2021-05-21 20:22:38

by Vincent Donnefort

Subject: [PATCH v2 1/3] PM / EM: Fix inefficient state detection

Currently, a debug message is printed if an inefficient state is detected
in the Energy Model. Unfortunately, it won't detect if the first state is
inefficient or if two successive states are. Fix this behavior.

Signed-off-by: Vincent Donnefort <[email protected]>

diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0c620eb..c4871a8 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -107,8 +107,7 @@ static void em_debug_remove_pd(struct device *dev) {}
static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
int nr_states, struct em_data_callback *cb)
{
- unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
- unsigned long power, freq, prev_freq = 0;
+ unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX;
struct em_perf_state *table;
int i, ret;
u64 fmax;
@@ -153,25 +152,19 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,

table[i].power = power;
table[i].frequency = prev_freq = freq;
-
- /*
- * The hertz/watts efficiency ratio should decrease as the
- * frequency grows on sane platforms. But this isn't always
- * true in practice so warn the user if a higher OPP is more
- * power efficient than a lower one.
- */
- opp_eff = freq / power;
- if (opp_eff >= prev_opp_eff)
- dev_dbg(dev, "EM: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
- i, i - 1);
- prev_opp_eff = opp_eff;
}

/* Compute the cost of each performance state. */
fmax = (u64) table[nr_states - 1].frequency;
- for (i = 0; i < nr_states; i++) {
+ for (i = nr_states - 1; i >= 0; i--) {
table[i].cost = div64_u64(fmax * table[i].power,
table[i].frequency);
+ if (table[i].cost >= prev_cost) {
+ dev_dbg(dev, "EM: OPP:%lu is inefficient\n",
+ table[i].frequency);
+ } else {
+ prev_cost = table[i].cost;
+ }
}

pd->table = table;
--
2.7.4

2021-05-24 12:44:29

by Lukasz Luba

Subject: Re: [PATCH v2 1/3] PM / EM: Fix inefficient state detection

On 5/21/21 5:54 PM, Vincent Donnefort wrote:
> Currently, a debug message is printed if an inefficient state is detected
> in the Energy Model. Unfortunately, it won't detect if the first state is
> inefficient or if two successive states are. Fix this behavior.
>
> Signed-off-by: Vincent Donnefort <[email protected]>
>
> diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
> index 0c620eb..c4871a8 100644
> --- a/kernel/power/energy_model.c
> +++ b/kernel/power/energy_model.c

Reviewed-by: Lukasz Luba <[email protected]>

2021-05-25 10:32:35

by Quentin Perret

Subject: Re: [PATCH v2 1/3] PM / EM: Fix inefficient state detection

On Friday 21 May 2021 at 17:54:22 (+0100), Vincent Donnefort wrote:
> Currently, a debug message is printed if an inefficient state is detected
> in the Energy Model. Unfortunately, it won't detect if the first state is
> inefficient or if two successive states are. Fix this behavior.

Right, and the first OPPs in the table often are the inefficient ones
(because e.g. they share the same voltage), so this definitely wants
fixing. I wonder if this wants a Fixes: tag even?

> Signed-off-by: Vincent Donnefort <[email protected]>

Reviewed-by: Quentin Perret <[email protected]>

Thanks,
Quentin