Recursively zap all to-be-orphaned children, unsynced or otherwise, when
zapping a shadow page for a nested TDP MMU.  KVM currently only zaps the
unsynced child pages, but not the synced ones.  This can create problems
over time when running many nested guests because it leaves unlinked
pages which will not be freed until the page quota is hit. With the
default page quota of 20 shadow pages per 1000 guest pages, this looks
like a memory leak and can degrade MMU performance.

In a recent benchmark, substantial performance degradation was observed:
An L1 guest was booted with 64G memory.
2G nested Windows guests were booted, 10 at a time for 20
iterations. (200 total boots)
Windows was used in this benchmark because they touch all of their
memory on startup.
By the end of the benchmark, the nested guests were taking ~10% longer
to boot. With this patch there is no degradation in boot time.
Without this patch the benchmark ends with hundreds of thousands of
stale EPT02 pages cluttering up rmaps and the page hash map. As a
result, VM shutdown is also much slower: deleting memslot 0 was
observed to take over a minute. With this patch it takes just a
few miliseconds.

Cc: Peter Shier <pshier@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200923221406.16297-3-sean.j.christopherson@intel.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>