19 files changed, 242 insertions, 149 deletions

diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index a9c2c06..b80e456 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -229,5 +229,5 @@ int ccw_device_siosl(struct ccw_device *);
 
 extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
 
-extern void *ccw_device_get_chp_desc(struct ccw_device *, int);
+struct channel_path_desc *ccw_device_get_chp_desc(struct ccw_device *, int);
 #endif /* _S390_CCWDEV_H_ */
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 6e670f8..057ce0c 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -10,6 +10,8 @@ struct ccw_driver;
  * @count: number of attached slave devices
  * @dev: embedded device structure
  * @cdev: variable number of slave devices, allocated as needed
+ * @ungroup_work: work to be done when a ccwgroup notifier has action
+ *	type %BUS_NOTIFY_UNBIND_DRIVER
  */
 struct ccwgroup_device {
 	enum {
@@ -22,8 +24,8 @@ struct ccwgroup_device {
 /* public: */
 	unsigned int count;
 	struct device	dev;
-	struct ccw_device *cdev[0];
 	struct work_struct ungroup_work;
+	struct ccw_device *cdev[0];
 };
 
 /**
diff --git a/arch/s390/include/asm/chpid.h b/arch/s390/include/asm/chpid.h
index 38c405e..7298eec 100644
--- a/arch/s390/include/asm/chpid.h
+++ b/arch/s390/include/asm/chpid.h
@@ -8,6 +8,17 @@
 #include <uapi/asm/chpid.h>
 #include <asm/cio.h>
 
+struct channel_path_desc {
+	u8 flags;
+	u8 lsn;
+	u8 desc;
+	u8 chpid;
+	u8 swla;
+	u8 zeroes;
+	u8 chla;
+	u8 chpp;
+} __packed;
+
 static inline void chp_id_init(struct chp_id *chpid)
 {
 	memset(chpid, 0, sizeof(struct chp_id));
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 69cf5b5..a4811aa 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -29,7 +29,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, newval, ret;
 
-	update_primary_asce(current);
+	load_kernel_asce();
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
@@ -79,7 +79,7 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	int ret;
 
-	update_primary_asce(current);
+	load_kernel_asce();
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141..2070cad 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -93,7 +93,9 @@ struct _lowcore {
 	__u32	save_area_sync[8];		/* 0x0200 */
 	__u32	save_area_async[8];		/* 0x0220 */
 	__u32	save_area_restart[1];		/* 0x0240 */
-	__u8	pad_0x0244[0x0248-0x0244];	/* 0x0244 */
+
+	/* CPU flags. */
+	__u32	cpu_flags;			/* 0x0244 */
 
 	/* Return psws. */
 	psw_t	return_psw;			/* 0x0248 */
@@ -139,12 +141,9 @@ struct _lowcore {
 	__u32	percpu_offset;			/* 0x02f0 */
 	__u32	machine_flags;			/* 0x02f4 */
 	__u32	ftrace_func;			/* 0x02f8 */
-	__u8	pad_0x02fc[0x0300-0x02fc];	/* 0x02fc */
-
-	/* Interrupt response block */
-	__u8	irb[64];			/* 0x0300 */
+	__u32	spinlock_lockval;		/* 0x02fc */
 
-	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
+	__u8	pad_0x0300[0x0e00-0x0300];	/* 0x0300 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -237,7 +236,9 @@ struct _lowcore {
 	__u64	save_area_sync[8];		/* 0x0200 */
 	__u64	save_area_async[8];		/* 0x0240 */
 	__u64	save_area_restart[1];		/* 0x0280 */
-	__u8	pad_0x0288[0x0290-0x0288];	/* 0x0288 */
+
+	/* CPU flags. */
+	__u64	cpu_flags;			/* 0x0288 */
 
 	/* Return psws. */
 	psw_t	return_psw;			/* 0x0290 */
@@ -285,15 +286,13 @@ struct _lowcore {
 	__u64	machine_flags;			/* 0x0388 */
 	__u64	ftrace_func;			/* 0x0390 */
 	__u64	gmap;				/* 0x0398 */
-	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
-
-	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0400 */
+	__u32	spinlock_lockval;		/* 0x03a0 */
+	__u8	pad_0x03a0[0x0400-0x03a4];	/* 0x03a4 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0440 */
+	__u32	paste[16];			/* 0x0400 */
 
-	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
+	__u8	pad_0x04c0[0x0e00-0x0440];	/* 0x0440 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 71be346..056d7ef 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -30,33 +30,31 @@ static inline int init_new_context(struct task_struct *tsk,
 
 #define destroy_context(mm)             do { } while (0)
 
-static inline void update_user_asce(struct mm_struct *mm, int load_primary)
+static inline void set_user_asce(struct mm_struct *mm)
 {
 	pgd_t *pgd = mm->pgd;
 
 	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
-	if (load_primary)
-		__ctl_load(S390_lowcore.user_asce, 1, 1);
 	set_fs(current->thread.mm_segment);
+	set_cpu_flag(CIF_ASCE);
 }
 
-static inline void clear_user_asce(struct mm_struct *mm, int load_primary)
+static inline void clear_user_asce(void)
 {
 	S390_lowcore.user_asce = S390_lowcore.kernel_asce;
 
-	if (load_primary)
-		__ctl_load(S390_lowcore.user_asce, 1, 1);
+	__ctl_load(S390_lowcore.user_asce, 1, 1);
 	__ctl_load(S390_lowcore.user_asce, 7, 7);
 }
 
-static inline void update_primary_asce(struct task_struct *tsk)
+static inline void load_kernel_asce(void)
 {
 	unsigned long asce;
 
 	__ctl_store(asce, 1, 1);
 	if (asce != S390_lowcore.kernel_asce)
 		__ctl_load(S390_lowcore.kernel_asce, 1, 1);
-	set_tsk_thread_flag(tsk, TIF_ASCE);
+	set_cpu_flag(CIF_ASCE);
 }
 
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
@@ -64,25 +62,17 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	update_primary_asce(tsk);
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	if (atomic_inc_return(&next->context.attach_count) >> 16) {
-		/* Delay update_user_asce until all TLB flushes are done. */
-		set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
-		/* Clear old ASCE by loading the kernel ASCE. */
-		clear_user_asce(next, 0);
-	} else {
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-		update_user_asce(next, 0);
-		if (next->context.flush_mm)
-			/* Flush pending TLBs */
-			__tlb_flush_mm(next);
-	}
+	/* Clear old ASCE by loading the kernel ASCE. */
+	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
+	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	/* Delay loading of the new ASCE to control registers CR1 & CR7 */
+	set_cpu_flag(CIF_ASCE);
+	atomic_inc(&next->context.attach_count);
 	atomic_dec(&prev->context.attach_count);
-	WARN_ON(atomic_read(&prev->context.attach_count) < 0);
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
@@ -93,15 +83,14 @@ static inline void finish_arch_post_lock_switch(void)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT))
+	if (!mm)
 		return;
 	preempt_disable();
-	clear_tsk_thread_flag(tsk, TIF_TLB_WAIT);
 	while (atomic_read(&mm->context.attach_count) >> 16)
 		cpu_relax();
 
 	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-	update_user_asce(mm, 0);
+	set_user_asce(mm);
 	if (mm->context.flush_mm)
 		__tlb_flush_mm(mm);
 	preempt_enable();
@@ -113,7 +102,9 @@ static inline void finish_arch_post_lock_switch(void)
 static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
-        switch_mm(prev, next, current);
+	switch_mm(prev, next, current);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+	set_user_asce(next);
 }
 
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 2583466..c030900 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -78,10 +78,16 @@ struct zpci_dev {
 	enum zpci_state state;
 	u32		fid;		/* function ID, used by sclp */
 	u32		fh;		/* function handle, used by insn's */
+	u16		vfn;		/* virtual function number */
 	u16		pchid;		/* physical channel ID */
 	u8		pfgid;		/* function group ID */
+	u8		pft;		/* pci function type */
 	u16		domain;
 
+	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
+	u32 uid;			/* user defined id */
+	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
+
 	/* IRQ stuff */
 	u64		msi_addr;	/* MSI address */
 	struct airq_iv *aibv;		/* adapter interrupt bit vector */
@@ -120,6 +126,8 @@ static inline bool zdev_enabled(struct zpci_dev *zdev)
 	return (zdev->fh & (1UL << 31)) ? true : false;
 }
 
+extern const struct attribute_group *zpci_attr_groups[];
+
 /* -----------------------------------------------------------------------------
   Prototypes
 ----------------------------------------------------------------------------- */
@@ -166,10 +174,6 @@ static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
 struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
 
-/* sysfs */
-int zpci_sysfs_add_device(struct device *);
-void zpci_sysfs_remove_device(struct device *);
-
 /* DMA */
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index d31d739..dd78f92 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -44,6 +44,7 @@ struct clp_fh_list_entry {
 #define CLP_SET_DISABLE_PCI_FN	1	/* Yes, 1 disables it */
 
 #define CLP_UTIL_STR_LEN	64
+#define CLP_PFIP_NR_SEGMENTS	4
 
 /* List PCI functions request */
 struct clp_req_list_pci {
@@ -85,7 +86,7 @@ struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
 	u32 fmt			:  4;	/* cmd request block format */
 	u32			: 28;
-	u64 reserved1;
+	u64			: 64;
 	u16 vfn;			/* virtual fn number */
 	u16			:  7;
 	u16 util_str_avail	:  1;	/* utility string available? */
@@ -94,10 +95,13 @@ struct clp_rsp_query_pci {
 	u8 bar_size[PCI_BAR_COUNT];
 	u16 pchid;
 	u32 bar[PCI_BAR_COUNT];
-	u64 reserved2;
+	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
+	u32			: 24;
+	u8 pft;				/* pci function type */
 	u64 sdma;			/* start dma as */
 	u64 edma;			/* end dma as */
-	u64 reserved3[6];
+	u32 reserved[11];
+	u32 uid;			/* user defined id */
 	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
 } __packed;
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dc5fc4f..6f02d45 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -11,6 +11,13 @@
 #ifndef __ASM_S390_PROCESSOR_H
 #define __ASM_S390_PROCESSOR_H
 
+#define CIF_MCCK_PENDING	0	/* machine check handling is pending */
+#define CIF_ASCE		1	/* user asce needs fixup / uaccess */
+
+#define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
+#define _CIF_ASCE		(1<<CIF_ASCE)
+
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
@@ -21,6 +28,21 @@
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
 
+static inline void set_cpu_flag(int flag)
+{
+	S390_lowcore.cpu_flags |= (1U << flag);
+}
+
+static inline void clear_cpu_flag(int flag)
+{
+	S390_lowcore.cpu_flags &= ~(1U << flag);
+}
+
+static inline int test_cpu_flag(int flag)
+{
+	return !!(S390_lowcore.cpu_flags & (1U << flag));
+}
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index f4783c0..1b5300c 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -8,6 +8,12 @@
 
 #include <uapi/asm/ptrace.h>
 
+#define PIF_SYSCALL		0	/* inside a system call */
+#define PIF_PER_TRAP		1	/* deliver sigtrap on return to user */
+
+#define _PIF_SYSCALL		(1<<PIF_SYSCALL)
+#define _PIF_PER_TRAP		(1<<PIF_PER_TRAP)
+
 #ifndef __ASSEMBLY__
 
 #define PSW_KERNEL_BITS	(PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_HOME | \
@@ -29,6 +35,7 @@ struct pt_regs
 	unsigned int int_code;
 	unsigned int int_parm;
 	unsigned long int_parm_long;
+	unsigned long flags;
 };
 
 /*
@@ -79,6 +86,21 @@ struct per_struct_kernel {
 #define PER_CONTROL_SUSPENSION		0x00400000UL
 #define PER_CONTROL_ALTERATION		0x00200000UL
 
+static inline void set_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	regs->flags |= (1U << flag);
+}
+
+static inline void clear_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	regs->flags &= ~(1U << flag);
+}
+
+static inline int test_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	return !!(regs->flags & (1U << flag));
+}
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index b31b22d..089a498 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -9,7 +9,6 @@
 
 
 #define PARMAREA		0x10400
-#define MEMORY_CHUNKS		256
 
 #ifndef __ASSEMBLY__
 
@@ -31,22 +30,11 @@
 #endif /* CONFIG_64BIT */
 #define COMMAND_LINE      ((char *)            (0x10480))
 
-#define CHUNK_READ_WRITE 0
-#define CHUNK_READ_ONLY  1
-
-struct mem_chunk {
-	unsigned long addr;
-	unsigned long size;
-	int type;
-};
-
-extern struct mem_chunk memory_chunk[];
 extern int memory_end_set;
 extern unsigned long memory_end;
+extern unsigned long max_physmem_end;
 
-void detect_memory_layout(struct mem_chunk chunk[], unsigned long maxsize);
-void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
-		     unsigned long size);
+extern void detect_memory_memblock(void);
 
 /*
  * Machine features detected in head.S
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 21703f8..4f13079 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -30,7 +30,6 @@ extern int smp_store_status(int cpu);
 extern int smp_vcpu_scheduled(int cpu);
 extern void smp_yield_cpu(int cpu);
 extern void smp_yield(void);
-extern void smp_stop_cpu(void);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
 extern void smp_fill_possible_mask(void);
@@ -54,6 +53,8 @@ static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_yield(void) { }
 static inline void smp_fill_possible_mask(void) { }
 
+#endif /* CONFIG_SMP */
+
 static inline void smp_stop_cpu(void)
 {
 	u16 pcpu = stap();
@@ -64,8 +65,6 @@ static inline void smp_stop_cpu(void)
 	}
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern int smp_rescan_cpus(void);
 extern void __noreturn cpu_die(void);
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 83e5d216..96879f7 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -11,18 +11,21 @@
 
 #include <linux/smp.h>
 
+#define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
+
 extern int spin_retry;
 
 static inline int
-_raw_compare_and_swap(volatile unsigned int *lock,
-		      unsigned int old, unsigned int new)
+_raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
 {
+	unsigned int old_expected = old;
+
 	asm volatile(
 		"	cs	%0,%3,%1"
 		: "=d" (old), "=Q" (*lock)
 		: "0" (old), "d" (new), "Q" (*lock)
 		: "cc", "memory" );
-	return old;
+	return old == old_expected;
 }
 
 /*
@@ -34,57 +37,69 @@ _raw_compare_and_swap(volatile unsigned int *lock,
  * (the type definitions are in asm/spinlock_types.h)
  */
 
-#define arch_spin_is_locked(x) ((x)->owner_cpu != 0)
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) \
-		 arch_spin_relax(lock); } while (0)
+void arch_spin_lock_wait(arch_spinlock_t *);
+int arch_spin_trylock_retry(arch_spinlock_t *);
+void arch_spin_relax(arch_spinlock_t *);
+void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 
-extern void arch_spin_lock_wait(arch_spinlock_t *);
-extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
-extern int arch_spin_trylock_retry(arch_spinlock_t *);
-extern void arch_spin_relax(arch_spinlock_t *lock);
+static inline u32 arch_spin_lockval(int cpu)
+{
+	return ~cpu;
+}
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
-	return lock.owner_cpu == 0;
+	return lock.lock == 0;
 }
 
-static inline void arch_spin_lock(arch_spinlock_t *lp)
+static inline int arch_spin_is_locked(arch_spinlock_t *lp)
 {
-	int old;
+	return ACCESS_ONCE(lp->lock) != 0;
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return;
-	arch_spin_lock_wait(lp);
+static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
+{
+	barrier();
+	return likely(arch_spin_value_unlocked(*lp) &&
+		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
-static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
-					 unsigned long flags)
+static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
 {
-	int old;
+	return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0);
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return;
-	arch_spin_lock_wait_flags(lp, flags);
+static inline void arch_spin_lock(arch_spinlock_t *lp)
+{
+	if (!arch_spin_trylock_once(lp))
+		arch_spin_lock_wait(lp);
 }
 
-static inline int arch_spin_trylock(arch_spinlock_t *lp)
+static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
+					unsigned long flags)
 {
-	int old;
+	if (!arch_spin_trylock_once(lp))
+		arch_spin_lock_wait_flags(lp, flags);
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return 1;
-	return arch_spin_trylock_retry(lp);
+static inline int arch_spin_trylock(arch_spinlock_t *lp)
+{
+	if (!arch_spin_trylock_once(lp))
+		return arch_spin_trylock_retry(lp);
+	return 1;
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
-	_raw_compare_and_swap(&lp->owner_cpu, lp->owner_cpu, 0);
+	arch_spin_tryrelease_once(lp);
+}
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	while (arch_spin_is_locked(lock))
+		arch_spin_relax(lock);
 }
-		
+
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -115,42 +130,50 @@ extern void _raw_write_lock_wait(arch_rwlock_t *lp);
 extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
+static inline int arch_read_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely((int) old >= 0 &&
+		      _raw_compare_and_swap(&rw->lock, old, old + 1));
+}
+
+static inline int arch_write_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely(old == 0 &&
+		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
+}
+
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old)
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait(rw);
 }
 
 static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old)
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait_flags(rw, flags);
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
-	unsigned int old, cmp;
+	unsigned int old;
 
-	old = rw->lock;
 	do {
-		cmp = old;
-		old = _raw_compare_and_swap(&rw->lock, old, old - 1);
-	} while (cmp != old);
+		old = ACCESS_ONCE(rw->lock);
+	} while (!_raw_compare_and_swap(&rw->lock, old, old - 1));
 }
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
-	if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait(rw);
 }
 
 static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait_flags(rw, flags);
 }
 
@@ -161,18 +184,16 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (likely(_raw_compare_and_swap(&rw->lock, old, old + 1) == old))
-		return 1;
-	return _raw_read_trylock_retry(rw);
+	if (!arch_read_trylock_once(rw))
+		return _raw_read_trylock_retry(rw);
+	return 1;
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0))
-		return 1;
-	return _raw_write_trylock_retry(rw);
+	if (!arch_write_trylock_once(rw))
+		return _raw_write_trylock_retry(rw);
+	return 1;
 }
 
 #define arch_read_relax(lock)	cpu_relax()
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index 9c76656..b2cd6ff 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -6,13 +6,13 @@
 #endif
 
 typedef struct {
-	volatile unsigned int owner_cpu;
+	unsigned int lock;
 } __attribute__ ((aligned (4))) arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0, }
 
 typedef struct {
-	volatile unsigned int lock;
+	unsigned int lock;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index e759181..29c81f8 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -132,7 +132,6 @@ static inline void restore_access_regs(unsigned int *acrs)
 		update_cr_regs(next);					\
 	}								\
 	prev = __switch_to(prev,next);					\
-	update_primary_asce(current);					\
 } while (0)
 
 #define finish_arch_switch(prev) do {					     \
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 7776870..abad78d 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -28,7 +28,7 @@ extern const unsigned int sys_call_table_emu[];
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
-	return test_tsk_thread_flag(task, TIF_SYSCALL) ?
+	return test_pt_regs_flag(regs, PIF_SYSCALL) ?
 		(regs->int_code & 0xffff) : -1;
 }
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 50630e6..b833e9c 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -77,32 +77,22 @@ static inline struct thread_info *current_thread_info(void)
 /*
  * thread information flags bit numbers
  */
-#define TIF_SYSCALL		0	/* inside a system call */
-#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
-#define TIF_SIGPENDING		2	/* signal pending */
-#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_TLB_WAIT		4	/* wait for TLB flush completion */
-#define TIF_ASCE		5	/* primary asce needs fixup / uaccess */
-#define TIF_PER_TRAP		6	/* deliver sigtrap on return to user */
-#define TIF_MCCK_PENDING	7	/* machine check handling is pending */
-#define TIF_SYSCALL_TRACE	8	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	9	/* syscall auditing active */
-#define TIF_SECCOMP		10	/* secure computing */
-#define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
-#define TIF_31BIT		17	/* 32bit process */
-#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
-#define TIF_SINGLE_STEP		20	/* This task is single stepped */
-#define TIF_BLOCK_STEP		21	/* This task is block stepped */
+#define TIF_NOTIFY_RESUME	0	/* callback before returning to user */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_SYSCALL_TRACE	3	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
+#define TIF_SECCOMP		5	/* secure computing */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_31BIT		16	/* 32bit process */
+#define TIF_MEMDIE		17	/* is terminating due to OOM killer */
+#define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
+#define TIF_SINGLE_STEP		19	/* This task is single stepped */
+#define TIF_BLOCK_STEP		20	/* This task is block stepped */
 
-#define _TIF_SYSCALL		(1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
-#define _TIF_TLB_WAIT		(1<<TIF_TLB_WAIT)
-#define _TIF_ASCE		(1<<TIF_ASCE)
-#define _TIF_PER_TRAP		(1<<TIF_PER_TRAP)
-#define _TIF_MCCK_PENDING	(1<<TIF_MCCK_PENDING)
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index c544b6f..a25f09f 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -59,12 +59,23 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 	tlb->batch = NULL;
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	__tlb_flush_mm_lazy(tlb->mm);
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
 	tlb_table_flush(tlb);
 }
 
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 1be64a1..cd4c68e 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -132,6 +132,34 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+
+#define __put_get_user_asm(to, from, size, spec)		\
+({								\
+	register unsigned long __reg0 asm("0") = spec;		\
+	int __rc;						\
+								\
+	asm volatile(						\
+		"0:	mvcos	%1,%3,%2\n"			\
+		"1:	xr	%0,%0\n"			\
+		"2:\n"						\
+		".pushsection .fixup, \"ax\"\n"			\
+		"3:	lhi	%0,%5\n"			\
+		"	jg	2b\n"				\
+		".popsection\n"					\
+		EX_TABLE(0b,3b) EX_TABLE(1b,3b)			\
+		: "=d" (__rc), "=Q" (*(to))			\
+		: "d" (size), "Q" (*(from)),			\
+		  "d" (__reg0), "K" (-EFAULT)			\
+		: "cc");					\
+	__rc;							\
+})
+
+#define __put_user_fn(x, ptr, size) __put_get_user_asm(ptr, x, size, 0x810000UL)
+#define __get_user_fn(x, ptr, size) __put_get_user_asm(x, ptr, size, 0x81UL)
+
+#else /* CONFIG_HAVE_MARCH_Z10_FEATURES */
+
 static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
 	size = __copy_to_user(ptr, x, size);
@@ -144,6 +172,8 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 	return size ? -EFAULT : 0;
 }
 
+#endif /* CONFIG_HAVE_MARCH_Z10_FEATURES */
+
 /*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.