#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/xprt.h>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
rqstp->rq_xprt_ctxt = NULL;
dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram_locked(svsk->sk_sk, skb);
}
}
}
break;
}
- return;
}
/*
- * Generic sendto routine
+ * send routine intended to be shared by the fore- and back-channel
*/
-static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
+int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
+ struct page *headpage, unsigned long headoffset,
+ struct page *tailpage, unsigned long tailoffset)
{
- struct svc_sock *svsk =
- container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
- struct socket *sock = svsk->sk_sock;
- int slen;
- union {
- struct cmsghdr hdr;
- long all[SVC_PKTINFO_SPACE / sizeof(long)];
- } buffer;
- struct cmsghdr *cmh = &buffer.hdr;
- int len = 0;
int result;
int size;
struct page **ppage = xdr->pages;
size_t base = xdr->page_base;
unsigned int pglen = xdr->page_len;
unsigned int flags = MSG_MORE;
- RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
+ int slen;
+ int len = 0;
slen = xdr->len;
- if (rqstp->rq_prot == IPPROTO_UDP) {
- struct msghdr msg = {
- .msg_name = &rqstp->rq_addr,
- .msg_namelen = rqstp->rq_addrlen,
- .msg_control = cmh,
- .msg_controllen = sizeof(buffer),
- .msg_flags = MSG_MORE,
- };
-
- svc_set_cmsg_data(rqstp, cmh);
-
- if (sock_sendmsg(sock, &msg, 0) < 0)
- goto out;
- }
-
/* send head */
if (slen == xdr->head[0].iov_len)
flags = 0;
- len = kernel_sendpage(sock, rqstp->rq_respages[0], 0,
+ len = kernel_sendpage(sock, headpage, headoffset,
xdr->head[0].iov_len, flags);
if (len != xdr->head[0].iov_len)
goto out;
base = 0;
ppage++;
}
+
/* send tail */
if (xdr->tail[0].iov_len) {
- result = kernel_sendpage(sock, rqstp->rq_respages[0],
- ((unsigned long)xdr->tail[0].iov_base)
- & (PAGE_SIZE-1),
- xdr->tail[0].iov_len, 0);
-
+ result = kernel_sendpage(sock, tailpage, tailoffset,
+ xdr->tail[0].iov_len, 0);
if (result > 0)
len += result;
}
+
+out:
+ return len;
+}
+
+
+/*
+ * Generic sendto routine
+ */
+static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
+{
+ struct svc_sock *svsk =
+ container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+ struct socket *sock = svsk->sk_sock;
+ union {
+ struct cmsghdr hdr;
+ long all[SVC_PKTINFO_SPACE / sizeof(long)];
+ } buffer;
+ struct cmsghdr *cmh = &buffer.hdr;
+ int len = 0;
+ unsigned long tailoff;
+ unsigned long headoff;
+ RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
+
+ if (rqstp->rq_prot == IPPROTO_UDP) {
+ struct msghdr msg = {
+ .msg_name = &rqstp->rq_addr,
+ .msg_namelen = rqstp->rq_addrlen,
+ .msg_control = cmh,
+ .msg_controllen = sizeof(buffer),
+ .msg_flags = MSG_MORE,
+ };
+
+ svc_set_cmsg_data(rqstp, cmh);
+
+ if (sock_sendmsg(sock, &msg, 0) < 0)
+ goto out;
+ }
+
+ tailoff = ((unsigned long)xdr->tail[0].iov_base) & (PAGE_SIZE-1);
+ headoff = 0;
+ len = svc_send_common(sock, xdr, rqstp->rq_respages[0], headoff,
+ rqstp->rq_respages[0], tailoff);
+
out:
dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n",
svsk, xdr->head[0].iov_base, xdr->head[0].iov_len,
case PF_INET:
len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n",
proto_name,
- &inet_sk(sk)->rcv_saddr,
- inet_sk(sk)->num);
+ &inet_sk(sk)->inet_rcv_saddr,
+ inet_sk(sk)->inet_num);
break;
case PF_INET6:
len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
proto_name,
&inet6_sk(sk)->rcv_saddr,
- inet_sk(sk)->num);
+ inet_sk(sk)->inet_num);
break;
default:
len = snprintf(buf, remaining, "*unknown-%d*\n",
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) {
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) {
dprintk("RPC svc_write_space: someone sleeping on %p\n",
svsk);
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
}
}
dprintk("svc: recvfrom returned error %d\n", -err);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
}
- svc_xprt_received(&svsk->sk_xprt);
return -EAGAIN;
}
len = svc_addr_len(svc_addr(rqstp));
svsk->sk_sk->sk_stamp = skb->tstamp;
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
- /*
- * Maybe more packets - kick another thread ASAP.
- */
- svc_xprt_received(&svsk->sk_xprt);
-
len = skb->len - sizeof(struct udphdr);
rqstp->rq_arg.len = len;
"svc: received unknown control message %d/%d; "
"dropping RPC reply datagram\n",
cmh->cmsg_level, cmh->cmsg_type);
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram_locked(svsk->sk_sk, skb);
return 0;
}
if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
local_bh_enable();
/* checksum error */
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram_locked(svsk->sk_sk, skb);
return 0;
}
local_bh_enable();
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram_locked(svsk->sk_sk, skb);
} else {
/* we can use it in-place */
rqstp->rq_arg.head[0].iov_base = skb->data +
sizeof(struct udphdr);
rqstp->rq_arg.head[0].iov_len = len;
if (skb_checksum_complete(skb)) {
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram_locked(svsk->sk_sk, skb);
return 0;
}
rqstp->rq_xprt_ctxt = skb;
printk("svc: socket %p: no user data\n", sk);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_all(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible_all(sk_sleep(sk));
}
/*
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_all(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible_all(sk_sleep(sk));
}
static void svc_tcp_data_ready(struct sock *sk, int count)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
}
/*
- * Receive data from a TCP socket.
+ * Receive data.
+ * If we haven't gotten the record length yet, get the next four bytes.
+ * Otherwise try to gobble up as much as possible up to the complete
+ * record length.
*/
-static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
+static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
- struct svc_sock *svsk =
- container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
- int len;
- struct kvec *vec;
- int pnum, vlen;
-
- dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
- svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
- test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
- test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
+ int len;
if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
/* sndbuf needs to have room for one request
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- /* Receive data. If we haven't got the record length yet, get
- * the next four bytes. Otherwise try to gobble up as much as
- * possible up to the complete record length.
- */
if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
int want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
struct kvec iov;
if (len < want) {
dprintk("svc: short recvfrom while reading record "
"length (%d of %d)\n", len, want);
- svc_xprt_received(&svsk->sk_xprt);
- return -EAGAIN; /* record header not complete */
+ goto err_again; /* record header not complete */
}
svsk->sk_reclen = ntohl(svsk->sk_reclen);
"per record not supported\n");
goto err_delete;
}
+
svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK;
dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
if (svsk->sk_reclen > serv->sv_max_mesg) {
if (len < svsk->sk_reclen) {
dprintk("svc: incomplete TCP record (%d of %d)\n",
len, svsk->sk_reclen);
- svc_xprt_received(&svsk->sk_xprt);
- return -EAGAIN; /* record not complete */
+ goto err_again; /* record not complete */
}
len = svsk->sk_reclen;
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ return len;
+ error:
+ if (len == -EAGAIN)
+ dprintk("RPC: TCP recv_record got EAGAIN\n");
+ return len;
+ err_delete:
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+ err_again:
+ return -EAGAIN;
+}
+
+static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp,
+ struct rpc_rqst **reqpp, struct kvec *vec)
+{
+ struct rpc_rqst *req = NULL;
+ u32 *p;
+ u32 xid;
+ u32 calldir;
+ int len;
+
+ len = svc_recvfrom(rqstp, vec, 1, 8);
+ if (len < 0)
+ goto error;
+
+ p = (u32 *)rqstp->rq_arg.head[0].iov_base;
+ xid = *p++;
+ calldir = *p;
+
+ if (calldir == 0) {
+ /* REQUEST is the most common case */
+ vec[0] = rqstp->rq_arg.head[0];
+ } else {
+ /* REPLY */
+ if (svsk->sk_bc_xprt)
+ req = xprt_lookup_rqst(svsk->sk_bc_xprt, xid);
+
+ if (!req) {
+ printk(KERN_NOTICE
+ "%s: Got unrecognized reply: "
+ "calldir 0x%x sk_bc_xprt %p xid %08x\n",
+ __func__, ntohl(calldir),
+ svsk->sk_bc_xprt, xid);
+ vec[0] = rqstp->rq_arg.head[0];
+ goto out;
+ }
+
+ memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
+ sizeof(struct xdr_buf));
+ /* copy the xid and call direction */
+ memcpy(req->rq_private_buf.head[0].iov_base,
+ rqstp->rq_arg.head[0].iov_base, 8);
+ vec[0] = req->rq_private_buf.head[0];
+ }
+ out:
+ vec[0].iov_base += 8;
+ vec[0].iov_len -= 8;
+ len = svsk->sk_reclen - 8;
+ error:
+ *reqpp = req;
+ return len;
+}
+
+/*
+ * Receive data from a TCP socket.
+ */
+static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
+{
+ struct svc_sock *svsk =
+ container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
+ int len;
+ struct kvec *vec;
+ int pnum, vlen;
+ struct rpc_rqst *req = NULL;
+
+ dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
+ svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
+ test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
+ test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
+
+ len = svc_tcp_recv_record(svsk, rqstp);
+ if (len < 0)
+ goto error;
+
vec = rqstp->rq_vec;
vec[0] = rqstp->rq_arg.head[0];
vlen = PAGE_SIZE;
+
+ /*
+ * We have enough data for the whole tcp record. Let's try and read the
+ * first 8 bytes to get the xid and the call direction. We can use this
+ * to figure out if this is a call or a reply to a callback. If
+ * sk_reclen is < 8 (xid and calldir), then this is a malformed packet.
+ * In that case, don't bother with the calldir and just read the data.
+ * It will be rejected in svc_process.
+ */
+ if (len >= 8) {
+ len = svc_process_calldir(svsk, rqstp, &req, vec);
+ if (len < 0)
+ goto err_again;
+ vlen -= 8;
+ }
+
pnum = 1;
while (vlen < len) {
- vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]);
+ vec[pnum].iov_base = (req) ?
+ page_address(req->rq_private_buf.pages[pnum - 1]) :
+ page_address(rqstp->rq_pages[pnum]);
vec[pnum].iov_len = PAGE_SIZE;
pnum++;
vlen += PAGE_SIZE;
/* Now receive data */
len = svc_recvfrom(rqstp, vec, pnum, len);
if (len < 0)
- goto error;
+ goto err_again;
+
+ /*
+ * Account for the 8 bytes we read earlier
+ */
+ len += 8;
+ if (req) {
+ xprt_complete_rqst(req->rq_task, len);
+ len = 0;
+ goto out;
+ }
dprintk("svc: TCP complete record (%d bytes)\n", len);
rqstp->rq_arg.len = len;
rqstp->rq_arg.page_base = 0;
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
+out:
/* Reset TCP read info */
svsk->sk_reclen = 0;
svsk->sk_tcplen = 0;
svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
- svc_xprt_received(&svsk->sk_xprt);
if (serv->sv_stats)
serv->sv_stats->nettcpcnt++;
return len;
- err_delete:
- set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
- return -EAGAIN;
-
- error:
+err_again:
if (len == -EAGAIN) {
dprintk("RPC: TCP recvfrom got EAGAIN\n");
- svc_xprt_received(&svsk->sk_xprt);
- } else {
+ return len;
+ }
+error:
+ if (len != -EAGAIN) {
printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
svsk->sk_xprt.xpt_server->sv_name, -len);
- goto err_delete;
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
}
-
- return len;
+ return -EAGAIN;
}
/*
/* Register socket with portmapper */
if (*errp >= 0 && pmap_register)
*errp = svc_register(serv, inet->sk_family, inet->sk_protocol,
- ntohs(inet_sk(inet)->sport));
+ ntohs(inet_sk(inet)->inet_sport));
if (*errp < 0) {
kfree(svsk);
if (!so)
return err;
- if (so->sk->sk_family != AF_INET)
+ if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
err = -EAFNOSUPPORT;
else if (so->sk->sk_protocol != IPPROTO_TCP &&
so->sk->sk_protocol != IPPROTO_UDP)
sk->sk_data_ready = svsk->sk_odata;
sk->sk_write_space = svsk->sk_owspace;
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff