diff mbox series

[v4,2/4] cpufreq: qcom-hw: fix the race between LMH worker and cpuhp

Message ID 20220326155153.7377-3-dmitry.baryshkov@linaro.org (mailing list archive)
State New, archived
Delegated to: viresh kumar
Headers show
Series cpufreq: qcom-hw: Fixes for cpu hotplug support | expand

Commit Message

Dmitry Baryshkov March 26, 2022, 3:51 p.m. UTC
The driver would disable the worker when cpu is being put offline, but
it happens closer to the end of cpufreq_offline(). The function
qcom_lmh_dcvs_poll() can be running in parallel with this, when
policy->cpus already has been updated. Read policy->related_cpus
instead.

[   37.122433] ------------[ cut here ]------------
[   37.127225] WARNING: CPU: 0 PID: 187 at drivers/base/arch_topology.c:180 topology_update_thermal_pressure+0xec/0x100
[   37.138098] Modules linked in:
[   37.141279] CPU: 0 PID: 187 Comm: kworker/0:3 Tainted: G S                5.17.0-rc6-00389-g37c83d0b8710-dirty #713
[   37.158306] Workqueue: events qcom_lmh_dcvs_poll
[   37.163095] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   37.170278] pc : topology_update_thermal_pressure+0xec/0x100
[   37.176131] lr : topology_update_thermal_pressure+0x20/0x100
[   37.181977] sp : ffff800009b6bce0
[   37.185402] x29: ffff800009b6bce0 x28: ffffd87abe92b000 x27: ffff04bd7292e205
[   37.192792] x26: ffffd87abe930af8 x25: ffffd87abe94e4c8 x24: 0000000000000000
[   37.200180] x23: ffff04bb01177018 x22: ffff04bb011770c0 x21: ffff04bb01177000
[   37.207567] x20: ffff04bb0a419000 x19: 00000000000c4e00 x18: 0000000000000000
[   37.214954] x17: 000000040044ffff x16: 004000b2b5503510 x15: 0000006aaa1326d2
[   37.222333] x14: 0000000000000232 x13: 0000000000000001 x12: 0000000000000040
[   37.229718] x11: ffff04bb00400000 x10: 968f57bd39f701c8 x9 : ffff04bb0acc8674
[   37.237095] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffffd87abd90092c
[   37.244478] x5 : 0000000000000016 x4 : 0000000000000000 x3 : 0000000000000100
[   37.251852] x2 : ffff04bb0a419020 x1 : 0000000000000100 x0 : 0000000000000100
[   37.259235] Call trace:
[   37.261771]  topology_update_thermal_pressure+0xec/0x100
[   37.267266]  qcom_lmh_dcvs_poll+0xbc/0x154
[   37.271505]  process_one_work+0x288/0x69c
[   37.275654]  worker_thread+0x74/0x470
[   37.279450]  kthread+0xfc/0x100
[   37.282712]  ret_from_fork+0x10/0x20
[   37.286417] irq event stamp: 74
[   37.289664] hardirqs last  enabled at (73): [<ffffd87abdd78af4>] _raw_spin_unlock_irq+0x44/0x80
[   37.298632] hardirqs last disabled at (74): [<ffffd87abdd71fc0>] __schedule+0x710/0xa10
[   37.306885] softirqs last  enabled at (58): [<ffffd87abcc90410>] _stext+0x410/0x588
[   37.314778] softirqs last disabled at (51): [<ffffd87abcd1bf68>] __irq_exit_rcu+0x158/0x174
[   37.323386] ---[ end trace 0000000000000000 ]---

Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Bjorn Andersson March 31, 2022, 6:33 p.m. UTC | #1
On Sat 26 Mar 08:51 PDT 2022, Dmitry Baryshkov wrote:

> The driver would disable the worker when cpu is being put offline, but
> it happens closer to the end of cpufreq_offline(). The function
> qcom_lmh_dcvs_poll() can be running in parallel with this, when
> policy->cpus already has been updated. Read policy->related_cpus
> instead.
> 
> [   37.122433] ------------[ cut here ]------------
> [   37.127225] WARNING: CPU: 0 PID: 187 at drivers/base/arch_topology.c:180 topology_update_thermal_pressure+0xec/0x100
> [   37.138098] Modules linked in:
> [   37.141279] CPU: 0 PID: 187 Comm: kworker/0:3 Tainted: G S                5.17.0-rc6-00389-g37c83d0b8710-dirty #713
> [   37.158306] Workqueue: events qcom_lmh_dcvs_poll
> [   37.163095] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> [   37.170278] pc : topology_update_thermal_pressure+0xec/0x100
> [   37.176131] lr : topology_update_thermal_pressure+0x20/0x100
> [   37.181977] sp : ffff800009b6bce0
> [   37.185402] x29: ffff800009b6bce0 x28: ffffd87abe92b000 x27: ffff04bd7292e205
> [   37.192792] x26: ffffd87abe930af8 x25: ffffd87abe94e4c8 x24: 0000000000000000
> [   37.200180] x23: ffff04bb01177018 x22: ffff04bb011770c0 x21: ffff04bb01177000
> [   37.207567] x20: ffff04bb0a419000 x19: 00000000000c4e00 x18: 0000000000000000
> [   37.214954] x17: 000000040044ffff x16: 004000b2b5503510 x15: 0000006aaa1326d2
> [   37.222333] x14: 0000000000000232 x13: 0000000000000001 x12: 0000000000000040
> [   37.229718] x11: ffff04bb00400000 x10: 968f57bd39f701c8 x9 : ffff04bb0acc8674
> [   37.237095] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffffd87abd90092c
> [   37.244478] x5 : 0000000000000016 x4 : 0000000000000000 x3 : 0000000000000100
> [   37.251852] x2 : ffff04bb0a419020 x1 : 0000000000000100 x0 : 0000000000000100
> [   37.259235] Call trace:
> [   37.261771]  topology_update_thermal_pressure+0xec/0x100
> [   37.267266]  qcom_lmh_dcvs_poll+0xbc/0x154
> [   37.271505]  process_one_work+0x288/0x69c
> [   37.275654]  worker_thread+0x74/0x470
> [   37.279450]  kthread+0xfc/0x100
> [   37.282712]  ret_from_fork+0x10/0x20
> [   37.286417] irq event stamp: 74
> [   37.289664] hardirqs last  enabled at (73): [<ffffd87abdd78af4>] _raw_spin_unlock_irq+0x44/0x80
> [   37.298632] hardirqs last disabled at (74): [<ffffd87abdd71fc0>] __schedule+0x710/0xa10
> [   37.306885] softirqs last  enabled at (58): [<ffffd87abcc90410>] _stext+0x410/0x588
> [   37.314778] softirqs last disabled at (51): [<ffffd87abcd1bf68>] __irq_exit_rcu+0x158/0x174
> [   37.323386] ---[ end trace 0000000000000000 ]---
> 
> Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support")

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>

Regards,
Bjorn

> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---
>  drivers/cpufreq/qcom-cpufreq-hw.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
> index 44d46e52baea..d39a0ef9ea45 100644
> --- a/drivers/cpufreq/qcom-cpufreq-hw.c
> +++ b/drivers/cpufreq/qcom-cpufreq-hw.c
> @@ -290,7 +290,7 @@ static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
>  static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
>  {
>  	struct cpufreq_policy *policy = data->policy;
> -	int cpu = cpumask_first(policy->cpus);
> +	int cpu = cpumask_first(policy->related_cpus);
>  	struct device *dev = get_cpu_device(cpu);
>  	unsigned long freq_hz, throttled_freq;
>  	struct dev_pm_opp *opp;
> -- 
> 2.35.1
>
diff mbox series

Patch

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 44d46e52baea..d39a0ef9ea45 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -290,7 +290,7 @@  static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
 static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 {
 	struct cpufreq_policy *policy = data->policy;
-	int cpu = cpumask_first(policy->cpus);
+	int cpu = cpumask_first(policy->related_cpus);
 	struct device *dev = get_cpu_device(cpu);
 	unsigned long freq_hz, throttled_freq;
 	struct dev_pm_opp *opp;