Re: [RFC PATCH 24/37] mm: implement speculative handling in __do_fault()

From: Matthew Wilcox <willy@infradead.org>
To: Michel Lespinasse <michel@lespinasse.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Linux-MM <linux-mm@kvack.org>,
	Laurent Dufour <ldufour@linux.ibm.com>,
	Michal Hocko <mhocko@suse.com>, Rik van Riel <riel@surriel.com>,
	Paul McKenney <paulmck@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Joel Fernandes <joelaf@google.com>,
	Rom Lemarchand <romlem@google.com>,
	Linux-Kernel <linux-kernel@vger.kernel.org>
Subject: Re: [RFC PATCH 24/37] mm: implement speculative handling in __do_fault()
Date: Thu, 8 Apr 2021 12:28:08 +0100	[thread overview]
Message-ID: <20210408112808.GK2531743@casper.infradead.org> (raw)
In-Reply-To: <20210408083734.GB27824@lespinasse.org>

On Thu, Apr 08, 2021 at 01:37:34AM -0700, Michel Lespinasse wrote:
> On Thu, Apr 08, 2021 at 08:13:43AM +0100, Matthew Wilcox wrote:
> > On Thu, Apr 08, 2021 at 09:00:26AM +0200, Peter Zijlstra wrote:
> > > On Wed, Apr 07, 2021 at 10:27:12PM +0100, Matthew Wilcox wrote:
> > > > Doing I/O without any lock held already works; it just uses the file
> > > > refcount.  It would be better to use a vma refcount, as I already said.
> > > 
> > > The original workload that I developed SPF for (waaaay back when) was
> > > prefaulting a single huge vma. Using a vma refcount was a total loss
> > > because it resulted in the same cacheline contention that down_read()
> > > was having.
> > > 
> > > As such, I'm always incredibly sad to see mention of vma refcounts.
> > > They're fundamentally not solving the problem :/
> > 
> > OK, let me outline my locking scheme because I think it's rather better
> > than Michel's.  The vma refcount is the slow path.
> > 
> > 1. take the RCU read lock
> > 2. walk the pgd/p4d/pud/pmd
> > 3. allocate page tables if necessary.  *handwave GFP flags*.
> > 4. walk the vma tree
> > 5. call ->map_pages
> > 6. take ptlock
> > 7. insert page(s)
> > 8. drop ptlock
> > if this all worked out, we're done, drop the RCU read lock and return.
> > 9. increment vma refcount
> > 10. drop RCU read lock
> > 11. call ->fault
> > 12. decrement vma refcount
> 
> Note that most of your proposed steps seem similar in principle to mine.
> Looking at the fast path (steps 1-8):
> - step 2 sounds like the speculative part of __handle_mm_fault()
> - (step 3 not included in my proposal)
> - step 4 is basically the lookup I currently have in the arch fault handler
> - step 6 sounds like the speculative part of map_pte_lock()
> 
> I have working implementations for each step, while your proposal
> summarizes each as a point item. It's not clear to me what to make of it;
> presumably you would be "filling in the blanks" in a different way
> than I have but you are not explaining how. Are you suggesting that
> the precautions taken in each step to avoid races with mmap writers
> would not be necessary in your proposal ? if that is the case, what is
> the alternative mechanism would you use to handle such races ?

I don't know if you noticed, I've been a little busy with memory folios.
I did tell you that on the call, but you don't seem to retain anything
I tell you on the call, so maybe I shouldn't bother calling in any more.

> Going back to the source of this, you suggested not copying the VMA,
> what is your proposed alternative ? Do you suggest that fault handlers
> should deal with the vma potentially mutating under them ? Or should
> mmap writers consider vmas as immutable and copy them whenever they
> want to change them ? or are you implying a locking mechanism that would
> prevent mmap writers from executing while the fault is running ?

The VMA should be immutable, as I explained to you before.