From b9b71f43683ae9d76b0989249607bbe8c9eb6c5c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 24 Jun 2022 17:18:08 +0000 Subject: [PATCH] KVM: x86/mmu: Buffer nested MMU split_desc_cache only by default capacity Buffer split_desc_cache, the cache used to allcoate rmap list entries, only by the default cache capacity (currently 40), not by doubling the minimum (513). Aliasing L2 GPAs to L1 GPAs is uncommon, thus eager page splitting is unlikely to need 500+ entries. And because each object is a non-trivial 128 bytes (see struct pte_list_desc), those extra ~500 entries means KVM is in all likelihood wasting ~64kb of memory per VM. Link: https://lore.kernel.org/all/YrTDcrsn0%2F+alpzf@google.com Cc: David Matlack Signed-off-by: Sean Christopherson Message-Id: <20220624171808.2845941-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d5554cd61492..f7fa4c31b7c5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6118,17 +6118,25 @@ static bool need_topup_split_caches_or_resched(struct kvm *kvm) static int topup_split_caches(struct kvm *kvm) { + /* + * Allocating rmap list entries when splitting huge pages for nested + * MMUs is uncommon as KVM needs to allocate if and only if there is + * more than one rmap entry for a gfn, i.e. requires an L1 gfn to be + * aliased by multiple L2 gfns. Aliasing gfns when using TDP is very + * atypical for VMMs; a few gfns are often aliased during boot, e.g. + * when remapping firmware, but aliasing rarely occurs post-boot). If + * there is only one rmap entry, rmap->val points directly at that one + * entry and doesn't need to allocate a list. Buffer the cache by the + * default capacity so that KVM doesn't have to topup the cache if it + * encounters an aliased gfn or two. + */ + const int capacity = SPLIT_DESC_CACHE_MIN_NR_OBJECTS + + KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE; int r; lockdep_assert_held(&kvm->slots_lock); - /* - * Setting capacity == min would cause KVM to drop mmu_lock even if - * just one object was consumed from the cache, so make capacity - * larger than min. - */ - r = __kvm_mmu_topup_memory_cache(&kvm->arch.split_desc_cache, - 2 * SPLIT_DESC_CACHE_MIN_NR_OBJECTS, + r = __kvm_mmu_topup_memory_cache(&kvm->arch.split_desc_cache, capacity, SPLIT_DESC_CACHE_MIN_NR_OBJECTS); if (r) return r;