sched_ext: Clarify CPU context for running/stopping callbacks
PATCH 1/1 sched_ext: Clarify CPU context for running/stopping callbacks
The ops.running() and ops.stopping() callbacks can be invoked from a CPU other than the one the task is assigned to, particularly during affinity changes, as both scx_next_task_scx() and dequeue_task_scx() may run on CPUs different from the task's target CPU.
This behavior can lead to confusion or incorrect assumptions if not properly clarified, potentially resulting in bugs (see [1]).
Therefore, update the documentation to clarify this aspect and advise users to use scx_bpf_task_cpu() to determine the actual CPU the task will run on or was running on.
[1] https://github.com/sched-ext/scx/pull/1728
--- kernel/sched/ext.c | 8 ++++++++ 1 file changed, 8 insertions(+)
kernel/sched/ext.c +8 -0
@@ -373,6 +373,10 @@ struct sched_ext_ops {* @running: A task is starting to run on its associated CPU * @p: task starting to run * +* Note that this callback may be called from a CPU other than the +* one the task is going to run on. Use scx_bpf_task_cpu(@p) to +* determine the target CPU the task is going to use. +* * See ->runnable() for explanation on the task state notifiers. */ void (*running)(struct task_struct *p);
@@ -382,6 +386,10 @@ struct sched_ext_ops {* @p: task stopping to run * @runnable: is task @p still runnable? * +* Note that this callback may be called from a CPU other than the +* one the task was running on. Use scx_bpf_task_cpu(@p) to +* retrieve the CPU used by the task. +* * See ->runnable() for explanation on the task state notifiers. If * !@runnable, ->quiescent() will be invoked after this operation * returns.
Signature · 1 line
2.49.0
Quoted 26 lines · Andrea Righi
The
ops.running()andops.stopping()callbacks can be invoked from a CPU other than the one the task is assigned to, particularly during affinity changes, as bothscx_next_task_scx()anddequeue_task_scx()may run on CPUs different from the task's target CPU.This behavior can lead to confusion or incorrect assumptions if not properly clarified, potentially resulting in bugs (see [1]).
Therefore, update the documentation to clarify this aspect and advise users to use
scx_bpf_task_cpu()to determine the actual CPU the task will run on or was running on.[1] https://github.com/sched-ext/scx/pull/1728
Cc Jake Hillion <[email protected]>Cc Changwoo Min <[email protected]>Signed-off-by Andrea Righi <[email protected]>--- kernel/sched/ext.c | 8 ++++++++ 1 file changed, 8 insertions(+)kernel/sched/ext.c +0
-0
kernel/sched/ext.c struct sched_ext_ops { · line 378
Quoted 6 lines
kernel/sched/ext.c +3
-0@@ -373,6 +373,10 @@ struct sched_ext_ops {* @running: A task is starting to run on its associated CPU * @p: task starting to run * +* Note that this callback may be called from a CPU other than the +* one the task is going to run on. Use scx_bpf_task_cpu(@p) to +* determine the target CPU the task is going to use.
Can you briefly explain the scenario as a part of the comment? Just a couple sentences can go a long way against future head scratches.
Thanks.
Signature · 1 line
tejun