From: Avinash Repaka <avinash.rep...@oracle.com>
RDS support max message size as 1M but the code doesn't check this
in all cases. Patch fixes it for RDMA & non-RDMA and RDS MR size
and its enforced irrespective of underlying transport.
Signed-off-by: Avinash Repaka <avinash.rep...@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilim...@oracle.com>
---
net/rds/rdma.c | 9 ++++++++-
net/rds/rds.h | 3 +++
net/rds/send.c | 31 +++++++++++++++++++++++++++++++
3 files changed, 42 insertions(+), 1 deletion(-)
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 138aef6..f06fac4 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -40,7 +40,6 @@
/*
* XXX
* - build with sparse
- * - should we limit the size of a mr region? let transport return failure?
* - should we detect duplicate keys on a socket? hmm.
* - an rdma is an mlock, apply rlimit?
*/
@@ -200,6 +199,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct
rds_get_mr_args *args,
goto out;
}
+ /* Restrict the size of mr irrespective of underlying transport
+ * To account for unaligned mr regions, subtract one from nr_pages
+ */
+ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) {
+ ret = -EMSGSIZE;
+ goto out;
+ }
+
rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n",
args->vec.addr, args->vec.bytes, nr_pages);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 8ccd5a9..f713194 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -50,6 +50,9 @@ void rdsdebug(char *fmt, ...)
#define RDS_FRAG_SHIFT 12
#define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT))
+/* Used to limit both RDMA and non-RDMA RDS message to 1MB */
+#define RDS_MAX_MSG_SIZE ((unsigned int)(1 << 20))
+
#define RDS_CONG_MAP_BYTES (65536 / 8)
#define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE)
#define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8)
diff --git a/net/rds/send.c b/net/rds/send.c
index 45e025b..5cc6403 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -994,6 +994,26 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct
rds_connection *conn)
return hash;
}
+static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
+{
+ struct rds_rdma_args *args;
+ struct cmsghdr *cmsg;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+
+ if (cmsg->cmsg_level != SOL_RDS)
+ continue;
+
+ if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+ args = CMSG_DATA(cmsg);
+ *rdma_bytes += args->remote_vec.bytes;
+ }
+ }
+ return 0;
+}
+
int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
{
struct sock *sk = sock->sk;
@@ -1008,6 +1028,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg,
size_t payload_len)
int nonblock = msg->msg_flags & MSG_DONTWAIT;
long timeo = sock_sndtimeo(sk, nonblock);
struct rds_conn_path *cpath;
+ size_t total_payload_len = payload_len, rdma_payload_len = 0;
/* Mirror Linux UDP mirror of BSD error message compatibility */
/* XXX: Perhaps MSG_MORE someday */
@@ -1040,6 +1061,16 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg,
size_t payload_len)
}
release_sock(sk);
+ ret = rds_rdma_bytes(msg, &rdma_payload_len);
+ if (ret)
+ goto out;
+
+ total_payload_len += rdma_payload_len;
+ if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) {
+ ret = -EMSGSIZE;
+ goto out;
+ }
+
if (payload_len > rds_sk_sndbuf(rs)) {
ret = -EMSGSIZE;
goto out;
--
1.9.1
