zipf: use 64-bit safe hash for zipf/pareto

[fio.git] / hash.h

diff --git a/hash.h b/hash.h
index 3e7854b12615e354ca4e518443833d187f0d91b1..13600f4e5e4b3602df1e59636e3d687b1ce0dc82 100644 (file)
--- a/hash.h
+++ b/hash.h
@@ -1,5 +1,9 @@
 #ifndef _LINUX_HASH_H
 #define _LINUX_HASH_H
+
+#include <inttypes.h>
+#include "arch/arch.h"
+
 /* Fast hashing routine for a long.
    (C) 2002 William Lee Irwin III, IBM */
 
@@ -14,12 +18,6 @@
  * machines where multiplications are slow.
  */
 
-#ifdef __WORDSIZE
-#define BITS_PER_LONG  __WORDSIZE
-#else
-#define BITS_PER_LONG  32
-#endif
-
 #if BITS_PER_LONG == 32
 /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
 #define GOLDEN_RATIO_PRIME 0x9e370001UL
@@ -30,7 +28,9 @@
 #error Define GOLDEN_RATIO_PRIME for your wordsize.
 #endif
 
-static inline unsigned long hash_long(unsigned long val, unsigned int bits)
+#define GR_PRIME_64    0x9e37fffffffc0001UL
+
+static inline unsigned long __hash_long(unsigned long val)
 {
        unsigned long hash = val;
 
@@ -54,12 +54,98 @@ static inline unsigned long hash_long(unsigned long val, unsigned int bits)
        hash *= GOLDEN_RATIO_PRIME;
 #endif
 
+       return hash;
+}
+
+static inline unsigned long hash_long(unsigned long val, unsigned int bits)
+{
        /* High bits are more random, so use them. */
-       return hash >> (BITS_PER_LONG - bits);
+       return __hash_long(val) >> (BITS_PER_LONG - bits);
+}
+
+static inline uint64_t __hash_u64(uint64_t val)
+{
+       return val * GR_PRIME_64;
 }
        
 static inline unsigned long hash_ptr(void *ptr, unsigned int bits)
 {
-       return hash_long((unsigned long)ptr, bits);
+       return hash_long((uintptr_t)ptr, bits);
 }
+
+/*
+ * Bob Jenkins jhash
+ */
+
+#define JHASH_INITVAL  GOLDEN_RATIO_PRIME
+
+static inline uint32_t rol32(uint32_t word, uint32_t shift)
+{
+       return (word << shift) | (word >> (32 - shift));
+}
+
+/* __jhash_mix -- mix 3 32-bit values reversibly. */
+#define __jhash_mix(a, b, c)                   \
+{                                              \
+       a -= c;  a ^= rol32(c, 4);  c += b;     \
+       b -= a;  b ^= rol32(a, 6);  a += c;     \
+       c -= b;  c ^= rol32(b, 8);  b += a;     \
+       a -= c;  a ^= rol32(c, 16); c += b;     \
+       b -= a;  b ^= rol32(a, 19); a += c;     \
+       c -= b;  c ^= rol32(b, 4);  b += a;     \
+}
+
+/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */
+#define __jhash_final(a, b, c)                 \
+{                                              \
+       c ^= b; c -= rol32(b, 14);              \
+       a ^= c; a -= rol32(c, 11);              \
+       b ^= a; b -= rol32(a, 25);              \
+       c ^= b; c -= rol32(b, 16);              \
+       a ^= c; a -= rol32(c, 4);               \
+       b ^= a; b -= rol32(a, 14);              \
+       c ^= b; c -= rol32(b, 24);              \
+}
+
+static inline uint32_t jhash(const void *key, uint32_t length, uint32_t initval)
+{
+       const uint8_t *k = key;
+       uint32_t a, b, c;
+
+       /* Set up the internal state */
+       a = b = c = JHASH_INITVAL + length + initval;
+
+       /* All but the last block: affect some 32 bits of (a,b,c) */
+       while (length > 12) {
+               a += *k;
+               b += *(k + 4);
+               c += *(k + 8);
+               __jhash_mix(a, b, c);
+               length -= 12;
+               k += 12;
+       }
+
+       /* Last block: affect all 32 bits of (c) */
+       /* All the case statements fall through */
+       switch (length) {
+       case 12: c += (uint32_t) k[11] << 24;
+       case 11: c += (uint32_t) k[10] << 16;
+       case 10: c += (uint32_t) k[9] << 8;
+       case 9:  c += k[8];
+       case 8:  b += (uint32_t) k[7] << 24;
+       case 7:  b += (uint32_t) k[6] << 16;
+       case 6:  b += (uint32_t) k[5] << 8;
+       case 5:  b += k[4];
+       case 4:  a += (uint32_t) k[3] << 24;
+       case 3:  a += (uint32_t) k[2] << 16;
+       case 2:  a += (uint32_t) k[1] << 8;
+       case 1:  a += k[0];
+                __jhash_final(a, b, c);
+       case 0: /* Nothing left to add */
+               break;
+       }
+
+       return c;
+}
+
 #endif /* _LINUX_HASH_H */