From b83ab124ded3c17f911668522a2e916ca8d3c523 Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Fri, 28 Jul 2023 18:35:24 -0700 Subject: [PATCH] KVM: x86: Add a new page-track hook to handle memslot deletion Add a new page-track hook, track_remove_region(), that is called when a memslot DELETE operation is about to be committed. The "remove" hook will be used by KVMGT and will effectively replace the existing track_flush_slot() altogether now that KVM itself doesn't rely on the "flush" hook either. The "flush" hook is flawed as it's invoked before the memslot operation is guaranteed to succeed, i.e. KVM might ultimately keep the existing memslot without notifying external page track users, a.k.a. KVMGT. In practice, this can't currently happen on x86, but there are no guarantees that won't change in the future, not to mention that "flush" does a very poor job of describing what is happening. Pass in the gfn+nr_pages instead of the slot itself so external users, i.e. KVMGT, don't need to exposed to KVM internals (memslots). This will help set the stage for additional cleanups to the page-track APIs. Opportunistically align the existing srcu_read_lock_held() usage so that the new case doesn't stand out like a sore thumb (and not aligning the new code makes bots unhappy). Cc: Zhenyu Wang Tested-by: Yongwei Ma Signed-off-by: Yan Zhao Co-developed-by: Sean Christopherson Link: https://lore.kernel.org/r/20230729013535.1070024-19-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_page_track.h | 12 ++++++++++++ arch/x86/kvm/mmu/page_track.c | 27 +++++++++++++++++++++++++-- arch/x86/kvm/x86.c | 3 +++ 3 files changed, 40 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index f74468264..cfd36c2 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -43,6 +43,17 @@ struct kvm_page_track_notifier_node { */ void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot, struct kvm_page_track_notifier_node *node); + + /* + * Invoked when a memory region is removed from the guest. Or in KVM + * terms, when a memslot is deleted. + * + * @gfn: base gfn of the region being removed + * @nr_pages: number of pages in the to-be-removed region + * @node: this node + */ + void (*track_remove_region)(gfn_t gfn, unsigned long nr_pages, + struct kvm_page_track_notifier_node *node); }; int kvm_page_track_init(struct kvm *kvm); @@ -75,6 +86,7 @@ kvm_page_track_unregister_notifier(struct kvm *kvm, void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot); +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot); bool kvm_page_track_has_external_user(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index cfd0b80..640e383 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -270,7 +270,7 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) + srcu_read_lock_held(&head->track_srcu)) if (n->track_write) n->track_write(gpa, new, bytes, n); srcu_read_unlock(&head->track_srcu, idx); @@ -298,12 +298,35 @@ void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot) idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) + srcu_read_lock_held(&head->track_srcu)) if (n->track_flush_slot) n->track_flush_slot(kvm, slot, n); srcu_read_unlock(&head->track_srcu, idx); } +/* + * Notify external page track nodes that a memory region is being removed from + * the VM, e.g. so that users can free any associated metadata. + */ +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + struct kvm_page_track_notifier_head *head; + struct kvm_page_track_notifier_node *n; + int idx; + + head = &kvm->arch.track_notifier_head; + + if (hlist_empty(&head->track_notifier_list)) + return; + + idx = srcu_read_lock(&head->track_srcu); + hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, + srcu_read_lock_held(&head->track_srcu)) + if (n->track_remove_region) + n->track_remove_region(slot->base_gfn, slot->npages, n); + srcu_read_unlock(&head->track_srcu, idx); +} + bool kvm_page_track_has_external_user(struct kvm *kvm) { return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 161e97e..7928464 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12793,6 +12793,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { + if (change == KVM_MR_DELETE) + kvm_page_track_delete_slot(kvm, old); + if (!kvm->arch.n_requested_mmu_pages && (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { unsigned long nr_mmu_pages; -- 2.7.4