Hi all, Considering the feedback on my first version https://lore.kernel.org/linux-arm-kernel/20210319161711.24972-1-yoan.picchi@xxxxxxx/ I started from scratch and focussed only on stage 2 page fault. For the context, as mentioned in the KVM forum talk from 2019 (https://kvmforum2019.sched.com/event/Tmwf/kvmstat-and-beyond-past-present-and-future-of-performance-monitoring-christian-borntrager-ibm page 10), there are few event counters for kvm_stat in the arm64 version of kvm when you compare it to something like the x86 version. Those counters are used in kvm_stat by kernel/driver developers to have a rough idea of the impact of their patches on the general performance. In this patchset I introduce 3 counters to use in kvm stat. They aim to help a kernel/driver dev troubleshot performance issues by letting them know how much exits comes from stage 2 table faults, and thus, see if their changes added a lot. Between the existing mmio_user_exit and the added page_mapped, the main reasons for a stage 2 page fault should be covered and thus give some finer granularity when looking for the source of exits. Yoan Picchi (3): KVM: arm64: Add a stage2 page fault counter for kvm_stat KVM: arm64: Add two page mapping counters for kvm_stat KVM: arm64: Add irq_exit counter for kvm_stat arch/arm64/include/asm/kvm_host.h | 4 ++++ arch/arm64/kvm/guest.c | 4 ++++ arch/arm64/kvm/handle_exit.c | 1 + arch/arm64/kvm/hyp/pgtable.c | 5 +++++ arch/arm64/kvm/mmu.c | 2 ++ 5 files changed, 16 insertions(+) -- 2.17.1 _______________________________________________ kvmarm mailing list kvmarm@xxxxxxxxxxxxxxxxxxxxx https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
