diff options
| author | Javi Merino <javi.merino@arm.com> | 2015-05-02 11:15:24 +0200 |
|---|---|---|
| committer | Eduardo Valentin <edubezval@gmail.com> | 2015-05-12 03:57:44 +0200 |
| commit | ea54cac9065112724f3432e0574ba3e346fd695d (patch) | |
| tree | 1d8fab906d5d50ee2ebf374ac480b1559fdfd077 /drivers/thermal/power_allocator.c | |
| parent | thermal: exynos: Add the support for Exynos5433 TMU (diff) | |
| download | linux-ea54cac9065112724f3432e0574ba3e346fd695d.tar.xz linux-ea54cac9065112724f3432e0574ba3e346fd695d.zip | |
thermal: power_allocator: round the division when divvying up power
In situations where there is an uneven number of cooling devices, the
division of power among them can lead to a milliwatt being dropped on
the floor due to rounding errors. This doesn't sound like a lot, but
some devices only grant the lowest cooling device state for their
maximum power. So for instance, if the granted_power is the maximum
power and all devices are getting their maximum power, one would get
max_power - 1, making it choose cooling device state 1, instead of 0.
Round the division to make the calculation more accurate.
Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
Diffstat (limited to 'drivers/thermal/power_allocator.c')
| -rw-r--r-- | drivers/thermal/power_allocator.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 3ca7530deac6..4672250b329f 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -196,7 +196,8 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors, for (i = 0; i < num_actors; i++) { u64 req_range = req_power[i] * power_range; - granted_power[i] = div_u64(req_range, total_req_power); + granted_power[i] = DIV_ROUND_CLOSEST_ULL(req_range, + total_req_power); if (granted_power[i] > max_power[i]) { extra_power += granted_power[i] - max_power[i]; |