sched: DL replenish lagged too much
BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 40s!
Showing busy workqueues and worker pools:
workqueue events: flags=0x100
  pwq 2: cpus=0 node=0 flags=0x0 nice=0 active=19 refcnt=20
    in-flight: 869:reg_todo for 40s
    pending: drm_fb_helper_damage_work, 5*nsim_dev_hwstats_traffic_work, 4*psi_avgs_work, vmstat_shepherd, ovs_dp_masks_rebalance, psi_avgs_work, 5*ovs_dp_masks_rebalance
workqueue events_unbound: flags=0x2
  pwq 8: cpus=0-1 flags=0x6 nice=0 active=28 refcnt=29