lib/lzo: Update LZO compression to current upstream version

This commit updates the kernel LZO code to the current upsteam version
which features a significant speed improvement - benchmarking the Calgary
and Silesia test corpora typically shows a doubled performance in
both compression and decompression on modern i386/x86_64/powerpc machines.

Signed-off-by: Markus F.X.J. Oberhumer <markus@oberhumer.com>

4 files changed, 395 insertions, 343 deletions

diff --git a/include/linux/lzo.h b/include/linux/lzo.h
index d793497ec1ca..a0848d9377e5 100644
--- a/include/linux/lzo.h
+++ b/include/linux/lzo.h
@@ -4,28 +4,28 @@
  *  LZO Public Kernel Interface
  *  A mini subset of the LZO real-time data compression library
  *
- *  Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
  *
  *  The full LZO package can be found at:
  *  http://www.oberhumer.com/opensource/lzo/
  *
- *  Changed for kernel use by:
+ *  Changed for Linux kernel use by:
  *  Nitin Gupta <nitingupta910@gmail.com>
  *  Richard Purdie <rpurdie@openedhand.com>
  */
 
-#define LZO1X_MEM_COMPRESS      (16384 * sizeof(unsigned char *))
-#define LZO1X_1_MEM_COMPRESS    LZO1X_MEM_COMPRESS
+#define LZO1X_1_MEM_COMPRESS    (8192 * sizeof(unsigned short))
+#define LZO1X_MEM_COMPRESS      LZO1X_1_MEM_COMPRESS
 
 #define lzo1x_worst_compress(x) ((x) + ((x) / 16) + 64 + 3)
 
-/* This requires 'workmem' of size LZO1X_1_MEM_COMPRESS */
+/* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */
 int lzo1x_1_compress(const unsigned char *src, size_t src_len,
-                        unsigned char *dst, size_t *dst_len, void *wrkmem);
+                     unsigned char *dst, size_t *dst_len, void *wrkmem);
 
 /* safe decompression with overrun testing */
 int lzo1x_decompress_safe(const unsigned char *src, size_t src_len,
-                        unsigned char *dst, size_t *dst_len);
+                          unsigned char *dst, size_t *dst_len);
 
 /*
  * Return values (< 0 = Error)
@@ -40,5 +40,6 @@ int lzo1x_decompress_safe(const unsigned char *src, size_t src_len,
 #define LZO_E_EOF_NOT_FOUND             (-7)
 #define LZO_E_INPUT_NOT_CONSUMED        (-8)
 #define LZO_E_NOT_YET_IMPLEMENTED       (-9)
+#define LZO_E_INVALID_ARGUMENT          (-10)
 
 #endif
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
index a6040990a62e..236eb21167b5 100644
--- a/lib/lzo/lzo1x_compress.c
+++ b/lib/lzo/lzo1x_compress.c
@@ -1,194 +1,243 @@
 /*
- *  LZO1X Compressor from MiniLZO
+ *  LZO1X Compressor from LZO
  *
- *  Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
  *
  *  The full LZO package can be found at:
  *  http://www.oberhumer.com/opensource/lzo/
  *
- *  Changed for kernel use by:
+ *  Changed for Linux kernel use by:
  *  Nitin Gupta <nitingupta910@gmail.com>
  *  Richard Purdie <rpurdie@openedhand.com>
  */
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/lzo.h>
 #include <asm/unaligned.h>
+#include <linux/lzo.h>
 #include "lzodefs.h"
 
 static noinline size_t
-_lzo1x_1_do_compress(const unsigned char *in, size_t in_len,
-                unsigned char *out, size_t *out_len, void *wrkmem)
+lzo1x_1_do_compress(const unsigned char *in, size_t in_len,
+                    unsigned char *out, size_t *out_len,
+                    size_t ti, void *wrkmem)
 {
+        const unsigned char *ip;
+        unsigned char *op;
         const unsigned char * const in_end = in + in_len;
-        const unsigned char * const ip_end = in + in_len - M2_MAX_LEN - 5;
-        const unsigned char ** const dict = wrkmem;
-        const unsigned char *ip = in, *ii = ip;
-        const unsigned char *end, *m, *m_pos;
-        size_t m_off, m_len, dindex;
-        unsigned char *op = out;
+        const unsigned char * const ip_end = in + in_len - 20;
+        const unsigned char *ii;
+        lzo_dict_t * const dict = (lzo_dict_t *) wrkmem;
 
-        ip += 4;
+        op = out;
+        ip = in;
+        ii = ip;
+        ip += ti < 4 ? 4 - ti : 0;
 
         for (;;) {
-                dindex = ((size_t)(0x21 * DX3(ip, 5, 5, 6)) >> 5) & D_MASK;
-                m_pos = dict[dindex];
-
-                if (m_pos < in)
-                        goto literal;
-
-                if (ip == m_pos || ((size_t)(ip - m_pos) > M4_MAX_OFFSET))
-                        goto literal;
-
-                m_off = ip - m_pos;
-                if (m_off <= M2_MAX_OFFSET || m_pos[3] == ip[3])
-                        goto try_match;
-
-                dindex = (dindex & (D_MASK & 0x7ff)) ^ (D_HIGH | 0x1f);
-                m_pos = dict[dindex];
-
-                if (m_pos < in)
-                        goto literal;
-
-                if (ip == m_pos || ((size_t)(ip - m_pos) > M4_MAX_OFFSET))
-                        goto literal;
-
-                m_off = ip - m_pos;
-                if (m_off <= M2_MAX_OFFSET || m_pos[3] == ip[3])
-                        goto try_match;
-
-                goto literal;
-
-try_match:
-                if (get_unaligned((const unsigned short *)m_pos)
-                                == get_unaligned((const unsigned short *)ip)) {
-                        if (likely(m_pos[2] == ip[2]))
-                                        goto match;
-                }
-
+                const unsigned char *m_pos;
+                size_t t, m_len, m_off;
+                u32 dv;
 literal:
-                dict[dindex] = ip;
-                ++ip;
+                ip += 1 + ((ip - ii) >> 5);
+next:
                 if (unlikely(ip >= ip_end))
                         break;
-                continue;
-
-match:
-                dict[dindex] = ip;
-                if (ip != ii) {
-                        size_t t = ip - ii;
+                dv = get_unaligned_le32(ip);
+                t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK;
+                m_pos = in + dict[t];
+                dict[t] = (lzo_dict_t) (ip - in);
+                if (unlikely(dv != get_unaligned_le32(m_pos)))
+                        goto literal;
 
+                ii -= ti;
+                ti = 0;
+                t = ip - ii;
+                if (t != 0) {
                         if (t <= 3) {
                                 op[-2] |= t;
-                        } else if (t <= 18) {
+                                COPY4(op, ii);
+                                op += t;
+                        } else if (t <= 16) {
                                 *op++ = (t - 3);
+                                COPY8(op, ii);
+                                COPY8(op + 8, ii + 8);
+                                op += t;
                         } else {
-                                size_t tt = t - 18;
+                                if (t <= 18) {