Merge tag 'kvmarm-fixes-5.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 5.15, take #2

- Properly refcount pages used as a concatenated stage-2 PGD
- Fix missing unlock when detecting the use of MTE+VM_SHARED

Author: bonzini

arch/arm64/kvm/hyp/include/nvhe/gfp.h

@@ -24,6 +24,7 @@ struct hyp_pool {
 
 /* Allocation */
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
 void hyp_get_page(struct hyp_pool *pool, void *addr);
 void hyp_put_page(struct hyp_pool *pool, void *addr);
 

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
 
 static void *host_s2_zalloc_pages_exact(size_t size)
 {
-	return hyp_alloc_pages(&host_s2_pool, get_order(size));
+	void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+	hyp_split_page(hyp_virt_to_page(addr));
+
+	/*
+	 * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+	 * so there should be no need to free any of the tail pages to make the
+	 * allocation exact.
+	 */
+	WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+	return addr;
 }
 
 static void *host_s2_zalloc_page(void *pool)

arch/arm64/kvm/hyp/nvhe/page_alloc.c

@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
 
 static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
 {
+	BUG_ON(!p->refcount);
 	p->refcount--;
 	return (p->refcount == 0);
 }
@@ -193,6 +194,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
 	hyp_spin_unlock(&pool->lock);
 }
 
+void hyp_split_page(struct hyp_page *p)
+{
+	unsigned short order = p->order;
+	unsigned int i;
+
+	p->order = 0;
+	for (i = 1; i < (1 << order); i++) {
+		struct hyp_page *tail = p + i;
+
+		tail->order = 0;
+		hyp_set_page_refcounted(tail);
+	}
+}
+
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
 {
 	unsigned short i = order;

arch/arm64/kvm/mmu.c

@@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		 * when updating the PG_mte_tagged page flag, see
 		 * sanitise_mte_tags for more details.
 		 */
-		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
-			return -EINVAL;
+		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) {
+			ret = -EINVAL;
+			break;
+		}
 
 		if (vma->vm_flags & VM_PFNMAP) {
 			/* IO region dirty page logging not allowed */