Initial import

147 files changed, 11209 insertions, 0 deletions

diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
new file mode 100644
index 000000000..5bdab6bff
--- /dev/null
+++ b/include/asm-generic/4level-fixup.h
@@ -0,0 +1,38 @@
+#ifndef _4LEVEL_FIXUP_H
+#define _4LEVEL_FIXUP_H
+
+#define __ARCH_HAS_4LEVEL_HACK
+#define __PAGETABLE_PUD_FOLDED
+
+#define PUD_SHIFT			PGDIR_SHIFT
+#define PUD_SIZE			PGDIR_SIZE
+#define PUD_MASK			PGDIR_MASK
+#define PTRS_PER_PUD			1
+
+#define pud_t				pgd_t
+
+#define pmd_alloc(mm, pud, address) \
+	((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \
+ 		NULL: pmd_offset(pud, address))
+
+#define pud_alloc(mm, pgd, address)	(pgd)
+#define pud_offset(pgd, start)		(pgd)
+#define pud_none(pud)			0
+#define pud_bad(pud)			0
+#define pud_present(pud)		1
+#define pud_ERROR(pud)			do { } while (0)
+#define pud_clear(pud)			pgd_clear(pud)
+#define pud_val(pud)			pgd_val(pud)
+#define pud_populate(mm, pud, pmd)	pgd_populate(mm, pud, pmd)
+#define pud_page(pud)			pgd_page(pud)
+#define pud_page_vaddr(pud)		pgd_page_vaddr(pud)
+
+#undef pud_free_tlb
+#define pud_free_tlb(tlb, x, addr)	do { } while (0)
+#define pud_free(mm, x)			do { } while (0)
+#define __pud_free_tlb(tlb, x, addr)	do { } while (0)
+
+#undef  pud_addr_end
+#define pud_addr_end(addr, end)		(end)
+
+#endif
diff --git a/include/asm-generic/Kbuild.asm b/include/asm-generic/Kbuild.asm
new file mode 100644
index 000000000..d2ee86b4c
--- /dev/null
+++ b/include/asm-generic/Kbuild.asm
@@ -0,0 +1 @@
+include include/uapi/asm-generic/Kbuild.asm
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
new file mode 100644
index 000000000..b7babf020
--- /dev/null
+++ b/include/asm-generic/atomic-long.h
@@ -0,0 +1,258 @@
+#ifndef _ASM_GENERIC_ATOMIC_LONG_H
+#define _ASM_GENERIC_ATOMIC_LONG_H
+/*
+ * Copyright (C) 2005 Silicon Graphics, Inc.
+ *	Christoph Lameter
+ *
+ * Allows to provide arch independent atomic definitions without the need to
+ * edit all arch specific atomic.h files.
+ */
+
+#include <asm/types.h>
+
+/*
+ * Suppport for atomic_long_t
+ *
+ * Casts for parameters are avoided for existing atomic functions in order to
+ * avoid issues with cast-as-lval under gcc 4.x and other limitations that the
+ * macros of a platform may have.
+ */
+
+#if BITS_PER_LONG == 64
+
+typedef atomic64_t atomic_long_t;
+
+#define ATOMIC_LONG_INIT(i)	ATOMIC64_INIT(i)
+
+static inline long atomic_long_read(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_read(v);
+}
+
+static inline void atomic_long_set(atomic_long_t *l, long i)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	atomic64_set(v, i);
+}
+
+static inline void atomic_long_inc(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	atomic64_inc(v);
+}
+
+static inline void atomic_long_dec(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	atomic64_dec(v);
+}
+
+static inline void atomic_long_add(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	atomic64_add(i, v);
+}
+
+static inline void atomic_long_sub(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	atomic64_sub(i, v);
+}
+
+static inline int atomic_long_sub_and_test(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return atomic64_sub_and_test(i, v);
+}
+
+static inline int atomic_long_dec_and_test(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return atomic64_dec_and_test(v);
+}
+
+static inline int atomic_long_inc_and_test(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return atomic64_inc_and_test(v);
+}
+
+static inline int atomic_long_add_negative(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return atomic64_add_negative(i, v);
+}
+
+static inline long atomic_long_add_return(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_add_return(i, v);
+}
+
+static inline long atomic_long_sub_return(long i, atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_sub_return(i, v);
+}
+
+static inline long atomic_long_inc_return(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_inc_return(v);
+}
+
+static inline long atomic_long_dec_return(atomic_long_t *l)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_dec_return(v);
+}
+
+static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
+{
+	atomic64_t *v = (atomic64_t *)l;
+
+	return (long)atomic64_add_unless(v, a, u);
+}
+
+#define atomic_long_inc_not_zero(l) atomic64_inc_not_zero((atomic64_t *)(l))
+
+#define atomic_long_cmpxchg(l, old, new) \
+	(atomic64_cmpxchg((atomic64_t *)(l), (old), (new)))
+#define atomic_long_xchg(v, new) \
+	(atomic64_xchg((atomic64_t *)(v), (new)))
+
+#else  /*  BITS_PER_LONG == 64  */
+
+typedef atomic_t atomic_long_t;
+
+#define ATOMIC_LONG_INIT(i)	ATOMIC_INIT(i)
+static inline long atomic_long_read(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_read(v);
+}
+
+static inline void atomic_long_set(atomic_long_t *l, long i)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	atomic_set(v, i);
+}
+
+static inline void atomic_long_inc(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	atomic_inc(v);
+}
+
+static inline void atomic_long_dec(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	atomic_dec(v);
+}
+
+static inline void atomic_long_add(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	atomic_add(i, v);
+}
+
+static inline void atomic_long_sub(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	atomic_sub(i, v);
+}
+
+static inline int atomic_long_sub_and_test(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return atomic_sub_and_test(i, v);
+}
+
+static inline int atomic_long_dec_and_test(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return atomic_dec_and_test(v);
+}
+
+static inline int atomic_long_inc_and_test(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return atomic_inc_and_test(v);
+}
+
+static inline int atomic_long_add_negative(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return atomic_add_negative(i, v);
+}
+
+static inline long atomic_long_add_return(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_add_return(i, v);
+}
+
+static inline long atomic_long_sub_return(long i, atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_sub_return(i, v);
+}
+
+static inline long atomic_long_inc_return(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_inc_return(v);
+}
+
+static inline long atomic_long_dec_return(atomic_long_t *l)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_dec_return(v);
+}
+
+static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
+{
+	atomic_t *v = (atomic_t *)l;
+
+	return (long)atomic_add_unless(v, a, u);
+}
+
+#define atomic_long_inc_not_zero(l) atomic_inc_not_zero((atomic_t *)(l))
+
+#define atomic_long_cmpxchg(l, old, new) \
+	(atomic_cmpxchg((atomic_t *)(l), (old), (new)))
+#define atomic_long_xchg(v, new) \
+	(atomic_xchg((atomic_t *)(v), (new)))
+
+#endif  /*  BITS_PER_LONG == 64  */
+
+#endif  /*  _ASM_GENERIC_ATOMIC_LONG_H  */
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
new file mode 100644
index 000000000..1973ad2b1
--- /dev/null
+++ b/include/asm-generic/atomic.h
@@ -0,0 +1,187 @@
+/*
+ * Generic C implementation of atomic counter operations. Usable on
+ * UP systems only. Do not include in machine independent code.
+ *
+ * Originally implemented for MN10300.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_ATOMIC_H
+#define __ASM_GENERIC_ATOMIC_H
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+/*
+ * atomic_$op() - $op integer to atomic variable
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does not strictly guarantee a memory-barrier, use
+ * smp_mb__{before,after}_atomic().
+ */
+
+/*
+ * atomic_$op_return() - $op interer to atomic variable and returns the result
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does imply a full memory barrier.
+ */
+
+#ifdef CONFIG_SMP
+
+/* we can build all atomic primitives from cmpxchg */
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c c_op i;						\
+}
+
+#else
+
+#include <linux/irqflags.h>
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = (v->counter = v->counter c_op i);				\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
+#endif /* CONFIG_SMP */
+
+#ifndef atomic_add_return
+ATOMIC_OP_RETURN(add, +)
+#endif
+
+#ifndef atomic_sub_return
+ATOMIC_OP_RETURN(sub, -)
+#endif
+
+#ifndef atomic_clear_mask
+ATOMIC_OP(and, &)
+#define atomic_clear_mask(i, v) atomic_and(~(i), (v))
+#endif
+
+#ifndef atomic_set_mask
+#define CONFIG_ARCH_HAS_ATOMIC_OR
+ATOMIC_OP(or, |)
+#define atomic_set_mask(i, v)	atomic_or((i), (v))
+#endif
+
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+#ifndef atomic_read
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
+#endif
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+#define atomic_set(v, i) (((v)->counter) = (i))
+
+#include <linux/irqflags.h>
+
+static inline int atomic_add_negative(int i, atomic_t *v)
+{
+	return atomic_add_return(i, v) < 0;
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	atomic_add_return(i, v);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	atomic_sub_return(i, v);
+}
+
+static inline void atomic_inc(atomic_t *v)
+{
+	atomic_add_return(1, v);
+}
+
+static inline void atomic_dec(atomic_t *v)
+{
+	atomic_sub_return(1, v);
+}
+
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+
+#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
+#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
+
+#define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
+#define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
+		c = old;
+	return c;
+}
+
+#endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
new file mode 100644
index 000000000..30ad9c86c
--- /dev/null
+++ b/include/asm-generic/atomic64.h
@@ -0,0 +1,54 @@
+/*
+ * Generic implementation of 64-bit atomics using spinlocks,
+ * useful on processors that don't have 64-bit atomic instructions.
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_GENERIC_ATOMIC64_H
+#define _ASM_GENERIC_ATOMIC64_H
+
+typedef struct {
+	long long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i)	{ (i) }
+
+extern long long atomic64_read(const atomic64_t *v);
+extern void	 atomic64_set(atomic64_t *v, long long i);
+
+#define ATOMIC64_OP(op)							\
+extern void	 atomic64_##op(long long a, atomic64_t *v);
+
+#define ATOMIC64_OP_RETURN(op)						\
+extern long long atomic64_##op##_return(long long a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(sub)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+extern long long atomic64_dec_if_positive(atomic64_t *v);
+extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
+extern long long atomic64_xchg(atomic64_t *v, long long new);
+extern int	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
+
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v)			atomic64_add(1LL, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v)			atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v) 	atomic64_add_unless((v), 1LL, 0LL)
+
+#endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/asm-generic/audit_change_attr.h b/include/asm-generic/audit_change_attr.h
new file mode 100644
index 000000000..a18655373
--- /dev/null
+++ b/include/asm-generic/audit_change_attr.h
@@ -0,0 +1,32 @@
+#ifdef __NR_chmod
+__NR_chmod,
+#endif
+__NR_fchmod,
+#ifdef __NR_chown
+__NR_chown,
+__NR_lchown,
+#endif
+#ifdef __NR_fchown
+__NR_fchown,
+#endif
+__NR_setxattr,
+__NR_lsetxattr,
+__NR_fsetxattr,
+__NR_removexattr,
+__NR_lremovexattr,
+__NR_fremovexattr,
+#ifdef __NR_fchownat
+__NR_fchownat,
+__NR_fchmodat,
+#endif
+#ifdef __NR_chown32
+__NR_chown32,
+__NR_fchown32,
+__NR_lchown32,
+#endif
+#ifdef __NR_link
+__NR_link,
+#endif
+#ifdef __NR_linkat
+__NR_linkat,
+#endif
diff --git a/include/asm-generic/audit_dir_write.h b/include/asm-generic/audit_dir_write.h
new file mode 100644
index 000000000..7b61db4fe
--- /dev/null
+++ b/include/asm-generic/audit_dir_write.h
@@ -0,0 +1,32 @@
+#ifdef __NR_rename
+__NR_rename,
+#endif
+#ifdef __NR_mkdir
+__NR_mkdir,
+#endif
+#ifdef __NR_rmdir
+__NR_rmdir,
+#endif
+#ifdef __NR_creat
+__NR_creat,
+#endif
+#ifdef __NR_link
+__NR_link,
+#endif
+#ifdef __NR_unlink
+__NR_unlink,
+#endif
+#ifdef __NR_symlink
+__NR_symlink,
+#endif
+#ifdef __NR_mknod
+__NR_mknod,
+#endif
+#ifdef __NR_mkdirat
+__NR_mkdirat,
+__NR_mknodat,
+__NR_unlinkat,
+__NR_renameat,
+__NR_linkat,
+__NR_symlinkat,
+#endif
diff --git a/include/asm-generic/audit_read.h b/include/asm-generic/audit_read.h
new file mode 100644
index 000000000..3b249cb85
--- /dev/null
+++ b/include/asm-generic/audit_read.h
@@ -0,0 +1,13 @@
+#ifdef __NR_readlink
+__NR_readlink,
+#endif
+__NR_quotactl,
+__NR_listxattr,
+__NR_llistxattr,
+__NR_flistxattr,
+__NR_getxattr,
+__NR_lgetxattr,
+__NR_fgetxattr,
+#ifdef __NR_readlinkat
+__NR_readlinkat,
+#endif
diff --git a/include/asm-generic/audit_signal.h b/include/asm-generic/audit_signal.h
new file mode 100644
index 000000000..6feab7f18
--- /dev/null
+++ b/include/asm-generic/audit_signal.h
@@ -0,0 +1,3 @@
+__NR_kill,
+__NR_tgkill,
+__NR_tkill,
diff --git a/include/asm-generic/audit_write.h b/include/asm-generic/audit_write.h
new file mode 100644
index 000000000..274575d71
--- /dev/null
+++ b/include/asm-generic/audit_write.h
@@ -0,0 +1,21 @@
+#include <asm-generic/audit_dir_write.h>
+__NR_acct,
+#ifdef __NR_swapon
+__NR_swapon,
+#endif
+__NR_quotactl,
+#ifdef __NR_truncate
+__NR_truncate,
+#endif
+#ifdef __NR_truncate64
+__NR_truncate64,
+#endif
+#ifdef __NR_ftruncate
+__NR_ftruncate,
+#endif
+#ifdef __NR_ftruncate64
+__NR_ftruncate64,
+#endif
+#ifdef __NR_bind
+__NR_bind,		/* bind can affect fs object only in one way... */
+#endif
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
new file mode 100644
index 000000000..f5c40b0fa
--- /dev/null
+++ b/include/asm-generic/barrier.h
@@ -0,0 +1,97 @@
+/*
+ * Generic barrier definitions, originally based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_BARRIER_H
+#define __ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+#ifndef nop
+#define nop()	asm volatile ("nop")
+#endif
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
+#define rmb()	mb()
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#ifndef dma_rmb
+#define dma_rmb()	rmb()
+#endif
+
+#ifndef dma_wmb
+#define dma_wmb()	wmb()
+#endif
+
+#ifndef read_barrier_depends
+#define read_barrier_depends()		do { } while (0)
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#endif
+
+#ifndef set_mb
+#define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
+#endif
+
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	smp_mb()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	smp_mb()
+#endif
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
new file mode 100644
index 000000000..dcdcacf2f
--- /dev/null
+++ b/include/asm-generic/bitops.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_GENERIC_BITOPS_H
+#define __ASM_GENERIC_BITOPS_H
+
+/*
+ * For the benefit of those who are trying to port Linux to another
+ * architecture, here are some C-language equivalents.  You should
+ * recode these in the native assembly language, if at all possible.
+ *
+ * C language equivalents written by Theodore Ts'o, 9/26/92
+ */
+
+#include <linux/irqflags.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#endif /* __ASM_GENERIC_BITOPS_H */
diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h
new file mode 100644
index 000000000..937d7c435
--- /dev/null
+++ b/include/asm-generic/bitops/__ffs.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_GENERIC_BITOPS___FFS_H_
+#define _ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+	int num = 0;
+
+#if BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h
new file mode 100644
index 000000000..a60a7ccb6
--- /dev/null
+++ b/include/asm-generic/bitops/__fls.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_GENERIC_BITOPS___FLS_H_
+#define _ASM_GENERIC_BITOPS___FLS_H_
+
+#include <asm/types.h>
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+	int num = BITS_PER_LONG - 1;
+
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-1))))
+		num -= 1;
+	return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000..6a211f406
--- /dev/null
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,25 @@
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
new file mode 100644
index 000000000..49673510b
--- /dev/null
+++ b/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,189 @@
+#ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <asm/types.h>
+#include <linux/irqflags.h>
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock.h>
+#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
+
+/* Use an array of spinlocks for our atomic_ts.
+ * Hash function to index into a different SPINLOCK.
+ * Since "a" is usually an address, use one spinlock per cacheline.
+ */
+#  define ATOMIC_HASH_SIZE 4
+#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
+
+extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
+
+/* Can't use raw_spin_lock_irq because of #include problems, so
+ * this is the substitute */
+#define _atomic_spin_lock_irqsave(l,f) do {	\
+	arch_spinlock_t *s = ATOMIC_HASH(l);	\
+	local_irq_save(f);			\
+	arch_spin_lock(s);			\
+} while(0)
+
+#define _atomic_spin_unlock_irqrestore(l,f) do {	\
+	arch_spinlock_t *s = ATOMIC_HASH(l);		\
+	arch_spin_unlock(s);				\
+	local_irq_restore(f);				\
+} while(0)
+
+
+#else
+#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
+#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
+#endif
+
+/*
+ * NMI events can occur at any time, including when interrupts have been
+ * disabled by *_irqsave().  So you can get NMI events occurring while a
+ * *_bit function is holding a spin lock.  If the NMI handler also wants
+ * to do bit manipulation (and they do) then you can get a deadlock
+ * between the original caller of *_bit() and the NMI handler.
+ *
+ * by Keith Owens
+ */
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	*p  |= mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	*p &= ~mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	*p ^= mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	old = *p;
+	*p = old | mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+
+	return (old & mask) != 0;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reorderdered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	old = *p;
+	*p = old & ~mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+
+	return (old & mask) != 0;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+	unsigned long flags;
+
+	_atomic_spin_lock_irqsave(p, flags);
+	old = *p;
+	*p = old ^ mask;
+	_atomic_spin_unlock_irqrestore(p, flags);
+
+	return (old & mask) != 0;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
diff --git a/include/asm-generic/bitops/builtin-__ffs.h b/include/asm-generic/bitops/builtin-__ffs.h
new file mode 100644
index 000000000..90041e3a4
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-__ffs.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+	return __builtin_ctzl(word);
+}
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-__fls.h b/include/asm-generic/bitops/builtin-__fls.h
new file mode 100644
index 000000000..0248f3866
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-__fls.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN___FLS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN___FLS_H_
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+	return (sizeof(word) * 8) - 1 - __builtin_clzl(word);
+}
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-ffs.h b/include/asm-generic/bitops/builtin-ffs.h
new file mode 100644
index 000000000..064825829
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-ffs.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN_FFS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN_FFS_H_
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static __always_inline int ffs(int x)
+{
+	return __builtin_ffs(x);
+}
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-fls.h b/include/asm-generic/bitops/builtin-fls.h
new file mode 100644
index 000000000..eda652d0a
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-fls.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+static __always_inline int fls(int x)
+{
+	return x ? sizeof(x) * 8 - __builtin_clz(x) : 0;
+}
+
+#endif
diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000..0a7e06623
--- /dev/null
+++ b/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)		\
+	((unsigned int)			\
+	 ((!!((w) & (1ULL << 0))) +	\
+	  (!!((w) & (1ULL << 1))) +	\
+	  (!!((w) & (1ULL << 2))) +	\
+	  (!!((w) & (1ULL << 3))) +	\
+	  (!!((w) & (1ULL << 4))) +	\
+	  (!!((w) & (1ULL << 5))) +	\
+	  (!!((w) & (1ULL << 6))) +	\
+	  (!!((w) & (1ULL << 7)))))
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/count_zeros.h b/include/asm-generic/bitops/count_zeros.h
new file mode 100644
index 000000000..97520d21f
--- /dev/null
+++ b/include/asm-generic/bitops/count_zeros.h
@@ -0,0 +1,57 @@
+/* Count leading and trailing zeros functions
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_GENERIC_BITOPS_COUNT_ZEROS_H_
+#define _ASM_GENERIC_BITOPS_COUNT_ZEROS_H_
+
+#include <asm/bitops.h>
+
+/**
+ * count_leading_zeros - Count the number of zeros from the MSB back
+ * @x: The value
+ *
+ * Count the number of leading zeros from the MSB going towards the LSB in @x.
+ *
+ * If the MSB of @x is set, the result is 0.
+ * If only the LSB of @x is set, then the result is BITS_PER_LONG-1.
+ * If @x is 0 then the result is COUNT_LEADING_ZEROS_0.
+ */
+static inline int count_leading_zeros(unsigned long x)
+{
+	if (sizeof(x) == 4)
+		return BITS_PER_LONG - fls(x);
+	else
+		return BITS_PER_LONG - fls64(x);
+}
+
+#define COUNT_LEADING_ZEROS_0 BITS_PER_LONG
+
+/**
+ * count_trailing_zeros - Count the number of zeros from the LSB forwards
+ * @x: The value
+ *
+ * Count the number of trailing zeros from the LSB going towards the MSB in @x.
+ *
+ * If the LSB of @x is set, the result is 0.
+ * If only the MSB of @x is set, then the result is BITS_PER_LONG-1.
+ * If @x is 0 then the result is COUNT_TRAILING_ZEROS_0.
+ */
+static inline int count_trailing_zeros(unsigned long x)
+{
+#define COUNT_TRAILING_ZEROS_0 (-1)
+
+	if (sizeof(x) == 4)
+		return ffs(x);
+	else
+		return (x != 0) ? __ffs(x) : COUNT_TRAILING_ZEROS_0;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_COUNT_ZEROS_H_ */
diff --git a/include/asm-generic/bitops/ext2-atomic-setbit.h b/include/asm-generic/bitops/ext2-atomic-setbit.h
new file mode 100644
index 000000000..5a0997857
--- /dev/null
+++ b/include/asm-generic/bitops/ext2-atomic-setbit.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_GENERIC_BITOPS_EXT2_ATOMIC_SETBIT_H_
+#define _ASM_GENERIC_BITOPS_EXT2_ATOMIC_SETBIT_H_
+
+/*
+ * Atomic bitops based version of ext2 atomic bitops
+ */
+
+#define ext2_set_bit_atomic(l, nr, addr)	test_and_set_bit_le(nr, addr)
+#define ext2_clear_bit_atomic(l, nr, addr)	test_and_clear_bit_le(nr, addr)
+
+#endif /* _ASM_GENERIC_BITOPS_EXT2_ATOMIC_SETBIT_H_ */
diff --git a/include/asm-generic/bitops/ext2-atomic.h b/include/asm-generic/bitops/ext2-atomic.h
new file mode 100644
index 000000000..87f0f109d
--- /dev/null
+++ b/include/asm-generic/bitops/ext2-atomic.h
@@ -0,0 +1,26 @@
+#ifndef _ASM_GENERIC_BITOPS_EXT2_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_EXT2_ATOMIC_H_
+
+/*
+ * Spinlock based version of ext2 atomic bitops
+ */
+
+#define ext2_set_bit_atomic(lock, nr, addr)		\
+	({						\
+		int ret;				\
+		spin_lock(lock);			\
+		ret = __test_and_set_bit_le(nr, addr);	\
+		spin_unlock(lock);			\
+		ret;					\
+	})
+
+#define ext2_clear_bit_atomic(lock, nr, addr)		\
+	({						\
+		int ret;				\
+		spin_lock(lock);			\
+		ret = __test_and_clear_bit_le(nr, addr);	\
+		spin_unlock(lock);			\
+		ret;					\
+	})
+
+#endif /* _ASM_GENERIC_BITOPS_EXT2_ATOMIC_H_ */
diff --git a/include/asm-generic/bitops/ffs.h b/include/asm-generic/bitops/ffs.h
new file mode 100644
index 000000000..fbbb43af7
--- /dev/null
+++ b/include/asm-generic/bitops/ffs.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_GENERIC_BITOPS_FFS_H_
+#define _ASM_GENERIC_BITOPS_FFS_H_
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static inline int ffs(int x)
+{
+	int r = 1;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff)) {
+		x >>= 16;
+		r += 16;
+	}
+	if (!(x & 0xff)) {
+		x >>= 8;
+		r += 8;
+	}
+	if (!(x & 0xf)) {
+		x >>= 4;
+		r += 4;
+	}
+	if (!(x & 3)) {
+		x >>= 2;
+		r += 2;
+	}
+	if (!(x & 1)) {
+		x >>= 1;
+		r += 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FFS_H_ */
diff --git a/include/asm-generic/bitops/ffz.h b/include/asm-generic/bitops/ffz.h
new file mode 100644
index 000000000..6744bd4cd
--- /dev/null
+++ b/include/asm-generic/bitops/ffz.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
+#define _ASM_GENERIC_BITOPS_FFZ_H_
+
+/*
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+#define ffz(x)  __ffs(~(x))
+
+#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */
diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
new file mode 100644
index 000000000..998d4d544
--- /dev/null
+++ b/include/asm-generic/bitops/find.h
@@ -0,0 +1,62 @@
+#ifndef _ASM_GENERIC_BITOPS_FIND_H_
+#define _ASM_GENERIC_BITOPS_FIND_H_
+
+#ifndef find_next_bit
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
+		size, unsigned long offset);
+#endif
+
+#ifndef find_next_zero_bit
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number of the next zero bit
+ * If no bits are zero, returns @size.
+ */
+extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
+		long size, unsigned long offset);
+#endif
+
+#ifdef CONFIG_GENERIC_FIND_FIRST_BIT
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first set bit.
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_first_bit(const unsigned long *addr,
+				    unsigned long size);
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first cleared bit.
+ * If no bits are zero, returns @size.
+ */
+extern unsigned long find_first_zero_bit(const unsigned long *addr,
+					 unsigned long size);
+#else /* CONFIG_GENERIC_FIND_FIRST_BIT */
+
+#define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
+#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
+
+#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
+
+#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h
new file mode 100644
index 000000000..0576d1f42
--- /dev/null
+++ b/include/asm-generic/bitops/fls.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __always_inline int fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h
new file mode 100644
index 000000000..b097cf844
--- /dev/null
+++ b/include/asm-generic/bitops/fls64.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#if BITS_PER_LONG == 32
+static __always_inline int fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(h) + 32;
+	return fls(x);
+}
+#elif BITS_PER_LONG == 64
+static __always_inline int fls64(__u64 x)
+{
+	if (x == 0)
+		return 0;
+	return __fls(x) + 1;
+}
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
new file mode 100644
index 000000000..a94d6519c
--- /dev/null
+++ b/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h
new file mode 100644
index 000000000..61731543c
--- /dev/null
+++ b/include/asm-generic/bitops/le.h
@@ -0,0 +1,97 @@
+#ifndef _ASM_GENERIC_BITOPS_LE_H_
+#define _ASM_GENERIC_BITOPS_LE_H_
+
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#if defined(__LITTLE_ENDIAN)
+
+#define BITOP_LE_SWIZZLE	0
+
+static inline unsigned long find_next_zero_bit_le(const void *addr,
+		unsigned long size, unsigned long offset)
+{
+	return find_next_zero_bit(addr, size, offset);
+}
+
+static inline unsigned long find_next_bit_le(const void *addr,
+		unsigned long size, unsigned long offset)
+{
+	return find_next_bit(addr, size, offset);
+}
+
+static inline unsigned long find_first_zero_bit_le(const void *addr,
+		unsigned long size)
+{
+	return find_first_zero_bit(addr, size);
+}
+
+#elif defined(__BIG_ENDIAN)
+
+#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+
+#ifndef find_next_zero_bit_le
+extern unsigned long find_next_zero_bit_le(const void *addr,
+		unsigned long size, unsigned long offset);
+#endif
+
+#ifndef find_next_bit_le
+extern unsigned long find_next_bit_le(const void *addr,
+		unsigned long size, unsigned long offset);
+#endif
+
+#ifndef find_first_zero_bit_le
+#define find_first_zero_bit_le(addr, size) \
+	find_next_zero_bit_le((addr), (size), 0)
+#endif
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+static inline int test_bit_le(int nr, const void *addr)
+{
+	return test_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline void set_bit_le(int nr, void *addr)
+{
+	set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline void clear_bit_le(int nr, void *addr)
+{
+	clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline void __set_bit_le(int nr, void *addr)
+{
+	__set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline void __clear_bit_le(int nr, void *addr)
+{
+	__clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline int test_and_set_bit_le(int nr, void *addr)
+{
+	return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline int test_and_clear_bit_le(int nr, void *addr)
+{
+	return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline int __test_and_set_bit_le(int nr, void *addr)
+{
+	return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+static inline int __test_and_clear_bit_le(int nr, void *addr)
+{
+	return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
+}
+
+#endif /* _ASM_GENERIC_BITOPS_LE_H_ */
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
new file mode 100644
index 000000000..c30266e94
--- /dev/null
+++ b/include/asm-generic/bitops/lock.h
@@ -0,0 +1,45 @@
+#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
+#define _ASM_GENERIC_BITOPS_LOCK_H_
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics.
+ * It can be used to implement bit locks.
+ */
+#define test_and_set_bit_lock(nr, addr)	test_and_set_bit(nr, addr)
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+#define clear_bit_unlock(nr, addr)	\
+do {					\
+	smp_mb__before_atomic();	\
+	clear_bit(nr, addr);		\
+} while (0)
+
+/**
+ * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is like clear_bit_unlock, however it is not atomic.
+ * It does provide release barrier semantics so it can be used to unlock
+ * a bit lock, however it would only be used if no other CPU can modify
+ * any bits in the memory until the lock is released (a good example is
+ * if the bit lock itself protects access to the other bits in the word).
+ */
+#define __clear_bit_unlock(nr, addr)	\
+do {					\
+	smp_mb();			\
+	__clear_bit(nr, addr);		\
+} while (0)
+
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 000000000..697cc2b7e
--- /dev/null
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,108 @@
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <asm/types.h>
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/include/asm-generic/bitops/sched.h b/include/asm-generic/bitops/sched.h
new file mode 100644
index 000000000..604fab703
--- /dev/null
+++ b/include/asm-generic/bitops/sched.h
@@ -0,0 +1,31 @@
+#ifndef _ASM_GENERIC_BITOPS_SCHED_H_
+#define _ASM_GENERIC_BITOPS_SCHED_H_
+
+#include <linux/compiler.h>	/* unlikely() */
+#include <asm/types.h>
+
+/*
+ * Every architecture must define this function. It's the fastest
+ * way of searching a 100-bit bitmap.  It's guaranteed that at least
+ * one of the 100 bits is cleared.
+ */
+static inline int sched_find_first_bit(const unsigned long *b)
+{
+#if BITS_PER_LONG == 64
+	if (b[0])
+		return __ffs(b[0]);
+	return __ffs(b[1]) + 64;
+#elif BITS_PER_LONG == 32
+	if (b[0])
+		return __ffs(b[0]);
+	if (b[1])
+		return __ffs(b[1]) + 32;
+	if (b[2])
+		return __ffs(b[2]) + 64;
+	return __ffs(b[3]) + 96;
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+
+#endif /* _ASM_GENERIC_BITOPS_SCHED_H_ */
diff --git a/include/asm-generic/bitsperlong.h b/include/asm-generic/bitsperlong.h
new file mode 100644
index 000000000..d1d70aa19
--- /dev/null
+++ b/include/asm-generic/bitsperlong.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+
+#ifdef CONFIG_64BIT
+#define BITS_PER_LONG 64
+#else
+#define BITS_PER_LONG 32
+#endif /* CONFIG_64BIT */
+
+/*
+ * FIXME: The check currently breaks x86-64 build, so it's
+ * temporarily disabled. Please fix x86-64 and reenable
+ */
+#if 0 && BITS_PER_LONG != __BITS_PER_LONG
+#error Inconsistent word size. Check asm/bitsperlong.h
+#endif
+
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
new file mode 100644
index 000000000..630dd2372
--- /dev/null
+++ b/include/asm-generic/bug.h
@@ -0,0 +1,211 @@
+#ifndef _ASM_GENERIC_BUG_H
+#define _ASM_GENERIC_BUG_H
+
+#include <linux/compiler.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define BUGFLAG_WARNING		(1 << 0)
+#define BUGFLAG_TAINT(taint)	(BUGFLAG_WARNING | ((taint) << 8))
+#define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
+#endif
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+
+#ifdef CONFIG_BUG
+
+#ifdef CONFIG_GENERIC_BUG
+struct bug_entry {
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	unsigned long	bug_addr;
+#else
+	signed int	bug_addr_disp;
+#endif
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	const char	*file;
+#else
+	signed int	file_disp;
+#endif
+	unsigned short	line;
+#endif
+	unsigned short	flags;
+};
+#endif	/* CONFIG_GENERIC_BUG */
+
+/*
+ * Don't use BUG() or BUG_ON() unless there's really no way out; one
+ * example might be detecting data structure corruption in the middle
+ * of an operation that can't be backed out of.  If the (sub)system
+ * can somehow continue operating, perhaps with reduced functionality,
+ * it's probably not BUG-worthy.
+ *
+ * If you're tempted to BUG(), think again:  is completely giving up
+ * really the *only* solution?  There are usually better options, where
+ * users don't need to reboot ASAP and can mostly shut down cleanly.
+ */
+#ifndef HAVE_ARCH_BUG
+#define BUG() do { \
+	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
+	panic("BUG!"); \
+} while (0)
+#endif
+
+#ifndef HAVE_ARCH_BUG_ON
+#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
+#endif
+
+/*
+ * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
+ * significant issues that need prompt attention if they should ever
+ * appear at runtime.  Use the versions with printk format strings
+ * to provide better diagnostics.
+ */
+#ifndef __WARN_TAINT
+extern __printf(3, 4)
+void warn_slowpath_fmt(const char *file, const int line,
+		       const char *fmt, ...);
+extern __printf(4, 5)
+void warn_slowpath_fmt_taint(const char *file, const int line, unsigned taint,
+			     const char *fmt, ...);
+extern void warn_slowpath_null(const char *file, const int line);
+#define WANT_WARN_ON_SLOWPATH
+#define __WARN()		warn_slowpath_null(__FILE__, __LINE__)
+#define __WARN_printf(arg...)	warn_slowpath_fmt(__FILE__, __LINE__, arg)
+#define __WARN_printf_taint(taint, arg...)				\
+	warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
+#else
+#define __WARN()		__WARN_TAINT(TAINT_WARN)
+#define __WARN_printf(arg...)	do { printk(arg); __WARN(); } while (0)
+#define __WARN_printf_taint(taint, arg...)				\
+	do { printk(arg); __WARN_TAINT(taint); } while (0)
+#endif
+
+#ifndef WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN();						\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN
+#define WARN(condition, format...) ({						\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_printf(format);					\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#define WARN_TAINT(condition, taint, format...) ({			\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_printf_taint(taint, format);			\
+	unlikely(__ret_warn_on);					\
+})
+
+#define WARN_ON_ONCE(condition)	({				\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once))				\
+		if (WARN_ON(!__warned)) 			\
+			__warned = true;			\
+	unlikely(__ret_warn_once);				\
+})
+
+#define WARN_ONCE(condition, format...)	({			\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once))				\
+		if (WARN(!__warned, format)) 			\
+			__warned = true;			\
+	unlikely(__ret_warn_once);				\
+})
+
+#define WARN_TAINT_ONCE(condition, taint, format...)	({	\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once))				\
+		if (WARN_TAINT(!__warned, taint, format))	\
+			__warned = true;			\
+	unlikely(__ret_warn_once);				\
+})
+
+#else /* !CONFIG_BUG */
+#ifndef HAVE_ARCH_BUG
+#define BUG() do {} while (1)
+#endif
+
+#ifndef HAVE_ARCH_BUG_ON
+#define BUG_ON(condition) do { if (condition) ; } while (0)
+#endif
+
+#ifndef HAVE_ARCH_WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN
+#define WARN(condition, format...) ({					\
+	int __ret_warn_on = !!(condition);				\
+	no_printk(format);						\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#define WARN_ON_ONCE(condition) WARN_ON(condition)
+#define WARN_ONCE(condition, format...) WARN(condition, format)
+#define WARN_TAINT(condition, taint, format...) WARN(condition, format)
+#define WARN_TAINT_ONCE(condition, taint, format...) WARN(condition, format)
+
+#endif
+
+/*
+ * WARN_ON_SMP() is for cases that the warning is either
+ * meaningless for !SMP or may even cause failures.
+ * This is usually used for cases that we have
+ * WARN_ON(!spin_is_locked(&lock)) checks, as spin_is_locked()
+ * returns 0 for uniprocessor settings.
+ * It can also be used with values that are only defined
+ * on SMP:
+ *
+ * struct foo {
+ *  [...]
+ * #ifdef CONFIG_SMP
+ *	int bar;
+ * #endif
+ * };
+ *
+ * void func(struct foo *zoot)
+ * {
+ *	WARN_ON_SMP(!zoot->bar);
+ *
+ * For CONFIG_SMP, WARN_ON_SMP() should act the same as WARN_ON(),
+ * and should be a nop and return false for uniprocessor.
+ *
+ * if (WARN_ON_SMP(x)) returns true only when CONFIG_SMP is set
+ * and x is true.
+ */
+#ifdef CONFIG_SMP
+# define WARN_ON_SMP(x)			WARN_ON(x)
+#else
+/*
+ * Use of ({0;}) because WARN_ON_SMP(x) may be used either as
+ * a stand alone line statement or as a condition in an if ()
+ * statement.
+ * A simple "0" would cause gcc to give a "statement has no effect"
+ * warning.
+ */
+# define WARN_ON_SMP(x)			({0;})
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h
new file mode 100644
index 000000000..6c4f62ea7
--- /dev/null
+++ b/include/asm-generic/bugs.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_GENERIC_BUGS_H
+#define __ASM_GENERIC_BUGS_H
+/*
+ * This file is included by 'init/main.c' to check for
+ * architecture-dependent bugs.
+ */
+
+static inline void check_bugs(void) { }
+
+#endif	/* __ASM_GENERIC_BUGS_H */
diff --git a/include/asm-generic/cache.h b/include/asm-generic/cache.h
new file mode 100644
index 000000000..1bfcfe5c2
--- /dev/null
+++ b/include/asm-generic/cache.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_GENERIC_CACHE_H
+#define __ASM_GENERIC_CACHE_H
+/*
+ * 32 bytes appears to be the most common cache line size,
+ * so make that the default here. Architectures with larger
+ * cache lines need to provide their own cache.h.
+ */
+
+#define L1_CACHE_SHIFT		5
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#endif /* __ASM_GENERIC_CACHE_H */
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
new file mode 100644
index 000000000..87bc536cc
--- /dev/null
+++ b/include/asm-generic/cacheflush.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_CACHEFLUSH_H
+#define __ASM_CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/*
+ * The cache doesn't need to be flushed when TLB entries change when
+ * the cache is mapped to physical memory, not virtual memory
+ */
+#define flush_cache_all()			do { } while (0)
+#define flush_cache_mm(mm)			do { } while (0)
+#define flush_cache_dup_mm(mm)			do { } while (0)
+#define flush_cache_range(vma, start, end)	do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define flush_dcache_page(page)			do { } while (0)
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+#define flush_icache_range(start, end)		do { } while (0)
+#define flush_icache_page(vma,pg)		do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
+#define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vunmap(start, end)		do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+	do { \
+		memcpy(dst, src, len); \
+		flush_icache_user_range(vma, page, vaddr, len); \
+	} while (0)
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+	memcpy(dst, src, len)
+
+#endif /* __ASM_CACHEFLUSH_H */
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
new file mode 100644
index 000000000..59811df58
--- /dev/null
+++ b/include/asm-generic/checksum.h
@@ -0,0 +1,87 @@
+#ifndef __ASM_GENERIC_CHECKSUM_H
+#define __ASM_GENERIC_CHECKSUM_H
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+extern __wsum csum_partial_copy(const void *src, void *dst, int len, __wsum sum);
+
+/*
+ * the same as csum_partial_copy, but copies from user space.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+					int len, __wsum sum, int *csum_err);
+
+#ifndef csum_partial_copy_nocheck
+#define csum_partial_copy_nocheck(src, dst, len, sum)	\
+	csum_partial_copy((src), (dst), (len), (sum))
+#endif
+
+#ifndef ip_fast_csum
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.
+ */
+extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+#endif
+
+#ifndef csum_fold
+/*
+ * Fold a partial checksum
+ */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+#endif
+
+#ifndef csum_tcpudp_nofold
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+extern __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+		unsigned short proto, __wsum sum);
+#endif
+
+#ifndef csum_tcpudp_magic
+static inline __sum16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
+		  unsigned short proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+#endif
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+extern __sum16 ip_compute_csum(const void *buff, int len);
+
+#endif /* __ASM_GENERIC_CHECKSUM_H */
diff --git a/include/asm-generic/clkdev.h b/include/asm-generic/clkdev.h
new file mode 100644
index 000000000..4ff334749
--- /dev/null
+++ b/include/asm-generic/clkdev.h
@@ -0,0 +1,30 @@
+/*
+ *  include/asm-generic/clkdev.h
+ *
+ * Based on the ARM clkdev.h:
+ *  Copyright (C) 2008 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Helper for the clk API to assist looking up a struct clk.
+ */
+#ifndef __ASM_CLKDEV_H
+#define __ASM_CLKDEV_H
+
+#include <linux/slab.h>
+
+#ifndef CONFIG_COMMON_CLK
+struct clk;
+
+static inline int __clk_get(struct clk *clk) { return 1; }
+static inline void __clk_put(struct clk *clk) { }
+#endif
+
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	return kzalloc(size, GFP_KERNEL);
+}
+
+#endif
diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
new file mode 100644
index 000000000..70bef7891
--- /dev/null
+++ b/include/asm-generic/cmpxchg-local.h
@@ -0,0 +1,67 @@
+#ifndef __ASM_GENERIC_CMPXCHG_LOCAL_H
+#define __ASM_GENERIC_CMPXCHG_LOCAL_H
+
+#include <linux/types.h>
+#include <linux/irqflags.h>
+
+extern unsigned long wrong_size_cmpxchg(volatile void *ptr)
+	__noreturn;
+
+/*
+ * Generic version of __cmpxchg_local (disables interrupts). Takes an unsigned
+ * long parameter, supporting various types of architectures.
+ */
+static inline unsigned long __cmpxchg_local_generic(volatile void *ptr,
+		unsigned long old, unsigned long new, int size)
+{
+	unsigned long flags, prev;
+
+	/*
+	 * Sanity checking, compile-time.
+	 */
+	if (size == 8 && sizeof(unsigned long) != 8)
+		wrong_size_cmpxchg(ptr);
+
+	raw_local_irq_save(flags);
+	switch (size) {
+	case 1: prev = *(u8 *)ptr;
+		if (prev == old)
+			*(u8 *)ptr = (u8)new;
+		break;
+	case 2: prev = *(u16 *)ptr;
+		if (prev == old)
+			*(u16 *)ptr = (u16)new;
+		break;
+	case 4: prev = *(u32 *)ptr;
+		if (prev == old)
+			*(u32 *)ptr = (u32)new;
+		break;
+	case 8: prev = *(u64 *)ptr;
+		if (prev == old)
+			*(u64 *)ptr = (u64)new;
+		break;
+	default:
+		wrong_size_cmpxchg(ptr);
+	}
+	raw_local_irq_restore(flags);
+	return prev;
+}
+
+/*
+ * Generic version of __cmpxchg64_local. Takes an u64 parameter.
+ */
+static inline u64 __cmpxchg64_local_generic(volatile void *ptr,
+		u64 old, u64 new)
+{
+	u64 prev;
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	prev = *(u64 *)ptr;
+	if (prev == old)
+		*(u64 *)ptr = new;
+	raw_local_irq_restore(flags);
+	return prev;
+}
+
+#endif
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
new file mode 100644
index 000000000..811fb1e9b
--- /dev/null
+++ b/include/asm-generic/cmpxchg.h
@@ -0,0 +1,108 @@
+/*
+ * Generic UP xchg and cmpxchg using interrupt disablement.  Does not
+ * support SMP.
+ */
+
+#ifndef __ASM_GENERIC_CMPXCHG_H
+#define __ASM_GENERIC_CMPXCHG_H
+
+#ifdef CONFIG_SMP
+#error "Cannot use generic cmpxchg on SMP"
+#endif
+
+#include <linux/types.h>
+#include <linux/irqflags.h>
+
+#ifndef xchg
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalidly-sized xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline
+unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	unsigned long ret, flags;
+
+	switch (size) {
+	case 1:
+#ifdef __xchg_u8
+		return __xchg_u8(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u8 *)ptr;
+		*(volatile u8 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u8 */
+
+	case 2:
+#ifdef __xchg_u16
+		return __xchg_u16(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u16 *)ptr;
+		*(volatile u16 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u16 */
+
+	case 4:
+#ifdef __xchg_u32
+		return __xchg_u32(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u32 *)ptr;
+		*(volatile u32 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u32 */
+
+#ifdef CONFIG_64BIT
+	case 8:
+#ifdef __xchg_u64
+		return __xchg_u64(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u64 *)ptr;
+		*(volatile u64 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u64 */
+#endif /* CONFIG_64BIT */
+
+	default:
+		__xchg_called_with_bad_pointer();
+		return x;
+	}
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#endif /* xchg */
+
+/*
+ * Atomic compare and exchange.
+ *
+ * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
+ * a cmpxchg primitive faster than repeated local irq save/restore exists.
+ */
+#include <asm-generic/cmpxchg-local.h>
+
+#ifndef cmpxchg_local
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#endif
+
+#ifndef cmpxchg64_local
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
+#define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
+
+#endif /* __ASM_GENERIC_CMPXCHG_H */
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
new file mode 100644
index 000000000..51969436b
--- /dev/null
+++ b/include/asm-generic/cputime.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_GENERIC_CPUTIME_H
+#define _ASM_GENERIC_CPUTIME_H
+
+#include <linux/time.h>
+#include <linux/jiffies.h>
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+# include <asm-generic/cputime_jiffies.h>
+#endif
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+# include <asm-generic/cputime_nsecs.h>
+#endif
+
+#endif
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
new file mode 100644
index 000000000..fe386fc6e
--- /dev/null
+++ b/include/asm-generic/cputime_jiffies.h
@@ -0,0 +1,76 @@
+#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
+#define _ASM_GENERIC_CPUTIME_JIFFIES_H
+
+typedef unsigned long __nocast cputime_t;
+
+#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
+
+typedef u64 __nocast cputime64_t;
+
+#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
+#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
+
+
+/*
+ * Convert nanoseconds <-> cputime
+ */
+#define cputime_to_nsecs(__ct)		\
+	jiffies_to_nsecs(cputime_to_jiffies(__ct))
+#define nsecs_to_cputime64(__nsec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
+#define nsecs_to_cputime(__nsec)	\
+	jiffies_to_cputime(nsecs_to_jiffies(__nsec))
+
+
+/*
+ * Convert cputime to microseconds and back.
+ */
+#define cputime_to_usecs(__ct)		\
+	jiffies_to_usecs(cputime_to_jiffies(__ct))
+#define usecs_to_cputime(__usec)	\
+	jiffies_to_cputime(usecs_to_jiffies(__usec))
+#define usecs_to_cputime64(__usec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
+
+/*
+ * Convert cputime to seconds and back.
+ */
+#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
+#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
+
+/*
+ * Convert cputime to timespec and back.
+ */
+#define timespec_to_cputime(__val)	\
+	jiffies_to_cputime(timespec_to_jiffies(__val))
+#define cputime_to_timespec(__ct,__val)	\
+	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to timeval and back.
+ */
+#define timeval_to_cputime(__val)	\
+	jiffies_to_cputime(timeval_to_jiffies(__val))
+#define cputime_to_timeval(__ct,__val)	\
+	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to clock and back.
+ */
+#define cputime_to_clock_t(__ct)	\
+	jiffies_to_clock_t(cputime_to_jiffies(__ct))
+#define clock_t_to_cputime(__x)		\
+	jiffies_to_cputime(clock_t_to_jiffies(__x))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
+
+#endif
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
new file mode 100644
index 000000000..041948589
--- /dev/null
+++ b/include/asm-generic/cputime_nsecs.h
@@ -0,0 +1,119 @@
+/*
+ * Definitions for measuring cputime in nsecs resolution.
+ *
+ * Based on <arch/ia64/include/asm/cputime.h>
+ *
+ * Copyright (C) 2007 FUJITSU LIMITED
+ * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
+#define _ASM_GENERIC_CPUTIME_NSECS_H
+
+#include <linux/math64.h>
+
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
+
+#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+
+#define cputime_div(__ct, divisor)  div_u64((__force u64)__ct, divisor)
+#define cputime_div_rem(__ct, divisor, remainder) \
+	div_u64_rem((__force u64)__ct, divisor, remainder);
+
+/*
+ * Convert cputime <-> jiffies (HZ)
+ */
+#define cputime_to_jiffies(__ct)	\
+	cputime_div(__ct, NSEC_PER_SEC / HZ)
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__jif)	\
+	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)	\
+	cputime_div(__ct, NSEC_PER_SEC / HZ)
+#define jiffies64_to_cputime64(__jif)	\
+	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
+
+
+/*
+ * Convert cputime <-> nanoseconds
+ */
+#define cputime_to_nsecs(__ct)		\
+	(__force u64)(__ct)
+#define nsecs_to_cputime(__nsecs)	\
+	(__force cputime_t)(__nsecs)
+
+
+/*
+ * Convert cputime <-> microseconds
+ */
+#define cputime_to_usecs(__ct)		\
+	cputime_div(__ct, NSEC_PER_USEC)
+#define usecs_to_cputime(__usecs)	\
+	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs)	\
+	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
+
+/*
+ * Convert cputime <-> seconds
+ */
+#define cputime_to_secs(__ct)		\
+	cputime_div(__ct, NSEC_PER_SEC)
+#define secs_to_cputime(__secs)		\
+	(__force cputime_t)((__secs) * NSEC_PER_SEC)
+
+/*
+ * Convert cputime <-> timespec (nsec)
+ */
+static inline cputime_t timespec_to_cputime(const struct timespec *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
+{
+	u32 rem;
+
+	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
+	val->tv_nsec = rem;
+}
+
+/*
+ * Convert cputime <-> timeval (msec)
+ */
+static inline cputime_t timeval_to_cputime(const struct timeval *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
+{
+	u32 rem;
+
+	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
+	val->tv_usec = rem / NSEC_PER_USEC;
+}
+
+/*
+ * Convert cputime <-> clock (USER_HZ)
+ */
+#define cputime_to_clock_t(__ct)	\
+	cputime_div(__ct, (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)		\
+	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	cputime_to_clock_t((__force cputime_t)__ct)
+
+#endif
diff --git a/include/asm-generic/current.h b/include/asm-generic/current.h
new file mode 100644
index 000000000..5e86f6ae7
--- /dev/null
+++ b/include/asm-generic/current.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_GENERIC_CURRENT_H
+#define __ASM_GENERIC_CURRENT_H
+
+#include <linux/thread_info.h>
+
+#define get_current() (current_thread_info()->task)
+#define current get_current()
+
+#endif /* __ASM_GENERIC_CURRENT_H */
diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h
new file mode 100644
index 000000000..0f79054ce
--- /dev/null
+++ b/include/asm-generic/delay.h
@@ -0,0 +1,44 @@
+#ifndef __ASM_GENERIC_DELAY_H
+#define __ASM_GENERIC_DELAY_H
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/*
+ * The weird n/20000 thing suppresses a "comparison is always false due to
+ * limited range of data type" warning with non-const 8-bit arguments.
+ */
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n)							\
+	({								\
+		if (__builtin_constant_p(n)) {				\
+			if ((n) / 20000 >= 1)				\
+				 __bad_udelay();			\
+			else						\
+				__const_udelay((n) * 0x10c7ul);		\
+		} else {						\
+			__udelay(n);					\
+		}							\
+	})
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n)							\
+	({								\
+		if (__builtin_constant_p(n)) {				\
+			if ((n) / 20000 >= 1)				\
+				__bad_ndelay();				\
+			else						\
+				__const_udelay((n) * 5ul);		\
+		} else {						\
+			__ndelay(n);					\
+		}							\
+	})
+
+#endif /* __ASM_GENERIC_DELAY_H */
diff --git a/include/asm-generic/device.h b/include/asm-generic/device.h
new file mode 100644
index 000000000..d7c76bba6
--- /dev/null
+++ b/include/asm-generic/device.h
@@ -0,0 +1,15 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef _ASM_GENERIC_DEVICE_H
+#define _ASM_GENERIC_DEVICE_H
+
+struct dev_archdata {
+};
+
+struct pdev_archdata {
+};
+
+#endif /* _ASM_GENERIC_DEVICE_H */
diff --git a/include/asm-generic/div64.h b/include/asm-generic/div64.h
new file mode 100644
index 000000000..8f4e31933
--- /dev/null
+++ b/include/asm-generic/div64.h
@@ -0,0 +1,58 @@
+#ifndef _ASM_GENERIC_DIV64_H
+#define _ASM_GENERIC_DIV64_H
+/*
+ * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
+ * Based on former asm-ppc/div64.h and asm-m68knommu/div64.h
+ *
+ * The semantics of do_div() are:
+ *
+ * uint32_t do_div(uint64_t *n, uint32_t base)
+ * {
+ * 	uint32_t remainder = *n % base;
+ * 	*n = *n / base;
+ * 	return remainder;
+ * }
+ *
+ * NOTE: macro parameter n is evaluated multiple times,
+ *       beware of side effects!
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+#if BITS_PER_LONG == 64
+
+# define do_div(n,base) ({					\
+	uint32_t __base = (base);				\
+	uint32_t __rem;						\
+	__rem = ((uint64_t)(n)) % __base;			\
+	(n) = ((uint64_t)(n)) / __base;				\
+	__rem;							\
+ })
+
+#elif BITS_PER_LONG == 32
+
+extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
+
+/* The unnecessary pointer compare is there
+ * to check for type safety (n must be 64bit)
+ */
+# define do_div(n,base) ({				\
+	uint32_t __base = (base);			\
+	uint32_t __rem;					\
+	(void)(((typeof((n)) *)0) == ((uint64_t *)0));	\
+	if (likely(((n) >> 32) == 0)) {			\
+		__rem = (uint32_t)(n) % __base;		\
+		(n) = (uint32_t)(n) / __base;		\
+	} else 						\
+		__rem = __div64_32(&(n), __base);	\
+	__rem;						\
+ })
+
+#else /* BITS_PER_LONG == ?? */
+
+# error do_div() does not yet support the C64
+
+#endif /* BITS_PER_LONG */
+
+#endif /* _ASM_GENERIC_DIV64_H */
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
new file mode 100644
index 000000000..0297e5875
--- /dev/null
+++ b/include/asm-generic/dma-coherent.h
@@ -0,0 +1,32 @@
+#ifndef DMA_COHERENT_H
+#define DMA_COHERENT_H
+
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+/*
+ * These three functions are only for dma allocator.
+ * Don't use them in device drivers.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret);
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
+
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+			    void *cpu_addr, size_t size, int *ret);
+/*
+ * Standard interface
+ */
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				dma_addr_t device_addr, size_t size, int flags);
+
+void dma_release_declared_memory(struct device *dev);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size);
+#else
+#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
+#endif
+
+#endif
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
new file mode 100644
index 000000000..292c57175
--- /dev/null
+++ b/include/asm-generic/dma-contiguous.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
+#define _ASM_GENERIC_DMA_CONTIGUOUS_H
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
new file mode 100644
index 000000000..6c32af918
--- /dev/null
+++ b/include/asm-generic/dma-mapping-broken.h
@@ -0,0 +1,95 @@
+#ifndef _ASM_GENERIC_DMA_MAPPING_H
+#define _ASM_GENERIC_DMA_MAPPING_H
+
+/* define the dma api to allow compilation but not linking of
+ * dma dependent code.  Code that depends on the dma-mapping
+ * API needs to set 'depends on HAS_DMA' in its Kconfig
+ */
+
+struct scatterlist;
+
+extern void *
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		   gfp_t flag);
+
+extern void
+dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
+		    dma_addr_t dma_handle);
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	return dma_alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	dma_free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+extern dma_addr_t
+dma_map_single(struct device *dev, void *ptr, size_t size,
+	       enum dma_data_direction direction);
+
+extern void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+		 enum dma_data_direction direction);
+
+extern int
+dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+	   enum dma_data_direction direction);
+
+extern void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+	     enum dma_data_direction direction);
+
+extern dma_addr_t
+dma_map_page(struct device *dev, struct page *page, unsigned long offset,
+	     size_t size, enum dma_data_direction direction);
+
+extern void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+	       enum dma_data_direction direction);
+
+extern void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction direction);
+
+extern void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
+			      unsigned long offset, size_t size,
+			      enum dma_data_direction direction);
+
+extern void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		    enum dma_data_direction direction);
+
+#define dma_sync_single_for_device dma_sync_single_for_cpu
+#define dma_sync_single_range_for_device dma_sync_single_range_for_cpu
+#define dma_sync_sg_for_device dma_sync_sg_for_cpu
+
+extern int
+dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+
+extern int
+dma_supported(struct device *dev, u64 mask);
+
+extern int
+dma_set_mask(struct device *dev, u64 mask);
+
+extern int
+dma_get_cache_alignment(void);
+
+extern void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+	       enum dma_data_direction direction);
+
+#endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
new file mode 100644
index 000000000..940d5ec12
--- /dev/null
+++ b/include/asm-generic/dma-mapping-common.h
@@ -0,0 +1,240 @@
+#ifndef _ASM_GENERIC_DMA_MAPPING_H
+#define _ASM_GENERIC_DMA_MAPPING_H
+
+#include <linux/kmemcheck.h>
+#include <linux/bug.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/dma-attrs.h>
+
+static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
+					      size_t size,
+					      enum dma_data_direction dir,
+					      struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	kmemcheck_mark_initialized(ptr, size);
+	BUG_ON(!valid_dma_direction(dir));
+	addr = ops->map_page(dev, virt_to_page(ptr),
+			     (unsigned long)ptr & ~PAGE_MASK, size,
+			     dir, attrs);
+	debug_dma_map_page(dev, virt_to_page(ptr),
+			   (unsigned long)ptr & ~PAGE_MASK, size,
+			   dir, addr, true);
+	return addr;
+}
+
+static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
+					  size_t size,
+					  enum dma_data_direction dir,
+					  struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir, true);
+}
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+				   int nents, enum dma_data_direction dir,
+				   struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	int i, ents;
+	struct scatterlist *s;
+
+	for_each_sg(sg, s, nents, i)
+		kmemcheck_mark_initialized(sg_virt(s), s->length);
+	BUG_ON(!valid_dma_direction(dir));
+	ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+
+static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	kmemcheck_mark_initialized(page_address(page) + offset, size);
+	BUG_ON(!valid_dma_direction(dir));
+	addr = ops->map_page(dev, page, offset, size, dir, NULL);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
+
+	return addr;
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
+				  size_t size, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, NULL);
+	debug_dma_unmap_page(dev, addr, size, dir, false);
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+					   size_t size,
+					   enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+					      dma_addr_t addr, size_t size,
+					      enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+						 dma_addr_t addr,
+						 unsigned long offset,
+						 size_t size,
+						 enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr + offset, size, dir);
+	debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+						    dma_addr_t addr,
+						    unsigned long offset,
+						    size_t size,
+						    enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr + offset, size, dir);
+	debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+
+}
+
+#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
+#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL)
+#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL)
+#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL)
+
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
+/**
+ * dma_mmap_attrs - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
+ * @handle: device-view address returned from dma_alloc_attrs
+ * @size: size of memory originally requested in dma_alloc_attrs
+ * @attrs: attributes of mapping properties requested in dma_alloc_attrs
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
+ * into user space.  The coherent DMA buffer must not be freed by the
+ * driver until the user space mapping has been released.
+ */
+static inline int
+dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
+	       dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->mmap)
+		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
+
+int
+dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+static inline int
+dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
+		      dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->get_sgtable)
+		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
+					attrs);
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size);
+}
+
+#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL)
+
+#endif
diff --git a/include/asm-generic/dma.h b/include/asm-generic/dma.h
new file mode 100644
index 000000000..9dfc3a7f3
--- /dev/null
+++ b/include/asm-generic/dma.h
@@ -0,0 +1,15 @@
+#ifndef __ASM_GENERIC_DMA_H
+#define __ASM_GENERIC_DMA_H
+/*
+ * This file traditionally describes the i8237 PC style DMA controller.
+ * Most architectures don't have these any more and can get the minimal
+ * implementation from kernel/dma.c by not defining MAX_DMA_CHANNELS.
+ *
+ * Some code relies on seeing MAX_DMA_ADDRESS though.
+ */
+#define MAX_DMA_ADDRESS PAGE_OFFSET
+
+extern int request_dma(unsigned int dmanr, const char *device_id);
+extern void free_dma(unsigned int dmanr);
+
+#endif /* __ASM_GENERIC_DMA_H */
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
new file mode 100644
index 000000000..a5de55c04
--- /dev/null
+++ b/include/asm-generic/early_ioremap.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_EARLY_IOREMAP_H_
+#define _ASM_EARLY_IOREMAP_H_
+
+#include <linux/types.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ */
+extern void __iomem *early_ioremap(resource_size_t phys_addr,
+				   unsigned long size);
+extern void *early_memremap(resource_size_t phys_addr,
+			    unsigned long size);
+extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void early_memunmap(void *addr, unsigned long size);
+
+/*
+ * Weak function called by early_ioremap_reset(). It does nothing, but
+ * architectures may provide their own version to do any needed cleanups.
+ */
+extern void early_ioremap_shutdown(void);
+
+#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU)
+/* Arch-specific initialization */
+extern void early_ioremap_init(void);
+
+/* Generic initialization called by architecture code */
+extern void early_ioremap_setup(void);
+
+/*
+ * Called as last step in paging_init() so library can act
+ * accordingly for subsequent map/unmap requests.
+ */
+extern void early_ioremap_reset(void);
+
+#else
+static inline void early_ioremap_init(void) { }
+static inline void early_ioremap_setup(void) { }
+static inline void early_ioremap_reset(void) { }
+#endif
+
+#endif /* _ASM_EARLY_IOREMAP_H_ */
diff --git a/include/asm-generic/emergency-restart.h b/include/asm-generic/emergency-restart.h
new file mode 100644
index 000000000..0d68a1eae
--- /dev/null
+++ b/include/asm-generic/emergency-restart.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_GENERIC_EMERGENCY_RESTART_H
+#define _ASM_GENERIC_EMERGENCY_RESTART_H
+
+static inline void machine_emergency_restart(void)
+{
+	machine_restart(NULL);
+}
+
+#endif /* _ASM_GENERIC_EMERGENCY_RESTART_H */
diff --git a/include/asm-generic/exec.h b/include/asm-generic/exec.h
new file mode 100644
index 000000000..567766b00
--- /dev/null
+++ b/include/asm-generic/exec.h
@@ -0,0 +1,19 @@
+/* Generic process execution definitions, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_EXEC_H
+#define __ASM_GENERIC_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_GENERIC_EXEC_H */
diff --git a/include/asm-generic/fb.h b/include/asm-generic/fb.h
new file mode 100644
index 000000000..fe8ca7fce
--- /dev/null
+++ b/include/asm-generic/fb.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_GENERIC_FB_H_
+#define __ASM_GENERIC_FB_H_
+#include <linux/fb.h>
+
+#define fb_pgprotect(...) do {} while (0)
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* __ASM_GENERIC_FB_H_ */
diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h
new file mode 100644
index 000000000..f23174fb9
--- /dev/null
+++ b/include/asm-generic/fixmap.h
@@ -0,0 +1,100 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009
+ * Break out common bits to asm-generic by Mark Salter, November 2013
+ */
+
+#ifndef __ASM_GENERIC_FIXMAP_H
+#define __ASM_GENERIC_FIXMAP_H
+
+#include <linux/bug.h>
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+#ifndef __ASSEMBLY__
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+
+/*
+ * Provide some reasonable defaults for page flags.
+ * Not all architectures use all of these different types and some
+ * architectures use different names.
+ */
+#ifndef FIXMAP_PAGE_NORMAL
+#define FIXMAP_PAGE_NORMAL PAGE_KERNEL
+#endif
+#ifndef FIXMAP_PAGE_NOCACHE
+#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NOCACHE
+#endif
+#ifndef FIXMAP_PAGE_IO
+#define FIXMAP_PAGE_IO PAGE_KERNEL_IO
+#endif
+#ifndef FIXMAP_PAGE_CLEAR
+#define FIXMAP_PAGE_CLEAR __pgprot(0)
+#endif
+
+#ifndef set_fixmap
+#define set_fixmap(idx, phys)				\
+	__set_fixmap(idx, phys, FIXMAP_PAGE_NORMAL)
+#endif
+
+#ifndef clear_fixmap
+#define clear_fixmap(idx)			\
+	__set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR)
+#endif
+
+/* Return a pointer with offset calculated */
+#define __set_fixmap_offset(idx, phys, flags)		      \
+({							      \
+	unsigned long addr;				      \
+	__set_fixmap(idx, phys, flags);			      \
+	addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \
+	addr;						      \
+})
+
+#define set_fixmap_offset(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_NORMAL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+	__set_fixmap(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+#define set_fixmap_offset_nocache(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+/*
+ * Some fixmaps are for IO
+ */
+#define set_fixmap_io(idx, phys) \
+	__set_fixmap(idx, phys, FIXMAP_PAGE_IO)
+
+#define set_fixmap_offset_io(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_IO)
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_GENERIC_FIXMAP_H */
diff --git a/include/asm-generic/ftrace.h b/include/asm-generic/ftrace.h
new file mode 100644
index 000000000..51abba9ea
--- /dev/null
+++ b/include/asm-generic/ftrace.h
@@ -0,0 +1,16 @@
+/*
+ * linux/include/asm-generic/ftrace.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_GENERIC_FTRACE_H__
+#define __ASM_GENERIC_FTRACE_H__
+
+/*
+ * Not all architectures need their own ftrace.h, the most
+ * common definitions are already in linux/ftrace.h.
+ */
+
+#endif /* __ASM_GENERIC_FTRACE_H__ */
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
new file mode 100644
index 000000000..b59b5a526
--- /dev/null
+++ b/include/asm-generic/futex.h
@@ -0,0 +1,171 @@
+#ifndef _ASM_GENERIC_FUTEX_H
+#define _ASM_GENERIC_FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#ifndef CONFIG_SMP
+/*
+ * The following implementation only for uniprocessor machines.
+ * For UP, it's relies on the fact that pagefault_disable() also disables
+ * preemption to ensure mutual exclusion.
+ *
+ */
+
+/**
+ * futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ *			  argument and comparison of the previous
+ *			  futex value with another constant.
+ *
+ * @encoded_op:	encoded operation to execute
+ * @uaddr:	pointer to user space address
+ *
+ * Return:
+ * 0 - On success
+ * <0 - On error
+ */
+static inline int
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval, ret;
+	u32 tmp;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	pagefault_disable();
+
+	ret = -EFAULT;
+	if (unlikely(get_user(oldval, uaddr) != 0))
+		goto out_pagefault_enable;
+
+	ret = 0;
+	tmp = oldval;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		tmp = oparg;
+		break;
+	case FUTEX_OP_ADD:
+		tmp += oparg;
+		break;
+	case FUTEX_OP_OR:
+		tmp |= oparg;
+		break;
+	case FUTEX_OP_ANDN:
+		tmp &= ~oparg;
+		break;
+	case FUTEX_OP_XOR:
+		tmp ^= oparg;
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	if (ret == 0 && unlikely(put_user(tmp, uaddr) != 0))
+		ret = -EFAULT;
+
+out_pagefault_enable:
+	pagefault_enable();
+
+	if (ret == 0) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+/**
+ * futex_atomic_cmpxchg_inatomic() - Compare and exchange the content of the
+ *				uaddr with newval if the current value is
+ *				oldval.
+ * @uval:	pointer to store content of @uaddr
+ * @uaddr:	pointer to user space address
+ * @oldval:	old value
+ * @newval:	new value to store to @uaddr
+ *
+ * Return:
+ * 0 - On success
+ * <0 - On error
+ */
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	u32 val;
+
+	if (unlikely(get_user(val, uaddr) != 0))
+		return -EFAULT;
+
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+		return -EFAULT;
+
+	*uval = val;
+
+	return 0;
+}
+
+#else
+static inline int
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+	case FUTEX_OP_ADD:
+	case FUTEX_OP_OR:
+	case FUTEX_OP_ANDN:
+	case FUTEX_OP_XOR:
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	return -ENOSYS;
+}
+
+#endif /* CONFIG_SMP */
+#endif
diff --git a/include/asm-generic/getorder.h b/include/asm-generic/getorder.h
new file mode 100644
index 000000000..65e4468ac
--- /dev/null
+++ b/include/asm-generic/getorder.h
@@ -0,0 +1,61 @@
+#ifndef __ASM_GENERIC_GETORDER_H
+#define __ASM_GENERIC_GETORDER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/log2.h>
+
+/*
+ * Runtime evaluation of get_order()
+ */
+static inline __attribute_const__
+int __get_order(unsigned long size)
+{
+	int order;
+
+	size--;
+	size >>= PAGE_SHIFT;
+#if BITS_PER_LONG == 32
+	order = fls(size);
+#else
+	order = fls64(size);
+#endif
+	return order;
+}
+
+/**
+ * get_order - Determine the allocation order of a memory size
+ * @size: The size for which to get the order
+ *
+ * Determine the allocation order of a particular sized block of memory.  This
+ * is on a logarithmic scale, where:
+ *
+ *	0 -> 2^0 * PAGE_SIZE and below
+ *	1 -> 2^1 * PAGE_SIZE to 2^0 * PAGE_SIZE + 1
+ *	2 -> 2^2 * PAGE_SIZE to 2^1 * PAGE_SIZE + 1
+ *	3 -> 2^3 * PAGE_SIZE to 2^2 * PAGE_SIZE + 1
+ *	4 -> 2^4 * PAGE_SIZE to 2^3 * PAGE_SIZE + 1
+ *	...
+ *
+ * The order returned is used to find the smallest allocation granule required
+ * to hold an object of the specified size.
+ *
+ * The result is undefined if the size is 0.
+ *
+ * This function may be used to initialise variables with compile time
+ * evaluations of constants.
+ */
+#define get_order(n)						\
+(								\
+	__builtin_constant_p(n) ? (				\
+		((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT :	\
+		(((n) < (1UL << PAGE_SHIFT)) ? 0 :		\
+		 ilog2((n) - 1) - PAGE_SHIFT + 1)		\
+	) :							\
+	__get_order(n)						\
+)
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* __ASM_GENERIC_GETORDER_H */
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
new file mode 100644
index 000000000..9bb0d1172
--- /dev/null
+++ b/include/asm-generic/gpio.h
@@ -0,0 +1,172 @@
+#ifndef _ASM_GENERIC_GPIO_H
+#define _ASM_GENERIC_GPIO_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+
+#ifdef CONFIG_GPIOLIB
+
+#include <linux/compiler.h>
+#include <linux/gpio/driver.h>
+#include <linux/gpio/consumer.h>
+
+/* Platforms may implement their GPIO interface with library code,
+ * at a small performance cost for non-inlined operations and some
+ * extra memory (for code and for per-GPIO table entries).
+ *
+ * While the GPIO programming interface defines valid GPIO numbers
+ * to be in the range 0..MAX_INT, this library restricts them to the
+ * smaller range 0..ARCH_NR_GPIOS-1.
+ *
+ * ARCH_NR_GPIOS is somewhat arbitrary; it usually reflects the sum of
+ * builtin/SoC GPIOs plus a number of GPIOs on expanders; the latter is
+ * actually an estimate of a board-specific value.
+ */
+
+#ifndef ARCH_NR_GPIOS
+#define ARCH_NR_GPIOS		512
+#endif
+
+/*
+ * "valid" GPIO numbers are nonnegative and may be passed to
+ * setup routines like gpio_request().  only some valid numbers
+ * can successfully be requested and used.
+ *
+ * Invalid GPIO numbers are useful for indicating no-such-GPIO in
+ * platform data and other tables.
+ */
+
+static inline bool gpio_is_valid(int number)
+{
+	return number >= 0 && number < ARCH_NR_GPIOS;
+}
+
+struct device;
+struct gpio;
+struct seq_file;
+struct module;
+struct device_node;
+struct gpio_desc;
+
+/* caller holds gpio_lock *OR* gpio is marked as requested */
+static inline struct gpio_chip *gpio_to_chip(unsigned gpio)
+{
+	return gpiod_to_chip(gpio_to_desc(gpio));
+}
+
+/* Always use the library code for GPIO management calls,
+ * or when sleeping may be involved.
+ */
+extern int gpio_request(unsigned gpio, const char *label);
+extern void gpio_free(unsigned gpio);
+
+static inline int gpio_direction_input(unsigned gpio)
+{
+	return gpiod_direction_input(gpio_to_desc(gpio));
+}
+static inline int gpio_direction_output(unsigned gpio, int value)
+{
+	return gpiod_direction_output_raw(gpio_to_desc(gpio), value);
+}
+
+static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
+{
+	return gpiod_set_debounce(gpio_to_desc(gpio), debounce);
+}
+
+static inline int gpio_get_value_cansleep(unsigned gpio)
+{
+	return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio));
+}
+static inline void gpio_set_value_cansleep(unsigned gpio, int value)
+{
+	return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value);
+}
+
+
+/* A platform's <asm/gpio.h> code may want to inline the I/O calls when
+ * the GPIO is constant and refers to some always-present controller,
+ * giving direct access to chip registers and tight bitbanging loops.
+ */
+static inline int __gpio_get_value(unsigned gpio)
+{
+	return gpiod_get_raw_value(gpio_to_desc(gpio));
+}
+static inline void __gpio_set_value(unsigned gpio, int value)
+{
+	return gpiod_set_raw_value(gpio_to_desc(gpio), value);
+}
+
+static inline int __gpio_cansleep(unsigned gpio)
+{
+	return gpiod_cansleep(gpio_to_desc(gpio));
+}
+
+static inline int __gpio_to_irq(unsigned gpio)
+{
+	return gpiod_to_irq(gpio_to_desc(gpio));
+}
+
+extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+extern int gpio_request_array(const struct gpio *array, size_t num);
+extern void gpio_free_array(const struct gpio *array, size_t num);
+
+/*
+ * A sysfs interface can be exported by individual drivers if they want,
+ * but more typically is configured entirely from userspace.
+ */
+static inline int gpio_export(unsigned gpio, bool direction_may_change)
+{
+	return gpiod_export(gpio_to_desc(gpio), direction_may_change);
+}
+
+static inline int gpio_export_link(struct device *dev, const char *name,
+				   unsigned gpio)
+{
+	return gpiod_export_link(dev, name, gpio_to_desc(gpio));
+}
+
+static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
+{
+	return gpiod_sysfs_set_active_low(gpio_to_desc(gpio), value);
+}
+
+static inline void gpio_unexport(unsigned gpio)
+{
+	gpiod_unexport(gpio_to_desc(gpio));
+}
+
+#else	/* !CONFIG_GPIOLIB */
+
+static inline bool gpio_is_valid(int number)
+{
+	/* only non-negative numbers are valid */
+	return number >= 0;
+}
+
+/* platforms that don't directly support access to GPIOs through I2C, SPI,
+ * or other blocking infrastructure can use these wrappers.
+ */
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+	return 0;
+}
+
+static inline int gpio_get_value_cansleep(unsigned gpio)
+{
+	might_sleep();
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value_cansleep(unsigned gpio, int value)
+{
+	might_sleep();
+	__gpio_set_value(gpio, value);
+}
+
+#endif /* !CONFIG_GPIOLIB */
+
+#endif /* _ASM_GENERIC_GPIO_H */
diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h
new file mode 100644
index 000000000..04d0a977c
--- /dev/null
+++ b/include/asm-generic/hardirq.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_GENERIC_HARDIRQ_H
+#define __ASM_GENERIC_HARDIRQ_H
+
+#include <linux/cache.h>
+#include <linux/threads.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
+
+#ifndef ack_bad_irq
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+#endif
+
+#endif /* __ASM_GENERIC_HARDIRQ_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
new file mode 100644
index 000000000..99b490b4d
--- /dev/null
+++ b/include/asm-generic/hugetlb.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_GENERIC_HUGETLB_H
+#define _ASM_GENERIC_HUGETLB_H
+
+static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
+{
+	return mk_pte(page, pgprot);
+}
+
+static inline unsigned long huge_pte_write(pte_t pte)
+{
+	return pte_write(pte);
+}
+
+static inline unsigned long huge_pte_dirty(pte_t pte)
+{
+	return pte_dirty(pte);
+}
+
+static inline pte_t huge_pte_mkwrite(pte_t pte)
+{
+	return pte_mkwrite(pte);
+}
+
+static inline pte_t huge_pte_mkdirty(pte_t pte)
+{
+	return pte_mkdirty(pte);
+}
+
+static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return pte_modify(pte, newprot);
+}
+
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+				  pte_t *ptep)
+{
+	pte_clear(mm, addr, ptep);
+}
+
+#endif /* _ASM_GENERIC_HUGETLB_H */
diff --git a/include/asm-generic/hw_irq.h b/include/asm-generic/hw_irq.h
new file mode 100644
index 000000000..89036d7b4
--- /dev/null
+++ b/include/asm-generic/hw_irq.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_GENERIC_HW_IRQ_H
+#define __ASM_GENERIC_HW_IRQ_H
+/*
+ * hw_irq.h has internal declarations for the low-level interrupt
+ * controller, like the original i8259A.
+ * In general, this is not needed for new architectures.
+ */
+
+#endif /* __ASM_GENERIC_HW_IRQ_H */
diff --git a/include/asm-generic/ide_iops.h b/include/asm-generic/ide_iops.h
new file mode 100644
index 000000000..1b91d0681
--- /dev/null
+++ b/include/asm-generic/ide_iops.h
@@ -0,0 +1,38 @@
+/* Generic I/O and MEMIO string operations.  */
+
+#define __ide_insw	insw
+#define __ide_insl	insl
+#define __ide_outsw	outsw
+#define __ide_outsl	outsl
+
+static __inline__ void __ide_mm_insw(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		*(u16 *)addr = readw(port);
+		addr += 2;
+	}
+}
+
+static __inline__ void __ide_mm_insl(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		*(u32 *)addr = readl(port);
+		addr += 4;
+	}
+}
+
+static __inline__ void __ide_mm_outsw(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		writew(*(u16 *)addr, port);
+		addr += 2;
+	}
+}
+
+static __inline__ void __ide_mm_outsl(void __iomem * port, void *addr, u32 count)
+{
+	while (count--) {
+		writel(*(u32 *)addr, port);
+		addr += 4;
+	}
+}
diff --git a/include/asm-generic/int-ll64.h b/include/asm-generic/int-ll64.h
new file mode 100644
index 000000000..4cd84855c
--- /dev/null
+++ b/include/asm-generic/int-ll64.h
@@ -0,0 +1,49 @@
+/*
+ * asm-generic/int-ll64.h
+ *
+ * Integer declarations for architectures which use "long long"
+ * for 64-bit types.
+ */
+#ifndef _ASM_GENERIC_INT_LL64_H
+#define _ASM_GENERIC_INT_LL64_H
+
+#include <uapi/asm-generic/int-ll64.h>
+
+
+#ifndef __ASSEMBLY__
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+#define S8_C(x)  x
+#define U8_C(x)  x ## U
+#define S16_C(x) x
+#define U16_C(x) x ## U
+#define S32_C(x) x
+#define U32_C(x) x ## U
+#define S64_C(x) x ## LL
+#define U64_C(x) x ## ULL
+
+#else /* __ASSEMBLY__ */
+
+#define S8_C(x)  x
+#define U8_C(x)  x
+#define S16_C(x) x
+#define U16_C(x) x
+#define S32_C(x) x
+#define U32_C(x) x
+#define S64_C(x) x
+#define U64_C(x) x
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_GENERIC_INT_LL64_H */
diff --git a/include/asm-generic/io-64-nonatomic-hi-lo.h b/include/asm-generic/io-64-nonatomic-hi-lo.h
new file mode 100644
index 000000000..2e29d13fc
--- /dev/null
+++ b/include/asm-generic/io-64-nonatomic-hi-lo.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_IO_64_NONATOMIC_HI_LO_H_
+#define _ASM_IO_64_NONATOMIC_HI_LO_H_
+
+#include <linux/io.h>
+#include <asm-generic/int-ll64.h>
+
+static inline __u64 hi_lo_readq(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	high = readl(p + 1);
+	low = readl(p);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void hi_lo_writeq(__u64 val, volatile void __iomem *addr)
+{
+	writel(val >> 32, addr + 4);
+	writel(val, addr);
+}
+
+#ifndef readq
+#define readq hi_lo_readq
+#endif
+
+#ifndef writeq
+#define writeq hi_lo_writeq
+#endif
+
+#endif	/* _ASM_IO_64_NONATOMIC_HI_LO_H_ */
diff --git a/include/asm-generic/io-64-nonatomic-lo-hi.h b/include/asm-generic/io-64-nonatomic-lo-hi.h
new file mode 100644
index 000000000..0efacff0a
--- /dev/null
+++ b/include/asm-generic/io-64-nonatomic-lo-hi.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_IO_64_NONATOMIC_LO_HI_H_
+#define _ASM_IO_64_NONATOMIC_LO_HI_H_
+
+#include <linux/io.h>
+#include <asm-generic/int-ll64.h>
+
+static inline __u64 lo_hi_readq(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	low = readl(p);
+	high = readl(p + 1);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void lo_hi_writeq(__u64 val, volatile void __iomem *addr)
+{
+	writel(val, addr);
+	writel(val >> 32, addr + 4);
+}
+
+#ifndef readq
+#define readq lo_hi_readq
+#endif
+
+#ifndef writeq
+#define writeq lo_hi_writeq
+#endif
+
+#endif	/* _ASM_IO_64_NONATOMIC_LO_HI_H_ */
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
new file mode 100644
index 000000000..9db042304
--- /dev/null
+++ b/include/asm-generic/io.h
@@ -0,0 +1,877 @@
+/* Generic I/O port emulation, based on MN10300 code
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_IO_H
+#define __ASM_GENERIC_IO_H
+
+#include <asm/page.h> /* I/O is all done through memory accesses */
+#include <linux/string.h> /* for memset() and memcpy() */
+#include <linux/types.h>
+
+#ifdef CONFIG_GENERIC_IOMAP
+#include <asm-generic/iomap.h>
+#endif
+
+#include <asm-generic/pci_iomap.h>
+
+#ifndef mmiowb
+#define mmiowb() do {} while (0)
+#endif
+
+/*
+ * __raw_{read,write}{b,w,l,q}() access memory in native endianness.
+ *
+ * On some architectures memory mapped IO needs to be accessed differently.
+ * On the simple architectures, we just read/write the memory location
+ * directly.
+ */
+
+#ifndef __raw_readb
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	return *(const volatile u8 __force *)addr;
+}
+#endif
+
+#ifndef __raw_readw
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	return *(const volatile u16 __force *)addr;
+}
+#endif
+
+#ifndef __raw_readl
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	return *(const volatile u32 __force *)addr;
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef __raw_readq
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+	return *(const volatile u64 __force *)addr;
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef __raw_writeb
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 value, volatile void __iomem *addr)
+{
+	*(volatile u8 __force *)addr = value;
+}
+#endif
+
+#ifndef __raw_writew
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 value, volatile void __iomem *addr)
+{
+	*(volatile u16 __force *)addr = value;
+}
+#endif
+
+#ifndef __raw_writel
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 value, volatile void __iomem *addr)
+{
+	*(volatile u32 __force *)addr = value;
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef __raw_writeq
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 value, volatile void __iomem *addr)
+{
+	*(volatile u64 __force *)addr = value;
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+/*
+ * {read,write}{b,w,l,q}() access little endian memory and return result in
+ * native endianness.
+ */
+
+#ifndef readb
+#define readb readb
+static inline u8 readb(const volatile void __iomem *addr)
+{
+	return __raw_readb(addr);
+}
+#endif
+
+#ifndef readw
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __le16_to_cpu(__raw_readw(addr));
+}
+#endif
+
+#ifndef readl
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
+{
+	return __le32_to_cpu(__raw_readl(addr));
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef readq
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return __le64_to_cpu(__raw_readq(addr));
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef writeb
+#define writeb writeb
+static inline void writeb(u8 value, volatile void __iomem *addr)
+{
+	__raw_writeb(value, addr);
+}
+#endif
+
+#ifndef writew
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
+{
+	__raw_writew(cpu_to_le16(value), addr);
+}
+#endif
+
+#ifndef writel
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
+{
+	__raw_writel(__cpu_to_le32(value), addr);
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef writeq
+#define writeq writeq
+static inline void writeq(u64 value, volatile void __iomem *addr)
+{
+	__raw_writeq(__cpu_to_le64(value), addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+/*
+ * {read,write}{b,w,l,q}_relaxed() are like the regular version, but
+ * are not guaranteed to provide ordering against spinlocks or memory
+ * accesses.
+ */
+#ifndef readb_relaxed
+#define readb_relaxed readb
+#endif
+
+#ifndef readw_relaxed
+#define readw_relaxed readw
+#endif
+
+#ifndef readl_relaxed
+#define readl_relaxed readl
+#endif
+
+#ifndef readq_relaxed
+#define readq_relaxed readq
+#endif
+
+#ifndef writeb_relaxed
+#define writeb_relaxed writeb
+#endif
+
+#ifndef writew_relaxed
+#define writew_relaxed writew
+#endif
+
+#ifndef writel_relaxed
+#define writel_relaxed writel
+#endif
+
+#ifndef writeq_relaxed
+#define writeq_relaxed writeq
+#endif
+
+/*
+ * {read,write}s{b,w,l,q}() repeatedly access the same memory address in
+ * native endianness in 8-, 16-, 32- or 64-bit chunks (@count times).
+ */
+#ifndef readsb
+#define readsb readsb
+static inline void readsb(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u8 *buf = buffer;
+
+		do {
+			u8 x = __raw_readb(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef readsw
+#define readsw readsw
+static inline void readsw(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u16 *buf = buffer;
+
+		do {
+			u16 x = __raw_readw(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef readsl
+#define readsl readsl
+static inline void readsl(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u32 *buf = buffer;
+
+		do {
+			u32 x = __raw_readl(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef readsq
+#define readsq readsq
+static inline void readsq(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u64 *buf = buffer;
+
+		do {
+			u64 x = __raw_readq(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef writesb
+#define writesb writesb
+static inline void writesb(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u8 *buf = buffer;
+
+		do {
+			__raw_writeb(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesw
+#define writesw writesw
+static inline void writesw(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u16 *buf = buffer;
+
+		do {
+			__raw_writew(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesl
+#define writesl writesl
+static inline void writesl(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u32 *buf = buffer;
+
+		do {
+			__raw_writel(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef writesq
+#define writesq writesq
+static inline void writesq(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u64 *buf = buffer;
+
+		do {
+			__raw_writeq(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef PCI_IOBASE
+#define PCI_IOBASE ((void __iomem *)0)
+#endif
+
+#ifndef IO_SPACE_LIMIT
+#define IO_SPACE_LIMIT 0xffff
+#endif
+
+/*
+ * {in,out}{b,w,l}() access little endian I/O. {in,out}{b,w,l}_p() can be
+ * implemented on hardware that needs an additional delay for I/O accesses to
+ * take effect.
+ */
+
+#ifndef inb
+#define inb inb
+static inline u8 inb(unsigned long addr)
+{
+	return readb(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inw
+#define inw inw
+static inline u16 inw(unsigned long addr)
+{
+	return readw(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inl
+#define inl inl
+static inline u32 inl(unsigned long addr)
+{
+	return readl(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outb
+#define outb outb
+static inline void outb(u8 value, unsigned long addr)
+{
+	writeb(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outw
+#define outw outw
+static inline void outw(u16 value, unsigned long addr)
+{
+	writew(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outl
+#define outl outl
+static inline void outl(u32 value, unsigned long addr)
+{
+	writel(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inb_p
+#define inb_p inb_p
+static inline u8 inb_p(unsigned long addr)
+{
+	return inb(addr);
+}
+#endif
+
+#ifndef inw_p
+#define inw_p inw_p
+static inline u16 inw_p(unsigned long addr)
+{
+	return inw(addr);
+}
+#endif
+
+#ifndef inl_p
+#define inl_p inl_p
+static inline u32 inl_p(unsigned long addr)
+{
+	return inl(addr);
+}
+#endif
+
+#ifndef outb_p
+#define outb_p outb_p
+static inline void outb_p(u8 value, unsigned long addr)
+{
+	outb(value, addr);
+}
+#endif
+
+#ifndef outw_p
+#define outw_p outw_p
+static inline void outw_p(u16 value, unsigned long addr)
+{
+	outw(value, addr);
+}
+#endif
+
+#ifndef outl_p
+#define outl_p outl_p
+static inline void outl_p(u32 value, unsigned long addr)
+{
+	outl(value, addr);
+}
+#endif
+
+/*
+ * {in,out}s{b,w,l}{,_p}() are variants of the above that repeatedly access a
+ * single I/O port multiple times.
+ */
+
+#ifndef insb
+#define insb insb
+static inline void insb(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insw
+#define insw insw
+static inline void insw(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insl
+#define insl insl
+static inline void insl(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsb
+#define outsb outsb
+static inline void outsb(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsw
+#define outsw outsw
+static inline void outsw(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsl
+#define outsl outsl
+static inline void outsl(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insb_p
+#define insb_p insb_p
+static inline void insb_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insb(addr, buffer, count);
+}
+#endif
+
+#ifndef insw_p
+#define insw_p insw_p
+static inline void insw_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insw(addr, buffer, count);
+}
+#endif
+
+#ifndef insl_p
+#define insl_p insl_p
+static inline void insl_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insl(addr, buffer, count);
+}
+#endif
+
+#ifndef outsb_p
+#define outsb_p outsb_p
+static inline void outsb_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsb(addr, buffer, count);
+}
+#endif
+
+#ifndef outsw_p
+#define outsw_p outsw_p
+static inline void outsw_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsw(addr, buffer, count);
+}
+#endif
+
+#ifndef outsl_p
+#define outsl_p outsl_p
+static inline void outsl_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsl(addr, buffer, count);
+}
+#endif
+
+#ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioread8
+#define ioread8 ioread8
+static inline u8 ioread8(const volatile void __iomem *addr)
+{
+	return readb(addr);
+}
+#endif
+
+#ifndef ioread16
+#define ioread16 ioread16
+static inline u16 ioread16(const volatile void __iomem *addr)
+{
+	return readw(addr);
+}
+#endif
+
+#ifndef ioread32
+#define ioread32 ioread32
+static inline u32 ioread32(const volatile void __iomem *addr)
+{
+	return readl(addr);
+}
+#endif
+
+#ifndef iowrite8
+#define iowrite8 iowrite8
+static inline void iowrite8(u8 value, volatile void __iomem *addr)
+{
+	writeb(value, addr);
+}
+#endif
+
+#ifndef iowrite16
+#define iowrite16 iowrite16
+static inline void iowrite16(u16 value, volatile void __iomem *addr)
+{
+	writew(value, addr);
+}
+#endif
+
+#ifndef iowrite32
+#define iowrite32 iowrite32
+static inline void iowrite32(u32 value, volatile void __iomem *addr)
+{
+	writel(value, addr);
+}
+#endif
+
+#ifndef ioread16be
+#define ioread16be ioread16be
+static inline u16 ioread16be(const volatile void __iomem *addr)
+{
+	return __be16_to_cpu(__raw_readw(addr));
+}
+#endif
+
+#ifndef ioread32be
+#define ioread32be ioread32be
+static inline u32 ioread32be(const volatile void __iomem *addr)
+{
+	return __be32_to_cpu(__raw_readl(addr));
+}
+#endif
+
+#ifndef iowrite16be
+#define iowrite16be iowrite16be
+static inline void iowrite16be(u16 value, void volatile __iomem *addr)
+{
+	__raw_writew(__cpu_to_be16(value), addr);
+}
+#endif
+
+#ifndef iowrite32be
+#define iowrite32be iowrite32be
+static inline void iowrite32be(u32 value, volatile void __iomem *addr)
+{
+	__raw_writel(__cpu_to_be32(value), addr);
+}
+#endif
+
+#ifndef ioread8_rep
+#define ioread8_rep ioread8_rep
+static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
+			       unsigned int count)
+{
+	readsb(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread16_rep
+#define ioread16_rep ioread16_rep
+static inline void ioread16_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsw(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread32_rep
+#define ioread32_rep ioread32_rep
+static inline void ioread32_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsl(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite8_rep
+#define iowrite8_rep iowrite8_rep
+static inline void iowrite8_rep(volatile void __iomem *addr,
+				const void *buffer,
+				unsigned int count)
+{
+	writesb(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite16_rep
+#define iowrite16_rep iowrite16_rep
+static inline void iowrite16_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesw(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite32_rep
+#define iowrite32_rep iowrite32_rep
+static inline void iowrite32_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesl(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
+#ifdef __KERNEL__
+
+#include <linux/vmalloc.h>
+#define __io_virt(x) ((void __force *)(x))
+
+#ifndef CONFIG_GENERIC_IOMAP
+struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef pci_iounmap
+#define pci_iounmap pci_iounmap
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
+{
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+#ifndef virt_to_phys
+#define virt_to_phys virt_to_phys
+static inline unsigned long virt_to_phys(volatile void *address)
+{
+	return __pa((unsigned long)address);
+}
+#endif
+
+#ifndef phys_to_virt
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+#endif
+
+/*
+ * Change "struct page" to physical address.
+ *
+ * This implementation is for the no-MMU case only... if you have an MMU
+ * you'll need to provide your own definitions.
+ */
+
+#ifndef CONFIG_MMU
+#ifndef ioremap
+#define ioremap ioremap
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
+{
+	return (void __iomem *)(unsigned long)offset;
+}
+#endif
+
+#ifndef __ioremap
+#define __ioremap __ioremap
+static inline void __iomem *__ioremap(phys_addr_t offset, size_t size,
+				      unsigned long flags)
+{
+	return ioremap(offset, size);
+}
+#endif
+
+#ifndef ioremap_nocache
+#define ioremap_nocache ioremap_nocache
+static inline void __iomem *ioremap_nocache(phys_addr_t offset, size_t size)
+{
+	return ioremap(offset, size);
+}
+#endif
+
+#ifndef ioremap_wc
+#define ioremap_wc ioremap_wc
+static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
+{
+	return ioremap_nocache(offset, size);
+}
+#endif
+
+#ifndef iounmap
+#define iounmap iounmap
+static inline void iounmap(void __iomem *addr)
+{
+}
+#endif
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_HAS_IOPORT_MAP
+#ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioport_map
+#define ioport_map ioport_map
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return PCI_IOBASE + (port & IO_SPACE_LIMIT);
+}
+#endif
+
+#ifndef ioport_unmap
+#define ioport_unmap ioport_unmap
+static inline void ioport_unmap(void __iomem *p)
+{
+}
+#endif
+#else /* CONFIG_GENERIC_IOMAP */
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+extern void ioport_unmap(void __iomem *p);
+#endif /* CONFIG_GENERIC_IOMAP */
+#endif /* CONFIG_HAS_IOPORT_MAP */
+
+#ifndef xlate_dev_kmem_ptr
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+static inline void *xlate_dev_kmem_ptr(void *addr)
+{
+	return addr;
+}
+#endif
+
+#ifndef xlate_dev_mem_ptr
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+static inline void *xlate_dev_mem_ptr(phys_addr_t addr)
+{
+	return __va(addr);
+}
+#endif
+
+#ifndef unxlate_dev_mem_ptr
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
+{
+}
+#endif
+
+#ifdef CONFIG_VIRT_TO_BUS
+#ifndef virt_to_bus
+static inline unsigned long virt_to_bus(void *address)
+{
+	return (unsigned long)address;
+}
+
+static inline void *bus_to_virt(unsigned long address)
+{
+	return (void *)address;
+}
+#endif
+#endif
+
+#ifndef memset_io
+#define memset_io memset_io
+static inline void memset_io(volatile void __iomem *addr, int value,
+			     size_t size)
+{
+	memset(__io_virt(addr), value, size);
+}
+#endif
+
+#ifndef memcpy_fromio
+#define memcpy_fromio memcpy_fromio
+static inline void memcpy_fromio(void *buffer,
+				 const volatile void __iomem *addr,
+				 size_t size)
+{
+	memcpy(buffer, __io_virt(addr), size);
+}
+#endif
+
+#ifndef memcpy_toio
+#define memcpy_toio memcpy_toio
+static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
+			       size_t size)
+{
+	memcpy(__io_virt(addr), buffer, size);
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_GENERIC_IO_H */
diff --git a/include/asm-generic/ioctl.h b/include/asm-generic/ioctl.h
new file mode 100644
index 000000000..297fb0d7c
--- /dev/null
+++ b/include/asm-generic/ioctl.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_GENERIC_IOCTL_H
+#define _ASM_GENERIC_IOCTL_H
+
+#include <uapi/asm-generic/ioctl.h>
+
+#ifdef __CHECKER__
+#define _IOC_TYPECHECK(t) (sizeof(t))
+#else
+/* provoke compile error for invalid uses of size argument */
+extern unsigned int __invalid_size_argument_for_IOC;
+#define _IOC_TYPECHECK(t) \
+	((sizeof(t) == sizeof(t[1]) && \
+	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
+	  sizeof(t) : __invalid_size_argument_for_IOC)
+#endif
+
+#endif /* _ASM_GENERIC_IOCTL_H */
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
new file mode 100644
index 000000000..1b4101164
--- /dev/null
+++ b/include/asm-generic/iomap.h
@@ -0,0 +1,81 @@
+#ifndef __GENERIC_IO_H
+#define __GENERIC_IO_H
+
+#include <linux/linkage.h>
+#include <asm/byteorder.h>
+
+/*
+ * These are the "generic" interfaces for doing new-style
+ * memory-mapped or PIO accesses. Architectures may do
+ * their own arch-optimized versions, these just act as
+ * wrappers around the old-style IO register access functions:
+ * read[bwl]/write[bwl]/in[bwl]/out[bwl]
+ *
+ * Don't include this directly, include it from <asm/io.h>.
+ */
+
+/*
+ * Read/write from/to an (offsettable) iomem cookie. It might be a PIO
+ * access or a MMIO access, these functions don't care. The info is
+ * encoded in the hardware mapping set up by the mapping functions
+ * (or the cookie itself, depending on implementation and hw).
+ *
+ * The generic routines just encode the PIO/MMIO as part of the
+ * cookie, and coldly assume that the MMIO IO mappings are not
+ * in the low address range. Architectures for which this is not
+ * true can't use this generic implementation.
+ */
+extern unsigned int ioread8(void __iomem *);
+extern unsigned int ioread16(void __iomem *);
+extern unsigned int ioread16be(void __iomem *);
+extern unsigned int ioread32(void __iomem *);
+extern unsigned int ioread32be(void __iomem *);
+
+extern void iowrite8(u8, void __iomem *);
+extern void iowrite16(u16, void __iomem *);
+extern void iowrite16be(u16, void __iomem *);
+extern void iowrite32(u32, void __iomem *);
+extern void iowrite32be(u32, void __iomem *);
+
+/*
+ * "string" versions of the above. Note that they
+ * use native byte ordering for the accesses (on
+ * the assumption that IO and memory agree on a
+ * byte order, and CPU byteorder is irrelevant).
+ *
+ * They do _not_ update the port address. If you
+ * want MMIO that copies stuff laid out in MMIO
+ * memory across multiple ports, use "memcpy_toio()"
+ * and friends.
+ */
+extern void ioread8_rep(void __iomem *port, void *buf, unsigned long count);
+extern void ioread16_rep(void __iomem *port, void *buf, unsigned long count);
+extern void ioread32_rep(void __iomem *port, void *buf, unsigned long count);
+
+extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count);
+
+#ifdef CONFIG_HAS_IOPORT_MAP
+/* Create a virtual mapping cookie for an IO port range */
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+extern void ioport_unmap(void __iomem *);
+#endif
+
+#ifndef ARCH_HAS_IOREMAP_WC
+#define ioremap_wc ioremap_nocache
+#endif
+
+#ifdef CONFIG_PCI
+/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
+struct pci_dev;
+extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
+#elif defined(CONFIG_GENERIC_IOMAP)
+struct pci_dev;
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{ }
+#endif
+
+#include <asm-generic/pci_iomap.h>
+
+#endif
diff --git a/include/asm-generic/irq.h b/include/asm-generic/irq.h
new file mode 100644
index 000000000..b90ec0bc4
--- /dev/null
+++ b/include/asm-generic/irq.h
@@ -0,0 +1,18 @@
+#ifndef __ASM_GENERIC_IRQ_H
+#define __ASM_GENERIC_IRQ_H
+
+/*
+ * NR_IRQS is the upper bound of how many interrupts can be handled
+ * in the platform. It is used to size the static irq_map array,
+ * so don't make it too big.
+ */
+#ifndef NR_IRQS
+#define NR_IRQS 64
+#endif
+
+static inline int irq_canonicalize(int irq)
+{
+	return irq;
+}
+
+#endif /* __ASM_GENERIC_IRQ_H */
diff --git a/include/asm-generic/irq_regs.h b/include/asm-generic/irq_regs.h
new file mode 100644
index 000000000..6bf9355fa
--- /dev/null
+++ b/include/asm-generic/irq_regs.h
@@ -0,0 +1,37 @@
+/* Fallback per-CPU frame pointer holder
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_GENERIC_IRQ_REGS_H
+#define _ASM_GENERIC_IRQ_REGS_H
+
+#include <linux/percpu.h>
+
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack
+ */
+DECLARE_PER_CPU(struct pt_regs *, __irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+	return __this_cpu_read(__irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = __this_cpu_read(__irq_regs);
+	__this_cpu_write(__irq_regs, new_regs);
+	return old_regs;
+}
+
+#endif /* _ASM_GENERIC_IRQ_REGS_H */
diff --git a/include/asm-generic/irq_work.h b/include/asm-generic/irq_work.h
new file mode 100644
index 000000000..a44f452c6
--- /dev/null
+++ b/include/asm-generic/irq_work.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return false;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
+
diff --git a/include/asm-generic/irqflags.h b/include/asm-generic/irqflags.h
new file mode 100644
index 000000000..1f40d0024
--- /dev/null
+++ b/include/asm-generic/irqflags.h
@@ -0,0 +1,66 @@
+#ifndef __ASM_GENERIC_IRQFLAGS_H
+#define __ASM_GENERIC_IRQFLAGS_H
+
+/*
+ * All architectures should implement at least the first two functions,
+ * usually inline assembly will be the best way.
+ */
+#ifndef ARCH_IRQ_DISABLED
+#define ARCH_IRQ_DISABLED 0
+#define ARCH_IRQ_ENABLED 1
+#endif
+
+/* read interrupt enabled status */
+#ifndef arch_local_save_flags
+unsigned long arch_local_save_flags(void);
+#endif
+
+/* set interrupt enabled status */
+#ifndef arch_local_irq_restore
+void arch_local_irq_restore(unsigned long flags);
+#endif
+
+/* get status and disable interrupts */
+#ifndef arch_local_irq_save
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+	flags = arch_local_save_flags();
+	arch_local_irq_restore(ARCH_IRQ_DISABLED);
+	return flags;
+}
+#endif
+
+/* test flags */
+#ifndef arch_irqs_disabled_flags
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags == ARCH_IRQ_DISABLED;
+}
+#endif
+
+/* unconditionally enable interrupts */
+#ifndef arch_local_irq_enable
+static inline void arch_local_irq_enable(void)
+{
+	arch_local_irq_restore(ARCH_IRQ_ENABLED);
+}
+#endif
+
+/* unconditionally disable interrupts */
+#ifndef arch_local_irq_disable
+static inline void arch_local_irq_disable(void)
+{
+	arch_local_irq_restore(ARCH_IRQ_DISABLED);
+}
+#endif
+
+/* test hardware interrupt enable bit */
+#ifndef arch_irqs_disabled
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+#endif
+
+#endif /* __ASM_GENERIC_IRQFLAGS_H */
diff --git a/include/asm-generic/kdebug.h b/include/asm-generic/kdebug.h
new file mode 100644
index 000000000..d1814497b
--- /dev/null
+++ b/include/asm-generic/kdebug.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_GENERIC_KDEBUG_H
+#define _ASM_GENERIC_KDEBUG_H
+
+enum die_val {
+	DIE_UNUSED,
+	DIE_OOPS = 1,
+};
+
+#endif /* _ASM_GENERIC_KDEBUG_H */
diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h
new file mode 100644
index 000000000..90f99c74d
--- /dev/null
+++ b/include/asm-generic/kmap_types.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_GENERIC_KMAP_TYPES_H
+#define _ASM_GENERIC_KMAP_TYPES_H
+
+#ifdef __WITH_KM_FENCE
+# define KM_TYPE_NR 41
+#else
+# define KM_TYPE_NR 20
+#endif
+
+#endif
diff --git a/include/asm-generic/kvm_para.h b/include/asm-generic/kvm_para.h
new file mode 100644
index 000000000..fa25becbd
--- /dev/null
+++ b/include/asm-generic/kvm_para.h
@@ -0,0 +1,26 @@
+#ifndef _ASM_GENERIC_KVM_PARA_H
+#define _ASM_GENERIC_KVM_PARA_H
+
+#include <uapi/asm-generic/kvm_para.h>
+
+
+/*
+ * This function is used by architectures that support kvm to avoid issuing
+ * false soft lockup messages.
+ */
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+static inline bool kvm_para_available(void)
+{
+	return false;
+}
+
+#endif
diff --git a/include/asm-generic/libata-portmap.h b/include/asm-generic/libata-portmap.h
new file mode 100644
index 000000000..cf14f2ff4
--- /dev/null
+++ b/include/asm-generic/libata-portmap.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_GENERIC_LIBATA_PORTMAP_H
+#define __ASM_GENERIC_LIBATA_PORTMAP_H
+
+#define ATA_PRIMARY_IRQ(dev)	14
+#define ATA_SECONDARY_IRQ(dev)	15
+
+#endif
diff --git a/include/asm-generic/linkage.h b/include/asm-generic/linkage.h
new file mode 100644
index 000000000..fef7a01e5
--- /dev/null
+++ b/include/asm-generic/linkage.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_GENERIC_LINKAGE_H
+#define __ASM_GENERIC_LINKAGE_H
+/*
+ * linux/linkage.h provides reasonable defaults.
+ * an architecture can override them by providing its own version.
+ */
+
+#endif /* __ASM_GENERIC_LINKAGE_H */
diff --git a/include/asm-generic/local.h b/include/asm-generic/local.h
new file mode 100644
index 000000000..9ceb03b4f
--- /dev/null
+++ b/include/asm-generic/local.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_GENERIC_LOCAL_H
+#define _ASM_GENERIC_LOCAL_H
+
+#include <linux/percpu.h>
+#include <linux/atomic.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic_long_t.  Which is
+ * rather pointless.  The whole point behind local_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set((&(l)->a),(i))
+#define local_inc(l)	atomic_long_inc(&(l)->a)
+#define local_dec(l)	atomic_long_dec(&(l)->a)
+#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
+#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
+
+#define local_sub_and_test(i, l) atomic_long_sub_and_test((i), (&(l)->a))
+#define local_dec_and_test(l) atomic_long_dec_and_test(&(l)->a)
+#define local_inc_and_test(l) atomic_long_inc_and_test(&(l)->a)
+#define local_add_negative(i, l) atomic_long_add_negative((i), (&(l)->a))
+#define local_add_return(i, l) atomic_long_add_return((i), (&(l)->a))
+#define local_sub_return(i, l) atomic_long_sub_return((i), (&(l)->a))
+#define local_inc_return(l) atomic_long_inc_return(&(l)->a)
+
+#define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n))
+#define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n))
+#define local_add_unless(l, _a, u) atomic_long_add_unless((&(l)->a), (_a), (u))
+#define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local_inc(l)		local_set((l), local_read(l) + 1)
+#define __local_dec(l)		local_set((l), local_read(l) - 1)
+#define __local_add(i,l)	local_set((l), local_read(l) + (i))
+#define __local_sub(i,l)	local_set((l), local_read(l) - (i))
+
+#endif /* _ASM_GENERIC_LOCAL_H */
diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h
new file mode 100644
index 000000000..5980002b8
--- /dev/null
+++ b/include/asm-generic/local64.h
@@ -0,0 +1,96 @@
+#ifndef _ASM_GENERIC_LOCAL64_H
+#define _ASM_GENERIC_LOCAL64_H
+
+#include <linux/percpu.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic64_t.  Which is
+ * rather pointless.  The whole point behind local64_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local64_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+#if BITS_PER_LONG == 64
+
+#include <asm/local.h>
+
+typedef struct {
+	local_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ LOCAL_INIT(i) }
+
+#define local64_read(l)		local_read(&(l)->a)
+#define local64_set(l,i)	local_set((&(l)->a),(i))
+#define local64_inc(l)		local_inc(&(l)->a)
+#define local64_dec(l)		local_dec(&(l)->a)
+#define local64_add(i,l)	local_add((i),(&(l)->a))
+#define local64_sub(i,l)	local_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) local_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) local_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) local_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	local_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)	local_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	local_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#else /* BITS_PER_LONG != 64 */
+
+#include <linux/atomic.h>
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct {
+	atomic64_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local64_read(l)		atomic64_read(&(l)->a)
+#define local64_set(l,i)	atomic64_set((&(l)->a),(i))
+#define local64_inc(l)		atomic64_inc(&(l)->a)
+#define local64_dec(l)		atomic64_dec(&(l)->a)
+#define local64_add(i,l)	atomic64_add((i),(&(l)->a))
+#define local64_sub(i,l)	atomic64_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	atomic64_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)	atomic64_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	atomic64_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#endif /* BITS_PER_LONG != 64 */
+
+#endif /* _ASM_GENERIC_LOCAL64_H */
diff --git a/include/asm-generic/mcs_spinlock.h b/include/asm-generic/mcs_spinlock.h
new file mode 100644
index 000000000..10cd4ffc6
--- /dev/null
+++ b/include/asm-generic/mcs_spinlock.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MCS_SPINLOCK_H
+#define __ASM_MCS_SPINLOCK_H
+
+/*
+ * Architectures can define their own:
+ *
+ *   arch_mcs_spin_lock_contended(l)
+ *   arch_mcs_spin_unlock_contended(l)
+ *
+ * See kernel/locking/mcs_spinlock.c.
+ */
+
+#endif /* __ASM_MCS_SPINLOCK_H */
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
new file mode 100644
index 000000000..14909b0b9
--- /dev/null
+++ b/include/asm-generic/memory_model.h
@@ -0,0 +1,77 @@
+#ifndef __ASM_MEMORY_MODEL_H
+#define __ASM_MEMORY_MODEL_H
+
+#ifndef __ASSEMBLY__
+
+#if defined(CONFIG_FLATMEM)
+
+#ifndef ARCH_PFN_OFFSET
+#define ARCH_PFN_OFFSET		(0UL)
+#endif
+
+#elif defined(CONFIG_DISCONTIGMEM)
+
+#ifndef arch_pfn_to_nid
+#define arch_pfn_to_nid(pfn)	pfn_to_nid(pfn)
+#endif
+
+#ifndef arch_local_page_offset
+#define arch_local_page_offset(pfn, nid)	\
+	((pfn) - NODE_DATA(nid)->node_start_pfn)
+#endif
+
+#endif /* CONFIG_DISCONTIGMEM */
+
+/*
+ * supports 3 memory models.
+ */
+#if defined(CONFIG_FLATMEM)
+
+#define __pfn_to_page(pfn)	(mem_map + ((pfn) - ARCH_PFN_OFFSET))
+#define __page_to_pfn(page)	((unsigned long)((page) - mem_map) + \
+				 ARCH_PFN_OFFSET)
+#elif defined(CONFIG_DISCONTIGMEM)
+
+#define __pfn_to_page(pfn)			\
+({	unsigned long __pfn = (pfn);		\
+	unsigned long __nid = arch_pfn_to_nid(__pfn);  \
+	NODE_DATA(__nid)->node_mem_map + arch_local_page_offset(__pfn, __nid);\
+})
+
+#define __page_to_pfn(pg)						\
+({	const struct page *__pg = (pg);					\
+	struct pglist_data *__pgdat = NODE_DATA(page_to_nid(__pg));	\
+	(unsigned long)(__pg - __pgdat->node_mem_map) +			\
+	 __pgdat->node_start_pfn;					\
+})
+
+#elif defined(CONFIG_SPARSEMEM_VMEMMAP)
+
+/* memmap is virtually contiguous.  */
+#define __pfn_to_page(pfn)	(vmemmap + (pfn))
+#define __page_to_pfn(page)	(unsigned long)((page) - vmemmap)
+
+#elif defined(CONFIG_SPARSEMEM)
+/*
+ * Note: section's mem_map is encoded to reflect its start_pfn.
+ * section[i].section_mem_map == mem_map's address - start_pfn;
+ */
+#define __page_to_pfn(pg)					\
+({	const struct page *__pg = (pg);				\
+	int __sec = page_to_section(__pg);			\
+	(unsigned long)(__pg - __section_mem_map_addr(__nr_to_section(__sec)));	\
+})
+
+#define __pfn_to_page(pfn)				\
+({	unsigned long __pfn = (pfn);			\
+	struct mem_section *__sec = __pfn_to_section(__pfn);	\
+	__section_mem_map_addr(__sec) + __pfn;		\
+})
+#endif /* CONFIG_FLATMEM/DISCONTIGMEM/SPARSEMEM */
+
+#define page_to_pfn __page_to_pfn
+#define pfn_to_page __pfn_to_page
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
new file mode 100644
index 000000000..866aa461e
--- /dev/null
+++ b/include/asm-generic/mm_hooks.h
@@ -0,0 +1,29 @@
+/*
+ * Define generic no-op hooks for arch_dup_mmap, arch_exit_mmap
+ * and arch_unmap to be included in asm-FOO/mmu_context.h for any
+ * arch FOO which doesn't need to hook these.
+ */
+#ifndef _ASM_GENERIC_MM_HOOKS_H
+#define _ASM_GENERIC_MM_HOOKS_H
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
+#endif	/* _ASM_GENERIC_MM_HOOKS_H */
diff --git a/include/asm-generic/mmu.h b/include/asm-generic/mmu.h
new file mode 100644
index 000000000..0ed3f1cfb
--- /dev/null
+++ b/include/asm-generic/mmu.h
@@ -0,0 +1,19 @@
+#ifndef __ASM_GENERIC_MMU_H
+#define __ASM_GENERIC_MMU_H
+
+/*
+ * This is the mmu.h header for nommu implementations.
+ * Architectures with an MMU need something more complex.
+ */
+#ifndef __ASSEMBLY__
+typedef struct {
+	unsigned long		end_brk;
+
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long		exec_fdpic_loadmap;
+	unsigned long		interp_fdpic_loadmap;
+#endif
+} mm_context_t;
+#endif
+
+#endif /* __ASM_GENERIC_MMU_H */
diff --git a/include/asm-generic/mmu_context.h b/include/asm-generic/mmu_context.h
new file mode 100644
index 000000000..a7eec910b
--- /dev/null
+++ b/include/asm-generic/mmu_context.h
@@ -0,0 +1,45 @@
+#ifndef __ASM_GENERIC_MMU_CONTEXT_H
+#define __ASM_GENERIC_MMU_CONTEXT_H
+
+/*
+ * Generic hooks for NOMMU architectures, which do not need to do
+ * anything special here.
+ */
+
+#include <asm-generic/mm_hooks.h>
+
+struct task_struct;
+struct mm_struct;
+
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+			struct task_struct *tsk)
+{
+}
+
+static inline int init_new_context(struct task_struct *tsk,
+			struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+}
+
+static inline void deactivate_mm(struct task_struct *task,
+			struct mm_struct *mm)
+{
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+			struct mm_struct *next,
+			struct task_struct *tsk)
+{
+}
+
+static inline void activate_mm(struct mm_struct *prev_mm,
+			       struct mm_struct *next_mm)
+{
+}
+
+#endif /* __ASM_GENERIC_MMU_CONTEXT_H */
diff --git a/include/asm-generic/module.h b/include/asm-generic/module.h
new file mode 100644
index 000000000..14dc41d18
--- /dev/null
+++ b/include/asm-generic/module.h
@@ -0,0 +1,48 @@
+#ifndef __ASM_GENERIC_MODULE_H
+#define __ASM_GENERIC_MODULE_H
+
+/*
+ * Many architectures just need a simple module
+ * loader without arch specific data.
+ */
+#ifndef CONFIG_HAVE_MOD_ARCH_SPECIFIC
+struct mod_arch_specific
+{
+};
+#endif
+
+#ifdef CONFIG_64BIT
+#define Elf_Shdr	Elf64_Shdr
+#define Elf_Phdr	Elf64_Phdr
+#define Elf_Sym		Elf64_Sym
+#define Elf_Dyn		Elf64_Dyn
+#define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Addr	Elf64_Addr
+#ifdef CONFIG_MODULES_USE_ELF_REL
+#define Elf_Rel		Elf64_Rel
+#endif
+#ifdef CONFIG_MODULES_USE_ELF_RELA
+#define Elf_Rela	Elf64_Rela
+#endif
+#define ELF_R_TYPE(X)	ELF64_R_TYPE(X)
+#define ELF_R_SYM(X)	ELF64_R_SYM(X)
+
+#else /* CONFIG_64BIT */
+
+#define Elf_Shdr	Elf32_Shdr
+#define Elf_Phdr	Elf32_Phdr
+#define Elf_Sym		Elf32_Sym
+#define Elf_Dyn		Elf32_Dyn
+#define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Addr	Elf32_Addr
+#ifdef CONFIG_MODULES_USE_ELF_REL
+#define Elf_Rel		Elf32_Rel
+#endif
+#ifdef CONFIG_MODULES_USE_ELF_RELA
+#define Elf_Rela	Elf32_Rela
+#endif
+#define ELF_R_TYPE(X)	ELF32_R_TYPE(X)
+#define ELF_R_SYM(X)	ELF32_R_SYM(X)
+#endif
+
+#endif /* __ASM_GENERIC_MODULE_H */
diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h
new file mode 100644
index 000000000..61c58d887
--- /dev/null
+++ b/include/asm-generic/msi.h
@@ -0,0 +1,32 @@
+#ifndef __ASM_GENERIC_MSI_H
+#define __ASM_GENERIC_MSI_H
+
+#include <linux/types.h>
+
+#ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS
+# define NUM_MSI_ALLOC_SCRATCHPAD_REGS	2
+#endif
+
+struct msi_desc;
+
+/**
+ * struct msi_alloc_info - Default structure for MSI interrupt allocation.
+ * @desc:	Pointer to msi descriptor
+ * @hwirq:	Associated hw interrupt number in the domain
+ * @scratchpad:	Storage for implementation specific scratch data
+ *
+ * Architectures can provide their own implementation by not including
+ * asm-generic/msi.h into their arch specific header file.
+ */
+typedef struct msi_alloc_info {
+	struct msi_desc			*desc;
+	irq_hw_number_t			hwirq;
+	union {
+		unsigned long		ul;
+		void			*ptr;
+	} scratchpad[NUM_MSI_ALLOC_SCRATCHPAD_REGS];
+} msi_alloc_info_t;
+
+#define GENERIC_MSI_DOMAIN_OPS		1
+
+#endif
diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
new file mode 100644
index 000000000..d4f9fb4e5
--- /dev/null
+++ b/include/asm-generic/mutex-dec.h
@@ -0,0 +1,88 @@
+/*
+ * include/asm-generic/mutex-dec.h
+ *
+ * Generic implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ */
+#ifndef _ASM_GENERIC_MUTEX_DEC_H
+#define _ASM_GENERIC_MUTEX_DEC_H
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function MUST leave the value lower than
+ * 1 even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		fail_fn(count);
+}
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *
+ * Change the count from 1 to a value lower than 1. This function returns 0
+ * if the fastpath succeeds, or -1 otherwise.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count)
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return -1;
+	return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, then the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_inc_return(count) <= 0))
+		fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock()		1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ *
+ * If the architecture has no effective trylock variant, it should call the
+ * <fail_fn> spinlock-based trylock variant unconditionally.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+		return 1;
+	return 0;
+}
+
+#endif
diff --git a/include/asm-generic/mutex-null.h b/include/asm-generic/mutex-null.h
new file mode 100644
index 000000000..61069ed33
--- /dev/null
+++ b/include/asm-generic/mutex-null.h
@@ -0,0 +1,19 @@
+/*
+ * include/asm-generic/mutex-null.h
+ *
+ * Generic implementation of the mutex fastpath, based on NOP :-)
+ *
+ * This is used by the mutex-debugging infrastructure, but it can also
+ * be used by architectures that (for whatever reason) want to use the
+ * spinlock based slowpath.
+ */
+#ifndef _ASM_GENERIC_MUTEX_NULL_H
+#define _ASM_GENERIC_MUTEX_NULL_H
+
+#define __mutex_fastpath_lock(count, fail_fn)		fail_fn(count)
+#define __mutex_fastpath_lock_retval(count)		(-1)
+#define __mutex_fastpath_unlock(count, fail_fn)		fail_fn(count)
+#define __mutex_fastpath_trylock(count, fail_fn)	fail_fn(count)
+#define __mutex_slowpath_needs_to_unlock()		1
+
+#endif
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
new file mode 100644
index 000000000..f169ec064
--- /dev/null
+++ b/include/asm-generic/mutex-xchg.h
@@ -0,0 +1,116 @@
+/*
+ * include/asm-generic/mutex-xchg.h
+ *
+ * Generic implementation of the mutex fastpath, based on xchg().
+ *
+ * NOTE: An xchg based implementation might be less optimal than an atomic
+ *       decrement/increment based implementation. If your architecture
+ *       has a reasonable atomic dec/inc then you should probably use
+ *	 asm-generic/mutex-dec.h instead, or you could open-code an
+ *	 optimized version in asm/mutex.h.
+ */
+#ifndef _ASM_GENERIC_MUTEX_XCHG_H
+#define _ASM_GENERIC_MUTEX_XCHG_H
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_xchg(count, 0) != 1))
+		/*
+		 * We failed to acquire the lock, so mark it contended
+		 * to ensure that any waiting tasks are woken up by the
+		 * unlock slow path.
+		 */
+		if (likely(atomic_xchg(count, -1) != 1))
+			fail_fn(count);
+}
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *
+ * Change the count from 1 to a value lower than 1. This function returns 0
+ * if the fastpath succeeds, or -1 otherwise.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count)
+{
+	if (unlikely(atomic_xchg(count, 0) != 1))
+		if (likely(atomic_xchg(count, -1) != 1))
+			return -1;
+	return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <function>
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than one.
+ * If the implementation sets it to a value of lower than one, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_xchg(count, 1) != 0))
+		fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock()		0
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: spinlock based trylock implementation
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ *
+ * If the architecture has no effective trylock variant, it should call the
+ * <fail_fn> spinlock-based trylock variant unconditionally.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int prev = atomic_xchg(count, 0);
+
+	if (unlikely(prev < 0)) {
+		/*
+		 * The lock was marked contended so we must restore that
+		 * state. If while doing so we get back a prev value of 1
+		 * then we just own it.
+		 *
+		 * [ In the rare case of the mutex going to 1, to 0, to -1
+		 *   and then back to 0 in this few-instructions window,
+		 *   this has the potential to trigger the slowpath for the
+		 *   owner's unlock path needlessly, but that's not a problem
+		 *   in practice. ]
+		 */
+		prev = atomic_xchg(count, prev);
+		if (prev < 0)
+			prev = 0;
+	}
+
+	return prev;
+}
+
+#endif
diff --git a/include/asm-generic/mutex.h b/include/asm-generic/mutex.h
new file mode 100644
index 000000000..fe91ab502
--- /dev/null
+++ b/include/asm-generic/mutex.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_GENERIC_MUTEX_H
+#define __ASM_GENERIC_MUTEX_H
+/*
+ * Pull in the generic implementation for the mutex fastpath,
+ * which is a reasonable default on many architectures.
+ */
+
+#include <asm-generic/mutex-dec.h>
+#endif /* __ASM_GENERIC_MUTEX_H */
diff --git a/include/asm-generic/page.h b/include/asm-generic/page.h
new file mode 100644
index 000000000..37d1fe289
--- /dev/null
+++ b/include/asm-generic/page.h
@@ -0,0 +1,103 @@
+#ifndef __ASM_GENERIC_PAGE_H
+#define __ASM_GENERIC_PAGE_H
+/*
+ * Generic page.h implementation, for NOMMU architectures.
+ * This provides the dummy definitions for the memory management.
+ */
+
+#ifdef CONFIG_MMU
+#error need to prove a real asm/page.h
+#endif
+
+
+/* PAGE_SHIFT determines the page size */
+
+#define PAGE_SHIFT	12
+#ifdef __ASSEMBLY__
+#define PAGE_SIZE	(1 << PAGE_SHIFT)
+#else
+#define PAGE_SIZE	(1UL << PAGE_SHIFT)
+#endif
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#include <asm/setup.h>
+
+#ifndef __ASSEMBLY__
+
+#define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
+#define free_user_page(page, addr)	free_page(addr)
+
+#define clear_page(page)	memset((page), 0, PAGE_SIZE)
+#define copy_page(to,from)	memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct {
+	unsigned long pte;
+} pte_t;
+typedef struct {
+	unsigned long pmd[16];
+} pmd_t;
+typedef struct {
+	unsigned long pgd;
+} pgd_t;
+typedef struct {
+	unsigned long pgprot;
+} pgprot_t;
+typedef struct page *pgtable_t;
+
+#define pte_val(x)	((x).pte)
+#define pmd_val(x)	((&x)->pmd[0])
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pte(x)	((pte_t) { (x) } )
+#define __pmd(x)	((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+extern unsigned long memory_start;
+extern unsigned long memory_end;
+
+#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_KERNEL_RAM_BASE_ADDRESS
+#define PAGE_OFFSET		(CONFIG_KERNEL_RAM_BASE_ADDRESS)
+#else
+#define PAGE_OFFSET		(0)
+#endif
+
+#ifndef ARCH_PFN_OFFSET
+#define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
+#endif
+
+#ifndef __ASSEMBLY__
+
+#define __va(x) ((void *)((unsigned long) (x)))
+#define __pa(x) ((unsigned long) (x))
+
+#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#define virt_to_page(addr)	pfn_to_page(virt_to_pfn(addr))
+#define page_to_virt(page)	pfn_to_virt(page_to_pfn(page))
+
+#ifndef page_to_phys
+#define page_to_phys(page)      ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+#endif
+
+#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && ((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
+
+#define	virt_addr_valid(kaddr)	(((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
+				((void *)(kaddr) < (void *)memory_end))
+
+#endif /* __ASSEMBLY__ */
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+#endif /* __ASM_GENERIC_PAGE_H */
diff --git a/include/asm-generic/param.h b/include/asm-generic/param.h
new file mode 100644
index 000000000..04e715bcc
--- /dev/null
+++ b/include/asm-generic/param.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_GENERIC_PARAM_H
+#define __ASM_GENERIC_PARAM_H
+
+#include <uapi/asm-generic/param.h>
+
+# undef HZ
+# define HZ		CONFIG_HZ	/* Internal kernel timer frequency */
+# define USER_HZ	100		/* some user interfaces are */
+# define CLOCKS_PER_SEC	(USER_HZ)       /* in "ticks" like times() */
+#endif /* __ASM_GENERIC_PARAM_H */
diff --git a/include/asm-generic/parport.h b/include/asm-generic/parport.h
new file mode 100644
index 000000000..2c9f9d433
--- /dev/null
+++ b/include/asm-generic/parport.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_GENERIC_PARPORT_H
+#define __ASM_GENERIC_PARPORT_H
+
+/*
+ * An ISA bus may have i8255 parallel ports at well-known
+ * locations in the I/O space, which are scanned by
+ * parport_pc_find_isa_ports.
+ *
+ * Without ISA support, the driver will only attach
+ * to devices on the PCI bus.
+ */
+
+static int parport_pc_find_isa_ports(int autoirq, int autodma);
+static int parport_pc_find_nonpci_ports(int autoirq, int autodma)
+{
+#ifdef CONFIG_ISA
+	return parport_pc_find_isa_ports(autoirq, autodma);
+#else
+	return 0;
+#endif
+}
+
+#endif /* __ASM_GENERIC_PARPORT_H */
diff --git a/include/asm-generic/pci-bridge.h b/include/asm-generic/pci-bridge.h
new file mode 100644
index 000000000..20db2e5a0
--- /dev/null
+++ b/include/asm-generic/pci-bridge.h
@@ -0,0 +1,74 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_GENERIC_PCI_BRIDGE_H
+#define _ASM_GENERIC_PCI_BRIDGE_H
+
+#ifdef __KERNEL__
+
+enum {
+	/* Force re-assigning all resources (ignore firmware
+	 * setup completely)
+	 */
+	PCI_REASSIGN_ALL_RSRC	= 0x00000001,
+
+	/* Re-assign all bus numbers */
+	PCI_REASSIGN_ALL_BUS	= 0x00000002,
+
+	/* Do not try to assign, just use existing setup */
+	PCI_PROBE_ONLY		= 0x00000004,
+
+	/* Don't bother with ISA alignment unless the bridge has
+	 * ISA forwarding enabled
+	 */
+	PCI_CAN_SKIP_ISA_ALIGN	= 0x00000008,
+
+	/* Enable domain numbers in /proc */
+	PCI_ENABLE_PROC_DOMAINS	= 0x00000010,
+	/* ... except for domain 0 */
+	PCI_COMPAT_DOMAIN_0	= 0x00000020,
+
+	/* PCIe downstream ports are bridges that normally lead to only a
+	 * device 0, but if this is set, we scan all possible devices, not
+	 * just device 0.
+	 */
+	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,
+};
+
+#ifdef CONFIG_PCI
+extern unsigned int pci_flags;
+
+static inline void pci_set_flags(int flags)
+{
+	pci_flags = flags;
+}
+
+static inline void pci_add_flags(int flags)
+{
+	pci_flags |= flags;
+}
+
+static inline void pci_clear_flags(int flags)
+{
+	pci_flags &= ~flags;
+}
+
+static inline int pci_has_flag(int flag)
+{
+	return pci_flags & flag;
+}
+#else
+static inline void pci_set_flags(int flags) { }
+static inline void pci_add_flags(int flags) { }
+static inline void pci_clear_flags(int flags) { }
+static inline int pci_has_flag(int flag)
+{
+	return 0;
+}
+#endif	/* CONFIG_PCI */
+
+#endif	/* __KERNEL__ */
+#endif	/* _ASM_GENERIC_PCI_BRIDGE_H */
diff --git a/include/asm-generic/pci-dma-compat.h b/include/asm-generic/pci-dma-compat.h
new file mode 100644
index 000000000..c110843fc
--- /dev/null
+++ b/include/asm-generic/pci-dma-compat.h
@@ -0,0 +1,124 @@
+/* include this file if the platform implements the dma_ DMA Mapping API
+ * and wants to provide the pci_ DMA Mapping API in terms of it */
+
+#ifndef _ASM_GENERIC_PCI_DMA_COMPAT_H
+#define _ASM_GENERIC_PCI_DMA_COMPAT_H
+
+#include <linux/dma-mapping.h>
+
+static inline int
+pci_dma_supported(struct pci_dev *hwdev, u64 mask)
+{
+	return dma_supported(hwdev == NULL ? NULL : &hwdev->dev, mask);
+}
+
+static inline void *
+pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
+		     dma_addr_t *dma_handle)
+{
+	return dma_alloc_coherent(hwdev == NULL ? NULL : &hwdev->dev, size, dma_handle, GFP_ATOMIC);
+}
+
+static inline void *
+pci_zalloc_consistent(struct pci_dev *hwdev, size_t size,
+		      dma_addr_t *dma_handle)
+{
+	return dma_zalloc_coherent(hwdev == NULL ? NULL : &hwdev->dev,
+				   size, dma_handle, GFP_ATOMIC);
+}
+
+static inline void
+pci_free_consistent(struct pci_dev *hwdev, size_t size,
+		    void *vaddr, dma_addr_t dma_handle)
+{
+	dma_free_coherent(hwdev == NULL ? NULL : &hwdev->dev, size, vaddr, dma_handle);
+}
+
+static inline dma_addr_t
+pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction)
+{
+	return dma_map_single(hwdev == NULL ? NULL : &hwdev->dev, ptr, size, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
+		 size_t size, int direction)
+{
+	dma_unmap_single(hwdev == NULL ? NULL : &hwdev->dev, dma_addr, size, (enum dma_data_direction)direction);
+}
+
+static inline dma_addr_t
+pci_map_page(struct pci_dev *hwdev, struct page *page,
+	     unsigned long offset, size_t size, int direction)
+{
+	return dma_map_page(hwdev == NULL ? NULL : &hwdev->dev, page, offset, size, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address,
+	       size_t size, int direction)
+{
+	dma_unmap_page(hwdev == NULL ? NULL : &hwdev->dev, dma_address, size, (enum dma_data_direction)direction);
+}
+
+static inline int
+pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
+	   int nents, int direction)
+{
+	return dma_map_sg(hwdev == NULL ? NULL : &hwdev->dev, sg, nents, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
+	     int nents, int direction)
+{
+	dma_unmap_sg(hwdev == NULL ? NULL : &hwdev->dev, sg, nents, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle,
+		    size_t size, int direction)
+{
+	dma_sync_single_for_cpu(hwdev == NULL ? NULL : &hwdev->dev, dma_handle, size, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle,
+		    size_t size, int direction)
+{
+	dma_sync_single_for_device(hwdev == NULL ? NULL : &hwdev->dev, dma_handle, size, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg,
+		int nelems, int direction)
+{
+	dma_sync_sg_for_cpu(hwdev == NULL ? NULL : &hwdev->dev, sg, nelems, (enum dma_data_direction)direction);
+}
+
+static inline void
+pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg,
+		int nelems, int direction)
+{
+	dma_sync_sg_for_device(hwdev == NULL ? NULL : &hwdev->dev, sg, nelems, (enum dma_data_direction)direction);
+}
+
+static inline int
+pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr)
+{
+	return dma_mapping_error(&pdev->dev, dma_addr);
+}
+
+#ifdef CONFIG_PCI
+static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	return dma_set_mask(&dev->dev, mask);
+}
+
+static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	return dma_set_coherent_mask(&dev->dev, mask);
+}
+#endif
+
+#endif
diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h
new file mode 100644
index 000000000..e80a0495e
--- /dev/null
+++ b/include/asm-generic/pci.h
@@ -0,0 +1,37 @@
+/*
+ * linux/include/asm-generic/pci.h
+ *
+ *  Copyright (C) 2003 Russell King
+ */
+#ifndef _ASM_GENERIC_PCI_H
+#define _ASM_GENERIC_PCI_H
+
+static inline struct resource *
+pcibios_select_root(struct pci_dev *pdev, struct resource *res)
+{
+	struct resource *root = NULL;
+
+	if (res->flags & IORESOURCE_IO)
+		root = &ioport_resource;
+	if (res->flags & IORESOURCE_MEM)
+		root = &iomem_resource;
+
+	return root;
+}
+
+#ifndef HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return channel ? 15 : 14;
+}
+#endif /* HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ */
+
+/*
+ * By default, assume that no iommu is in use and that the PCI
+ * space is mapped to address physical 0.
+ */
+#ifndef PCI_DMA_BUS_IS_PHYS
+#define PCI_DMA_BUS_IS_PHYS	(1)
+#endif
+
+#endif /* _ASM_GENERIC_PCI_H */
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
new file mode 100644
index 000000000..7389c8711
--- /dev/null
+++ b/include/asm-generic/pci_iomap.h
@@ -0,0 +1,45 @@
+/* Generic I/O port emulation, based on MN10300 code
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_PCI_IOMAP_H
+#define __ASM_GENERIC_PCI_IOMAP_H
+
+struct pci_dev;
+#ifdef CONFIG_PCI
+/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
+				     unsigned long offset,
+				     unsigned long maxlen);
+/* Create a virtual mapping cookie for a port on a given PCI device.
+ * Do not call this directly, it exists to make it easier for architectures
+ * to override */
+#ifdef CONFIG_NO_GENERIC_PCI_IOPORT_MAP
+extern void __iomem *__pci_ioport_map(struct pci_dev *dev, unsigned long port,
+				      unsigned int nr);
+#else
+#define __pci_ioport_map(dev, port, nr) ioport_map((port), (nr))
+#endif
+
+#elif defined(CONFIG_GENERIC_PCI_IOMAP)
+static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
+{
+	return NULL;
+}
+
+static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
+					    unsigned long offset,
+					    unsigned long maxlen)
+{
+	return NULL;
+}
+#endif
+
+#endif /* __ASM_GENERIC_IO_H */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
new file mode 100644
index 000000000..4d9f233c4
--- /dev/null
+++ b/include/asm-generic/percpu.h
@@ -0,0 +1,420 @@
+#ifndef _ASM_GENERIC_PERCPU_H_
+#define _ASM_GENERIC_PERCPU_H_
+
+#include <linux/compiler.h>
+#include <linux/threads.h>
+#include <linux/percpu-defs.h>
+
+#ifdef CONFIG_SMP
+
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ *
+ * Most arches use the __per_cpu_offset array for those offsets but
+ * some arches have their own ways of determining the offset (x86_64, s390).
+ */
+#ifndef __per_cpu_offset
+extern unsigned long __per_cpu_offset[NR_CPUS];
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+#endif
+
+/*
+ * Determine the offset for the currently active processor.
+ * An arch may define __my_cpu_offset to provide a more effective
+ * means of obtaining the offset to the per cpu variables of the
+ * current processor.
+ */
+#ifndef __my_cpu_offset
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#endif
+#ifdef CONFIG_DEBUG_PREEMPT
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+/*
+ * Arch may define arch_raw_cpu_ptr() to provide more efficient address
+ * translations for raw_cpu_ptr().
+ */
+#ifndef arch_raw_cpu_ptr
+#define arch_raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#endif
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void setup_per_cpu_areas(void);
+#endif
+
+#endif	/* SMP */
+
+#ifndef PER_CPU_BASE_SECTION
+#ifdef CONFIG_SMP
+#define PER_CPU_BASE_SECTION ".data..percpu"
+#else
+#define PER_CPU_BASE_SECTION ".data"
+#endif
+#endif
+
+#ifndef PER_CPU_ATTRIBUTES
+#define PER_CPU_ATTRIBUTES
+#endif
+
+#ifndef PER_CPU_DEF_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
+#endif
+
+#define raw_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+} while (0)
+
+#define raw_cpu_generic_add_return(pcp, val)				\
+({									\
+	raw_cpu_add(pcp, val);						\
+	raw_cpu_read(pcp);						\
+})
+
+#define raw_cpu_generic_xchg(pcp, nval)					\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	__ret;								\
+})
+
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	__ret;								\
+})
+
+#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+({									\
+	int __ret = 0;							\
+	if (raw_cpu_read(pcp1) == (oval1) &&				\
+			 raw_cpu_read(pcp2)  == (oval2)) {		\
+		raw_cpu_write(pcp1, nval1);				\
+		raw_cpu_write(pcp2, nval2);				\
+		__ret = 1;						\
+	}								\
+	(__ret);							\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	preempt_disable();						\
+	__ret = *this_cpu_ptr(&(pcp));					\
+	preempt_enable();						\
+	__ret;								\
+})
+
+#define this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+	raw_local_irq_restore(__flags);					\
+} while (0)
+
+#define this_cpu_generic_add_return(pcp, val)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	raw_cpu_add(pcp, val);						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_xchg(pcp, nval)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int __ret;							\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#ifndef raw_cpu_read_1
+#define raw_cpu_read_1(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_2
+#define raw_cpu_read_2(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_4
+#define raw_cpu_read_4(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_8
+#define raw_cpu_read_8(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+
+#ifndef raw_cpu_write_1
+#define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_2
+#define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_4
+#define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_8
+#define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+
+#ifndef raw_cpu_add_1
+#define raw_cpu_add_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_2
+#define raw_cpu_add_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_4
+#define raw_cpu_add_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_8
+#define raw_cpu_add_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+
+#ifndef raw_cpu_and_1
+#define raw_cpu_and_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_2
+#define raw_cpu_and_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_4
+#define raw_cpu_and_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_8
+#define raw_cpu_and_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef raw_cpu_or_1
+#define raw_cpu_or_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_2
+#define raw_cpu_or_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_4
+#define raw_cpu_or_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_8
+#define raw_cpu_or_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+
+#ifndef raw_cpu_add_return_1
+#define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_2
+#define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_4
+#define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_8
+#define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+
+#ifndef raw_cpu_xchg_1
+#define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_2
+#define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_4
+#define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_8
+#define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+
+#ifndef raw_cpu_cmpxchg_1
+#define raw_cpu_cmpxchg_1(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_2
+#define raw_cpu_cmpxchg_2(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_4
+#define raw_cpu_cmpxchg_4(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_8
+#define raw_cpu_cmpxchg_8(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+
+#ifndef raw_cpu_cmpxchg_double_1
+#define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_2
+#define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_4
+#define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_8
+#define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+
+#ifndef this_cpu_read_1
+#define this_cpu_read_1(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_2
+#define this_cpu_read_2(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_4
+#define this_cpu_read_4(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_8
+#define this_cpu_read_8(pcp)		this_cpu_generic_read(pcp)
+#endif
+
+#ifndef this_cpu_write_1
+#define this_cpu_write_1(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_2
+#define this_cpu_write_2(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_4
+#define this_cpu_write_4(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_8
+#define this_cpu_write_8(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+
+#ifndef this_cpu_add_1
+#define this_cpu_add_1(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_2
+#define this_cpu_add_2(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_4
+#define this_cpu_add_4(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_8
+#define this_cpu_add_8(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+
+#ifndef this_cpu_and_1
+#define this_cpu_and_1(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_2
+#define this_cpu_and_2(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_4
+#define this_cpu_and_4(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_8
+#define this_cpu_and_8(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef this_cpu_or_1
+#define this_cpu_or_1(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_2
+#define this_cpu_or_2(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_4
+#define this_cpu_or_4(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_8
+#define this_cpu_or_8(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+
+#ifndef this_cpu_add_return_1
+#define this_cpu_add_return_1(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_2
+#define this_cpu_add_return_2(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_4
+#define this_cpu_add_return_4(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_8
+#define this_cpu_add_return_8(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+
+#ifndef this_cpu_xchg_1
+#define this_cpu_xchg_1(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_2
+#define this_cpu_xchg_2(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_4
+#define this_cpu_xchg_4(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_8
+#define this_cpu_xchg_8(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+
+#ifndef this_cpu_cmpxchg_1
+#define this_cpu_cmpxchg_1(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_2
+#define this_cpu_cmpxchg_2(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_4
+#define this_cpu_cmpxchg_4(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_8
+#define this_cpu_cmpxchg_8(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+
+#ifndef this_cpu_cmpxchg_double_1
+#define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_2
+#define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_4
+#define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_8
+#define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+
+#endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
new file mode 100644
index 000000000..9e429d08b
--- /dev/null
+++ b/include/asm-generic/pgalloc.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_GENERIC_PGALLOC_H
+#define __ASM_GENERIC_PGALLOC_H
+/*
+ * an empty file is enough for a nommu architecture
+ */
+#ifdef CONFIG_MMU
+#error need to implement an architecture specific asm/pgalloc.h
+#endif
+
+#define check_pgt_cache()          do { } while (0)
+
+#endif /* __ASM_GENERIC_PGALLOC_H */
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
new file mode 100644
index 000000000..725612b79
--- /dev/null
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -0,0 +1,69 @@
+#ifndef _PGTABLE_NOPMD_H
+#define _PGTABLE_NOPMD_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm-generic/pgtable-nopud.h>
+
+struct mm_struct;
+
+#define __PAGETABLE_PMD_FOLDED
+
+/*
+ * Having the pmd type consist of a pud gets the size right, and allows
+ * us to conceptually access the pud entry that this pmd is folded into
+ * without casting.
+ */
+typedef struct { pud_t pud; } pmd_t;
+
+#define PMD_SHIFT	PUD_SHIFT
+#define PTRS_PER_PMD	1
+#define PMD_SIZE  	(1UL << PMD_SHIFT)
+#define PMD_MASK  	(~(PMD_SIZE-1))
+
+/*
+ * The "pud_xxx()" functions here are trivial for a folded two-level
+ * setup: the pmd is never bad, and a pmd always exists (as it's folded
+ * into the pud entry)
+ */
+static inline int pud_none(pud_t pud)		{ return 0; }
+static inline int pud_bad(pud_t pud)		{ return 0; }
+static inline int pud_present(pud_t pud)	{ return 1; }
+static inline void pud_clear(pud_t *pud)	{ }
+#define pmd_ERROR(pmd)				(pud_ERROR((pmd).pud))
+
+#define pud_populate(mm, pmd, pte)		do { } while (0)
+
+/*
+ * (pmds are folded into puds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pud(pudptr, pudval)			set_pmd((pmd_t *)(pudptr), (pmd_t) { pudval })
+
+static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
+{
+	return (pmd_t *)pud;
+}
+
+#define pmd_val(x)				(pud_val((x).pud))
+#define __pmd(x)				((pmd_t) { __pud(x) } )
+
+#define pud_page(pud)				(pmd_page((pmd_t){ pud }))
+#define pud_page_vaddr(pud)			(pmd_page_vaddr((pmd_t){ pud }))
+
+/*
+ * allocating and freeing a pmd is trivial: the 1-entry pmd is
+ * inside the pud, so has no extra memory associated with it.
+ */
+#define pmd_alloc_one(mm, address)		NULL
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+}
+#define __pmd_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  pmd_addr_end
+#define pmd_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _PGTABLE_NOPMD_H */
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
new file mode 100644
index 000000000..810431d83
--- /dev/null
+++ b/include/asm-generic/pgtable-nopud.h
@@ -0,0 +1,61 @@
+#ifndef _PGTABLE_NOPUD_H
+#define _PGTABLE_NOPUD_H
+
+#ifndef __ASSEMBLY__
+
+#define __PAGETABLE_PUD_FOLDED
+
+/*
+ * Having the pud type consist of a pgd gets the size right, and allows
+ * us to conceptually access the pgd entry that this pud is folded into
+ * without casting.
+ */
+typedef struct { pgd_t pgd; } pud_t;
+
+#define PUD_SHIFT	PGDIR_SHIFT
+#define PTRS_PER_PUD	1
+#define PUD_SIZE  	(1UL << PUD_SHIFT)
+#define PUD_MASK  	(~(PUD_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pud is never bad, and a pud always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t *pgd)	{ }
+#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
+
+#define pgd_populate(mm, pgd, pud)		do { } while (0)
+/*
+ * (puds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval)			set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+
+static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
+{
+	return (pud_t *)pgd;
+}
+
+#define pud_val(x)				(pgd_val((x).pgd))
+#define __pud(x)				((pud_t) { __pgd(x) } )
+
+#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
+#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
+
+/*
+ * allocating and freeing a pud is trivial: the 1-entry pud is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define pud_alloc_one(mm, address)		NULL
+#define pud_free(mm, x)				do { } while (0)
+#define __pud_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  pud_addr_end
+#define pud_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOPUD_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
new file mode 100644
index 000000000..9cf36952a
--- /dev/null
+++ b/include/asm-generic/pgtable.h
@@ -0,0 +1,743 @@
+#ifndef _ASM_GENERIC_PGTABLE_H
+#define _ASM_GENERIC_PGTABLE_H
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_MMU
+
+#include <linux/mm_types.h>
+#include <linux/bug.h>
+#include <linux/errno.h>
+
+#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
+	CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#endif
+
+/*
+ * On almost all architectures and configurations, 0 can be used as the
+ * upper ceiling to free_pgtables(): on many architectures it has the same
+ * effect as using TASK_SIZE.  However, there is one configuration which
+ * must impose a more careful limit, to avoid freeing kernel pgtables.
+ */
+#ifndef USER_PGTABLES_CEILING
+#define USER_PGTABLES_CEILING	0UL
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp,
+				 pmd_t entry, int dirty);
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	pte_t pte = *ptep;
+	int r = 1;
+	if (!pte_young(pte))
+		r = 0;
+	else
+		set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
+	return r;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+	int r = 1;
+	if (!pmd_young(pmd))
+		r = 0;
+	else
+		set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
+	return r;
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	BUG();
+	return 0;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+int ptep_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pte_t *ptep);
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pmd_t *pmdp);
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address,
+				       pte_t *ptep)
+{
+	pte_t pte = *ptep;
+	pte_clear(mm, address, ptep);
+	return pte;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+				       unsigned long address,
+				       pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+	pmd_clear(pmdp);
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp,
+					    int full)
+{
+	return pmdp_get_and_clear(mm, address, pmdp);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long address, pte_t *ptep,
+					    int full)
+{
+	pte_t pte;
+	pte = ptep_get_and_clear(mm, address, ptep);
+	return pte;
+}
+#endif
+
+/*
+ * Some architectures may be able to avoid expensive synchronization
+ * primitives when modifications are made to PTE's which are already
+ * not present, or in the process of an address space destruction.
+ */
+#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
+static inline void pte_clear_not_present_full(struct mm_struct *mm,
+					      unsigned long address,
+					      pte_t *ptep,
+					      int full)
+{
+	pte_clear(mm, address, ptep);
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
+extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep);
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
+extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pmd_t *pmdp);
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
+struct mm_struct;
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
+{
+	pte_t old_pte = *ptep;
+	set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	pmd_t old_pmd = *pmdp;
+	set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	BUG();
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+#endif
+
+#ifndef __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t pte_a, pte_t pte_b)
+{
+	return pte_val(pte_a) == pte_val(pte_b);
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTE_UNUSED
+/*
+ * Some architectures provide facilities to virtualization guests
+ * so that they can flag allocated pages as unused. This allows the
+ * host to transparently reclaim unused pages. This function returns
+ * whether the pte's page is unused.
+ */
+static inline int pte_unused(pte_t pte)
+{
+	return 0;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMD_SAME
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return pmd_val(pmd_a) == pmd_val(pmd_b);
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	BUG();
+	return 0;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
+#define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
+#endif
+
+#ifndef __HAVE_ARCH_MOVE_PTE
+#define move_pte(pte, prot, old_addr, new_addr)	(pte)
+#endif
+
+#ifndef pte_accessible
+# define pte_accessible(mm, pte)	((void)(pte), 1)
+#endif
+
+#ifndef flush_tlb_fix_spurious_fault
+#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#endif
+
+#ifndef pgprot_noncached
+#define pgprot_noncached(prot)	(prot)
+#endif
+
+#ifndef pgprot_writecombine
+#define pgprot_writecombine pgprot_noncached
+#endif
+
+#ifndef pgprot_device
+#define pgprot_device pgprot_noncached
+#endif
+
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+		newprot = pgprot_noncached(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+		newprot = pgprot_writecombine(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
+		newprot = pgprot_device(newprot);
+	return newprot;
+}
+#endif
+
+/*
+ * When walking page tables, get the address of the next boundary,
+ * or the end address of the range if that comes earlier.  Although no
+ * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
+ */
+
+#define pgd_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+#ifndef pud_addr_end
+#define pud_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+#endif
+
+#ifndef pmd_addr_end
+#define pmd_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+#endif
+
+/*
+ * When walking page tables, we usually want to skip any p?d_none entries;
+ * and any p?d_bad entries - reporting the error before resetting to none.
+ * Do the tests inline, but report and clear the bad entry in mm/memory.c.
+ */
+void pgd_clear_bad(pgd_t *);
+void pud_clear_bad(pud_t *);
+void pmd_clear_bad(pmd_t *);
+
+static inline int pgd_none_or_clear_bad(pgd_t *pgd)
+{
+	if (pgd_none(*pgd))
+		return 1;
+	if (unlikely(pgd_bad(*pgd))) {
+		pgd_clear_bad(pgd);
+		return 1;
+	}
+	return 0;
+}
+
+static inline int pud_none_or_clear_bad(pud_t *pud)
+{
+	if (pud_none(*pud))
+		return 1;
+	if (unlikely(pud_bad(*pud))) {
+		pud_clear_bad(pud);
+		return 1;
+	}
+	return 0;
+}
+
+static inline int pmd_none_or_clear_bad(pmd_t *pmd)
+{
+	if (pmd_none(*pmd))
+		return 1;
+	if (unlikely(pmd_bad(*pmd))) {
+		pmd_clear_bad(pmd);
+		return 1;
+	}
+	return 0;
+}
+
+static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
+					     unsigned long addr,
+					     pte_t *ptep)
+{
+	/*
+	 * Get the current pte state, but zero it out to make it
+	 * non-present, preventing the hardware from asynchronously
+	 * updating it.
+	 */
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
+					     unsigned long addr,
+					     pte_t *ptep, pte_t pte)
+{
+	/*
+	 * The pte is non-present, so there's no hardware state to
+	 * preserve.
+	 */
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+/*
+ * Start a pte protection read-modify-write transaction, which
+ * protects against asynchronous hardware modifications to the pte.
+ * The intention is not to prevent the hardware from making pte
+ * updates, but to prevent any updates it may make from being lost.
+ *
+ * This does not protect against other software modifications of the
+ * pte; the appropriate pte lock must be held over the transation.
+ *
+ * Note that this interface is intended to be batchable, meaning that
+ * ptep_modify_prot_commit may not actually update the pte, but merely
+ * queue the update to be done at some later time.  The update must be
+ * actually committed before the pte lock is released, however.
+ */
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
+					   unsigned long addr,
+					   pte_t *ptep)
+{
+	return __ptep_modify_prot_start(mm, addr, ptep);
+}
+
+/*
+ * Commit an update to a pte, leaving any hardware-controlled bits in
+ * the PTE unmodified.
+ */
+static inline void ptep_modify_prot_commit(struct mm_struct *mm,
+					   unsigned long addr,
+					   pte_t *ptep, pte_t pte)
+{
+	__ptep_modify_prot_commit(mm, addr, ptep, pte);
+}
+#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
+#endif /* CONFIG_MMU */
+
+/*
+ * A facility to provide lazy MMU batching.  This allows PTE updates and
+ * page invalidations to be delayed until a call to leave lazy MMU mode
+ * is issued.  Some architectures may benefit from doing this, and it is
+ * beneficial for both shadow and direct mode hypervisors, which may batch
+ * the PTE updates which happen during this window.  Note that using this
+ * interface requires that read hazards be removed from the code.  A read
+ * hazard could result in the direct mode hypervisor case, since the actual
+ * write to the page tables may not yet have taken place, so reads though
+ * a raw PTE pointer after it has been modified are not guaranteed to be
+ * up to date.  This mode can only be entered and left under the protection of
+ * the page table locks for all page tables which may be modified.  In the UP
+ * case, this is required so that preemption is disabled, and in the SMP case,
+ * it must synchronize the delayed page table writes properly on other CPUs.
+ */
+#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+#define arch_enter_lazy_mmu_mode()	do {} while (0)
+#define arch_leave_lazy_mmu_mode()	do {} while (0)
+#define arch_flush_lazy_mmu_mode()	do {} while (0)
+#endif
+
+/*
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
+ */
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev)	do {} while (0)
+#endif
+
+#ifndef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline int pte_soft_dirty(pte_t pte)
+{
+	return 0;
+}
+
+static inline int pmd_soft_dirty(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return pte;
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	return 0;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return pte;
+}
+#endif
+
+#ifndef __HAVE_PFNMAP_TRACKING
+/*
+ * Interfaces that can be used by architecture code to keep track of
+ * memory type of pfn mappings specified by the remap_pfn_range,
+ * vm_insert_pfn.
+ */
+
+/*
+ * track_pfn_remap is called when a _new_ pfn mapping is being established
+ * by remap_pfn_range() for physical range indicated by pfn and size.
+ */
+static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
+				  unsigned long pfn, unsigned long addr,
+				  unsigned long size)
+{
+	return 0;
+}
+
+/*
+ * track_pfn_insert is called when a _new_ single pfn is established
+ * by vm_insert_pfn().
+ */
+static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
+				   unsigned long pfn)
+{
+	return 0;
+}
+
+/*
+ * track_pfn_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ */
+static inline int track_pfn_copy(struct vm_area_struct *vma)
+{
+	return 0;
+}
+
+/*
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case pfn, size are zero).
+ */
+static inline void untrack_pfn(struct vm_area_struct *vma,
+			       unsigned long pfn, unsigned long size)
+{
+}
+#else
+extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
+			   unsigned long pfn, unsigned long addr,
+			   unsigned long size);
+extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
+			    unsigned long pfn);
+extern int track_pfn_copy(struct vm_area_struct *vma);
+extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
+			unsigned long size);
+#endif
+
+#ifdef CONFIG_UKSM
+static inline int is_uksm_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long uksm_zero_pfn;
+        return pfn == uksm_zero_pfn;
+}
+#else
+static inline int is_uksm_zero_pfn(unsigned long pfn)
+{
+        return 0;
+}
+#endif
+
+#ifdef __HAVE_COLOR_ZERO_PAGE
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT) || is_uksm_zero_pfn(pfn);
+}
+
+#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	return (pfn == zero_pfn) || (is_uksm_zero_pfn(pfn));
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	extern unsigned long zero_pfn;
+	return zero_pfn;
+}
+#endif
+
+#ifdef CONFIG_MMU
+
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return 0;
+}
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	return 0;
+}
+#ifndef __HAVE_ARCH_PMD_WRITE
+static inline int pmd_write(pmd_t pmd)
+{
+	BUG();
+	return 0;
+}
+#endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#ifndef pmd_read_atomic
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	/*
+	 * Depend on compiler for an atomic pmd read. NOTE: this is
+	 * only going to work, if the pmdval_t isn't larger than
+	 * an unsigned long.
+	 */
+	return *pmdp;
+}
+#endif
+
+#ifndef pmd_move_must_withdraw
+static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
+					 spinlock_t *old_pmd_ptl)
+{
+	/*
+	 * With split pmd lock we also need to move preallocated
+	 * PTE page table if new_pmd is on different PMD page table.
+	 */
+	return new_pmd_ptl != old_pmd_ptl;
+}
+#endif
+
+/*
+ * This function is meant to be used by sites walking pagetables with
+ * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
+ * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
+ * into a null pmd and the transhuge page fault can convert a null pmd
+ * into an hugepmd or into a regular pmd (if the hugepage allocation
+ * fails). While holding the mmap_sem in read mode the pmd becomes
+ * stable and stops changing under us only if it's not null and not a
+ * transhuge pmd. When those races occurs and this function makes a
+ * difference vs the standard pmd_none_or_clear_bad, the result is
+ * undefined so behaving like if the pmd was none is safe (because it
+ * can return none anyway). The compiler level barrier() is critically
+ * important to compute the two checks atomically on the same pmdval.
+ *
+ * For 32bit kernels with a 64bit large pmd_t this automatically takes
+ * care of reading the pmd atomically to avoid SMP race conditions
+ * against pmd_populate() when the mmap_sem is hold for reading by the
+ * caller (a special atomic read not done by "gcc" as in the generic
+ * version above, is also needed when THP is disabled because the page
+ * fault can populate the pmd from under us).
+ */
+static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
+{
+	pmd_t pmdval = pmd_read_atomic(pmd);
+	/*
+	 * The barrier will stabilize the pmdval in a register or on
+	 * the stack so that it will stop changing under the code.
+	 *
+	 * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
+	 * pmd_read_atomic is allowed to return a not atomic pmdval
+	 * (for example pointing to an hugepage that has never been
+	 * mapped in the pmd). The below checks will only care about
+	 * the low part of the pmd with 32bit PAE x86 anyway, with the
+	 * exception of pmd_none(). So the important thing is that if
+	 * the low part of the pmd is found null, the high part will
+	 * be also null or the pmd_none() check below would be
+	 * confused.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+	if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
+		return 1;
+	if (unlikely(pmd_bad(pmdval))) {
+		pmd_clear_bad(pmd);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * This is a noop if Transparent Hugepage Support is not built into
+ * the kernel. Otherwise it is equivalent to
+ * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
+ * places that already verified the pmd is not none and they want to
+ * walk ptes while holding the mmap sem in read mode (write mode don't
+ * need this). If THP is not enabled, the pmd can't go away under the
+ * code even if MADV_DONTNEED runs, but if THP is enabled we need to
+ * run a pmd_trans_unstable before walking the ptes after
+ * split_huge_page_pmd returns (because it may have run when the pmd
+ * become null, but then a page fault can map in a THP and not a
+ * regular page).
+ */
+static inline int pmd_trans_unstable(pmd_t *pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return pmd_none_or_trans_huge_or_clear_bad(pmd);
+#else
+	return 0;
+#endif
+}
+
+#ifndef CONFIG_NUMA_BALANCING
+/*
+ * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
+ * the only case the kernel cares is for NUMA balancing and is only ever set
+ * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
+ * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * is the responsibility of the caller to distinguish between PROT_NONE
+ * protections and NUMA hinting fault protections.
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return 0;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return 0;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
+int pud_clear_huge(pud_t *pud);
+int pmd_clear_huge(pmd_t *pmd);
+#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int pud_clear_huge(pud_t *pud)
+{
+	return 0;
+}
+static inline int pmd_clear_huge(pmd_t *pmd)
+{
+	return 0;
+}
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
+
+#endif /* !__ASSEMBLY__ */
+
+#ifndef io_remap_pfn_range
+#define io_remap_pfn_range remap_pfn_range
+#endif
+
+#endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
new file mode 100644
index 000000000..eb6f9e6c3
--- /dev/null
+++ b/include/asm-generic/preempt.h
@@ -0,0 +1,89 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <linux/thread_info.h>
+
+#define PREEMPT_ENABLED	(0)
+
+static __always_inline int preempt_count(void)
+{
+	return current_thread_info()->preempt_count;
+}
+
+static __always_inline int *preempt_count_ptr(void)
+{
+	return &current_thread_info()->preempt_count;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	*preempt_count_ptr() = pc;
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+} while (0)
+
+static __always_inline void set_preempt_need_resched(void)
+{
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return false;
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	*preempt_count_ptr() += val;
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	*preempt_count_ptr() -= val;
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	/*
+	 * Because of load-store architectures cannot do per-cpu atomic
+	 * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+	 * lost.
+	 */
+	return !--*preempt_count_ptr() && tif_need_resched();
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(void)
+{
+	return unlikely(!preempt_count() && tif_need_resched());
+}
+
+#ifdef CONFIG_PREEMPT
+extern asmlinkage void preempt_schedule(void);
+#define __preempt_schedule() preempt_schedule()
+
+#ifdef CONFIG_CONTEXT_TRACKING
+extern asmlinkage void preempt_schedule_context(void);
+#define __preempt_schedule_context() preempt_schedule_context()
+#endif
+#endif /* CONFIG_PREEMPT */
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/include/asm-generic/ptrace.h b/include/asm-generic/ptrace.h
new file mode 100644
index 000000000..82e674f6b
--- /dev/null
+++ b/include/asm-generic/ptrace.h
@@ -0,0 +1,74 @@
+/*
+ * Common low level (register) ptrace helpers
+ *
+ * Copyright 2004-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __ASM_GENERIC_PTRACE_H__
+#define __ASM_GENERIC_PTRACE_H__
+
+#ifndef __ASSEMBLY__
+
+/* Helpers for working with the instruction pointer */
+#ifndef GET_IP
+#define GET_IP(regs) ((regs)->pc)
+#endif
+#ifndef SET_IP
+#define SET_IP(regs, val) (GET_IP(regs) = (val))
+#endif
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return GET_IP(regs);
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+                                           unsigned long val)
+{
+	SET_IP(regs, val);
+}
+
+#ifndef profile_pc
+#define profile_pc(regs) instruction_pointer(regs)
+#endif
+
+/* Helpers for working with the user stack pointer */
+#ifndef GET_USP
+#define GET_USP(regs) ((regs)->usp)
+#endif
+#ifndef SET_USP
+#define SET_USP(regs, val) (GET_USP(regs) = (val))
+#endif
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return GET_USP(regs);
+}
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+                                          unsigned long val)
+{
+	SET_USP(regs, val);
+}
+
+/* Helpers for working with the frame pointer */
+#ifndef GET_FP
+#define GET_FP(regs) ((regs)->fp)
+#endif
+#ifndef SET_FP
+#define SET_FP(regs, val) (GET_FP(regs) = (val))
+#endif
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return GET_FP(regs);
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+                                     unsigned long val)
+{
+	SET_FP(regs, val);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
new file mode 100644
index 000000000..6383d54bf
--- /dev/null
+++ b/include/asm-generic/qrwlock.h
@@ -0,0 +1,166 @@
+/*
+ * Queue read/write lock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QRWLOCK_H
+#define __ASM_GENERIC_QRWLOCK_H
+
+#include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
+#include <asm-generic/qrwlock_types.h>
+
+/*
+ * Writer states & reader shift and bias
+ */
+#define	_QW_WAITING	1		/* A writer is waiting	   */
+#define	_QW_LOCKED	0xff		/* A writer holds the lock */
+#define	_QW_WMASK	0xff		/* Writer mask		   */
+#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define _QR_BIAS	(1U << _QR_SHIFT)
+
+/*
+ * External function declarations
+ */
+extern void queue_read_lock_slowpath(struct qrwlock *lock);
+extern void queue_write_lock_slowpath(struct qrwlock *lock);
+
+/**
+ * queue_read_can_lock- would read_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_read_can_lock(struct qrwlock *lock)
+{
+	return !(atomic_read(&lock->cnts) & _QW_WMASK);
+}
+
+/**
+ * queue_write_can_lock- would write_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_write_can_lock(struct qrwlock *lock)
+{
+	return !atomic_read(&lock->cnts);
+}
+
+/**
+ * queue_read_trylock - try to acquire read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_read_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (likely(!(cnts & _QW_WMASK))) {
+		cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts);
+		if (likely(!(cnts & _QW_WMASK)))
+			return 1;
+		atomic_sub(_QR_BIAS, &lock->cnts);
+	}
+	return 0;
+}
+
+/**
+ * queue_write_trylock - try to acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_write_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (unlikely(cnts))
+		return 0;
+
+	return likely(atomic_cmpxchg(&lock->cnts,
+				     cnts, cnts | _QW_LOCKED) == cnts);
+}
+/**
+ * queue_read_lock - acquire read lock of a queue rwlock
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline void queue_read_lock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_add_return(_QR_BIAS, &lock->cnts);
+	if (likely(!(cnts & _QW_WMASK)))
+		return;
+
+	/* The slowpath will decrement the reader count, if necessary. */
+	queue_read_lock_slowpath(lock);
+}
+
+/**
+ * queue_write_lock - acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_lock(struct qrwlock *lock)
+{
+	/* Optimize for the unfair lock case where the fair flag is 0. */
+	if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)
+		return;
+
+	queue_write_lock_slowpath(lock);
+}
+
+/**
+ * queue_read_unlock - release read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_read_unlock(struct qrwlock *lock)
+{
+	/*
+	 * Atomically decrement the reader count
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QR_BIAS, &lock->cnts);
+}
+
+#ifndef queue_write_unlock
+/**
+ * queue_write_unlock - release write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_unlock(struct qrwlock *lock)
+{
+	/*
+	 * If the writer field is atomic, it can be cleared directly.
+	 * Otherwise, an atomic subtraction will be used to clear it.
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QW_LOCKED, &lock->cnts);
+}
+#endif
+
+/*
+ * Remapping rwlock architecture specific functions to the corresponding
+ * queue rwlock functions.
+ */
+#define arch_read_can_lock(l)	queue_read_can_lock(l)
+#define arch_write_can_lock(l)	queue_write_can_lock(l)
+#define arch_read_lock(l)	queue_read_lock(l)
+#define arch_write_lock(l)	queue_write_lock(l)
+#define arch_read_trylock(l)	queue_read_trylock(l)
+#define arch_write_trylock(l)	queue_write_trylock(l)
+#define arch_read_unlock(l)	queue_read_unlock(l)
+#define arch_write_unlock(l)	queue_write_unlock(l)
+
+#endif /* __ASM_GENERIC_QRWLOCK_H */
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
new file mode 100644
index 000000000..4d76f24df
--- /dev/null
+++ b/include/asm-generic/qrwlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_GENERIC_QRWLOCK_TYPES_H
+#define __ASM_GENERIC_QRWLOCK_TYPES_H
+
+#include <linux/types.h>
+#include <asm/spinlock_types.h>
+
+/*
+ * The queue read/write lock data structure
+ */
+
+typedef struct qrwlock {
+	atomic_t		cnts;
+	arch_spinlock_t		lock;
+} arch_rwlock_t;
+
+#define	__ARCH_RW_LOCK_UNLOCKED {		\
+	.cnts = ATOMIC_INIT(0),			\
+	.lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+}
+
+#endif /* __ASM_GENERIC_QRWLOCK_TYPES_H */
diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
new file mode 100644
index 000000000..5e752b959
--- /dev/null
+++ b/include/asm-generic/resource.h
@@ -0,0 +1,30 @@
+#ifndef _ASM_GENERIC_RESOURCE_H
+#define _ASM_GENERIC_RESOURCE_H
+
+#include <uapi/asm-generic/resource.h>
+
+
+/*
+ * boot-time rlimit defaults for the init task:
+ */
+#define INIT_RLIMITS							\
+{									\
+	[RLIMIT_CPU]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_FSIZE]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_DATA]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_STACK]		= {       _STK_LIM,  RLIM_INFINITY },	\
+	[RLIMIT_CORE]		= {              0,  RLIM_INFINITY },	\
+	[RLIMIT_RSS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_NPROC]		= {              0,              0 },	\
+	[RLIMIT_NOFILE]		= {   INR_OPEN_CUR,   INR_OPEN_MAX },	\
+	[RLIMIT_MEMLOCK]	= {    MLOCK_LIMIT,    MLOCK_LIMIT },	\
+	[RLIMIT_AS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_LOCKS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+	[RLIMIT_SIGPENDING]	= { 		0,	       0 },	\
+	[RLIMIT_MSGQUEUE]	= {   MQ_BYTES_MAX,   MQ_BYTES_MAX },	\
+	[RLIMIT_NICE]		= { 0, 0 },				\
+	[RLIMIT_RTPRIO]		= { 0, 0 },				\
+	[RLIMIT_RTTIME]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
+}
+
+#endif
diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
new file mode 100644
index 000000000..fa86f240c
--- /dev/null
+++ b/include/asm-generic/rtc.h
@@ -0,0 +1,218 @@
+/* 
+ * include/asm-generic/rtc.h
+ *
+ * Author: Tom Rini <trini@mvista.com>
+ *
+ * Based on:
+ * drivers/char/rtc.c
+ *
+ * Please read the COPYING file for all license details.
+ */
+
+#ifndef __ASM_RTC_H__
+#define __ASM_RTC_H__
+
+#include <linux/mc146818rtc.h>
+#include <linux/rtc.h>
+#include <linux/bcd.h>
+#include <linux/delay.h>
+
+#define RTC_PIE 0x40		/* periodic interrupt enable */
+#define RTC_AIE 0x20		/* alarm interrupt enable */
+#define RTC_UIE 0x10		/* update-finished interrupt enable */
+
+/* some dummy definitions */
+#define RTC_BATT_BAD 0x100	/* battery bad */
+#define RTC_SQWE 0x08		/* enable square-wave output */
+#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
+#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
+#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
+
+/*
+ * Returns true if a clock update is in progress
+ */
+static inline unsigned char rtc_is_updating(void)
+{
+	unsigned char uip;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return uip;
+}
+
+static inline unsigned int __get_rtc_time(struct rtc_time *time)
+{
+	unsigned char ctrl;
+	unsigned long flags;
+
+#ifdef CONFIG_MACH_DECSTATION
+	unsigned int real_year;
+#endif
+
+	/*
+	 * read RTC once any update in progress is done. The update
+	 * can take just over 2ms. We wait 20ms. There is no need to
+	 * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP.
+	 * If you need to know *exactly* when a second has started, enable
+	 * periodic update complete interrupts, (via ioctl) and then 
+	 * immediately read /dev/rtc which will block until you get the IRQ.
+	 * Once the read clears, read the RTC time (again via ioctl). Easy.
+	 */
+	if (rtc_is_updating())
+		mdelay(20);
+
+	/*
+	 * Only the values that we read from the RTC are set. We leave
+	 * tm_wday, tm_yday and tm_isdst untouched. Even though the
+	 * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated
+	 * by the RTC when initially set to a non-zero value.
+	 */
+	spin_lock_irqsave(&rtc_lock, flags);
+	time->tm_sec = CMOS_READ(RTC_SECONDS);
+	time->tm_min = CMOS_READ(RTC_MINUTES);
+	time->tm_hour = CMOS_READ(RTC_HOURS);
+	time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH);
+	time->tm_mon = CMOS_READ(RTC_MONTH);
+	time->tm_year = CMOS_READ(RTC_YEAR);
+#ifdef CONFIG_MACH_DECSTATION
+	real_year = CMOS_READ(RTC_DEC_YEAR);
+#endif
+	ctrl = CMOS_READ(RTC_CONTROL);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
+	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+	{
+		time->tm_sec = bcd2bin(time->tm_sec);
+		time->tm_min = bcd2bin(time->tm_min);
+		time->tm_hour = bcd2bin(time->tm_hour);
+		time->tm_mday = bcd2bin(time->tm_mday);
+		time->tm_mon = bcd2bin(time->tm_mon);
+		time->tm_year = bcd2bin(time->tm_year);
+	}
+
+#ifdef CONFIG_MACH_DECSTATION
+	time->tm_year += real_year - 72;
+#endif
+
+	/*
+	 * Account for differences between how the RTC uses the values
+	 * and how they are defined in a struct rtc_time;
+	 */
+	if (time->tm_year <= 69)
+		time->tm_year += 100;
+
+	time->tm_mon--;
+
+	return RTC_24H;
+}
+
+#ifndef get_rtc_time
+#define get_rtc_time	__get_rtc_time
+#endif
+
+/* Set the current date and time in the real time clock. */
+static inline int __set_rtc_time(struct rtc_time *time)
+{
+	unsigned long flags;
+	unsigned char mon, day, hrs, min, sec;
+	unsigned char save_control, save_freq_select;
+	unsigned int yrs;
+#ifdef CONFIG_MACH_DECSTATION
+	unsigned int real_yrs, leap_yr;
+#endif
+
+	yrs = time->tm_year;
+	mon = time->tm_mon + 1;   /* tm_mon starts at zero */
+	day = time->tm_mday;
+	hrs = time->tm_hour;
+	min = time->tm_min;
+	sec = time->tm_sec;
+
+	if (yrs > 255)	/* They are unsigned */
+		return -EINVAL;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+#ifdef CONFIG_MACH_DECSTATION
+	real_yrs = yrs;
+	leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) ||
+			!((yrs + 1900) % 400));
+	yrs = 72;
+
+	/*
+	 * We want to keep the year set to 73 until March
+	 * for non-leap years, so that Feb, 29th is handled
+	 * correctly.
+	 */
+	if (!leap_yr && mon < 3) {
+		real_yrs--;
+		yrs = 73;
+	}
+#endif
+	/* These limits and adjustments are independent of
+	 * whether the chip is in binary mode or not.
+	 */
+	if (yrs > 169) {
+		spin_unlock_irqrestore(&rtc_lock, flags);
+		return -EINVAL;
+	}
+
+	if (yrs >= 100)
+		yrs -= 100;
+
+	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY)
+	    || RTC_ALWAYS_BCD) {
+		sec = bin2bcd(sec);
+		min = bin2bcd(min);
+		hrs = bin2bcd(hrs);
+		day = bin2bcd(day);
+		mon = bin2bcd(mon);
+		yrs = bin2bcd(yrs);
+	}
+
+	save_control = CMOS_READ(RTC_CONTROL);
+	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+	CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+#ifdef CONFIG_MACH_DECSTATION
+	CMOS_WRITE(real_yrs, RTC_DEC_YEAR);
+#endif
+	CMOS_WRITE(yrs, RTC_YEAR);
+	CMOS_WRITE(mon, RTC_MONTH);
+	CMOS_WRITE(day, RTC_DAY_OF_MONTH);
+	CMOS_WRITE(hrs, RTC_HOURS);
+	CMOS_WRITE(min, RTC_MINUTES);
+	CMOS_WRITE(sec, RTC_SECONDS);
+
+	CMOS_WRITE(save_control, RTC_CONTROL);
+	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
+	return 0;
+}
+
+#ifndef set_rtc_time
+#define set_rtc_time	__set_rtc_time
+#endif
+
+static inline unsigned int get_rtc_ss(void)
+{
+	struct rtc_time h;
+
+	get_rtc_time(&h);
+	return h.tm_sec;
+}
+
+static inline int get_rtc_pll(struct rtc_pll_info *pll)
+{
+	return -EINVAL;
+}
+static inline int set_rtc_pll(struct rtc_pll_info *pll)
+{
+	return -EINVAL;
+}
+
+#endif /* __ASM_RTC_H__ */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
new file mode 100644
index 000000000..d48bf5a95
--- /dev/null
+++ b/include/asm-generic/rwsem.h
@@ -0,0 +1,132 @@
+#ifndef _ASM_GENERIC_RWSEM_H
+#define _ASM_GENERIC_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
+#ifdef __KERNEL__
+
+/*
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
+ * Adapted largely from include/asm-i386/rwsem.h
+ * by Paul Mackerras <paulus@samba.org>.
+ */
+
+/*
+ * the semaphore definition
+ */
+#ifdef CONFIG_64BIT
+# define RWSEM_ACTIVE_MASK		0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000L
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0))
+		rwsem_down_read_failed(sem);
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	while ((tmp = sem->count) >= 0) {
+		if (tmp == cmpxchg(&sem->count, tmp,
+				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_t *)&sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		rwsem_down_write_failed(sem);
+}
+
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	__down_write_nested(sem, 0);
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+		      RWSEM_ACTIVE_WRITE_BIAS);
+	return tmp == RWSEM_UNLOCKED_VALUE;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_dec_return((atomic_long_t *)&sem->count);
+	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+				 (atomic_long_t *)&sem->count) < 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
+{
+	atomic_long_add(delta, (atomic_long_t *)&sem->count);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS,
+				     (atomic_long_t *)&sem->count);
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
+{
+	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
+}
+
+#endif	/* __KERNEL__ */
+#endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/asm-generic/scatterlist.h b/include/asm-generic/scatterlist.h
new file mode 100644
index 000000000..5de07355f
--- /dev/null
+++ b/include/asm-generic/scatterlist.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_GENERIC_SCATTERLIST_H
+#define __ASM_GENERIC_SCATTERLIST_H
+
+#include <linux/types.h>
+
+struct scatterlist {
+#ifdef CONFIG_DEBUG_SG
+	unsigned long	sg_magic;
+#endif
+	unsigned long	page_link;
+	unsigned int	offset;
+	unsigned int	length;
+	dma_addr_t	dma_address;
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+	unsigned int	dma_length;
+#endif
+};
+
+/*
+ * These macros should be used after a dma_map_sg call has been done
+ * to get bus addresses of each of the SG entries and their lengths.
+ * You should only work with the number of sg entries pci_map_sg
+ * returns, or alternatively stop on the first sg_dma_len(sg) which
+ * is 0.
+ */
+#define sg_dma_address(sg)	((sg)->dma_address)
+
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+#define sg_dma_len(sg)		((sg)->dma_length)
+#else
+#define sg_dma_len(sg)		((sg)->length)
+#endif
+
+#endif /* __ASM_GENERIC_SCATTERLIST_H */
diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
new file mode 100644
index 000000000..c9ccafa0d
--- /dev/null
+++ b/include/asm-generic/seccomp.h
@@ -0,0 +1,32 @@
+/*
+ * include/asm-generic/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_GENERIC_SECCOMP_H
+#define _ASM_GENERIC_SECCOMP_H
+
+#include <linux/unistd.h>
+
+#if defined(CONFIG_COMPAT) && !defined(__NR_seccomp_read_32)
+#define __NR_seccomp_read_32		__NR_read
+#define __NR_seccomp_write_32		__NR_write
+#define __NR_seccomp_exit_32		__NR_exit
+#ifndef __NR_seccomp_sigreturn_32
+#define __NR_seccomp_sigreturn_32	__NR_rt_sigreturn
+#endif
+#endif /* CONFIG_COMPAT && ! already defined */
+
+#define __NR_seccomp_read		__NR_read
+#define __NR_seccomp_write		__NR_write
+#define __NR_seccomp_exit		__NR_exit
+#ifndef __NR_seccomp_sigreturn
+#define __NR_seccomp_sigreturn		__NR_rt_sigreturn
+#endif
+
+#endif /* _ASM_GENERIC_SECCOMP_H */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
new file mode 100644
index 000000000..b58fd667f
--- /dev/null
+++ b/include/asm-generic/sections.h
@@ -0,0 +1,66 @@
+#ifndef _ASM_GENERIC_SECTIONS_H_
+#define _ASM_GENERIC_SECTIONS_H_
+
+/* References to section boundaries */
+
+#include <linux/compiler.h>
+
+/*
+ * Usage guidelines:
+ * _text, _data: architecture specific, don't use them in arch-independent code
+ * [_stext, _etext]: contains .text.* sections, may also contain .rodata.*
+ *                   and/or .init.* sections
+ * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.*
+ *                   and/or .init.* sections.
+ * [__start_rodata, __end_rodata]: contains .rodata.* sections
+ * [__init_begin, __init_end]: contains .init.* sections, but .init.text.*
+ *                   may be out of this range on some architectures.
+ * [_sinittext, _einittext]: contains .init.text.* sections
+ * [__bss_start, __bss_stop]: contains BSS sections
+ *
+ * Following global variables are optional and may be unavailable on some
+ * architectures and/or kernel configurations.
+ *	_text, _data
+ *	__kprobes_text_start, __kprobes_text_end
+ *	__entry_text_start, __entry_text_end
+ *	__ctors_start, __ctors_end
+ */
+extern char _text[], _stext[], _etext[];
+extern char _data[], _sdata[], _edata[];
+extern char __bss_start[], __bss_stop[];
+extern char __init_begin[], __init_end[];
+extern char _sinittext[], _einittext[];
+extern char _end[];
+extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
+extern char __start_rodata[], __end_rodata[];
+
+/* Start and end of .ctors section - used for constructor calls. */
+extern char __ctors_start[], __ctors_end[];
+
+extern __visible const void __nosave_begin, __nosave_end;
+
+/* function descriptor handling (if any).  Override
+ * in asm/sections.h */
+#ifndef dereference_function_descriptor
+#define dereference_function_descriptor(p) (p)
+#endif
+
+/* random extra sections (if any).  Override
+ * in asm/sections.h */
+#ifndef arch_is_kernel_text
+static inline int arch_is_kernel_text(unsigned long addr)
+{
+	return 0;
+}
+#endif
+
+#ifndef arch_is_kernel_data
+static inline int arch_is_kernel_data(unsigned long addr)
+{
+	return 0;
+}
+#endif
+
+#endif /* _ASM_GENERIC_SECTIONS_H_ */
diff --git a/include/asm-generic/segment.h b/include/asm-generic/segment.h
new file mode 100644
index 000000000..5580eace6
--- /dev/null
+++ b/include/asm-generic/segment.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_GENERIC_SEGMENT_H
+#define __ASM_GENERIC_SEGMENT_H
+/*
+ * Only here because we have some old header files that expect it...
+ *
+ * New architectures probably don't want to have their own version.
+ */
+
+#endif /* __ASM_GENERIC_SEGMENT_H */
diff --git a/include/asm-generic/serial.h b/include/asm-generic/serial.h
new file mode 100644
index 000000000..5e291090f
--- /dev/null
+++ b/include/asm-generic/serial.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_GENERIC_SERIAL_H
+#define __ASM_GENERIC_SERIAL_H
+
+/*
+ * This should not be an architecture specific #define, oh well.
+ *
+ * Traditionally, it just describes i8250 and related serial ports
+ * that have this clock rate.
+ */
+
+#define BASE_BAUD (1843200 / 16)
+
+#endif /* __ASM_GENERIC_SERIAL_H */
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
new file mode 100644
index 000000000..3d1a3af5c
--- /dev/null
+++ b/include/asm-generic/siginfo.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_GENERIC_SIGINFO_H
+#define _ASM_GENERIC_SIGINFO_H
+
+#include <uapi/asm-generic/siginfo.h>
+
+#define __SI_MASK	0xffff0000u
+#define __SI_KILL	(0 << 16)
+#define __SI_TIMER	(1 << 16)
+#define __SI_POLL	(2 << 16)
+#define __SI_FAULT	(3 << 16)
+#define __SI_CHLD	(4 << 16)
+#define __SI_RT		(5 << 16)
+#define __SI_MESGQ	(6 << 16)
+#define __SI_SYS	(7 << 16)
+#define __SI_CODE(T,N)	((T) | ((N) & 0xffff))
+
+struct siginfo;
+void do_schedule_next_timer(struct siginfo *info);
+
+#ifndef HAVE_ARCH_COPY_SIGINFO
+
+#include <linux/string.h>
+
+static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
+{
+	if (from->si_code < 0)
+		memcpy(to, from, sizeof(*to));
+	else
+		/* _sigchld is currently the largest know union member */
+		memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
+}
+
+#endif
+
+extern int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from);
+
+#endif
diff --git a/include/asm-generic/signal.h b/include/asm-generic/signal.h
new file mode 100644
index 000000000..d840c90a1
--- /dev/null
+++ b/include/asm-generic/signal.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_GENERIC_SIGNAL_H
+#define __ASM_GENERIC_SIGNAL_H
+
+#include <uapi/asm-generic/signal.h>
+
+#ifndef __ASSEMBLY__
+#ifdef SA_RESTORER
+#endif
+
+#include <asm/sigcontext.h>
+#undef __HAVE_ARCH_SIG_BITOPS
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_GENERIC_SIGNAL_H */
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
new file mode 100644
index 000000000..f57eb7b5c
--- /dev/null
+++ b/include/asm-generic/simd.h
@@ -0,0 +1,14 @@
+
+#include <linux/hardirq.h>
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ *                instructions or access the SIMD register file
+ *
+ * As architectures typically don't preserve the SIMD register file when
+ * taking an interrupt, !in_interrupt() should be a reasonable default.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	return !in_interrupt();
+}
diff --git a/include/asm-generic/sizes.h b/include/asm-generic/sizes.h
new file mode 100644
index 000000000..1dcfad962
--- /dev/null
+++ b/include/asm-generic/sizes.h
@@ -0,0 +1,2 @@
+/* This is a placeholder, to be removed over time */
+#include <linux/sizes.h>
diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h
new file mode 100644
index 000000000..1547a03ac
--- /dev/null
+++ b/include/asm-generic/spinlock.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_GENERIC_SPINLOCK_H
+#define __ASM_GENERIC_SPINLOCK_H
+/*
+ * You need to implement asm/spinlock.h for SMP support. The generic
+ * version does not handle SMP.
+ */
+#ifdef CONFIG_SMP
+#error need an architecture specific asm/spinlock.h
+#endif
+
+#endif /* __ASM_GENERIC_SPINLOCK_H */
diff --git a/include/asm-generic/statfs.h b/include/asm-generic/statfs.h
new file mode 100644
index 000000000..4b934e9ec
--- /dev/null
+++ b/include/asm-generic/statfs.h
@@ -0,0 +1,7 @@
+#ifndef _GENERIC_STATFS_H
+#define _GENERIC_STATFS_H
+
+#include <uapi/asm-generic/statfs.h>
+
+typedef __kernel_fsid_t	fsid_t;
+#endif
diff --git a/include/asm-generic/string.h b/include/asm-generic/string.h
new file mode 100644
index 000000000..de5e02014
--- /dev/null
+++ b/include/asm-generic/string.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_GENERIC_STRING_H
+#define __ASM_GENERIC_STRING_H
+/*
+ * The kernel provides all required functions in lib/string.c
+ *
+ * Architectures probably want to provide at least their own optimized
+ * memcpy and memset functions though.
+ */
+
+#endif /* __ASM_GENERIC_STRING_H */
diff --git a/include/asm-generic/switch_to.h b/include/asm-generic/switch_to.h
new file mode 100644
index 000000000..052c4ac04
--- /dev/null
+++ b/include/asm-generic/switch_to.h
@@ -0,0 +1,30 @@
+/* Generic task switch macro wrapper, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_SWITCH_TO_H
+#define __ASM_GENERIC_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * Context switching is now performed out-of-line in switch_to.S
+ */
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct task_struct *);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		((last) = __switch_to((prev), (next)));			\
+	} while (0)
+
+#endif /* __ASM_GENERIC_SWITCH_TO_H */
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
new file mode 100644
index 000000000..0c938a435
--- /dev/null
+++ b/include/asm-generic/syscall.h
@@ -0,0 +1,157 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008-2009 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * This file is a stub providing documentation for what functions
+ * asm-ARCH/syscall.h files need to define.  Most arch definitions
+ * will be simple inlines.
+ *
+ * All of these functions expect to be called with no locks,
+ * and only when the caller is sure that the task of interest
+ * cannot return to user mode while we are looking at it.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H	1
+
+struct task_struct;
+struct pt_regs;
+
+/**
+ * syscall_get_nr - find what system call a task is executing
+ * @task:	task of interest, must be blocked
+ * @regs:	task_pt_regs() of @task
+ *
+ * If @task is executing a system call or is at system call
+ * tracing about to attempt one, returns the system call number.
+ * If @task is not executing a system call, i.e. it's blocked
+ * inside the kernel for a fault or signal, returns -1.
+ *
+ * Note this returns int even on 64-bit machines.  Only 32 bits of
+ * system call number can be meaningful.  If the actual arch value
+ * is 64 bits, this truncates to 32 bits so 0xffffffff means -1.
+ *
+ * It's only valid to call this when @task is known to be blocked.
+ */
+int syscall_get_nr(struct task_struct *task, struct pt_regs *regs);
+
+/**
+ * syscall_rollback - roll back registers after an aborted system call
+ * @task:	task of interest, must be in system call exit tracing
+ * @regs:	task_pt_regs() of @task
+ *
+ * It's only valid to call this when @task is stopped for system
+ * call exit tracing (due to TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT),
+ * after tracehook_report_syscall_entry() returned nonzero to prevent
+ * the system call from taking place.
+ *
+ * This rolls back the register state in @regs so it's as if the
+ * system call instruction was a no-op.  The registers containing
+ * the system call number and arguments are as they were before the
+ * system call instruction.  This may not be the same as what the
+ * register state looked like at system call entry tracing.
+ */
+void syscall_rollback(struct task_struct *task, struct pt_regs *regs);
+
+/**
+ * syscall_get_error - check result of traced system call
+ * @task:	task of interest, must be blocked
+ * @regs:	task_pt_regs() of @task
+ *
+ * Returns 0 if the system call succeeded, or -ERRORCODE if it failed.
+ *
+ * It's only valid to call this when @task is stopped for tracing on exit
+ * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ */
+long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
+
+/**
+ * syscall_get_return_value - get the return value of a traced system call
+ * @task:	task of interest, must be blocked
+ * @regs:	task_pt_regs() of @task
+ *
+ * Returns the return value of the successful system call.
+ * This value is meaningless if syscall_get_error() returned nonzero.
+ *
+ * It's only valid to call this when @task is stopped for tracing on exit
+ * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ */
+long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
+
+/**
+ * syscall_set_return_value - change the return value of a traced system call
+ * @task:	task of interest, must be blocked
+ * @regs:	task_pt_regs() of @task
+ * @error:	negative error code, or zero to indicate success
+ * @val:	user return value if @error is zero
+ *
+ * This changes the results of the system call that user mode will see.
+ * If @error is zero, the user sees a successful system call with a
+ * return value of @val.  If @error is nonzero, it's a negated errno
+ * code; the user sees a failed system call with this errno code.
+ *
+ * It's only valid to call this when @task is stopped for tracing on exit
+ * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ */
+void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
+			      int error, long val);
+
+/**
+ * syscall_get_arguments - extract system call parameter values
+ * @task:	task of interest, must be blocked
+ * @regs:	task_pt_regs() of @task
+ * @i:		argument index [0,5]
+ * @n:		number of arguments; n+i must be [1,6].
+ * @args:	array filled with argument values
+ *
+ * Fetches @n arguments to the system call starting with the @i'th argument
+ * (from 0 through 5).  Argument @i is stored in @args[0], and so on.
+ * An arch inline version is probably optimal when @i and @n are constants.
+ *
+ * It's only valid to call this when @task is stopped for tracing on
+ * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * It's invalid to call this with @i + @n > 6; we only support system calls
+ * taking up to 6 arguments.
+ */
+void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+			   unsigned int i, unsigned int n, unsigned long *args);
+
+/**
+ * syscall_set_arguments - change system call parameter value
+ * @task:	task of interest, must be in system call entry tracing
+ * @regs:	task_pt_regs() of @task
+ * @i:		argument index [0,5]
+ * @n:		number of arguments; n+i must be [1,6].
+ * @args:	array of argument values to store
+ *
+ * Changes @n arguments to the system call starting with the @i'th argument.
+ * Argument @i gets value @args[0], and so on.
+ * An arch inline version is probably optimal when @i and @n are constants.
+ *
+ * It's only valid to call this when @task is stopped for tracing on
+ * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * It's invalid to call this with @i + @n > 6; we only support system calls
+ * taking up to 6 arguments.
+ */
+void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+			   unsigned int i, unsigned int n,
+			   const unsigned long *args);
+
+/**
+ * syscall_get_arch - return the AUDIT_ARCH for the current system call
+ *
+ * Returns the AUDIT_ARCH_* based on the system call convention in use.
+ *
+ * It's only valid to call this when current is stopped on entry to a system
+ * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
+ *
+ * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
+ * provide an implementation of this.
+ */
+int syscall_get_arch(void);
+#endif	/* _ASM_SYSCALL_H */
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
new file mode 100644
index 000000000..1f74be511
--- /dev/null
+++ b/include/asm-generic/syscalls.h
@@ -0,0 +1,28 @@
+#ifndef __ASM_GENERIC_SYSCALLS_H
+#define __ASM_GENERIC_SYSCALLS_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+
+/*
+ * Calling conventions for these system calls can differ, so
+ * it's possible to override them.
+ */
+
+#ifndef sys_mmap2
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+			unsigned long prot, unsigned long flags,
+			unsigned long fd, unsigned long pgoff);
+#endif
+
+#ifndef sys_mmap
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
+			unsigned long prot, unsigned long flags,
+			unsigned long fd, off_t pgoff);
+#endif
+
+#ifndef sys_rt_sigreturn
+asmlinkage long sys_rt_sigreturn(struct pt_regs *regs);
+#endif
+
+#endif /* __ASM_GENERIC_SYSCALLS_H */
diff --git a/include/asm-generic/termios-base.h b/include/asm-generic/termios-base.h
new file mode 100644
index 000000000..0a769feb2
--- /dev/null
+++ b/include/asm-generic/termios-base.h
@@ -0,0 +1,77 @@
+/* termios.h: generic termios/termio user copying/translation
+ */
+
+#ifndef _ASM_GENERIC_TERMIOS_BASE_H
+#define _ASM_GENERIC_TERMIOS_BASE_H
+
+#include <asm/uaccess.h>
+
+#ifndef __ARCH_TERMIO_GETPUT
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+static inline int user_termio_to_kernel_termios(struct ktermios *termios,
+						struct termio __user *termio)
+{
+	unsigned short tmp;
+
+	if (get_user(tmp, &termio->c_iflag) < 0)
+		goto fault;
+	termios->c_iflag = (0xffff0000 & termios->c_iflag) | tmp;
+
+	if (get_user(tmp, &termio->c_oflag) < 0)
+		goto fault;
+	termios->c_oflag = (0xffff0000 & termios->c_oflag) | tmp;
+
+	if (get_user(tmp, &termio->c_cflag) < 0)
+		goto fault;
+	termios->c_cflag = (0xffff0000 & termios->c_cflag) | tmp;
+
+	if (get_user(tmp, &termio->c_lflag) < 0)
+		goto fault;
+	termios->c_lflag = (0xffff0000 & termios->c_lflag) | tmp;
+
+	if (get_user(termios->c_line, &termio->c_line) < 0)
+		goto fault;
+
+	if (copy_from_user(termios->c_cc, termio->c_cc, NCC) != 0)
+		goto fault;
+
+	return 0;
+
+ fault:
+	return -EFAULT;
+}
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+static inline int kernel_termios_to_user_termio(struct termio __user *termio,
+						struct ktermios *termios)
+{
+	if (put_user(termios->c_iflag, &termio->c_iflag) < 0 ||
+	    put_user(termios->c_oflag, &termio->c_oflag) < 0 ||
+	    put_user(termios->c_cflag, &termio->c_cflag) < 0 ||
+	    put_user(termios->c_lflag, &termio->c_lflag) < 0 ||
+	    put_user(termios->c_line,  &termio->c_line) < 0 ||
+	    copy_to_user(termio->c_cc, termios->c_cc, NCC) != 0)
+		return -EFAULT;
+
+	return 0;
+}
+
+#ifndef user_termios_to_kernel_termios
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios))
+#endif
+
+#ifndef kernel_termios_to_user_termios
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
+#endif
+
+#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif	/* __ARCH_TERMIO_GETPUT */
+
+#endif /* _ASM_GENERIC_TERMIOS_BASE_H */
diff --git a/include/asm-generic/termios.h b/include/asm-generic/termios.h
new file mode 100644
index 000000000..4fa6fe0fc
--- /dev/null
+++ b/include/asm-generic/termios.h
@@ -0,0 +1,107 @@
+#ifndef _ASM_GENERIC_TERMIOS_H
+#define _ASM_GENERIC_TERMIOS_H
+
+
+#include <asm/uaccess.h>
+#include <uapi/asm-generic/termios.h>
+
+/*	intr=^C		quit=^\		erase=del	kill=^U
+	eof=^D		vtime=\0	vmin=\1		sxtc=\0
+	start=^Q	stop=^S		susp=^Z		eol=\0
+	reprint=^R	discard=^U	werase=^W	lnext=^V
+	eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+static inline int user_termio_to_kernel_termios(struct ktermios *termios,
+						const struct termio __user *termio)
+{
+	unsigned short tmp;
+
+	if (get_user(tmp, &termio->c_iflag) < 0)
+		goto fault;
+	termios->c_iflag = (0xffff0000 & termios->c_iflag) | tmp;
+
+	if (get_user(tmp, &termio->c_oflag) < 0)
+		goto fault;
+	termios->c_oflag = (0xffff0000 & termios->c_oflag) | tmp;
+
+	if (get_user(tmp, &termio->c_cflag) < 0)
+		goto fault;
+	termios->c_cflag = (0xffff0000 & termios->c_cflag) | tmp;
+
+	if (get_user(tmp, &termio->c_lflag) < 0)
+		goto fault;
+	termios->c_lflag = (0xffff0000 & termios->c_lflag) | tmp;
+
+	if (get_user(termios->c_line, &termio->c_line) < 0)
+		goto fault;
+
+	if (copy_from_user(termios->c_cc, termio->c_cc, NCC) != 0)
+		goto fault;
+
+	return 0;
+
+ fault:
+	return -EFAULT;
+}
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+static inline int kernel_termios_to_user_termio(struct termio __user *termio,
+						struct ktermios *termios)
+{
+	if (put_user(termios->c_iflag, &termio->c_iflag) < 0 ||
+	    put_user(termios->c_oflag, &termio->c_oflag) < 0 ||
+	    put_user(termios->c_cflag, &termio->c_cflag) < 0 ||
+	    put_user(termios->c_lflag, &termio->c_lflag) < 0 ||
+	    put_user(termios->c_line,  &termio->c_line) < 0 ||
+	    copy_to_user(termio->c_cc, termios->c_cc, NCC) != 0)
+		return -EFAULT;
+
+	return 0;
+}
+
+#ifdef TCGETS2
+static inline int user_termios_to_kernel_termios(struct ktermios *k,
+						 struct termios2 __user *u)
+{
+	return copy_from_user(k, u, sizeof(struct termios2));
+}
+
+static inline int kernel_termios_to_user_termios(struct termios2 __user *u,
+						 struct ktermios *k)
+{
+	return copy_to_user(u, k, sizeof(struct termios2));
+}
+
+static inline int user_termios_to_kernel_termios_1(struct ktermios *k,
+						   struct termios __user *u)
+{
+	return copy_from_user(k, u, sizeof(struct termios));
+}
+
+static inline int kernel_termios_to_user_termios_1(struct termios __user *u,
+						   struct ktermios *k)
+{
+	return copy_to_user(u, k, sizeof(struct termios));
+}
+#else /* TCGETS2 */
+static inline int user_termios_to_kernel_termios(struct ktermios *k,
+						 struct termios __user *u)
+{
+	return copy_from_user(k, u, sizeof(struct termios));
+}
+
+static inline int kernel_termios_to_user_termios(struct termios __user *u,
+						 struct ktermios *k)
+{
+	return copy_to_user(u, k, sizeof(struct termios));
+}
+#endif /* TCGETS2 */
+
+#endif /* _ASM_GENERIC_TERMIOS_H */
diff --git a/include/asm-generic/timex.h b/include/asm-generic/timex.h
new file mode 100644
index 000000000..b2243cb8d
--- /dev/null
+++ b/include/asm-generic/timex.h
@@ -0,0 +1,22 @@
+#ifndef __ASM_GENERIC_TIMEX_H
+#define __ASM_GENERIC_TIMEX_H
+
+/*
+ * If you have a cycle counter, return the value here.
+ */
+typedef unsigned long cycles_t;
+#ifndef get_cycles
+static inline cycles_t get_cycles(void)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Architectures are encouraged to implement read_current_timer
+ * and define this in order to avoid the expensive delay loop
+ * calibration during boot.
+ */
+#undef ARCH_HAS_READ_CURRENT_TIMER
+
+#endif /* __ASM_GENERIC_TIMEX_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
new file mode 100644
index 000000000..db284bff2
--- /dev/null
+++ b/include/asm-generic/tlb.h
@@ -0,0 +1,221 @@
+/* include/asm-generic/tlb.h
+ *
+ *	Generic TLB shootdown code
+ *
+ * Copyright 2001 Red Hat, Inc.
+ * Based on code from mm/memory.c Copyright Linus Torvalds and others.
+ *
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_GENERIC__TLB_H
+#define _ASM_GENERIC__TLB_H
+
+#include <linux/swap.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+/*
+ * Semi RCU freeing of the page directories.
+ *
+ * This is needed by some architectures to implement software pagetable walkers.
+ *
+ * gup_fast() and other software pagetable walkers do a lockless page-table
+ * walk and therefore needs some synchronization with the freeing of the page
+ * directories. The chosen means to accomplish that is by disabling IRQs over
+ * the walk.
+ *
+ * Architectures that use IPIs to flush TLBs will then automagically DTRT,
+ * since we unlink the page, flush TLBs, free the page. Since the disabling of
+ * IRQs delays the completion of the TLB flush we can never observe an already
+ * freed page.
+ *
+ * Architectures that do not have this (PPC) need to delay the freeing by some
+ * other means, this is that means.
+ *
+ * What we do is batch the freed directory pages (tables) and RCU free them.
+ * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
+ * holds off grace periods.
+ *
+ * However, in order to batch these pages we need to allocate storage, this
+ * allocation is deep inside the MM code and can thus easily fail on memory
+ * pressure. To guarantee progress we fall back to single table freeing, see
+ * the implementation of tlb_remove_table_one().
+ *
+ */
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
+
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#endif
+
+/*
+ * If we can't allocate a page to make a big batch of page pointers
+ * to work on, then just handle a few from the on-stack structure.
+ */
+#define MMU_GATHER_BUNDLE	8
+
+struct mmu_gather_batch {
+	struct mmu_gather_batch	*next;
+	unsigned int		nr;
+	unsigned int		max;
+	struct page		*pages[0];
+};
+
+#define MAX_GATHER_BATCH	\
+	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
+
+/*
+ * Limit the maximum number of mmu_gather batches to reduce a risk of soft
+ * lockups for non-preemptible kernels on huge machines when a lot of memory
+ * is zapped during unmapping.
+ * 10K pages freed at once should be safe even without a preemption point.
+ */
+#define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
+
+/* struct mmu_gather is an opaque type used by the mm code for passing around
+ * any data needed by arch specific code for tlb_remove_page.
+ */
+struct mmu_gather {
+	struct mm_struct	*mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch	*batch;
+#endif
+	unsigned long		start;
+	unsigned long		end;
+	/* we are in the middle of an operation to clear
+	 * a full mm and can make some optimizations */
+	unsigned int		fullmm : 1,
+	/* we have performed an operation which
+	 * requires a complete flush of the tlb */
+				need_flush_all : 1;
+
+	struct mmu_gather_batch *active;
+	struct mmu_gather_batch	local;
+	struct page		*__pages[MMU_GATHER_BUNDLE];
+	unsigned int		batch_count;
+};
+
+#define HAVE_GENERIC_MMU_GATHER
+
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);
+void tlb_flush_mmu(struct mmu_gather *tlb);
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
+							unsigned long end);
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
+
+/* tlb_remove_page
+ *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *	required.
+ */
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	if (!__tlb_remove_page(tlb, page))
+		tlb_flush_mmu(tlb);
+}
+
+static inline void __tlb_adjust_range(struct mmu_gather *tlb,
+				      unsigned long address)
+{
+	tlb->start = min(tlb->start, address);
+	tlb->end = max(tlb->end, address + PAGE_SIZE);
+}
+
+static inline void __tlb_reset_range(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm) {
+		tlb->start = tlb->end = ~0;
+	} else {
+		tlb->start = TASK_SIZE;
+		tlb->end = 0;
+	}
+}
+
+/*
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
+ */
+#ifndef tlb_start_vma
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#endif
+
+#define __tlb_end_vma(tlb, vma)					\
+	do {							\
+		if (!tlb->fullmm && tlb->end) {			\
+			tlb_flush(tlb);				\
+			__tlb_reset_range(tlb);			\
+		}						\
+	} while (0)
+
+#ifndef tlb_end_vma
+#define tlb_end_vma	__tlb_end_vma
+#endif
+
+#ifndef __tlb_remove_tlb_entry
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#endif
+
+/**
+ * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
+ *
+ * Record the fact that pte's were really unmapped by updating the range,
+ * so we can later optimise away the tlb invalidate.   This helps when
+ * userspace is unmapping already-unmapped pages, which happens quite a lot.
+ */
+#define tlb_remove_tlb_entry(tlb, ptep, address)		\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
+	} while (0)
+
+/**
+ * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
+ * This is a nop so far, because only x86 needs it.
+ */
+#ifndef __tlb_remove_pmd_tlb_entry
+#define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
+#endif
+
+#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)		\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
+	} while (0)
+
+#define pte_free_tlb(tlb, ptep, address)			\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__pte_free_tlb(tlb, ptep, address);		\
+	} while (0)
+
+#ifndef __ARCH_HAS_4LEVEL_HACK
+#define pud_free_tlb(tlb, pudp, address)			\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__pud_free_tlb(tlb, pudp, address);		\
+	} while (0)
+#endif
+
+#define pmd_free_tlb(tlb, pmdp, address)			\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__pmd_free_tlb(tlb, pmdp, address);		\
+	} while (0)
+
+#define tlb_migrate_finish(mm) do {} while (0)
+
+#endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/asm-generic/tlbflush.h b/include/asm-generic/tlbflush.h
new file mode 100644
index 000000000..d6d0a8843
--- /dev/null
+++ b/include/asm-generic/tlbflush.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_GENERIC_TLBFLUSH_H
+#define __ASM_GENERIC_TLBFLUSH_H
+/*
+ * This is a dummy tlbflush implementation that can be used on all
+ * nommu architectures.
+ * If you have an MMU, you need to write your own functions.
+ */
+#ifdef CONFIG_MMU
+#error need to implement an architecture specific asm/tlbflush.h
+#endif
+
+#include <linux/bug.h>
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	BUG();
+}
+
+
+#endif /* __ASM_GENERIC_TLBFLUSH_H */
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
new file mode 100644
index 000000000..fc824e282
--- /dev/null
+++ b/include/asm-generic/topology.h
@@ -0,0 +1,76 @@
+/*
+ * linux/include/asm-generic/topology.h
+ *
+ * Written by: Matthew Dobson, IBM Corporation
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <colpatch@us.ibm.com>
+ */
+#ifndef _ASM_GENERIC_TOPOLOGY_H
+#define _ASM_GENERIC_TOPOLOGY_H
+
+#ifndef	CONFIG_NUMA
+
+/* Other architectures wishing to use this simple topology API should fill
+   in the below functions as appropriate in their own <asm/topology.h> file. */
+#ifndef cpu_to_node
+#define cpu_to_node(cpu)	((void)(cpu),0)
+#endif
+#ifndef set_numa_node
+#define set_numa_node(node)
+#endif
+#ifndef set_cpu_numa_node
+#define set_cpu_numa_node(cpu, node)
+#endif
+#ifndef cpu_to_mem
+#define cpu_to_mem(cpu)		((void)(cpu),0)
+#endif
+
+#ifndef parent_node
+#define parent_node(node)	((void)(node),0)
+#endif
+#ifndef cpumask_of_node
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+#endif
+#ifndef pcibus_to_node
+#define pcibus_to_node(bus)	((void)(bus), -1)
+#endif
+
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+#endif
+
+#endif	/* CONFIG_NUMA */
+
+#if !defined(CONFIG_NUMA) || !defined(CONFIG_HAVE_MEMORYLESS_NODES)
+
+#ifndef set_numa_mem
+#define set_numa_mem(node)
+#endif
+#ifndef set_cpu_numa_mem
+#define set_cpu_numa_mem(cpu, node)
+#endif
+
+#endif	/* !CONFIG_NUMA || !CONFIG_HAVE_MEMORYLESS_NODES */
+
+#endif /* _ASM_GENERIC_TOPOLOGY_H */
diff --git a/include/asm-generic/trace_clock.h b/include/asm-generic/trace_clock.h
new file mode 100644
index 000000000..6726f1baf
--- /dev/null
+++ b/include/asm-generic/trace_clock.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_TRACE_CLOCK_H
+#define _ASM_GENERIC_TRACE_CLOCK_H
+/*
+ * Arch-specific trace clocks.
+ */
+
+/*
+ * Additional trace clocks added to the trace_clocks
+ * array in kernel/trace/trace.c
+ * None if the architecture has not defined it.
+ */
+#ifndef ARCH_TRACE_CLOCKS
+# define ARCH_TRACE_CLOCKS
+#endif
+
+#endif  /* _ASM_GENERIC_TRACE_CLOCK_H */
diff --git a/include/asm-generic/uaccess-unaligned.h b/include/asm-generic/uaccess-unaligned.h
new file mode 100644
index 000000000..67deb898f
--- /dev/null
+++ b/include/asm-generic/uaccess-unaligned.h
@@ -0,0 +1,26 @@
+#ifndef __ASM_GENERIC_UACCESS_UNALIGNED_H
+#define __ASM_GENERIC_UACCESS_UNALIGNED_H
+
+/*
+ * This macro should be used instead of __get_user() when accessing
+ * values at locations that are not known to be aligned.
+ */
+#define __get_user_unaligned(x, ptr)					\
+({									\
+	__typeof__ (*(ptr)) __x;					\
+	__copy_from_user(&__x, (ptr), sizeof(*(ptr))) ? -EFAULT : 0;	\
+	(x) = __x;							\
+})
+
+
+/*
+ * This macro should be used instead of __put_user() when accessing
+ * values at locations that are not known to be aligned.
+ */
+#define __put_user_unaligned(x, ptr)					\
+({									\
+	__typeof__ (*(ptr)) __x = (x);					\
+	__copy_to_user((ptr), &__x, sizeof(*(ptr))) ? -EFAULT : 0;	\
+})
+
+#endif /* __ASM_GENERIC_UACCESS_UNALIGNED_H */
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
new file mode 100644
index 000000000..72d880383
--- /dev/null
+++ b/include/asm-generic/uaccess.h
@@ -0,0 +1,346 @@
+#ifndef __ASM_GENERIC_UACCESS_H
+#define __ASM_GENERIC_UACCESS_H
+
+/*
+ * User space memory access functions, these should work
+ * on any machine that has kernel and user data in the same
+ * address space, e.g. all NOMMU machines.
+ */
+#include <linux/sched.h>
+#include <linux/string.h>
+
+#include <asm/segment.h>
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+#ifndef KERNEL_DS
+#define KERNEL_DS	MAKE_MM_SEG(~0UL)
+#endif
+
+#ifndef USER_DS
+#define USER_DS		MAKE_MM_SEG(TASK_SIZE - 1)
+#endif
+
+#ifndef get_fs
+#define get_ds()	(KERNEL_DS)
+#define get_fs()	(current_thread_info()->addr_limit)
+
+static inline void set_fs(mm_segment_t fs)
+{
+	current_thread_info()->addr_limit = fs;
+}
+#endif
+
+#ifndef segment_eq
+#define segment_eq(a, b) ((a).seg == (b).seg)
+#endif
+
+#define VERIFY_READ	0
+#define VERIFY_WRITE	1
+
+#define access_ok(type, addr, size) __access_ok((unsigned long)(addr),(size))
+
+/*
+ * The architecture should really override this if possible, at least
+ * doing a check on the get_fs()
+ */
+#ifndef __access_ok
+static inline int __access_ok(unsigned long addr, unsigned long size)
+{
+	return 1;
+}
+#endif
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	unsigned long insn, fixup;
+};
+
+/* Returns 0 if exception not found and fixup otherwise.  */
+extern unsigned long search_exception_table(unsigned long);
+
+/*
+ * architectures with an MMU should override these two
+ */
+#ifndef __copy_from_user
+static inline __must_check long __copy_from_user(void *to,
+		const void __user * from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		switch(n) {
+		case 1:
+			*(u8 *)to = *(u8 __force *)from;
+			return 0;
+		case 2:
+			*(u16 *)to = *(u16 __force *)from;
+			return 0;
+		case 4:
+			*(u32 *)to = *(u32 __force *)from;
+			return 0;
+#ifdef CONFIG_64BIT
+		case 8:
+			*(u64 *)to = *(u64 __force *)from;
+			return 0;
+#endif
+		default:
+			break;
+		}
+	}
+
+	memcpy(to, (const void __force *)from, n);
+	return 0;
+}
+#endif
+
+#ifndef __copy_to_user
+static inline __must_check long __copy_to_user(void __user *to,
+		const void *from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		switch(n) {
+		case 1:
+			*(u8 __force *)to = *(u8 *)from;
+			return 0;
+		case 2:
+			*(u16 __force *)to = *(u16 *)from;
+			return 0;
+		case 4:
+			*(u32 __force *)to = *(u32 *)from;
+			return 0;
+#ifdef CONFIG_64BIT
+		case 8:
+			*(u64 __force *)to = *(u64 *)from;
+			return 0;
+#endif
+		default:
+			break;
+		}
+	}
+
+	memcpy((void __force *)to, from, n);
+	return 0;
+}
+#endif
+
+/*
+ * These are the main single-value transfer routines.  They automatically
+ * use the right size if we just have the right pointer type.
+ * This version just falls back to copy_{from,to}_user, which should
+ * provide a fast-path for small values.
+ */
+#define __put_user(x, ptr) \
+({								\
+	__typeof__(*(ptr)) __x = (x);				\
+	int __pu_err = -EFAULT;					\
+        __chk_user_ptr(ptr);                                    \
+	switch (sizeof (*(ptr))) {				\
+	case 1:							\
+	case 2:							\
+	case 4:							\
+	case 8:							\
+		__pu_err = __put_user_fn(sizeof (*(ptr)),	\
+					 ptr, &__x);		\
+		break;						\
+	default:						\
+		__put_user_bad();				\
+		break;						\
+	 }							\
+	__pu_err;						\
+})
+
+#define put_user(x, ptr)					\
+({								\
+	might_fault();						\
+	access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)) ?		\
+		__put_user(x, ptr) :				\
+		-EFAULT;					\
+})
+
+#ifndef __put_user_fn
+
+static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+{
+	size = __copy_to_user(ptr, x, size);
+	return size ? -EFAULT : size;
+}
+
+#define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
+
+#endif
+
+extern int __put_user_bad(void) __attribute__((noreturn));
+
+#define __get_user(x, ptr)					\
+({								\
+	int __gu_err = -EFAULT;					\
+	__chk_user_ptr(ptr);					\
+	switch (sizeof(*(ptr))) {				\
+	case 1: {						\
+		unsigned char __x;				\
+		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
+					 ptr, &__x);		\
+		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
+		break;						\
+	};							\
+	case 2: {						\
+		unsigned short __x;				\
+		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
+					 ptr, &__x);		\
+		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
+		break;						\
+	};							\
+	case 4: {						\
+		unsigned int __x;				\
+		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
+					 ptr, &__x);		\
+		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
+		break;						\
+	};							\
+	case 8: {						\
+		unsigned long long __x;				\
+		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
+					 ptr, &__x);		\
+		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
+		break;						\
+	};							\
+	default:						\
+		__get_user_bad();				\
+		break;						\
+	}							\
+	__gu_err;						\
+})
+
+#define get_user(x, ptr)					\
+({								\
+	might_fault();						\
+	access_ok(VERIFY_READ, ptr, sizeof(*ptr)) ?		\
+		__get_user(x, ptr) :				\
+		-EFAULT;					\
+})
+
+#ifndef __get_user_fn
+static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+{
+	size = __copy_from_user(x, ptr, size);
+	return size ? -EFAULT : size;
+}
+
+#define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
+
+#endif
+
+extern int __get_user_bad(void) __attribute__((noreturn));
+
+#ifndef __copy_from_user_inatomic
+#define __copy_from_user_inatomic __copy_from_user
+#endif
+
+#ifndef __copy_to_user_inatomic
+#define __copy_to_user_inatomic __copy_to_user
+#endif
+
+static inline long copy_from_user(void *to,
+		const void __user * from, unsigned long n)
+{
+	might_fault();
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_from_user(to, from, n);
+	else
+		return n;
+}
+
+static inline long copy_to_user(void __user *to,
+		const void *from, unsigned long n)
+{
+	might_fault();
+	if (access_ok(VERIFY_WRITE, to, n))
+		return __copy_to_user(to, from, n);
+	else
+		return n;
+}
+
+/*
+ * Copy a null terminated string from userspace.
+ */
+#ifndef __strncpy_from_user
+static inline long
+__strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	char *tmp;
+	strncpy(dst, (const char __force *)src, count);
+	for (tmp = dst; *tmp && count > 0; tmp++, count--)
+		;
+	return (tmp - dst);
+}
+#endif
+
+static inline long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return -EFAULT;
+	return __strncpy_from_user(dst, src, count);
+}
+
+/*
+ * Return the size of a string (including the ending 0)
+ *
+ * Return 0 on exception, a value greater than N if too long
+ */
+#ifndef __strnlen_user
+#define __strnlen_user(s, n) (strnlen((s), (n)) + 1)
+#endif
+
+/*
+ * Unlike strnlen, strnlen_user includes the nul terminator in
+ * its returned count. Callers should check for a returned value
+ * greater than N as an indication the string is too long.
+ */
+static inline long strnlen_user(const char __user *src, long n)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return 0;
+	return __strnlen_user(src, n);
+}
+
+static inline long strlen_user(const char __user *src)
+{
+	return strnlen_user(src, 32767);
+}
+
+/*
+ * Zero Userspace
+ */
+#ifndef __clear_user
+static inline __must_check unsigned long
+__clear_user(void __user *to, unsigned long n)
+{
+	memset((void __force *)to, 0, n);
+	return 0;
+}
+#endif
+
+static inline __must_check unsigned long
+clear_user(void __user *to, unsigned long n)
+{
+	might_fault();
+	if (!access_ok(VERIFY_WRITE, to, n))
+		return n;
+
+	return __clear_user(to, n);
+}
+
+#endif /* __ASM_GENERIC_UACCESS_H */
diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
new file mode 100644
index 000000000..1ac097279
--- /dev/null
+++ b/include/asm-generic/unaligned.h
@@ -0,0 +1,35 @@
+#ifndef __ASM_GENERIC_UNALIGNED_H
+#define __ASM_GENERIC_UNALIGNED_H
+
+/*
+ * This is the most generic implementation of unaligned accesses
+ * and should work almost anywhere.
+ */
+#include <asm/byteorder.h>
+
+/* Set by the arch if it can handle unaligned accesses in hardware. */
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+# include <linux/unaligned/access_ok.h>
+#endif
+
+#if defined(__LITTLE_ENDIAN)
+# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#  include <linux/unaligned/le_struct.h>
+#  include <linux/unaligned/be_byteshift.h>
+# endif
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#elif defined(__BIG_ENDIAN)
+# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#  include <linux/unaligned/be_struct.h>
+#  include <linux/unaligned/le_byteshift.h>
+# endif
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#else
+# error need to define endianess
+#endif
+
+#endif /* __ASM_GENERIC_UNALIGNED_H */
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
new file mode 100644
index 000000000..cccc86ecf
--- /dev/null
+++ b/include/asm-generic/unistd.h
@@ -0,0 +1,12 @@
+#include <uapi/asm-generic/unistd.h>
+#include <linux/export.h>
+
+/*
+ * These are required system calls, we should
+ * invert the logic eventually and let them
+ * be selected by default.
+ */
+#if __BITS_PER_LONG == 32
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_LLSEEK
+#endif
diff --git a/include/asm-generic/user.h b/include/asm-generic/user.h
new file mode 100644
index 000000000..35638c347
--- /dev/null
+++ b/include/asm-generic/user.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_GENERIC_USER_H
+#define __ASM_GENERIC_USER_H
+/*
+ * This file may define a 'struct user' structure. However, it is only
+ * used for a.out files, which are not supported on new architectures.
+ */
+
+#endif	/* __ASM_GENERIC_USER_H */
diff --git a/include/asm-generic/vga.h b/include/asm-generic/vga.h
new file mode 100644
index 000000000..36c8ff520
--- /dev/null
+++ b/include/asm-generic/vga.h
@@ -0,0 +1,24 @@
+/*
+ *	Access to VGA videoram
+ *
+ *	(c) 1998 Martin Mares <mj@ucw.cz>
+ */
+#ifndef __ASM_GENERIC_VGA_H
+#define __ASM_GENERIC_VGA_H
+
+/*
+ *	On most architectures that support VGA, we can just
+ *	recalculate addresses and then access the videoram
+ *	directly without any black magic.
+ *
+ *	Everyone else needs to ioremap the address and use
+ *	proper I/O accesses.
+ */
+#ifndef VGA_MAP_MEM
+#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x)
+#endif
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x, y) (*(y) = (x))
+
+#endif /* _ASM_GENERIC_VGA_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
new file mode 100644
index 000000000..8bd374d3c
--- /dev/null
+++ b/include/asm-generic/vmlinux.lds.h
@@ -0,0 +1,830 @@
+/*
+ * Helper macros to support writing architecture specific
+ * linker scripts.
+ *
+ * A minimal linker scripts has following content:
+ * [This is a sample, architectures may have special requiriements]
+ *
+ * OUTPUT_FORMAT(...)
+ * OUTPUT_ARCH(...)
+ * ENTRY(...)
+ * SECTIONS
+ * {
+ *	. = START;
+ *	__init_begin = .;
+ *	HEAD_TEXT_SECTION
+ *	INIT_TEXT_SECTION(PAGE_SIZE)
+ *	INIT_DATA_SECTION(...)
+ *	PERCPU_SECTION(CACHELINE_SIZE)
+ *	__init_end = .;
+ *
+ *	_stext = .;
+ *	TEXT_SECTION = 0
+ *	_etext = .;
+ *
+ *      _sdata = .;
+ *	RO_DATA_SECTION(PAGE_SIZE)
+ *	RW_DATA_SECTION(...)
+ *	_edata = .;
+ *
+ *	EXCEPTION_TABLE(...)
+ *	NOTES
+ *
+ *	BSS_SECTION(0, 0, 0)
+ *	_end = .;
+ *
+ *	STABS_DEBUG
+ *	DWARF_DEBUG
+ *
+ *	DISCARDS		// must be the last
+ * }
+ *
+ * [__init_begin, __init_end] is the init section that may be freed after init
+ * 	// __init_begin and __init_end should be page aligned, so that we can
+ *	// free the whole .init memory
+ * [_stext, _etext] is the text section
+ * [_sdata, _edata] is the data section
+ *
+ * Some of the included output section have their own set of constants.
+ * Examples are: [__initramfs_start, __initramfs_end] for initramfs and
+ *               [__nosave_begin, __nosave_end] for the nosave data
+ */
+
+#ifndef LOAD_OFFSET
+#define LOAD_OFFSET 0
+#endif
+
+#include <linux/export.h>
+
+/* Align . to a 8 byte boundary equals to maximum function alignment. */
+#define ALIGN_FUNCTION()  . = ALIGN(8)
+
+/*
+ * Align to a 32 byte boundary equal to the
+ * alignment gcc 4.5 uses for a struct
+ */
+#define STRUCT_ALIGNMENT 32
+#define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT)
+
+/* The actual configuration determine if the init/exit sections
+ * are handled as text/data or they can be discarded (which
+ * often happens at runtime)
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+#define CPU_KEEP(sec)    *(.cpu##sec)
+#define CPU_DISCARD(sec)
+#else
+#define CPU_KEEP(sec)
+#define CPU_DISCARD(sec) *(.cpu##sec)
+#endif
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+#define MEM_KEEP(sec)    *(.mem##sec)
+#define MEM_DISCARD(sec)
+#else
+#define MEM_KEEP(sec)
+#define MEM_DISCARD(sec) *(.mem##sec)
+#endif
+
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#define MCOUNT_REC()	. = ALIGN(8);				\
+			VMLINUX_SYMBOL(__start_mcount_loc) = .; \
+			*(__mcount_loc)				\
+			VMLINUX_SYMBOL(__stop_mcount_loc) = .;
+#else
+#define MCOUNT_REC()
+#endif
+
+#ifdef CONFIG_TRACE_BRANCH_PROFILING
+#define LIKELY_PROFILE()	VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \
+				*(_ftrace_annotated_branch)			      \
+				VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .;
+#else
+#define LIKELY_PROFILE()
+#endif
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+#define BRANCH_PROFILE()	VMLINUX_SYMBOL(__start_branch_profile) = .;   \
+				*(_ftrace_branch)			      \
+				VMLINUX_SYMBOL(__stop_branch_profile) = .;
+#else
+#define BRANCH_PROFILE()
+#endif
+
+#ifdef CONFIG_KPROBES
+#define KPROBE_BLACKLIST()	. = ALIGN(8);				      \
+				VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \
+				*(_kprobe_blacklist)			      \
+				VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .;
+#else
+#define KPROBE_BLACKLIST()
+#endif
+
+#ifdef CONFIG_EVENT_TRACING
+#define FTRACE_EVENTS()	. = ALIGN(8);					\
+			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
+			*(_ftrace_events)				\
+			VMLINUX_SYMBOL(__stop_ftrace_events) = .;	\
+			VMLINUX_SYMBOL(__start_ftrace_enum_maps) = .;	\
+			*(_ftrace_enum_map)				\
+			VMLINUX_SYMBOL(__stop_ftrace_enum_maps) = .;
+#else
+#define FTRACE_EVENTS()
+#endif
+
+#ifdef CONFIG_TRACING
+#define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .;      \
+			 *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \
+			 VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .;
+#define TRACEPOINT_STR() VMLINUX_SYMBOL(__start___tracepoint_str) = .;	\
+			 *(__tracepoint_str) /* Trace_printk fmt' pointer */ \
+			 VMLINUX_SYMBOL(__stop___tracepoint_str) = .;
+#else
+#define TRACE_PRINTKS()
+#define TRACEPOINT_STR()
+#endif
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define TRACE_SYSCALLS() . = ALIGN(8);					\
+			 VMLINUX_SYMBOL(__start_syscalls_metadata) = .;	\
+			 *(__syscalls_metadata)				\
+			 VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
+#else
+#define TRACE_SYSCALLS()
+#endif
+
+#ifdef CONFIG_SERIAL_EARLYCON
+#define EARLYCON_TABLE() STRUCT_ALIGN();			\
+			 VMLINUX_SYMBOL(__earlycon_table) = .;	\
+			 *(__earlycon_table)			\
+			 *(__earlycon_table_end)
+#else
+#define EARLYCON_TABLE()
+#endif
+
+#define ___OF_TABLE(cfg, name)	_OF_TABLE_##cfg(name)
+#define __OF_TABLE(cfg, name)	___OF_TABLE(cfg, name)
+#define OF_TABLE(cfg, name)	__OF_TABLE(config_enabled(cfg), name)
+#define _OF_TABLE_0(name)
+#define _OF_TABLE_1(name)						\
+	. = ALIGN(8);							\
+	VMLINUX_SYMBOL(__##name##_of_table) = .;			\
+	*(__##name##_of_table)						\
+	*(__##name##_of_table_end)
+
+#define CLKSRC_OF_TABLES()	OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
+#define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
+#define CLK_OF_TABLES()		OF_TABLE(CONFIG_COMMON_CLK, clk)
+#define IOMMU_OF_TABLES()	OF_TABLE(CONFIG_OF_IOMMU, iommu)
+#define RESERVEDMEM_OF_TABLES()	OF_TABLE(CONFIG_OF_RESERVED_MEM, reservedmem)
+#define CPU_METHOD_OF_TABLES()	OF_TABLE(CONFIG_SMP, cpu_method)
+#define CPUIDLE_METHOD_OF_TABLES() OF_TABLE(CONFIG_CPU_IDLE, cpuidle_method)
+#define EARLYCON_OF_TABLES()	OF_TABLE(CONFIG_SERIAL_EARLYCON, earlycon)
+
+#define KERNEL_DTB()							\
+	STRUCT_ALIGN();							\
+	VMLINUX_SYMBOL(__dtb_start) = .;				\
+	*(.dtb.init.rodata)						\
+	VMLINUX_SYMBOL(__dtb_end) = .;
+
+/* .data section */
+#define DATA_DATA							\
+	*(.data)							\
+	*(.ref.data)							\
+	*(.data..shared_aligned) /* percpu related */			\
+	MEM_KEEP(init.data)						\
+	MEM_KEEP(exit.data)						\
+	*(.data.unlikely)						\
+	STRUCT_ALIGN();							\
+	*(__tracepoints)						\
+	/* implement dynamic printk debug */				\
+	. = ALIGN(8);                                                   \
+	VMLINUX_SYMBOL(__start___jump_table) = .;                       \
+	*(__jump_table)                                                 \
+	VMLINUX_SYMBOL(__stop___jump_table) = .;                        \
+	. = ALIGN(8);							\
+	VMLINUX_SYMBOL(__start___verbose) = .;                          \
+	*(__verbose)                                                    \
+	VMLINUX_SYMBOL(__stop___verbose) = .;				\
+	LIKELY_PROFILE()		       				\
+	BRANCH_PROFILE()						\
+	TRACE_PRINTKS()							\
+	TRACEPOINT_STR()
+
+/*
+ * Data section helpers
+ */
+#define NOSAVE_DATA							\
+	. = ALIGN(PAGE_SIZE);						\
+	VMLINUX_SYMBOL(__nosave_begin) = .;				\
+	*(.data..nosave)						\
+	. = ALIGN(PAGE_SIZE);						\
+	VMLINUX_SYMBOL(__nosave_end) = .;
+
+#define PAGE_ALIGNED_DATA(page_align)					\
+	. = ALIGN(page_align);						\
+	*(.data..page_aligned)
+
+#define READ_MOSTLY_DATA(align)						\
+	. = ALIGN(align);						\
+	*(.data..read_mostly)						\
+	. = ALIGN(align);
+
+#define CACHELINE_ALIGNED_DATA(align)					\
+	. = ALIGN(align);						\
+	*(.data..cacheline_aligned)
+
+#define INIT_TASK_DATA(align)						\
+	. = ALIGN(align);						\
+	*(.data..init_task)
+
+/*
+ * Read only Data
+ */
+#define RO_DATA_SECTION(align)						\
+	. = ALIGN((align));						\
+	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start_rodata) = .;			\
+		*(.rodata) *(.rodata.*)					\
+		*(__vermagic)		/* Kernel version magic */	\
+		. = ALIGN(8);						\
+		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
+		*(__tracepoints_ptrs)	/* Tracepoints: pointer array */\
+		VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .;		\
+		*(__tracepoints_strings)/* Tracepoints: strings */	\
+	}								\
+									\
+	.rodata1          : AT(ADDR(.rodata1) - LOAD_OFFSET) {		\
+		*(.rodata1)						\
+	}								\
+									\
+	BUG_TABLE							\
+									\
+	/* PCI quirks */						\
+	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
+		*(.pci_fixup_early)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_early) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_header) = .;		\
+		*(.pci_fixup_header)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_header) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_final) = .;		\
+		*(.pci_fixup_final)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_final) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_enable) = .;		\
+		*(.pci_fixup_enable)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_enable) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_resume) = .;		\
+		*(.pci_fixup_resume)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_resume) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_resume_early) = .;	\
+		*(.pci_fixup_resume_early)				\
+		VMLINUX_SYMBOL(__end_pci_fixups_resume_early) = .;	\
+		VMLINUX_SYMBOL(__start_pci_fixups_suspend) = .;		\
+		*(.pci_fixup_suspend)					\
+		VMLINUX_SYMBOL(__end_pci_fixups_suspend) = .;		\
+		VMLINUX_SYMBOL(__start_pci_fixups_suspend_late) = .;	\
+		*(.pci_fixup_suspend_late)				\
+		VMLINUX_SYMBOL(__end_pci_fixups_suspend_late) = .;	\
+	}								\
+									\
+	/* Built-in firmware blobs */					\
+	.builtin_fw        : AT(ADDR(.builtin_fw) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start_builtin_fw) = .;			\
+		*(.builtin_fw)						\
+		VMLINUX_SYMBOL(__end_builtin_fw) = .;			\
+	}								\
+									\
+	TRACEDATA							\
+									\
+	/* Kernel symbol table: Normal symbols */			\
+	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___ksymtab) = .;			\
+		*(SORT(___ksymtab+*))					\
+		VMLINUX_SYMBOL(__stop___ksymtab) = .;			\
+	}								\
+									\
+	/* Kernel symbol table: GPL-only symbols */			\
+	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start___ksymtab_gpl) = .;		\
+		*(SORT(___ksymtab_gpl+*))				\
+		VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .;		\
+	}								\
+									\
+	/* Kernel symbol table: Normal unused symbols */		\
+	__ksymtab_unused  : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start___ksymtab_unused) = .;		\
+		*(SORT(___ksymtab_unused+*))				\
+		VMLINUX_SYMBOL(__stop___ksymtab_unused) = .;		\
+	}								\
+									\
+	/* Kernel symbol table: GPL-only unused symbols */		\
+	__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
+		VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .;	\
+		*(SORT(___ksymtab_unused_gpl+*))			\
+		VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .;	\
+	}								\
+									\
+	/* Kernel symbol table: GPL-future-only symbols */		\
+	__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
+		VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .;	\
+		*(SORT(___ksymtab_gpl_future+*))			\
+		VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .;	\
+	}								\
+									\
+	/* Kernel symbol table: Normal symbols */			\
+	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___kcrctab) = .;			\
+		*(SORT(___kcrctab+*))					\
+		VMLINUX_SYMBOL(__stop___kcrctab) = .;			\
+	}								\
+									\
+	/* Kernel symbol table: GPL-only symbols */			\
+	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start___kcrctab_gpl) = .;		\
+		*(SORT(___kcrctab_gpl+*))				\
+		VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .;		\
+	}								\
+									\
+	/* Kernel symbol table: Normal unused symbols */		\
+	__kcrctab_unused  : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__start___kcrctab_unused) = .;		\
+		*(SORT(___kcrctab_unused+*))				\
+		VMLINUX_SYMBOL(__stop___kcrctab_unused) = .;		\
+	}								\
+									\
+	/* Kernel symbol table: GPL-only unused symbols */		\
+	__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
+		VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .;	\
+		*(SORT(___kcrctab_unused_gpl+*))			\
+		VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .;	\
+	}								\
+									\
+	/* Kernel symbol table: GPL-future-only symbols */		\
+	__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
+		VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .;	\
+		*(SORT(___kcrctab_gpl_future+*))			\
+		VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .;	\
+	}								\
+									\
+	/* Kernel symbol table: strings */				\
+        __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) {	\
+		*(__ksymtab_strings)					\
+	}								\
+									\
+	/* __*init sections */						\
+	__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) {		\
+		*(.ref.rodata)						\
+		MEM_KEEP(init.rodata)					\
+		MEM_KEEP(exit.rodata)					\
+	}								\
+									\
+	/* Built-in module parameters. */				\
+	__param : AT(ADDR(__param) - LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__start___param) = .;			\
+		*(__param)						\
+		VMLINUX_SYMBOL(__stop___param) = .;			\
+	}								\
+									\
+	/* Built-in module versions. */					\
+	__modver : AT(ADDR(__modver) - LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__start___modver) = .;			\
+		*(__modver)						\
+		VMLINUX_SYMBOL(__stop___modver) = .;			\
+		. = ALIGN((align));					\
+		VMLINUX_SYMBOL(__end_rodata) = .;			\
+	}								\
+	. = ALIGN((align));
+
+/* RODATA & RO_DATA provided for backward compatibility.
+ * All archs are supposed to use RO_DATA() */
+#define RODATA          RO_DATA_SECTION(4096)
+#define RO_DATA(align)  RO_DATA_SECTION(align)
+
+#define SECURITY_INIT							\
+	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
+		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
+		*(.security_initcall.init) 				\
+		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
+	}
+
+/* .text section. Map to function alignment to avoid address changes
+ * during second ld run in second ld pass when generating System.map */
+#define TEXT_TEXT							\
+		ALIGN_FUNCTION();					\
+		*(.text.hot)						\
+		*(.text .text.fixup)					\
+		*(.ref.text)						\
+	MEM_KEEP(init.text)						\
+	MEM_KEEP(exit.text)						\
+		*(.text.unlikely)
+
+
+/* sched.text is aling to function alignment to secure we have same
+ * address even at second ld pass when generating System.map */
+#define SCHED_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__sched_text_start) = .;			\
+		*(.sched.text)						\
+		VMLINUX_SYMBOL(__sched_text_end) = .;
+
+/* spinlock.text is aling to function alignment to secure we have same
+ * address even at second ld pass when generating System.map */
+#define LOCK_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__lock_text_start) = .;			\
+		*(.spinlock.text)					\
+		VMLINUX_SYMBOL(__lock_text_end) = .;
+
+#define KPROBES_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__kprobes_text_start) = .;		\
+		*(.kprobes.text)					\
+		VMLINUX_SYMBOL(__kprobes_text_end) = .;
+
+#define ENTRY_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__entry_text_start) = .;			\
+		*(.entry.text)						\
+		VMLINUX_SYMBOL(__entry_text_end) = .;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define IRQENTRY_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__irqentry_text_start) = .;		\
+		*(.irqentry.text)					\
+		VMLINUX_SYMBOL(__irqentry_text_end) = .;
+#else
+#define IRQENTRY_TEXT
+#endif
+
+/* Section used for early init (in .S files) */
+#define HEAD_TEXT  *(.head.text)
+
+#define HEAD_TEXT_SECTION							\
+	.head.text : AT(ADDR(.head.text) - LOAD_OFFSET) {		\
+		HEAD_TEXT						\
+	}
+
+/*
+ * Exception table
+ */
+#define EXCEPTION_TABLE(align)						\
+	. = ALIGN(align);						\
+	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___ex_table) = .;			\
+		*(__ex_table)						\
+		VMLINUX_SYMBOL(__stop___ex_table) = .;			\
+	}
+
+/*
+ * Init task
+ */
+#define INIT_TASK_DATA_SECTION(align)					\
+	. = ALIGN(align);						\
+	.data..init_task :  AT(ADDR(.data..init_task) - LOAD_OFFSET) {	\
+		INIT_TASK_DATA(align)					\
+	}
+
+#ifdef CONFIG_CONSTRUCTORS
+#define KERNEL_CTORS()	. = ALIGN(8);			   \
+			VMLINUX_SYMBOL(__ctors_start) = .; \
+			*(.ctors)			   \
+			*(SORT(.init_array.*))		   \
+			*(.init_array)			   \
+			VMLINUX_SYMBOL(__ctors_end) = .;
+#else
+#define KERNEL_CTORS()
+#endif
+
+/* init and exit section handling */
+#define INIT_DATA							\
+	*(.init.data)							\
+	MEM_DISCARD(init.data)						\
+	KERNEL_CTORS()							\
+	MCOUNT_REC()							\
+	*(.init.rodata)							\
+	FTRACE_EVENTS()							\
+	TRACE_SYSCALLS()						\
+	KPROBE_BLACKLIST()						\
+	MEM_DISCARD(init.rodata)					\
+	CLK_OF_TABLES()							\
+	RESERVEDMEM_OF_TABLES()						\
+	CLKSRC_OF_TABLES()						\
+	IOMMU_OF_TABLES()						\
+	CPU_METHOD_OF_TABLES()						\
+	CPUIDLE_METHOD_OF_TABLES()					\
+	KERNEL_DTB()							\
+	IRQCHIP_OF_MATCH_TABLE()					\
+	EARLYCON_TABLE()						\
+	EARLYCON_OF_TABLES()
+
+#define INIT_TEXT							\
+	*(.init.text)							\
+	MEM_DISCARD(init.text)
+
+#define EXIT_DATA							\
+	*(.exit.data)							\
+	MEM_DISCARD(exit.data)						\
+	MEM_DISCARD(exit.rodata)
+
+#define EXIT_TEXT							\
+	*(.exit.text)							\
+	MEM_DISCARD(exit.text)
+
+#define EXIT_CALL							\
+	*(.exitcall.exit)
+
+/*
+ * bss (Block Started by Symbol) - uninitialized data
+ * zeroed during startup
+ */
+#define SBSS(sbss_align)						\
+	. = ALIGN(sbss_align);						\
+	.sbss : AT(ADDR(.sbss) - LOAD_OFFSET) {				\
+		*(.sbss)						\
+		*(.scommon)						\
+	}
+
+/*
+ * Allow archectures to redefine BSS_FIRST_SECTIONS to add extra
+ * sections to the front of bss.
+ */
+#ifndef BSS_FIRST_SECTIONS
+#define BSS_FIRST_SECTIONS
+#endif
+
+#define BSS(bss_align)							\
+	. = ALIGN(bss_align);						\
+	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {				\
+		BSS_FIRST_SECTIONS					\
+		*(.bss..page_aligned)					\
+		*(.dynbss)						\
+		*(.bss)							\
+		*(COMMON)						\
+	}
+
+/*
+ * DWARF debug sections.
+ * Symbols in the DWARF debugging sections are relative to
+ * the beginning of the section so we begin them at 0.
+ */
+#define DWARF_DEBUG							\
+		/* DWARF 1 */						\
+		.debug          0 : { *(.debug) }			\
+		.line           0 : { *(.line) }			\
+		/* GNU DWARF 1 extensions */				\
+		.debug_srcinfo  0 : { *(.debug_srcinfo) }		\
+		.debug_sfnames  0 : { *(.debug_sfnames) }		\
+		/* DWARF 1.1 and DWARF 2 */				\
+		.debug_aranges  0 : { *(.debug_aranges) }		\
+		.debug_pubnames 0 : { *(.debug_pubnames) }		\
+		/* DWARF 2 */						\
+		.debug_info     0 : { *(.debug_info			\
+				.gnu.linkonce.wi.*) }			\
+		.debug_abbrev   0 : { *(.debug_abbrev) }		\
+		.debug_line     0 : { *(.debug_line) }			\
+		.debug_frame    0 : { *(.debug_frame) }			\
+		.debug_str      0 : { *(.debug_str) }			\
+		.debug_loc      0 : { *(.debug_loc) }			\
+		.debug_macinfo  0 : { *(.debug_macinfo) }		\
+		/* SGI/MIPS DWARF 2 extensions */			\
+		.debug_weaknames 0 : { *(.debug_weaknames) }		\
+		.debug_funcnames 0 : { *(.debug_funcnames) }		\
+		.debug_typenames 0 : { *(.debug_typenames) }		\
+		.debug_varnames  0 : { *(.debug_varnames) }		\
+
+		/* Stabs debugging sections.  */
+#define STABS_DEBUG							\
+		.stab 0 : { *(.stab) }					\
+		.stabstr 0 : { *(.stabstr) }				\
+		.stab.excl 0 : { *(.stab.excl) }			\
+		.stab.exclstr 0 : { *(.stab.exclstr) }			\
+		.stab.index 0 : { *(.stab.index) }			\
+		.stab.indexstr 0 : { *(.stab.indexstr) }		\
+		.comment 0 : { *(.comment) }
+
+#ifdef CONFIG_GENERIC_BUG
+#define BUG_TABLE							\
+	. = ALIGN(8);							\
+	__bug_table : AT(ADDR(__bug_table) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___bug_table) = .;		\
+		*(__bug_table)						\
+		VMLINUX_SYMBOL(__stop___bug_table) = .;			\
+	}
+#else
+#define BUG_TABLE
+#endif
+
+#ifdef CONFIG_PM_TRACE
+#define TRACEDATA							\
+	. = ALIGN(4);							\
+	.tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__tracedata_start) = .;			\
+		*(.tracedata)						\
+		VMLINUX_SYMBOL(__tracedata_end) = .;			\
+	}
+#else
+#define TRACEDATA
+#endif
+
+#define NOTES								\
+	.notes : AT(ADDR(.notes) - LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__start_notes) = .;			\
+		*(.note.*)						\
+		VMLINUX_SYMBOL(__stop_notes) = .;			\
+	}
+
+#define INIT_SETUP(initsetup_align)					\
+		. = ALIGN(initsetup_align);				\
+		VMLINUX_SYMBOL(__setup_start) = .;			\
+		*(.init.setup)						\
+		VMLINUX_SYMBOL(__setup_end) = .;
+
+#define INIT_CALLS_LEVEL(level)						\
+		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
+		*(.initcall##level##.init)				\
+		*(.initcall##level##s.init)				\
+
+#define INIT_CALLS							\
+		VMLINUX_SYMBOL(__initcall_start) = .;			\
+		*(.initcallearly.init)					\
+		INIT_CALLS_LEVEL(0)					\
+		INIT_CALLS_LEVEL(1)					\
+		INIT_CALLS_LEVEL(2)					\
+		INIT_CALLS_LEVEL(3)					\
+		INIT_CALLS_LEVEL(4)					\
+		INIT_CALLS_LEVEL(5)					\
+		INIT_CALLS_LEVEL(rootfs)				\
+		INIT_CALLS_LEVEL(6)					\
+		INIT_CALLS_LEVEL(7)					\
+		VMLINUX_SYMBOL(__initcall_end) = .;
+
+#define CON_INITCALL							\
+		VMLINUX_SYMBOL(__con_initcall_start) = .;		\
+		*(.con_initcall.init)					\
+		VMLINUX_SYMBOL(__con_initcall_end) = .;
+
+#define SECURITY_INITCALL						\
+		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
+		*(.security_initcall.init)				\
+		VMLINUX_SYMBOL(__security_initcall_end) = .;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+#define INIT_RAM_FS							\
+	. = ALIGN(4);							\
+	VMLINUX_SYMBOL(__initramfs_start) = .;				\
+	*(.init.ramfs)							\
+	. = ALIGN(8);							\
+	*(.init.ramfs.info)
+#else
+#define INIT_RAM_FS
+#endif
+
+/*
+ * Default discarded sections.
+ *
+ * Some archs want to discard exit text/data at runtime rather than
+ * link time due to cross-section references such as alt instructions,
+ * bug table, eh_frame, etc.  DISCARDS must be the last of output
+ * section definitions so that such archs put those in earlier section
+ * definitions.
+ */
+#define DISCARDS							\
+	/DISCARD/ : {							\
+	EXIT_TEXT							\
+	EXIT_DATA							\
+	EXIT_CALL							\
+	*(.discard)							\
+	*(.discard.*)							\
+	}
+
+/**
+ * PERCPU_INPUT - the percpu input sections
+ * @cacheline: cacheline size
+ *
+ * The core percpu section names and core symbols which do not rely
+ * directly upon load addresses.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ */
+#define PERCPU_INPUT(cacheline)						\
+	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
+	*(.data..percpu..first)						\
+	. = ALIGN(PAGE_SIZE);						\
+	*(.data..percpu..page_aligned)					\
+	. = ALIGN(cacheline);						\
+	*(.data..percpu..read_mostly)					\
+	. = ALIGN(cacheline);						\
+	*(.data..percpu)						\
+	*(.data..percpu..shared_aligned)				\
+	VMLINUX_SYMBOL(__per_cpu_end) = .;
+
+/**
+ * PERCPU_VADDR - define output section for percpu area
+ * @cacheline: cacheline size
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ *
+ * Macro which expands to output section for percpu area.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ *
+ * If @vaddr is not blank, it specifies explicit base address and all
+ * percpu symbols will be offset from the given address.  If blank,
+ * @vaddr always equals @laddr + LOAD_OFFSET.
+ *
+ * @phdr defines the output PHDR to use if not blank.  Be warned that
+ * output PHDR is sticky.  If @phdr is specified, the next output
+ * section in the linker script will go there too.  @phdr should have
+ * a leading colon.
+ *
+ * Note that this macros defines __per_cpu_load as an absolute symbol.
+ * If there is no need to put the percpu section at a predetermined
+ * address, use PERCPU_SECTION.
+ */
+#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
+	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
+	.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
+				- LOAD_OFFSET) {			\
+		PERCPU_INPUT(cacheline)					\
+	} phdr								\
+	. = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data..percpu);
+
+/**
+ * PERCPU_SECTION - define output section for percpu area, simple version
+ * @cacheline: cacheline size
+ *
+ * Align to PAGE_SIZE and outputs output section for percpu area.  This
+ * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
+ * __per_cpu_start will be identical.
+ *
+ * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
+ * except that __per_cpu_load is defined as a relative symbol against
+ * .data..percpu which is required for relocatable x86_32 configuration.
+ */
+#define PERCPU_SECTION(cacheline)					\
+	. = ALIGN(PAGE_SIZE);						\
+	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
+		PERCPU_INPUT(cacheline)					\
+	}
+
+
+/*
+ * Definition of the high level *_SECTION macros
+ * They will fit only a subset of the architectures
+ */
+
+
+/*
+ * Writeable data.
+ * All sections are combined in a single .data section.
+ * The sections following CONSTRUCTORS are arranged so their
+ * typical alignment matches.
+ * A cacheline is typical/always less than a PAGE_SIZE so
+ * the sections that has this restriction (or similar)
+ * is located before the ones requiring PAGE_SIZE alignment.
+ * NOSAVE_DATA starts and ends with a PAGE_SIZE alignment which
+ * matches the requirement of PAGE_ALIGNED_DATA.
+ *
+ * use 0 as page_align if page_aligned data is not used */
+#define RW_DATA_SECTION(cacheline, pagealigned, inittask)		\
+	. = ALIGN(PAGE_SIZE);						\
+	.data : AT(ADDR(.data) - LOAD_OFFSET) {				\
+		INIT_TASK_DATA(inittask)				\
+		NOSAVE_DATA						\
+		PAGE_ALIGNED_DATA(pagealigned)				\
+		CACHELINE_ALIGNED_DATA(cacheline)			\
+		READ_MOSTLY_DATA(cacheline)				\
+		DATA_DATA						\
+		CONSTRUCTORS						\
+	}
+
+#define INIT_TEXT_SECTION(inittext_align)				\
+	. = ALIGN(inittext_align);					\
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(_sinittext) = .;				\
+		INIT_TEXT						\
+		VMLINUX_SYMBOL(_einittext) = .;				\
+	}
+
+#define INIT_DATA_SECTION(initsetup_align)				\
+	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {		\
+		INIT_DATA						\
+		INIT_SETUP(initsetup_align)				\
+		INIT_CALLS						\
+		CON_INITCALL						\
+		SECURITY_INITCALL					\
+		INIT_RAM_FS						\
+	}
+
+#define BSS_SECTION(sbss_align, bss_align, stop_align)			\
+	. = ALIGN(sbss_align);						\
+	VMLINUX_SYMBOL(__bss_start) = .;				\
+	SBSS(sbss_align)						\
+	BSS(bss_align)							\
+	. = ALIGN(stop_align);						\
+	VMLINUX_SYMBOL(__bss_stop) = .;
diff --git a/include/asm-generic/vtime.h b/include/asm-generic/vtime.h
new file mode 100644
index 000000000..b1a49677f
--- /dev/null
+++ b/include/asm-generic/vtime.h
@@ -0,0 +1 @@
+/* no content, but patch(1) dislikes empty files */
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
new file mode 100644
index 000000000..94f9ea8ab
--- /dev/null
+++ b/include/asm-generic/word-at-a-time.h
@@ -0,0 +1,56 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This says "generic", but it's actually big-endian only.
+ * Little-endian can use more efficient versions of these
+ * interfaces, see for example
+ *	 arch/x86/include/asm/word-at-a-time.h
+ * for those.
+ */
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long high_bits, low_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
+
+/* Bit set in the bytes that have a zero */
+static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
+{
+	unsigned long mask = (val & c->low_bits) + c->low_bits;
+	return ~(mask | rhs);
+}
+
+#define create_zero_mask(mask) (mask)
+
+static inline long find_zero(unsigned long mask)
+{
+	long byte = 0;
+#ifdef CONFIG_64BIT
+	if (mask >> 32)
+		mask >>= 32;
+	else
+		byte = 4;
+#endif
+	if (mask >> 16)
+		mask >>= 16;
+	else
+		byte += 2;
+	return (mask >> 8) ? byte : byte + 1;
+}
+
+static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+{
+	unsigned long rhs = val | c->low_bits;
+	*data = rhs;
+	return (val + c->high_bits) & ~rhs;
+}
+
+#ifndef zero_bytemask
+#define zero_bytemask(mask) (~1ul << __fls(mask))
+#endif
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h
new file mode 100644
index 000000000..b4d843225
--- /dev/null
+++ b/include/asm-generic/xor.h
@@ -0,0 +1,718 @@
+/*
+ * include/asm-generic/xor.h
+ *
+ * Generic optimized RAID-5 checksumming functions.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/prefetch.h>
+
+static void
+xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0];
+		p1[1] ^= p2[1];
+		p1[2] ^= p2[2];
+		p1[3] ^= p2[3];
+		p1[4] ^= p2[4];
+		p1[5] ^= p2[5];
+		p1[6] ^= p2[6];
+		p1[7] ^= p2[7];
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0];
+		p1[1] ^= p2[1] ^ p3[1];
+		p1[2] ^= p2[2] ^ p3[2];
+		p1[3] ^= p2[3] ^ p3[3];
+		p1[4] ^= p2[4] ^ p3[4];
+		p1[5] ^= p2[5] ^ p3[5];
+		p1[6] ^= p2[6] ^ p3[6];
+		p1[7] ^= p2[7] ^ p3[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		d0 ^= p5[0];
+		d1 ^= p5[1];
+		d2 ^= p5[2];
+		d3 ^= p5[3];
+		d4 ^= p5[4];
+		d5 ^= p5[5];
+		d6 ^= p5[6];
+		d7 ^= p5[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+	prefetchw(p1);
+	prefetch(p2);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+ once_more:
+		p1[0] ^= p2[0];
+		p1[1] ^= p2[1];
+		p1[2] ^= p2[2];
+		p1[3] ^= p2[3];
+		p1[4] ^= p2[4];
+		p1[5] ^= p2[5];
+		p1[6] ^= p2[6];
+		p1[7] ^= p2[7];
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0];
+		p1[1] ^= p2[1] ^ p3[1];
+		p1[2] ^= p2[2] ^ p3[2];
+		p1[3] ^= p2[3] ^ p3[3];
+		p1[4] ^= p2[4] ^ p3[4];
+		p1[5] ^= p2[5] ^ p3[5];
+		p1[6] ^= p2[6] ^ p3[6];
+		p1[7] ^= p2[7] ^ p3[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+	prefetch(p5);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+		prefetch(p5+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	    unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+	prefetch(p5);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+		prefetch(p5+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		d0 ^= p5[0];
+		d1 ^= p5[1];
+		d2 ^= p5[2];
+		d3 ^= p5[3];
+		d4 ^= p5[4];
+		d5 ^= p5[5];
+		d6 ^= p5[6];
+		d7 ^= p5[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static struct xor_block_template xor_block_8regs = {
+	.name = "8regs",
+	.do_2 = xor_8regs_2,
+	.do_3 = xor_8regs_3,
+	.do_4 = xor_8regs_4,
+	.do_5 = xor_8regs_5,
+};
+
+static struct xor_block_template xor_block_32regs = {
+	.name = "32regs",
+	.do_2 = xor_32regs_2,
+	.do_3 = xor_32regs_3,
+	.do_4 = xor_32regs_4,
+	.do_5 = xor_32regs_5,
+};
+
+static struct xor_block_template xor_block_8regs_p __maybe_unused = {
+	.name = "8regs_prefetch",
+	.do_2 = xor_8regs_p_2,
+	.do_3 = xor_8regs_p_3,
+	.do_4 = xor_8regs_p_4,
+	.do_5 = xor_8regs_p_5,
+};
+
+static struct xor_block_template xor_block_32regs_p __maybe_unused = {
+	.name = "32regs_prefetch",
+	.do_2 = xor_32regs_p_2,
+	.do_3 = xor_32regs_p_3,
+	.do_4 = xor_32regs_p_4,
+	.do_5 = xor_32regs_p_5,
+};
+
+#define XOR_TRY_TEMPLATES			\
+	do {					\
+		xor_speed(&xor_block_8regs);	\
+		xor_speed(&xor_block_8regs_p);	\
+		xor_speed(&xor_block_32regs);	\
+		xor_speed(&xor_block_32regs_p);	\
+	} while (0)