KVM: Rename/refactor kvm_is_reserved_pfn() to kvm_pfn_to_refcounted_page()

Rename and refactor kvm_is_reserved_pfn() to kvm_pfn_to_refcounted_page()
to better reflect what KVM is actually checking, and to eliminate extra
pfn_to_page() lookups.  The kvm_release_pfn_*() an kvm_try_get_pfn()
helpers in particular benefit from "refouncted" nomenclature, as it's not
all that obvious why KVM needs to get/put refcounts for some PG_reserved
pages (ZERO_PAGE and ZONE_DEVICE).

Add a comment to call out that the list of exceptions to PG_reserved is
all but guaranteed to be incomplete.  The list has mostly been compiled
by people throwing noodles at KVM and finding out they stick a little too
well, e.g. the ZERO_PAGE's refcount overflowed and ZONE_DEVICE pages
didn't get freed.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b209aaf..7ebb97c 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -534,6 +534,7 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
        kvm_pfn_t pfn;
        u64 old_spte = *sptep;
        int level = sptep_to_sp(sptep)->role.level;
+       struct page *page;
 
        if (!is_shadow_present_pte(old_spte) ||
            !spte_has_volatile_bits(old_spte))
@@ -549,11 +550,13 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
        pfn = spte_to_pfn(old_spte);
 
        /*
-        * KVM does not hold the refcount of the page used by
-        * kvm mmu, before reclaiming the page, we should
-        * unmap it from mmu first.
+        * KVM doesn't hold a reference to any pages mapped into the guest, and
+        * instead uses the mmu_notifier to ensure that KVM unmaps any pages
+        * before they are reclaimed.  Sanity check that, if the pfn is backed
+        * by a refcounted page, the refcount is elevated.
         */
-       WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+       page = kvm_pfn_to_refcounted_page(pfn);
+       WARN_ON(page && !page_count(page));
 
        if (is_accessed_spte(old_spte))
                kvm_set_pfn_accessed(pfn);
@@ -2881,7 +2884,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
        if (unlikely(fault->max_level == PG_LEVEL_4K))
                return;
 
-       if (is_error_noslot_pfn(fault->pfn) || kvm_is_reserved_pfn(fault->pfn))
+       if (is_error_noslot_pfn(fault->pfn) || !kvm_pfn_to_refcounted_page(fault->pfn))
                return;
 
        if (kvm_slot_dirty_track_enabled(slot))
@@ -5993,7 +5996,7 @@ restart:
                 * the guest, and the guest page table is using 4K page size
                 * mapping if the indirect sp has level = 1.
                 */
-               if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
+               if (sp->role.direct && kvm_pfn_to_refcounted_page(pfn) &&
                    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
                                                               pfn, PG_LEVEL_NUM)) {
                        pte_list_remove(kvm, rmap_head, sptep);

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 8e8d412..1e777b7 100644 (file)
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1751,7 +1751,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
                 */
                pfn = spte_to_pfn(iter.old_spte);
 
-               if (kvm_is_reserved_pfn(pfn))
+               if (!kvm_pfn_to_refcounted_page(pfn))
                        continue;
 
                max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6fb433a..a2bbdf3 100644 (file)
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1570,7 +1570,7 @@ void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 
-bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn);
 bool kvm_is_zone_device_page(struct page *page);
 
 struct kvm_irq_ack_notifier {

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index aa1bcd5..0419609 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -182,19 +182,36 @@ bool kvm_is_zone_device_page(struct page *page)
        return is_zone_device_page(page);
 }
 
-bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
+/*
+ * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted
+ * page, NULL otherwise.  Note, the list of refcounted PG_reserved page types
+ * is likely incomplete, it has been compiled purely through people wanting to
+ * back guest with a certain type of memory and encountering issues.
+ */
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn)
 {
+       struct page *page;
+
+       if (!pfn_valid(pfn))
+               return NULL;
+
+       page = pfn_to_page(pfn);
+       if (!PageReserved(page))
+               return page;
+
+       /* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */
+       if (is_zero_pfn(pfn))
+               return page;
+
        /*
         * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
         * perspective they are "normal" pages, albeit with slightly different
         * usage rules.
         */
-       if (pfn_valid(pfn))
-               return PageReserved(pfn_to_page(pfn)) &&
-                      !is_zero_pfn(pfn) &&
-                      !kvm_is_zone_device_page(pfn_to_page(pfn));
+       if (kvm_is_zone_device_page(page))
+               return page;
 
-       return true;
+       return NULL;
 }
 
 /*
@@ -2501,9 +2518,12 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
 
 static int kvm_try_get_pfn(kvm_pfn_t pfn)
 {
-       if (kvm_is_reserved_pfn(pfn))
+       struct page *page = kvm_pfn_to_refcounted_page(pfn);
+
+       if (!page)
                return 1;
-       return get_page_unless_zero(pfn_to_page(pfn));
+
+       return get_page_unless_zero(page);
 }
 
 static int hva_to_pfn_remapped(struct vm_area_struct *vma,
@@ -2728,6 +2748,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
  */
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
+       struct page *page;
        kvm_pfn_t pfn;
 
        pfn = gfn_to_pfn(kvm, gfn);
@@ -2735,10 +2756,11 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
        if (is_error_noslot_pfn(pfn))
                return KVM_ERR_PTR_BAD_PAGE;
 
-       if (kvm_is_reserved_pfn(pfn))
+       page = kvm_pfn_to_refcounted_page(pfn);
+       if (!page)
                return KVM_ERR_PTR_BAD_PAGE;
 
-       return pfn_to_page(pfn);
+       return page;
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
@@ -2841,8 +2863,16 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(kvm_pfn_t pfn)
 {
-       if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
-               kvm_release_page_clean(pfn_to_page(pfn));
+       struct page *page;
+
+       if (is_error_noslot_pfn(pfn))
+               return;
+
+       page = kvm_pfn_to_refcounted_page(pfn);
+       if (!page)
+               return;
+
+       kvm_release_page_clean(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
@@ -2857,8 +2887,16 @@ EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
 
 void kvm_release_pfn_dirty(kvm_pfn_t pfn)
 {
-       if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
-               kvm_release_page_dirty(pfn_to_page(pfn));
+       struct page *page;
+
+       if (is_error_noslot_pfn(pfn))
+               return;
+
+       page = kvm_pfn_to_refcounted_page(pfn);
+       if (!page)
+               return;
+
+       kvm_release_page_dirty(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);