Merge branch 'perf/urgent' into perf/core, to pick up fixes before applying new changes

[deliverable/linux.git] / arch / x86 / kernel / tsc.c

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c8d52cb4cb6e8b9ee9d81cfc9c0fa3603284ce0e..69b84a26ea17a215bbd7169af0148b176b40f242 100644 (file)
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -21,6 +21,7 @@
 #include <asm/hypervisor.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/geode.h>
 
 unsigned int __read_mostly cpu_khz;    /* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -167,21 +168,20 @@ static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
  *              ns = cycles * cyc2ns_scale / SC
  *
  *      And since SC is a constant power of two, we can convert the div
- *  into a shift.
+ *  into a shift. The larger SC is, the more accurate the conversion, but
+ *  cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication
+ *  (64-bit result) can be used.
  *
- *  We can use khz divisor instead of mhz to keep a better precision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ *  We can use khz divisor instead of mhz to keep a better precision.
  *  (mathieu.desnoyers@polymtl.ca)
  *
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
 static void cyc2ns_data_init(struct cyc2ns_data *data)
 {
        data->cyc2ns_mul = 0;
-       data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+       data->cyc2ns_shift = 0;
        data->cyc2ns_offset = 0;
        data->__count = 0;
 }
@@ -215,14 +215,14 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 
        if (likely(data == tail)) {
                ns = data->cyc2ns_offset;
-               ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+               ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
        } else {
                data->__count++;
 
                barrier();
 
                ns = data->cyc2ns_offset;
-               ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+               ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
 
                barrier();
 
@@ -256,12 +256,11 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
         * time function is continuous; see the comment near struct
         * cyc2ns_data.
         */
-       data->cyc2ns_mul =
-               DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
-                                 cpu_khz);
-       data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+       clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz,
+                              NSEC_PER_MSEC, 0);
+
        data->cyc2ns_offset = ns_now -
-               mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+               mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
 
        cyc2ns_write_end(cpu, data);
 
@@ -1013,15 +1012,17 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
 static void __init check_system_tsc_reliable(void)
 {
-#ifdef CONFIG_MGEODE_LX
-       /* RTSC counts during suspend */
+#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
+       if (is_geode_lx()) {
+               /* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-       unsigned long res_low, res_high;
+               unsigned long res_low, res_high;
 
-       rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
-       /* Geode_LX - the OLPC CPU has a very reliable TSC */
-       if (res_low & RTSC_SUSP)
-               tsc_clocksource_reliable = 1;
+               rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+               /* Geode_LX - the OLPC CPU has a very reliable TSC */
+               if (res_low & RTSC_SUSP)
+                       tsc_clocksource_reliable = 1;
+       }
 #endif
        if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
                tsc_clocksource_reliable = 1;