| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20260106073608.278644-3-kprateek.nayak@amd.com>
Date: Tue, 6 Jan 2026 07:36:08 +0000
From: K Prateek Nayak <kprateek.nayak@....com>
To: Huang Rui <ray.huang@....com>, "Gautham R. Shenoy"
<gautham.shenoy@....com>, Mario Limonciello <mario.limonciello@....com>,
"Rafael J. Wysocki" <rafael@...nel.org>, Viresh Kumar
<viresh.kumar@...aro.org>, Srinivas Pandruvada
<srinivas.pandruvada@...ux.intel.com>, Len Brown <lenb@...nel.org>,
"Sebastian Andrzej Siewior" <bigeasy@...utronix.de>, Clark Williams
<clrkwllms@...nel.org>, Bert Karwatzki <spasswolf@....de>,
<linux-pm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-rt-devel@...ts.linux.dev>
CC: Perry Yuan <perry.yuan@....com>
Subject: [RFC PATCH 2/2] 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.
Link: https://lore.kernel.org/all/20250731092316.3191-1-spasswolf@web.de/ [1]
Signed-off-by: K Prateek Nayak <kprateek.nayak@....com>
---
drivers/cpufreq/amd-pstate.c | 3 +--
drivers/cpufreq/cpufreq.c | 4 ++--
drivers/cpufreq/intel_pstate.c | 4 ++--
include/linux/cpufreq.h | 4 ++--
kernel/sched/cpufreq_schedutil.c | 5 +++--
5 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 5818a92d96b9..455e58a9b738 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -697,13 +697,12 @@ 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 50dde2980f1b..8bdc8f9b8d86 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2244,12 +2244,12 @@ 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 ec4abe374573..8d25f0f2925c 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -3237,12 +3237,12 @@ 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;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 0465d1e6f72a..fd26b3a4aa28 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -367,7 +367,7 @@ struct cpufreq_driver {
* conditions) scale invariance can be disabled, which causes the
* schedutil governor to fall back to the latter.
*/
- void (*adjust_perf)(unsigned int cpu,
+ void (*adjust_perf)(struct cpufreq_policy *policy,
unsigned long min_perf,
unsigned long target_perf,
unsigned long capacity);
@@ -612,7 +612,7 @@ struct cpufreq_governor {
/* Pass a target to the cpufreq driver */
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq);
-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);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 0ab5f9d4bc59..307f3076635e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -461,6 +461,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
unsigned int flags)
{
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
unsigned long prev_util = sg_cpu->util;
unsigned long max_cap;
@@ -482,10 +483,10 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util)
sg_cpu->util = prev_util;
- cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
+ cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min,
sg_cpu->util, max_cap);
- sg_cpu->sg_policy->last_freq_update_time = time;
+ sg_policy->last_freq_update_time = time;
}
static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
--
2.34.1
Powered by blists - more mailing lists