diff options
Diffstat (limited to 'net')
| -rw-r--r-- | net/sunrpc/clnt.c | 29 | ||||
| -rw-r--r-- | net/sunrpc/rpcb_clnt.c | 97 | ||||
| -rw-r--r-- | net/sunrpc/svc.c | 2 | ||||
| -rw-r--r-- | net/sunrpc/svcsock.c | 336 | ||||
| -rw-r--r-- | net/sunrpc/xdr.c | 19 | ||||
| -rw-r--r-- | net/sunrpc/xprtsock.c | 435 |
6 files changed, 725 insertions, 193 deletions
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8d83f9d4871..b84d7395535 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -13,10 +13,6 @@ * and need to be refreshed, or when a packet was damaged in transit. * This may be have to be moved to the VFS layer. * - * NB: BSD uses a more intelligent approach to guessing when a request - * or reply has been lost by keeping the RTO estimate for each procedure. - * We currently make do with a constant timeout value. - * * Copyright (C) 1992,1993 Rick Sladkey <jrs@world.std.com> * Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de> */ @@ -32,7 +28,9 @@ #include <linux/slab.h> #include <linux/utsname.h> #include <linux/workqueue.h> +#include <linux/in.h> #include <linux/in6.h> +#include <linux/un.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/rpc_pipe_fs.h> @@ -298,22 +296,27 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) * up a string representation of the passed-in address. */ if (args->servername == NULL) { + struct sockaddr_un *sun = + (struct sockaddr_un *)args->address; + struct sockaddr_in *sin = + (struct sockaddr_in *)args->address; + struct sockaddr_in6 *sin6 = + (struct sockaddr_in6 *)args->address; + servername[0] = '\0'; switch (args->address->sa_family) { - case AF_INET: { - struct sockaddr_in *sin = - (struct sockaddr_in *)args->address; + case AF_LOCAL: + snprintf(servername, sizeof(servername), "%s", + sun->sun_path); + break; + case AF_INET: snprintf(servername, sizeof(servername), "%pI4", &sin->sin_addr.s_addr); break; - } - case AF_INET6: { - struct sockaddr_in6 *sin = - (struct sockaddr_in6 *)args->address; + case AF_INET6: snprintf(servername, sizeof(servername), "%pI6", - &sin->sin6_addr); + &sin6->sin6_addr); break; - } default: /* caller wants default server name, but * address family isn't recognized. */ diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c652e4cc9fe..9a80a922c52 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -16,6 +16,7 @@ #include <linux/types.h> #include <linux/socket.h> +#include <linux/un.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/kernel.h> @@ -32,6 +33,8 @@ # define RPCDBG_FACILITY RPCDBG_BIND #endif +#define RPCBIND_SOCK_PATHNAME "/var/run/rpcbind.sock" + #define RPCBIND_PROGRAM (100000u) #define RPCBIND_PORT (111u) @@ -158,20 +161,69 @@ static void rpcb_map_release(void *data) kfree(map); } -static const struct sockaddr_in rpcb_inaddr_loopback = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_LOOPBACK), - .sin_port = htons(RPCBIND_PORT), -}; +/* + * Returns zero on success, otherwise a negative errno value + * is returned. + */ +static int rpcb_create_local_unix(void) +{ + static const struct sockaddr_un rpcb_localaddr_rpcbind = { + .sun_family = AF_LOCAL, + .sun_path = RPCBIND_SOCK_PATHNAME, + }; + struct rpc_create_args args = { + .net = &init_net, + .protocol = XPRT_TRANSPORT_LOCAL, + .address = (struct sockaddr *)&rpcb_localaddr_rpcbind, + .addrsize = sizeof(rpcb_localaddr_rpcbind), + .servername = "localhost", + .program = &rpcb_program, + .version = RPCBVERS_2, + .authflavor = RPC_AUTH_NULL, + }; + struct rpc_clnt *clnt, *clnt4; + int result = 0; + + /* + * Because we requested an RPC PING at transport creation time, + * this works only if the user space portmapper is rpcbind, and + * it's listening on AF_LOCAL on the named socket. + */ + clnt = rpc_create(&args); + if (IS_ERR(clnt)) { + dprintk("RPC: failed to create AF_LOCAL rpcbind " + "client (errno %ld).\n", PTR_ERR(clnt)); + result = -PTR_ERR(clnt); + goto out; + } + + clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4); + if (IS_ERR(clnt4)) { + dprintk("RPC: failed to bind second program to " + "rpcbind v4 client (errno %ld).\n", + PTR_ERR(clnt4)); + clnt4 = NULL; + } + + /* Protected by rpcb_create_local_mutex */ + rpcb_local_clnt = clnt; + rpcb_local_clnt4 = clnt4; -static DEFINE_MUTEX(rpcb_create_local_mutex); +out: + return result; +} /* * Returns zero on success, otherwise a negative errno value * is returned. */ -static int rpcb_create_local(void) +static int rpcb_create_local_net(void) { + static const struct sockaddr_in rpcb_inaddr_loopback = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + .sin_port = htons(RPCBIND_PORT), + }; struct rpc_create_args args = { .net = &init_net, .protocol = XPRT_TRANSPORT_TCP, @@ -186,13 +238,6 @@ static int rpcb_create_local(void) struct rpc_clnt *clnt, *clnt4; int result = 0; - if (rpcb_local_clnt) - return result; - - mutex_lock(&rpcb_create_local_mutex); - if (rpcb_local_clnt) - goto out; - clnt = rpc_create(&args); if (IS_ERR(clnt)) { dprintk("RPC: failed to create local rpcbind " @@ -214,10 +259,34 @@ static int rpcb_create_local(void) clnt4 = NULL; } + /* Protected by rpcb_create_local_mutex */ rpcb_local_clnt = clnt; rpcb_local_clnt4 = clnt4; out: + return result; +} + +/* + * Returns zero on success, otherwise a negative errno value + * is returned. + */ +static int rpcb_create_local(void) +{ + static DEFINE_MUTEX(rpcb_create_local_mutex); + int result = 0; + + if (rpcb_local_clnt) + return result; + + mutex_lock(&rpcb_create_local_mutex); + if (rpcb_local_clnt) + goto out; + + if (rpcb_create_local_unix() != 0) + result = rpcb_create_local_net(); + +out: mutex_unlock(&rpcb_create_local_mutex); return result; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 08e05a8ce02..2b90292e950 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -942,6 +942,8 @@ static void svc_unregister(const struct svc_serv *serv) if (progp->pg_vers[i]->vs_hidden) continue; + dprintk("svc: attempting to unregister %sv%u\n", + progp->pg_name, i); __svc_unregister(progp->pg_prog, i, progp->pg_name); } } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index b7d435c3f19..af04f779ce9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -387,6 +387,33 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, return len; } +static int svc_partial_recvfrom(struct svc_rqst *rqstp, + struct kvec *iov, int nr, + int buflen, unsigned int base) +{ + size_t save_iovlen; + void __user *save_iovbase; + unsigned int i; + int ret; + + if (base == 0) + return svc_recvfrom(rqstp, iov, nr, buflen); + + for (i = 0; i < nr; i++) { + if (iov[i].iov_len > base) + break; + base -= iov[i].iov_len; + } + save_iovlen = iov[i].iov_len; + save_iovbase = iov[i].iov_base; + iov[i].iov_len -= base; + iov[i].iov_base += base; + ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen); + iov[i].iov_len = save_iovlen; + iov[i].iov_base = save_iovbase; + return ret; +} + /* * Set socket snd and rcv buffer lengths */ @@ -409,7 +436,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, lock_sock(sock->sk); sock->sk->sk_sndbuf = snd * 2; sock->sk->sk_rcvbuf = rcv * 2; - sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK; sock->sk->sk_write_space(sock->sk); release_sock(sock->sk); #endif @@ -884,6 +910,56 @@ failed: return NULL; } +static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp) +{ + unsigned int i, len, npages; + + if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + return 0; + len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + for (i = 0; i < npages; i++) { + if (rqstp->rq_pages[i] != NULL) + put_page(rqstp->rq_pages[i]); + BUG_ON(svsk->sk_pages[i] == NULL); + rqstp->rq_pages[i] = svsk->sk_pages[i]; + svsk->sk_pages[i] = NULL; + } + rqstp->rq_arg.head[0].iov_base = page_address(rqstp->rq_pages[0]); + return len; +} + +static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp) +{ + unsigned int i, len, npages; + + if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + return; + len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + for (i = 0; i < npages; i++) { + svsk->sk_pages[i] = rqstp->rq_pages[i]; + rqstp->rq_pages[i] = NULL; + } +} + +static void svc_tcp_clear_pages(struct svc_sock *svsk) +{ + unsigned int i, len, npages; + + if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + goto out; + len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + for (i = 0; i < npages; i++) { + BUG_ON(svsk->sk_pages[i] == NULL); + put_page(svsk->sk_pages[i]); + svsk->sk_pages[i] = NULL; + } +out: + svsk->sk_tcplen = 0; +} + /* * Receive data. * If we haven't gotten the record length yet, get the next four bytes. @@ -893,31 +969,15 @@ failed: static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) { struct svc_serv *serv = svsk->sk_xprt.xpt_server; + unsigned int want; int len; - if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags)) - /* sndbuf needs to have room for one request - * per thread, otherwise we can stall even when the - * network isn't a bottleneck. - * - * We count all threads rather than threads in a - * particular pool, which provides an upper bound - * on the number of threads which will access the socket. - * - * rcvbuf just needs to be able to hold a few requests. - * Normally they will be removed from the queue - * as soon a a complete request arrives. - */ - svc_sock_setbufsize(svsk->sk_sock, - (serv->sv_nrthreads+3) * serv->sv_max_mesg, - 3 * serv->sv_max_mesg); - clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) { - int want = sizeof(rpc_fraghdr) - svsk->sk_tcplen; struct kvec iov; + want = sizeof(rpc_fraghdr) - svsk->sk_tcplen; iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen; iov.iov_len = want; if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0) @@ -927,7 +987,7 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) if (len < want) { dprintk("svc: short recvfrom while reading record " "length (%d of %d)\n", len, want); - goto err_again; /* record header not complete */ + return -EAGAIN; } svsk->sk_reclen = ntohl(svsk->sk_reclen); @@ -954,83 +1014,75 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) } } - /* Check whether enough data is available */ - len = svc_recv_available(svsk); - if (len < 0) - goto error; + if (svsk->sk_reclen < 8) + goto err_delete; /* client is nuts. */ - if (len < svsk->sk_reclen) { - dprintk("svc: incomplete TCP record (%d of %d)\n", - len, svsk->sk_reclen); - 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"); +error: + dprintk("RPC: TCP recv_record got %d\n", len); return len; - err_delete: +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) +static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) { + struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt; 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; + struct kvec *src, *dst; + __be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base; + __be32 xid; + __be32 calldir; - 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 */ - struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt; - - if (bc_xprt) - req = xprt_lookup_rqst(bc_xprt, xid); - - if (!req) { - printk(KERN_NOTICE - "%s: Got unrecognized reply: " - "calldir 0x%x xpt_bc_xprt %p xid %08x\n", - __func__, ntohl(calldir), - bc_xprt, xid); - vec[0] = rqstp->rq_arg.head[0]; - goto out; - } + if (bc_xprt) + req = xprt_lookup_rqst(bc_xprt, xid); - 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]; + if (!req) { + printk(KERN_NOTICE + "%s: Got unrecognized reply: " + "calldir 0x%x xpt_bc_xprt %p xid %08x\n", + __func__, ntohl(calldir), + bc_xprt, xid); + return -EAGAIN; } - out: - vec[0].iov_base += 8; - vec[0].iov_len -= 8; - len = svsk->sk_reclen - 8; - error: - *reqpp = req; - return len; + + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); + /* + * XXX!: cheating for now! Only copying HEAD. + * But we know this is good enough for now (in fact, for any + * callback reply in the forseeable future). + */ + dst = &req->rq_private_buf.head[0]; + src = &rqstp->rq_arg.head[0]; + if (dst->iov_len < src->iov_len) + return -EAGAIN; /* whatever; just giving up. */ + memcpy(dst->iov_base, src->iov_base, src->iov_len); + xprt_complete_rqst(req->rq_task, svsk->sk_reclen); + rqstp->rq_arg.len = 0; + return 0; } +static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len) +{ + int i = 0; + int t = 0; + + while (t < len) { + vec[i].iov_base = page_address(pages[i]); + vec[i].iov_len = PAGE_SIZE; + i++; + t += PAGE_SIZE; + } + return i; +} + + /* * Receive data from a TCP socket. */ @@ -1041,8 +1093,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) struct svc_serv *serv = svsk->sk_xprt.xpt_server; int len; struct kvec *vec; - int pnum, vlen; - struct rpc_rqst *req = NULL; + unsigned int want, base; + __be32 *p; + __be32 calldir; + int pnum; dprintk("svc: tcp_recv %p data %d conn %d close %d\n", svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags), @@ -1053,87 +1107,73 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (len < 0) goto error; + base = svc_tcp_restore_pages(svsk, rqstp); + want = svsk->sk_reclen - base; + 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 = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], + svsk->sk_reclen); - pnum = 1; - while (vlen < len) { - 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; - } rqstp->rq_respages = &rqstp->rq_pages[pnum]; /* Now receive data */ - len = svc_recvfrom(rqstp, vec, pnum, len); - if (len < 0) - 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; + len = svc_partial_recvfrom(rqstp, vec, pnum, want, base); + if (len >= 0) + svsk->sk_tcplen += len; + if (len != want) { + if (len < 0 && len != -EAGAIN) + goto err_other; + svc_tcp_save_pages(svsk, rqstp); + dprintk("svc: incomplete TCP record (%d of %d)\n", + svsk->sk_tcplen, svsk->sk_reclen); + goto err_noclose; } - dprintk("svc: TCP complete record (%d bytes)\n", len); - rqstp->rq_arg.len = len; + + rqstp->rq_arg.len = svsk->sk_reclen; rqstp->rq_arg.page_base = 0; - if (len <= rqstp->rq_arg.head[0].iov_len) { - rqstp->rq_arg.head[0].iov_len = len; + if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { + rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; rqstp->rq_arg.page_len = 0; - } else { - rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len; - } + } else + rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; -out: + p = (__be32 *)rqstp->rq_arg.head[0].iov_base; + calldir = p[1]; + if (calldir) + len = receive_cb_reply(svsk, rqstp); + /* Reset TCP read info */ svsk->sk_reclen = 0; svsk->sk_tcplen = 0; + /* If we have more data, signal svc_xprt_enqueue() to try again */ + if (svc_recv_available(svsk) > sizeof(rpc_fraghdr)) + set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + + if (len < 0) + goto error; svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt); if (serv->sv_stats) serv->sv_stats->nettcpcnt++; - return len; + dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len); + return rqstp->rq_arg.len; -err_again: - if (len == -EAGAIN) { - dprintk("RPC: TCP recvfrom got EAGAIN\n"); - return len; - } error: - if (len != -EAGAIN) { - printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", - svsk->sk_xprt.xpt_server->sv_name, -len); - set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); - } + if (len != -EAGAIN) + goto err_other; + dprintk("RPC: TCP recvfrom got EAGAIN\n"); return -EAGAIN; +err_other: + printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", + svsk->sk_xprt.xpt_server->sv_name, -len); + set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); +err_noclose: + return -EAGAIN; /* record not complete */ } /* @@ -1304,18 +1344,10 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) svsk->sk_reclen = 0; svsk->sk_tcplen = 0; + memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; - /* initialise setting must have enough space to - * receive and respond to one request. - * svc_tcp_recvfrom will re-adjust if necessary - */ - svc_sock_setbufsize(svsk->sk_sock, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg); - - set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); if (sk->sk_state != TCP_ESTABLISHED) set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); @@ -1379,8 +1411,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Initialize the socket */ if (sock->type == SOCK_DGRAM) svc_udp_init(svsk, serv); - else + else { + /* initialise setting must have enough space to + * receive and respond to one request. + */ + svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg, + 4 * serv->sv_max_mesg); svc_tcp_init(svsk, serv); + } dprintk("svc: svc_setup_socket created %p (inet %p)\n", svsk, svsk->sk_sk); @@ -1562,8 +1600,10 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) svc_sock_detach(xprt); - if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) + if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) { + svc_tcp_clear_pages(svsk); kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR); + } } /* diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 679cd674b81..f008c14ad34 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -638,6 +638,25 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) } EXPORT_SYMBOL_GPL(xdr_init_decode); +/** + * xdr_init_decode - Initialize an xdr_stream for decoding data. + * @xdr: pointer to xdr_stream struct + * @buf: pointer to XDR buffer from which to decode data + * @pages: list of pages to decode into + * @len: length in bytes of buffer in pages + */ +void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, + struct page **pages, unsigned int len) +{ + memset(buf, 0, sizeof(*buf)); + buf->pages = pages; + buf->page_len = len; + buf->buflen = len; + buf->len = len; + xdr_init_decode(xdr, buf, NULL); +} +EXPORT_SYMBOL_GPL(xdr_init_decode_pages); + static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { __be32 *p = xdr->p; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index bf005d3c65e..72abb735893 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -19,6 +19,7 @@ */ #include <linux/types.h> +#include <linux/string.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/capability.h> @@ -28,6 +29,7 @@ #include <linux/in.h> #include <linux/net.h> #include <linux/mm.h> +#include <linux/un.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/sunrpc/clnt.h> @@ -45,6 +47,9 @@ #include <net/tcp.h> #include "sunrpc.h" + +static void xs_close(struct rpc_xprt *xprt); + /* * xprtsock tunables */ @@ -261,6 +266,11 @@ static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt) return (struct sockaddr *) &xprt->addr; } +static inline struct sockaddr_un *xs_addr_un(struct rpc_xprt *xprt) +{ + return (struct sockaddr_un *) &xprt->addr; +} + static inline struct sockaddr_in *xs_addr_in(struct rpc_xprt *xprt) { return (struct sockaddr_in *) &xprt->addr; @@ -276,23 +286,34 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) struct sockaddr *sap = xs_addr(xprt); struct sockaddr_in6 *sin6; struct sockaddr_in *sin; + struct sockaddr_un *sun; char buf[128]; - (void)rpc_ntop(sap, buf, sizeof(buf)); - xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - switch (sap->sa_family) { + case AF_LOCAL: + sun = xs_addr_un(xprt); + strlcpy(buf, sun->sun_path, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = + kstrdup(buf, GFP_KERNEL); + break; case AF_INET: + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = + kstrdup(buf, GFP_KERNEL); sin = xs_addr_in(xprt); snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr)); break; case AF_INET6: + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = + kstrdup(buf, GFP_KERNEL); sin6 = xs_addr_in6(xprt); snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); break; default: BUG(); } + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); } @@ -495,6 +516,70 @@ static int xs_nospace(struct rpc_task *task) return ret; } +/* + * Construct a stream transport record marker in @buf. + */ +static inline void xs_encode_stream_record_marker(struct xdr_buf *buf) +{ + u32 reclen = buf->len - sizeof(rpc_fraghdr); + rpc_fraghdr *base = buf->head[0].iov_base; + *base = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | reclen); +} + +/** + * xs_local_send_request - write an RPC request to an AF_LOCAL socket + * @task: RPC task that manages the state of an RPC request + * + * Return values: + * 0: The request has been sent + * EAGAIN: The socket was blocked, please call again later to + * complete the request + * ENOTCONN: Caller needs to invoke connect logic then call again + * other: Some other error occured, the request was not sent + */ +static int xs_local_send_request(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); + struct xdr_buf *xdr = &req->rq_snd_buf; + int status; + + xs_encode_stream_record_marker(&req->rq_snd_buf); + + xs_pktdump("packet data:", + req->rq_svec->iov_base, req->rq_svec->iov_len); + + status = xs_sendpages(transport->sock, NULL, 0, + xdr, req->rq_bytes_sent); + dprintk("RPC: %s(%u) = %d\n", + __func__, xdr->len - req->rq_bytes_sent, status); + if (likely(status >= 0)) { + req->rq_bytes_sent += status; + req->rq_xmit_bytes_sent += status; + if (likely(req->rq_bytes_sent >= req->rq_slen)) { + req->rq_bytes_sent = 0; + return 0; + } + status = -EAGAIN; + } + + switch (status) { + case -EAGAIN: + status = xs_nospace(task); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); + case -EPIPE: + xs_close(xprt); + status = -ENOTCONN; + } + + return status; +} + /** * xs_udp_send_request - write an RPC request to a UDP socket * @task: address of RPC task that manages the state of an RPC request @@ -574,13 +659,6 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) 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); - rpc_fraghdr *base = buf->head[0].iov_base; - *base = htonl(RPC_LAST_STREAM_FRAGMENT | reclen); -} - /** * xs_tcp_send_request - write an RPC request to a TCP socket * @task: address of RPC task that manages the state of an RPC request @@ -603,7 +681,7 @@ static int xs_tcp_send_request(struct rpc_task *task) struct xdr_buf *xdr = &req->rq_snd_buf; int status; - xs_encode_tcp_record_marker(&req->rq_snd_buf); + xs_encode_stream_record_marker(&req->rq_snd_buf); xs_pktdump("packet data:", req->rq_svec->iov_base, @@ -785,6 +863,88 @@ static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) return (struct rpc_xprt *) sk->sk_user_data; } +static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) +{ + struct xdr_skb_reader desc = { + .skb = skb, + .offset = sizeof(rpc_fraghdr), + .count = skb->len - sizeof(rpc_fraghdr), + }; + + if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0) + return -1; + if (desc.count) + return -1; + return 0; +} + +/** + * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets + * @sk: socket with data to read + * @len: how much data to read + * + * Currently this assumes we can read the whole reply in a single gulp. + */ +static void xs_local_data_ready(struct sock *sk, int len) +{ + struct rpc_task *task; + struct rpc_xprt *xprt; + struct rpc_rqst *rovr; + struct sk_buff *skb; + int err, repsize, copied; + u32 _xid; + __be32 *xp; + + read_lock_bh(&sk->sk_callback_lock); + dprintk("RPC: %s...\n", __func__); + xprt = xprt_from_sock(sk); + if (xprt == NULL) + goto out; + + skb = skb_recv_datagram(sk, 0, 1, &err); + if (skb == NULL) + goto out; + + if (xprt->shutdown) + goto dropit; + + repsize = skb->len - sizeof(rpc_fraghdr); + if (repsize < 4) { + dprintk("RPC: impossible RPC reply size %d\n", repsize); + goto dropit; + } + + /* Copy the XID from the skb... */ + xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid); + if (xp == NULL) + goto dropit; + + /* Look up and lock the request corresponding to the given XID */ + spin_lock(&xprt->transport_lock); + rovr = xprt_lookup_rqst(xprt, *xp); + if (!rovr) + goto out_unlock; + task = rovr->rq_task; + + copied = rovr->rq_private_buf.buflen; + if (copied > repsize) + copied = repsize; + + if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) { + dprintk("RPC: sk_buff copy failed\n"); + goto out_unlock; + } + + xprt_complete_rqst(task, copied); + + out_unlock: + spin_unlock(&xprt->transport_lock); + dropit: + skb_free_datagram(sk, skb); + out: + read_unlock_bh(&sk->sk_callback_lock); +} + /** * xs_udp_data_ready - "data ready" callback for UDP sockets * @sk: socket with data to read @@ -1344,7 +1504,6 @@ static void xs_tcp_state_change(struct sock *sk) case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ xprt_force_disconnect(xprt); - case TCP_SYN_SENT: xprt->connect_cookie++; case TCP_CLOSING: /* @@ -1571,11 +1730,31 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) return err; } +/* + * We don't support autobind on AF_LOCAL sockets + */ +static void xs_local_rpcbind(struct rpc_task *task) +{ + xprt_set_bound(task->tk_xprt); +} + +static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port) +{ +} #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key xs_key[2]; static struct lock_class_key xs_slock_key[2]; +static inline void xs_reclassify_socketu(struct socket *sock) +{ + struct sock *sk = sock->sk; + + BUG_ON(sock_owned_by_user(sk)); + sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC", + &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]); +} + static inline void xs_reclassify_socket4(struct socket *sock) { struct sock *sk = sock->sk; @@ -1597,6 +1776,9 @@ static inline void xs_reclassify_socket6(struct socket *sock) static inline void xs_reclassify_socket(int family, struct socket *sock) { switch (family) { + case AF_LOCAL: + xs_reclassify_socketu(sock); + break; case AF_INET: xs_reclassify_socket4(sock); break; @@ -1606,6 +1788,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } } #else +static inline void xs_reclassify_socketu(struct socket *sock) +{ +} + static inline void xs_reclassify_socket4(struct socket *sock) { } @@ -1644,6 +1830,94 @@ out: return ERR_PTR(err); } +static int xs_local_finish_connecting(struct rpc_xprt *xprt, + struct socket *sock) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + + if (!transport->inet) { + struct sock *sk = sock->sk; + + write_lock_bh(&sk->sk_callback_lock); + + xs_save_old_callbacks(transport, sk); + + sk->sk_user_data = xprt; + sk->sk_data_ready = xs_local_data_ready; + sk->sk_write_space = xs_udp_write_space; + sk->sk_error_report = xs_error_report; + sk->sk_allocation = GFP_ATOMIC; + + xprt_clear_connected(xprt); + + /* Reset to new socket */ + transport->sock = sock; + transport->inet = sk; + + write_unlock_bh(&sk->sk_callback_lock); + } + + /* Tell the socket layer to start connecting... */ + xprt->stat.connect_count++; + xprt->stat.connect_start = jiffies; + return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0); +} + +/** + * xs_local_setup_socket - create AF_LOCAL socket, connect to a local 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_local_setup_socket(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; + int status = -EIO; + + if (xprt->shutdown) + goto out; + + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + status = __sock_create(xprt->xprt_net, AF_LOCAL, + SOCK_STREAM, 0, &sock, 1); + if (status < 0) { + dprintk("RPC: can't create AF_LOCAL " + "transport socket (%d).\n", -status); + goto out; + } + xs_reclassify_socketu(sock); + + dprintk("RPC: worker connecting xprt %p via AF_LOCAL to %s\n", + xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); + + status = xs_local_finish_connecting(xprt, sock); + switch (status) { + case 0: + dprintk("RPC: xprt %p connected to %s\n", + xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); + xprt_set_connected(xprt); + break; + case -ENOENT: + dprintk("RPC: xprt %p: socket %s does not exist\n", + xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); + break; + default: + printk(KERN_ERR "%s: unhandled error (%d) connecting to %s\n", + __func__, -status, + xprt->address_strings[RPC_DISPLAY_ADDR]); + } + +out: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); +} + static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1758,6 +2032,7 @@ static void xs_tcp_reuse_connection(struct sock_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); + int ret = -ENOTCONN; if (!transport->inet) { struct sock *sk = sock->sk; @@ -1789,12 +2064,22 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) } if (!xprt_bound(xprt)) - return -ENOTCONN; + goto out; /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; - return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); + ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); + switch (ret) { + case 0: + case -EINPROGRESS: + /* SYN_SENT! */ + xprt->connect_cookie++; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + } +out: + return ret; } /** @@ -1917,6 +2202,32 @@ static void xs_connect(struct rpc_task *task) } /** + * xs_local_print_stats - display AF_LOCAL socket-specifc stats + * @xprt: rpc_xprt struct containing statistics + * @seq: output file + * + */ +static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) +{ + long idle_time = 0; + + if (xprt_connected(xprt)) + idle_time = (long)(jiffies - xprt->last_used) / HZ; + + seq_printf(seq, "\txprt:\tlocal %lu %lu %lu %ld %lu %lu %lu " + "%llu %llu\n", + xprt->stat.bind_count, + xprt->stat.connect_count, + xprt->stat.connect_time, + idle_time, + xprt->stat.sends, + xprt->stat.recvs, + xprt->stat.bad_xids, + xprt->stat.req_u, + xprt->stat.bklog_u); +} + +/** * xs_udp_print_stats - display UDP socket-specifc stats * @xprt: rpc_xprt struct containing statistics * @seq: output file @@ -2014,10 +2325,7 @@ static int bc_sendto(struct rpc_rqst *req) unsigned long headoff; unsigned long tailoff; - /* - * Set up the rpc header and record marker stuff - */ - xs_encode_tcp_record_marker(xbufp); + xs_encode_stream_record_marker(xbufp); tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK; headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK; @@ -2089,6 +2397,21 @@ static void bc_destroy(struct rpc_xprt *xprt) { } +static struct rpc_xprt_ops xs_local_ops = { + .reserve_xprt = xprt_reserve_xprt, + .release_xprt = xs_tcp_release_xprt, + .rpcbind = xs_local_rpcbind, + .set_port = xs_local_set_port, + .connect = xs_connect, + .buf_alloc = rpc_malloc, + .buf_free = rpc_free, + .send_request = xs_local_send_request, + .set_retrans_timeout = xprt_set_retrans_timeout_def, + .close = xs_close, + .destroy = xs_destroy, + .print_stats = xs_local_print_stats, +}; + static struct rpc_xprt_ops xs_udp_ops = { .set_buffer_size = xs_udp_set_buffer_size, .reserve_xprt = xprt_reserve_xprt_cong, @@ -2150,6 +2473,8 @@ static int xs_init_anyaddr(const int family, struct sockaddr *sap) }; switch (family) { + case AF_LOCAL: + break; case AF_INET: memcpy(sap, &sin, sizeof(sin)); break; @@ -2197,6 +2522,70 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, return xprt; } +static const struct rpc_timeout xs_local_default_timeout = { + .to_initval = 10 * HZ, + .to_maxval = 10 * HZ, + .to_retries = 2, +}; + +/** + * xs_setup_local - Set up transport to use an AF_LOCAL socket + * @args: rpc transport creation arguments + * + * AF_LOCAL is a "tpi_cots_ord" transport, just like TCP + */ +static struct rpc_xprt *xs_setup_local(struct xprt_create *args) +{ + struct sockaddr_un *sun = (struct sockaddr_un *)args->dstaddr; + struct sock_xprt *transport; + struct rpc_xprt *xprt; + struct rpc_xprt *ret; + + 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 = 0; + xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32); + xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; + + xprt->bind_timeout = XS_BIND_TO; + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + xprt->idle_timeout = XS_IDLE_DISC_TO; + + xprt->ops = &xs_local_ops; + xprt->timeout = &xs_local_default_timeout; + + switch (sun->sun_family) { + case AF_LOCAL: + if (sun->sun_path[0] != '/') { + dprintk("RPC: bad AF_LOCAL address: %s\n", + sun->sun_path); + ret = ERR_PTR(-EINVAL); + goto out_err; + } + xprt_set_bound(xprt); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_local_setup_socket); + xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); + break; + default: + ret = ERR_PTR(-EAFNOSUPPORT); + goto out_err; + } + + dprintk("RPC: set up xprt to %s via AF_LOCAL\n", + xprt->address_strings[RPC_DISPLAY_ADDR]); + + if (try_module_get(THIS_MODULE)) + return xprt; + ret = ERR_PTR(-EINVAL); +out_err: + xprt_free(xprt); + return ret; +} + static const struct rpc_timeout xs_udp_default_timeout = { .to_initval = 5 * HZ, .to_maxval = 30 * HZ, @@ -2438,6 +2827,14 @@ out_err: return ret; } +static struct xprt_class xs_local_transport = { + .list = LIST_HEAD_INIT(xs_local_transport.list), + .name = "named UNIX socket", + .owner = THIS_MODULE, + .ident = XPRT_TRANSPORT_LOCAL, + .setup = xs_setup_local, +}; + static struct xprt_class xs_udp_transport = { .list = LIST_HEAD_INIT(xs_udp_transport.list), .name = "udp", @@ -2473,6 +2870,7 @@ int init_socket_xprt(void) sunrpc_table_header = register_sysctl_table(sunrpc_table); #endif + xprt_register_transport(&xs_local_transport); xprt_register_transport(&xs_udp_transport); xprt_register_transport(&xs_tcp_transport); xprt_register_transport(&xs_bc_tcp_transport); @@ -2493,6 +2891,7 @@ void cleanup_socket_xprt(void) } #endif + xprt_unregister_transport(&xs_local_transport); xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); xprt_unregister_transport(&xs_bc_tcp_transport); |