common implementation of iterative div/mod

We have a few instances of the open-coded iterative div/mod loop, used when we don't expcet the dividend to be much bigger than the divisor. Unfortunately modern gcc's have the tendency to strength "reduce" this into a full mod operation, which isn't necessarily any faster, and even if it were, doesn't exist if gcc implements it in libgcc.

The workaround is to put a dummy asm statement in the loop to prevent gcc from performing the transformation.

This patch creates a single implementation of this loop, and uses it to replace the open-coded versions I know about.

[ Andrew: this patch has your fixes folded into it. ]

---

arch/x86/xen/time.c    |   13 +++----------
include/linux/math64.h |    2 ++
include/linux/time.h   |   11 ++---------
lib/div64.c            |   23 +++++++++++++++++++++++
4 files changed, 30 insertions(+), 19 deletions(-)

===================================================================

@@ -12,6 +12,7 @@

#include <linux/clocksource.h>
#include <linux/clockchips.h>
#include <linux/kernel_stat.h>
+#include <linux/math64.h>

#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
@@ -150,11 +151,7 @@

	if (stolen < 0)
		stolen = 0;

- ticks = 0;
- while (stolen >= NS_PER_TICK) {
- ticks++;
- stolen -= NS_PER_TICK;
- }

+	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
	__get_cpu_var(residual_stolen) = stolen;
	account_steal_time(NULL, ticks);

@@ -166,11 +163,7 @@

	if (blocked < 0)
		blocked = 0;

- ticks = 0;
- while (blocked >= NS_PER_TICK) {
- ticks++;
- blocked -= NS_PER_TICK;
- }

+	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
	__get_cpu_var(residual_blocked) = blocked;
	account_steal_time(idle_task(smp_processor_id()), ticks);
}

===================================================================

@@ -81,4 +81,6 @@

}
#endif

+u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); +
#endif /* _LINUX_MATH64_H */
===================================================================

@@ -6,6 +6,7 @@

#ifdef __KERNEL__

# include <linux/cache.h>
# include <linux/seqlock.h>
+# include <linux/math64.h>
#endif

#ifndef _STRUCT_TIMESPEC
@@ -172,15 +173,7 @@
*/
static inline void timespec_add_ns(struct timespec *a, u64 ns) {
- ns += a->tv_nsec;
- while(unlikely(ns >= NSEC_PER_SEC)) {
- /* The following asm() prevents the compiler from
- * optimising this loop into a modulo operation. */
- asm("" : "+r"(ns));
-
- ns -= NSEC_PER_SEC;
- a->tv_sec++;
- }

+	a->tv_sec += iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
	a->tv_nsec = ns;
}

#endif /* __KERNEL__ */
===================================================================

@@ -98,3 +98,26 @@

#endif

#endif /* BITS_PER_LONG == 32 */
+
+/*
+ * Iterative div/mod for use when dividend is not expected to be much
+ * bigger than divisor.
+ */
+u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{
+ u32 ret = 0;
+
+ while (dividend >= divisor) {
+ /* The following asm() prevents the compiler from
+ optimising this loop into a modulo operation. */
+ asm("" : "+rm"(dividend));
+
+ dividend -= divisor;
+ ret++;
+ }
+
+ *remainder = dividend;
+
+ return ret;
+}
+EXPORT_SYMBOL(iter_div_u64_rem);