@@ -622,10 +622,7 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy,
if (!policy->boost_supported)
return -EINVAL;
- cpus_read_lock();
ret = policy_set_boost(policy, enable);
- cpus_read_unlock();
-
if (!ret)
return count;
@@ -1006,16 +1003,28 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
{
struct cpufreq_policy *policy = to_policy(kobj);
struct freq_attr *fattr = to_attr(attr);
+ int ret = -EBUSY;
if (!fattr->store)
return -EIO;
- guard(cpufreq_policy_write)(policy);
+ /*
+ * store_local_boost() requires cpu_hotplug_lock to be held, and must be
+ * called with that lock acquired *before* taking policy->rwsem to avoid
+ * lock ordering violations.
+ */
+ if (fattr == &local_boost)
+ cpus_read_lock();
- if (likely(!policy_is_inactive(policy)))
- return fattr->store(policy, buf, count);
+ scoped_guard(cpufreq_policy_write, policy) {
+ if (likely(!policy_is_inactive(policy)))
+ ret = fattr->store(policy, buf, count);
+ }
- return -EBUSY;
+ if (fattr == &local_boost)
+ cpus_read_unlock();
+
+ return ret;
}
static void cpufreq_sysfs_release(struct kobject *kobj)
Lockdep reports a possible circular locking dependency[1] when writing to /sys/devices/system/cpu/cpufreq/policyN/boost, triggered by power-profiles-daemon at boot. store_local_boost() used to acquire cpu_hotplug_lock *after* the policy lock had already been taken by the store() handler. However, the expected locking hierarchy is to acquire cpu_hotplug_lock before the policy guard. This inverted lock order creates a *theoretical* deadlock possibility. Acquire cpu_hotplug_lock in the store() handler *only* for the local_boost attribute, before entering the policy guard block, and remove the cpus_read_lock/unlock() calls from store_local_boost(). Also switch from guard() to scoped_guard() to allow explicitly wrapping the policy guard inside the cpu_hotplug_lock critical section. [1] ====================================================== WARNING: possible circular locking dependency detected 6.15.0-rc4-debug #28 Not tainted ------------------------------------------------------ power-profiles-/596 is trying to acquire lock: ffffffffb147e910 (cpu_hotplug_lock){++++}-{0:0}, at: store_local_boost+0x6a/0xd0 but task is already holding lock: ffff9eaa48377b80 (&policy->rwsem){++++}-{4:4}, at: store+0x37/0x90 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&policy->rwsem){++++}-{4:4}: down_write+0x29/0xb0 cpufreq_online+0x841/0xa00 cpufreq_add_dev+0x71/0x80 subsys_interface_register+0x14b/0x170 cpufreq_register_driver+0x154/0x250 amd_pstate_register_driver+0x36/0x70 amd_pstate_init+0x1e7/0x270 do_one_initcall+0x67/0x2c0 kernel_init_freeable+0x230/0x270 kernel_init+0x15/0x130 ret_from_fork+0x2c/0x50 ret_from_fork_asm+0x11/0x20 -> #1 (subsys mutex#3){+.+.}-{4:4}: __mutex_lock+0xc2/0x930 subsys_interface_register+0x83/0x170 cpufreq_register_driver+0x154/0x250 amd_pstate_register_driver+0x36/0x70 amd_pstate_init+0x1e7/0x270 do_one_initcall+0x67/0x2c0 kernel_init_freeable+0x230/0x270 kernel_init+0x15/0x130 ret_from_fork+0x2c/0x50 ret_from_fork_asm+0x11/0x20 -> #0 (cpu_hotplug_lock){++++}-{0:0}: __lock_acquire+0x1087/0x17e0 lock_acquire.part.0+0x66/0x1b0 cpus_read_lock+0x2a/0xc0 store_local_boost+0x6a/0xd0 store+0x50/0x90 kernfs_fop_write_iter+0x135/0x200 vfs_write+0x2ab/0x540 ksys_write+0x6c/0xe0 do_syscall_64+0xbb/0x1d0 entry_SYSCALL_64_after_hwframe+0x56/0x5e Signed-off-by: Seyediman Seyedarab <ImanDevel@gmail.com> --- Changes in v3: - Rebased over PM tree's linux-next branch - Added a comment to explain why this piece of code is required - Switched from guard() to scoped_guard() to allow explicitly wrapping the policy guard inside the cpu_hotplug_lock critical section. Changes in v2: - Restrict cpu_hotplug_lock acquisition to only the local_boost attribute in store() handler. Regards, Seyediman drivers/cpufreq/cpufreq.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-)