KVM: MMU: Reinstate pte prefetch on invlpg

Commit fb341f57 removed the pte prefetch on guest invlpg, citing guest races.
However, the SDM is adamant that prefetch is allowed:

  "The processor may create entries in paging-structure caches for
   translations required for prefetches and for accesses that are a
   result of speculative execution that would never actually occur
   in the executed code path."

And, in fact, there was a race in the prefetch code: we picked up the pte
without the mmu lock held, so an older invlpg could install the pte over
a newer invlpg.

Reinstate the prefetch logic, but this time note whether another invlpg has
executed using a counter.  If a race occured, do not install the pte.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -389,6 +389,7 @@ struct kvm_arch {
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_alloc_mmu_pages;
+	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
 	 * Hash table of struct kvm_mmu_page.

arch/x86/kvm/mmu.c

@@ -2613,20 +2613,11 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	int flooded = 0;
 	int npte;
 	int r;
+	int invlpg_counter;
 
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 
-	switch (bytes) {
-	case 4:
-		gentry = *(const u32 *)new;
-		break;
-	case 8:
-		gentry = *(const u64 *)new;
-		break;
-	default:
-		gentry = 0;
-		break;
-	}
+	invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter);
 
 	/*
 	 * Assume that the pte write on a page table of the same type
@@ -2634,16 +2625,34 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	 * (might be false while changing modes).  Note it is verified later
 	 * by update_pte().
 	 */
-	if (is_pae(vcpu) && bytes == 4) {
+	if ((is_pae(vcpu) && bytes == 4) || !new) {
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
-		gpa &= ~(gpa_t)7;
-		r = kvm_read_guest(vcpu->kvm, gpa, &gentry, 8);
+		if (is_pae(vcpu)) {
+			gpa &= ~(gpa_t)7;
+			bytes = 8;
+		}
+		r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8));
 		if (r)
 			gentry = 0;
+		new = (const u8 *)&gentry;
+	}
+
+	switch (bytes) {
+	case 4:
+		gentry = *(const u32 *)new;
+		break;
+	case 8:
+		gentry = *(const u64 *)new;
+		break;
+	default:
+		gentry = 0;
+		break;
 	}
 
 	mmu_guess_page_from_pte_write(vcpu, gpa, gentry);
 	spin_lock(&vcpu->kvm->mmu_lock);
+	if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
+		gentry = 0;
 	kvm_mmu_access_page(vcpu, gfn);
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;

arch/x86/kvm/paging_tmpl.h

@@ -463,6 +463,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	struct kvm_shadow_walk_iterator iterator;
+	gpa_t pte_gpa = -1;
 	int level;
 	u64 *sptep;
 	int need_flush = 0;
@@ -476,6 +477,10 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		if (level == PT_PAGE_TABLE_LEVEL  ||
 		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
 		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
+			struct kvm_mmu_page *sp = page_header(__pa(sptep));
+
+			pte_gpa = (sp->gfn << PAGE_SHIFT);
+			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
 			if (is_shadow_present_pte(*sptep)) {
 				rmap_remove(vcpu->kvm, sptep);
@@ -493,7 +498,17 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 
 	if (need_flush)
 		kvm_flush_remote_tlbs(vcpu->kvm);
+
+	atomic_inc(&vcpu->kvm->arch.invlpg_counter);
+
 	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	if (pte_gpa == -1)
+		return;
+
+	if (mmu_topup_memory_caches(vcpu))
+		return;
+	kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0);
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,