On 2017-10-03 12:49:20 [-0300], Arnaldo Carvalho de Melo wrote:

From: Arnaldo Carvalho de Melo <redacted>

The hfi1 driver calls request_threaded_irq with two parameters:

      handler = receive_context_interrupt;
      thread = receive_context_thread;
      request_threaded_irq(me->msix.vector, handler, thread, 0, me->name, arg);

And tries to process packets on the hard irq one, receive_context_interrupt(),
only waking up the thread (returning IRQ_WAKE_THREAD) when some threshold is
crossed in the number of packets available in the NIC, trying to balance
latency and bandwidth.

But in a CONFIG_PREEMPT_RT_FULL kernel it ends up calling spin locks from the
hard irq handler (receive_context_interrupt) which causes BUGs like this:

If I am not mistaken current devel-tree of RT (and a few releases before
that) handle that case correctly and force-thread both threads.

Sebastian