RFC 5666 Section 4.2 states:
> When the peer detects an RPC-over-RDMA header version that it does
> not support (currently this document defines only version 1), it
> replies with an error code of ERR_VERS, and provides the low and
> high inclusive version numbers it does, in fact, support.
And:
> When other decoding errors are detected in the header or chunks,
> either an RPC decode error MAY be returned or the RPC/RDMA error
> code ERR_CHUNK MUST be returned.
The Linux NFS server does throw ERR_VERS when a client sends it
a request whose rdma_version is not "one." But it does not return
ERR_CHUNK when a header decoding error occurs. It just drops the
request.
To improve protocol extensibility, it should reject invalid values
in the rdma_proc field instead of treating them all like RDMA_MSG.
Otherwise clients can't detect when the server doesn't support
new rdma_proc values.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
Reviewed-by: Devesh Sharma <devesh.sharma@xxxxxxxxxxxx>
Tested-by: Devesh Sharma <devesh.sharma@xxxxxxxxxxxx>
---
net/sunrpc/xprtrdma/svc_rdma_marshal.c | 55 ++++++++++++++++++++++++-------
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 4 ++
2 files changed, 46 insertions(+), 13 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index b9ce01f..765bca4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -148,22 +148,41 @@ static __be32 *decode_reply_array(__be32 *va, __be32 *vaend)
int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
{
__be32 *va, *vaend;
+ unsigned int len;
u32 hdr_len;
/* Verify that there's enough bytes for header + something */
- if (rqstp->rq_arg.len <= RPCRDMA_HDRLEN_MIN) {
+ if (rqstp->rq_arg.len <= RPCRDMA_HDRLEN_ERR) {
dprintk("svcrdma: header too short = %d\n",
rqstp->rq_arg.len);
return -EINVAL;
}
- if (rmsgp->rm_vers != rpcrdma_version)
+ if (rmsgp->rm_vers != rpcrdma_version) {
+ dprintk("%s: bad version %u\n", __func__,
+ be32_to_cpu(rmsgp->rm_vers));
return -EPROTONOSUPPORT;
+ }
- /* Pull in the extra for the padded case and bump our pointer */
- if (rmsgp->rm_type == rdma_msgp) {
- int hdrlen;
-
+ switch (be32_to_cpu(rmsgp->rm_type)) {
+ case RDMA_MSG:
+ case RDMA_NOMSG:
+ break;
+
+ case RDMA_DONE:
+ /* Just drop it */
+ dprintk("svcrdma: dropping RDMA_DONE message\n");
+ return 0;
+
+ case RDMA_ERROR:
+ /* Possible if this is a backchannel reply.
+ * XXX: We should cancel this XID, though.
+ */
+ dprintk("svcrdma: dropping RDMA_ERROR message\n");
+ return 0;
+
+ case RDMA_MSGP:
+ /* Pull in the extra for the padded case, bump our pointer */
rmsgp->rm_body.rm_padded.rm_align =
be32_to_cpu(rmsgp->rm_body.rm_padded.rm_align);
rmsgp->rm_body.rm_padded.rm_thresh =
@@ -171,11 +190,15 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
va = &rmsgp->rm_body.rm_padded.rm_pempty[4];
rqstp->rq_arg.head[0].iov_base = va;
- hdrlen = (u32)((unsigned long)va - (unsigned long)rmsgp);
- rqstp->rq_arg.head[0].iov_len -= hdrlen;
- if (hdrlen > rqstp->rq_arg.len)
+ len = (u32)((unsigned long)va - (unsigned long)rmsgp);
+ rqstp->rq_arg.head[0].iov_len -= len;
+ if (len > rqstp->rq_arg.len)
return -EINVAL;
- return hdrlen;
+ return len;
+ default:
+ dprintk("svcrdma: bad rdma procedure (%u)\n",
+ be32_to_cpu(rmsgp->rm_type));
+ return -EINVAL;
}
/* The chunk list may contain either a read chunk list or a write
@@ -184,14 +207,20 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg *rmsgp, struct svc_rqst *rqstp)
va = &rmsgp->rm_body.rm_chunks[0];
vaend = (__be32 *)((unsigned long)rmsgp + rqstp->rq_arg.len);
va = decode_read_list(va, vaend);
- if (!va)
+ if (!va) {
+ dprintk("svcrdma: failed to decode read list\n");
return -EINVAL;
+ }
va = decode_write_list(va, vaend);
- if (!va)
+ if (!va) {
+ dprintk("svcrdma: failed to decode write list\n");
return -EINVAL;
+ }
va = decode_reply_array(va, vaend);
- if (!va)
+ if (!va) {
+ dprintk("svcrdma: failed to decode reply chunk\n");
return -EINVAL;
+ }
rqstp->rq_arg.head[0].iov_base = va;
hdr_len = (unsigned long)va - (unsigned long)rmsgp;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 8f68cb6..f8b840b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -657,6 +657,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
ret = svc_rdma_xdr_decode_req(rmsgp, rqstp);
if (ret < 0)
goto out_err;
+ if (ret == 0)
+ goto out_drop;
rqstp->rq_xprt_hlen = ret;
if (svc_rdma_is_backchannel_reply(xprt, rmsgp)) {
@@ -710,6 +712,8 @@ out_err:
defer:
return 0;
+out_drop:
+ svc_rdma_put_context(ctxt, 1);
repost:
return svc_rdma_repost_recv(rdma_xprt, GFP_KERNEL);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
