rcu_sched detected stall is observed on a CPU upon a mlx5 device removal.

Updated 2020-09-24T07:17:18+00:00

Issue

  • rcu_sched detected stall is observed on a CPU upon a mlx5 device removal during server shutdown.
  • A task on the stalled CPU is getting stuck in a spinlock loop with a backtrace like this:


    call trace logged with rcu_sched detected CPU stall


Environment

  • Red Hat Enterprise Linux 8.2 (kernel-4.18.0-193.19.1.el8_2)
  • mlx5_ib inbox driver

Subscriber content preview. For full access to the Red Hat Knowledgebase, please log in.

Not a subscriber? Learn more about the benefits of Red Hat Subscriptions.