KVM: MMU: large page support

Create large pages mappings if the guest PTE's are marked as such and
the underlying memory is hugetlbfs backed.  If the largepage contains
write-protected pages, a large pte is not used.

Gives a consistent 2% improvement for data copies on ram mounted
filesystem, without NPT/EPT.

Anthony measures a 4% improvement on 4-way kernbench, with NPT.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

2 files changed, 14 insertions, 0 deletions

diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index 8c3f74b73524..95473ef5a906 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -39,6 +39,13 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
+/* shadow tables are PAE even on non-PAE hosts */
+#define KVM_HPAGE_SHIFT 21
+#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
+#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
+
+#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+
 #define DE_VECTOR 0
 #define UD_VECTOR 6
 #define NM_VECTOR 7
@@ -230,6 +237,7 @@ struct kvm_vcpu_arch {
         struct {
                 gfn_t gfn;          /* presumed gfn during guest pte update */
                 struct page *page;  /* page corresponding to that gfn */
+                int largepage;
         } update_pte;
 
         struct i387_fxsave_struct host_fx_image;
@@ -307,6 +315,7 @@ struct kvm_vm_stat {
         u32 mmu_recycled;
         u32 mmu_cache_miss;
         u32 remote_tlb_flush;
+        u32 lpages;
 };
 
 struct kvm_vcpu_stat {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 994278fb5883..9750bb3c5a75 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -103,6 +103,10 @@ struct kvm_memory_slot {
         unsigned long flags;
         unsigned long *rmap;
         unsigned long *dirty_bitmap;
+        struct {
+                unsigned long rmap_pde;
+                int write_count;
+        } *lpage_info;
         unsigned long userspace_addr;
         int user_alloc;
 };
@@ -169,6 +173,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
                                 int user_alloc);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,