2009-02-24 08:30:18 -07:00
|
|
|
/*
|
|
|
|
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/gfp.h>
|
2009-02-24 08:30:18 -07:00
|
|
|
#include <linux/in.h>
|
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <net/sock.h>
|
|
|
|
|
|
|
|
#include "rds.h"
|
|
|
|
#include "rdma.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;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
if (sk == NULL)
|
|
|
|
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);
|
|
|
|
rds_remove_bound(rs);
|
|
|
|
rds_send_drop_to(rs, NULL);
|
|
|
|
rds_rdma_drop_keys(rs);
|
|
|
|
rds_notify_queue_get(rs, NULL);
|
|
|
|
|
|
|
|
spin_lock_irqsave(&rds_sock_lock, flags);
|
|
|
|
list_del_init(&rs->rs_item);
|
|
|
|
rds_sock_count--;
|
|
|
|
spin_unlock_irqrestore(&rds_sock_lock, flags);
|
|
|
|
|
|
|
|
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->sk_sleep, wait);
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
2009-11-29 17:55:45 -07:00
|
|
|
if (!list_empty(&rs->rs_recv_queue) ||
|
|
|
|
!list_empty(&rs->rs_notify_queue))
|
2009-02-24 08:30:18 -07:00
|
|
|
mask |= (POLLIN | POLLRDNORM);
|
|
|
|
if (rs->rs_snd_bytes < rds_sk_sndbuf(rs))
|
|
|
|
mask |= (POLLOUT | POLLWRNORM);
|
|
|
|
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
|
|
|
|
|
|
|
|
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_setsockopt(struct socket *sock, int level, int optname,
|
2009-09-30 17:12:20 -06:00
|
|
|
char __user *optval, unsigned int optlen)
|
2009-02-24 08:30:18 -07:00
|
|
|
{
|
|
|
|
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;
|
2009-10-30 02:54:53 -06:00
|
|
|
case RDS_GET_MR_FOR_DEST:
|
|
|
|
ret = rds_get_mr_for_dest(rs, optval, optlen);
|
|
|
|
break;
|
2009-02-24 08:30:18 -07:00
|
|
|
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;
|
|
|
|
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;
|
|
|
|
|
|
|
|
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
|
2009-11-29 17:55:45 -07:00
|
|
|
if (put_user(rs->rs_recverr, (int __user *) optval) ||
|
|
|
|
put_user(sizeof(int), optlen))
|
2009-02-24 08:30:18 -07:00
|
|
|
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),
|
|
|
|
};
|
|
|
|
|
2009-09-14 06:23:23 -06:00
|
|
|
static const struct proto_ops rds_proto_ops = {
|
2009-02-24 08:30:18 -07:00
|
|
|
.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)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
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_irqsave(&rds_sock_lock, flags);
|
|
|
|
list_add_tail(&rs->rs_item, &rds_sock_list);
|
|
|
|
rds_sock_count++;
|
|
|
|
spin_unlock_irqrestore(&rds_sock_lock, flags);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-11-05 23:18:14 -07:00
|
|
|
static int rds_create(struct net *net, struct socket *sock, int protocol,
|
|
|
|
int kern)
|
2009-02-24 08:30:18 -07:00
|
|
|
{
|
|
|
|
struct sock *sk;
|
|
|
|
|
|
|
|
if (sock->type != SOCK_SEQPACKET || protocol)
|
|
|
|
return -ESOCKTNOSUPPORT;
|
|
|
|
|
|
|
|
sk = sk_alloc(net, AF_RDS, GFP_ATOMIC, &rds_proto);
|
|
|
|
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));
|
|
|
|
}
|
|
|
|
|
2009-10-04 23:58:39 -06:00
|
|
|
static const struct net_proto_family rds_family_ops = {
|
2009-02-24 08:30:18 -07:00
|
|
|
.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 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);
|
|
|
|
|
|
|
|
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.. */
|
|
|
|
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_irqrestore(&rds_sock_lock, flags);
|
|
|
|
|
|
|
|
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;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
len /= sizeof(struct rds_info_socket);
|
|
|
|
|
|
|
|
spin_lock_irqsave(&rds_sock_lock, flags);
|
|
|
|
|
|
|
|
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_irqrestore(&rds_sock_lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit 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 __init 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);
|