KVM: x86/mmu: Expose number of shadow MMU shadow pages as a stat

Turn arch.n_used_mmu_pages into a stat, mmu_shadow_pages, as the number of
live shadow pages is arguably _the_ most critical datapoint when it comes
to analyzing the shadow MMU.  Before the TDP MMU came along, i.e. when the
shadow MMU was the only MMU, explicitly tracking the number of shadow pages
wasn't as interesting, because the same information could more or less be
gleaned from the pages_{1g,2m,4k} stats.  But with the TDP MMU, where the
shadow MMU is only used for nested TDP, it becomes extremely difficult, if
not impossible, to determine which SPTEs are coming from the TDP MMU, and
which are coming from the shadow MMU.

E.g. when triaging/debugging shadow MMU performance issues due to "too many
shadow pages", being able to observe that 99%+ of all shadow pages are
unsync is critical to being able to deduce that KVM is effectively leaking
shadow pages.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260612133727.411902-1-seanjc@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 eee473717c0e5a1ee128f2ba0c66415b0be6ab1e..9347c2b62cba499f5e14c827d1806c217fbe8016 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1434,7 +1434,6 @@ enum kvm_mmu_type {
 };
 
 struct kvm_arch {
-       unsigned long n_used_mmu_pages;
        unsigned long n_requested_mmu_pages;
        unsigned long n_max_mmu_pages;
        unsigned int indirect_shadow_pages;
@@ -1700,6 +1699,7 @@ struct kvm_vm_stat {
        u64 mmu_recycled;
        u64 mmu_cache_miss;
        u64 mmu_unsync;
+       u64 mmu_shadow_pages;
        union {
                struct {
                        atomic64_t pages_4k;

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 26ed97efda919a315359d3f7333ba523b81ce3c9..bb09a9af3a353a1d39f4031b4daddb38d23d1e73 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1801,13 +1801,13 @@ static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 
 static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-       kvm->arch.n_used_mmu_pages++;
+       kvm->stat.mmu_shadow_pages++;
        kvm_account_pgtable_pages((void *)sp->spt, +1);
 }
 
 static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-       kvm->arch.n_used_mmu_pages--;
+       kvm->stat.mmu_shadow_pages--;
        kvm_account_pgtable_pages((void *)sp->spt, -1);
 }
 
@@ -2835,9 +2835,9 @@ restart:
 
 static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
 {
-       if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
+       if (kvm->arch.n_max_mmu_pages > kvm->stat.mmu_shadow_pages)
                return kvm->arch.n_max_mmu_pages -
-                       kvm->arch.n_used_mmu_pages;
+                       kvm->stat.mmu_shadow_pages;
 
        return 0;
 }
@@ -2873,11 +2873,11 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
 {
        write_lock(&kvm->mmu_lock);
 
-       if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
-               kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages -
+       if (kvm->stat.mmu_shadow_pages > goal_nr_mmu_pages) {
+               kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->stat.mmu_shadow_pages -
                                                  goal_nr_mmu_pages);
 
-               goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
+               goal_nr_mmu_pages = kvm->stat.mmu_shadow_pages;
        }
 
        kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;

diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index fa01719baf8d4f046e90dc0676109145628afe15..8354d9f39777871449edf0aba8206806c4bfdb6d 100644 (file)
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -303,7 +303,7 @@ TRACE_EVENT(
 
        TP_fast_assign(
                __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen;
-               __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages;
+               __entry->mmu_used_pages = kvm->stat.mmu_shadow_pages;
        ),
 
        TP_printk("kvm-mmu-valid-gen %u used_pages %x",

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 96c465040756f93985a742d59afe40a437aa6ba1..afcac1042947a56f5bb8de44c88de3d4b4f30bb8 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -244,6 +244,7 @@ const struct kvm_stats_desc kvm_vm_stats_desc[] = {
        STATS_DESC_COUNTER(VM, mmu_recycled),
        STATS_DESC_COUNTER(VM, mmu_cache_miss),
        STATS_DESC_ICOUNTER(VM, mmu_unsync),
+       STATS_DESC_ICOUNTER(VM, mmu_shadow_pages),
        STATS_DESC_ICOUNTER(VM, pages_4k),
        STATS_DESC_ICOUNTER(VM, pages_2m),
        STATS_DESC_ICOUNTER(VM, pages_1g),