On Sat, 5 Sep 2015 12:30:59 +0200 (CEST)
Thomas Gleixner [off-list ref] wrote:

So the problem we need to solve is:

retry:
	lock(B);
	if (!try_lock(A)) {
		unlock(B);
		cpu_relax();
		goto retry;
	}

So instead of doing that proposed magic boost, we can do something
more straight forward:

retry:
	lock(B);
	if (!try_lock(A)) {
		lock_and_drop(A, B);
		unlock(A);
		goto retry;
	}

lock_and_drop() queues the task as a waiter on A, drops B and then
does the PI adjustment on A. 

That was my original solution, and I believe I added patches to do
exactly that to the networking code in the past. I remember writing
that helper function such that on non PREEMPT_RT it was a nop.

I even had that solution in my slides at LinuxCon/LinuxPlumbers ;-)


But then I talk about dcache.c. Take a look at that file, and the
complexity of that. Is it safe to take the inode and dcache parent
locks after you unlock the other locks?

-- Steve