[PATCH 7/7] um: simplify IRQ handling code

[Johannes Berg]

On Mon, 2020-11-30 at 16:30 +0000, Anton Ivanov wrote:
> On 23/11/2020 19:56, Johannes Berg wrote:
> > From: Johannes Berg <johannes.berg at intel.com>
> > 
> > Reduce dynamic allocations (and thereby cache misses) by simply
> > embedding the registration data for IRQs in the irq_entry, we
> > never supported these being really dynamic anyway as only one
> > was ever allowed ("Trying to reregister ...").
> > 
> > Lockless behaviour is preserved by removing the FD from the poll
> > set appropriately, but we use reg->events to indicate whether or
> > not this entry is used, rather than dynamically allocating them.
> > 
> > Also port the list of IRQ entries to list_head instead of the
> > current open-coded singly-linked list implementation, just for
> > sanity.
> 
> This one is broken. I will look exactly where. It is somewhere in the IRQ delete/re-request logic.
> 
> How to test
> 
> run iperf -s in the UML with a vector network driver.
> 
> run iperf -c to the UML instance from the host in a loop

How do you usually use it? tap device?

> Try to ifup/ifdown the vecX interface inside the UML.
> 
> With master it works fine. With this patch it fails.

How does it fail?

johannes