KVM: PPC: Book3S: Fix race and leak in kvm_vm_ioctl_create_spapr_tce()

commit 47c5310a8dbe7c2cb9f0083daa43ceed76c257fa upstream, with part
of commit edd03602d97236e8fea13cd76886c576186aa307 folded in.

Nixiaoming pointed out that there is a memory leak in
kvm_vm_ioctl_create_spapr_tce() if the call to anon_inode_getfd()
fails; the memory allocated for the kvmppc_spapr_tce_table struct
is not freed, and nor are the pages allocated for the iommu
tables.

David Hildenbrand pointed out that there is a race in that the
function checks early on that there is not already an entry in the
stt->iommu_tables list with the same LIOBN, but an entry with the
same LIOBN could get added between then and when the new entry is
added to the list.

This fixes both problems.  To simplify things, we now call
anon_inode_getfd() before placing the new entry in the list.  The
check for an existing entry is done while holding the kvm->lock
mutex, immediately before adding the new entry to the list.

[paulus@ozlabs.org - folded in that part of edd03602d972 ("KVM:
 PPC: Book3S HV: Protect updates to spapr_tce_tables list", 2017-08-28)
 which restructured the code that 47c5310a8dbe modified, to avoid
 a build failure caused by the absence of put_unused_fd().
 Also removed the locked memory accounting, since it doesn't exist
 in this version, and adjusted the commit message.]

Fixes: 54738c097163 ("KVM: PPC: Accelerate H_PUT_TCE by implementing it in real mode")
Reported-by: Nixiaoming <nixiaoming@huawei.com>
Reported-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 27 insertions, 19 deletions

diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 54cf9bc94dad..3a095670b0c4 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -101,22 +101,17 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				   struct kvm_create_spapr_tce *args)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
+	struct kvmppc_spapr_tce_table *siter;
 	long npages;
 	int ret = -ENOMEM;
 	int i;
 
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
 	npages = kvmppc_stt_npages(args->window_size);
 
 	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
 		      GFP_KERNEL);
 	if (!stt)
-		goto fail;
+		return ret;
 
 	stt->liobn = args->liobn;
 	stt->window_size = args->window_size;
@@ -128,23 +123,36 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 			goto fail;
 	}
 
-	kvm_get_kvm(kvm);
-
 	mutex_lock(&kvm->lock);
-	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+
+	/* Check this LIOBN hasn't been previously allocated */
+	ret = 0;
+	list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+		if (siter->liobn == args->liobn) {
+			ret = -EBUSY;
+			break;
+		}
+	}
+
+	if (!ret)
+		ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				       stt, O_RDWR | O_CLOEXEC);
+
+	if (ret >= 0) {
+		list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+		kvm_get_kvm(kvm);
+	}
 
 	mutex_unlock(&kvm->lock);
 
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR | O_CLOEXEC);
+	if (ret >= 0)
+		return ret;
 
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
+ fail:
+	for (i = 0; i < npages; i++)
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
 
-		kfree(stt);
-	}
+	kfree(stt);
 	return ret;
 }