KVM: MMU: Avoid handling same rmap_pde in kvm_handle_hva_range()

When we invalidate a THP page, we call the handler with the same
rmap_pde argument 512 times in the following loop:

  for each guest page in the range
    for each level
      unmap using rmap

This patch avoids these extra handler calls by changing the loop order
like this:

  for each level
    for each rmap in the range
      unmap using rmap

With the preceding patches in the patch series, this made THP page
invalidation more than 5 times faster on our x86 host: the host became
more responsive during swapping the guest's memory as a result.
Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/kvm/mmu.c

@@ -1277,7 +1277,7 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 
 	kvm_for_each_memslot(memslot, slots) {
 		unsigned long hva_start, hva_end;
-		gfn_t gfn, gfn_end;
+		gfn_t gfn_start, gfn_end;
 
 		hva_start = max(start, memslot->userspace_addr);
 		hva_end = min(end, memslot->userspace_addr +
@@ -1286,19 +1286,27 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 			continue;
 		/*
 		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
-		 * {gfn, gfn+1, ..., gfn_end-1}.
+		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
 		 */
-		gfn = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_start = hva_to_gfn_memslot(hva_start, memslot);
 		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
 
-		for (; gfn < gfn_end; ++gfn) {
-			for (j = PT_PAGE_TABLE_LEVEL;
-			     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
-				unsigned long *rmapp;
+		for (j = PT_PAGE_TABLE_LEVEL;
+		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
+			unsigned long idx, idx_end;
+			unsigned long *rmapp;
 
-				rmapp = __gfn_to_rmap(gfn, j, memslot);
-				ret |= handler(kvm, rmapp, memslot, data);
-			}
+			/*
+			 * {idx(page_j) | page_j intersects with
+			 *  [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+			 */
+			idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
+			idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
+
+			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
+
+			for (; idx <= idx_end; ++idx)
+				ret |= handler(kvm, rmapp++, memslot, data);
 		}
 	}