From: Wu Zhangjin <wuzhangjin@xxxxxxxxx>
Changes:
v2 -> v3:
o use 32bit instead of 64bit for mult and shift as the 'struct
clocksource' does, which saves several instructions for the 32bit
version of mips_cyc2ns().
o removes the 'easy way' of 128bit arithmatic for it not work with
some compilers. (feedback from David)
v1 -> v2:
o change the old mips_sched_clock() to mips_cyc2ns() and modify the
arguments to support 32bit.
o add 32bit support: use a smaller shift to avoid the quick overflow
of 64bit arithmatic and balance the overhead of the 128bit arithmatic
and the precision lost with the smaller shift.
----------------------
Because the high resolution sched_clock() for r4k has the same overflow
problem and solution mentioned in "MIPS: Octeon: Use non-overflowing
arithmetic in sched_clock".
"With typical mult and shift values, the calculation for Octeon's
sched_clock overflows when using 64-bit arithmetic. Use 128-bit
calculations instead."
To reduce the duplication, This patch abstracts the solution into an
inline funciton mips_cyc2ns() into arch/mips/include/asm/time.h from
arch/mips/cavium-octeon/csrc-octeon.c.
Two patches for Cavium and R4K will be sent out respectively to use this
common function.
Signed-off-by: Wu Zhangjin <wuzhangjin@xxxxxxxxx>
---
arch/mips/include/asm/time.h | 34 ++++++++++++++++++++++++++++++++++
1 files changed, 34 insertions(+), 0 deletions(-)
diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
index c7f1bfe..f0ee643 100644
--- a/arch/mips/include/asm/time.h
+++ b/arch/mips/include/asm/time.h
@@ -96,4 +96,38 @@ static inline void clockevent_set_clock(struct clock_event_device *cd,
clockevents_calc_mult_shift(cd, clock, 4);
}
+static inline unsigned long long mips_cyc2ns(u64 cyc, u32 __mult, u32 __shift)
+{
+#ifdef CONFIG_32BIT
+ /*
+ * To balance the overhead of 128bit-arithematic and the precision
+ * lost, we choose a smaller shift to avoid the quick overflow as the
+ * X86 & ARM does. please refer to arch/x86/kernel/tsc.c and
+ * arch/arm/plat-orion/time.c
+ */
+ return (cyc * __mult) >> __shift;
+#else /* CONFIG_64BIT */
+ /* 64-bit arithmatic can overflow, so use 128-bit */
+ u64 t1, t2, t3;
+ unsigned long long rv;
+ u64 mult, shift;
+ mult = __mult;
+ shift = __shift;
+
+ asm (
+ "dmultu\t%[cyc],%[mult]\n\t"
+ "nor\t%[t1],$0,%[shift]\n\t"
+ "mfhi\t%[t2]\n\t"
+ "mflo\t%[t3]\n\t"
+ "dsll\t%[t2],%[t2],1\n\t"
+ "dsrlv\t%[rv],%[t3],%[shift]\n\t"
+ "dsllv\t%[t1],%[t2],%[t1]\n\t"
+ "or\t%[rv],%[t1],%[rv]\n\t"
+ : [rv] "=&r" (rv), [t1] "=&r" (t1), [t2] "=&r" (t2), [t3] "=&r" (t3)
+ : [cyc] "r" (cyc), [mult] "r" (mult), [shift] "r" (shift)
+ : "hi", "lo");
+ return rv;
+#endif
+}
+
#endif /* _ASM_TIME_H */
--
1.7.0.1
