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

Pull s390 updates from Martin Schwidefsky:
 "The big one is support for fake NUMA, splitting a really large machine
  in more manageable piece improves performance in some cases, e.g. for
  a KVM host.

  The FICON Link Incident handling has been improved, this helps the
  operator to identify degraded or non-operational FICON connections.

  The save and restore of floating point and vector registers has been
  overhauled to allow the future use of vector registers in the kernel.

  A few small enhancement, magic sys-requests for the vt220 console via
  SCLP, some more assembler code has been converted to C, the PCI error
  handling is improved.

  And the usual cleanup and bug fixing"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (59 commits)
  s390/jump_label: Use %*ph to print small buffers
  s390/sclp_vt220: support magic sysrequests
  s390/ctrlchar: improve handling of magic sysrequests
  s390/numa: remove superfluous ARCH_WANT defines
  s390/3270: redraw screen on unsolicited device end
  s390/dcssblk: correct out of bounds array indexes
  s390/mm: simplify page table alloc/free code
  s390/pci: move debug messages to debugfs
  s390/nmi: initialize control register 0 earlier
  s390/zcrypt: use msleep() instead of mdelay()
  s390/hmcdrv: fix interrupt registration
  s390/setup: fix novx parameter
  s390/uaccess: remove uaccess_primary kernel parameter
  s390: remove unneeded sizeof(void *) comparisons
  s390/facilities: remove transactional-execution bits
  s390/numa: re-add DIE sched_domain_topology_level
  s390/dasd: enhance CUIR scope detection
  s390/dasd: fix failing path verification
  s390/vdso: emit a GNU hash
  s390/numa: make core to node mapping data dynamic
  ...

16 files changed, 810 insertions, 171 deletions

diff --git a/arch/s390/include/asm/cpufeature.h b/arch/s390/include/asm/cpufeature.h
new file mode 100644
index 000000000000..fa7e69b7c299
--- /dev/null
+++ b/arch/s390/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Module interface for CPU features
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_S390_CPUFEATURE_H
+#define __ASM_S390_CPUFEATURE_H
+
+#include <asm/elf.h>
+
+/* Hardware features on Linux on z Systems are indicated by facility bits that
+ * are mapped to the so-called machine flags.  Particular machine flags are
+ * then used to define ELF hardware capabilities; most notably hardware flags
+ * that are essential for user space / glibc.
+ *
+ * Restrict the set of exposed CPU features to ELF hardware capabilities for
+ * now.  Additional machine flags can be indicated by values larger than
+ * MAX_ELF_HWCAP_FEATURES.
+ */
+#define MAX_ELF_HWCAP_FEATURES	(8 * sizeof(elf_hwcap))
+#define MAX_CPU_FEATURES	MAX_ELF_HWCAP_FEATURES
+
+#define cpu_feature(feat)	ilog2(HWCAP_S390_ ## feat)
+
+int cpu_have_feature(unsigned int nr);
+
+#endif /* __ASM_S390_CPUFEATURE_H */
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab802f6..17a373576868 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -46,6 +46,8 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 	__ctl_load(reg, cr, cr);
 }
 
+void __ctl_set_vx(void);
+
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
diff --git a/arch/s390/include/asm/fpu-internal.h b/arch/s390/include/asm/fpu-internal.h
new file mode 100644
index 000000000000..55dc2c0fb40a
--- /dev/null
+++ b/arch/s390/include/asm/fpu-internal.h
@@ -0,0 +1,110 @@
+/*
+ * General floating pointer and vector register helpers
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_S390_FPU_INTERNAL_H
+#define _ASM_S390_FPU_INTERNAL_H
+
+#define FPU_USE_VX		1	/* Vector extension is active */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <asm/linkage.h>
+#include <asm/ctl_reg.h>
+#include <asm/sigcontext.h>
+
+struct fpu {
+	__u32 fpc;			/* Floating-point control */
+	__u32 flags;
+	union {
+		void *regs;
+		freg_t *fprs;		/* Floating-point register save area */
+		__vector128 *vxrs;	/* Vector register save area */
+	};
+};
+
+void save_fpu_regs(void);
+
+#define is_vx_fpu(fpu) (!!((fpu)->flags & FPU_USE_VX))
+#define is_vx_task(tsk) (!!((tsk)->thread.fpu.flags & FPU_USE_VX))
+
+/* VX array structure for address operand constraints in inline assemblies */
+struct vx_array { __vector128 _[__NUM_VXRS]; };
+
+static inline int test_fp_ctl(u32 fpc)
+{
+	u32 orig_fpc;
+	int rc;
+
+	asm volatile(
+		"	efpc    %1\n"
+		"	sfpc	%2\n"
+		"0:	sfpc	%1\n"
+		"	la	%0,0\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "=d" (rc), "=d" (orig_fpc)
+		: "d" (fpc), "0" (-EINVAL));
+	return rc;
+}
+
+static inline void save_vx_regs_safe(__vector128 *vxrs)
+{
+	unsigned long cr0, flags;
+
+	flags = arch_local_irq_save();
+	__ctl_store(cr0, 0, 0);
+	__ctl_set_bit(0, 17);
+	__ctl_set_bit(0, 18);
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		: "=Q" (*(struct vx_array *) vxrs) : : "1");
+	__ctl_load(cr0, 0, 0);
+	arch_local_irq_restore(flags);
+}
+
+static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		fprs[i] = *(freg_t *)(vxrs + i);
+}
+
+static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		*(freg_t *)(vxrs + i) = fprs[i];
+}
+
+static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	fpregs->pad = 0;
+	if (is_vx_fpu(fpu))
+		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
+	else
+		memcpy((freg_t *)&fpregs->fprs, fpu->fprs,
+		       sizeof(fpregs->fprs));
+}
+
+static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	if (is_vx_fpu(fpu))
+		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
+	else
+		memcpy(fpu->fprs, (freg_t *)&fpregs->fprs,
+		       sizeof(fpregs->fprs));
+}
+
+#endif
+
+#endif /* _ASM_S390_FPU_INTERNAL_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index df4db81254d3..3d012e071647 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -22,6 +22,7 @@
 #include <linux/kvm.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
+#include <asm/fpu-internal.h>
 #include <asm/isc.h>
 
 #define KVM_MAX_VCPUS 64
@@ -501,10 +502,9 @@ struct kvm_guestdbg_info_arch {
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
-	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
-	s390_fp_regs      guest_fpregs;
-	struct kvm_s390_vregs	*host_vregs;
+	struct fpu	  host_fpregs;
+	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index fc8a8284778e..27da78cf416d 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -6,4 +6,26 @@
 #define __ALIGN .align 4, 0x07
 #define __ALIGN_STR __stringify(__ALIGN)
 
+#ifndef __ASSEMBLY__
+
+/*
+ * Helper macro for exception table entries
+ */
+#define EX_TABLE(_fault, _target)	\
+	".section __ex_table,\"a\"\n"	\
+	".align	4\n"			\
+	".long	(" #_fault ") - .\n"	\
+	".long	(" #_target ") - .\n"	\
+	".previous\n"
+
+#else /* __ASSEMBLY__ */
+
+#define EX_TABLE(_fault, _target)	\
+	.section __ex_table,"a"	;	\
+	.align	4 ;			\
+	.long	(_fault) - . ;		\
+	.long	(_target) - . ;		\
+	.previous
+
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/include/asm/mmzone.h b/arch/s390/include/asm/mmzone.h
new file mode 100644
index 000000000000..a9e834e60b84
--- /dev/null
+++ b/arch/s390/include/asm/mmzone.h
@@ -0,0 +1,16 @@
+/*
+ * NUMA support for s390
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#ifndef _ASM_S390_MMZONE_H
+#define _ASM_S390_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid) (node_data[nid])
+
+#endif /* CONFIG_NUMA */
+#endif /* _ASM_S390_MMZONE_H */
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
new file mode 100644
index 000000000000..2a0efc63b9e5
--- /dev/null
+++ b/arch/s390/include/asm/numa.h
@@ -0,0 +1,35 @@
+/*
+ * NUMA support for s390
+ *
+ * Declare the NUMA core code structures and functions.
+ *
+ * Copyright IBM Corp. 2015
+ */
+
+#ifndef _ASM_S390_NUMA_H
+#define _ASM_S390_NUMA_H
+
+#ifdef CONFIG_NUMA
+
+#include <linux/numa.h>
+#include <linux/cpumask.h>
+
+void numa_setup(void);
+int numa_pfn_to_nid(unsigned long pfn);
+int __node_distance(int a, int b);
+void numa_update_cpu_topology(void);
+
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+extern int numa_debug_enabled;
+
+#else
+
+static inline void numa_setup(void) { }
+static inline void numa_update_cpu_topology(void) { }
+static inline int numa_pfn_to_nid(unsigned long pfn)
+{
+	return 0;
+}
+
+#endif /* CONFIG_NUMA */
+#endif /* _ASM_S390_NUMA_H */
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index a648338c434a..34d960353a08 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -170,7 +170,11 @@ static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
 #endif /* CONFIG_HOTPLUG_PCI_S390 */
 
 /* Helpers */
-struct zpci_dev *get_zdev(struct pci_dev *);
+static inline struct zpci_dev *to_zpci(struct pci_dev *pdev)
+{
+	return pdev->sysdata;
+}
+
 struct zpci_dev *get_zdev_by_fid(u32);
 
 /* DMA */
@@ -188,4 +192,20 @@ void zpci_debug_init_device(struct zpci_dev *);
 void zpci_debug_exit_device(struct zpci_dev *);
 void zpci_debug_info(struct zpci_dev *, struct seq_file *);
 
+#ifdef CONFIG_NUMA
+
+/* Returns the node based on PCI bus */
+static inline int __pcibus_to_node(const struct pci_bus *bus)
+{
+	return NUMA_NO_NODE;
+}
+
+static inline const struct cpumask *
+cpumask_of_pcibus(const struct pci_bus *bus)
+{
+	return cpu_online_mask;
+}
+
+#endif /* CONFIG_NUMA */
+
 #endif
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index f66d82798a6a..bdb2f51124ed 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -576,6 +576,19 @@ static inline int pte_same(pte_t a, pte_t b)
 	return pte_val(a) == pte_val(b);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline int pte_protnone(pte_t pte)
+{
+	return pte_present(pte) && !(pte_val(pte) & _PAGE_READ);
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	/* pmd_large(pmd) implies pmd_present(pmd) */
+	return pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_READ);
+}
+#endif
+
 static inline pgste_t pgste_get_lock(pte_t *ptep)
 {
 	unsigned long new = 0;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dedb6218544b..085fb0d3c54e 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,10 +14,12 @@
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE		1	/* user asce needs fixup / uaccess */
 #define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
+#define CIF_FPU			3	/* restore vector registers */
 
 #define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
 #define _CIF_ASCE		(1<<CIF_ASCE)
 #define _CIF_NOHZ_DELAY		(1<<CIF_NOHZ_DELAY)
+#define _CIF_FPU		(1<<CIF_FPU)
 
 #ifndef __ASSEMBLY__
 
@@ -28,6 +30,7 @@
 #include <asm/ptrace.h>
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
+#include <asm/fpu-internal.h>
 
 static inline void set_cpu_flag(int flag)
 {
@@ -85,7 +88,7 @@ typedef struct {
  * Thread structure
  */
 struct thread_struct {
-	s390_fp_regs fp_regs;
+	struct fpu fpu;			/* FP and VX register save area */
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	mm_segment_t mm_segment;
@@ -101,7 +104,6 @@ struct thread_struct {
 	struct runtime_instr_cb *ri_cb;
 	int ri_signum;
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
-	__vector128 *vxrs;		/* Vector register save area */
 };
 
 /* Flag to disable transactions. */
@@ -231,6 +233,17 @@ static inline void __load_psw_mask (unsigned long mask)
 }
 
 /*
+ * Extract current PSW mask
+ */
+static inline unsigned long __extract_psw(void)
+{
+	unsigned int reg1, reg2;
+
+	asm volatile("epsw %0,%1" : "=d" (reg1), "=a" (reg2));
+	return (((unsigned long) reg1) << 32) | ((unsigned long) reg2);
+}
+
+/*
  * Rewind PSW instruction address by specified number of bytes.
  */
 static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
@@ -336,25 +349,6 @@ extern void memcpy_absolute(void *, void *, size_t);
 	memcpy_absolute(&(dest), &__tmp, sizeof(__tmp));	\
 }
 
-/*
- * Helper macro for exception table entries
- */
-#define EX_TABLE(_fault, _target)	\
-	".section __ex_table,\"a\"\n"	\
-	".align	4\n"			\
-	".long	(" #_fault ") - .\n"	\
-	".long	(" #_target ") - .\n"	\
-	".previous\n"
-
-#else /* __ASSEMBLY__ */
-
-#define EX_TABLE(_fault, _target)	\
-	.section __ex_table,"a"	;	\
-	.align	4 ;			\
-	.long	(_fault) - . ;		\
-	.long	(_target) - . ;		\
-	.previous
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_S390_PROCESSOR_H */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index f6ff06077631..821dde5f425d 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -79,6 +79,6 @@ int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 void sclp_early_detect(void);
-long _sclp_print_early(const char *);
+int _sclp_print_early(const char *);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index d62e7a69605f..dcadfde32265 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -8,139 +8,12 @@
 #define __ASM_SWITCH_TO_H
 
 #include <linux/thread_info.h>
+#include <asm/fpu-internal.h>
 #include <asm/ptrace.h>
 
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_cr_regs(struct task_struct *task);
 
-static inline int test_fp_ctl(u32 fpc)
-{
-	u32 orig_fpc;
-	int rc;
-
-	asm volatile(
-		"	efpc    %1\n"
-		"	sfpc	%2\n"
-		"0:	sfpc	%1\n"
-		"	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc), "=d" (orig_fpc)
-		: "d" (fpc), "0" (-EINVAL));
-	return rc;
-}
-
-static inline void save_fp_ctl(u32 *fpc)
-{
-	asm volatile(
-		"       stfpc   %0\n"
-		: "+Q" (*fpc));
-}
-
-static inline int restore_fp_ctl(u32 *fpc)
-{
-	int rc;
-
-	asm volatile(
-		"	lfpc    %1\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc) : "Q" (*fpc), "0" (-EINVAL));
-	return rc;
-}
-
-static inline void save_fp_regs(freg_t *fprs)
-{
-	asm volatile("std 0,%0" : "=Q" (fprs[0]));
-	asm volatile("std 2,%0" : "=Q" (fprs[2]));
-	asm volatile("std 4,%0" : "=Q" (fprs[4]));
-	asm volatile("std 6,%0" : "=Q" (fprs[6]));
-	asm volatile("std 1,%0" : "=Q" (fprs[1]));
-	asm volatile("std 3,%0" : "=Q" (fprs[3]));
-	asm volatile("std 5,%0" : "=Q" (fprs[5]));
-	asm volatile("std 7,%0" : "=Q" (fprs[7]));
-	asm volatile("std 8,%0" : "=Q" (fprs[8]));
-	asm volatile("std 9,%0" : "=Q" (fprs[9]));
-	asm volatile("std 10,%0" : "=Q" (fprs[10]));
-	asm volatile("std 11,%0" : "=Q" (fprs[11]));
-	asm volatile("std 12,%0" : "=Q" (fprs[12]));
-	asm volatile("std 13,%0" : "=Q" (fprs[13]));
-	asm volatile("std 14,%0" : "=Q" (fprs[14]));
-	asm volatile("std 15,%0" : "=Q" (fprs[15]));
-}
-
-static inline void restore_fp_regs(freg_t *fprs)
-{
-	asm volatile("ld 0,%0" : : "Q" (fprs[0]));
-	asm volatile("ld 2,%0" : : "Q" (fprs[2]));
-	asm volatile("ld 4,%0" : : "Q" (fprs[4]));
-	asm volatile("ld 6,%0" : : "Q" (fprs[6]));
-	asm volatile("ld 1,%0" : : "Q" (fprs[1]));
-	asm volatile("ld 3,%0" : : "Q" (fprs[3]));
-	asm volatile("ld 5,%0" : : "Q" (fprs[5]));
-	asm volatile("ld 7,%0" : : "Q" (fprs[7]));
-	asm volatile("ld 8,%0" : : "Q" (fprs[8]));
-	asm volatile("ld 9,%0" : : "Q" (fprs[9]));
-	asm volatile("ld 10,%0" : : "Q" (fprs[10]));
-	asm volatile("ld 11,%0" : : "Q" (fprs[11]));
-	asm volatile("ld 12,%0" : : "Q" (fprs[12]));
-	asm volatile("ld 13,%0" : : "Q" (fprs[13]));
-	asm volatile("ld 14,%0" : : "Q" (fprs[14]));
-	asm volatile("ld 15,%0" : : "Q" (fprs[15]));
-}
-
-static inline void save_vx_regs(__vector128 *vxrs)
-{
-	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
-
-	asm volatile(
-		"	la	1,%0\n"
-		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
-		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
-		: "=Q" (*(addrtype *) vxrs) : : "1");
-}
-
-static inline void save_vx_regs_safe(__vector128 *vxrs)
-{
-	unsigned long cr0, flags;
-
-	flags = arch_local_irq_save();
-	__ctl_store(cr0, 0, 0);
-	__ctl_set_bit(0, 17);
-	__ctl_set_bit(0, 18);
-	save_vx_regs(vxrs);
-	__ctl_load(cr0, 0, 0);
-	arch_local_irq_restore(flags);
-}
-
-static inline void restore_vx_regs(__vector128 *vxrs)
-{
-	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
-
-	asm volatile(
-		"	la	1,%0\n"
-		"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
-		"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
-		: : "Q" (*(addrtype *) vxrs) : "1");
-}
-
-static inline void save_fp_vx_regs(struct task_struct *task)
-{
-	if (task->thread.vxrs)
-		save_vx_regs(task->thread.vxrs);
-	else
-		save_fp_regs(task->thread.fp_regs.fprs);
-}
-
-static inline void restore_fp_vx_regs(struct task_struct *task)
-{
-	if (task->thread.vxrs)
-		restore_vx_regs(task->thread.vxrs);
-	else
-		restore_fp_regs(task->thread.fp_regs.fprs);
-}
-
 static inline void save_access_regs(unsigned int *acrs)
 {
 	typedef struct { int _[NUM_ACRS]; } acrstype;
@@ -157,15 +30,13 @@ static inline void restore_access_regs(unsigned int *acrs)
 
 #define switch_to(prev,next,last) do {					\
 	if (prev->mm) {							\
-		save_fp_ctl(&prev->thread.fp_regs.fpc);			\
-		save_fp_vx_regs(prev);					\
+		save_fpu_regs();					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
 	if (next->mm) {							\
 		update_cr_regs(next);					\
-		restore_fp_ctl(&next->thread.fp_regs.fpc);		\
-		restore_fp_vx_regs(next);				\
+		set_cpu_flag(CIF_FPU);					\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
 	}								\
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 4990f6c66288..27ebde643933 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -2,6 +2,7 @@
 #define _ASM_S390_TOPOLOGY_H
 
 #include <linux/cpumask.h>
+#include <asm/numa.h>
 
 struct sysinfo_15_1_x;
 struct cpu;
@@ -13,6 +14,7 @@ struct cpu_topology_s390 {
 	unsigned short core_id;
 	unsigned short socket_id;
 	unsigned short book_id;
+	unsigned short node_id;
 	cpumask_t thread_mask;
 	cpumask_t core_mask;
 	cpumask_t book_mask;
@@ -52,6 +54,43 @@ static inline void topology_expect_change(void) { }
 #define POLARIZATION_VM		(2)
 #define POLARIZATION_VH		(3)
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
+#ifdef CONFIG_NUMA
+
+#define cpu_to_node cpu_to_node
+static inline int cpu_to_node(int cpu)
+{
+	return per_cpu(cpu_topology, cpu).node_id;
+}
+
+/* Returns a pointer to the cpumask of CPUs on node 'node'. */
+#define cpumask_of_node cpumask_of_node
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+	return node_to_cpumask_map[node];
+}
+
+/*
+ * Returns the number of the node containing node 'node'. This
+ * architecture is flat, so it is a pretty simple function!
+ */
+#define parent_node(node) (node)
+
+#define pcibus_to_node(bus) __pcibus_to_node(bus)
+
+#define node_distance(a, b) __node_distance(a, b)
+
+#else /* !CONFIG_NUMA */
+
+#define numa_node_id numa_node_id
+static inline int numa_node_id(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_NUMA */
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 91f56b1d8156..525cef73b085 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -11,16 +11,24 @@
 
 #define __IGNORE_time
 
-/* Ignore NUMA system calls. Not wired up on s390. */
-#define __IGNORE_mbind
-#define __IGNORE_get_mempolicy
-#define __IGNORE_set_mempolicy
-#define __IGNORE_migrate_pages
-#define __IGNORE_move_pages
-
-/* Ignore system calls that are also reachable via sys_socket */
+/* Ignore system calls that are also reachable via sys_socketcall */
 #define __IGNORE_recvmmsg
 #define __IGNORE_sendmmsg
+#define __IGNORE_socket
+#define __IGNORE_socketpair
+#define __IGNORE_bind
+#define __IGNORE_connect
+#define __IGNORE_listen
+#define __IGNORE_accept4
+#define __IGNORE_getsockopt
+#define __IGNORE_setsockopt
+#define __IGNORE_getsockname
+#define __IGNORE_getpeername
+#define __IGNORE_sendto
+#define __IGNORE_sendmsg
+#define __IGNORE_recvfrom
+#define __IGNORE_recvmsg
+#define __IGNORE_shutdown
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h
new file mode 100644
index 000000000000..4a3135620f5e
--- /dev/null
+++ b/arch/s390/include/asm/vx-insn.h
@@ -0,0 +1,480 @@
+/*
+ * Support for Vector Instructions
+ *
+ * Assembler macros to generate .byte/.word code for particular
+ * vector instructions that are supported by recent binutils (>= 2.26) only.
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_S390_VX_INSN_H
+#define __ASM_S390_VX_INSN_H
+
+#ifdef __ASSEMBLY__
+
+
+/* Macros to generate vector instruction byte code */
+
+#define REG_NUM_INVALID	       255
+
+/* GR_NUM - Retrieve general-purpose register number
+ *
+ * @opd:	Operand to store register number
+ * @r64:	String designation register in the format "%rN"
+ */
+.macro	GR_NUM	opd gr
+	\opd = REG_NUM_INVALID
+	.ifc \gr,%r0
+		\opd = 0
+	.endif
+	.ifc \gr,%r1
+		\opd = 1
+	.endif
+	.ifc \gr,%r2
+		\opd = 2
+	.endif
+	.ifc \gr,%r3
+		\opd = 3
+	.endif
+	.ifc \gr,%r4
+		\opd = 4
+	.endif
+	.ifc \gr,%r5
+		\opd = 5
+	.endif
+	.ifc \gr,%r6
+		\opd = 6
+	.endif
+	.ifc \gr,%r7
+		\opd = 7
+	.endif
+	.ifc \gr,%r8
+		\opd = 8
+	.endif
+	.ifc \gr,%r9
+		\opd = 9
+	.endif
+	.ifc \gr,%r10
+		\opd = 10
+	.endif
+	.ifc \gr,%r11
+		\opd = 11
+	.endif
+	.ifc \gr,%r12
+		\opd = 12
+	.endif
+	.ifc \gr,%r13
+		\opd = 13
+	.endif
+	.ifc \gr,%r14
+		\opd = 14
+	.endif
+	.ifc \gr,%r15
+		\opd = 15
+	.endif
+	.if \opd == REG_NUM_INVALID
+		.error "Invalid general-purpose register designation: \gr"
+	.endif
+.endm
+
+/* VX_R() - Macro to encode the VX_NUM into the instruction */
+#define VX_R(v)		(v & 0x0F)
+
+/* VX_NUM - Retrieve vector register number
+ *
+ * @opd:	Operand to store register number
+ * @vxr:	String designation register in the format "%vN"
+ *
+ * The vector register number is used for as input number to the
+ * instruction and, as well as, to compute the RXB field of the
+ * instruction.  To encode the particular vector register number,
+ * use the VX_R(v) macro to extract the instruction opcode.
+ */
+.macro	VX_NUM	opd vxr
+	\opd = REG_NUM_INVALID
+	.ifc \vxr,%v0
+		\opd = 0
+	.endif
+	.ifc \vxr,%v1
+		\opd = 1
+	.endif
+	.ifc \vxr,%v2
+		\opd = 2
+	.endif
+	.ifc \vxr,%v3
+		\opd = 3
+	.endif
+	.ifc \vxr,%v4
+		\opd = 4
+	.endif
+	.ifc \vxr,%v5
+		\opd = 5
+	.endif
+	.ifc \vxr,%v6
+		\opd = 6
+	.endif
+	.ifc \vxr,%v7
+		\opd = 7
+	.endif
+	.ifc \vxr,%v8
+		\opd = 8
+	.endif
+	.ifc \vxr,%v9
+		\opd = 9
+	.endif
+	.ifc \vxr,%v10
+		\opd = 10
+	.endif
+	.ifc \vxr,%v11
+		\opd = 11
+	.endif
+	.ifc \vxr,%v12
+		\opd = 12
+	.endif
+	.ifc \vxr,%v13
+		\opd = 13
+	.endif
+	.ifc \vxr,%v14
+		\opd = 14
+	.endif
+	.ifc \vxr,%v15
+		\opd = 15
+	.endif
+	.ifc \vxr,%v16
+		\opd = 16
+	.endif
+	.ifc \vxr,%v17
+		\opd = 17
+	.endif
+	.ifc \vxr,%v18
+		\opd = 18
+	.endif
+	.ifc \vxr,%v19
+		\opd = 19
+	.endif
+	.ifc \vxr,%v20
+		\opd = 20
+	.endif
+	.ifc \vxr,%v21
+		\opd = 21
+	.endif
+	.ifc \vxr,%v22
+		\opd = 22
+	.endif
+	.ifc \vxr,%v23
+		\opd = 23
+	.endif
+	.ifc \vxr,%v24
+		\opd = 24
+	.endif
+	.ifc \vxr,%v25
+		\opd = 25
+	.endif
+	.ifc \vxr,%v26
+		\opd = 26
+	.endif
+	.ifc \vxr,%v27
+		\opd = 27
+	.endif
+	.ifc \vxr,%v28
+		\opd = 28
+	.endif
+	.ifc \vxr,%v29
+		\opd = 29
+	.endif
+	.ifc \vxr,%v30
+		\opd = 30
+	.endif
+	.ifc \vxr,%v31
+		\opd = 31
+	.endif
+	.if \opd == REG_NUM_INVALID
+		.error "Invalid vector register designation: \vxr"
+	.endif
+.endm
+
+/* RXB - Compute most significant bit used vector registers
+ *
+ * @rxb:	Operand to store computed RXB value
+ * @v1:		First vector register designated operand
+ * @v2:		Second vector register designated operand
+ * @v3:		Third vector register designated operand
+ * @v4:		Fourth vector register designated operand
+ */
+.macro	RXB	rxb v1 v2=0 v3=0 v4=0
+	\rxb = 0
+	.if \v1 & 0x10
+		\rxb = \rxb | 0x08
+	.endif
+	.if \v2 & 0x10
+		\rxb = \rxb | 0x04
+	.endif
+	.if \v3 & 0x10
+		\rxb = \rxb | 0x02
+	.endif
+	.if \v4 & 0x10
+		\rxb = \rxb | 0x01
+	.endif
+.endm
+
+/* MRXB - Generate Element Size Control and RXB value
+ *
+ * @m:		Element size control
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXB	m v1 v2=0 v3=0 v4=0
+	rxb = 0
+	RXB	rxb, \v1, \v2, \v3, \v4
+	.byte	(\m << 4) | rxb
+.endm
+
+/* MRXBOPC - Generate Element Size Control, RXB, and final Opcode fields
+ *
+ * @m:		Element size control
+ * @opc:	Opcode
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXBOPC	m opc v1 v2=0 v3=0 v4=0
+	MRXB	\m, \v1, \v2, \v3, \v4
+	.byte	\opc
+.endm
+
+/* Vector support instructions */
+
+/* VECTOR GENERATE BYTE MASK */
+.macro	VGBM	vr imm2
+	VX_NUM	v1, \vr
+	.word	(0xE700 | (VX_R(v1) << 4))
+	.word	\imm2
+	MRXBOPC	0, 0x44, v1
+.endm
+.macro	VZERO	vxr
+	VGBM	\vxr, 0
+.endm
+.macro	VONE	vxr
+	VGBM	\vxr, 0xFFFF
+.endm
+
+/* VECTOR LOAD VR ELEMENT FROM GR */
+.macro	VLVG	v, gr, disp, m
+	VX_NUM	v1, \v
+	GR_NUM	b2, "%r0"
+	GR_NUM	r3, \gr
+	.word	0xE700 | (VX_R(v1) << 4) | r3
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x22, v1
+.endm
+.macro	VLVGB	v, gr, index, base
+	VLVG	\v, \gr, \index, \base, 0
+.endm
+.macro	VLVGH	v, gr, index
+	VLVG	\v, \gr, \index, 1
+.endm
+.macro	VLVGF	v, gr, index
+	VLVG	\v, \gr, \index, 2
+.endm
+.macro	VLVGG	v, gr, index
+	VLVG	\v, \gr, \index, 3
+.endm
+
+/* VECTOR LOAD */
+.macro	VL	v, disp, index="%r0", base
+	VX_NUM	v1, \v
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | (VX_R(v1) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC 0, 0x06, v1
+.endm
+
+/* VECTOR LOAD ELEMENT */
+.macro	VLEx	vr1, disp, index="%r0", base, m3, opc
+	VX_NUM	v1, \vr1
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | (VX_R(v1) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEB	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x00
+.endm
+.macro	VLEH	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x01
+.endm
+.macro	VLEF	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x03
+.endm
+.macro	VLEG	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x02
+.endm
+
+/* VECTOR LOAD ELEMENT IMMEDIATE */
+.macro	VLEIx	vr1, imm2, m3, opc
+	VX_NUM	v1, \vr1
+	.word	0xE700 | (VX_R(v1) << 4)
+	.word	\imm2
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEIB	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x40
+.endm
+.macro	VLEIH	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x41
+.endm
+.macro	VLEIF	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x43
+.endm
+.macro	VLEIG	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x42
+.endm
+
+/* VECTOR LOAD GR FROM VR ELEMENT */
+.macro	VLGV	gr, vr, disp, base="%r0", m
+	GR_NUM	r1, \gr
+	GR_NUM	b2, \base
+	VX_NUM	v3, \vr
+	.word	0xE700 | (r1 << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x21, v3
+.endm
+.macro	VLGVB	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 0
+.endm
+.macro	VLGVH	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 1
+.endm
+.macro	VLGVF	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 2
+.endm
+.macro	VLGVG	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 3
+.endm
+
+/* VECTOR LOAD MULTIPLE */
+.macro	VLM	vfrom, vto, disp, base
+	VX_NUM	v1, \vfrom
+	VX_NUM	v3, \vto
+	GR_NUM	b2, \base	    /* Base register */
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	0, 0x36, v1, v3
+.endm
+
+/* VECTOR STORE MULTIPLE */
+.macro	VSTM	vfrom, vto, disp, base
+	VX_NUM	v1, \vfrom
+	VX_NUM	v3, \vto
+	GR_NUM	b2, \base	    /* Base register */
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v3)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	0, 0x3E, v1, v3
+.endm
+
+/* VECTOR PERMUTE */
+.macro	VPERM	vr1, vr2, vr3, vr4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	VX_NUM	v4, \vr4
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	VX_R(v4), 0x8C, v1, v2, v3, v4
+.endm
+
+/* VECTOR UNPACK LOGICAL LOW */
+.macro	VUPLL	vr1, vr2, m3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	0x0000
+	MRXBOPC	\m3, 0xD4, v1, v2
+.endm
+.macro	VUPLLB	vr1, vr2
+	VUPLL	\vr1, \vr2, 0
+.endm
+.macro	VUPLLH	vr1, vr2
+	VUPLL	\vr1, \vr2, 1
+.endm
+.macro	VUPLLF	vr1, vr2
+	VUPLL	\vr1, \vr2, 2
+.endm
+
+
+/* Vector integer instructions */
+
+/* VECTOR EXCLUSIVE OR */
+.macro	VX	vr1, vr2, vr3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	0, 0x6D, v1, v2, v3
+.endm
+
+/* VECTOR GALOIS FIELD MULTIPLY SUM */
+.macro	VGFM	vr1, vr2, vr3, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	\m4, 0xB4, v1, v2, v3
+.endm
+.macro	VGFMB	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 0
+.endm
+.macro	VGFMH	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 1
+.endm
+.macro	VGFMF	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 2
+.endm
+.macro	VGFMG	vr1, vr2, vr3
+	VGFM	\vr1, \vr2, \vr3, 3
+.endm
+
+/* VECTOR GALOIS FIELD MULTIPLY SUM AND ACCUMULATE */
+.macro	VGFMA	vr1, vr2, vr3, vr4, m5
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	VX_NUM	v4, \vr4
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12) | (\m5 << 8)
+	MRXBOPC	VX_R(v4), 0xBC, v1, v2, v3, v4
+.endm
+.macro	VGFMAB	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 0
+.endm
+.macro	VGFMAH	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 1
+.endm
+.macro	VGFMAF	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 2
+.endm
+.macro	VGFMAG	vr1, vr2, vr3, vr4
+	VGFMA	\vr1, \vr2, \vr3, \vr4, 3
+.endm
+
+/* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
+.macro	VSRLB	vr1, vr2, vr3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | (VX_R(v1) << 4) | VX_R(v2)
+	.word	(VX_R(v3) << 12)
+	MRXBOPC	0, 0x7D, v1, v2, v3
+.endm
+
+
+#endif	/* __ASSEMBLY__ */
+#endif	/* __ASM_S390_VX_INSN_H */
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 67878af257a0..59d2bb4e2d0c 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -204,9 +204,9 @@
 #define __NR_statfs64		265
 #define __NR_fstatfs64		266
 #define __NR_remap_file_pages	267
-/* Number 268 is reserved for new sys_mbind */
-/* Number 269 is reserved for new sys_get_mempolicy */
-/* Number 270 is reserved for new sys_set_mempolicy */
+#define __NR_mbind		268
+#define __NR_get_mempolicy	269
+#define __NR_set_mempolicy	270
 #define __NR_mq_open		271
 #define __NR_mq_unlink		272
 #define __NR_mq_timedsend	273
@@ -223,7 +223,7 @@
 #define __NR_inotify_init	284
 #define __NR_inotify_add_watch	285
 #define __NR_inotify_rm_watch	286
-/* Number 287 is reserved for new sys_migrate_pages */
+#define __NR_migrate_pages	287
 #define __NR_openat		288
 #define __NR_mkdirat		289
 #define __NR_mknodat		290
@@ -245,7 +245,7 @@
 #define __NR_sync_file_range	307
 #define __NR_tee		308
 #define __NR_vmsplice		309
-/* Number 310 is reserved for new sys_move_pages */
+#define __NR_move_pages		310
 #define __NR_getcpu		311
 #define __NR_epoll_pwait	312
 #define __NR_utimes		313