cpufreq: Pass the policy to cpufreq_driver->adjust_perf()

cpufreq_cpu_get() can sleep on PREEMPT_RT in presence of concurrent
writer(s), however amd-pstate depends on fetching the cpudata via the
policy's driver data which necessitates grabbing the reference.

Since schedutil governor can call "cpufreq_driver->update_perf()"
during sched_tick/enqueue/dequeue with rq_lock held and IRQs disabled,
fetching the policy object using the cpufreq_cpu_get() helper in the
scheduler fast-path leads to "BUG: scheduling while atomic" on
PREEMPT_RT [1].

Pass the cached cpufreq policy object in sg_policy to the update_perf()
instead of just the CPU. The CPU can be inferred using "policy->cpu".

The lifetime of cpufreq_policy object outlasts that of the governor and
the cpufreq driver (allocated when the CPU is onlined and only reclaimed
when the CPU is offlined / the CPU device is removed) which makes it
safe to be referenced throughout the governor's lifetime.

Closes:https://lore.kernel.org/all/20250731092316.3191-1-spasswolf@web.de/ [1]

Fixes: 1d215f0319c2 ("cpufreq: amd-pstate: Add fast switch function for AMD P-State")
Reported-by: Bert Karwatzki <spasswolf@web.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Gary Guo <gary@garyguo.net> # Rust
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Reviewed-by: Zhongqiu Han <zhongqiu.han@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260316081849.19368-3-kprateek.nayak@amd.com
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>

3 files changed, 6 insertions, 7 deletions

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 2ea4d27fe020..c825fab0bf5c 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -788,13 +788,12 @@ static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
 	return policy->cur;
 }
 
-static void amd_pstate_adjust_perf(unsigned int cpu,
+static void amd_pstate_adjust_perf(struct cpufreq_policy *policy,
 				   unsigned long _min_perf,
 				   unsigned long target_perf,
 				   unsigned long capacity)
 {
 	u8 max_perf, min_perf, des_perf, cap_perf;
-	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata;
 	union perf_cached perf;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 277884d91913..90e939069cde 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2231,7 +2231,7 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 
 /**
  * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go.
- * @cpu: Target CPU.
+ * @policy: cpufreq policy object of the target CPU.
  * @min_perf: Minimum (required) performance level (units of @capacity).
  * @target_perf: Target (desired) performance level (units of @capacity).
  * @capacity: Capacity of the target CPU.
@@ -2250,12 +2250,12 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
  * parallel with either ->target() or ->target_index() or ->fast_switch() for
  * the same CPU.
  */
-void cpufreq_driver_adjust_perf(unsigned int cpu,
+void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy,
 				 unsigned long min_perf,
 				 unsigned long target_perf,
 				 unsigned long capacity)
 {
-	cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity);
+	cpufreq_driver->adjust_perf(policy, min_perf, target_perf, capacity);
 }
 
 /**
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 11c58af41900..0f50034e4b68 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -3239,12 +3239,12 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	return target_pstate * cpu->pstate.scaling;
 }
 
-static void intel_cpufreq_adjust_perf(unsigned int cpunum,
+static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy,
 				      unsigned long min_perf,
 				      unsigned long target_perf,
 				      unsigned long capacity)
 {
-	struct cpudata *cpu = all_cpu_data[cpunum];
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached);
 	int old_pstate = cpu->pstate.current_pstate;
 	int cap_pstate, min_pstate, max_pstate, target_pstate;