Comment 12 for bug 1838575

A trace into the early phase (first some other init with ~16 cpus) then the long phase of 1 thread blocking.
So we will see it "enter" the slow phase as well as iterating in it.

There seem to be two phases one around alloc_pages_current and then one around slot_rmap_walk_next/rmap_get_first.
I'd appreciate if the kernel Team could take a look at the details here and how the call chains actually are.
And how this is related to the IOCTL that seem to trigger it.

After all the testcase is rather simple:
uvt-simplestreams-libvirt --verbose sync --source http://cloud-images.ubuntu.com/daily arch=amd64 label=daily release=bionic
uvt-kvm create --password ubuntu test-slowstart arch=amd64 release=bionic label=daily
Then add to guest config:
  <memory unit='KiB'>1258291200</memory>
  <currentMemory unit='KiB'>1258291200</currentMemory>
  <type arch='x86_64' machine='pc-i440fx-bionic-hpb'>hvm</type>
    <hostdev mode='subsystem' type='pci' managed='yes'>
      <source>
        <address domain='0x0000' bus='0x34' slot='0x00' function='0x0'/>
      </source>
      <address type='pci' domain='0x0000' bus='0x00' slot='0x07' function='0x0'/>
    </hostdev>

A guest like that is already on the system for testing.

ftrace log (compressed 179M, full 4.8G) can be found on the system.