Re: [RFC PATCH 00/12] KVM: arm64: Eager huge-page splitting for dirty-logging

[Ricardo Koller <ricarkol@google.com>]

On Mon, Nov 14, 2022 at 06:42:36PM +0000, Oliver Upton wrote:
> Hi Ricardo,
> 
> On Sat, Nov 12, 2022 at 08:17:02AM +0000, Ricardo Koller wrote:
> > Hi,
> > 
> > I'm sending this RFC mainly to get some early feedback on the approach used
> > for implementing "Eager Page Splitting" on ARM.  "Eager Page Splitting"
> > improves the performance of dirty-logging (used in live migrations) when
> > guest memory is backed by huge-pages.  It's an optimization used in Google
> > Cloud since 2016 on x86, and for the last couple of months on ARM.
> > 
> > I tried multiple ways of implementing this optimization on ARM: from
> > completely reusing the stage2 mapper, to implementing a new walker from
> > scratch, and some versions in between. This RFC is one of those in
> > between. They all have similar performance benefits, based on some light
> > performance testing (mainly dirty_log_perf_test).
> > 
> > Background and motivation
> > =========================
> > Dirty logging is typically used for live-migration iterative copying.  KVM
> > implements dirty-logging at the PAGE_SIZE granularity (will refer to 4K
> > pages from now on).  It does it by faulting on write-protected 4K pages.
> > Therefore, enabling dirty-logging on a huge-page requires breaking it into
> > 4K pages in the first place.  KVM does this breaking on fault, and because
> > it's in the critical path it only maps the 4K page that faulted; every
> > other 4K page is left unmapped.  This is not great for performance on ARM
> > for a couple of reasons:
> > 
> > - Splitting on fault can halt vcpus for milliseconds in some
> >   implementations. Splitting a block PTE requires using a broadcasted TLB
> >   invalidation (TLBI) for every huge-page (due to the break-before-make
> >   requirement). Note that x86 doesn't need this. We observed some
> >   implementations that take millliseconds to complete broadcasted TLBIs
> >   when done in parallel from multiple vcpus.  And that's exactly what
> >   happens when doing it on fault: multiple vcpus fault at the same time
> >   triggering TLBIs in parallel.
> > 
> > - Read intensive guest workloads end up paying for dirty-logging.  Only
> >   mapping the faulting 4K page means that all the other pages that were
> >   part of the huge-page will now be unmapped. The effect is that any
> >   access, including reads, now has to fault.
> > 
> > Eager Page Splitting (on ARM)
> > =============================
> > Eager Page Splitting fixes the above two issues by eagerly splitting
> > huge-pages when enabling dirty logging. The goal is to avoid doing it while
> > faulting on write-protected pages. This is what the TDP MMU does for x86
> > [0], except that x86 does it for different reasons: to avoid grabbing the
> > MMU lock on fault. Note that taking care of write-protection faults still
> > requires grabbing the MMU lock on ARM, but not on x86 (with the
> > fast_page_fault path).
> > 
> > An additional benefit of eagerly splitting huge-pages is that it can be
> > done in a controlled way (e.g., via an IOCTL). This series provides two
> > knobs for doing it, just like its x86 counterpart: when enabling dirty
> > logging, and when using the KVM_CLEAR_DIRTY_LOG ioctl. The benefit of doing
> > it on KVM_CLEAR_DIRTY_LOG is that this ioctl takes ranges, and not complete
> > memslots like when enabling dirty logging. This means that the cost of
> > splitting (mainly broadcasted TLBIs) can be throttled: split a range, wait
> > for a bit, split another range, etc. The benefits of this approach were
> > presented by Oliver Upton at KVM Forum 2022 [1].
> > 
> > Implementation
> > ==============
> > Patches 1-4 add a pgtable utility function for splitting huge block PTEs:
> > kvm_pgtable_stage2_split(). Patches 5-6 add support for not doing
> > break-before-make on huge-page breaking when FEAT_BBM level 2 is supported.
> 
> I would suggest you split up FEAT_BBM=2 and eager page splitting into
> two separate series, if possible. IMO, the eager page split is easier to
> reason about if it follows the existing pattern of break-before-make.

Dropping these changes in v1.

> 
> --
> Thanks,
> Oliver