kvm: x86/mmu: Allocate struct kvm_mmu_pages for all pages in TDP MMU

Attach struct kvm_mmu_pages to every page in the TDP MMU to track
metadata, facilitate NX reclaim, and enable inproved parallelism of MMU
operations in future patches.

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 <bgardon@google.com>
Message-Id: <20201014182700.2888246-12-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 082684c..d44858b 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1004,7 +1004,11 @@ struct kvm_arch {
         * operations.
         */
        bool tdp_mmu_enabled;
+
+       /* List of struct tdp_mmu_pages being used as roots */
        struct list_head tdp_mmu_roots;
+       /* List of struct tdp_mmu_pages not being used as roots */
+       struct list_head tdp_mmu_pages;
 };
 
 struct kvm_vm_stat {

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index ae8ac15..f068022 100644 (file)
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -28,6 +28,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
        kvm->arch.tdp_mmu_enabled = true;
 
        INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
+       INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
 }
 
 void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
@@ -169,6 +170,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
        bool is_leaf = is_present && is_last_spte(new_spte, level);
        bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
        u64 *pt;
+       struct kvm_mmu_page *sp;
        u64 old_child_spte;
        int i;
 
@@ -234,6 +236,9 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
         */
        if (was_present && !was_leaf && (pfn_changed || !is_present)) {
                pt = spte_to_child_pt(old_spte, level);
+               sp = sptep_to_sp(pt);
+
+               list_del(&sp->link);
 
                for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
                        old_child_spte = READ_ONCE(*(pt + i));
@@ -247,6 +252,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
                                                   KVM_PAGES_PER_HPAGE(level));
 
                free_page((unsigned long)pt);
+               kmem_cache_free(mmu_page_header_cache, sp);
        }
 }
 
@@ -424,8 +430,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
        bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
        struct kvm_mmu *mmu = vcpu->arch.mmu;
        struct tdp_iter iter;
-       struct kvm_mmu_memory_cache *pf_pt_cache =
-                       &vcpu->arch.mmu_shadow_page_cache;
+       struct kvm_mmu_page *sp;
        u64 *child_pt;
        u64 new_spte;
        int ret;
@@ -471,7 +476,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
                }
 
                if (!is_shadow_present_pte(iter.old_spte)) {
-                       child_pt = kvm_mmu_memory_cache_alloc(pf_pt_cache);
+                       sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
+                       list_add(&sp->link, &vcpu->kvm->arch.tdp_mmu_pages);
+                       child_pt = sp->spt;
                        clear_page(child_pt);
                        new_spte = make_nonleaf_spte(child_pt,
                                                     !shadow_accessed_mask);