aboutsummaryrefslogtreecommitdiff
path: root/net/rds/af_rds.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds/af_rds.c')
-rw-r--r--net/rds/af_rds.c74
1 files changed, 48 insertions, 26 deletions
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 98e05382fd3..424ff622ab5 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -33,12 +33,21 @@
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
+#include <linux/gfp.h>
#include <linux/in.h>
#include <linux/poll.h>
#include <net/sock.h>
#include "rds.h"
-#include "rdma.h"
+
+char *rds_str_array(char **array, size_t elements, size_t index)
+{
+ if ((index < elements) && array[index])
+ return array[index];
+ else
+ return "unknown";
+}
+EXPORT_SYMBOL(rds_str_array);
/* this is just used for stats gathering :/ */
static DEFINE_SPINLOCK(rds_sock_lock);
@@ -59,9 +68,8 @@ static int rds_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct rds_sock *rs;
- unsigned long flags;
- if (sk == NULL)
+ if (!sk)
goto out;
rs = rds_sk_to_rs(sk);
@@ -72,15 +80,25 @@ static int rds_release(struct socket *sock)
* with the socket. */
rds_clear_recv_queue(rs);
rds_cong_remove_socket(rs);
+
+ /*
+ * the binding lookup hash uses rcu, we need to
+ * make sure we sychronize_rcu before we free our
+ * entry
+ */
rds_remove_bound(rs);
+ synchronize_rcu();
+
rds_send_drop_to(rs, NULL);
rds_rdma_drop_keys(rs);
rds_notify_queue_get(rs, NULL);
- spin_lock_irqsave(&rds_sock_lock, flags);
+ spin_lock_bh(&rds_sock_lock);
list_del_init(&rs->rs_item);
rds_sock_count--;
- spin_unlock_irqrestore(&rds_sock_lock, flags);
+ spin_unlock_bh(&rds_sock_lock);
+
+ rds_trans_put(rs->rs_transport);
sock->sk = NULL;
sock_put(sk);
@@ -157,9 +175,10 @@ static unsigned int rds_poll(struct file *file, struct socket *sock,
unsigned int mask = 0;
unsigned long flags;
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
- poll_wait(file, &rds_poll_waitq, wait);
+ if (rs->rs_seen_congestion)
+ poll_wait(file, &rds_poll_waitq, wait);
read_lock_irqsave(&rs->rs_recv_lock, flags);
if (!rs->rs_cong_monitor) {
@@ -174,13 +193,17 @@ static unsigned int rds_poll(struct file *file, struct socket *sock,
mask |= (POLLIN | POLLRDNORM);
spin_unlock(&rs->rs_lock);
}
- if (!list_empty(&rs->rs_recv_queue)
- || !list_empty(&rs->rs_notify_queue))
+ if (!list_empty(&rs->rs_recv_queue) ||
+ !list_empty(&rs->rs_notify_queue))
mask |= (POLLIN | POLLRDNORM);
if (rs->rs_snd_bytes < rds_sk_sndbuf(rs))
mask |= (POLLOUT | POLLWRNORM);
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
+ /* clear state any time we wake a seen-congested socket */
+ if (mask)
+ rs->rs_seen_congestion = 0;
+
return mask;
}
@@ -265,6 +288,9 @@ static int rds_setsockopt(struct socket *sock, int level, int optname,
case RDS_GET_MR:
ret = rds_get_mr(rs, optval, optlen);
break;
+ case RDS_GET_MR_FOR_DEST:
+ ret = rds_get_mr_for_dest(rs, optval, optlen);
+ break;
case RDS_FREE_MR:
ret = rds_free_mr(rs, optval, optlen);
break;
@@ -305,8 +331,8 @@ static int rds_getsockopt(struct socket *sock, int level, int optname,
if (len < sizeof(int))
ret = -EINVAL;
else
- if (put_user(rs->rs_recverr, (int __user *) optval)
- || put_user(sizeof(int), optlen))
+ if (put_user(rs->rs_recverr, (int __user *) optval) ||
+ put_user(sizeof(int), optlen))
ret = -EFAULT;
else
ret = 0;
@@ -382,7 +408,6 @@ static const struct proto_ops rds_proto_ops = {
static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
{
- unsigned long flags;
struct rds_sock *rs;
sock_init_data(sock, sk);
@@ -399,15 +424,16 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
spin_lock_init(&rs->rs_rdma_lock);
rs->rs_rdma_keys = RB_ROOT;
- spin_lock_irqsave(&rds_sock_lock, flags);
+ spin_lock_bh(&rds_sock_lock);
list_add_tail(&rs->rs_item, &rds_sock_list);
rds_sock_count++;
- spin_unlock_irqrestore(&rds_sock_lock, flags);
+ spin_unlock_bh(&rds_sock_lock);
return 0;
}
-static int rds_create(struct net *net, struct socket *sock, int protocol)
+static int rds_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
{
struct sock *sk;
@@ -431,7 +457,7 @@ void rds_sock_put(struct rds_sock *rs)
sock_put(rds_rs_to_sk(rs));
}
-static struct net_proto_family rds_family_ops = {
+static const struct net_proto_family rds_family_ops = {
.family = AF_RDS,
.create = rds_create,
.owner = THIS_MODULE,
@@ -442,17 +468,14 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
struct rds_info_lengths *lens)
{
struct rds_sock *rs;
- struct sock *sk;
struct rds_incoming *inc;
- unsigned long flags;
unsigned int total = 0;
len /= sizeof(struct rds_info_message);
- spin_lock_irqsave(&rds_sock_lock, flags);
+ spin_lock_bh(&rds_sock_lock);
list_for_each_entry(rs, &rds_sock_list, rs_item) {
- sk = rds_rs_to_sk(rs);
read_lock(&rs->rs_recv_lock);
/* XXX too lazy to maintain counts.. */
@@ -466,7 +489,7 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
read_unlock(&rs->rs_recv_lock);
}
- spin_unlock_irqrestore(&rds_sock_lock, flags);
+ spin_unlock_bh(&rds_sock_lock);
lens->nr = total;
lens->each = sizeof(struct rds_info_message);
@@ -478,11 +501,10 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
{
struct rds_info_socket sinfo;
struct rds_sock *rs;
- unsigned long flags;
len /= sizeof(struct rds_info_socket);
- spin_lock_irqsave(&rds_sock_lock, flags);
+ spin_lock_bh(&rds_sock_lock);
if (len < rds_sock_count)
goto out;
@@ -503,10 +525,10 @@ out:
lens->nr = rds_sock_count;
lens->each = sizeof(struct rds_info_socket);
- spin_unlock_irqrestore(&rds_sock_lock, flags);
+ spin_unlock_bh(&rds_sock_lock);
}
-static void __exit rds_exit(void)
+static void rds_exit(void)
{
sock_unregister(rds_family_ops.family);
proto_unregister(&rds_proto);
@@ -521,7 +543,7 @@ static void __exit rds_exit(void)
}
module_exit(rds_exit);
-static int __init rds_init(void)
+static int rds_init(void)
{
int ret;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-07 11:38:23 +0000