[PATCH 04/20] KVM: arm64: Use block-level annotations when setting up the host stage-2

During pKVM initialisation, fix_host_ownership() configures the host
stage-2 mappings to match the hypervisor stage-1. Previously this was
done page-by-page. Now that the host stage-2 supports block-level
annotations, refactor the walker to apply the ownership state to an
entire range at once.

This reduces host stage-2 page-table fragmentation and memory usage by
avoiding allocation of intermediate page-table pages.

Signed-off-by: Vincent Donnefort <[email protected]>

diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index b50712d47f6d..86a51cf1d590 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -122,6 +122,11 @@ static inline void set_hyp_state(struct hyp_page *p, enum pkvm_page_state state)
 	p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_VMEMMAP_MASK;
 }
 
+#define for_each_hyp_page(__p, __st, __sz)				\
+	for (struct hyp_page *__p = hyp_phys_to_page(__st),		\
+			     *__e = __p + ((__sz) >> PAGE_SHIFT);	\
+	     __p < __e; __p++)
+
 /*
  * Refcounting for 'struct hyp_page'.
  * hyp_pool::lock must be held if atomic access to the refcount is required.
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 4e329e39a695..3c3e0c3d66d1 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -76,11 +76,6 @@ static void hyp_unlock_component(void)
 	hyp_spin_unlock(&pkvm_pgd_lock);
 }
 
-#define for_each_hyp_page(__p, __st, __sz)				\
-	for (struct hyp_page *__p = hyp_phys_to_page(__st),		\
-			     *__e = __p + ((__sz) >> PAGE_SHIFT);	\
-	     __p < __e; __p++)
-
 static void *host_s2_zalloc_pages_exact(size_t size)
 {
 	void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 75b00c323310..d7beb2ccf1e1 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -186,50 +186,46 @@ static void hpool_put_page(void *addr)
 	hyp_put_page(&hpool, addr);
 }
 
-static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
-				     enum kvm_pgtable_walk_flags visit)
+struct fix_host_ownership_data {
+	phys_addr_t		phys;
+	size_t			size;
+	enum kvm_pgtable_prot	prot;
+};
+
+static int __fix_host_ownership(const struct fix_host_ownership_data *data)
 {
-	enum pkvm_page_state state;
-	struct hyp_page *page;
-	phys_addr_t phys;
-	enum kvm_pgtable_prot prot;
+	enum pkvm_page_state state = pkvm_getstate(data->prot);
 
-	if (!kvm_pte_valid(ctx->old))
+	if (!data->prot)
 		return 0;
 
-	if (ctx->level != KVM_PGTABLE_LAST_LEVEL)
-		return -EINVAL;
-
-	phys = kvm_pte_to_phys(ctx->old);
-	if (!addr_is_memory(phys))
-		return -EINVAL;
-
-	page = hyp_phys_to_page(phys);
-
 	/*
 	 * Adjust the host stage-2 mappings to match the ownership attributes
 	 * configured in the hypervisor stage-1, and make sure to propagate them
 	 * to the hyp_vmemmap state.
 	 */
-	prot = kvm_pgtable_hyp_pte_prot(ctx->old);
-	state = pkvm_getstate(prot);
 	switch (state) {
 	case PKVM_PAGE_OWNED:
-		set_hyp_state(page, PKVM_PAGE_OWNED);
-		/* hyp text is RO in the host stage-2 to be inspected on panic. */
-		if (prot == PAGE_HYP_EXEC) {
+		for_each_hyp_page(page, data->phys, data->size) {
+			set_hyp_state(page, PKVM_PAGE_OWNED);
 			set_host_state(page, PKVM_NOPAGE);
-			return host_stage2_idmap_locked(phys, PAGE_SIZE, KVM_PGTABLE_PROT_R);
-		} else {
-			return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP);
 		}
+		/* hyp text is RO in the host stage-2 to be inspected on panic. */
+		if (data->prot == PAGE_HYP_EXEC)
+			return host_stage2_idmap_locked(data->phys, data->size, KVM_PGTABLE_PROT_R);
+		else
+			return host_stage2_set_owner_locked(data->phys, data->size, PKVM_ID_HYP);
 	case PKVM_PAGE_SHARED_OWNED:
-		set_hyp_state(page, PKVM_PAGE_SHARED_OWNED);
-		set_host_state(page, PKVM_PAGE_SHARED_BORROWED);
+		for_each_hyp_page(page, data->phys, data->size) {
+			set_hyp_state(page, PKVM_PAGE_SHARED_OWNED);
+			set_host_state(page, PKVM_PAGE_SHARED_BORROWED);
+		}
 		break;
 	case PKVM_PAGE_SHARED_BORROWED:
-		set_hyp_state(page, PKVM_PAGE_SHARED_BORROWED);
-		set_host_state(page, PKVM_PAGE_SHARED_OWNED);
+		for_each_hyp_page(page, data->phys, data->size) {
+			set_hyp_state(page, PKVM_PAGE_SHARED_BORROWED);
+			set_host_state(page, PKVM_PAGE_SHARED_OWNED);
+		}
 		break;
 	default:
 		return -EINVAL;
@@ -238,6 +234,78 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	return 0;
 }
 
+static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
+				     enum kvm_pgtable_walk_flags visit)
+{
+	struct fix_host_ownership_data *data = ctx->arg;
+	enum kvm_pgtable_prot prot = 0;
+	phys_addr_t phys = 0;
+	int ret;
+
+	if (kvm_pte_valid(ctx->old))
+		prot = kvm_pgtable_hyp_pte_prot(ctx->old);
+
+	if (!prot) {
+		/* Unchanged region */
+		if (!data->prot)
+			return 0;
+
+		goto apply_ownership;
+	}
+
+	phys = kvm_pte_to_phys(ctx->old);
+	if (!addr_is_memory(phys))
+		return -EINVAL;
+
+	/* We already know phys is contiguous as we walk the linear map */
+
+	if (prot != data->prot)
+		goto apply_ownership;
+
+	/* Accumulate in the current region */
+	data->size += kvm_granule_size(ctx->level);
+
+	return 0;
+
+apply_ownership:
+	ret = __fix_host_ownership(data);
+	if (ret)
+		return ret;
+
+	data->phys = phys;
+	data->size = kvm_granule_size(ctx->level);
+	data->prot = prot;
+
+	return 0;
+}
+
+static int fix_host_ownership(void)
+{
+	struct fix_host_ownership_data data;
+	struct kvm_pgtable_walker walker = {
+		.cb	= fix_host_ownership_walker,
+		.flags	= KVM_PGTABLE_WALK_LEAF,
+		.arg	= &data,
+	};
+	int i, ret;
+
+	for (i = 0; i < hyp_memblock_nr; i++) {
+		struct memblock_region *reg = &hyp_memory[i];
+		u64 start = (u64)hyp_phys_to_virt(reg->base);
+
+		data = (struct fix_host_ownership_data){ 0 };
+		ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker);
+		if (ret)
+			return ret;
+
+		ret = __fix_host_ownership(&data);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx,
 					 enum kvm_pgtable_walk_flags visit)
 {
@@ -252,26 +320,6 @@ static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx
 	return 0;
 }
 
-static int fix_host_ownership(void)
-{
-	struct kvm_pgtable_walker walker = {
-		.cb	= fix_host_ownership_walker,
-		.flags	= KVM_PGTABLE_WALK_LEAF,
-	};
-	int i, ret;
-
-	for (i = 0; i < hyp_memblock_nr; i++) {
-		struct memblock_region *reg = &hyp_memory[i];
-		u64 start = (u64)hyp_phys_to_virt(reg->base);
-
-		ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 static int fix_hyp_pgtable_refcnt(void)
 {
 	struct kvm_pgtable_walker walker = {
-- 
2.55.0.508.g3f0d502094-goog