summaryrefslogtreecommitdiff
path: root/net/rds/send.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds/send.c')
-rw-r--r--net/rds/send.c54
1 files changed, 42 insertions, 12 deletions
diff --git a/net/rds/send.c b/net/rds/send.c
index b1b0022b8370..acad04243b41 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -649,7 +649,6 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status)
rm->rdma.op_notifier = NULL;
}
was_on_sock = 1;
- rm->m_rs = NULL;
}
spin_unlock(&rs->rs_lock);
@@ -756,9 +755,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
*/
if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) {
spin_unlock_irqrestore(&cp->cp_lock, flags);
- spin_lock_irqsave(&rm->m_rs_lock, flags);
- rm->m_rs = NULL;
- spin_unlock_irqrestore(&rm->m_rs_lock, flags);
continue;
}
list_del_init(&rm->m_conn_item);
@@ -774,7 +770,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
__rds_send_complete(rs, rm, RDS_RDMA_CANCELED);
spin_unlock(&rs->rs_lock);
- rm->m_rs = NULL;
spin_unlock_irqrestore(&rm->m_rs_lock, flags);
rds_message_put(rm);
@@ -798,7 +793,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
__rds_send_complete(rs, rm, RDS_RDMA_CANCELED);
spin_unlock(&rs->rs_lock);
- rm->m_rs = NULL;
spin_unlock_irqrestore(&rm->m_rs_lock, flags);
rds_message_put(rm);
@@ -849,6 +843,7 @@ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn,
list_add_tail(&rm->m_sock_item, &rs->rs_send_queue);
set_bit(RDS_MSG_ON_SOCK, &rm->m_flags);
rds_message_addref(rm);
+ sock_hold(rds_rs_to_sk(rs));
rm->m_rs = rs;
/* The code ordering is a little weird, but we're
@@ -880,12 +875,13 @@ out:
* rds_message is getting to be quite complicated, and we'd like to allocate
* it all in one go. This figures out how big it needs to be up front.
*/
-static int rds_rm_size(struct msghdr *msg, int data_len)
+static int rds_rm_size(struct msghdr *msg, int num_sgs)
{
struct cmsghdr *cmsg;
int size = 0;
int cmsg_groups = 0;
int retval;
+ bool zcopy_cookie = false;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
@@ -904,6 +900,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len)
break;
+ case RDS_CMSG_ZCOPY_COOKIE:
+ zcopy_cookie = true;
+ /* fall through */
+
case RDS_CMSG_RDMA_DEST:
case RDS_CMSG_RDMA_MAP:
cmsg_groups |= 2;
@@ -924,7 +924,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len)
}
- size += ceil(data_len, PAGE_SIZE) * sizeof(struct scatterlist);
+ if ((msg->msg_flags & MSG_ZEROCOPY) && !zcopy_cookie)
+ return -EINVAL;
+
+ size += num_sgs * sizeof(struct scatterlist);
/* Ensure (DEST, MAP) are never used with (ARGS, ATOMIC) */
if (cmsg_groups == 3)
@@ -933,6 +936,19 @@ static int rds_rm_size(struct msghdr *msg, int data_len)
return size;
}
+static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm,
+ struct cmsghdr *cmsg)
+{
+ u32 *cookie;
+
+ if (cmsg->cmsg_len < CMSG_LEN(sizeof(*cookie)) ||
+ !rm->data.op_mmp_znotifier)
+ return -EINVAL;
+ cookie = CMSG_DATA(cmsg);
+ rm->data.op_mmp_znotifier->z_cookie = *cookie;
+ return 0;
+}
+
static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
struct msghdr *msg, int *allocated_mr)
{
@@ -975,6 +991,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
ret = rds_cmsg_atomic(rs, rm, cmsg);
break;
+ case RDS_CMSG_ZCOPY_COOKIE:
+ ret = rds_cmsg_zcopy(rs, rm, cmsg);
+ break;
+
default:
return -EINVAL;
}
@@ -1045,10 +1065,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
long timeo = sock_sndtimeo(sk, nonblock);
struct rds_conn_path *cpath;
size_t total_payload_len = payload_len, rdma_payload_len = 0;
+ bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) &&
+ sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY));
+ int num_sgs = ceil(payload_len, PAGE_SIZE);
/* Mirror Linux UDP mirror of BSD error message compatibility */
/* XXX: Perhaps MSG_MORE someday */
- if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT)) {
+ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT | MSG_ZEROCOPY)) {
ret = -EOPNOTSUPP;
goto out;
}
@@ -1092,8 +1115,15 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
goto out;
}
+ if (zcopy) {
+ if (rs->rs_transport->t_type != RDS_TRANS_TCP) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX);
+ }
/* size of rm including all sgs */
- ret = rds_rm_size(msg, payload_len);
+ ret = rds_rm_size(msg, num_sgs);
if (ret < 0)
goto out;
@@ -1105,12 +1135,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
/* Attach data to the rm */
if (payload_len) {
- rm->data.op_sg = rds_message_alloc_sgs(rm, ceil(payload_len, PAGE_SIZE));
+ rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
if (!rm->data.op_sg) {
ret = -ENOMEM;
goto out;
}
- ret = rds_message_copy_from_user(rm, &msg->msg_iter);
+ ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy);
if (ret)
goto out;
}