*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
struct connection {
struct socket *sock; /* NULL if not connected */
uint32_t nodeid; /* So we know who we are in the list */
- struct rw_semaphore sock_sem; /* Stop connect races */
- struct list_head read_list; /* On this list when ready for reading */
- struct list_head write_list; /* On this list when ready for writing */
- struct list_head state_list; /* On this list when ready to connect */
+ struct mutex sock_mutex;
unsigned long flags; /* bit 1,2 = We are on the read/write lists */
#define CF_READ_PENDING 1
#define CF_WRITE_PENDING 2
struct page *rx_page;
struct cbuf cb;
int retries;
- atomic_t waiting_requests;
#define MAX_CONNECT_RETRIES 3
struct connection *othercon;
struct work_struct rwork; /* Receive workqueue */
goto finish;
con->nodeid = nodeid;
- init_rwsem(&con->sock_sem);
+ mutex_init(&con->sock_mutex);
INIT_LIST_HEAD(&con->writequeue);
spin_lock_init(&con->writequeue_lock);
INIT_WORK(&con->swork, process_send_sockets);
/* Close a remote connection and tidy up */
static void close_connection(struct connection *con, bool and_other)
{
- down_write(&con->sock_sem);
+ mutex_lock(&con->sock_mutex);
if (con->sock) {
sock_release(con->sock);
con->rx_page = NULL;
}
con->retries = 0;
- up_write(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
}
/* Data received from remote end */
static int receive_from_sock(struct connection *con)
{
int ret = 0;
- struct msghdr msg;
- struct iovec iov[2];
- mm_segment_t fs;
+ struct msghdr msg = {};
+ struct kvec iov[2];
unsigned len;
int r;
int call_again_soon = 0;
+ int nvec;
- down_read(&con->sock_sem);
+ mutex_lock(&con->sock_mutex);
+
+ if (con->sock == NULL) {
+ ret = -EAGAIN;
+ goto out_close;
+ }
- if (con->sock == NULL)
- goto out;
if (con->rx_page == NULL) {
/*
* This doesn't need to be atomic, but I think it should
cbuf_init(&con->cb, PAGE_CACHE_SIZE);
}
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_iovlen = 1;
- msg.msg_iov = iov;
- msg.msg_name = NULL;
- msg.msg_namelen = 0;
- msg.msg_flags = 0;
-
/*
* iov[0] is the bit of the circular buffer between the current end
* point (cb.base + cb.len) and the end of the buffer.
*/
iov[0].iov_len = con->cb.base - cbuf_data(&con->cb);
iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb);
- iov[1].iov_len = 0;
+ nvec = 1;
/*
* iov[1] is the bit of the circular buffer between the start of the
iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb);
iov[1].iov_len = con->cb.base;
iov[1].iov_base = page_address(con->rx_page);
- msg.msg_iovlen = 2;
+ nvec = 2;
}
len = iov[0].iov_len + iov[1].iov_len;
- fs = get_fs();
- set_fs(get_ds());
- r = ret = sock_recvmsg(con->sock, &msg, len,
+ r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len,
MSG_DONTWAIT | MSG_NOSIGNAL);
- set_fs(fs);
if (ret <= 0)
goto out_close;
+ if (ret == -EAGAIN)
+ goto out_resched;
+
if (ret == len)
call_again_soon = 1;
cbuf_add(&con->cb, ret);
con->rx_page = NULL;
}
-out:
if (call_again_soon)
goto out_resched;
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
return 0;
out_resched:
if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
queue_work(recv_workqueue, &con->rwork);
- up_read(&con->sock_sem);
- cond_resched();
- return 0;
+ mutex_unlock(&con->sock_mutex);
+ return -EAGAIN;
out_close:
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
if (ret != -EAGAIN && !test_bit(CF_IS_OTHERCON, &con->flags)) {
close_connection(con, false);
/* Reconnect when there is something to send */
}
+ /* Don't return success if we really got EOF */
+ if (ret == 0)
+ ret = -EAGAIN;
return ret;
}
int len;
int nodeid;
struct connection *newcon;
+ struct connection *addcon;
memset(&peeraddr, 0, sizeof(peeraddr));
result = sock_create_kern(dlm_local_addr.ss_family, SOCK_STREAM,
if (result < 0)
return -ENOMEM;
- down_read(&con->sock_sem);
+ mutex_lock_nested(&con->sock_mutex, 0);
result = -ENOTCONN;
if (con->sock == NULL)
if (dlm_addr_to_nodeid(&peeraddr, &nodeid)) {
printk("dlm: connect from non cluster node\n");
sock_release(newsock);
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
return -1;
}
result = -ENOMEM;
goto accept_err;
}
- down_write(&newcon->sock_sem);
+ mutex_lock_nested(&newcon->sock_mutex, 1);
if (newcon->sock) {
struct connection *othercon = newcon->othercon;
othercon = kmem_cache_zalloc(con_cache, GFP_KERNEL);
if (!othercon) {
printk("dlm: failed to allocate incoming socket\n");
- up_write(&newcon->sock_sem);
+ mutex_unlock(&newcon->sock_mutex);
result = -ENOMEM;
goto accept_err;
}
othercon->nodeid = nodeid;
othercon->rx_action = receive_from_sock;
- init_rwsem(&othercon->sock_sem);
+ mutex_init(&othercon->sock_mutex);
INIT_WORK(&othercon->swork, process_send_sockets);
INIT_WORK(&othercon->rwork, process_recv_sockets);
set_bit(CF_IS_OTHERCON, &othercon->flags);
othercon->sock = newsock;
newsock->sk->sk_user_data = othercon;
add_sock(newsock, othercon);
+ addcon = othercon;
}
else {
newsock->sk->sk_user_data = newcon;
newcon->rx_action = receive_from_sock;
add_sock(newsock, newcon);
-
+ addcon = newcon;
}
- up_write(&newcon->sock_sem);
+ mutex_unlock(&newcon->sock_mutex);
/*
* Add it to the active queue in case we got data
* beween processing the accept adding the socket
* to the read_sockets list
*/
- if (!test_and_set_bit(CF_READ_PENDING, &newcon->flags))
- queue_work(recv_workqueue, &newcon->rwork);
- up_read(&con->sock_sem);
+ if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
+ queue_work(recv_workqueue, &addcon->rwork);
+ mutex_unlock(&con->sock_mutex);
return 0;
accept_err:
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
sock_release(newsock);
if (result != -EAGAIN)
return;
}
- down_write(&con->sock_sem);
+ mutex_lock(&con->sock_mutex);
if (con->retries++ > MAX_CONNECT_RETRIES)
goto out;
result = 0;
}
out:
- up_write(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
return;
}
result = sock->ops->listen(sock, 5);
if (result < 0) {
- printk("dlm: Can't listen on port %d\n",
- dlm_config.ci_tcp_port);
+ printk("dlm: Can't listen on port %d\n", dlm_config.ci_tcp_port);
sock_release(sock);
sock = NULL;
goto create_out;
struct writequeue_entry *e;
int len, offset;
- down_read(&con->sock_sem);
+ mutex_lock(&con->sock_mutex);
if (con->sock == NULL)
goto out_connect;
}
spin_unlock(&con->writequeue_lock);
out:
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
return;
send_error:
- up_read(&con->sock_sem);
+ mutex_unlock(&con->sock_mutex);
close_connection(con, false);
lowcomms_connect_sock(con);
return;
out_connect:
- up_read(&con->sock_sem);
- lowcomms_connect_sock(con);
+ mutex_unlock(&con->sock_mutex);
+ connect_to_sock(con);
return;
}
if (con) {
clean_one_writequeue(con);
close_connection(con, true);
- atomic_set(&con->waiting_requests, 0);
}
return 0;
connect_to_sock(con);
}
- if (test_and_clear_bit(CF_WRITE_PENDING, &con->flags)) {
- send_to_sock(con);
- }
+ clear_bit(CF_WRITE_PENDING, &con->flags);
+ send_to_sock(con);
}