[6/5] KVM: MMU: Optimize is_last_gpte()

Commit Message

Avi Kivity Sept. 12, 2012, 5:49 p.m. UTC

Instead of branchy code depending on level, gpte.ps, and mmu configuration,
prepare everything in a bitmap during mode changes and look it up during
runtime.

Signed-off-by: Avi Kivity <[e-mail]>
---
 arch/x86/include/asm/kvm_host.h |  7 +++++++
 arch/x86/kvm/mmu.c              | 20 ++++++++++++++++++++
 arch/x86/kvm/mmu.h              |  3 ++-
 arch/x86/kvm/paging_tmpl.h      | 25 +++++--------------------
 4 files changed, 34 insertions(+), 21 deletions(-)

Comments

Avi Kivity Sept. 12, 2012, 6:03 p.m. UTC | #1

On 09/12/2012 08:49 PM, Avi Kivity wrote:
> Instead of branchy code depending on level, gpte.ps, and mmu configuration,
> prepare everything in a bitmap during mode changes and look it up during
> runtime.

6/5 is buggy, sorry, will update it tomorrow.

Patch

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3318bde..78525f6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -298,6 +298,13 @@  struct kvm_mmu {
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
 
+	/*
+	 * Bitmap: bit set = last pte in walk
+	 * index[0]: pte.ps
+	 * index[1:2]: level
+	 */
+	u8 last_pte;
+
 	bool nx;
 
 	u64 pdptrs[4]; /* pae */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ce78408..30a574f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3548,6 +3548,22 @@  static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu
 	}
 }
 
+static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	u8 map = 0;
+	unsigned level, root_level = mmu->root_level;
+
+	if (root_level == PT32E_ROOT_LEVEL)
+		--root_level;
+	map |= 3;  /* PT_PAGE_TABLE_LEVEL always terminates */
+	for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
+		if (level <= PT_PDPE_LEVEL
+		    && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
+			map |= 2 << (2 * level - 1);
+	}
+	mmu->last_pte = map;
+}
+
 static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 					struct kvm_mmu *context,
 					int level)
@@ -3557,6 +3573,7 @@  static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 
 	reset_rsvds_bits_mask(vcpu, context);
 	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
 	context->new_cr3 = paging_new_cr3;
@@ -3586,6 +3603,7 @@  static int paging32_init_context(struct kvm_vcpu *vcpu,
 
 	reset_rsvds_bits_mask(vcpu, context);
 	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
@@ -3647,6 +3665,7 @@  static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	}
 
 	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	return 0;
 }
@@ -3724,6 +3743,7 @@  static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 	}
 
 	update_permission_bitmask(vcpu, g_context);
+	update_last_pte_bitmap(vcpu, g_context);
 
 	return 0;
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 143ee70..b08dd34 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -20,7 +20,8 @@ 
 #define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
 #define PT_DIRTY_SHIFT 6
 #define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
+#define PT_PAGE_SIZE_SHIFT 7
+#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
 #define PT_PAT_MASK (1ULL << 7)
 #define PT_GLOBAL_MASK (1ULL << 8)
 #define PT64_NX_SHIFT 63
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index eb4a668..dd89404 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -101,24 +101,6 @@  static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
-static bool FNAME(is_last_gpte)(struct guest_walker *walker,
-				struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				pt_element_t gpte)
-{
-	if (walker->level == PT_PAGE_TABLE_LEVEL)
-		return true;
-
-	if ((walker->level == PT_DIRECTORY_LEVEL) && is_large_pte(gpte) &&
-	    (PTTYPE == 64 || is_pse(vcpu)))
-		return true;
-
-	if ((walker->level == PT_PDPE_LEVEL) && is_large_pte(gpte) &&
-	    (mmu->root_level == PT64_ROOT_LEVEL))
-		return true;
-
-	return false;
-}
-
 /*
  * Fetch a guest pte for a guest virtual address
  */
@@ -140,6 +122,7 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	gpa_t real_gpa;
 	gfn_t gfn;
 	u32 ac;
+	bool last;
 
 	trace_kvm_mmu_pagetable_walk(addr, access);
 retry_walk:
@@ -220,8 +203,10 @@  retry_walk:
 			pte |= PT_ACCESSED_MASK;
 		}
 
-		walker->ptes[walker->level - 1] = pte;
-	} while (!FNAME(is_last_gpte)(walker, vcpu, mmu, pte));
+		index = (walker->level - 1) << 1;
+		index |= (pte >> PT_PAGE_SIZE_SHIFT) & 1;
+		last = mmu->last_pte & (1 << index);
+	} while (!last);
 
 	if (unlikely(eperm)) {
 		errcode |= PFERR_PRESENT_MASK;