Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends

[Steven Rostedt]

On Thu, 24 Sep 2020 08:57:52 +0200
Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:

> > Now as for migration disabled nesting, at least now we would have
> > groupings of this, and perhaps the theorists can handle that. I mean,
> > how is this much different that having a bunch of tasks blocked on a
> > mutex with the owner is pinned on a CPU?
> >
> > migrate_disable() is a BKL of pinning affinity.  
> 
> No. That's just wrong. preempt disable is a concurrency control,

I think you totally misunderstood what I was saying. The above wasn't about
comparing preempt_disable to migrate_disable. It was comparing
migrate_disable to a chain of tasks blocked on mutexes where the top owner
has preempt_disable set. You still have a bunch of tasks that can't move to
other CPUs.


> > If we only have local_lock() available (even on !RT), then it makes
> > the blocking in groups. At least this way you could grep for all the
> > different local_locks in the system and plug that into the algorithm
> > for WCS, just like one would with a bunch of mutexes.  
> 
> You cannot do that on RT at all where migrate disable is substituting
> preempt disable in spin and rw locks. The result would be the same as
> with a !RT kernel just with horribly bad performance.

Note, the spin and rwlocks already have a lock associated with them. Why
would it be any different on RT? I wasn't suggesting adding another lock
inside a spinlock. Why would I recommend THAT? I wasn't recommending
blindly replacing migrate_disable() with local_lock(). I just meant expose
local_lock() but not migrate_disable().

> 
> That means the stacking problem has to be solved anyway.
> 
> So why on earth do you want to create yet another special duct tape case
> for kamp_local() which proliferates inconsistency instead of aiming for
> consistency accross all preemption models?

The idea was to help with the scheduling issue.

Anyway, instead of blocking. What about having a counter of number of
migrate disabled tasks per cpu, and when taking a migrate_disable(), and there's
already another task with migrate_disabled() set, and the current task has
an affinity greater than 1, it tries to migrate to another CPU?

This way migrate_disable() is less likely to have a bunch of tasks blocked
on one CPU serialized by each task exiting the migrate_disable() section.

Yes, there's more overhead, but it only happens if multiple tasks are in a
migrate disable section on the same CPU.

-- Steve