Re: [RFC PATCH 2/4] softirq: Per vector deferment to workqueue

[Frederic Weisbecker <frederic@kernel.org>]

On Sat, Jan 20, 2018 at 02:11:39PM +0530, Pavan Kondeti wrote:

Hi Pavan,


> I have couple questions/comments.
> 
> (1) Since the work is queued on a bounded per-cpu worker, we may run
> into a deadlock if a TASKLET is killed from another work running on
> the same bounded per-cpu worker.
> 
> For example,
> 
> (1) Schedule a TASKLET on CPU#0 from IRQ.
> (2) Another IRQ comes on the same CPU and we queue a work to kill
> the TASKLET. 
> (3) The TASKLET vector is deferred to workqueue.
> (4) We run the TASKLET kill work and wait for the TASKLET to finish,
> which won't happen.
> 
> We can fix this by queueing the TASKLET kill work on an unbounded
> workqueue so that this runs in parallel with TASKLET vector work.
> 
> Just wanted to know if we have to be aware of this *condition*.

But IIRC the workqueues have several workers per CPU so the tasklet to
be killed can run while the tasklet killer yields.

> 
> (2) Ksoftirqd thread gets parked when a CPU is hotplugged out. So
> there is a gaurantee that the softirq handling never happens on
> another CPU. Where as a bounded worker gets detached and the queued
> work can run on another CPU. I guess, some special handling is
> needed to handle hotplug.

Good catch. Funny, I worried a bit about CPU hotplug but I assumed
the pending CPU-bound worklets would be simply sync'ed before CPU gets down.

Breaking their CPU-bound properties doesn't look sane to me.

Anyway, I'll need to make a CPU hotplug hook.

Thanks for reporting that!