[PATCH] Fix problem introduced by do_div() patch

 - export the __div64_32 symbol for modules;

 - add likely() to the fast path (divisor>>32 == 0);

 - add __attribute__((pure)) to __div64_32() prototype so
   the compiler knows global memory isn't clobbered;

 - avoid building __div64_32() on 64bit architectures.

include/asm-generic/div64.h

@@ -18,6 +18,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/compiler.h>
 
 #if BITS_PER_LONG == 64
 
@@ -31,12 +32,12 @@
 
 #elif BITS_PER_LONG == 32
 
-extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
+extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor) __attribute_pure__;
 
 # define do_div(n,base) ({				\
 	uint32_t __base = (base);			\
 	uint32_t __rem;					\
-	if (((n) >> 32) == 0) {				\
+	if (likely(((n) >> 32) == 0)) {			\
 		__rem = (uint32_t)(n) % __base;		\
 		(n) = (uint32_t)(n) / __base;		\
 	} else 						\

include/linux/compiler.h

@@ -56,6 +56,24 @@
 #define __attribute_used__	__attribute__((__unused__))
 #endif
 
+/*
+ * From the GCC manual:
+ *
+ * Many functions have no effects except the return value and their
+ * return value depends only on the parameters and/or global
+ * variables.  Such a function can be subject to common subexpression
+ * elimination and loop optimization just as an arithmetic operator
+ * would be.
+ * [...]
+ * The attribute `pure' is not implemented in GCC versions earlier
+ * than 2.96.
+ */
+#if (__GNUC__ == 2 && __GNUC_MINOR >= 96) || __GNUC__ > 2
+#define __attribute_pure__	__attribute__((pure))
+#else
+#define __attribute_pure__	/* unimplemented */
+#endif
+
 /* This macro obfuscates arithmetic on a variable address so that gcc
    shouldn't recognize the original var, and make assumptions about it */
 #define RELOC_HIDE(ptr, off)					\

lib/div64.c

@@ -12,13 +12,17 @@
  * The fast case for (n>>32 == 0) is handled inline by do_div(). 
  *
  * Code generated for this function might be very inefficient
- * for some CPUs. div64_32() can be overridden by linking arch-specific
+ * for some CPUs. __div64_32() can be overridden by linking arch-specific
  * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
  */
 
 #include <linux/types.h>
+#include <linux/module.h>
 #include <asm/div64.h>
 
+/* Not needed on 64bit architectures */
+#if BITS_PER_LONG == 32
+
 uint32_t __div64_32(uint64_t *n, uint32_t base)
 {
 	uint32_t low, low2, high, rem;
@@ -43,3 +47,6 @@ uint32_t __div64_32(uint64_t *n, uint32_t base)
 	return rem;
 }
 
+EXPORT_SYMBOL(__div64_32);
+
+#endif /* BITS_PER_LONG == 32 */