vfs: use 'unsigned long' accesses for dcache name comparison and hashing

Ok, this is hacky, and only works on little-endian machines with goo
unaligned handling.  And even then only with CONFIG_DEBUG_PAGEALLOC
disabled, since it can access up to 7 bytes after the pathname.

But it runs like a bat out of hell.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5bed94e189fab8ef9bf24f038763ee90bc45b798..09675d3e0ac30c5e2e8b183fd6fecc7ee4daa3c8 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -82,6 +82,7 @@ config X86
        select CLKEVT_I8253
        select ARCH_HAVE_NMI_SAFE_CMPXCHG
        select GENERIC_IOMAP
+       select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
 
 config INSTRUCTION_DECODER
        def_bool (KPROBES || PERF_EVENTS)

diff --git a/fs/Kconfig b/fs/Kconfig
index d621f02a3f9e26ee9f98160566981c12be69e395..aa195265362f539fb6b5f1f87802b14d3ab1987a 100644 (file)
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -4,6 +4,10 @@
 
 menu "File systems"
 
+# Use unaligned word dcache accesses
+config DCACHE_WORD_ACCESS
+       bool
+
 if BLOCK
 
 source "fs/ext2/Kconfig"

diff --git a/fs/dcache.c b/fs/dcache.c
index bcbdb33fcc205aad37110be50752131aae894062..ffd47a16d870303bac9455961aa938c6aae298e5 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -144,6 +144,28 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
 static inline int dentry_cmp(const unsigned char *cs, size_t scount,
                                const unsigned char *ct, size_t tcount)
 {
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+       unsigned long a,b,mask;
+
+       if (unlikely(scount != tcount))
+               return 1;
+
+       for (;;) {
+               a = *(unsigned long *)cs;
+               b = *(unsigned long *)ct;
+               if (tcount < sizeof(unsigned long))
+                       break;
+               if (unlikely(a != b))
+                       return 1;
+               cs += sizeof(unsigned long);
+               ct += sizeof(unsigned long);
+               tcount -= sizeof(unsigned long);
+               if (!tcount)
+                       return 0;
+       }
+       mask = ~(~0ul << tcount*8);
+       return unlikely(!!((a ^ b) & mask));
+#else
        if (scount != tcount)
                return 1;
 
@@ -155,6 +177,7 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount,
                tcount--;
        } while (tcount);
        return 0;
+#endif
 }
 
 static void __d_free(struct rcu_head *head)

diff --git a/fs/namei.c b/fs/namei.c
index e2ba62820a0f35ee0531a4ad6ac0dc6725ad0b58..378497a744b4a2bc6b1a107eaeb689ffefec570c 100644 (file)
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1374,6 +1374,126 @@ static inline int can_lookup(struct inode *inode)
        return 1;
 }
 
+/*
+ * We can do the critical dentry name comparison and hashing
+ * operations one word at a time, but we are limited to:
+ *
+ * - Architectures with fast unaligned word accesses. We could
+ *   do a "get_unaligned()" if this helps and is sufficiently
+ *   fast.
+ *
+ * - Little-endian machines (so that we can generate the mask
+ *   of low bytes efficiently). Again, we *could* do a byte
+ *   swapping load on big-endian architectures if that is not
+ *   expensive enough to make the optimization worthless.
+ *
+ * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
+ *   do not trap on the (extremely unlikely) case of a page
+ *   crossing operation.
+ *
+ * - Furthermore, we need an efficient 64-bit compile for the
+ *   64-bit case in order to generate the "number of bytes in
+ *   the final mask". Again, that could be replaced with a
+ *   efficient population count instruction or similar.
+ */
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+       return mask*0x0001020304050608 >> 56;
+}
+
+static inline unsigned int fold_hash(unsigned long hash)
+{
+       hash += hash >> (8*sizeof(int));
+       return hash;
+}
+
+#else  /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+       /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+       long a = (0x0ff0001+mask) >> 23;
+       /* Fix the 1 for 00 case */
+       return a & mask;
+}
+
+#define fold_hash(x) (x)
+
+#endif
+
+unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+{
+       unsigned long a, mask;
+       unsigned long hash = 0;
+
+       for (;;) {
+               a = *(unsigned long *)name;
+               hash *= 9;
+               if (len < sizeof(unsigned long))
+                       break;
+               hash += a;
+               name += sizeof(unsigned long);
+               len -= sizeof(unsigned long);
+               if (!len)
+                       goto done;
+       }
+       mask = ~(~0ul << len*8);
+       hash += mask & a;
+done:
+       return fold_hash(hash);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+#define ONEBYTES       0x0101010101010101ul
+#define SLASHBYTES     0x2f2f2f2f2f2f2f2ful
+#define HIGHBITS       0x8080808080808080ul
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+       return ((a - ONEBYTES) & ~a) & HIGHBITS;
+}
+
+/*
+ * Calculate the length and hash of the path component, and
+ * return the length of the component;
+ */
+static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+{
+       unsigned long a, mask, hash, len;
+
+       hash = a = 0;
+       len = -sizeof(unsigned long);
+       do {
+               hash = (hash + a) * 9;
+               len += sizeof(unsigned long);
+               a = *(unsigned long *)(name+len);
+               /* Do we have any NUL or '/' bytes in this word? */
+               mask = has_zero(a) | has_zero(a ^ SLASHBYTES);
+       } while (!mask);
+
+       /* The mask *below* the first high bit set */
+       mask = (mask - 1) & ~mask;
+       mask >>= 7;
+       hash += a & mask;
+       *hashp = fold_hash(hash);
+
+       return len + count_masked_bytes(mask);
+}
+
+#else
+
 unsigned int full_name_hash(const unsigned char *name, unsigned int len)
 {
        unsigned long hash = init_name_hash();
@@ -1402,6 +1522,8 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp)
        return len;
 }
 
+#endif
+
 /*
  * Name resolution.
  * This is the basic name resolution function, turning a pathname into