mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-08 06:06:40 +07:00
e0456717e4
Pull networking updates from David Miller: 1) Add TX fast path in mac80211, from Johannes Berg. 2) Add TSO/GRO support to ibmveth, from Thomas Falcon 3) Move away from cached routes in ipv6, just like ipv4, from Martin KaFai Lau. 4) Lots of new rhashtable tests, from Thomas Graf. 5) Run ingress qdisc lockless, from Alexei Starovoitov. 6) Allow servers to fetch TCP packet headers for SYN packets of new connections, for fingerprinting. From Eric Dumazet. 7) Add mode parameter to pktgen, for testing receive. From Alexei Starovoitov. 8) Cache access optimizations via simplifications of build_skb(), from Alexander Duyck. 9) Move page frag allocator under mm/, also from Alexander. 10) Add xmit_more support to hv_netvsc, from KY Srinivasan. 11) Add a counter guard in case we try to perform endless reclassify loops in the packet scheduler. 12) Extern flow dissector to be programmable and use it in new "Flower" classifier. From Jiri Pirko. 13) AF_PACKET fanout rollover fixes, performance improvements, and new statistics. From Willem de Bruijn. 14) Add netdev driver for GENEVE tunnels, from John W Linville. 15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso. 16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet. 17) Add an ECN retry fallback for the initial TCP handshake, from Daniel Borkmann. 18) Add tail call support to BPF, from Alexei Starovoitov. 19) Add several pktgen helper scripts, from Jesper Dangaard Brouer. 20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa. 21) Favor even port numbers for allocation to connect() requests, and odd port numbers for bind(0), in an effort to help avoid ip_local_port_range exhaustion. From Eric Dumazet. 22) Add Cavium ThunderX driver, from Sunil Goutham. 23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata, from Alexei Starovoitov. 24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai. 25) Double TCP Small Queues default to 256K to accomodate situations like the XEN driver and wireless aggregation. From Wei Liu. 26) Add more entropy inputs to flow dissector, from Tom Herbert. 27) Add CDG congestion control algorithm to TCP, from Kenneth Klette Jonassen. 28) Convert ipset over to RCU locking, from Jozsef Kadlecsik. 29) Track and act upon link status of ipv4 route nexthops, from Andy Gospodarek. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits) bridge: vlan: flush the dynamically learned entries on port vlan delete bridge: multicast: add a comment to br_port_state_selection about blocking state net: inet_diag: export IPV6_V6ONLY sockopt stmmac: troubleshoot unexpected bits in des0 & des1 net: ipv4 sysctl option to ignore routes when nexthop link is down net: track link-status of ipv4 nexthops net: switchdev: ignore unsupported bridge flags net: Cavium: Fix MAC address setting in shutdown state drivers: net: xgene: fix for ACPI support without ACPI ip: report the original address of ICMP messages net/mlx5e: Prefetch skb data on RX net/mlx5e: Pop cq outside mlx5e_get_cqe net/mlx5e: Remove mlx5e_cq.sqrq back-pointer net/mlx5e: Remove extra spaces net/mlx5e: Avoid TX CQE generation if more xmit packets expected net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq() net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device ...
632 lines
15 KiB
C
632 lines
15 KiB
C
/*
|
|
* Copyright (c) 2006 Oracle. All rights reserved.
|
|
*
|
|
* This software is available to you under a choice of one of two
|
|
* licenses. You may choose to be licensed under the terms of the GNU
|
|
* General Public License (GPL) Version 2, available from the file
|
|
* COPYING in the main directory of this source tree, or the
|
|
* OpenIB.org BSD license below:
|
|
*
|
|
* Redistribution and use in source and binary forms, with or
|
|
* without modification, are permitted provided that the following
|
|
* conditions are met:
|
|
*
|
|
* - Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer.
|
|
*
|
|
* - Redistributions in binary form must reproduce the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
|
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
|
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*
|
|
*/
|
|
#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"
|
|
|
|
/* this is just used for stats gathering :/ */
|
|
static DEFINE_SPINLOCK(rds_sock_lock);
|
|
static unsigned long rds_sock_count;
|
|
static LIST_HEAD(rds_sock_list);
|
|
DECLARE_WAIT_QUEUE_HEAD(rds_poll_waitq);
|
|
|
|
/*
|
|
* This is called as the final descriptor referencing this socket is closed.
|
|
* We have to unbind the socket so that another socket can be bound to the
|
|
* address it was using.
|
|
*
|
|
* We have to be careful about racing with the incoming path. sock_orphan()
|
|
* sets SOCK_DEAD and we use that as an indicator to the rx path that new
|
|
* messages shouldn't be queued.
|
|
*/
|
|
static int rds_release(struct socket *sock)
|
|
{
|
|
struct sock *sk = sock->sk;
|
|
struct rds_sock *rs;
|
|
|
|
if (!sk)
|
|
goto out;
|
|
|
|
rs = rds_sk_to_rs(sk);
|
|
|
|
sock_orphan(sk);
|
|
/* Note - rds_clear_recv_queue grabs rs_recv_lock, so
|
|
* that ensures the recv path has completed messing
|
|
* 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 synchronize_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_bh(&rds_sock_lock);
|
|
list_del_init(&rs->rs_item);
|
|
rds_sock_count--;
|
|
spin_unlock_bh(&rds_sock_lock);
|
|
|
|
rds_trans_put(rs->rs_transport);
|
|
|
|
sock->sk = NULL;
|
|
sock_put(sk);
|
|
out:
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Careful not to race with rds_release -> sock_orphan which clears sk_sleep.
|
|
* _bh() isn't OK here, we're called from interrupt handlers. It's probably OK
|
|
* to wake the waitqueue after sk_sleep is clear as we hold a sock ref, but
|
|
* this seems more conservative.
|
|
* NB - normally, one would use sk_callback_lock for this, but we can
|
|
* get here from interrupts, whereas the network code grabs sk_callback_lock
|
|
* with _lock_bh only - so relying on sk_callback_lock introduces livelocks.
|
|
*/
|
|
void rds_wake_sk_sleep(struct rds_sock *rs)
|
|
{
|
|
unsigned long flags;
|
|
|
|
read_lock_irqsave(&rs->rs_recv_lock, flags);
|
|
__rds_wake_sk_sleep(rds_rs_to_sk(rs));
|
|
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
|
|
}
|
|
|
|
static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
|
|
int *uaddr_len, int peer)
|
|
{
|
|
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
|
|
struct rds_sock *rs = rds_sk_to_rs(sock->sk);
|
|
|
|
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
|
|
|
|
/* racey, don't care */
|
|
if (peer) {
|
|
if (!rs->rs_conn_addr)
|
|
return -ENOTCONN;
|
|
|
|
sin->sin_port = rs->rs_conn_port;
|
|
sin->sin_addr.s_addr = rs->rs_conn_addr;
|
|
} else {
|
|
sin->sin_port = rs->rs_bound_port;
|
|
sin->sin_addr.s_addr = rs->rs_bound_addr;
|
|
}
|
|
|
|
sin->sin_family = AF_INET;
|
|
|
|
*uaddr_len = sizeof(*sin);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* RDS' poll is without a doubt the least intuitive part of the interface,
|
|
* as POLLIN and POLLOUT do not behave entirely as you would expect from
|
|
* a network protocol.
|
|
*
|
|
* POLLIN is asserted if
|
|
* - there is data on the receive queue.
|
|
* - to signal that a previously congested destination may have become
|
|
* uncongested
|
|
* - A notification has been queued to the socket (this can be a congestion
|
|
* update, or a RDMA completion).
|
|
*
|
|
* POLLOUT is asserted if there is room on the send queue. This does not mean
|
|
* however, that the next sendmsg() call will succeed. If the application tries
|
|
* to send to a congested destination, the system call may still fail (and
|
|
* return ENOBUFS).
|
|
*/
|
|
static unsigned int rds_poll(struct file *file, struct socket *sock,
|
|
poll_table *wait)
|
|
{
|
|
struct sock *sk = sock->sk;
|
|
struct rds_sock *rs = rds_sk_to_rs(sk);
|
|
unsigned int mask = 0;
|
|
unsigned long flags;
|
|
|
|
poll_wait(file, sk_sleep(sk), 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) {
|
|
/* When a congestion map was updated, we signal POLLIN for
|
|
* "historical" reasons. Applications can also poll for
|
|
* WRBAND instead. */
|
|
if (rds_cong_updated_since(&rs->rs_cong_track))
|
|
mask |= (POLLIN | POLLRDNORM | POLLWRBAND);
|
|
} else {
|
|
spin_lock(&rs->rs_lock);
|
|
if (rs->rs_cong_notify)
|
|
mask |= (POLLIN | POLLRDNORM);
|
|
spin_unlock(&rs->rs_lock);
|
|
}
|
|
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;
|
|
}
|
|
|
|
static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
|
|
{
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
|
|
static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
|
|
int len)
|
|
{
|
|
struct sockaddr_in sin;
|
|
int ret = 0;
|
|
|
|
/* racing with another thread binding seems ok here */
|
|
if (rs->rs_bound_addr == 0) {
|
|
ret = -ENOTCONN; /* XXX not a great errno */
|
|
goto out;
|
|
}
|
|
|
|
if (len < sizeof(struct sockaddr_in)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (copy_from_user(&sin, optval, sizeof(sin))) {
|
|
ret = -EFAULT;
|
|
goto out;
|
|
}
|
|
|
|
rds_send_drop_to(rs, &sin);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
static int rds_set_bool_option(unsigned char *optvar, char __user *optval,
|
|
int optlen)
|
|
{
|
|
int value;
|
|
|
|
if (optlen < sizeof(int))
|
|
return -EINVAL;
|
|
if (get_user(value, (int __user *) optval))
|
|
return -EFAULT;
|
|
*optvar = !!value;
|
|
return 0;
|
|
}
|
|
|
|
static int rds_cong_monitor(struct rds_sock *rs, char __user *optval,
|
|
int optlen)
|
|
{
|
|
int ret;
|
|
|
|
ret = rds_set_bool_option(&rs->rs_cong_monitor, optval, optlen);
|
|
if (ret == 0) {
|
|
if (rs->rs_cong_monitor) {
|
|
rds_cong_add_socket(rs);
|
|
} else {
|
|
rds_cong_remove_socket(rs);
|
|
rs->rs_cong_mask = 0;
|
|
rs->rs_cong_notify = 0;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static int rds_set_transport(struct rds_sock *rs, char __user *optval,
|
|
int optlen)
|
|
{
|
|
int t_type;
|
|
|
|
if (rs->rs_transport)
|
|
return -EOPNOTSUPP; /* previously attached to transport */
|
|
|
|
if (optlen != sizeof(int))
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(&t_type, (int __user *)optval, sizeof(t_type)))
|
|
return -EFAULT;
|
|
|
|
if (t_type < 0 || t_type >= RDS_TRANS_COUNT)
|
|
return -EINVAL;
|
|
|
|
rs->rs_transport = rds_trans_get(t_type);
|
|
|
|
return rs->rs_transport ? 0 : -ENOPROTOOPT;
|
|
}
|
|
|
|
static int rds_setsockopt(struct socket *sock, int level, int optname,
|
|
char __user *optval, unsigned int optlen)
|
|
{
|
|
struct rds_sock *rs = rds_sk_to_rs(sock->sk);
|
|
int ret;
|
|
|
|
if (level != SOL_RDS) {
|
|
ret = -ENOPROTOOPT;
|
|
goto out;
|
|
}
|
|
|
|
switch (optname) {
|
|
case RDS_CANCEL_SENT_TO:
|
|
ret = rds_cancel_sent_to(rs, optval, optlen);
|
|
break;
|
|
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;
|
|
case RDS_RECVERR:
|
|
ret = rds_set_bool_option(&rs->rs_recverr, optval, optlen);
|
|
break;
|
|
case RDS_CONG_MONITOR:
|
|
ret = rds_cong_monitor(rs, optval, optlen);
|
|
break;
|
|
case SO_RDS_TRANSPORT:
|
|
lock_sock(sock->sk);
|
|
ret = rds_set_transport(rs, optval, optlen);
|
|
release_sock(sock->sk);
|
|
break;
|
|
default:
|
|
ret = -ENOPROTOOPT;
|
|
}
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
static int rds_getsockopt(struct socket *sock, int level, int optname,
|
|
char __user *optval, int __user *optlen)
|
|
{
|
|
struct rds_sock *rs = rds_sk_to_rs(sock->sk);
|
|
int ret = -ENOPROTOOPT, len;
|
|
int trans;
|
|
|
|
if (level != SOL_RDS)
|
|
goto out;
|
|
|
|
if (get_user(len, optlen)) {
|
|
ret = -EFAULT;
|
|
goto out;
|
|
}
|
|
|
|
switch (optname) {
|
|
case RDS_INFO_FIRST ... RDS_INFO_LAST:
|
|
ret = rds_info_getsockopt(sock, optname, optval,
|
|
optlen);
|
|
break;
|
|
|
|
case RDS_RECVERR:
|
|
if (len < sizeof(int))
|
|
ret = -EINVAL;
|
|
else
|
|
if (put_user(rs->rs_recverr, (int __user *) optval) ||
|
|
put_user(sizeof(int), optlen))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = 0;
|
|
break;
|
|
case SO_RDS_TRANSPORT:
|
|
if (len < sizeof(int)) {
|
|
ret = -EINVAL;
|
|
break;
|
|
}
|
|
trans = (rs->rs_transport ? rs->rs_transport->t_type :
|
|
RDS_TRANS_NONE); /* unbound */
|
|
if (put_user(trans, (int __user *)optval) ||
|
|
put_user(sizeof(int), optlen))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = 0;
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
out:
|
|
return ret;
|
|
|
|
}
|
|
|
|
static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
|
|
int addr_len, int flags)
|
|
{
|
|
struct sock *sk = sock->sk;
|
|
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
|
|
struct rds_sock *rs = rds_sk_to_rs(sk);
|
|
int ret = 0;
|
|
|
|
lock_sock(sk);
|
|
|
|
if (addr_len != sizeof(struct sockaddr_in)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (sin->sin_family != AF_INET) {
|
|
ret = -EAFNOSUPPORT;
|
|
goto out;
|
|
}
|
|
|
|
if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
|
|
ret = -EDESTADDRREQ;
|
|
goto out;
|
|
}
|
|
|
|
rs->rs_conn_addr = sin->sin_addr.s_addr;
|
|
rs->rs_conn_port = sin->sin_port;
|
|
|
|
out:
|
|
release_sock(sk);
|
|
return ret;
|
|
}
|
|
|
|
static struct proto rds_proto = {
|
|
.name = "RDS",
|
|
.owner = THIS_MODULE,
|
|
.obj_size = sizeof(struct rds_sock),
|
|
};
|
|
|
|
static const struct proto_ops rds_proto_ops = {
|
|
.family = AF_RDS,
|
|
.owner = THIS_MODULE,
|
|
.release = rds_release,
|
|
.bind = rds_bind,
|
|
.connect = rds_connect,
|
|
.socketpair = sock_no_socketpair,
|
|
.accept = sock_no_accept,
|
|
.getname = rds_getname,
|
|
.poll = rds_poll,
|
|
.ioctl = rds_ioctl,
|
|
.listen = sock_no_listen,
|
|
.shutdown = sock_no_shutdown,
|
|
.setsockopt = rds_setsockopt,
|
|
.getsockopt = rds_getsockopt,
|
|
.sendmsg = rds_sendmsg,
|
|
.recvmsg = rds_recvmsg,
|
|
.mmap = sock_no_mmap,
|
|
.sendpage = sock_no_sendpage,
|
|
};
|
|
|
|
static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
|
|
{
|
|
struct rds_sock *rs;
|
|
|
|
sock_init_data(sock, sk);
|
|
sock->ops = &rds_proto_ops;
|
|
sk->sk_protocol = protocol;
|
|
|
|
rs = rds_sk_to_rs(sk);
|
|
spin_lock_init(&rs->rs_lock);
|
|
rwlock_init(&rs->rs_recv_lock);
|
|
INIT_LIST_HEAD(&rs->rs_send_queue);
|
|
INIT_LIST_HEAD(&rs->rs_recv_queue);
|
|
INIT_LIST_HEAD(&rs->rs_notify_queue);
|
|
INIT_LIST_HEAD(&rs->rs_cong_list);
|
|
spin_lock_init(&rs->rs_rdma_lock);
|
|
rs->rs_rdma_keys = RB_ROOT;
|
|
|
|
spin_lock_bh(&rds_sock_lock);
|
|
list_add_tail(&rs->rs_item, &rds_sock_list);
|
|
rds_sock_count++;
|
|
spin_unlock_bh(&rds_sock_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int rds_create(struct net *net, struct socket *sock, int protocol,
|
|
int kern)
|
|
{
|
|
struct sock *sk;
|
|
|
|
if (sock->type != SOCK_SEQPACKET || protocol)
|
|
return -ESOCKTNOSUPPORT;
|
|
|
|
sk = sk_alloc(net, AF_RDS, GFP_ATOMIC, &rds_proto, kern);
|
|
if (!sk)
|
|
return -ENOMEM;
|
|
|
|
return __rds_create(sock, sk, protocol);
|
|
}
|
|
|
|
void rds_sock_addref(struct rds_sock *rs)
|
|
{
|
|
sock_hold(rds_rs_to_sk(rs));
|
|
}
|
|
|
|
void rds_sock_put(struct rds_sock *rs)
|
|
{
|
|
sock_put(rds_rs_to_sk(rs));
|
|
}
|
|
|
|
static const struct net_proto_family rds_family_ops = {
|
|
.family = AF_RDS,
|
|
.create = rds_create,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static void rds_sock_inc_info(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens)
|
|
{
|
|
struct rds_sock *rs;
|
|
struct rds_incoming *inc;
|
|
unsigned int total = 0;
|
|
|
|
len /= sizeof(struct rds_info_message);
|
|
|
|
spin_lock_bh(&rds_sock_lock);
|
|
|
|
list_for_each_entry(rs, &rds_sock_list, rs_item) {
|
|
read_lock(&rs->rs_recv_lock);
|
|
|
|
/* XXX too lazy to maintain counts.. */
|
|
list_for_each_entry(inc, &rs->rs_recv_queue, i_item) {
|
|
total++;
|
|
if (total <= len)
|
|
rds_inc_info_copy(inc, iter, inc->i_saddr,
|
|
rs->rs_bound_addr, 1);
|
|
}
|
|
|
|
read_unlock(&rs->rs_recv_lock);
|
|
}
|
|
|
|
spin_unlock_bh(&rds_sock_lock);
|
|
|
|
lens->nr = total;
|
|
lens->each = sizeof(struct rds_info_message);
|
|
}
|
|
|
|
static void rds_sock_info(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens)
|
|
{
|
|
struct rds_info_socket sinfo;
|
|
struct rds_sock *rs;
|
|
|
|
len /= sizeof(struct rds_info_socket);
|
|
|
|
spin_lock_bh(&rds_sock_lock);
|
|
|
|
if (len < rds_sock_count)
|
|
goto out;
|
|
|
|
list_for_each_entry(rs, &rds_sock_list, rs_item) {
|
|
sinfo.sndbuf = rds_sk_sndbuf(rs);
|
|
sinfo.rcvbuf = rds_sk_rcvbuf(rs);
|
|
sinfo.bound_addr = rs->rs_bound_addr;
|
|
sinfo.connected_addr = rs->rs_conn_addr;
|
|
sinfo.bound_port = rs->rs_bound_port;
|
|
sinfo.connected_port = rs->rs_conn_port;
|
|
sinfo.inum = sock_i_ino(rds_rs_to_sk(rs));
|
|
|
|
rds_info_copy(iter, &sinfo, sizeof(sinfo));
|
|
}
|
|
|
|
out:
|
|
lens->nr = rds_sock_count;
|
|
lens->each = sizeof(struct rds_info_socket);
|
|
|
|
spin_unlock_bh(&rds_sock_lock);
|
|
}
|
|
|
|
static void rds_exit(void)
|
|
{
|
|
sock_unregister(rds_family_ops.family);
|
|
proto_unregister(&rds_proto);
|
|
rds_conn_exit();
|
|
rds_cong_exit();
|
|
rds_sysctl_exit();
|
|
rds_threads_exit();
|
|
rds_stats_exit();
|
|
rds_page_exit();
|
|
rds_info_deregister_func(RDS_INFO_SOCKETS, rds_sock_info);
|
|
rds_info_deregister_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info);
|
|
}
|
|
module_exit(rds_exit);
|
|
|
|
static int rds_init(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = rds_conn_init();
|
|
if (ret)
|
|
goto out;
|
|
ret = rds_threads_init();
|
|
if (ret)
|
|
goto out_conn;
|
|
ret = rds_sysctl_init();
|
|
if (ret)
|
|
goto out_threads;
|
|
ret = rds_stats_init();
|
|
if (ret)
|
|
goto out_sysctl;
|
|
ret = proto_register(&rds_proto, 1);
|
|
if (ret)
|
|
goto out_stats;
|
|
ret = sock_register(&rds_family_ops);
|
|
if (ret)
|
|
goto out_proto;
|
|
|
|
rds_info_register_func(RDS_INFO_SOCKETS, rds_sock_info);
|
|
rds_info_register_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info);
|
|
|
|
goto out;
|
|
|
|
out_proto:
|
|
proto_unregister(&rds_proto);
|
|
out_stats:
|
|
rds_stats_exit();
|
|
out_sysctl:
|
|
rds_sysctl_exit();
|
|
out_threads:
|
|
rds_threads_exit();
|
|
out_conn:
|
|
rds_conn_exit();
|
|
rds_cong_exit();
|
|
rds_page_exit();
|
|
out:
|
|
return ret;
|
|
}
|
|
module_init(rds_init);
|
|
|
|
#define DRV_VERSION "4.0"
|
|
#define DRV_RELDATE "Feb 12, 2009"
|
|
|
|
MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>");
|
|
MODULE_DESCRIPTION("RDS: Reliable Datagram Sockets"
|
|
" v" DRV_VERSION " (" DRV_RELDATE ")");
|
|
MODULE_VERSION(DRV_VERSION);
|
|
MODULE_LICENSE("Dual BSD/GPL");
|
|
MODULE_ALIAS_NETPROTO(PF_RDS);
|