NFSv4: Fix buffer overflow checking in __nfs4_get_acl_uncached

Pass the checks made by decode_getacl back to __nfs4_get_acl_uncached
so that it knows if the acl has been truncated.

The current overflow checking is broken, resulting in Oopses on
user-triggered nfs4_getfacl calls, and is opaque to the point
where several attempts at fixing it have failed.
This patch tries to clean up the code in addition to fixing the
Oopses by ensuring that the overflow checks are performed in
a single place (decode_getacl). If the overflow check failed,
we will still be able to report the acl length, but at least
we will no longer attempt to cache the acl or copy the
truncated contents to user space.

Reported-by: Sachin Prabhu <sprabhu@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Tested-by: Sachin Prabhu <sprabhu@redhat.com>

1 files changed, 5 insertions, 9 deletions

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1bfbd67c556d..541e796e6db5 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5072,18 +5072,14 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
 		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
-
-		/* We ignore &savep and don't do consistency checks on
-		 * the attr length.  Let userspace figure it out.... */
 		res->acl_len = attrlen;
-		if (attrlen > (xdr->nwords << 2)) {
-			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
-				/* getxattr interface called with a NULL buf */
-				goto out;
-			}
+
+		/* Check for receive buffer overflow */
+		if (res->acl_len > (xdr->nwords << 2) ||
+		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+			res->acl_flags |= NFS4_ACL_TRUNC;
 			dprintk("NFS: acl reply: attrlen %u > page_len %u\n",
 					attrlen, xdr->nwords << 2);
-			return -EINVAL;
 		}
 	} else
 		status = -EOPNOTSUPP;