From: Zhuang yanying <ann.zhuangyanying@xxxxxxxxxx>
When live-migration with large-memory guests, vcpu may hang for a long
time while starting migration, such as 9s for 2T
(linux-5.0.0-rc2+qemu-3.1.0).
The reason is memory_global_dirty_log_start() taking too long, and the
vcpu is waiting for BQL. The page-by-page D bit clearup is the main time
consumption. I think that the idea of "KVM: MMU: fast write protect" by
xiaoguangrong, especially the function kvm_mmu_write_protect_all_pages(),
is very helpful. After a little modifcation, on his patch, can solve
this problem, 9s to 0.5s.
At the beginning of live migration, write protection is only applied to the
top-level SPTE. Then the write from vm trigger the EPT violation, with
for_each_shadow_entry write protection is performed at dirct_map.
Finally the Dirty bit of the target page(at level 1 page table) is cleared,
and the dirty page tracking is started. The page where GPA is located is
marked dirty when mmu_set_spte.
A similar implementation on xen, just emt instead of write protection.
Xiao Guangrong (2):
KVM: MMU: introduce possible_writable_spte_bitmap
KVM: MMU: introduce kvm_mmu_write_protect_all_pages
Zhuang Yanying (1):
KVM: MMU: fast cleanup D bit based on fast write protect
arch/x86/include/asm/kvm_host.h | 24 ++++-
arch/x86/kvm/mmu.c | 229 ++++++++++++++++++++++++++++++++++++++--
arch/x86/kvm/mmu.h | 1 +
arch/x86/kvm/paging_tmpl.h | 13 ++-
arch/x86/kvm/vmx/vmx.c | 5 +-
5 files changed, 257 insertions(+), 15 deletions(-)
--
v1 -> v2:
- drop "KVM: MMU: correct the behavior of mmu_spte_update_no_track"
- mmu_write_protect_all_indicator is no longer an atomic variable,
protected by mmu_lock
- Implement kvm_mmu_slot_set_dirty with kvm_mmu_write_protect_all_pages
- some modification on the commit messages
--
1.8.3.1
