summaryrefslogtreecommitdiffstats
path: root/net/sunrpc
diff options
context:
space:
mode:
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/clnt.c5
-rw-r--r--net/sunrpc/sched.c2
-rw-r--r--net/sunrpc/svc.c2
-rw-r--r--net/sunrpc/svc_xprt.c81
-rw-r--r--net/sunrpc/svcsock.c25
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c2
-rw-r--r--net/sunrpc/xprtrdma/transport.c2
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h7
-rw-r--r--net/sunrpc/xprtsock.c121
9 files changed, 123 insertions, 124 deletions
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 488ddeed936..9acd6ce88db 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -461,6 +461,8 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
clnt->cl_autobind = 1;
+ if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT)
+ clnt->cl_noretranstimeo = 1;
if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
clnt->cl_discrtry = 1;
if (!(args->flags & RPC_CLNT_CREATE_QUIET))
@@ -579,6 +581,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
/* Turn off autobind on clones */
new->cl_autobind = 0;
new->cl_softrtry = clnt->cl_softrtry;
+ new->cl_noretranstimeo = clnt->cl_noretranstimeo;
new->cl_discrtry = clnt->cl_discrtry;
new->cl_chatty = clnt->cl_chatty;
return new;
@@ -1913,6 +1916,7 @@ call_transmit_status(struct rpc_task *task)
case -EHOSTDOWN:
case -EHOSTUNREACH:
case -ENETUNREACH:
+ case -EPERM:
if (RPC_IS_SOFTCONN(task)) {
xprt_end_transmit(task);
rpc_exit(task, task->tk_status);
@@ -2018,6 +2022,7 @@ call_status(struct rpc_task *task)
case -EHOSTDOWN:
case -EHOSTUNREACH:
case -ENETUNREACH:
+ case -EPERM:
if (RPC_IS_SOFTCONN(task)) {
rpc_exit(task, status);
break;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 9358c79fd58..fe3441abdbe 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -821,9 +821,7 @@ void rpc_execute(struct rpc_task *task)
static void rpc_async_schedule(struct work_struct *work)
{
- current->flags |= PF_FSTRANS;
__rpc_execute(container_of(work, struct rpc_task, u.tk_work));
- current->flags &= ~PF_FSTRANS;
}
/**
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 1db5007ddbc..ca8a7958f4e 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -612,8 +612,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
if (!rqstp)
goto out_enomem;
- init_waitqueue_head(&rqstp->rq_wait);
-
serv->sv_nrthreads++;
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads++;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 6666c674585..c179ca2a5aa 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -346,20 +346,6 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
if (!svc_xprt_has_something_to_do(xprt))
return;
- cpu = get_cpu();
- pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
- put_cpu();
-
- spin_lock_bh(&pool->sp_lock);
-
- if (!list_empty(&pool->sp_threads) &&
- !list_empty(&pool->sp_sockets))
- printk(KERN_ERR
- "svc_xprt_enqueue: "
- "threads and transports both waiting??\n");
-
- pool->sp_stats.packets++;
-
/* Mark transport as busy. It will remain in this state until
* the provider calls svc_xprt_received. We update XPT_BUSY
* atomically because it also guards against trying to enqueue
@@ -368,9 +354,15 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
/* Don't enqueue transport while already enqueued */
dprintk("svc: transport %p busy, not enqueued\n", xprt);
- goto out_unlock;
+ return;
}
+ cpu = get_cpu();
+ pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
+ spin_lock_bh(&pool->sp_lock);
+
+ pool->sp_stats.packets++;
+
if (!list_empty(&pool->sp_threads)) {
rqstp = list_entry(pool->sp_threads.next,
struct svc_rqst,
@@ -382,18 +374,23 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
printk(KERN_ERR
"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
rqstp, rqstp->rq_xprt);
- rqstp->rq_xprt = xprt;
+ /* Note the order of the following 3 lines:
+ * We want to assign xprt to rqstp->rq_xprt only _after_
+ * we've woken up the process, so that we don't race with
+ * the lockless check in svc_get_next_xprt().
+ */
svc_xprt_get(xprt);
+ wake_up_process(rqstp->rq_task);
+ rqstp->rq_xprt = xprt;
pool->sp_stats.threads_woken++;
- wake_up(&rqstp->rq_wait);
} else {
dprintk("svc: transport %p put into queue\n", xprt);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
pool->sp_stats.sockets_queued++;
}
-out_unlock:
spin_unlock_bh(&pool->sp_lock);
+ put_cpu();
}
/*
@@ -509,7 +506,7 @@ void svc_wake_up(struct svc_serv *serv)
svc_thread_dequeue(pool, rqstp);
rqstp->rq_xprt = NULL;
*/
- wake_up(&rqstp->rq_wait);
+ wake_up_process(rqstp->rq_task);
} else
pool->sp_task_pending = 1;
spin_unlock_bh(&pool->sp_lock);
@@ -628,8 +625,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
{
struct svc_xprt *xprt;
struct svc_pool *pool = rqstp->rq_pool;
- DECLARE_WAITQUEUE(wait, current);
- long time_left;
+ long time_left = 0;
/* Normally we will wait up to 5 seconds for any required
* cache information to be provided.
@@ -651,40 +647,32 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
} else {
if (pool->sp_task_pending) {
pool->sp_task_pending = 0;
- spin_unlock_bh(&pool->sp_lock);
- return ERR_PTR(-EAGAIN);
+ xprt = ERR_PTR(-EAGAIN);
+ goto out;
}
- /* No data pending. Go to sleep */
- svc_thread_enqueue(pool, rqstp);
-
/*
* We have to be able to interrupt this wait
* to bring down the daemons ...
*/
set_current_state(TASK_INTERRUPTIBLE);
- /*
- * checking kthread_should_stop() here allows us to avoid
- * locking and signalling when stopping kthreads that call
- * svc_recv. If the thread has already been woken up, then
- * we can exit here without sleeping. If not, then it
- * it'll be woken up quickly during the schedule_timeout
- */
- if (kthread_should_stop()) {
- set_current_state(TASK_RUNNING);
- spin_unlock_bh(&pool->sp_lock);
- return ERR_PTR(-EINTR);
- }
-
- add_wait_queue(&rqstp->rq_wait, &wait);
+ /* No data pending. Go to sleep */
+ svc_thread_enqueue(pool, rqstp);
spin_unlock_bh(&pool->sp_lock);
- time_left = schedule_timeout(timeout);
+ if (!(signalled() || kthread_should_stop())) {
+ time_left = schedule_timeout(timeout);
+ __set_current_state(TASK_RUNNING);
- try_to_freeze();
+ try_to_freeze();
+
+ xprt = rqstp->rq_xprt;
+ if (xprt != NULL)
+ return xprt;
+ } else
+ __set_current_state(TASK_RUNNING);
spin_lock_bh(&pool->sp_lock);
- remove_wait_queue(&rqstp->rq_wait, &wait);
if (!time_left)
pool->sp_stats.threads_timedout++;
@@ -699,6 +687,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
return ERR_PTR(-EAGAIN);
}
}
+out:
spin_unlock_bh(&pool->sp_lock);
return xprt;
}
@@ -744,7 +733,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
svc_add_new_temp_xprt(serv, newxpt);
else
module_put(xprt->xpt_class->xcl_owner);
- } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
+ } else {
/* XPT_DATA|XPT_DEFERRED case: */
dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
rqstp, rqstp->rq_pool->sp_id, xprt,
@@ -781,10 +770,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
printk(KERN_ERR
"svc_recv: service %p, transport not NULL!\n",
rqstp);
- if (waitqueue_active(&rqstp->rq_wait))
- printk(KERN_ERR
- "svc_recv: service %p, wait queue active!\n",
- rqstp);
err = svc_alloc_arg(rqstp);
if (err)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index c24a8ff33f8..3f959c68188 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -312,19 +312,6 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
}
/*
- * Check input queue length
- */
-static int svc_recv_available(struct svc_sock *svsk)
-{
- struct socket *sock = svsk->sk_sock;
- int avail, err;
-
- err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);
-
- return (err >= 0)? avail : err;
-}
-
-/*
* Generic recvfrom routine.
*/
static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
@@ -339,8 +326,14 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
rqstp->rq_xprt_hlen = 0;
+ clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
msg.msg_flags);
+ /* If we read a full record, then assume there may be more
+ * data to read (stream based sockets only!)
+ */
+ if (len == buflen)
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
svsk, iov[0].iov_base, iov[0].iov_len, len);
@@ -980,8 +973,6 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
unsigned int want;
int len;
- clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-
if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
struct kvec iov;
@@ -1036,7 +1027,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
"%s: Got unrecognized reply: "
"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
__func__, ntohl(calldir),
- bc_xprt, xid);
+ bc_xprt, ntohl(xid));
return -EAGAIN;
}
@@ -1073,8 +1064,6 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
static void svc_tcp_fragment_received(struct svc_sock *svsk)
{
/* If we have more data, signal svc_xprt_enqueue() to try again */
- if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
- set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
dprintk("svc: TCP %s record (%d bytes)\n",
svc_sock_final_rec(svsk) ? "final" : "nonfinal",
svc_sock_reclen(svsk));
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 374feb44afe..4e618808bc9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = {
.xcl_name = "rdma",
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_rdma_ops,
- .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+ .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
.xcl_ident = XPRT_TRANSPORT_RDMA,
};
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 2faac494056..6a4615dd026 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -205,7 +205,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
struct rpc_xprt *xprt = &r_xprt->xprt;
int rc = 0;
- current->flags |= PF_FSTRANS;
xprt_clear_connected(xprt);
dprintk("RPC: %s: %sconnect\n", __func__,
@@ -216,7 +215,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
dprintk("RPC: %s: exit\n", __func__);
xprt_clear_connecting(xprt);
- current->flags &= ~PF_FSTRANS;
}
/*
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c419498b8f4..ac7fc9a3134 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -51,6 +51,7 @@
#include <linux/sunrpc/clnt.h> /* rpc_xprt */
#include <linux/sunrpc/rpc_rdma.h> /* RPC/RDMA protocol */
#include <linux/sunrpc/xprtrdma.h> /* xprt parameters */
+#include <linux/sunrpc/svc.h> /* RPCSVC_MAXPAYLOAD */
#define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */
#define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */
@@ -392,4 +393,10 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep;
/* Workqueue created in svc_rdma.c */
extern struct workqueue_struct *svc_rdma_wq;
+#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
+#else
+#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#endif
+
#endif /* _LINUX_SUNRPC_XPRT_RDMA_H */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 43cd89eacfa..3b305ab17af 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -399,13 +399,13 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen,
return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy, int *sent_p)
{
ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
int offset, size_t size, int flags);
struct page **ppage;
unsigned int remainder;
- int err, sent = 0;
+ int err;
remainder = xdr->page_len - base;
base += xdr->page_base;
@@ -424,15 +424,15 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
err = do_sendpage(sock, *ppage, base, len, flags);
if (remainder == 0 || err != len)
break;
- sent += err;
+ *sent_p += err;
ppage++;
base = 0;
}
- if (sent == 0)
- return err;
- if (err > 0)
- sent += err;
- return sent;
+ if (err > 0) {
+ *sent_p += err;
+ err = 0;
+ }
+ return err;
}
/**
@@ -443,12 +443,14 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
* @xdr: buffer containing this request
* @base: starting position in the buffer
* @zerocopy: true if it is safe to use sendpage()
+ * @sent_p: return the total number of bytes successfully queued for sending
*
*/
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy, int *sent_p)
{
unsigned int remainder = xdr->len - base;
- int err, sent = 0;
+ int err = 0;
+ int sent = 0;
if (unlikely(!sock))
return -ENOTSOCK;
@@ -465,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
if (remainder == 0 || err != len)
goto out;
- sent += err;
+ *sent_p += err;
base = 0;
} else
base -= xdr->head[0].iov_len;
@@ -473,23 +475,23 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
if (base < xdr->page_len) {
unsigned int len = xdr->page_len - base;
remainder -= len;
- err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
- if (remainder == 0 || err != len)
+ err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy, &sent);
+ *sent_p += sent;
+ if (remainder == 0 || sent != len)
goto out;
- sent += err;
base = 0;
} else
base -= xdr->page_len;
if (base >= xdr->tail[0].iov_len)
- return sent;
+ return 0;
err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
out:
- if (sent == 0)
- return err;
- if (err > 0)
- sent += err;
- return sent;
+ if (err > 0) {
+ *sent_p += err;
+ err = 0;
+ }
+ return err;
}
static void xs_nospace_callback(struct rpc_task *task)
@@ -573,19 +575,20 @@ static int xs_local_send_request(struct rpc_task *task)
container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status;
+ int sent = 0;
xs_encode_stream_record_marker(&req->rq_snd_buf);
xs_pktdump("packet data:",
req->rq_svec->iov_base, req->rq_svec->iov_len);
- status = xs_sendpages(transport->sock, NULL, 0,
- xdr, req->rq_bytes_sent, true);
+ status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent,
+ true, &sent);
dprintk("RPC: %s(%u) = %d\n",
__func__, xdr->len - req->rq_bytes_sent, status);
- if (likely(status >= 0)) {
- req->rq_bytes_sent += status;
- req->rq_xmit_bytes_sent += status;
+ if (likely(sent > 0) || status == 0) {
+ req->rq_bytes_sent += sent;
+ req->rq_xmit_bytes_sent += sent;
if (likely(req->rq_bytes_sent >= req->rq_slen)) {
req->rq_bytes_sent = 0;
return 0;
@@ -626,6 +629,7 @@ static int xs_udp_send_request(struct rpc_task *task)
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
+ int sent = 0;
int status;
xs_pktdump("packet data:",
@@ -634,22 +638,25 @@ static int xs_udp_send_request(struct rpc_task *task)
if (!xprt_bound(xprt))
return -ENOTCONN;
- status = xs_sendpages(transport->sock,
- xs_addr(xprt),
- xprt->addrlen, xdr,
- req->rq_bytes_sent, true);
+ status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen,
+ xdr, req->rq_bytes_sent, true, &sent);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
- if (status >= 0) {
- req->rq_xmit_bytes_sent += status;
- if (status >= req->rq_slen)
+ /* firewall is blocking us, don't return -EAGAIN or we end up looping */
+ if (status == -EPERM)
+ goto process_status;
+
+ if (sent > 0 || status == 0) {
+ req->rq_xmit_bytes_sent += sent;
+ if (sent >= req->rq_slen)
return 0;
/* Still some bytes left; set up for a retry later. */
status = -EAGAIN;
}
+process_status:
switch (status) {
case -ENOTSOCK:
status = -ENOTCONN;
@@ -665,6 +672,7 @@ static int xs_udp_send_request(struct rpc_task *task)
case -ENOBUFS:
case -EPIPE:
case -ECONNREFUSED:
+ case -EPERM:
/* When the server has died, an ICMP port unreachable message
* prompts ECONNREFUSED. */
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
@@ -713,6 +721,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
struct xdr_buf *xdr = &req->rq_snd_buf;
bool zerocopy = true;
int status;
+ int sent;
xs_encode_stream_record_marker(&req->rq_snd_buf);
@@ -730,26 +739,26 @@ static int xs_tcp_send_request(struct rpc_task *task)
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
while (1) {
- status = xs_sendpages(transport->sock,
- NULL, 0, xdr, req->rq_bytes_sent,
- zerocopy);
+ sent = 0;
+ status = xs_sendpages(transport->sock, NULL, 0, xdr,
+ req->rq_bytes_sent, zerocopy, &sent);
dprintk("RPC: xs_tcp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
- if (unlikely(status < 0))
+ if (unlikely(sent == 0 && status < 0))
break;
/* If we've sent the entire packet, immediately
* reset the count of bytes sent. */
- req->rq_bytes_sent += status;
- req->rq_xmit_bytes_sent += status;
+ req->rq_bytes_sent += sent;
+ req->rq_xmit_bytes_sent += sent;
if (likely(req->rq_bytes_sent >= req->rq_slen)) {
req->rq_bytes_sent = 0;
return 0;
}
- if (status != 0)
+ if (sent != 0)
continue;
status = -EAGAIN;
break;
@@ -845,6 +854,8 @@ static void xs_error_report(struct sock *sk)
dprintk("RPC: xs_error_report client %p, error=%d...\n",
xprt, -err);
trace_rpc_socket_error(xprt, sk->sk_socket, err);
+ if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
+ goto out;
xprt_wake_pending_tasks(xprt, err);
out:
read_unlock_bh(&sk->sk_callback_lock);
@@ -1746,13 +1757,29 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
unsigned short port = xs_get_srcport(transport);
unsigned short last;
+ /*
+ * If we are asking for any ephemeral port (i.e. port == 0 &&
+ * transport->xprt.resvport == 0), don't bind. Let the local
+ * port selection happen implicitly when the socket is used
+ * (for example at connect time).
+ *
+ * This ensures that we can continue to establish TCP
+ * connections even when all local ephemeral ports are already
+ * a part of some TCP connection. This makes no difference
+ * for UDP sockets, but also doens't harm them.
+ *
+ * If we're asking for any reserved port (i.e. port == 0 &&
+ * transport->xprt.resvport == 1) xs_get_srcport above will
+ * ensure that port is non-zero and we will bind as needed.
+ */
+ if (port == 0)
+ return 0;
+
memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
do {
rpc_set_port((struct sockaddr *)&myaddr, port);
err = kernel_bind(sock, (struct sockaddr *)&myaddr,
transport->xprt.addrlen);
- if (port == 0)
- break;
if (err == 0) {
transport->srcport = port;
break;
@@ -1927,8 +1954,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
struct socket *sock;
int status = -EIO;
- current->flags |= PF_FSTRANS;
-
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
status = __sock_create(xprt->xprt_net, AF_LOCAL,
SOCK_STREAM, 0, &sock, 1);
@@ -1968,7 +1993,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
- current->flags &= ~PF_FSTRANS;
return status;
}
@@ -2071,8 +2095,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
struct socket *sock = transport->sock;
int status = -EIO;
- current->flags |= PF_FSTRANS;
-
/* Start by resetting any existing state */
xs_reset_transport(transport);
sock = xs_create_sock(xprt, transport,
@@ -2092,7 +2114,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
- current->flags &= ~PF_FSTRANS;
}
/*
@@ -2229,8 +2250,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
struct rpc_xprt *xprt = &transport->xprt;
int status = -EIO;
- current->flags |= PF_FSTRANS;
-
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
sock = xs_create_sock(xprt, transport,
@@ -2245,7 +2264,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
&xprt->state);
/* "close" the socket, preserving the local port */
+ set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
xs_tcp_reuse_connection(transport);
+ clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
if (abort_and_exit)
goto out_eagain;
@@ -2276,7 +2297,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
case -EINPROGRESS:
case -EALREADY:
xprt_clear_connecting(xprt);
- current->flags &= ~PF_FSTRANS;
return;
case -EINVAL:
/* Happens, for instance, if the user specified a link
@@ -2294,7 +2314,6 @@ out_eagain:
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
- current->flags &= ~PF_FSTRANS;
}
/**
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-14 07:21:01 +0000