| From | Andi Kleen <> | Subject | [PATCH] [26/99] cpuidle: menu: fixed wrapping timers at 4.294 seconds | Date | Wed, 27 Jul 2011 14:48:24 -0700 (PDT) |
| |
2.6.35-longterm review patch. If anyone has any objections, please let me know.
------------------ From: Tero Kristo <tero.kristo@nokia.com>
commit 7467571f4480b273007517b26297c07154c73924 upstream.
Cpuidle menu governor is using u32 as a temporary datatype for storing nanosecond values which wrap around at 4.294 seconds. This causes errors in predicted sleep times resulting in higher than should be C state selection and increased power consumption. This also breaks cpuidle state residency statistics.
Signed-off-by: Tero Kristo <tero.kristo@nokia.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Andi Kleen <ak@linux.intel.com>
--- drivers/cpuidle/governors/menu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
Index: linux-2.6.35.y/drivers/cpuidle/governors/menu.c =================================================================== --- linux-2.6.35.y.orig/drivers/cpuidle/governors/menu.c +++ linux-2.6.35.y/drivers/cpuidle/governors/menu.c @@ -236,6 +236,7 @@ static int menu_select(struct cpuidle_de int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY); int i; int multiplier; + struct timespec t; if (data->needs_update) { menu_update(dev); @@ -250,8 +251,9 @@ static int menu_select(struct cpuidle_de return 0; /* determine the expected residency time, round up */ + t = ktime_to_timespec(tick_nohz_get_sleep_length()); data->expected_us = - DIV_ROUND_UP((u32)ktime_to_ns(tick_nohz_get_sleep_length()), 1000); + t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC; data->bucket = which_bucket(data->expected_us);
|