kernel: add common infrastructure for unaligned access

Create a linux/unaligned folder similar in spirit to the linux/byteorder folder to hold generic implementations collected from various arches.

Currently there are five implementations:
1) cpu_endian.h: C-struct based, from asm-generic/unaligned.h
2) little_endian.h: Open coded byte-swapping, heavily based on asm-arm
3) big_endian.h: Open coded byte-swapping, heavily based on asm-arm
4) no_builtin_memcpy.h: taken from multiple implementations in tree
5) access_ok.h: taken from x86 and others, unaligned access is ok.

All of the new implementations checks for sizes not equal to 1,2,4,8 and will BUG at compile time.

API additions:

get_unaligned_{le16|le32|le64|be16|be32|be64}(p) which is meant to replace code of the form:
le16_to_cpu(get_unaligned((__le16 *)p));

put_unaligned_{le16|le32|le64|be16|be32|be64}(val, pointer) which is meant to replace code of the form:
put_unaligned(cpu_to_le16(val), (__le16 *)p);

Headers to create these based on the selected implementation and defining the appropriate get_unaligned() and put_unaligned() macros are:

generic_le.h: Use the C-struct for get/put_unaligned and the le helpers, use the opencoded be byteswapping implementation for big-endian.

generic_be.h: Use the C-struct for get/put_unaligned and the be helpers, use the opencoded le byteswapping implementation for little-endian.

generic.h: Use opencoded byteswapping for all helpers, leaves it to the arch to define get/put_unaligned.

---
Removed some superfluous casts noticed by David Howells. Made all arches check the only size 1,2,4,8 types are passed to get/put_unaligned.

 include/linux/unaligned/access_ok.h         |   98 +++++++++++++++++++++++++
 include/linux/unaligned/big_endian.h        |   86 ++++++++++++++++++++++
 include/linux/unaligned/cpu_endian.h        |   92 ++++++++++++++++++++++++
 include/linux/unaligned/generic.h           |   67 +++++++++++++++++
 include/linux/unaligned/generic_be.h        |   70 ++++++++++++++++++
 include/linux/unaligned/generic_le.h        |   70 ++++++++++++++++++
 include/linux/unaligned/little_endian.h     |   86 ++++++++++++++++++++++
 include/linux/unaligned/no_builtin_memcpy.h |  102 +++++++++++++++++++++++++++
 8 files changed, 671 insertions(+), 0 deletions(-)

new file mode 100644
index 0000000..69f4520
@@ -0,0 +1,98 @@
+#ifndef _LINUX_UNALIGNED_ACCESS_OK_H_
+#define _LINUX_UNALIGNED_ACCESS_OK_H_
+
+#include <linux/kernel.h>
+#include <asm/byteorder.h>
+
+extern void __build_bug_unaligned_length(void);
+
+#define get_unaligned(ptr) ({			\
+	typeof(*(ptr)) __tmp;			\
+	switch (sizeof(__tmp)) {		\
+	case 1:					\
+	case 2:					\
+	case 4:					\
+	case 8:					\
+		__tmp = *(ptr);			\
+		break;				\
+	default:				\
+		__build_bug_unaligned_length();	\
+		break;				\
+	}					\
+	__tmp; })
+
+#define put_unaligned(val, ptr) ({		\
+	switch (sizeof(*(ptr))) {		\
+	case 1:					\
+	case 2:					\
+	case 4:					\
+	case 8:					\
+		*(ptr) = (val);			\
+		break;				\
+	default:				\
+		__build_bug_unaligned_length();	\
+		break;				\
+	}					\
+	(void)0; })
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpup((__le16 *)p);
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpup((__le32 *)p);
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpup((__le64 *)p);
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpup((__be16 *)p);
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpup((__be32 *)p);
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpup((__be64 *)p);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	*((__le16 *)p) = cpu_to_le16(val);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	*((__le32 *)p) = cpu_to_le32(val);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	*((__le64 *)p) = cpu_to_le64(val);
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	*((__be16 *)p) = cpu_to_be16(val);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	*((__be32 *)p) = cpu_to_be32(val);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	*((__be64 *)p) = cpu_to_be64(val);
+}
+
+#endif /* _LINUX_UNALIGNED_ACCESS_OK_H_ */

1.5.5.144.g3e42

[Harvey Harrison - Thu, Apr 10, 2008 at 08:38:57PM -0700] [...]

| +
| +static inline void __put_unaligned_be16(u16 val, u8 *p)
| +{
| +	*p++ = val >> 8;
| +	*p++ = val;
| +}
| +
[...]
| +static inline void __put_unaligned_le16(u16 val, u8 *p)
| +{
| +	*p++ = val;
| +	*p++ = val >> 8;
| +}

[...]

Hi Harvey, do we really need second increments? I mean, wouldn't be better to use *p = val >> 8 and *p << 8?

- Cyrill -