diff options
| -rw-r--r-- | kernel/sched/ext/ext.c | 32 |
1 files changed, 24 insertions, 8 deletions
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 27b027833f06..f1c833f1b78d 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -3377,17 +3377,32 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev update_curr_scx(rq); /* + * Under bypass, @prev's slice can't be trusted as a cpu-form + * scheduler can write it directly from BPF. Skipping the keep + * below is not enough as the post-dispatch test in + * scx_dispatch_sched() would keep @prev on the same slice. + * + * Expire it as the bypass tick would, so that neither test + * keeps @prev on it and @prev rotates through the bypass + * enqueue. A kernel slice is left alone and the keep below + * keeps @prev on it, see %SCX_TASK_KERNEL_SLICE. + * + * TODO: Once the cpu form is deprecated and the kfuncs refuse + * slice raises from a bypassing scheduler, slices can be + * trusted under bypass. This expiry, the bypass tick's zeroing + * and the related slice handling can then be cleaned up. + */ + if (scx_bypassing(scx_task_sched(prev), cpu)) + expire_task_slice(prev); + + /* * If @prev is runnable & has slice left, it has priority and * fetching more just increases latency for the fetched tasks. * Tell pick_task_scx() to keep running @prev. If the BPF * scheduler wants to handle this explicitly, it should * implement ->cpu_release(). - * - * See scx_disable_workfn() for the explanation on the bypassing - * test. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && - !scx_bypassing(scx_task_sched(prev), cpu)) { + if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice) { verdict = SCX_DSP_PREV; goto has_tasks; } @@ -6917,9 +6932,10 @@ static void unbypass_renotify_idle(struct rq *rq, struct scx_sched *pos, * - ops.sub_ecaps_updated() and ops.sub_child_ecaps_updated() are still called. * The bypassed tasks are on the bypass DSQs, out of their reach. * - * - dispatch_one() does not report %SCX_DSP_PREV on non-zero slice as slice - * can't be trusted. Whenever a tick triggers, the running task is rotated to - * the tail of the queue. + * - dispatch_one() expires prev's slice before its keep test as the slice can't + * be trusted. Each tick does the same and rotates the running task to the + * tail of the queue. A kernel slice is left alone, see + * %SCX_TASK_KERNEL_SLICE. * * - pick_next_task() suppresses zero slice warning. * |