lib: add lz4 compressor module

This patchset is for supporting LZ4 compression and the crypto API using
it.

As shown below, the size of data is a little bit bigger but compressing
speed is faster under the enabled unaligned memory access.  We can use
lz4 de/compression through crypto API as well.  Also, It will be useful
for another potential user of lz4 compression.

lz4 Compression Benchmark:
Compiler: ARM gcc 4.6.4
ARMv7, 1 GHz based board
   Kernel: linux 3.4
   Uncompressed data Size: 101 MB
         Compressed Size  compression Speed
   LZO   72.1MB		  32.1MB/s, 33.0MB/s(UA)
   LZ4   75.1MB		  30.4MB/s, 35.9MB/s(UA)
   LZ4HC 59.8MB		   2.4MB/s,  2.5MB/s(UA)
- UA: Unaligned memory Access support
- Latest patch set for LZO applied

This patch:

Add support for LZ4 compression in the Linux Kernel.  LZ4 Compression APIs
for kernel are based on LZ4 implementation by Yann Collet and were changed
for kernel coding style.

LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
LZ4 source repository : http://code.google.com/p/lz4/
svn revision : r90

Two APIs are added:

lz4_compress() support basic lz4 compression whereas lz4hc_compress()
support high compression or CPU performance get lower but compression
ratio get higher.  Also, we require the pre-allocated working memory with
the defined size and destination buffer must be allocated with the size of
lz4_compressbound.

[akpm@linux-foundation.org: make lz4_compresshcctx() static]
Signed-off-by: Chanho Min <chanho.min@lge.com>
Cc: "Darrick J. Wong" <djwong@us.ibm.com>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Herbert Xu <herbert@gondor.hengli.com.au>
Cc: Yann Collet <yann.collet.73@gmail.com>
Cc: Kyungsik Lee <kyungsik.lee@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 64 insertions, 2 deletions

diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 43ac31d63f36..abcecdc2d0f2 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -22,23 +22,40 @@
  * Architecture-specific macros
  */
 #define BYTE    u8
+typedef struct _U16_S { u16 v; } U16_S;
+typedef struct _U32_S { u32 v; } U32_S;
+typedef struct _U64_S { u64 v; } U64_S;
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)             \
         || defined(CONFIG_ARM) && __LINUX_ARM_ARCH__ >= 6       \
         && defined(ARM_EFFICIENT_UNALIGNED_ACCESS)
-typedef struct _U32_S { u32 v; } U32_S;
-typedef struct _U64_S { u64 v; } U64_S;
 
+#define A16(x) (((U16_S *)(x))->v)
 #define A32(x) (((U32_S *)(x))->v)
 #define A64(x) (((U64_S *)(x))->v)
 
 #define PUT4(s, d) (A32(d) = A32(s))
 #define PUT8(s, d) (A64(d) = A64(s))
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+        do {    \
+                A16(p) = v; \
+                p += 2; \
+        } while (0)
 #else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
 
+#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v))
+#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v))
+#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v))
+
 #define PUT4(s, d) \
         put_unaligned(get_unaligned((const u32 *) s), (u32 *) d)
 #define PUT8(s, d) \
         put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
+
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+        do {    \
+                put_unaligned(v, (u16 *)(p)); \
+                p += 2; \
+        } while (0)
 #endif
 
 #define COPYLENGTH 8
@@ -46,6 +63,29 @@ typedef struct _U64_S { u64 v; } U64_S;
 #define ML_MASK  ((1U << ML_BITS) - 1)
 #define RUN_BITS (8 - ML_BITS)
 #define RUN_MASK ((1U << RUN_BITS) - 1)
+#define MEMORY_USAGE    14
+#define MINMATCH        4
+#define SKIPSTRENGTH    6
+#define LASTLITERALS    5
+#define MFLIMIT         (COPYLENGTH + MINMATCH)
+#define MINLENGTH       (MFLIMIT + 1)
+#define MAXD_LOG        16
+#define MAXD            (1 << MAXD_LOG)
+#define MAXD_MASK       (u32)(MAXD - 1)
+#define MAX_DISTANCE    (MAXD - 1)
+#define HASH_LOG        (MAXD_LOG - 1)
+#define HASHTABLESIZE   (1 << HASH_LOG)
+#define MAX_NB_ATTEMPTS 256
+#define OPTIMAL_ML      (int)((ML_MASK-1)+MINMATCH)
+#define LZ4_64KLIMIT    ((1<<16) + (MFLIMIT - 1))
+#define HASHLOG64K      ((MEMORY_USAGE - 2) + 1)
+#define HASH64KTABLESIZE        (1U << HASHLOG64K)
+#define LZ4_HASH_VALUE(p)       (((A32(p)) * 2654435761U) >> \
+                                ((MINMATCH * 8) - (MEMORY_USAGE-2)))
+#define LZ4_HASH64K_VALUE(p)    (((A32(p)) * 2654435761U) >> \
+                                ((MINMATCH * 8) - HASHLOG64K))
+#define HASH_VALUE(p)           (((A32(p)) * 2654435761U) >> \
+                                ((MINMATCH * 8) - HASH_LOG))
 
 #if LZ4_ARCH64/* 64-bit */
 #define STEPSIZE 8
@@ -65,6 +105,13 @@ typedef struct _U64_S { u64 v; } U64_S;
                         LZ4_WILDCOPY(s, d, e);  \
                 }                               \
         } while (0)
+#define HTYPE u32
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3)
+#endif
 
 #else   /* 32-bit */
 #define STEPSIZE 4
@@ -83,6 +130,14 @@ typedef struct _U64_S { u64 v; } U64_S;
         } while (0)
 
 #define LZ4_SECURECOPY  LZ4_WILDCOPY
+#define HTYPE const u8*
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3)
+#endif
+
 #endif
 
 #define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
@@ -92,3 +147,10 @@ typedef struct _U64_S { u64 v; } U64_S;
         do {                            \
                 LZ4_COPYPACKET(s, d);   \
         } while (d < e)
+
+#define LZ4_BLINDCOPY(s, d, l)  \
+        do {    \
+                u8 *e = (d) + l;        \
+                LZ4_WILDCOPY(s, d, e);  \
+                d = e;  \
+        } while (0)