must have at least 'crash_size'
-	 * bytes free space before crash_base
-	 */
-	if (crash_size > crash_base) {
-		*msg = "crashkernel offset must be greater than size";
-		return -EINVAL;
-	}
-
-	/* First memory chunk must be at least crash_size */
-	if (memory_chunk[0].size < crash_size) {
-		*msg = "first memory chunk must be at least crashkernel size";
-		return -EINVAL;
-	}
-	/* Check if we fit into the respective memory chunk */
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		chunk = &memory_chunk[i];
-		if (chunk->size == 0)
-			continue;
-		if (crash_base < chunk->addr)
-			continue;
-		if (crash_base >= chunk->addr + chunk->size)
-			continue;
-		/* we have found the memory chunk */
-		if (crash_base + crash_size > chunk->addr + chunk->size) {
-			*msg = "selected memory chunk is too small for "
-				"crashkernel memory";
-			return -EINVAL;
-		}
-		return 0;
-	}
-	*msg = "invalid memory range specified";
-	return -EINVAL;
-}
-
-/*
  * When kdump is enabled, we have to ensure that no memory from
  * the area [0 - crashkernel memory size] and
  * [crashk_res.start - crashk_res.end] is set offline.
@@ -653,23 +517,44 @@ static struct notifier_block kdump_mem_nb = {
 #endif
 
 /*
+ * Make sure that the area behind memory_end is protected
+ */
+static void reserve_memory_end(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
+	    !OLDMEM_BASE && sclp_get_hsa_size()) {
+		memory_end = sclp_get_hsa_size();
+		memory_end &= PAGE_MASK;
+		memory_end_set = 1;
+	}
+#endif
+	if (!memory_end_set)
+		return;
+	memblock_reserve(memory_end, ULONG_MAX);
+}
+
+/*
  * Make sure that oldmem, where the dump is stored, is protected
  */
 static void reserve_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	unsigned long real_size = 0;
-	int i;
-
-	if (!OLDMEM_BASE)
-		return;
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		struct mem_chunk *chunk = &memory_chunk[i];
+	if (OLDMEM_BASE)
+		/* Forget all memory above the running kdump system */
+		memblock_reserve(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX);
+#endif
+}
 
-		real_size = max(real_size, chunk->addr + chunk->size);
-	}
-	create_mem_hole(memory_chunk, OLDMEM_BASE, OLDMEM_SIZE);
-	create_mem_hole(memory_chunk, OLDMEM_SIZE, real_size - OLDMEM_SIZE);
+/*
+ * Make sure that oldmem, where the dump is stored, is protected
+ */
+static void remove_oldmem(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (OLDMEM_BASE)
+		/* Forget all memory above the running kdump system */
+		memblock_remove(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX);
 #endif
 }
 
@@ -680,167 +565,132 @@ static void __init reserve_crashkernel(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	unsigned long long crash_base, crash_size;
-	char *msg = NULL;
+	phys_addr_t low, high;
 	int rc;
 
 	rc = parse_crashkernel(boot_command_line, memory_end, &crash_size,
 			       &crash_base);
-	if (rc || crash_size == 0)
-		return;
+
 	crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN);
 	crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN);
-	if (register_memory_notifier(&kdump_mem_nb))
+	if (rc || crash_size == 0)
 		return;
-	if (!crash_base)
-		crash_base = find_crash_base(crash_size, &msg);
-	if (!crash_base) {
-		pr_info("crashkernel reservation failed: %s\n", msg);
-		unregister_memory_notifier(&kdump_mem_nb);
+
+	if (memblock.memory.regions[0].size < crash_size) {
+		pr_info("crashkernel reservation failed: %s\n",
+			"first memory chunk must be at least crashkernel size");
 		return;
 	}
-	if (verify_crash_base(crash_base, crash_size, &msg)) {
-		pr_info("crashkernel reservation failed: %s\n", msg);
-		unregister_memory_notifier(&kdump_mem_nb);
+
+	low = crash_base ?: OLDMEM_BASE;
+	high = low + crash_size;
+	if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) {
+		/* The crashkernel fits into OLDMEM, reuse OLDMEM */
+		crash_base = low;
+	} else {
+		/* Find suitable area in free memory */
+		low = max_t(unsigned long, crash_size, sclp_get_hsa_size());
+		high = crash_base ? crash_base + crash_size : ULONG_MAX;
+
+		if (crash_base && crash_base < low) {
+			pr_info("crashkernel reservation failed: %s\n",
+				"crash_base too low");
+			return;
+		}
+		low = crash_base ?: low;
+		crash_base = memblock_find_in_range(low, high, crash_size,
+						    KEXEC_CRASH_MEM_ALIGN);
+	}
+
+	if (!crash_base) {
+		pr_info("crashkernel reservation failed: %s\n",
+			"no suitable area found");
 		return;
 	}
+
+	if (register_memory_notifier(&kdump_mem_nb))
+		return;
+
 	if (!OLDMEM_BASE && MACHINE_IS_VM)
 		diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 	insert_resource(&iomem_resource, &crashk_res);
-	create_mem_hole(memory_chunk, crash_base, crash_size);
+	memblock_remove(crash_base, crash_size);
 	pr_info("Reserving %lluMB of memory at %lluMB "
 		"for crashkernel (System RAM: %luMB)\n",
-		crash_size >> 20, crash_base >> 20, memory_end >> 20);
+		crash_size >> 20, crash_base >> 20,
+		(unsigned long)memblock.memory.total_size >> 20);
 	os_info_crashkernel_add(crash_base, crash_size);
 #endif
 }
 
-static void __init setup_memory(void)
+/*
+ * Reserve the initrd from being used by memblock
+ */
+static void __init reserve_initrd(void)
 {
-        unsigned long bootmap_size;
-	unsigned long start_pfn, end_pfn;
-	int i;
+#ifdef CONFIG_BLK_DEV_INITRD
+	initrd_start = INITRD_START;
+	initrd_end = initrd_start + INITRD_SIZE;
+	memblock_reserve(INITRD_START, INITRD_SIZE);
+#endif
+}
 
-	/*
-	 * partially used pages are not usable - thus
-	 * we are rounding upwards:
-	 */
+/*
+ * Check for initrd being in usable memory
+ */
+static void __init check_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (INITRD_START && INITRD_SIZE &&
+	    !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) {
+		pr_err("initrd does not fit memory.\n");
+		memblock_free(INITRD_START, INITRD_SIZE);
+		initrd_start = initrd_end = 0;
+	}
+#endif
+}
+
+/*
+ * Reserve all kernel text
+ */
+static void __init reserve_kernel(void)
+{
+	unsigned long start_pfn;
 	start_pfn = PFN_UP(__pa(&_end));
-	end_pfn = max_pfn = PFN_DOWN(memory_end);
 
-#ifdef CONFIG_BLK_DEV_INITRD
 	/*
-	 * Move the initrd in case the bitmap of the bootmem allocater
-	 * would overwrite it.
+	 * Reserve memory used for lowcore/command line/kernel image.
 	 */
+	memblock_reserve(0, (unsigned long)_ehead);
+	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
+			 - (unsigned long)_stext);
+}
 
-	if (INITRD_START && INITRD_SIZE) {
-		unsigned long bmap_size;
-		unsigned long start;
-
-		bmap_size = bootmem_bootmap_pages(end_pfn - start_pfn + 1);
-		bmap_size = PFN_PHYS(bmap_size);
-
-		if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) {
-			start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE;
-
+static void __init reserve_elfcorehdr(void)
+{
 #ifdef CONFIG_CRASH_DUMP
-			if (OLDMEM_BASE) {
-				/* Move initrd behind kdump oldmem */
-				if (start + INITRD_SIZE > OLDMEM_BASE &&
-				    start < OLDMEM_BASE + OLDMEM_SIZE)
-					start = OLDMEM_BASE + OLDMEM_SIZE;
-			}
-#endif
-			if (start + INITRD_SIZE > memory_end) {
-				pr_err("initrd extends beyond end of "
-				       "memory (0x%08lx > 0x%08lx) "
-				       "disabling initrd\n",
-				       start + INITRD_SIZE, memory_end);
-				INITRD_START = INITRD_SIZE = 0;
-			} else {
-				pr_info("Moving initrd (0x%08lx -> "
-					"0x%08lx, size: %ld)\n",
-					INITRD_START, start, INITRD_SIZE);
-				memmove((void *) start, (void *) INITRD_START,
-					INITRD_SIZE);
-				INITRD_START = start;
-			}
-		}
-	}
+	if (is_kdump_kernel())
+		memblock_reserve(elfcorehdr_addr - OLDMEM_BASE,
+				 PAGE_ALIGN(elfcorehdr_size));
 #endif
+}
 
-	/*
-	 * Initialize the boot-time allocator
-	 */
-	bootmap_size = init_bootmem(start_pfn, end_pfn);
+static void __init setup_memory(void)
+{
+	struct memblock_region *reg;
 
 	/*
-	 * Register RAM areas with the bootmem allocator.
+	 * Init storage key for present memory
 	 */
-
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		unsigned long start_chunk, end_chunk, pfn;
-
-		if (!memory_chunk[i].size)
-			continue;
-		start_chunk = PFN_DOWN(memory_chunk[i].addr);
-		end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size);
-		end_chunk = min(end_chunk, end_pfn);
-		if (start_chunk >= end_chunk)
-			continue;
-		memblock_add_node(PFN_PHYS(start_chunk),
-				  PFN_PHYS(end_chunk - start_chunk), 0);
-		pfn = max(start_chunk, start_pfn);
-		storage_key_init_range(PFN_PHYS(pfn), PFN_PHYS(end_chunk));
+	for_each_memblock(memory, reg) {
+		storage_key_init_range(reg->base, reg->base + reg->size);
 	}
-
 	psw_set_key(PAGE_DEFAULT_KEY);
 
-	free_bootmem_with_active_regions(0, max_pfn);
-
-	/*
-	 * Reserve memory used for lowcore/command line/kernel image.
-	 */
-	reserve_bootmem(0, (unsigned long)_ehead, BOOTMEM_DEFAULT);
-	reserve_bootmem((unsigned long)_stext,
-			PFN_PHYS(start_pfn) - (unsigned long)_stext,
-			BOOTMEM_DEFAULT);
-	/*
-	 * Reserve the bootmem bitmap itself as well. We do this in two
-	 * steps (first step was init_bootmem()) because this catches
-	 * the (very unlikely) case of us accidentally initializing the
-	 * bootmem allocator with an invalid RAM area.
-	 */
-	reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size,
-			BOOTMEM_DEFAULT);
-
-#ifdef CONFIG_CRASH_DUMP
-	if (crashk_res.start)
-		reserve_bootmem(crashk_res.start,
-				crashk_res.end - crashk_res.start + 1,
-				BOOTMEM_DEFAULT);
-	if (is_kdump_kernel())
-		reserve_bootmem(elfcorehdr_addr - OLDMEM_BASE,
-				PAGE_ALIGN(elfcorehdr_size), BOOTMEM_DEFAULT);
-#endif
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (INITRD_START && INITRD_SIZE) {
-		if (INITRD_START + INITRD_SIZE <= memory_end) {
-			reserve_bootmem(INITRD_START, INITRD_SIZE,
-					BOOTMEM_DEFAULT);
-			initrd_start = INITRD_START;
-			initrd_end = initrd_start + INITRD_SIZE;
-		} else {
-			pr_err("initrd extends beyond end of "
-			       "memory (0x%08lx > 0x%08lx) "
-			       "disabling initrd\n",
-			       initrd_start + INITRD_SIZE, memory_end);
-			initrd_start = initrd_end = 0;
-		}
-	}
-#endif
+	/* Only cosmetics */
+	memblock_enforce_memory_limit(memblock_end_of_DRAM());
 }
 
 /*
@@ -989,23 +839,46 @@ void __init setup_arch(char **cmdline_p)
 
         ROOT_DEV = Root_RAM0;
 
+	/* Is init_mm really needed? */
 	init_mm.start_code = PAGE_OFFSET;
 	init_mm.end_code = (unsigned long) &_etext;
 	init_mm.end_data = (unsigned long) &_edata;
 	init_mm.brk = (unsigned long) &_end;
 
 	parse_early_param();
-	detect_memory_layout(memory_chunk, memory_end);
 	os_info_init();
 	setup_ipl();
+
+	/* Do some memory reservations *before* memory is added to memblock */
+	reserve_memory_end();
 	reserve_oldmem();
+	reserve_kernel();
+	reserve_initrd();
+	reserve_elfcorehdr();
+	memblock_allow_resize();
+
+	/* Get information about *all* installed memory */
+	detect_memory_memblock();
+
+	remove_oldmem();
+
+	/*
+	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
+	 * extra checks that HOLES_IN_ZONE would require.
+	 *
+	 * Is this still required?
+	 */
+	memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT));
+
 	setup_memory_end();
-	reserve_crashkernel();
 	setup_memory();
+
+	check_initrd();
+	reserve_crashkernel();
+
 	setup_resources();
 	setup_vmcoreinfo();
 	setup_lowcore();
-
 	smp_fill_possible_mask();
         cpu_init();
 	s390_init_cpu_topology();
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index d8fd508ccd1e..42b49f9e19bf 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -113,7 +113,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	       sizeof(current->thread.fp_regs));
 
 	restore_fp_regs(current->thread.fp_regs.fprs);
-	clear_thread_flag(TIF_SYSCALL);	/* No longer in a system call */
+	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
@@ -356,7 +356,7 @@ void do_signal(struct pt_regs *regs)
 	 * call information.
 	 */
 	current_thread_info()->system_call =
-		test_thread_flag(TIF_SYSCALL) ? regs->int_code : 0;
+		test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0;
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
 	if (signr > 0) {
@@ -384,7 +384,7 @@ void do_signal(struct pt_regs *regs)
 			}
 		}
 		/* No longer in a system call */
-		clear_thread_flag(TIF_SYSCALL);
+		clear_pt_regs_flag(regs, PIF_SYSCALL);
 
 		if (is_compat_task())
 			handle_signal32(signr, &ka, &info, oldset, regs);
@@ -394,7 +394,7 @@ void do_signal(struct pt_regs *regs)
 	}
 
 	/* No handlers present - check for system call restart */
-	clear_thread_flag(TIF_SYSCALL);
+	clear_pt_regs_flag(regs, PIF_SYSCALL);
 	if (current_thread_info()->system_call) {
 		regs->int_code = current_thread_info()->system_call;
 		switch (regs->gprs[2]) {
@@ -407,9 +407,9 @@ void do_signal(struct pt_regs *regs)
 		case -ERESTARTNOINTR:
 			/* Restart system call with magic TIF bit. */
 			regs->gprs[2] = regs->orig_gpr2;
-			set_thread_flag(TIF_SYSCALL);
+			set_pt_regs_flag(regs, PIF_SYSCALL);
 			if (test_thread_flag(TIF_SINGLE_STEP))
-				set_thread_flag(TIF_PER_TRAP);
+				clear_pt_regs_flag(regs, PIF_PER_TRAP);
 			break;
 		}
 	}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 86e65ec3422b..243c7e512600 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -170,6 +170,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	lc->panic_stack = pcpu->panic_stack + PAGE_SIZE
 		- STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->cpu_nr = cpu;
+	lc->spinlock_lockval = arch_spin_lockval(cpu);
 #ifndef CONFIG_64BIT
 	if (MACHINE_HAS_IEEE) {
 		lc->extended_save_area_addr = get_zeroed_page(GFP_KERNEL);
@@ -226,6 +227,7 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
 	atomic_inc(&init_mm.context.attach_count);
 	lc->cpu_nr = cpu;
+	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = S390_lowcore.kernel_asce;
 	lc->machine_flags = S390_lowcore.machine_flags;
@@ -403,15 +405,6 @@ void smp_send_stop(void)
 }
 
 /*
- * Stop the current cpu.
- */
-void smp_stop_cpu(void)
-{
-	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
-	for (;;) ;
-}
-
-/*
  * This is the main routine where commands issued by other
  * cpus are handled.
  */
@@ -519,7 +512,7 @@ void smp_ctl_clear_bit(int cr, int bit)
 }
 EXPORT_SYMBOL(smp_ctl_clear_bit);
 
-#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP)
+#ifdef CONFIG_CRASH_DUMP
 
 static void __init smp_get_save_area(int cpu, u16 address)
 {
@@ -534,14 +527,12 @@ static void __init smp_get_save_area(int cpu, u16 address)
 	save_area = dump_save_area_create(cpu);
 	if (!save_area)
 		panic("could not allocate memory for save area\n");
-#ifdef CONFIG_CRASH_DUMP
 	if (address == boot_cpu_address) {
 		/* Copy the registers of the boot cpu. */
 		copy_oldmem_page(1, (void *) save_area, sizeof(*save_area),
 				 SAVE_AREA_BASE - PAGE_SIZE, 0);
 		return;
 	}
-#endif
 	/* Get the registers of a non-boot cpu. */
 	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
 	memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area));
@@ -558,11 +549,11 @@ int smp_store_status(int cpu)
 	return 0;
 }
 
-#else /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */
+#else /* CONFIG_CRASH_DUMP */
 
 static inline void smp_get_save_area(int cpu, u16 address) { }
 
-#endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */
+#endif /* CONFIG_CRASH_DUMP */
 
 void smp_cpu_set_polarization(int cpu, int val)
 {
@@ -809,6 +800,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 void __init smp_setup_processor_id(void)
 {
 	S390_lowcore.cpu_nr = 0;
+	S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
 }
 
 /*
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 386d37a228bb..0931b110c826 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -226,7 +226,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtom_clock_sec =
 		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = tk->xtime_nsec +
-		+ (tk->wall_to_monotonic.tv_nsec << tk->shift);
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift);
 	nsecps = (u64) NSEC_PER_SEC << tk->shift;
 	while (vdso_data->wtom_clock_nsec >= nsecps) {
 		vdso_data->wtom_clock_nsec -= nsecps;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 6298fed11ced..355a16c55702 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -333,7 +333,9 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
 		nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
 	nr_masks = max(nr_masks, 1);
 	for (i = 0; i < nr_masks; i++) {
-		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask->next = alloc_bootmem_align(
+			roundup_pow_of_two(sizeof(struct mask_info)),
+			roundup_pow_of_two(sizeof(struct mask_info)));
 		mask = mask->next;
 	}
 }
@@ -443,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu)
 	return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
 }
 
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_mask;
+}
+
+static const struct cpumask *cpu_book_mask(int cpu)
+{
+	return &cpu_topology[cpu].book_mask;
+}
+
+static struct sched_domain_topology_level s390_topology[] = {
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 static int __init topology_init(void)
 {
 	if (!MACHINE_HAS_TOPOLOGY) {
@@ -451,6 +470,9 @@ static int __init topology_init(void)
 	}
 	set_topology_timer();
 out:
+
+	set_sched_topology(s390_topology);
+
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);