[PATCH] tracing/hwlat: Replace sched_setaffinity with set_cpus_allowed_ptr

[PATCH] tracing/hwlat: Replace sched_setaffinity with set_cpus_allowed_ptr

[Costa Shulyupin]

There is a problem with the behavior of hwlat in a container,
resulting in incorrect output. A warning message is generated:
"cpumask changed while in round-robin mode, switching to mode none",
and the tracing_cpumask is ignored. This issue arises because
the kernel thread, hwlatd, is not a part of the container, and
the function sched_setaffinity is unable to locate it using its PID.
Additionally, the task_struct of hwlatd is already known.
Ultimately, the function set_cpus_allowed_ptr achieves
the same outcome as sched_setaffinity, but employs task_struct
instead of PID.

Test case:

  # cd /sys/kernel/tracing
  # echo 0 > tracing_on
  # echo round-robin > hwlat_detector/mode
  # echo hwlat > current_tracer
  # unshare --fork --pid bash -c 'echo 1 > tracing_on'
  # dmesg -c

Actual behavior:

[573502.809060] hwlat_detector: cpumask changed while in round-robin mode, switching to mode none

Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
 kernel/trace/trace_hwlat.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index d440ddd5fd8b..444dfc31f258 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -339,7 +339,7 @@ static void move_to_next_cpu(void)
 	cpumask_clear(current_mask);
 	cpumask_set_cpu(next_cpu, current_mask);
 
-	sched_setaffinity(0, current_mask);
+	set_cpus_allowed_ptr(current, current_mask);
 	return;
 
  change_mode:
@@ -446,7 +446,7 @@ static int start_single_kthread(struct trace_array *tr)
 
 	}
 
-	sched_setaffinity(kthread->pid, current_mask);
+	set_cpus_allowed_ptr(kthread, current_mask);
 
 	kdata->kthread = kthread;
 	wake_up_process(kthread);
-- 
2.39.2

Re: [PATCH] tracing/hwlat: Replace sched_setaffinity with set_cpus_allowed_ptr

[Daniel Bristot de Oliveira]

On 3/16/23 15:45, Costa Shulyupin wrote:
> There is a problem with the behavior of hwlat in a container,
> resulting in incorrect output. A warning message is generated:
> "cpumask changed while in round-robin mode, switching to mode none",
> and the tracing_cpumask is ignored. This issue arises because
> the kernel thread, hwlatd, is not a part of the container, and
> the function sched_setaffinity is unable to locate it using its PID.
> Additionally, the task_struct of hwlatd is already known.
> Ultimately, the function set_cpus_allowed_ptr achieves
> the same outcome as sched_setaffinity, but employs task_struct
> instead of PID.
> 
> Test case:
> 
>   # cd /sys/kernel/tracing
>   # echo 0 > tracing_on
>   # echo round-robin > hwlat_detector/mode
>   # echo hwlat > current_tracer
>   # unshare --fork --pid bash -c 'echo 1 > tracing_on'
>   # dmesg -c
> 
> Actual behavior:
> 
> [573502.809060] hwlat_detector: cpumask changed while in round-robin mode, switching to mode none
> 
> Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>

I tested it and... it works.

Acked-by: Daniel Bristot de Oliveira <bristot@kernel.org>

Thanks
-- Daniel

> ---
>  kernel/trace/trace_hwlat.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
> index d440ddd5fd8b..444dfc31f258 100644
> --- a/kernel/trace/trace_hwlat.c
> +++ b/kernel/trace/trace_hwlat.c
> @@ -339,7 +339,7 @@ static void move_to_next_cpu(void)
>  	cpumask_clear(current_mask);
>  	cpumask_set_cpu(next_cpu, current_mask);
>  
> -	sched_setaffinity(0, current_mask);
> +	set_cpus_allowed_ptr(current, current_mask);
>  	return;
>  
>   change_mode:
> @@ -446,7 +446,7 @@ static int start_single_kthread(struct trace_array *tr)
>  
>  	}
>  
> -	sched_setaffinity(kthread->pid, current_mask);
> +	set_cpus_allowed_ptr(kthread, current_mask);
>  
>  	kdata->kthread = kthread;
>  	wake_up_process(kthread);