Messages in this thread | | | From | nikita.shubin@maquefel ... | Subject | Re: [RFC PATCH 0/3] gpio: ep93xx: convert to multi irqchips | Date | Mon, 28 Dec 2020 18:14:44 +0300 |
| |
27.12.2020, 16:55, "Linus Walleij" <linus.walleij@linaro.org>: > Paging Hartley who I think uses this chip. > > On Thu, Dec 24, 2020 at 12:22 PM Nikita Shubin > <nikita.shubin@maquefel.me> wrote: > >> I was lucky enough to became an owner of some splendid piece's of >> antiques called ts7250 based on the top of Cirrus Logic EP9302. >> >> I don't know what fate expects this hardware (it's not EOL it's just Not >> recommended for new designs) but i wanted to share fixes in ep93xx gpio area. >> >> It seems ep93xx is deadly broken at current state usage of AB gpiochips >> interrupts leads to deadlocks coused by irq_unmask/irq_mask recursions. >> >> Port F is not working at all: > > Yeah when I converted this gpio driver I did not have access to a hardware > which made use of port F :( > > I used the SIM.One board but they all died on me, then I acquired another > EP93xx board that I just didn't have time to test. > > The long term plan is to convert these boards to use device tree and > multiplatform. Interested in the job? ;) >
I had such a thought, but I was stopped by the delusion that no one is using this hardware anymore.
Not promising anything right now - but such a job sounds like a real fun.
> Thanks for fixing up the GPIO chip, let's get the patches in shape and > merge as fixes. Bartosz is handling the fixes right now, I'll try to review too!
I am glad that this work is interesting not only for me. For this, I'm willing to put in a little effort to make the proposed changes look decent.
> > Yours, > Linus Walleij
| |