On Sat, Feb 25, 2023 at 08:47:59PM +0000, Shivam Kumar wrote:
> Call update_dirty_quota whenever a page is marked dirty with
> appropriate arch-specific page size. Process the KVM request
> KVM_REQ_DIRTY_QUOTA_EXIT (raised by update_dirty_quota) to exit to
> userspace with exit reason KVM_EXIT_DIRTY_QUOTA_EXHAUSTED.
>
> Suggested-by: Shaju Abraham <shaju.abraham@xxxxxxxxxxx>
> Suggested-by: Manish Mishra <manish.mishra@xxxxxxxxxxx>
> Co-developed-by: Anurag Madnawat <anurag.madnawat@xxxxxxxxxxx>
> Signed-off-by: Anurag Madnawat <anurag.madnawat@xxxxxxxxxxx>
> Signed-off-by: Shivam Kumar <shivam.kumar1@xxxxxxxxxxx>
> ---
> arch/x86/kvm/Kconfig | 1 +
> arch/x86/kvm/mmu/mmu.c | 8 +++++++-
> arch/x86/kvm/mmu/spte.c | 3 +++
> arch/x86/kvm/mmu/tdp_mmu.c | 3 +++
> arch/x86/kvm/vmx/vmx.c | 5 +++++
> arch/x86/kvm/x86.c | 16 ++++++++++++++++
> arch/x86/kvm/xen.c | 12 +++++++++++-
> 7 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> index 8e578311ca9d..8621a9512572 100644
> --- a/arch/x86/kvm/Kconfig
> +++ b/arch/x86/kvm/Kconfig
> @@ -48,6 +48,7 @@ config KVM
> select KVM_VFIO
> select SRCU
> select INTERVAL_TREE
> + select HAVE_KVM_DIRTY_QUOTA
> select HAVE_KVM_PM_NOTIFIER if PM
> select KVM_GENERIC_HARDWARE_ENABLING
> help
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index c8ebe542c565..e0c8348ecdf1 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3323,8 +3323,14 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
> if (!try_cmpxchg64(sptep, &old_spte, new_spte))
> return false;
>
> - if (is_writable_pte(new_spte) && !is_writable_pte(old_spte))
> + if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) {
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + struct kvm_mmu_page *sp = sptep_to_sp(sptep);
> +
> + update_dirty_quota(vcpu->kvm, (1L << SPTE_LEVEL_SHIFT(sp->role.level)));
> +#endif
> mark_page_dirty_in_slot(vcpu->kvm, fault->slot, fault->gfn);
Possible to call update_dirty_quota() from mark_page_dirty_in_slot() ?
Then other Architectures can be covered yet.
> + }
>
> return true;
> }
> diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
> index c15bfca3ed15..15f4f1d97ce9 100644
> --- a/arch/x86/kvm/mmu/spte.c
> +++ b/arch/x86/kvm/mmu/spte.c
> @@ -243,6 +243,9 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
> if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
> /* Enforced by kvm_mmu_hugepage_adjust. */
> WARN_ON(level > PG_LEVEL_4K);
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(vcpu->kvm, (1L << SPTE_LEVEL_SHIFT(level)));
> +#endif
> mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
> }
>
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 7c25dbf32ecc..4bf98e96343d 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -358,6 +358,9 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
>
> if ((!is_writable_pte(old_spte) || pfn_changed) &&
> is_writable_pte(new_spte)) {
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(kvm, (1L << SPTE_LEVEL_SHIFT(level)));
> +#endif
> slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
> mark_page_dirty_in_slot(kvm, slot, gfn);
> }
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index bcac3efcde41..da4c6342a647 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -5861,6 +5861,11 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
> */
> if (__xfer_to_guest_mode_work_pending())
> return 1;
> +
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + if (kvm_test_request(KVM_REQ_DIRTY_QUOTA_EXIT, vcpu))
> + return 1;
> +#endif
> }
>
> return 1;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 7713420abab0..1733be829197 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -3092,6 +3092,9 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
>
> guest_hv_clock->version = ++vcpu->hv_clock.version;
>
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(v->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
> read_unlock_irqrestore(&gpc->lock, flags);
>
> @@ -3566,6 +3569,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
> out:
> user_access_end();
> dirty:
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(vcpu->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
> }
>
> @@ -4815,6 +4821,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
> if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted)))
> vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
>
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(vcpu->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
> }
>
> @@ -10514,6 +10523,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
> r = 0;
> goto out;
> }
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + if (kvm_check_request(KVM_REQ_DIRTY_QUOTA_EXIT, vcpu)) {
> + vcpu->run->exit_reason = KVM_EXIT_DIRTY_QUOTA_EXHAUSTED;
> + r = 0;
> + goto out;
> + }
> +#endif
>
> /*
> * KVM_REQ_HV_STIMER has to be processed after
> diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
> index 40edf4d1974c..00a3ac438539 100644
> --- a/arch/x86/kvm/xen.c
> +++ b/arch/x86/kvm/xen.c
> @@ -435,9 +435,16 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
>
> read_unlock_irqrestore(&gpc1->lock, flags);
>
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(v->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(v->kvm, gpc1->memslot, gpc1->gpa >> PAGE_SHIFT);
> - if (user_len2)
> + if (user_len2) {
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(v->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(v->kvm, gpc2->memslot, gpc2->gpa >> PAGE_SHIFT);
> + }
> }
>
> void kvm_xen_update_runstate(struct kvm_vcpu *v, int state)
> @@ -549,6 +556,9 @@ void kvm_xen_inject_pending_events(struct kvm_vcpu *v)
> if (v->arch.xen.upcall_vector)
> kvm_xen_inject_vcpu_vector(v);
>
> +#ifdef CONFIG_HAVE_KVM_DIRTY_QUOTA
> + update_dirty_quota(v->kvm, PAGE_SIZE);
> +#endif
> mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
> }
>
> --
> 2.22.3
>
