*
* Client-side transport implementation for sockets.
*
- * TCP callback races fixes (C) 1998 Red Hat Software <alan@redhat.com>
- * TCP send fixes (C) 1998 Red Hat Software <alan@redhat.com>
+ * TCP callback races fixes (C) 1998 Red Hat
+ * TCP send fixes (C) 1998 Red Hat
* TCP NFS related read + write fixes
* (C) 1999 Dave Airlie, University of Limerick, Ireland <airlied@linux.ie>
*
#include <linux/types.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <linux/capability.h>
#include <linux/pagemap.h>
#include <linux/errno.h>
#include <linux/tcp.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/xprtsock.h>
#include <linux/file.h>
+#ifdef CONFIG_NFS_V4_1
+#include <linux/sunrpc/bc_xprt.h>
+#endif
#include <net/sock.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/tcp.h>
+#include "sunrpc.h"
/*
* xprtsock tunables
*/
unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;
+#define XS_TCP_LINGER_TO (15U * HZ)
+static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;
+
/*
* We can register our own files under /proc/sys/sunrpc by
* calling register_sysctl_table() again. The files in that
*/
static ctl_table xs_tunables_table[] = {
{
- .ctl_name = CTL_SLOTTABLE_UDP,
.procname = "udp_slot_table_entries",
.data = &xprt_udp_slot_table_entries,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &min_slot_table_size,
.extra2 = &max_slot_table_size
},
{
- .ctl_name = CTL_SLOTTABLE_TCP,
.procname = "tcp_slot_table_entries",
.data = &xprt_tcp_slot_table_entries,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &min_slot_table_size,
.extra2 = &max_slot_table_size
},
{
- .ctl_name = CTL_MIN_RESVPORT,
.procname = "min_resvport",
.data = &xprt_min_resvport,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xprt_min_resvport_limit,
.extra2 = &xprt_max_resvport_limit
},
{
- .ctl_name = CTL_MAX_RESVPORT,
.procname = "max_resvport",
.data = &xprt_max_resvport,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xprt_min_resvport_limit,
.extra2 = &xprt_max_resvport_limit
},
{
- .ctl_name = 0,
+ .procname = "tcp_fin_timeout",
+ .data = &xs_tcp_fin_timeout,
+ .maxlen = sizeof(xs_tcp_fin_timeout),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
},
+ { },
};
static ctl_table sunrpc_table[] = {
{
- .ctl_name = CTL_SUNRPC,
.procname = "sunrpc",
.mode = 0555,
.child = xs_tunables_table
},
- {
- .ctl_name = 0,
- },
+ { },
};
#endif
/*
- * How many times to try sending a request on a socket before waiting
- * for the socket buffer to clear.
- */
-#define XS_SENDMSG_RETRY (10U)
-
-/*
- * Time out for an RPC UDP socket connect. UDP socket connects are
- * synchronous, but we set a timeout anyway in case of resource
- * exhaustion on the local host.
- */
-#define XS_UDP_CONN_TO (5U * HZ)
-
-/*
- * Wait duration for an RPC TCP connection to be established. Solaris
- * NFS over TCP uses 60 seconds, for example, which is in line with how
- * long a server takes to reboot.
- */
-#define XS_TCP_CONN_TO (60U * HZ)
-
-/*
* Wait duration for a reply from the RPC portmapper.
*/
#define XS_BIND_TO (60U * HZ)
* Connection of transports
*/
struct delayed_work connect_worker;
- struct sockaddr_storage addr;
- unsigned short port;
+ struct sockaddr_storage srcaddr;
+ unsigned short srcport;
/*
* UDP socket buffer size parameters
void (*old_data_ready)(struct sock *, int);
void (*old_state_change)(struct sock *);
void (*old_write_space)(struct sock *);
+ void (*old_error_report)(struct sock *);
};
/*
#define TCP_RCV_COPY_FRAGHDR (1UL << 1)
#define TCP_RCV_COPY_XID (1UL << 2)
#define TCP_RCV_COPY_DATA (1UL << 3)
+#define TCP_RCV_READ_CALLDIR (1UL << 4)
+#define TCP_RCV_COPY_CALLDIR (1UL << 5)
+
+/*
+ * TCP RPC flags
+ */
+#define TCP_RPC_REPLY (1UL << 6)
static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
{
return (struct sockaddr_in6 *) &xprt->addr;
}
-static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt)
+static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)
{
- struct sockaddr_in *addr = xs_addr_in(xprt);
- char *buf;
-
- buf = kzalloc(20, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 20, NIPQUAD_FMT,
- NIPQUAD(addr->sin_addr.s_addr));
- }
- xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
-
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 8, "%u",
- ntohs(addr->sin_port));
- }
- xprt->address_strings[RPC_DISPLAY_PORT] = buf;
-
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- if (xprt->prot == IPPROTO_UDP)
- snprintf(buf, 8, "udp");
- else
- snprintf(buf, 8, "tcp");
- }
- xprt->address_strings[RPC_DISPLAY_PROTO] = buf;
-
- buf = kzalloc(48, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 48, "addr="NIPQUAD_FMT" port=%u proto=%s",
- NIPQUAD(addr->sin_addr.s_addr),
- ntohs(addr->sin_port),
- xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
- }
- xprt->address_strings[RPC_DISPLAY_ALL] = buf;
+ struct sockaddr *sap = xs_addr(xprt);
+ struct sockaddr_in6 *sin6;
+ struct sockaddr_in *sin;
+ char buf[128];
- buf = kzalloc(10, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 10, "%02x%02x%02x%02x",
- NIPQUAD(addr->sin_addr.s_addr));
- }
- xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
+ (void)rpc_ntop(sap, buf, sizeof(buf));
+ xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 8, "%4hx",
- ntohs(addr->sin_port));
+ switch (sap->sa_family) {
+ case AF_INET:
+ sin = xs_addr_in(xprt);
+ snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
+ break;
+ case AF_INET6:
+ sin6 = xs_addr_in6(xprt);
+ snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
+ break;
+ default:
+ BUG();
}
- xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
+ xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
}
-static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt)
+static void xs_format_common_peer_ports(struct rpc_xprt *xprt)
{
- struct sockaddr_in6 *addr = xs_addr_in6(xprt);
- char *buf;
+ struct sockaddr *sap = xs_addr(xprt);
+ char buf[128];
- buf = kzalloc(40, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 40, NIP6_FMT,
- NIP6(addr->sin6_addr));
- }
- xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
+ snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
+ xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 8, "%u",
- ntohs(addr->sin6_port));
- }
- xprt->address_strings[RPC_DISPLAY_PORT] = buf;
-
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- if (xprt->prot == IPPROTO_UDP)
- snprintf(buf, 8, "udp");
- else
- snprintf(buf, 8, "tcp");
- }
- xprt->address_strings[RPC_DISPLAY_PROTO] = buf;
-
- buf = kzalloc(64, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 64, "addr="NIP6_FMT" port=%u proto=%s",
- NIP6(addr->sin6_addr),
- ntohs(addr->sin6_port),
- xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
- }
- xprt->address_strings[RPC_DISPLAY_ALL] = buf;
+ snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
+ xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
+}
- buf = kzalloc(36, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 36, NIP6_SEQFMT,
- NIP6(addr->sin6_addr));
- }
- xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
+static void xs_format_peer_addresses(struct rpc_xprt *xprt,
+ const char *protocol,
+ const char *netid)
+{
+ xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;
+ xprt->address_strings[RPC_DISPLAY_NETID] = netid;
+ xs_format_common_peer_addresses(xprt);
+ xs_format_common_peer_ports(xprt);
+}
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 8, "%4hx",
- ntohs(addr->sin6_port));
- }
- xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
+static void xs_update_peer_port(struct rpc_xprt *xprt)
+{
+ kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
+ kfree(xprt->address_strings[RPC_DISPLAY_PORT]);
+
+ xs_format_common_peer_ports(xprt);
}
static void xs_free_peer_addresses(struct rpc_xprt *xprt)
{
- int i;
+ unsigned int i;
for (i = 0; i < RPC_DISPLAY_MAX; i++)
- kfree(xprt->address_strings[i]);
+ switch (i) {
+ case RPC_DISPLAY_PROTO:
+ case RPC_DISPLAY_NETID:
+ continue;
+ default:
+ kfree(xprt->address_strings[i]);
+ }
}
#define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
int err, sent = 0;
if (unlikely(!sock))
- return -ENOTCONN;
+ return -ENOTSOCK;
clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
if (base != 0) {
return sent;
}
+static void xs_nospace_callback(struct rpc_task *task)
+{
+ struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);
+
+ transport->inet->sk_write_pending--;
+ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+}
+
/**
* xs_nospace - place task on wait queue if transmit was incomplete
* @task: task to put to sleep
*
*/
-static void xs_nospace(struct rpc_task *task)
+static int xs_nospace(struct rpc_task *task)
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ int ret = 0;
dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
task->tk_pid, req->rq_slen - req->rq_bytes_sent,
req->rq_slen);
- if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
- /* Protect against races with write_space */
- spin_lock_bh(&xprt->transport_lock);
-
- /* Don't race with disconnect */
- if (!xprt_connected(xprt))
- task->tk_status = -ENOTCONN;
- else if (test_bit(SOCK_NOSPACE, &transport->sock->flags))
- xprt_wait_for_buffer_space(task);
+ /* Protect against races with write_space */
+ spin_lock_bh(&xprt->transport_lock);
+
+ /* Don't race with disconnect */
+ if (xprt_connected(xprt)) {
+ if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
+ ret = -EAGAIN;
+ /*
+ * Notify TCP that we're limited by the application
+ * window size
+ */
+ set_bit(SOCK_NOSPACE, &transport->sock->flags);
+ transport->inet->sk_write_pending++;
+ /* ...and wait for more buffer space */
+ xprt_wait_for_buffer_space(task, xs_nospace_callback);
+ }
+ } else {
+ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+ ret = -ENOTCONN;
+ }
- spin_unlock_bh(&xprt->transport_lock);
- } else
- /* Keep holding the socket if it is blocked */
- rpc_delay(task, HZ>>4);
+ spin_unlock_bh(&xprt->transport_lock);
+ return ret;
}
/**
req->rq_svec->iov_base,
req->rq_svec->iov_len);
- req->rq_xtime = jiffies;
+ if (!xprt_bound(xprt))
+ return -ENOTCONN;
status = xs_sendpages(transport->sock,
xs_addr(xprt),
xprt->addrlen, xdr,
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
- if (likely(status >= (int) req->rq_slen))
- return 0;
-
- /* Still some bytes left; set up for a retry later. */
- if (status > 0)
+ if (status >= 0) {
+ req->rq_xmit_bytes_sent += status;
+ if (status >= req->rq_slen)
+ return 0;
+ /* Still some bytes left; set up for a retry later. */
status = -EAGAIN;
+ }
switch (status) {
- case -ENETUNREACH:
- case -EPIPE:
- case -ECONNREFUSED:
- /* When the server has died, an ICMP port unreachable message
- * prompts ECONNREFUSED. */
+ case -ENOTSOCK:
+ status = -ENOTCONN;
+ /* Should we call xs_close() here? */
break;
case -EAGAIN:
- xs_nospace(task);
+ status = xs_nospace(task);
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
- break;
+ case -ENETUNREACH:
+ case -EPIPE:
+ case -ECONNREFUSED:
+ /* When the server has died, an ICMP port unreachable message
+ * prompts ECONNREFUSED. */
+ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
}
return status;
}
+/**
+ * xs_tcp_shutdown - gracefully shut down a TCP socket
+ * @xprt: transport
+ *
+ * Initiates a graceful shutdown of the TCP socket by calling the
+ * equivalent of shutdown(SHUT_WR);
+ */
+static void xs_tcp_shutdown(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct socket *sock = transport->sock;
+
+ if (sock != NULL)
+ kernel_sock_shutdown(sock, SHUT_WR);
+}
+
static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf)
{
u32 reclen = buf->len - sizeof(rpc_fraghdr);
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status;
- unsigned int retry = 0;
xs_encode_tcp_record_marker(&req->rq_snd_buf);
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
while (1) {
- req->rq_xtime = jiffies;
status = xs_sendpages(transport->sock,
NULL, 0, xdr, req->rq_bytes_sent);
/* If we've sent the entire packet, immediately
* reset the count of bytes sent. */
req->rq_bytes_sent += status;
- task->tk_bytes_sent += status;
+ req->rq_xmit_bytes_sent += status;
if (likely(req->rq_bytes_sent >= req->rq_slen)) {
req->rq_bytes_sent = 0;
return 0;
}
+ if (status != 0)
+ continue;
status = -EAGAIN;
- if (retry++ > XS_SENDMSG_RETRY)
- break;
+ break;
}
switch (status) {
- case -EAGAIN:
- xs_nospace(task);
- break;
- case -ECONNREFUSED:
- case -ECONNRESET:
- case -ENOTCONN:
- case -EPIPE:
+ case -ENOTSOCK:
status = -ENOTCONN;
+ /* Should we call xs_close() here? */
+ break;
+ case -EAGAIN:
+ status = xs_nospace(task);
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
- xprt_disconnect(xprt);
- break;
+ case -ECONNRESET:
+ case -EPIPE:
+ xs_tcp_shutdown(xprt);
+ case -ECONNREFUSED:
+ case -ENOTCONN:
+ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
}
return status;
xprt_release_xprt(xprt, task);
}
-/**
- * xs_close - close a socket
- * @xprt: transport
- *
- * This is used when all requests are complete; ie, no DRC state remains
- * on the server we want to save.
- */
-static void xs_close(struct rpc_xprt *xprt)
+static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
+{
+ transport->old_data_ready = sk->sk_data_ready;
+ transport->old_state_change = sk->sk_state_change;
+ transport->old_write_space = sk->sk_write_space;
+ transport->old_error_report = sk->sk_error_report;
+}
+
+static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
+{
+ sk->sk_data_ready = transport->old_data_ready;
+ sk->sk_state_change = transport->old_state_change;
+ sk->sk_write_space = transport->old_write_space;
+ sk->sk_error_report = transport->old_error_report;
+}
+
+static void xs_reset_transport(struct sock_xprt *transport)
{
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct socket *sock = transport->sock;
struct sock *sk = transport->inet;
- if (!sk)
- goto clear_close_wait;
-
- dprintk("RPC: xs_close xprt %p\n", xprt);
+ if (sk == NULL)
+ return;
write_lock_bh(&sk->sk_callback_lock);
transport->inet = NULL;
transport->sock = NULL;
sk->sk_user_data = NULL;
- sk->sk_data_ready = transport->old_data_ready;
- sk->sk_state_change = transport->old_state_change;
- sk->sk_write_space = transport->old_write_space;
+
+ xs_restore_old_callbacks(transport, sk);
write_unlock_bh(&sk->sk_callback_lock);
sk->sk_no_check = 0;
sock_release(sock);
-clear_close_wait:
+}
+
+/**
+ * xs_close - close a socket
+ * @xprt: transport
+ *
+ * This is used when all requests are complete; ie, no DRC state remains
+ * on the server we want to save.
+ *
+ * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with
+ * xs_reset_transport() zeroing the socket from underneath a writer.
+ */
+static void xs_close(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+
+ dprintk("RPC: xs_close xprt %p\n", xprt);
+
+ xs_reset_transport(transport);
+ xprt->reestablish_timeout = 0;
+
smp_mb__before_clear_bit();
+ clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
+ clear_bit(XPRT_CLOSING, &xprt->state);
smp_mb__after_clear_bit();
+ xprt_disconnect_done(xprt);
+}
+
+static void xs_tcp_close(struct rpc_xprt *xprt)
+{
+ if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
+ xs_close(xprt);
+ else
+ xs_tcp_shutdown(xprt);
}
/**
cancel_rearming_delayed_work(&transport->connect_worker);
- xprt_disconnect(xprt);
xs_close(xprt);
xs_free_peer_addresses(xprt);
kfree(xprt->slot);
kfree(xprt);
+ module_put(THIS_MODULE);
}
static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
copied = repsize;
/* Suck it into the iovec, verify checksum if not done by hw. */
- if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb))
+ if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) {
+ UDPX_INC_STATS_BH(sk, UDP_MIB_INERRORS);
goto out_unlock;
+ }
+
+ UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS);
/* Something worked... */
- dst_confirm(skb->dst);
+ dst_confirm(skb_dst(skb));
xprt_adjust_cwnd(task, copied);
- xprt_update_rtt(task);
xprt_complete_rqst(task, copied);
out_unlock:
transport->tcp_offset = 0;
/* Sanity check of the record length */
- if (unlikely(transport->tcp_reclen < 4)) {
+ if (unlikely(transport->tcp_reclen < 8)) {
dprintk("RPC: invalid TCP record fragment length\n");
- xprt_disconnect(xprt);
+ xprt_force_disconnect(xprt);
return;
}
dprintk("RPC: reading TCP record fragment of length %d\n",
if (used != len)
return;
transport->tcp_flags &= ~TCP_RCV_COPY_XID;
- transport->tcp_flags |= TCP_RCV_COPY_DATA;
+ transport->tcp_flags |= TCP_RCV_READ_CALLDIR;
transport->tcp_copied = 4;
- dprintk("RPC: reading reply for XID %08x\n",
+ dprintk("RPC: reading %s XID %08x\n",
+ (transport->tcp_flags & TCP_RPC_REPLY) ? "reply for"
+ : "request with",
ntohl(transport->tcp_xid));
xs_tcp_check_fraghdr(transport);
}
-static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
+static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
+ struct xdr_skb_reader *desc)
{
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
- struct rpc_rqst *req;
+ size_t len, used;
+ u32 offset;
+ __be32 calldir;
+
+ /*
+ * We want transport->tcp_offset to be 8 at the end of this routine
+ * (4 bytes for the xid and 4 bytes for the call/reply flag).
+ * When this function is called for the first time,
+ * transport->tcp_offset is 4 (after having already read the xid).
+ */
+ offset = transport->tcp_offset - sizeof(transport->tcp_xid);
+ len = sizeof(calldir) - offset;
+ dprintk("RPC: reading CALL/REPLY flag (%Zu bytes)\n", len);
+ used = xdr_skb_read_bits(desc, &calldir, len);
+ transport->tcp_offset += used;
+ if (used != len)
+ return;
+ transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR;
+ transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
+ transport->tcp_flags |= TCP_RCV_COPY_DATA;
+ /*
+ * We don't yet have the XDR buffer, so we will write the calldir
+ * out after we get the buffer from the 'struct rpc_rqst'
+ */
+ if (ntohl(calldir) == RPC_REPLY)
+ transport->tcp_flags |= TCP_RPC_REPLY;
+ else
+ transport->tcp_flags &= ~TCP_RPC_REPLY;
+ dprintk("RPC: reading %s CALL/REPLY flag %08x\n",
+ (transport->tcp_flags & TCP_RPC_REPLY) ?
+ "reply for" : "request with", calldir);
+ xs_tcp_check_fraghdr(transport);
+}
+
+static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc,
+ struct rpc_rqst *req)
+{
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *rcvbuf;
size_t len;
ssize_t r;
- /* Find and lock the request corresponding to this xid */
- spin_lock(&xprt->transport_lock);
- req = xprt_lookup_rqst(xprt, transport->tcp_xid);
- if (!req) {
- transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
- dprintk("RPC: XID %08x request not found!\n",
- ntohl(transport->tcp_xid));
- spin_unlock(&xprt->transport_lock);
- return;
+ rcvbuf = &req->rq_private_buf;
+
+ if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) {
+ /*
+ * Save the RPC direction in the XDR buffer
+ */
+ __be32 calldir = transport->tcp_flags & TCP_RPC_REPLY ?
+ htonl(RPC_REPLY) : 0;
+
+ memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied,
+ &calldir, sizeof(calldir));
+ transport->tcp_copied += sizeof(calldir);
+ transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR;
}
- rcvbuf = &req->rq_private_buf;
len = desc->count;
if (len > transport->tcp_reclen - transport->tcp_offset) {
struct xdr_skb_reader my_desc;
"tcp_offset = %u, tcp_reclen = %u\n",
xprt, transport->tcp_copied,
transport->tcp_offset, transport->tcp_reclen);
- goto out;
+ return;
}
dprintk("RPC: XID %08x read %Zd bytes\n",
if (transport->tcp_flags & TCP_RCV_LAST_FRAG)
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
}
+}
+
+/*
+ * Finds the request corresponding to the RPC xid and invokes the common
+ * tcp read code to read the data.
+ */
+static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc)
+{
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
+ struct rpc_rqst *req;
+
+ dprintk("RPC: read reply XID %08x\n", ntohl(transport->tcp_xid));
+
+ /* Find and lock the request corresponding to this xid */
+ spin_lock(&xprt->transport_lock);
+ req = xprt_lookup_rqst(xprt, transport->tcp_xid);
+ if (!req) {
+ dprintk("RPC: XID %08x request not found!\n",
+ ntohl(transport->tcp_xid));
+ spin_unlock(&xprt->transport_lock);
+ return -1;
+ }
+
+ xs_tcp_read_common(xprt, desc, req);
-out:
if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
xprt_complete_rqst(req->rq_task, transport->tcp_copied);
+
spin_unlock(&xprt->transport_lock);
- xs_tcp_check_fraghdr(transport);
+ return 0;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * Obtains an rpc_rqst previously allocated and invokes the common
+ * tcp read code to read the data. The result is placed in the callback
+ * queue.
+ * If we're unable to obtain the rpc_rqst we schedule the closing of the
+ * connection and return -1.
+ */
+static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc)
+{
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
+ struct rpc_rqst *req;
+
+ req = xprt_alloc_bc_request(xprt);
+ if (req == NULL) {
+ printk(KERN_WARNING "Callback slot table overflowed\n");
+ xprt_force_disconnect(xprt);
+ return -1;
+ }
+
+ req->rq_xid = transport->tcp_xid;
+ dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid));
+ xs_tcp_read_common(xprt, desc, req);
+
+ if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
+ struct svc_serv *bc_serv = xprt->bc_serv;
+
+ /*
+ * Add callback request to callback list. The callback
+ * service sleeps on the sv_cb_waitq waiting for new
+ * requests. Wake it up after adding enqueing the
+ * request.
+ */
+ dprintk("RPC: add callback request to list\n");
+ spin_lock(&bc_serv->sv_cb_lock);
+ list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
+ spin_unlock(&bc_serv->sv_cb_lock);
+ wake_up(&bc_serv->sv_cb_waitq);
+ }
+
+ req->rq_private_buf.len = transport->tcp_copied;
+
+ return 0;
+}
+
+static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc)
+{
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
+
+ return (transport->tcp_flags & TCP_RPC_REPLY) ?
+ xs_tcp_read_reply(xprt, desc) :
+ xs_tcp_read_callback(xprt, desc);
+}
+#else
+static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc)
+{
+ return xs_tcp_read_reply(xprt, desc);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Read data off the transport. This can be either an RPC_CALL or an
+ * RPC_REPLY. Relay the processing to helper functions.
+ */
+static void xs_tcp_read_data(struct rpc_xprt *xprt,
+ struct xdr_skb_reader *desc)
+{
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
+
+ if (_xs_tcp_read_data(xprt, desc) == 0)
+ xs_tcp_check_fraghdr(transport);
+ else {
+ /*
+ * The transport_lock protects the request handling.
+ * There's no need to hold it to update the tcp_flags.
+ */
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
+ }
}
static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
xs_tcp_read_xid(transport, &desc);
continue;
}
+ /* Read in the call/reply flag */
+ if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) {
+ xs_tcp_read_calldir(transport, &desc);
+ continue;
+ }
/* Read in the request data */
if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
- xs_tcp_read_request(xprt, &desc);
+ xs_tcp_read_data(xprt, &desc);
continue;
}
/* Skip over any trailing bytes on short reads */
{
struct rpc_xprt *xprt;
read_descriptor_t rd_desc;
+ int read;
dprintk("RPC: xs_tcp_data_ready...\n");
if (xprt->shutdown)
goto out;
+ /* Any data means we had a useful conversation, so
+ * the we don't need to delay the next reconnect
+ */
+ if (xprt->reestablish_timeout)
+ xprt->reestablish_timeout = 0;
+
/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
rd_desc.arg.data = xprt;
- rd_desc.count = 65536;
- tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
+ do {
+ rd_desc.count = 65536;
+ read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
+ } while (read > 0);
out:
read_unlock(&sk->sk_callback_lock);
}
-/**
- * xs_tcp_state_change - callback to handle TCP socket state changes
- * @sk: socket whose state has changed
- *
+/*
+ * Do the equivalent of linger/linger2 handling for dealing with
+ * broken servers that don't close the socket in a timely
+ * fashion
*/
-static void xs_tcp_state_change(struct sock *sk)
+static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt,
+ unsigned long timeout)
{
- struct rpc_xprt *xprt;
+ struct sock_xprt *transport;
- read_lock(&sk->sk_callback_lock);
- if (!(xprt = xprt_from_sock(sk)))
- goto out;
- dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
- dprintk("RPC: state %x conn %d dead %d zapped %d\n",
- sk->sk_state, xprt_connected(xprt),
+ if (xprt_test_and_set_connecting(xprt))
+ return;
+ set_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+ transport = container_of(xprt, struct sock_xprt, xprt);
+ queue_delayed_work(rpciod_workqueue, &transport->connect_worker,
+ timeout);
+}
+
+static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *transport;
+
+ transport = container_of(xprt, struct sock_xprt, xprt);
+
+ if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) ||
+ !cancel_delayed_work(&transport->connect_worker))
+ return;
+ clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+ xprt_clear_connecting(xprt);
+}
+
+static void xs_sock_mark_closed(struct rpc_xprt *xprt)
+{
+ smp_mb__before_clear_bit();
+ clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
+ clear_bit(XPRT_CLOSING, &xprt->state);
+ smp_mb__after_clear_bit();
+ /* Mark transport as closed and wake up all pending tasks */
+ xprt_disconnect_done(xprt);
+}
+
+/**
+ * xs_tcp_state_change - callback to handle TCP socket state changes
+ * @sk: socket whose state has changed
+ *
+ */
+static void xs_tcp_state_change(struct sock *sk)
+{
+ struct rpc_xprt *xprt;
+
+ read_lock(&sk->sk_callback_lock);
+ if (!(xprt = xprt_from_sock(sk)))
+ goto out;
+ dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
+ dprintk("RPC: state %x conn %d dead %d zapped %d\n",
+ sk->sk_state, xprt_connected(xprt),
sock_flag(sk, SOCK_DEAD),
sock_flag(sk, SOCK_ZAPPED));
transport->tcp_flags =
TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
- xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
- xprt_wake_pending_tasks(xprt, 0);
+ xprt_wake_pending_tasks(xprt, -EAGAIN);
}
spin_unlock_bh(&xprt->transport_lock);
break;
- case TCP_SYN_SENT:
- case TCP_SYN_RECV:
+ case TCP_FIN_WAIT1:
+ /* The client initiated a shutdown of the socket */
+ xprt->connect_cookie++;
+ xprt->reestablish_timeout = 0;
+ set_bit(XPRT_CLOSING, &xprt->state);
+ smp_mb__before_clear_bit();
+ clear_bit(XPRT_CONNECTED, &xprt->state);
+ clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
+ smp_mb__after_clear_bit();
+ xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
break;
case TCP_CLOSE_WAIT:
- /* Try to schedule an autoclose RPC calls */
- set_bit(XPRT_CLOSE_WAIT, &xprt->state);
- if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
- queue_work(rpciod_workqueue, &xprt->task_cleanup);
- default:
- xprt_disconnect(xprt);
+ /* The server initiated a shutdown of the socket */
+ xprt_force_disconnect(xprt);
+ case TCP_SYN_SENT:
+ xprt->connect_cookie++;
+ case TCP_CLOSING:
+ /*
+ * If the server closed down the connection, make sure that
+ * we back off before reconnecting
+ */
+ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+ xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+ break;
+ case TCP_LAST_ACK:
+ set_bit(XPRT_CLOSING, &xprt->state);
+ xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
+ smp_mb__before_clear_bit();
+ clear_bit(XPRT_CONNECTED, &xprt->state);
+ smp_mb__after_clear_bit();
+ break;
+ case TCP_CLOSE:
+ xs_tcp_cancel_linger_timeout(xprt);
+ xs_sock_mark_closed(xprt);
}
out:
read_unlock(&sk->sk_callback_lock);
}
/**
+ * xs_error_report - callback mainly for catching socket errors
+ * @sk: socket
+ */
+static void xs_error_report(struct sock *sk)
+{
+ struct rpc_xprt *xprt;
+
+ read_lock(&sk->sk_callback_lock);
+ if (!(xprt = xprt_from_sock(sk)))
+ goto out;
+ dprintk("RPC: %s client %p...\n"
+ "RPC: error %d\n",
+ __func__, xprt, sk->sk_err);
+ xprt_wake_pending_tasks(xprt, -EAGAIN);
+out:
+ read_unlock(&sk->sk_callback_lock);
+}
+
+static void xs_write_space(struct sock *sk)
+{
+ struct socket *sock;
+ struct rpc_xprt *xprt;
+
+ if (unlikely(!(sock = sk->sk_socket)))
+ return;
+ clear_bit(SOCK_NOSPACE, &sock->flags);
+
+ if (unlikely(!(xprt = xprt_from_sock(sk))))
+ return;
+ if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
+ return;
+
+ xprt_write_space(xprt);
+}
+
+/**
* xs_udp_write_space - callback invoked when socket buffer space
* becomes available
* @sk: socket whose state has changed
read_lock(&sk->sk_callback_lock);
/* from net/core/sock.c:sock_def_write_space */
- if (sock_writeable(sk)) {
- struct socket *sock;
- struct rpc_xprt *xprt;
-
- if (unlikely(!(sock = sk->sk_socket)))
- goto out;
- if (unlikely(!(xprt = xprt_from_sock(sk))))
- goto out;
- if (unlikely(!test_and_clear_bit(SOCK_NOSPACE, &sock->flags)))
- goto out;
+ if (sock_writeable(sk))
+ xs_write_space(sk);
- xprt_write_space(xprt);
- }
-
- out:
read_unlock(&sk->sk_callback_lock);
}
read_lock(&sk->sk_callback_lock);
/* from net/core/stream.c:sk_stream_write_space */
- if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
- struct socket *sock;
- struct rpc_xprt *xprt;
+ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
+ xs_write_space(sk);
- if (unlikely(!(sock = sk->sk_socket)))
- goto out;
- if (unlikely(!(xprt = xprt_from_sock(sk))))
- goto out;
- if (unlikely(!test_and_clear_bit(SOCK_NOSPACE, &sock->flags)))
- goto out;
-
- xprt_write_space(xprt);
- }
-
- out:
read_unlock(&sk->sk_callback_lock);
}
*/
static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
{
- struct sockaddr *addr = xs_addr(xprt);
-
dprintk("RPC: setting port for xprt %p to %u\n", xprt, port);
- switch (addr->sa_family) {
- case AF_INET:
- ((struct sockaddr_in *)addr)->sin_port = htons(port);
- break;
- case AF_INET6:
- ((struct sockaddr_in6 *)addr)->sin6_port = htons(port);
- break;
- default:
- BUG();
- }
+ rpc_set_port(xs_addr(xprt), port);
+ xs_update_peer_port(xprt);
+}
+
+static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock)
+{
+ unsigned short port = transport->srcport;
+
+ if (port == 0 && transport->xprt.resvport)
+ port = xs_get_random_port();
+ return port;
+}
+
+static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port)
+{
+ if (transport->srcport != 0)
+ transport->srcport = 0;
+ if (!transport->xprt.resvport)
+ return 0;
+ if (port <= xprt_min_resvport || port > xprt_max_resvport)
+ return xprt_max_resvport;
+ return --port;
}
static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
.sin_family = AF_INET,
};
struct sockaddr_in *sa;
- int err;
- unsigned short port = transport->port;
+ int err, nloop = 0;
+ unsigned short port = xs_get_srcport(transport, sock);
+ unsigned short last;
- if (!transport->xprt.resvport)
- port = 0;
- sa = (struct sockaddr_in *)&transport->addr;
+ sa = (struct sockaddr_in *)&transport->srcaddr;
myaddr.sin_addr = sa->sin_addr;
do {
myaddr.sin_port = htons(port);
err = kernel_bind(sock, (struct sockaddr *) &myaddr,
sizeof(myaddr));
- if (!transport->xprt.resvport)
+ if (port == 0)
break;
if (err == 0) {
- transport->port = port;
+ transport->srcport = port;
break;
}
- if (port <= xprt_min_resvport)
- port = xprt_max_resvport;
- else
- port--;
- } while (err == -EADDRINUSE && port != transport->port);
- dprintk("RPC: %s "NIPQUAD_FMT":%u: %s (%d)\n",
- __FUNCTION__, NIPQUAD(myaddr.sin_addr),
+ last = port;
+ port = xs_next_srcport(transport, sock, port);
+ if (port > last)
+ nloop++;
+ } while (err == -EADDRINUSE && nloop != 2);
+ dprintk("RPC: %s %pI4:%u: %s (%d)\n",
+ __func__, &myaddr.sin_addr,
port, err ? "failed" : "ok", err);
return err;
}
.sin6_family = AF_INET6,
};
struct sockaddr_in6 *sa;
- int err;
- unsigned short port = transport->port;
+ int err, nloop = 0;
+ unsigned short port = xs_get_srcport(transport, sock);
+ unsigned short last;
- if (!transport->xprt.resvport)
- port = 0;
- sa = (struct sockaddr_in6 *)&transport->addr;
+ sa = (struct sockaddr_in6 *)&transport->srcaddr;
myaddr.sin6_addr = sa->sin6_addr;
do {
myaddr.sin6_port = htons(port);
err = kernel_bind(sock, (struct sockaddr *) &myaddr,
sizeof(myaddr));
- if (!transport->xprt.resvport)
+ if (port == 0)
break;
if (err == 0) {
- transport->port = port;
+ transport->srcport = port;
break;
}
- if (port <= xprt_min_resvport)
- port = xprt_max_resvport;
- else
- port--;
- } while (err == -EADDRINUSE && port != transport->port);
- dprintk("RPC: xs_bind6 "NIP6_FMT":%u: %s (%d)\n",
- NIP6(myaddr.sin6_addr), port, err ? "failed" : "ok", err);
+ last = port;
+ port = xs_next_srcport(transport, sock, port);
+ if (port > last)
+ nloop++;
+ } while (err == -EADDRINUSE && nloop != 2);
+ dprintk("RPC: xs_bind6 %pI6:%u: %s (%d)\n",
+ &myaddr.sin6_addr, port, err ? "failed" : "ok", err);
return err;
}
static struct lock_class_key xs_key[2];
static struct lock_class_key xs_slock_key[2];
-static inline void xs_reclassify_socket(struct socket *sock)
+static inline void xs_reclassify_socket4(struct socket *sock)
{
struct sock *sk = sock->sk;
- BUG_ON(sk->sk_lock.owner != NULL);
- switch (sk->sk_family) {
- case AF_INET:
- sock_lock_init_class_and_name(sk, "slock-AF_INET-NFS",
- &xs_slock_key[0], "sk_lock-AF_INET-NFS", &xs_key[0]);
- break;
- case AF_INET6:
- sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFS",
- &xs_slock_key[1], "sk_lock-AF_INET6-NFS", &xs_key[1]);
- break;
+ BUG_ON(sock_owned_by_user(sk));
+ sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC",
+ &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]);
+}
- default:
- BUG();
- }
+static inline void xs_reclassify_socket6(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+
+ BUG_ON(sock_owned_by_user(sk));
+ sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
+ &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
}
#else
-static inline void xs_reclassify_socket(struct socket *sock)
+static inline void xs_reclassify_socket4(struct socket *sock)
+{
+}
+
+static inline void xs_reclassify_socket6(struct socket *sock)
{
}
#endif
write_lock_bh(&sk->sk_callback_lock);
+ xs_save_old_callbacks(transport, sk);
+
sk->sk_user_data = xprt;
- transport->old_data_ready = sk->sk_data_ready;
- transport->old_state_change = sk->sk_state_change;
- transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_udp_data_ready;
sk->sk_write_space = xs_udp_write_space;
+ sk->sk_error_report = xs_error_report;
sk->sk_no_check = UDP_CSUM_NORCV;
sk->sk_allocation = GFP_ATOMIC;
struct socket *sock = transport->sock;
int err, status = -EIO;
- if (xprt->shutdown || !xprt_bound(xprt))
+ if (xprt->shutdown)
goto out;
/* Start by resetting any existing state */
- xs_close(xprt);
+ xs_reset_transport(transport);
- if ((err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) {
+ err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
+ if (err < 0) {
dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
goto out;
}
- xs_reclassify_socket(sock);
+ xs_reclassify_socket4(sock);
if (xs_bind4(transport, sock)) {
sock_release(sock);
goto out;
}
- dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+ dprintk("RPC: worker connecting xprt %p via %s to "
+ "%s (port %s)\n", xprt,
+ xprt->address_strings[RPC_DISPLAY_PROTO],
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT]);
xs_udp_finish_connecting(xprt, sock);
status = 0;
out:
- xprt_wake_pending_tasks(xprt, status);
xprt_clear_connecting(xprt);
+ xprt_wake_pending_tasks(xprt, status);
}
/**
struct socket *sock = transport->sock;
int err, status = -EIO;
- if (xprt->shutdown || !xprt_bound(xprt))
+ if (xprt->shutdown)
goto out;
/* Start by resetting any existing state */
- xs_close(xprt);
+ xs_reset_transport(transport);
- if ((err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) {
+ err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
+ if (err < 0) {
dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
goto out;
}
- xs_reclassify_socket(sock);
+ xs_reclassify_socket6(sock);
if (xs_bind6(transport, sock) < 0) {
sock_release(sock);
goto out;
}
- dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+ dprintk("RPC: worker connecting xprt %p via %s to "
+ "%s (port %s)\n", xprt,
+ xprt->address_strings[RPC_DISPLAY_PROTO],
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT]);
xs_udp_finish_connecting(xprt, sock);
status = 0;
out:
- xprt_wake_pending_tasks(xprt, status);
xprt_clear_connecting(xprt);
+ xprt_wake_pending_tasks(xprt, status);
}
/*
* We need to preserve the port number so the reply cache on the server can
* find our cached RPC replies when we get around to reconnecting.
*/
-static void xs_tcp_reuse_connection(struct rpc_xprt *xprt)
+static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
{
int result;
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct sockaddr any;
dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt);
memset(&any, 0, sizeof(any));
any.sa_family = AF_UNSPEC;
result = kernel_connect(transport->sock, &any, sizeof(any), 0);
- if (result)
+ if (!result)
+ xs_sock_mark_closed(xprt);
+ else
dprintk("RPC: AF_UNSPEC connect return code %d\n",
result);
}
+static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
+{
+ unsigned int state = transport->inet->sk_state;
+
+ if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED)
+ return;
+ if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT))
+ return;
+ xs_abort_connection(xprt, transport);
+}
+
static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
write_lock_bh(&sk->sk_callback_lock);
+ xs_save_old_callbacks(transport, sk);
+
sk->sk_user_data = xprt;
- transport->old_data_ready = sk->sk_data_ready;
- transport->old_state_change = sk->sk_state_change;
- transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_tcp_data_ready;
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
+ sk->sk_error_report = xs_error_report;
sk->sk_allocation = GFP_ATOMIC;
/* socket options */
write_unlock_bh(&sk->sk_callback_lock);
}
+ if (!xprt_bound(xprt))
+ return -ENOTCONN;
+
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
}
/**
- * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint
- * @work: RPC transport to connect
+ * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint
+ * @xprt: RPC transport to connect
+ * @transport: socket transport to connect
+ * @create_sock: function to create a socket of the correct type
*
* Invoked by a work queue tasklet.
*/
-static void xs_tcp_connect_worker4(struct work_struct *work)
+static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
+ struct sock_xprt *transport,
+ struct socket *(*create_sock)(struct rpc_xprt *,
+ struct sock_xprt *))
{
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
- int err, status = -EIO;
+ int status = -EIO;
- if (xprt->shutdown || !xprt_bound(xprt))
+ if (xprt->shutdown)
goto out;
if (!sock) {
- /* start from scratch */
- if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n", -err);
+ clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+ sock = create_sock(xprt, transport);
+ if (IS_ERR(sock)) {
+ status = PTR_ERR(sock);
goto out;
}
- xs_reclassify_socket(sock);
+ } else {
+ int abort_and_exit;
- if (xs_bind4(transport, sock) < 0) {
- sock_release(sock);
- goto out;
- }
- } else
+ abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
+ &xprt->state);
/* "close" the socket, preserving the local port */
- xs_tcp_reuse_connection(xprt);
+ xs_tcp_reuse_connection(xprt, transport);
+
+ if (abort_and_exit)
+ goto out_eagain;
+ }
- dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+ dprintk("RPC: worker connecting xprt %p via %s to "
+ "%s (port %s)\n", xprt,
+ xprt->address_strings[RPC_DISPLAY_PROTO],
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT]);
status = xs_tcp_finish_connecting(xprt, sock);
dprintk("RPC: %p connect status %d connected %d sock state %d\n",
xprt, -status, xprt_connected(xprt),
sock->sk->sk_state);
- if (status < 0) {
- switch (status) {
- case -EINPROGRESS:
- case -EALREADY:
- goto out_clear;
- case -ECONNREFUSED:
- case -ECONNRESET:
- /* retry with existing socket, after a delay */
- break;
- default:
- /* get rid of existing socket, and retry */
- xs_close(xprt);
- break;
- }
+ switch (status) {
+ default:
+ printk("%s: connect returned unhandled error %d\n",
+ __func__, status);
+ case -EADDRNOTAVAIL:
+ /* We're probably in TIME_WAIT. Get rid of existing socket,
+ * and retry
+ */
+ set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+ xprt_force_disconnect(xprt);
+ break;
+ case -ECONNREFUSED:
+ case -ECONNRESET:
+ case -ENETUNREACH:
+ /* retry with existing socket, after a delay */
+ case 0:
+ case -EINPROGRESS:
+ case -EALREADY:
+ xprt_clear_connecting(xprt);
+ return;
+ case -EINVAL:
+ /* Happens, for instance, if the user specified a link
+ * local IPv6 address without a scope-id.
+ */
+ goto out;
}
+out_eagain:
+ status = -EAGAIN;
out:
- xprt_wake_pending_tasks(xprt, status);
-out_clear:
xprt_clear_connecting(xprt);
+ xprt_wake_pending_tasks(xprt, status);
+}
+
+static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt,
+ struct sock_xprt *transport)
+{
+ struct socket *sock;
+ int err;
+
+ /* start from scratch */
+ err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
+ if (err < 0) {
+ dprintk("RPC: can't create TCP transport socket (%d).\n",
+ -err);
+ goto out_err;
+ }
+ xs_reclassify_socket4(sock);
+
+ if (xs_bind4(transport, sock) < 0) {
+ sock_release(sock);
+ goto out_err;
+ }
+ return sock;
+out_err:
+ return ERR_PTR(-EIO);
}
/**
- * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint
+ * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint
* @work: RPC transport to connect
*
* Invoked by a work queue tasklet.
*/
-static void xs_tcp_connect_worker6(struct work_struct *work)
+static void xs_tcp_connect_worker4(struct work_struct *work)
{
struct sock_xprt *transport =
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
- struct socket *sock = transport->sock;
- int err, status = -EIO;
- if (xprt->shutdown || !xprt_bound(xprt))
- goto out;
-
- if (!sock) {
- /* start from scratch */
- if ((err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n", -err);
- goto out;
- }
- xs_reclassify_socket(sock);
+ xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock4);
+}
- if (xs_bind6(transport, sock) < 0) {
- sock_release(sock);
- goto out;
- }
- } else
- /* "close" the socket, preserving the local port */
- xs_tcp_reuse_connection(xprt);
+static struct socket *xs_create_tcp_sock6(struct rpc_xprt *xprt,
+ struct sock_xprt *transport)
+{
+ struct socket *sock;
+ int err;
- dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+ /* start from scratch */
+ err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock);
+ if (err < 0) {
+ dprintk("RPC: can't create TCP transport socket (%d).\n",
+ -err);
+ goto out_err;
+ }
+ xs_reclassify_socket6(sock);
- status = xs_tcp_finish_connecting(xprt, sock);
- dprintk("RPC: %p connect status %d connected %d sock state %d\n",
- xprt, -status, xprt_connected(xprt), sock->sk->sk_state);
- if (status < 0) {
- switch (status) {
- case -EINPROGRESS:
- case -EALREADY:
- goto out_clear;
- case -ECONNREFUSED:
- case -ECONNRESET:
- /* retry with existing socket, after a delay */
- break;
- default:
- /* get rid of existing socket, and retry */
- xs_close(xprt);
- break;
- }
+ if (xs_bind6(transport, sock) < 0) {
+ sock_release(sock);
+ goto out_err;
}
-out:
- xprt_wake_pending_tasks(xprt, status);
-out_clear:
- xprt_clear_connecting(xprt);
+ return sock;
+out_err:
+ return ERR_PTR(-EIO);
+}
+
+/**
+ * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint
+ * @work: RPC transport to connect
+ *
+ * Invoked by a work queue tasklet.
+ */
+static void xs_tcp_connect_worker6(struct work_struct *work)
+{
+ struct sock_xprt *transport =
+ container_of(work, struct sock_xprt, connect_worker.work);
+ struct rpc_xprt *xprt = &transport->xprt;
+
+ xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock6);
}
/**
struct rpc_xprt *xprt = task->tk_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
- if (xprt_test_and_set_connecting(xprt))
- return;
-
- if (transport->sock != NULL) {
+ if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) {
dprintk("RPC: xs_connect delayed xprt %p for %lu "
"seconds\n",
xprt, xprt->reestablish_timeout / HZ);
&transport->connect_worker,
xprt->reestablish_timeout);
xprt->reestablish_timeout <<= 1;
+ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+ xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO)
xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
} else {
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n",
- transport->port,
+ transport->srcport,
xprt->stat.bind_count,
xprt->stat.sends,
xprt->stat.recvs,
idle_time = (long)(jiffies - xprt->last_used) / HZ;
seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n",
- transport->port,
+ transport->srcport,
xprt->stat.bind_count,
xprt->stat.connect_count,
xprt->stat.connect_time,
xprt->stat.bklog_u);
}
+/*
+ * Allocate a bunch of pages for a scratch buffer for the rpc code. The reason
+ * we allocate pages instead doing a kmalloc like rpc_malloc is because we want
+ * to use the server side send routines.
+ */
+static void *bc_malloc(struct rpc_task *task, size_t size)
+{
+ struct page *page;
+ struct rpc_buffer *buf;
+
+ BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer));
+ page = alloc_page(GFP_KERNEL);
+
+ if (!page)
+ return NULL;
+
+ buf = page_address(page);
+ buf->len = PAGE_SIZE;
+
+ return buf->data;
+}
+
+/*
+ * Free the space allocated in the bc_alloc routine
+ */
+static void bc_free(void *buffer)
+{
+ struct rpc_buffer *buf;
+
+ if (!buffer)
+ return;
+
+ buf = container_of(buffer, struct rpc_buffer, data);
+ free_page((unsigned long)buf);
+}
+
+/*
+ * Use the svc_sock to send the callback. Must be called with svsk->sk_mutex
+ * held. Borrows heavily from svc_tcp_sendto and xs_tcp_send_request.
+ */
+static int bc_sendto(struct rpc_rqst *req)
+{
+ int len;
+ struct xdr_buf *xbufp = &req->rq_snd_buf;
+ struct rpc_xprt *xprt = req->rq_xprt;
+ struct sock_xprt *transport =
+ container_of(xprt, struct sock_xprt, xprt);
+ struct socket *sock = transport->sock;
+ unsigned long headoff;
+ unsigned long tailoff;
+
+ /*
+ * Set up the rpc header and record marker stuff
+ */
+ xs_encode_tcp_record_marker(xbufp);
+
+ tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
+ headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
+ len = svc_send_common(sock, xbufp,
+ virt_to_page(xbufp->head[0].iov_base), headoff,
+ xbufp->tail[0].iov_base, tailoff);
+
+ if (len != xbufp->len) {
+ printk(KERN_NOTICE "Error sending entire callback!\n");
+ len = -EAGAIN;
+ }
+
+ return len;
+}
+
+/*
+ * The send routine. Borrows from svc_send
+ */
+static int bc_send_request(struct rpc_task *task)
+{
+ struct rpc_rqst *req = task->tk_rqstp;
+ struct svc_xprt *xprt;
+ struct svc_sock *svsk;
+ u32 len;
+
+ dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
+ /*
+ * Get the server socket associated with this callback xprt
+ */
+ xprt = req->rq_xprt->bc_xprt;
+ svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+ /*
+ * Grab the mutex to serialize data as the connection is shared
+ * with the fore channel
+ */
+ if (!mutex_trylock(&xprt->xpt_mutex)) {
+ rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL);
+ if (!mutex_trylock(&xprt->xpt_mutex))
+ return -EAGAIN;
+ rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task);
+ }
+ if (test_bit(XPT_DEAD, &xprt->xpt_flags))
+ len = -ENOTCONN;
+ else
+ len = bc_sendto(req);
+ mutex_unlock(&xprt->xpt_mutex);
+
+ if (len > 0)
+ len = 0;
+
+ return len;
+}
+
+/*
+ * The close routine. Since this is client initiated, we do nothing
+ */
+
+static void bc_close(struct rpc_xprt *xprt)
+{
+}
+
+/*
+ * The xprt destroy routine. Again, because this connection is client
+ * initiated, we do nothing
+ */
+
+static void bc_destroy(struct rpc_xprt *xprt)
+{
+}
+
static struct rpc_xprt_ops xs_udp_ops = {
.set_buffer_size = xs_udp_set_buffer_size,
.reserve_xprt = xprt_reserve_xprt_cong,
.buf_free = rpc_free,
.send_request = xs_tcp_send_request,
.set_retrans_timeout = xprt_set_retrans_timeout_def,
- .close = xs_close,
+ .close = xs_tcp_close,
.destroy = xs_destroy,
.print_stats = xs_tcp_print_stats,
};
-static struct rpc_xprt *xs_setup_xprt(struct rpc_xprtsock_create *args, unsigned int slot_table_size)
+/*
+ * The rpc_xprt_ops for the server backchannel
+ */
+
+static struct rpc_xprt_ops bc_tcp_ops = {
+ .reserve_xprt = xprt_reserve_xprt,
+ .release_xprt = xprt_release_xprt,
+ .buf_alloc = bc_malloc,
+ .buf_free = bc_free,
+ .send_request = bc_send_request,
+ .set_retrans_timeout = xprt_set_retrans_timeout_def,
+ .close = bc_close,
+ .destroy = bc_destroy,
+ .print_stats = xs_tcp_print_stats,
+};
+
+static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
+ unsigned int slot_table_size)
{
struct rpc_xprt *xprt;
struct sock_xprt *new;
memcpy(&xprt->addr, args->dstaddr, args->addrlen);
xprt->addrlen = args->addrlen;
if (args->srcaddr)
- memcpy(&new->addr, args->srcaddr, args->addrlen);
- new->port = xs_get_random_port();
+ memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
return xprt;
}
+static const struct rpc_timeout xs_udp_default_timeout = {
+ .to_initval = 5 * HZ,
+ .to_maxval = 30 * HZ,
+ .to_increment = 5 * HZ,
+ .to_retries = 5,
+};
+
/**
* xs_setup_udp - Set up transport to use a UDP socket
* @args: rpc transport creation arguments
*
*/
-struct rpc_xprt *xs_setup_udp(struct rpc_xprtsock_create *args)
+static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
{
struct sockaddr *addr = args->dstaddr;
struct rpc_xprt *xprt;
xprt->max_payload = (1U << 16) - (MAX_HEADER << 3);
xprt->bind_timeout = XS_BIND_TO;
- xprt->connect_timeout = XS_UDP_CONN_TO;
xprt->reestablish_timeout = XS_UDP_REEST_TO;
xprt->idle_timeout = XS_IDLE_DISC_TO;
xprt->ops = &xs_udp_ops;
- if (args->timeout)
- xprt->timeout = *args->timeout;
- else
- xprt_set_timeout(&xprt->timeout, 5, 5 * HZ);
+ xprt->timeout = &xs_udp_default_timeout;
switch (addr->sa_family) {
case AF_INET:
INIT_DELAYED_WORK(&transport->connect_worker,
xs_udp_connect_worker4);
- xs_format_ipv4_peer_addresses(xprt);
+ xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
break;
case AF_INET6:
if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
INIT_DELAYED_WORK(&transport->connect_worker,
xs_udp_connect_worker6);
- xs_format_ipv6_peer_addresses(xprt);
+ xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
break;
default:
kfree(xprt);
return ERR_PTR(-EAFNOSUPPORT);
}
- dprintk("RPC: set up transport to address %s\n",
- xprt->address_strings[RPC_DISPLAY_ALL]);
+ if (xprt_bound(xprt))
+ dprintk("RPC: set up xprt to %s (port %s) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
+ else
+ dprintk("RPC: set up xprt to %s (autobind) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
- return xprt;
+ if (try_module_get(THIS_MODULE))
+ return xprt;
+
+ kfree(xprt->slot);
+ kfree(xprt);
+ return ERR_PTR(-EINVAL);
}
+static const struct rpc_timeout xs_tcp_default_timeout = {
+ .to_initval = 60 * HZ,
+ .to_maxval = 60 * HZ,
+ .to_retries = 2,
+};
+
/**
* xs_setup_tcp - Set up transport to use a TCP socket
* @args: rpc transport creation arguments
*
*/
-struct rpc_xprt *xs_setup_tcp(struct rpc_xprtsock_create *args)
+static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
{
struct sockaddr *addr = args->dstaddr;
struct rpc_xprt *xprt;
xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
xprt->bind_timeout = XS_BIND_TO;
- xprt->connect_timeout = XS_TCP_CONN_TO;
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
xprt->idle_timeout = XS_IDLE_DISC_TO;
xprt->ops = &xs_tcp_ops;
-
- if (args->timeout)
- xprt->timeout = *args->timeout;
- else
- xprt_set_timeout(&xprt->timeout, 2, 60 * HZ);
+ xprt->timeout = &xs_tcp_default_timeout;
switch (addr->sa_family) {
case AF_INET:
if (((struct sockaddr_in *)addr)->sin_port != htons(0))
xprt_set_bound(xprt);
- INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4);
- xs_format_ipv4_peer_addresses(xprt);
+ INIT_DELAYED_WORK(&transport->connect_worker,
+ xs_tcp_connect_worker4);
+ xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
break;
case AF_INET6:
if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
xprt_set_bound(xprt);
- INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6);
- xs_format_ipv6_peer_addresses(xprt);
+ INIT_DELAYED_WORK(&transport->connect_worker,
+ xs_tcp_connect_worker6);
+ xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
break;
default:
kfree(xprt);
return ERR_PTR(-EAFNOSUPPORT);
}
- dprintk("RPC: set up transport to address %s\n",
- xprt->address_strings[RPC_DISPLAY_ALL]);
+ if (xprt_bound(xprt))
+ dprintk("RPC: set up xprt to %s (port %s) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
+ else
+ dprintk("RPC: set up xprt to %s (autobind) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
- return xprt;
+
+ if (try_module_get(THIS_MODULE))
+ return xprt;
+
+ kfree(xprt->slot);
+ kfree(xprt);
+ return ERR_PTR(-EINVAL);
+}
+
+/**
+ * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket
+ * @args: rpc transport creation arguments
+ *
+ */
+static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
+{
+ struct sockaddr *addr = args->dstaddr;
+ struct rpc_xprt *xprt;
+ struct sock_xprt *transport;
+ struct svc_sock *bc_sock;
+
+ xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries);
+ if (IS_ERR(xprt))
+ return xprt;
+ transport = container_of(xprt, struct sock_xprt, xprt);
+
+ xprt->prot = IPPROTO_TCP;
+ xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
+ xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
+ xprt->timeout = &xs_tcp_default_timeout;
+
+ /* backchannel */
+ xprt_set_bound(xprt);
+ xprt->bind_timeout = 0;
+ xprt->reestablish_timeout = 0;
+ xprt->idle_timeout = 0;
+
+ /*
+ * The backchannel uses the same socket connection as the
+ * forechannel
+ */
+ xprt->bc_xprt = args->bc_xprt;
+ bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt);
+ bc_sock->sk_bc_xprt = xprt;
+ transport->sock = bc_sock->sk_sock;
+ transport->inet = bc_sock->sk_sk;
+
+ xprt->ops = &bc_tcp_ops;
+
+ switch (addr->sa_family) {
+ case AF_INET:
+ xs_format_peer_addresses(xprt, "tcp",
+ RPCBIND_NETID_TCP);
+ break;
+ case AF_INET6:
+ xs_format_peer_addresses(xprt, "tcp",
+ RPCBIND_NETID_TCP6);
+ break;
+ default:
+ kfree(xprt);
+ return ERR_PTR(-EAFNOSUPPORT);
+ }
+
+ if (xprt_bound(xprt))
+ dprintk("RPC: set up xprt to %s (port %s) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
+ else
+ dprintk("RPC: set up xprt to %s (autobind) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
+
+ /*
+ * Since we don't want connections for the backchannel, we set
+ * the xprt status to connected
+ */
+ xprt_set_connected(xprt);
+
+
+ if (try_module_get(THIS_MODULE))
+ return xprt;
+ kfree(xprt->slot);
+ kfree(xprt);
+ return ERR_PTR(-EINVAL);
}
+static struct xprt_class xs_udp_transport = {
+ .list = LIST_HEAD_INIT(xs_udp_transport.list),
+ .name = "udp",
+ .owner = THIS_MODULE,
+ .ident = XPRT_TRANSPORT_UDP,
+ .setup = xs_setup_udp,
+};
+
+static struct xprt_class xs_tcp_transport = {
+ .list = LIST_HEAD_INIT(xs_tcp_transport.list),
+ .name = "tcp",
+ .owner = THIS_MODULE,
+ .ident = XPRT_TRANSPORT_TCP,
+ .setup = xs_setup_tcp,
+};
+
+static struct xprt_class xs_bc_tcp_transport = {
+ .list = LIST_HEAD_INIT(xs_bc_tcp_transport.list),
+ .name = "tcp NFSv4.1 backchannel",
+ .owner = THIS_MODULE,
+ .ident = XPRT_TRANSPORT_BC_TCP,
+ .setup = xs_setup_bc_tcp,
+};
+
/**
- * init_socket_xprt - set up xprtsock's sysctls
+ * init_socket_xprt - set up xprtsock's sysctls, register with RPC client
*
*/
int init_socket_xprt(void)
sunrpc_table_header = register_sysctl_table(sunrpc_table);
#endif
+ xprt_register_transport(&xs_udp_transport);
+ xprt_register_transport(&xs_tcp_transport);
+ xprt_register_transport(&xs_bc_tcp_transport);
+
return 0;
}
/**
- * cleanup_socket_xprt - remove xprtsock's sysctls
+ * cleanup_socket_xprt - remove xprtsock's sysctls, unregister
*
*/
void cleanup_socket_xprt(void)
sunrpc_table_header = NULL;
}
#endif
+
+ xprt_unregister_transport(&xs_udp_transport);
+ xprt_unregister_transport(&xs_tcp_transport);
+ xprt_unregister_transport(&xs_bc_tcp_transport);
+}
+
+static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
+ unsigned int min, unsigned int max)
+{
+ unsigned long num;
+ int ret;
+
+ if (!val)
+ return -EINVAL;
+ ret = strict_strtoul(val, 0, &num);
+ if (ret == -EINVAL || num < min || num > max)
+ return -EINVAL;
+ *((unsigned int *)kp->arg) = num;
+ return 0;
+}
+
+static int param_set_portnr(const char *val, struct kernel_param *kp)
+{
+ return param_set_uint_minmax(val, kp,
+ RPC_MIN_RESVPORT,
+ RPC_MAX_RESVPORT);
}
+
+static int param_get_portnr(char *buffer, struct kernel_param *kp)
+{
+ return param_get_uint(buffer, kp);
+}
+#define param_check_portnr(name, p) \
+ __param_check(name, p, unsigned int);
+
+module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
+module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);
+
+static int param_set_slot_table_size(const char *val, struct kernel_param *kp)
+{
+ return param_set_uint_minmax(val, kp,
+ RPC_MIN_SLOT_TABLE,
+ RPC_MAX_SLOT_TABLE);
+}
+
+static int param_get_slot_table_size(char *buffer, struct kernel_param *kp)
+{
+ return param_get_uint(buffer, kp);
+}
+#define param_check_slot_table_size(name, p) \
+ __param_check(name, p, unsigned int);
+
+module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries,
+ slot_table_size, 0644);
+module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries,
+ slot_table_size, 0644);
+