Re: [PATCH] firewire: ohci: mask bus reset interrupts between ISR and bottom half

From: Takashi Sakamoto
Date: Wed May 01 2024 - 19:19:41 EST


Hi Adam,

On Wed, May 01, 2024 at 04:39:23AM -0700, Adam Goldman wrote:
> Hi Takashi,
>
> On Mon, Apr 01, 2024 at 09:18:00PM +0900, Takashi Sakamoto wrote:
> > I sent an additional patch[1] to handle the bus-reset event at the first
> > time. I'd like you to review and test it as well, especially under your
> > environment in which 1394:1995 and 1394a phys exist.
> >
> > [1] https://lore.kernel.org/lkml/20240401121200.220013-1-o-takashi@xxxxxxxxxxxxx/
>
> I'm sorry for another very late reply.
>
> Now that we eliminated the IRQ storm, it makes sense to always enable
> the bus-reset interrupt at startup. I tested your patch with various
> devices, with a FW800 repeater, with a FW400 hub, without a hub, etc.
> Everything works OK. However, I only tested with XIO2213B OHCI.
>
> -- Adam

Thanks for your test. The content of patch is equivalent to the first
one in the candidate series[1], so I appended Tested-by tag when
applying to for-next branch.

The for-next branch includes the commits to provide the following
tracepoints events:

* firewire:async_request_outbound_initiate
* firewire:async_request_outbound_complete
* firewire:async_response_inbound
* firewire:async_request_inbound
* firewire:async_response_outbound_initiate
* firewire:async_response_outbound_complete
* firewire:async_phy_outbound_initiate
* firewire:async_phy_outbound_complete
* firewire:async_phy_inbound
* firewire:bus_reset_initiate
* firewire:bus_reset_schedule
* firewire:bus_reset_postpone
* firewire:bus_reset_handle

All of them are used to trace the action of firewire core function,
instead of 1394 OHCI driver. I think they are helpful to debug the kind
of issue which we handled for v6.8 kernel.

[1] https://lore.kernel.org/lkml/20240501073238.72769-1-o-takashi@xxxxxxxxxxxxx/


Thanks

Takashi Sakamoto