cpufreq: Make drivers using CPUFREQ_ETERNAL specify transition latency

Commit a755d0e ("cpufreq: Honour transition_latency over
transition_delay_us") caused platforms where cpuinfo.transition_latency
is CPUFREQ_ETERNAL to get a very large transition latency whereas
previously it had been capped at 10 ms (and later at 2 ms).

This led to a user-observable regression between 6.6 and 6.12 as
described by Shawn:

"The dbs sampling_rate was 10000 us on 6.6 and suddently becomes
 6442450 us (4294967295 / 1000 * 1.5) on 6.12 for these platforms
 because the default transition delay was dropped [...].

 It slows down dbs governor's reacting to CPU loading change
 dramatically.  Also, as transition_delay_us is used by schedutil
 governor as rate_limit_us, it shows a negative impact on device
 idle power consumption, because the device gets slightly less time
 in the lowest OPP."

Evidently, the expectation of the drivers using CPUFREQ_ETERNAL as
cpuinfo.transition_latency was that it would be capped by the core,
but they may as well return a default transition latency value instead
of CPUFREQ_ETERNAL and the core need not do anything with it.

Accordingly, introduce CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS and make
all of the drivers in question use it instead of CPUFREQ_ETERNAL.  Also
update the related Rust binding.

Fixes: a755d0e ("cpufreq: Honour transition_latency over transition_delay_us")
Closes: https://lore.kernel.org/linux-pm/[email protected]/
Reported-by: Shawn Guo <[email protected]>
Reviewed-by: Mario Limonciello (AMD) <[email protected]>
Reviewed-by: Jie Zhan <[email protected]>
Acked-by: Viresh Kumar <[email protected]>
Cc: 6.6+ <[email protected]> # 6.6+
Signed-off-by: Rafael J. Wysocki <[email protected]>
Link: https://patch.msgid.link/[email protected]
[ rjw: Fix typo in new symbol name, drop redundant type cast from Rust binding ]
Tested-by: Shawn Guo <[email protected]> # with cpufreq-dt driver
Reviewed-by: Qais Yousef <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>

Author: rafaeljw

drivers/cpufreq/cpufreq-dt.c

@@ -104,7 +104,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
 	if (!transition_latency)
-		transition_latency = CPUFREQ_ETERNAL;
+		transition_latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	cpumask_copy(policy->cpus, priv->cpus);
 	policy->driver_data = priv;

drivers/cpufreq/imx6q-cpufreq.c

@@ -442,7 +442,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	if (of_property_read_u32(np, "clock-latency", &transition_latency))
-		transition_latency = CPUFREQ_ETERNAL;
+		transition_latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	/*
 	 * Calculate the ramp time for max voltage change in the

drivers/cpufreq/mediatek-cpufreq-hw.c

@@ -309,7 +309,7 @@ static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 
 	latency = readl_relaxed(data->reg_bases[REG_FREQ_LATENCY]) * 1000;
 	if (!latency)
-		latency = CPUFREQ_ETERNAL;
+		latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	policy->cpuinfo.transition_latency = latency;
 	policy->fast_switch_possible = true;

drivers/cpufreq/rcpufreq_dt.rs

@@ -123,7 +123,7 @@ impl cpufreq::Driver for CPUFreqDTDriver {
 
         let mut transition_latency = opp_table.max_transition_latency_ns() as u32;
         if transition_latency == 0 {
-            transition_latency = cpufreq::ETERNAL_LATENCY_NS;
+            transition_latency = cpufreq::DEFAULT_TRANSITION_LATENCY_NS;
         }
 
         policy

drivers/cpufreq/scmi-cpufreq.c

@@ -294,7 +294,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 
 	latency = perf_ops->transition_latency_get(ph, domain);
 	if (!latency)
-		latency = CPUFREQ_ETERNAL;
+		latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	policy->cpuinfo.transition_latency = latency;
 

drivers/cpufreq/scpi-cpufreq.c

@@ -157,7 +157,7 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 
 	latency = scpi_ops->get_transition_latency(cpu_dev);
 	if (!latency)
-		latency = CPUFREQ_ETERNAL;
+		latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	policy->cpuinfo.transition_latency = latency;
 

drivers/cpufreq/spear-cpufreq.c

@@ -182,7 +182,7 @@ static int spear_cpufreq_probe(struct platform_device *pdev)
 
 	if (of_property_read_u32(np, "clock-latency",
 				&spear_cpufreq.transition_latency))
-		spear_cpufreq.transition_latency = CPUFREQ_ETERNAL;
+		spear_cpufreq.transition_latency = CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 	cnt = of_property_count_u32_elems(np, "cpufreq_tbl");
 	if (cnt <= 0) {

include/linux/cpufreq.h

@@ -32,6 +32,9 @@
  */
 
 #define CPUFREQ_ETERNAL			(-1)
+
+#define CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS	NSEC_PER_MSEC
+
 #define CPUFREQ_NAME_LEN		16
 /* Print length for names. Extra 1 space for accommodating '\n' in prints */
 #define CPUFREQ_NAME_PLEN		(CPUFREQ_NAME_LEN + 1)

rust/kernel/cpufreq.rs

@@ -39,7 +39,8 @@ use macros::vtable;
 const CPUFREQ_NAME_LEN: usize = bindings::CPUFREQ_NAME_LEN as usize;
 
 /// Default transition latency value in nanoseconds.
-pub const ETERNAL_LATENCY_NS: u32 = bindings::CPUFREQ_ETERNAL as u32;
+pub const DEFAULT_TRANSITION_LATENCY_NS: u32 =
+        bindings::CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS;
 
 /// CPU frequency driver flags.
 pub mod flags {
@@ -400,13 +401,13 @@ impl TableBuilder {
 /// The following example demonstrates how to create a CPU frequency table.
 ///
 /// ```
-/// use kernel::cpufreq::{ETERNAL_LATENCY_NS, Policy};
+/// use kernel::cpufreq::{DEFAULT_TRANSITION_LATENCY_NS, Policy};
 ///
 /// fn update_policy(policy: &mut Policy) {
 ///     policy
 ///         .set_dvfs_possible_from_any_cpu(true)
 ///         .set_fast_switch_possible(true)
-///         .set_transition_latency_ns(ETERNAL_LATENCY_NS);
+///         .set_transition_latency_ns(DEFAULT_TRANSITION_LATENCY_NS);
 ///
 ///     pr_info!("The policy details are: {:?}\n", (policy.cpu(), policy.cur()));
 /// }