[RFC PATCH 3/3] KVM: MMU: Optimize guest page table walk

[Takuya Yoshikawa <takuya.yoshikawa@gmail.com>]

From: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>

We optimize multi level guest page table walk as follows:

  1. We cache the memslot which, probably, includes the next guest page
     tables to avoid searching for it many times.
  2. We use get_user() instead of copy_from_user().

Note that this is kind of a restricted way of Xiao's more generic
work: "KVM: optimize memslots searching and cache GPN to GFN."

With this patch applied, paging64_walk_addr_generic() has improved
as the following tracing results show.

Before:
  3.169 us   |  paging64_walk_addr_generic();
  1.880 us   |  paging64_walk_addr_generic();
  1.243 us   |  paging64_walk_addr_generic();
  1.517 us   |  paging64_walk_addr_generic();
  3.009 us   |  paging64_walk_addr_generic();
  1.814 us   |  paging64_walk_addr_generic();
  1.340 us   |  paging64_walk_addr_generic();
  1.659 us   |  paging64_walk_addr_generic();
  1.748 us   |  paging64_walk_addr_generic();
  1.488 us   |  paging64_walk_addr_generic();

After:
  1.714 us   |  paging64_walk_addr_generic();
  0.806 us   |  paging64_walk_addr_generic();
  0.664 us   |  paging64_walk_addr_generic();
  0.619 us   |  paging64_walk_addr_generic();
  0.645 us   |  paging64_walk_addr_generic();
  0.605 us   |  paging64_walk_addr_generic();
  1.388 us   |  paging64_walk_addr_generic();
  0.753 us   |  paging64_walk_addr_generic();
  0.594 us   |  paging64_walk_addr_generic();
  0.833 us   |  paging64_walk_addr_generic();

Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
---
 arch/x86/kvm/paging_tmpl.h |   37 ++++++++++++++++++++++++++++++++-----
 1 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 109939a..614aa3f 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -109,12 +109,37 @@ static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte)
 	return access;
 }
 
+/*
+ * Read the guest PTE refered to by table_gfn and offset and put it into ptep.
+ *
+ * *slot_hint, if not NULL, should point to a memslot which probably includes
+ * the guest PTE.  The actual memslot will be put back into this so that
+ * callers can cache it.
+ */
 static int FNAME(read_guest_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				 gfn_t table_gfn, int offset, pt_element_t *ptep)
+				 gfn_t table_gfn, int offset, pt_element_t *ptep,
+				 struct kvm_memory_slot **slot_hint)
 {
-	return kvm_read_guest_page_mmu(vcpu, mmu, table_gfn, ptep,
-				       offset, sizeof(*ptep),
-				       PFERR_USER_MASK | PFERR_WRITE_MASK);
+	unsigned long addr;
+	pt_element_t __user *ptep_user;
+	gfn_t real_gfn;
+
+	real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+				      PFERR_USER_MASK | PFERR_WRITE_MASK);
+	if (real_gfn == UNMAPPED_GVA)
+		return -EFAULT;
+
+	real_gfn = gpa_to_gfn(real_gfn);
+
+	if (!(*slot_hint) || !gfn_in_memslot(*slot_hint, real_gfn))
+		*slot_hint = gfn_to_memslot(vcpu->kvm, real_gfn);
+
+	addr = gfn_to_hva_memslot(*slot_hint, real_gfn);
+	if (kvm_is_error_hva(addr))
+		return -EFAULT;
+
+	ptep_user = (pt_element_t __user *)((void *)addr + offset);
+	return get_user(*ptep, ptep_user);
 }
 
 /*
@@ -130,6 +155,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	gpa_t pte_gpa;
 	bool eperm, present, rsvd_fault;
 	int offset, write_fault, user_fault, fetch_fault;
+	struct kvm_memory_slot *slot_cache = NULL;
 
 	write_fault = access & PFERR_WRITE_MASK;
 	user_fault = access & PFERR_USER_MASK;
@@ -168,7 +194,8 @@ walk:
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		if (FNAME(read_guest_pte)(vcpu, mmu, table_gfn, offset, &pte)) {
+		if (FNAME(read_guest_pte)(vcpu, mmu, table_gfn,
+					  offset, &pte, &slot_cache)) {
 			present = false;
 			break;
 		}
-- 
1.7.1