- Move jenkins.h to jenkins_hash.c

- Provide missing function that can do hashing of arbitrary sized buffer.
- Refetch lookup3.c and do only minimal edits to it, so that diff between
  our jenkins_hash.c and lookup3.c is minimal.
- Add declarations for jenkins_hash(), jenkins_hash32() to sys/hash.h.
- Document these functions in hash(9)

Obtained from:	http://burtleburtle.net/bob/c/lookup3.c

5 files changed, 476 insertions, 188 deletions

diff --git a/sys/conf/files b/sys/conf/files
index 08730fb064e7..e08c25916b20 100644
--- a/sys/conf/files
+++ b/sys/conf/files
@@ -2797,6 +2797,7 @@ libkern/inet_aton.c		standard
 libkern/inet_ntoa.c		standard
 libkern/inet_ntop.c		standard
 libkern/inet_pton.c		standard
+libkern/jenkins_hash.c		standard
 libkern/mcount.c		optional profiling-routine
 libkern/memcchr.c		standard
 libkern/memcmp.c		standard
diff --git a/sys/libkern/jenkins.h b/sys/libkern/jenkins.h
deleted file mode 100644
index 0846ae8c913d..000000000000
--- a/sys/libkern/jenkins.h
+++ /dev/null
@@ -1,185 +0,0 @@
-#ifndef __LIBKERN_JENKINS_H__
-#define __LIBKERN_JENKINS_H__
-/*
- * Taken from http://burtleburtle.net/bob/c/lookup3.c
- * $FreeBSD$
- */
-
-/*
--------------------------------------------------------------------------------
-  lookup3.c, by Bob Jenkins, May 2006, Public Domain.
-
-  These are functions for producing 32-bit hashes for hash table lookup.
-  hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final()
-  are externally useful functions.  Routines to test the hash are included
-  if SELF_TEST is defined.  You can use this free for any purpose.  It's in
-  the public domain.  It has no warranty.
-
-  You probably want to use hashlittle().  hashlittle() and hashbig()
-  hash byte arrays.  hashlittle() is faster than hashbig() on
-  little-endian machines.  Intel and AMD are little-endian machines.
-  On second thought, you probably want hashlittle2(), which is identical to
-  hashlittle() except it returns two 32-bit hashes for the price of one.
-  You could implement hashbig2() if you wanted but I haven't bothered here.
-
-  If you want to find a hash of, say, exactly 7 integers, do
-    a = i1;  b = i2;  c = i3;
-    mix(a,b,c);
-    a += i4; b += i5; c += i6;
-    mix(a,b,c);
-    a += i7;
-    final(a,b,c);
-  then use c as the hash value.  If you have a variable length array of
-  4-byte integers to hash, use hashword().  If you have a byte array (like
-  a character string), use hashlittle().  If you have several byte arrays, or
-  a mix of things, see the comments above hashlittle().
-  
-  Why is this so big?  I read 12 bytes at a time into 3 4-byte integers,
-  then mix those integers.  This is fast (you can do a lot more thorough
-  mixing with 12*3 instructions on 3 integers than you can with 3 instructions
-  on 1 byte), but shoehorning those bytes into integers efficiently is messy.
--------------------------------------------------------------------------------
-*/
-
-#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k))))
-
-/*
--------------------------------------------------------------------------------
-mix -- mix 3 32-bit values reversibly.
-
-This is reversible, so any information in (a,b,c) before mix() is
-still in (a,b,c) after mix().
-
-If four pairs of (a,b,c) inputs are run through mix(), or through
-mix() in reverse, there are at least 32 bits of the output that
-are sometimes the same for one pair and different for another pair.
-This was tested for:
-* pairs that differed by one bit, by two bits, in any combination
-  of top bits of (a,b,c), or in any combination of bottom bits of
-  (a,b,c).
-* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
-  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
-  is commonly produced by subtraction) look like a single 1-bit
-  difference.
-* the base values were pseudorandom, all zero but one bit set, or 
-  all zero plus a counter that starts at zero.
-
-Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
-satisfy this are
-    4  6  8 16 19  4
-    9 15  3 18 27 15
-   14  9  3  7 17  3
-Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
-for "differ" defined as + with a one-bit base and a two-bit delta.  I
-used http://burtleburtle.net/bob/hash/avalanche.html to choose 
-the operations, constants, and arrangements of the variables.
-
-This does not achieve avalanche.  There are input bits of (a,b,c)
-that fail to affect some output bits of (a,b,c), especially of a.  The
-most thoroughly mixed value is c, but it doesn't really even achieve
-avalanche in c.
-
-This allows some parallelism.  Read-after-writes are good at doubling
-the number of bits affected, so the goal of mixing pulls in the opposite
-direction as the goal of parallelism.  I did what I could.  Rotates
-seem to cost as much as shifts on every machine I could lay my hands
-on, and rotates are much kinder to the top and bottom bits, so I used
-rotates.
--------------------------------------------------------------------------------
-*/
-#define mix(a,b,c) \
-{ \
-  a -= c;  a ^= rot(c, 4);  c += b; \
-  b -= a;  b ^= rot(a, 6);  a += c; \
-  c -= b;  c ^= rot(b, 8);  b += a; \
-  a -= c;  a ^= rot(c,16);  c += b; \
-  b -= a;  b ^= rot(a,19);  a += c; \
-  c -= b;  c ^= rot(b, 4);  b += a; \
-}
-
-/*
--------------------------------------------------------------------------------
-final -- final mixing of 3 32-bit values (a,b,c) into c
-
-Pairs of (a,b,c) values differing in only a few bits will usually
-produce values of c that look totally different.  This was tested for
-* pairs that differed by one bit, by two bits, in any combination
-  of top bits of (a,b,c), or in any combination of bottom bits of
-  (a,b,c).
-* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
-  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
-  is commonly produced by subtraction) look like a single 1-bit
-  difference.
-* the base values were pseudorandom, all zero but one bit set, or 
-  all zero plus a counter that starts at zero.
-
-These constants passed:
- 14 11 25 16 4 14 24
- 12 14 25 16 4 14 24
-and these came close:
-  4  8 15 26 3 22 24
- 10  8 15 26 3 22 24
- 11  8 15 26 3 22 24
--------------------------------------------------------------------------------
-*/
-#define final(a,b,c) \
-{ \
-  c ^= b; c -= rot(b,14); \
-  a ^= c; a -= rot(c,11); \
-  b ^= a; b -= rot(a,25); \
-  c ^= b; c -= rot(b,16); \
-  a ^= c; a -= rot(c,4);  \
-  b ^= a; b -= rot(a,14); \
-  c ^= b; c -= rot(b,24); \
-}
-
-/*
---------------------------------------------------------------------
- This works on all machines.  To be useful, it requires
- -- that the key be an array of uint32_t's, and
- -- that the length be the number of uint32_t's in the key
-
- The function hashword() is identical to hashlittle() on little-endian
- machines, and identical to hashbig() on big-endian machines,
- except that the length has to be measured in uint32_ts rather than in
- bytes.  hashlittle() is more complicated than hashword() only because
- hashlittle() has to dance around fitting the key bytes into registers.
---------------------------------------------------------------------
-*/
-static uint32_t
-jenkins_hashword(
-                const uint32_t *k,  /* the key, an array of uint32_t values */
-                size_t length,      /* the length of the key, in uint32_ts */
-                uint32_t initval    /* the previous hash, or an arbitrary value */
-)
-{
-  uint32_t a,b,c;
-
-  /* Set up the internal state */
-  a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval;
-
-  /*------------------------------------------------- handle most of the key */
-  while (length > 3)
-  {
-    a += k[0];
-    b += k[1];
-    c += k[2];
-    mix(a,b,c);
-    length -= 3;
-    k += 3;
-  }
-
-  /*------------------------------------------- handle the last 3 uint32_t's */
-  switch(length)                     /* all the case statements fall through */
-  { 
-  case 3 : c+=k[2];
-  case 2 : b+=k[1];
-  case 1 : a+=k[0];
-    final(a,b,c);
-  case 0:     /* case 0: nothing left to add */
-    break;
-  }
-  /*------------------------------------------------------ report the result */
-  return c;
-}
-#endif 
diff --git a/sys/libkern/jenkins_hash.c b/sys/libkern/jenkins_hash.c
new file mode 100644
index 000000000000..e582bd85a9f9
--- /dev/null
+++ b/sys/libkern/jenkins_hash.c
@@ -0,0 +1,463 @@
+/*
+ * Taken from http://burtleburtle.net/bob/c/lookup3.c
+ * $FreeBSD$
+ */
+
+#include <sys/hash.h>
+#include <machine/endian.h>
+
+/*
+-------------------------------------------------------------------------------
+lookup3.c, by Bob Jenkins, May 2006, Public Domain.
+
+These are functions for producing 32-bit hashes for hash table lookup.
+hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() 
+are externally useful functions.  Routines to test the hash are included 
+if SELF_TEST is defined.  You can use this free for any purpose.  It's in
+the public domain.  It has no warranty.
+
+You probably want to use hashlittle().  hashlittle() and hashbig()
+hash byte arrays.  hashlittle() is is faster than hashbig() on
+little-endian machines.  Intel and AMD are little-endian machines.
+On second thought, you probably want hashlittle2(), which is identical to
+hashlittle() except it returns two 32-bit hashes for the price of one.  
+You could implement hashbig2() if you wanted but I haven't bothered here.
+
+If you want to find a hash of, say, exactly 7 integers, do
+  a = i1;  b = i2;  c = i3;
+  mix(a,b,c);
+  a += i4; b += i5; c += i6;
+  mix(a,b,c);
+  a += i7;
+  final(a,b,c);
+then use c as the hash value.  If you have a variable length array of
+4-byte integers to hash, use hashword().  If you have a byte array (like
+a character string), use hashlittle().  If you have several byte arrays, or
+a mix of things, see the comments above hashlittle().  
+
+Why is this so big?  I read 12 bytes at a time into 3 4-byte integers, 
+then mix those integers.  This is fast (you can do a lot more thorough
+mixing with 12*3 instructions on 3 integers than you can with 3 instructions
+on 1 byte), but shoehorning those bytes into integers efficiently is messy.
+-------------------------------------------------------------------------------
+*/
+
+#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k))))
+
+/*
+-------------------------------------------------------------------------------
+mix -- mix 3 32-bit values reversibly.
+
+This is reversible, so any information in (a,b,c) before mix() is
+still in (a,b,c) after mix().
+
+If four pairs of (a,b,c) inputs are run through mix(), or through
+mix() in reverse, there are at least 32 bits of the output that
+are sometimes the same for one pair and different for another pair.
+This was tested for:
+* pairs that differed by one bit, by two bits, in any combination
+  of top bits of (a,b,c), or in any combination of bottom bits of
+  (a,b,c).
+* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
+  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
+  is commonly produced by subtraction) look like a single 1-bit
+  difference.
+* the base values were pseudorandom, all zero but one bit set, or 
+  all zero plus a counter that starts at zero.
+
+Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
+satisfy this are
+    4  6  8 16 19  4
+    9 15  3 18 27 15
+   14  9  3  7 17  3
+Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
+for "differ" defined as + with a one-bit base and a two-bit delta.  I
+used http://burtleburtle.net/bob/hash/avalanche.html to choose 
+the operations, constants, and arrangements of the variables.
+
+This does not achieve avalanche.  There are input bits of (a,b,c)
+that fail to affect some output bits of (a,b,c), especially of a.  The
+most thoroughly mixed value is c, but it doesn't really even achieve
+avalanche in c.
+
+This allows some parallelism.  Read-after-writes are good at doubling
+the number of bits affected, so the goal of mixing pulls in the opposite
+direction as the goal of parallelism.  I did what I could.  Rotates
+seem to cost as much as shifts on every machine I could lay my hands
+on, and rotates are much kinder to the top and bottom bits, so I used
+rotates.
+-------------------------------------------------------------------------------
+*/
+#define mix(a,b,c) \
+{ \
+  a -= c;  a ^= rot(c, 4);  c += b; \
+  b -= a;  b ^= rot(a, 6);  a += c; \
+  c -= b;  c ^= rot(b, 8);  b += a; \
+  a -= c;  a ^= rot(c,16);  c += b; \
+  b -= a;  b ^= rot(a,19);  a += c; \
+  c -= b;  c ^= rot(b, 4);  b += a; \
+}
+
+/*
+-------------------------------------------------------------------------------
+final -- final mixing of 3 32-bit values (a,b,c) into c
+
+Pairs of (a,b,c) values differing in only a few bits will usually
+produce values of c that look totally different.  This was tested for
+* pairs that differed by one bit, by two bits, in any combination
+  of top bits of (a,b,c), or in any combination of bottom bits of
+  (a,b,c).
+* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
+  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
+  is commonly produced by subtraction) look like a single 1-bit
+  difference.
+* the base values were pseudorandom, all zero but one bit set, or 
+  all zero plus a counter that starts at zero.
+
+These constants passed:
+ 14 11 25 16 4 14 24
+ 12 14 25 16 4 14 24
+and these came close:
+  4  8 15 26 3 22 24
+ 10  8 15 26 3 22 24
+ 11  8 15 26 3 22 24
+-------------------------------------------------------------------------------
+*/
+#define final(a,b,c) \
+{ \
+  c ^= b; c -= rot(b,14); \
+  a ^= c; a -= rot(c,11); \
+  b ^= a; b -= rot(a,25); \
+  c ^= b; c -= rot(b,16); \
+  a ^= c; a -= rot(c,4);  \
+  b ^= a; b -= rot(a,14); \
+  c ^= b; c -= rot(b,24); \
+}
+
+/*
+--------------------------------------------------------------------
+ This works on all machines.  To be useful, it requires
+ -- that the key be an array of uint32_t's, and
+ -- that the length be the number of uint32_t's in the key
+
+ The function hashword() is identical to hashlittle() on little-endian
+ machines, and identical to hashbig() on big-endian machines,
+ except that the length has to be measured in uint32_ts rather than in
+ bytes.  hashlittle() is more complicated than hashword() only because
+ hashlittle() has to dance around fitting the key bytes into registers.
+--------------------------------------------------------------------
+*/
+uint32_t jenkins_hash32(
+const uint32_t *k,                   /* the key, an array of uint32_t values */
+size_t          length,               /* the length of the key, in uint32_ts */
+uint32_t        initval)         /* the previous hash, or an arbitrary value */
+{
+  uint32_t a,b,c;
+
+  /* Set up the internal state */
+  a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval;
+
+  /*------------------------------------------------- handle most of the key */
+  while (length > 3)
+  {
+    a += k[0];
+    b += k[1];
+    c += k[2];
+    mix(a,b,c);
+    length -= 3;
+    k += 3;
+  }
+
+  /*------------------------------------------- handle the last 3 uint32_t's */
+  switch(length)                     /* all the case statements fall through */
+  { 
+  case 3 : c+=k[2];
+  case 2 : b+=k[1];
+  case 1 : a+=k[0];
+    final(a,b,c);
+  case 0:     /* case 0: nothing left to add */
+    break;
+  }
+  /*------------------------------------------------------ report the result */
+  return c;
+}
+
+#if BYTE_ORDER == LITTLE_ENDIAN
+/*
+-------------------------------------------------------------------------------
+hashlittle() -- hash a variable-length key into a 32-bit value
+  k       : the key (the unaligned variable-length array of bytes)
+  length  : the length of the key, counting by bytes
+  initval : can be any 4-byte value
+Returns a 32-bit value.  Every bit of the key affects every bit of
+the return value.  Two keys differing by one or two bits will have
+totally different hash values.
+
+The best hash table sizes are powers of 2.  There is no need to do
+mod a prime (mod is sooo slow!).  If you need less than 32 bits,
+use a bitmask.  For example, if you need only 10 bits, do
+  h = (h & hashmask(10));
+In which case, the hash table should have hashsize(10) elements.
+
+If you are hashing n strings (uint8_t **)k, do it like this:
+  for (i=0, h=0; i<n; ++i) h = hashlittle( k[i], len[i], h);
+
+By Bob Jenkins, 2006.  bob_jenkins@burtleburtle.net.  You may use this
+code any way you wish, private, educational, or commercial.  It's free.
+
+Use for hash table lookup, or anything where one collision in 2^^32 is
+acceptable.  Do NOT use for cryptographic purposes.
+-------------------------------------------------------------------------------
+*/
+
+uint32_t jenkins_hash( const void *key, size_t length, uint32_t initval)
+{
+  uint32_t a,b,c;                                          /* internal state */
+  union { const void *ptr; size_t i; } u;     /* needed for Mac Powerbook G4 */
+
+  /* Set up the internal state */
+  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
+
+  u.ptr = key;
+  if ((u.i & 0x3) == 0) {
+    const uint32_t *k = (const uint32_t *)key;         /* read 32-bit chunks */
+
+    /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += k[0];
+      b += k[1];
+      c += k[2];
+      mix(a,b,c);
+      length -= 12;
+      k += 3;
+    }
+
+    /*----------------------------- handle the last (probably partial) block */
+    /* 
+     * "k[2]&0xffffff" actually reads beyond the end of the string, but
+     * then masks off the part it's not allowed to read.  Because the
+     * string is aligned, the masked-off tail is in the same word as the
+     * rest of the string.  Every machine with memory protection I've seen
+     * does it on word boundaries, so is OK with this.  But VALGRIND will
+     * still catch it and complain.  The masking trick does make the hash
+     * noticably faster for short strings (like English words).
+     */
+
+    switch(length)
+    {
+    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
+    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
+    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
+    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
+    case 8 : b+=k[1]; a+=k[0]; break;
+    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
+    case 6 : b+=k[1]&0xffff; a+=k[0]; break;
+    case 5 : b+=k[1]&0xff; a+=k[0]; break;
+    case 4 : a+=k[0]; break;
+    case 3 : a+=k[0]&0xffffff; break;
+    case 2 : a+=k[0]&0xffff; break;
+    case 1 : a+=k[0]&0xff; break;
+    case 0 : return c;              /* zero length strings require no mixing */
+    }
+
+  } else if ((u.i & 0x1) == 0) {
+    const uint16_t *k = (const uint16_t *)key;         /* read 16-bit chunks */
+    const uint8_t  *k8;
+
+    /*--------------- all but last block: aligned reads and different mixing */
+    while (length > 12)
+    {
+      a += k[0] + (((uint32_t)k[1])<<16);
+      b += k[2] + (((uint32_t)k[3])<<16);
+      c += k[4] + (((uint32_t)k[5])<<16);
+      mix(a,b,c);
+      length -= 12;
+      k += 6;
+    }
+
+    /*----------------------------- handle the last (probably partial) block */
+    k8 = (const uint8_t *)k;
+    switch(length)
+    {
+    case 12: c+=k[4]+(((uint32_t)k[5])<<16);
+             b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 11: c+=((uint32_t)k8[10])<<16;     /* fall through */
+    case 10: c+=k[4];
+             b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 9 : c+=k8[8];                      /* fall through */
+    case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 7 : b+=((uint32_t)k8[6])<<16;      /* fall through */
+    case 6 : b+=k[2];
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 5 : b+=k8[4];                      /* fall through */
+    case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 3 : a+=((uint32_t)k8[2])<<16;      /* fall through */
+    case 2 : a+=k[0];
+             break;
+    case 1 : a+=k8[0];
+             break;
+    case 0 : return c;                     /* zero length requires no mixing */
+    }
+
+  } else {                        /* need to read the key one byte at a time */
+    const uint8_t *k = (const uint8_t *)key;
+
+    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += k[0];
+      a += ((uint32_t)k[1])<<8;
+      a += ((uint32_t)k[2])<<16;
+      a += ((uint32_t)k[3])<<24;
+      b += k[4];
+      b += ((uint32_t)k[5])<<8;
+      b += ((uint32_t)k[6])<<16;
+      b += ((uint32_t)k[7])<<24;
+      c += k[8];
+      c += ((uint32_t)k[9])<<8;
+      c += ((uint32_t)k[10])<<16;
+      c += ((uint32_t)k[11])<<24;
+      mix(a,b,c);
+      length -= 12;
+      k += 12;
+    }
+
+    /*-------------------------------- last block: affect all 32 bits of (c) */
+    switch(length)                   /* all the case statements fall through */
+    {
+    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];
+             break;
+    case 0 : return c;
+    }
+  }
+
+  final(a,b,c);
+  return c;
+}
+
+#else /* !(BYTE_ORDER == LITTLE_ENDIAN) */
+
+/*
+ * hashbig():
+ * This is the same as hashword() on big-endian machines.  It is different
+ * from hashlittle() on all machines.  hashbig() takes advantage of
+ * big-endian byte ordering. 
+ */
+uint32_t jenkins_hash( const void *key, size_t length, uint32_t initval)
+{
+  uint32_t a,b,c;
+  union { const void *ptr; size_t i; } u; /* to cast key to (size_t) happily */
+
+  /* Set up the internal state */
+  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
+
+  u.ptr = key;
+  if ((u.i & 0x3) == 0) {
+    const uint32_t *k = (const uint32_t *)key;         /* read 32-bit chunks */
+
+    /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += k[0];
+      b += k[1];
+      c += k[2];
+      mix(a,b,c);
+      length -= 12;
+      k += 3;
+    }
+
+    /*----------------------------- handle the last (probably partial) block */
+    /* 
+     * "k[2]<<8" actually reads beyond the end of the string, but
+     * then shifts out the part it's not allowed to read.  Because the
+     * string is aligned, the illegal read is in the same word as the
+     * rest of the string.  Every machine with memory protection I've seen
+     * does it on word boundaries, so is OK with this.  But VALGRIND will
+     * still catch it and complain.  The masking trick does make the hash
+     * noticably faster for short strings (like English words).
+     */
+
+    switch(length)
+    {
+    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
+    case 11: c+=k[2]&0xffffff00; b+=k[1]; a+=k[0]; break;
+    case 10: c+=k[2]&0xffff0000; b+=k[1]; a+=k[0]; break;
+    case 9 : c+=k[2]&0xff000000; b+=k[1]; a+=k[0]; break;
+    case 8 : b+=k[1]; a+=k[0]; break;
+    case 7 : b+=k[1]&0xffffff00; a+=k[0]; break;
+    case 6 : b+=k[1]&0xffff0000; a+=k[0]; break;
+    case 5 : b+=k[1]&0xff000000; a+=k[0]; break;
+    case 4 : a+=k[0]; break;
+    case 3 : a+=k[0]&0xffffff00; break;
+    case 2 : a+=k[0]&0xffff0000; break;
+    case 1 : a+=k[0]&0xff000000; break;
+    case 0 : return c;              /* zero length strings require no mixing */
+    }
+
+  } else {                        /* need to read the key one byte at a time */
+    const uint8_t *k = (const uint8_t *)key;
+
+    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += ((uint32_t)k[0])<<24;
+      a += ((uint32_t)k[1])<<16;
+      a += ((uint32_t)k[2])<<8;
+      a += ((uint32_t)k[3]);
+      b += ((uint32_t)k[4])<<24;
+      b += ((uint32_t)k[5])<<16;
+      b += ((uint32_t)k[6])<<8;
+      b += ((uint32_t)k[7]);
+      c += ((uint32_t)k[8])<<24;
+      c += ((uint32_t)k[9])<<16;
+      c += ((uint32_t)k[10])<<8;
+      c += ((uint32_t)k[11]);
+      mix(a,b,c);
+      length -= 12;
+      k += 12;
+    }
+
+    /*-------------------------------- last block: affect all 32 bits of (c) */
+    switch(length)                   /* all the case statements fall through */
+    {
+    case 12: c+=k[11];
+    case 11: c+=((uint32_t)k[10])<<8;
+    case 10: c+=((uint32_t)k[9])<<16;
+    case 9 : c+=((uint32_t)k[8])<<24;
+    case 8 : b+=k[7];
+    case 7 : b+=((uint32_t)k[6])<<8;
+    case 6 : b+=((uint32_t)k[5])<<16;
+    case 5 : b+=((uint32_t)k[4])<<24;
+    case 4 : a+=k[3];
+    case 3 : a+=((uint32_t)k[2])<<8;
+    case 2 : a+=((uint32_t)k[1])<<16;
+    case 1 : a+=((uint32_t)k[0])<<24;
+             break;
+    case 0 : return c;
+    }
+  }
+
+  final(a,b,c);
+  return c;
+}
+#endif
diff --git a/sys/net/flowtable.c b/sys/net/flowtable.c
index 2e209ef0fa1f..6995798b3117 100644
--- a/sys/net/flowtable.c
+++ b/sys/net/flowtable.c
@@ -41,6 +41,7 @@ __FBSDID("$FreeBSD$");
 #include <sys/bitstring.h>
 #include <sys/condvar.h>
 #include <sys/callout.h>
+#include <sys/hash.h>
 #include <sys/kernel.h>  
 #include <sys/kthread.h>
 #include <sys/limits.h>
@@ -73,7 +74,6 @@ __FBSDID("$FreeBSD$");
 #include <netinet/udp.h>
 #include <netinet/sctp.h>
 
-#include <libkern/jenkins.h>
 #include <ddb/ddb.h>
 
 struct ipv4_tuple {
@@ -585,7 +585,7 @@ ipv4_flow_lookup_hash_internal(
 	} else
 		offset = V_flow_hashjitter + proto;
 
-	return (jenkins_hashword(key, 3, offset));
+	return (jenkins_hash32(key, 3, offset));
 }
 
 static struct flentry *
@@ -791,7 +791,7 @@ ipv6_flow_lookup_hash_internal(
 	} else
 		offset = V_flow_hashjitter + proto;
 
-	return (jenkins_hashword(key, 9, offset));
+	return (jenkins_hash32(key, 9, offset));
 }
 
 static struct flentry *
diff --git a/sys/sys/hash.h b/sys/sys/hash.h
index 6ad89c5ef905..ca9cc6789f02 100644
--- a/sys/sys/hash.h
+++ b/sys/sys/hash.h
@@ -118,4 +118,13 @@ hash32_strne(const void *buf, size_t len, int end, const char **ep,
 
 	return hash;
 }
+
+#ifdef _KERNEL
+/*
+ * Hashing function from Bob Jenkins. Implementation in libkern/jenkins_hash.c.
+ */
+uint32_t jenkins_hash(const void *, size_t, uint32_t);
+uint32_t jenkins_hash32(const uint32_t *, size_t, uint32_t);
+#endif /* _KERNEL */
+
 #endif /* !_SYS_HASH_H_ */