alpha: Use new generic strncpy_from_user() and strnlen_user()

Similar to x86/sparc/powerpc implementations except:
1) we implement an extremely efficient has_zero()/find_zero()
   sequence with both prep_zero_mask() and create_zero_mask()
   no-operations.
2) Our output from prep_zero_mask() differs in that only the
   lowest eight bits are used to represent the zero bytes
   nevertheless it can be safely ORed with other similar masks
   from prep_zero_mask() and forms input to create_zero_mask(),
   the two fundamental properties prep_zero_mask() must satisfy.

Tests on EV67 and EV68 CPUs revealed that the generic code is
essentially as fast (to within 0.5% of CPU cycles) of the old
Alpha specific code for large quadword-aligned strings, despite
the 30% extra CPU instructions executed.  In contrast, the
generic code for unaligned strings is substantially slower (by
more than a factor of 3) than the old Alpha specific code.

Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Acked-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 60 insertions, 29 deletions

diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index b49ec2f8d6e3..766fdfde2b7a 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -433,36 +433,12 @@ clear_user(void __user *to, long len)
 #undef __module_address
 #undef __module_call
 
-/* Returns: -EFAULT if exception before terminator, N if the entire
-   buffer filled, else strlen.  */
+#define user_addr_max() \
+        (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
-extern long __strncpy_from_user(char *__to, const char __user *__from, long __to_len);
-
-extern inline long
-strncpy_from_user(char *to, const char __user *from, long n)
-{
-        long ret = -EFAULT;
-        if (__access_ok((unsigned long)from, 0, get_fs()))
-                ret = __strncpy_from_user(to, from, n);
-        return ret;
-}
-
-/* Returns: 0 if bad, string length+1 (memory size) of string if ok */
-extern long __strlen_user(const char __user *);
-
-extern inline long strlen_user(const char __user *str)
-{
-        return access_ok(VERIFY_READ,str,0) ? __strlen_user(str) : 0;
-}
-
-/* Returns: 0 if exception before NUL or reaching the supplied limit (N),
- * a value greater than N if the limit would be exceeded, else strlen.  */
-extern long __strnlen_user(const char __user *, long);
-
-extern inline long strnlen_user(const char __user *str, long n)
-{
-        return access_ok(VERIFY_READ,str,0) ? __strnlen_user(str, n) : 0;
-}
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
 
 /*
  * About the exception table:
diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..6b340d0f1521
--- /dev/null
+++ b/arch/alpha/include/asm/word-at-a-time.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+#include <asm/compiler.h>
+
+/*
+ * word-at-a-time interface for Alpha.
+ */
+
+/*
+ * We do not use the word_at_a_time struct on Alpha, but it needs to be
+ * implemented to humour the generic code.
+ */
+struct word_at_a_time {
+        const unsigned long unused;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { 0 }
+
+/* Return nonzero if val has a zero */
+static inline unsigned long has_zero(unsigned long val, unsigned long *bits, const struct word_at_a_time *c)
+{
+        unsigned long zero_locations = __kernel_cmpbge(0, val);
+        *bits = zero_locations;
+        return zero_locations;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val, unsigned long bits, const struct word_at_a_time *c)
+{
+        return bits;
+}
+
+#define create_zero_mask(bits) (bits)
+
+static inline unsigned long find_zero(unsigned long bits)
+{
+#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67)
+        /* Simple if have CIX instructions */
+        return __kernel_cttz(bits);
+#else
+        unsigned long t1, t2, t3;
+        /* Retain lowest set bit only */
+        bits &= -bits;
+        /* Binary search for lowest set bit */
+        t1 = bits & 0xf0;
+        t2 = bits & 0xcc;
+        t3 = bits & 0xaa;
+        if (t1) t1 = 4;
+        if (t2) t2 = 2;
+        if (t3) t3 = 1;
+        return t1 + t2 + t3;
+#endif
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */