#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
*/
*/
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
},
.data = &xs_tcp_fin_timeout,
.maxlen = sizeof(xs_tcp_fin_timeout),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = sysctl_jiffies
- },
- {
- .ctl_name = 0,
+ .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
/*
- * 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
#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,
- const char *protocol,
- const char *netid)
+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, "%pI4", &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;
-
- xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;
+ struct sockaddr *sap = xs_addr(xprt);
+ struct sockaddr_in6 *sin6;
+ struct sockaddr_in *sin;
+ char buf[128];
- buf = kzalloc(48, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 48, "addr=%pI4 port=%u proto=%s",
- &addr->sin_addr.s_addr,
- ntohs(addr->sin_port),
- protocol);
- }
- xprt->address_strings[RPC_DISPLAY_ALL] = buf;
-
- 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));
- }
- xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
- buf = kzalloc(30, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 30, "%pI4.%u.%u",
- &addr->sin_addr.s_addr,
- ntohs(addr->sin_port) >> 8,
- ntohs(addr->sin_port) & 0xff);
+ 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_UNIVERSAL_ADDR] = buf;
-
- xprt->address_strings[RPC_DISPLAY_NETID] = netid;
+ xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
}
-static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt,
- const char *protocol,
- const char *netid)
+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, "%pI6",&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;
+ snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
+ xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
+}
+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(64, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 64, "addr=%pI6 port=%u proto=%s",
- &addr->sin6_addr,
- ntohs(addr->sin6_port),
- protocol);
- }
- xprt->address_strings[RPC_DISPLAY_ALL] = buf;
-
- buf = kzalloc(36, GFP_KERNEL);
- if (buf)
- snprintf(buf, 36, "%pi6", &addr->sin6_addr);
-
- xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
-
- buf = kzalloc(8, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 8, "%4hx",
- ntohs(addr->sin6_port));
- }
- xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
- buf = kzalloc(50, GFP_KERNEL);
- if (buf) {
- snprintf(buf, 50, "%pI6.%u.%u",
- &addr->sin6_addr,
- ntohs(addr->sin6_port) >> 8,
- ntohs(addr->sin6_port) & 0xff);
- }
- xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = 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]);
- xprt->address_strings[RPC_DISPLAY_NETID] = netid;
+ xs_format_common_peer_ports(xprt);
}
static void xs_free_peer_addresses(struct rpc_xprt *xprt)
xdr->len - req->rq_bytes_sent, status);
if (status >= 0) {
- task->tk_bytes_sent += status;
+ 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;
}
- if (!transport->sock)
- goto out;
switch (status) {
case -ENOTSOCK:
* prompts ECONNREFUSED. */
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
}
-out:
+
return status;
}
/* 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;
status = -EAGAIN;
break;
}
- if (!transport->sock)
- goto out;
switch (status) {
case -ENOTSOCK:
case -ENOTCONN:
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
}
-out:
+
return status;
}
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);
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_force_disconnect(xprt);
return;
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 */
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;
do {
*/
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->port;
+ unsigned short port = transport->srcport;
if (port == 0 && transport->xprt.resvport)
port = xs_get_random_port();
static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port)
{
- if (transport->port != 0)
- transport->port = 0;
+ if (transport->srcport != 0)
+ transport->srcport = 0;
if (!transport->xprt.resvport)
return 0;
if (port <= xprt_min_resvport || port > xprt_max_resvport)
unsigned short port = xs_get_srcport(transport, sock);
unsigned short last;
- sa = (struct sockaddr_in *)&transport->addr;
+ sa = (struct sockaddr_in *)&transport->srcaddr;
myaddr.sin_addr = sa->sin_addr;
do {
myaddr.sin_port = htons(port);
if (port == 0)
break;
if (err == 0) {
- transport->port = port;
+ transport->srcport = port;
break;
}
last = port;
unsigned short port = xs_get_srcport(transport, sock);
unsigned short last;
- sa = (struct sockaddr_in6 *)&transport->addr;
+ sa = (struct sockaddr_in6 *)&transport->srcaddr;
myaddr.sin6_addr = sa->sin6_addr;
do {
myaddr.sin6_port = htons(port);
if (port == 0)
break;
if (err == 0) {
- transport->port = port;
+ transport->srcport = port;
break;
}
last = port;
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;
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;
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",
*/
set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
xprt_force_disconnect(xprt);
+ break;
case -ECONNREFUSED:
case -ECONNRESET:
case -ENETUNREACH:
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;
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 {
}
}
-static void xs_tcp_connect(struct rpc_task *task)
-{
- struct rpc_xprt *xprt = task->tk_xprt;
-
- /* Exit if we need to wait for socket shutdown to complete */
- if (test_bit(XPRT_CLOSING, &xprt->state))
- return;
- xs_connect(task);
-}
-
/**
* xs_udp_print_stats - display UDP socket-specifc stats
* @xprt: rpc_xprt struct containing statistics
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,
.release_xprt = xs_tcp_release_xprt,
.rpcbind = rpcb_getport_async,
.set_port = xs_set_port,
- .connect = xs_tcp_connect,
+ .connect = xs_connect,
.buf_alloc = rpc_malloc,
.buf_free = rpc_free,
.send_request = xs_tcp_send_request,
.print_stats = xs_tcp_print_stats,
};
+/*
+ * 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)
{
memcpy(&xprt->addr, args->dstaddr, args->addrlen);
xprt->addrlen = args->addrlen;
if (args->srcaddr)
- memcpy(&new->addr, args->srcaddr, args->addrlen);
+ memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
return 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;
INIT_DELAYED_WORK(&transport->connect_worker,
xs_udp_connect_worker4);
- xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
+ 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, "udp", RPCBIND_NETID_UDP6);
+ 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]);
if (try_module_get(THIS_MODULE))
return 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;
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, "tcp", RPCBIND_NETID_TCP);
+ 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, "tcp", RPCBIND_NETID_TCP6);
+ 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]);
+
if (try_module_get(THIS_MODULE))
return 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 = IPPROTO_UDP,
+ .ident = XPRT_TRANSPORT_UDP,
.setup = xs_setup_udp,
};
.list = LIST_HEAD_INIT(xs_tcp_transport.list),
.name = "tcp",
.owner = THIS_MODULE,
- .ident = IPPROTO_TCP,
+ .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, register with RPC client
*
xprt_register_transport(&xs_udp_transport);
xprt_register_transport(&xs_tcp_transport);
+ xprt_register_transport(&xs_bc_tcp_transport);
return 0;
}
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);
+