Re: [Intel-gfx] [PATCH] kthread: finer-grained lockdep/cross-release completion

[Daniel Vetter <daniel@ffwll.ch>]

On Fri, Dec 08, 2017 at 11:14:16AM +0100, Peter Zijlstra wrote:
> On Thu, Dec 07, 2017 at 09:56:57PM +0100, Daniel Vetter wrote:
> > On Thu, Dec 07, 2017 at 08:57:09PM +0100, Peter Zijlstra wrote:
> 
> > > Is what it says I suppose. Now I don't know enough about that i915 code
> > > to say if that breadcrumbs_signal thread can ever trigger a fault or
> > > not. I got properly lost in that dma_fence callback maze.
> > > 
> > > You're saying not?
> > 
> > Our own kthread, no. At least a tons of run on our CI with the kthread
> > patch applied shut up lockdep splats for good. And since we have all the
> > i915 kthreads still with the same lockdep_map even with the patch applied,
> > since they are all created in the same function, I think that's pretty
> > solid evidence.
> > 
> > [There's also really no reasonable reason for it to fault, but I trust
> > automated tools more to check this stuff than my own brain. The test suite
> > we're running is fairly nasty and does all kinds of corner case
> > thrashing. Note that the dma_fence callbacks can be provideded by any
> > other driver (think multi-gpu desktops and stuff), but the contract is
> > that they must be able to handle hardirq context. Faulting's definitely
> > not on the table.]
> 
> OK, good.

Aside: Could/should we take some fake lockdep locks around these
callbacks, since not all drivers call them from a hardirq context? Just to
validate that everyone follows the contract.

I need to ponder proper lockdep annotations for dma_fence anyway, since
they're just completions which also have some support for direct hw->hw
signalling.

> > The problem lockdep seems to complain about is that some random other
> > kthread could fault, end up in the i915 fault handler, and get stuck until
> > i915_reset_device is done doing what it needs to do. But as long as that
> > kthread is in turn not providing a service that i915_reset_device needs, I
> > don't see how that can deadlock. And if we have that case (there was
> > definitely plenty of that stuff that cross-release uncovered in our code,
> > we had to shuffle a bunch of allocations and things out from under
> > dev->struct_mutex), then there should be another lock or completion that
> > closes the loop again.
> 
> Indeed so.
> 
> > > (also, that comment near need_resched() doesn't make sense to me)
> > 
> > I assume you mean the one in intel_breadcrumbs_signaler(). The hw design
> > is somewhat screwed up and depends upon ridiculously low interrupt
> > servicing time. We get there by essentially implementing something like
> > netdev polled mode, from irq context. Like net polling if the scheduler
> > gets pissed at us we stop and dump it all into a kthread. From a latency
> > and ops/sec pov a gpu is pretty close to networking sometimes.
> > 
> > [Note: I just have a rough idea what the code is supposed to do, I didn't
> > write/review/debug that one.]
> 
> The thing is though; that calling schedule() from an RT thread doesn't
> help anything if it goes running instantly again.
> 
> And looking more; that uses the waitqueue code 'creatively' it doesn't
> actually have a condition to wait on, so wtf is it doing with a
> waitqueue?

Yeah that looks fishy. I discussed it with Chris, and the waitqueue stuff
is indeed broken. Chris has a patch to address that.

The main wakeup logic of the thread is done through
wake_up_process(breadcrumb->signaller) directly, so no ordering issue wrt
adding to the waitqueue. And then the proper waker/wakee pattern holds:

- set tast state
- check condition
- schedule()

Link to Chris' patch:

https://www.spinics.net/lists/intel-gfx/msg149891.html

Thanks, Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch