Dirty logging ultimately breaks down MMU mappings to 4k granularity.
When dirty logging is no longer needed, these granaular mappings
represent a useless performance penalty. When dirty logging is disabled,
search the paging structure for mappings that could be re-constituted
into a large page mapping. Zap those mappings so that they can be
faulted in again at a higher mapping level.
Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.
This series can be viewed in Gerrit at:
https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538
Signed-off-by: Ben Gardon <bgar...@google.com>
---
arch/x86/kvm/mmu/mmu.c | 3 ++
arch/x86/kvm/mmu/tdp_mmu.c | 62 ++++++++++++++++++++++++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.h | 2 ++
3 files changed, 67 insertions(+)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b9074603f9df1..12892fc4f146d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6025,6 +6025,9 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
spin_lock(&kvm->mmu_lock);
slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
kvm_mmu_zap_collapsible_spte, true);
+
+ if (kvm->arch.tdp_mmu_enabled)
+ kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e5cb7f0ec23e8..a2895119655ac 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1099,3 +1099,65 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct
kvm_memory_slot *slot)
return spte_set;
}
+/*
+ * Clear non-leaf entries (and free associated page tables) which could
+ * be replaced by large mappings, for GFNs within the slot.
+ */
+static void zap_collapsible_spte_range(struct kvm *kvm,
+ struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end)
+{
+ struct tdp_iter iter;
+ kvm_pfn_t pfn;
+ bool spte_set = false;
+ int as_id = kvm_mmu_page_as_id(root);
+
+ for_each_tdp_pte_root(iter, root, start, end) {
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ is_last_spte(iter.old_spte, iter.level))
+ continue;
+
+ pfn = spte_to_pfn(iter.old_spte);
+ if (kvm_is_reserved_pfn(pfn) ||
+ !PageTransCompoundMap(pfn_to_page(pfn)))
+ continue;
+
+ *iter.sptep = 0;
+ handle_changed_spte(kvm, as_id, iter.gfn, iter.old_spte,
+ 0, iter.level);
+ spte_set = true;
+
+ spte_set = !tdp_mmu_iter_cond_resched(kvm, &iter);
+ }
+
+ if (spte_set)
+ kvm_flush_remote_tlbs(kvm);
+}
+
+/*
+ * Clear non-leaf entries (and free associated page tables) which could
+ * be replaced by large mappings, for GFNs within the slot.
+ */
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ struct kvm_mmu_page *root;
+ int root_as_id;
+
+ for_each_tdp_mmu_root(kvm, root) {
+ root_as_id = kvm_mmu_page_as_id(root);
+ if (root_as_id != slot->as_id)
+ continue;
+
+ /*
+ * Take a reference on the root so that it cannot be freed if
+ * this thread releases the MMU lock and yields in this loop.
+ */
+ get_tdp_mmu_root(kvm, root);
+
+ zap_collapsible_spte_range(kvm, root, slot->base_gfn,
+ slot->base_gfn + slot->npages);
+
+ put_tdp_mmu_root(kvm, root);
+ }
+}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 2c9322ba3462b..10e70699c5372 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -38,4 +38,6 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
gfn_t gfn, unsigned long mask,
bool wrprot);
bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot);
#endif /* __KVM_X86_MMU_TDP_MMU_H */
--
2.28.0.709.gb0816b6eb0-goog
