X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fmmu.c;h=6fbcb48d5a9bb8e144adddb81fa71d99c1b039d7;hp=6ed7d633aefece84228ed12dc25e71e7eb047840;hb=3be2264be3c00865116f997dc53ebcc90fe7fc4b;hpb=805d32dea4dfb8319aaf7e73a681ad410a5e331a

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 6ed7d63..6fbcb48 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -173,12 +173,7 @@ struct kvm_shadow_walk_iterator {
 	     shadow_walk_okay(&(_walker));			\
 	     shadow_walk_next(&(_walker)))
 
-
-struct kvm_unsync_walk {
-	int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
-};
-
-typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp);
+typedef int (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp);
 
 static struct kmem_cache *pte_chain_cache;
 static struct kmem_cache *rmap_desc_cache;
@@ -222,7 +217,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
-static int is_write_protection(struct kvm_vcpu *vcpu)
+static bool is_write_protection(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
 }
@@ -436,9 +431,9 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
 	int i;
 
 	gfn = unalias_gfn(kvm, gfn);
+	slot = gfn_to_memslot_unaliased(kvm, gfn);
 	for (i = PT_DIRECTORY_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		slot          = gfn_to_memslot_unaliased(kvm, gfn);
 		write_count   = slot_largepage_idx(gfn, slot, i);
 		*write_count -= 1;
 		WARN_ON(*write_count < 0);
@@ -652,7 +647,6 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
 {
 	struct kvm_rmap_desc *desc;
-	struct kvm_rmap_desc *prev_desc;
 	u64 *prev_spte;
 	int i;
 
@@ -664,7 +658,6 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
 		return NULL;
 	}
 	desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
-	prev_desc = NULL;
 	prev_spte = NULL;
 	while (desc) {
 		for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) {
@@ -792,7 +785,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 	int retval = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -923,7 +916,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 	sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	INIT_LIST_HEAD(&sp->oos_link);
 	bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
 	sp->multimapped = 0;
 	sp->parent_pte = parent_pte;
@@ -1007,8 +999,7 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
 }
 
 
-static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			    mmu_parent_walk_fn fn)
+static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn)
 {
 	struct kvm_pte_chain *pte_chain;
 	struct hlist_node *node;
@@ -1017,8 +1008,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 
 	if (!sp->multimapped && sp->parent_pte) {
 		parent_sp = page_header(__pa(sp->parent_pte));
-		fn(vcpu, parent_sp);
-		mmu_parent_walk(vcpu, parent_sp, fn);
+		fn(parent_sp);
+		mmu_parent_walk(parent_sp, fn);
 		return;
 	}
 	hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
@@ -1026,8 +1017,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			if (!pte_chain->parent_ptes[i])
 				break;
 			parent_sp = page_header(__pa(pte_chain->parent_ptes[i]));
-			fn(vcpu, parent_sp);
-			mmu_parent_walk(vcpu, parent_sp, fn);
+			fn(parent_sp);
+			mmu_parent_walk(parent_sp, fn);
 		}
 }
 
@@ -1064,16 +1055,15 @@ static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
 		}
 }
 
-static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static int unsync_walk_fn(struct kvm_mmu_page *sp)
 {
 	kvm_mmu_update_parents_unsync(sp);
 	return 1;
 }
 
-static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu,
-					struct kvm_mmu_page *sp)
+static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
 {
-	mmu_parent_walk(vcpu, sp, unsync_walk_fn);
+	mmu_parent_walk(sp, unsync_walk_fn);
 	kvm_mmu_update_parents_unsync(sp);
 }
 
@@ -1199,6 +1189,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	WARN_ON(!sp->unsync);
+	trace_kvm_mmu_sync_page(sp);
 	sp->unsync = 0;
 	--kvm->stat.mmu_unsync;
 }
@@ -1207,12 +1198,11 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 
 static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
-	if (sp->role.glevels != vcpu->arch.mmu.root_level) {
+	if (sp->role.cr4_pae != !!is_pae(vcpu)) {
 		kvm_mmu_zap_page(vcpu->kvm, sp);
 		return 1;
 	}
 
-	trace_kvm_mmu_sync_page(sp);
 	if (rmap_write_protect(vcpu->kvm, sp->gfn))
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	kvm_unlink_unsync_page(vcpu->kvm, sp);
@@ -1330,7 +1320,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role.level = level;
 	role.direct = direct;
 	if (role.direct)
-		role.glevels = 0;
+		role.cr4_pae = 0;
 	role.access = access;
 	if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
@@ -1351,7 +1341,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 			if (sp->unsync_children) {
 				set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
-				kvm_mmu_mark_parents_unsync(vcpu, sp);
+				kvm_mmu_mark_parents_unsync(sp);
 			}
 			trace_kvm_mmu_get_page(sp, false);
 			return sp;
@@ -1573,13 +1563,14 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	r = 0;
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
+restart:
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
 		if (sp->gfn == gfn && !sp->role.direct) {
 			pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
 				 sp->role.word);
 			r = 1;
 			if (kvm_mmu_zap_page(kvm, sp))
-				n = bucket->first;
+				goto restart;
 		}
 	return r;
 }
@@ -1593,13 +1584,14 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
+restart:
 	hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
 		if (sp->gfn == gfn && !sp->role.direct
 		    && !sp->role.invalid) {
 			pgprintk("%s: zap %lx %x\n",
 				 __func__, gfn, sp->role.word);
 			if (kvm_mmu_zap_page(kvm, sp))
-				nn = bucket->first;
+				goto restart;
 		}
 	}
 }
@@ -1626,20 +1618,6 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp)
 	}
 }
 
-struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
-{
-	struct page *page;
-
-	gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
-
-	if (gpa == UNMAPPED_GVA)
-		return NULL;
-
-	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-
-	return page;
-}
-
 /*
  * The function is based on mtrr_type_lookup() in
  * arch/x86/kernel/cpu/mtrr/generic.c
@@ -1752,7 +1730,6 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	struct kvm_mmu_page *s;
 	struct hlist_node *node, *n;
 
-	trace_kvm_mmu_unsync_page(sp);
 	index = kvm_page_table_hashfn(sp->gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	/* don't unsync if pagetable is shadowed with multiple roles */
@@ -1762,10 +1739,11 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		if (s->role.word != sp->role.word)
 			return 1;
 	}
+	trace_kvm_mmu_unsync_page(sp);
 	++vcpu->kvm->stat.mmu_unsync;
 	sp->unsync = 1;
 
-	kvm_mmu_mark_parents_unsync(vcpu, sp);
+	kvm_mmu_mark_parents_unsync(sp);
 
 	mmu_convert_notrap(sp);
 	return 0;
@@ -1892,6 +1870,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 			child = page_header(pte & PT64_BASE_ADDR_MASK);
 			mmu_page_remove_parent_pte(child, sptep);
+			__set_spte(sptep, shadow_trap_nonpresent_pte);
+			kvm_flush_remote_tlbs(vcpu->kvm);
 		} else if (pfn != spte_to_pfn(*sptep)) {
 			pgprintk("hfn old %lx new %lx\n",
 				 spte_to_pfn(*sptep), pfn);
@@ -2081,21 +2061,23 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
 		ASSERT(!VALID_PAGE(root));
-		if (tdp_enabled)
-			direct = 1;
 		if (mmu_check_root(vcpu, root_gfn))
 			return 1;
+		if (tdp_enabled) {
+			direct = 1;
+			root_gfn = 0;
+		}
+		spin_lock(&vcpu->kvm->mmu_lock);
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
 				      PT64_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
+		spin_unlock(&vcpu->kvm->mmu_lock);
 		vcpu->arch.mmu.root_hpa = root;
 		return 0;
 	}
 	direct = !is_paging(vcpu);
-	if (tdp_enabled)
-		direct = 1;
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
@@ -2111,11 +2093,18 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 			root_gfn = 0;
 		if (mmu_check_root(vcpu, root_gfn))
 			return 1;
+		if (tdp_enabled) {
+			direct = 1;
+			root_gfn = i << 30;
+		}
+		spin_lock(&vcpu->kvm->mmu_lock);
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
 				      PT32_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
+		spin_unlock(&vcpu->kvm->mmu_lock);
+
 		vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
 	}
 	vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
@@ -2444,7 +2433,8 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 	else
 		r = paging32_init_context(vcpu);
 
-	vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level;
+	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
+	vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
 
 	return r;
 }
@@ -2484,7 +2474,9 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 		goto out;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
+	spin_unlock(&vcpu->kvm->mmu_lock);
 	r = mmu_alloc_roots(vcpu);
+	spin_lock(&vcpu->kvm->mmu_lock);
 	mmu_sync_roots(vcpu);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	if (r)
@@ -2533,7 +2525,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
         }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
-	if (sp->role.glevels == PT32_ROOT_LEVEL)
+	if (!sp->role.cr4_pae)
 		paging32_update_pte(vcpu, sp, spte, new);
 	else
 		paging64_update_pte(vcpu, sp, spte, new);
@@ -2679,10 +2671,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	}
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
+
+restart:
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
 		if (sp->gfn != gfn || sp->role.direct || sp->role.invalid)
 			continue;
-		pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
+		pte_size = sp->role.cr4_pae ? 8 : 4;
 		misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
 		misaligned |= bytes < 4;
 		if (misaligned || flooded) {
@@ -2699,14 +2693,14 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			pgprintk("misaligned: gpa %llx bytes %d role %x\n",
 				 gpa, bytes, sp->role.word);
 			if (kvm_mmu_zap_page(vcpu->kvm, sp))
-				n = bucket->first;
+				goto restart;
 			++vcpu->kvm->stat.mmu_flooded;
 			continue;
 		}
 		page_offset = offset;
 		level = sp->role.level;
 		npte = 1;
-		if (sp->role.glevels == PT32_ROOT_LEVEL) {
+		if (!sp->role.cr4_pae) {
 			page_offset <<= 1;	/* 32->64 */
 			/*
 			 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -2908,22 +2902,23 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	struct kvm_mmu_page *sp, *node;
 
 	spin_lock(&kvm->mmu_lock);
+restart:
 	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link)
 		if (kvm_mmu_zap_page(kvm, sp))
-			node = container_of(kvm->arch.active_mmu_pages.next,
-					    struct kvm_mmu_page, link);
+			goto restart;
+
 	spin_unlock(&kvm->mmu_lock);
 
 	kvm_flush_remote_tlbs(kvm);
 }
 
-static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm)
 {
 	struct kvm_mmu_page *page;
 
 	page = container_of(kvm->arch.active_mmu_pages.prev,
 			    struct kvm_mmu_page, link);
-	kvm_mmu_zap_page(kvm, page);
+	return kvm_mmu_zap_page(kvm, page) + 1;
 }
 
 static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
@@ -2935,7 +2930,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 	spin_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		int npages, idx;
+		int npages, idx, freed_pages;
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
@@ -2943,8 +2938,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 			 kvm->arch.n_free_mmu_pages;
 		cache_count += npages;
 		if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
-			kvm_mmu_remove_one_alloc_mmu_page(kvm);
-			cache_count--;
+			freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm);
+			cache_count -= freed_pages;
 			kvm_freed = kvm;
 		}
 		nr_to_scan--;
@@ -3019,7 +3014,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	unsigned int  nr_pages = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
+
 	for (i = 0; i < slots->nmemslots; i++)
 		nr_pages += slots->memslots[i].npages;
 
@@ -3295,7 +3291,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
 	int i, j, k, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
 		struct kvm_memory_slot *m = &slots->memslots[i];
 		struct kvm_rmap_desc *d;