Merge branch 'hash' of git://ftp.sciencehorizons.net/linux

Pull string hash improvements from George Spelvin:
 "This series does several related things:

   - Makes the dcache hash (fs/namei.c) useful for general kernel use.

     (Thanks to Bruce for noticing the zero-length corner case)

   - Converts the string hashes in <linux/sunrpc/svcauth.h> to use the
     above.

   - Avoids 64-bit multiplies in hash_64() on 32-bit platforms.  Two
     32-bit multiplies will do well enough.

   - Rids the world of the bad hash multipliers in hash_32.

     This finishes the job started in commit 689de1d6ca95 ("Minimal
     fix-up of bad hashing behavior of hash_64()")

     The vast majority of Linux architectures have hardware support for
     32x32-bit multiply and so derive no benefit from "simplified"
     multipliers.

     The few processors that do not (68000, h8/300 and some models of
     Microblaze) have arch-specific implementations added.  Those
     patches are last in the series.

   - Overhauls the dcache hash mixing.

     The patch in commit 0fed3ac866ea ("namei: Improve hash mixing if
     CONFIG_DCACHE_WORD_ACCESS") was an off-the-cuff suggestion.
     Replaced with a much more careful design that's simultaneously
     faster and better.  (My own invention, as there was noting suitable
     in the literature I could find.  Comments welcome!)

   - Modify the hash_name() loop to skip the initial HASH_MIX().  This
     would let us salt the hash if we ever wanted to.

   - Sort out partial_name_hash().

     The hash function is declared as using a long state, even though
     it's truncated to 32 bits at the end and the extra internal state
     contributes nothing to the result.  And some callers do odd things:

      - fs/hfs/string.c only allocates 32 bits of state
      - fs/hfsplus/unicode.c uses it to hash 16-bit unicode symbols not bytes

   - Modify bytemask_from_count to handle inputs of 1..sizeof(long)
     rather than 0..sizeof(long)-1.  This would simplify users other
     than full_name_hash"

  Special thanks to Bruce Fields for testing and finding bugs in v1.  (I
  learned some humbling lessons about "obviously correct" code.)

  On the arch-specific front, the m68k assembly has been tested in a
  standalone test harness, I've been in contact with the Microblaze
  maintainers who mostly don't care, as the hardware multiplier is never
  omitted in real-world applications, and I haven't heard anything from
  the H8/300 world"

* 'hash' of git://ftp.sciencehorizons.net/linux:
  h8300: Add <asm/hash.h>
  microblaze: Add <asm/hash.h>
  m68k: Add <asm/hash.h>
  <linux/hash.h>: Add support for architecture-specific functions
  fs/namei.c: Improve dcache hash function
  Eliminate bad hash multipliers from hash_32() and  hash_64()
  Change hash_64() return value to 32 bits
  <linux/sunrpc/svcauth.h>: Define hash_str() in terms of hashlen_string()
  fs/namei.c: Add hashlen_string() function
  Pull out string hash to <linux/stringhash.h>

1 files changed, 9 insertions, 31 deletions

diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index c00f53a4ccdd..91d5a5d6f52b 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -16,6 +16,7 @@
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/gss_api.h>
 #include <linux/hash.h>
+#include <linux/stringhash.h>
 #include <linux/cred.h>
 
 struct svc_cred {
@@ -165,41 +166,18 @@ extern int svcauth_unix_set_client(struct svc_rqst *rqstp);
 extern int unix_gid_cache_create(struct net *net);
 extern void unix_gid_cache_destroy(struct net *net);
 
-static inline unsigned long hash_str(char *name, int bits)
+/*
+ * The <stringhash.h> functions are good enough that we don't need to
+ * use hash_32() on them; just extracting the high bits is enough.
+ */
+static inline unsigned long hash_str(char const *name, int bits)
 {
-        unsigned long hash = 0;
-        unsigned long l = 0;
-        int len = 0;
-        unsigned char c;
-        do {
-                if (unlikely(!(c = *name++))) {
-                        c = (char)len; len = -1;
-                }
-                l = (l << 8) | c;
-                len++;
-                if ((len & (BITS_PER_LONG/8-1))==0)
-                        hash = hash_long(hash^l, BITS_PER_LONG);
-        } while (len);
-        return hash >> (BITS_PER_LONG - bits);
+        return hashlen_hash(hashlen_string(name)) >> (32 - bits);
 }
 
-static inline unsigned long hash_mem(char *buf, int length, int bits)
+static inline unsigned long hash_mem(char const *buf, int length, int bits)
 {
-        unsigned long hash = 0;
-        unsigned long l = 0;
-        int len = 0;
-        unsigned char c;
-        do {
-                if (len == length) {
-                        c = (char)len; len = -1;
-                } else
-                        c = *buf++;
-                l = (l << 8) | c;
-                len++;
-                if ((len & (BITS_PER_LONG/8-1))==0)
-                        hash = hash_long(hash^l, BITS_PER_LONG);
-        } while (len);
-        return hash >> (BITS_PER_LONG - bits);
+        return full_name_hash(buf, length) >> (32 - bits);
 }
 
 #endif /* __KERNEL__ */