diff options
Diffstat (limited to 'net/sunrpc/xprtsock.c')
| -rw-r--r-- | net/sunrpc/xprtsock.c | 733 |
1 files changed, 325 insertions, 408 deletions
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d86c664ea6af..915b9902f673 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -54,9 +54,11 @@ #include <trace/events/sunrpc.h> +#include "socklib.h" #include "sunrpc.h" static void xs_close(struct rpc_xprt *xprt); +static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock); static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct socket *sock); @@ -90,6 +92,11 @@ static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT; static struct ctl_table_header *sunrpc_table_header; +static struct xprt_class xs_local_transport; +static struct xprt_class xs_udp_transport; +static struct xprt_class xs_tcp_transport; +static struct xprt_class xs_bc_tcp_transport; + /* * FIXME: changing the UDP slot table size should also resize the UDP * socket buffers for existing UDP transports @@ -254,7 +261,7 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) switch (sap->sa_family) { case AF_LOCAL: sun = xs_addr_un(xprt); - strlcpy(buf, sun->sun_path, sizeof(buf)); + strscpy(buf, sun->sun_path, sizeof(buf)); xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); break; @@ -421,9 +428,9 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, offset += want; } - want = xs_alloc_sparse_pages(buf, - min_t(size_t, count - offset, buf->page_len), - GFP_KERNEL); + want = xs_alloc_sparse_pages( + buf, min_t(size_t, count - offset, buf->page_len), + GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (seek < want) { ret = xs_read_bvec(sock, msg, flags, buf->bvec, xdr_buf_pagecount(buf), @@ -432,7 +439,8 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, if (ret <= 0) goto sock_err; xs_flush_bvec(buf->bvec, ret, seek + buf->page_base); - offset += ret - buf->page_base; + ret -= buf->page_base; + offset += ret; if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) goto out; if (ret != want) @@ -495,8 +503,8 @@ xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, int flags, struct rpc_rqst *req) { struct xdr_buf *buf = &req->rq_private_buf; - size_t want, uninitialized_var(read); - ssize_t uninitialized_var(ret); + size_t want, read; + ssize_t ret; xs_read_header(transport, buf); @@ -556,6 +564,10 @@ xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags) struct rpc_rqst *req; ssize_t ret; + /* Is this transport associated with the backchannel? */ + if (!xprt->bc_serv) + return -ESHUTDOWN; + /* Look up and lock the request corresponding to the given XID */ req = xprt_lookup_bc_request(xprt, transport->recv.xid); if (!req) { @@ -749,141 +761,19 @@ xs_stream_start_connect(struct sock_xprt *transport) #define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL) -static int xs_sendmsg(struct socket *sock, struct msghdr *msg, size_t seek) -{ - if (seek) - iov_iter_advance(&msg->msg_iter, seek); - return sock_sendmsg(sock, msg); -} - -static int xs_send_kvec(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t seek) -{ - iov_iter_kvec(&msg->msg_iter, WRITE, vec, 1, vec->iov_len); - return xs_sendmsg(sock, msg, seek); -} - -static int xs_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) -{ - int err; - - err = xdr_alloc_bvec(xdr, GFP_KERNEL); - if (err < 0) - return err; - - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, - xdr_buf_pagecount(xdr), - xdr->page_len + xdr->page_base); - return xs_sendmsg(sock, msg, base + xdr->page_base); -} - -#define xs_record_marker_len() sizeof(rpc_fraghdr) - -/* Common case: - * - stream transport - * - sending from byte 0 of the message - * - the message is wholly contained in @xdr's head iovec - */ -static int xs_send_rm_and_kvec(struct socket *sock, struct msghdr *msg, - rpc_fraghdr marker, struct kvec *vec, size_t base) -{ - struct kvec iov[2] = { - [0] = { - .iov_base = &marker, - .iov_len = sizeof(marker) - }, - [1] = *vec, - }; - size_t len = iov[0].iov_len + iov[1].iov_len; - - iov_iter_kvec(&msg->msg_iter, WRITE, iov, 2, len); - return xs_sendmsg(sock, msg, base); -} - -/** - * xs_sendpages - write pages directly to a socket - * @sock: socket to send on - * @addr: UDP only -- address of destination - * @addrlen: UDP only -- length of destination address - * @xdr: buffer containing this request - * @base: starting position in the buffer - * @rm: stream record marker field - * @sent_p: return the total number of bytes successfully queued for sending - * - */ -static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, rpc_fraghdr rm, int *sent_p) -{ - struct msghdr msg = { - .msg_name = addr, - .msg_namelen = addrlen, - .msg_flags = XS_SENDMSG_FLAGS | MSG_MORE, - }; - unsigned int rmsize = rm ? sizeof(rm) : 0; - unsigned int remainder = rmsize + xdr->len - base; - unsigned int want; - int err = 0; - - if (unlikely(!sock)) - return -ENOTSOCK; - - want = xdr->head[0].iov_len + rmsize; - if (base < want) { - unsigned int len = want - base; - remainder -= len; - if (remainder == 0) - msg.msg_flags &= ~MSG_MORE; - if (rmsize) - err = xs_send_rm_and_kvec(sock, &msg, rm, - &xdr->head[0], base); - else - err = xs_send_kvec(sock, &msg, &xdr->head[0], base); - if (remainder == 0 || err != len) - goto out; - *sent_p += err; - base = 0; - } else - base -= want; - - if (base < xdr->page_len) { - unsigned int len = xdr->page_len - base; - remainder -= len; - if (remainder == 0) - msg.msg_flags &= ~MSG_MORE; - err = xs_send_pagedata(sock, &msg, xdr, base); - if (remainder == 0 || err != len) - goto out; - *sent_p += err; - base = 0; - } else - base -= xdr->page_len; - - if (base >= xdr->tail[0].iov_len) - return 0; - msg.msg_flags &= ~MSG_MORE; - err = xs_send_kvec(sock, &msg, &xdr->tail[0], base); -out: - if (err > 0) { - *sent_p += err; - err = 0; - } - return err; -} - /** * xs_nospace - handle transmit was incomplete * @req: pointer to RPC request + * @transport: pointer to struct sock_xprt * */ -static int xs_nospace(struct rpc_rqst *req) +static int xs_nospace(struct rpc_rqst *req, struct sock_xprt *transport) { - struct rpc_xprt *xprt = req->rq_xprt; - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct rpc_xprt *xprt = &transport->xprt; struct sock *sk = transport->inet; int ret = -EAGAIN; - dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", - req->rq_task->tk_pid, - req->rq_slen - transport->xmit.offset, - req->rq_slen); + trace_rpc_socket_nospace(req, transport); /* Protect against races with write_space */ spin_lock(&xprt->transport_lock); @@ -891,32 +781,50 @@ static int xs_nospace(struct rpc_rqst *req) /* Don't race with disconnect */ if (xprt_connected(xprt)) { /* wait for more buffer space */ + set_bit(XPRT_SOCK_NOSPACE, &transport->sock_state); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; xprt_wait_for_buffer_space(xprt); } else ret = -ENOTCONN; spin_unlock(&xprt->transport_lock); + return ret; +} - /* Race breaker in case memory is freed before above code is called */ - if (ret == -EAGAIN) { - struct socket_wq *wq; +static int xs_sock_nospace(struct rpc_rqst *req) +{ + struct sock_xprt *transport = + container_of(req->rq_xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; + int ret = -EAGAIN; - rcu_read_lock(); - wq = rcu_dereference(sk->sk_wq); - set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags); - rcu_read_unlock(); + lock_sock(sk); + if (!sock_writeable(sk)) + ret = xs_nospace(req, transport); + release_sock(sk); + return ret; +} - sk->sk_write_space(sk); - } +static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) +{ + struct sock_xprt *transport = + container_of(req->rq_xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; + int ret = -EAGAIN; + + if (vm_wait) + return -ENOBUFS; + lock_sock(sk); + if (!sk_stream_memory_free(sk)) + ret = xs_nospace(req, transport); + release_sock(sk); return ret; } -static void -xs_stream_prepare_request(struct rpc_rqst *req) +static int xs_stream_prepare_request(struct rpc_rqst *req, struct xdr_buf *buf) { - xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec(&req->rq_rcv_buf, GFP_KERNEL); + return xdr_alloc_bvec(buf, rpc_task_gfp_mask()); } /* @@ -949,7 +857,7 @@ xs_stream_record_marker(struct xdr_buf *xdr) * 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 + * other: Some other error occurred, the request was not sent */ static int xs_local_send_request(struct rpc_rqst *req) { @@ -959,27 +867,30 @@ static int xs_local_send_request(struct rpc_rqst *req) struct xdr_buf *xdr = &req->rq_snd_buf; rpc_fraghdr rm = xs_stream_record_marker(xdr); unsigned int msglen = rm ? req->rq_slen + sizeof(rm) : req->rq_slen; + struct msghdr msg = { + .msg_flags = XS_SENDMSG_FLAGS, + }; + bool vm_wait; + unsigned int sent; int status; - int sent = 0; /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); + vm_wait = sk_stream_is_writeable(transport->inet) ? true : false; + req->rq_xtime = ktime_get(); - status = xs_sendpages(transport->sock, NULL, 0, xdr, - transport->xmit.offset, rm, &sent); + status = xprt_sock_sendmsg(transport->sock, &msg, xdr, + transport->xmit.offset, rm, &sent); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - transport->xmit.offset, status); - if (status == -EAGAIN && sock_writeable(transport->inet)) - status = -ENOBUFS; - if (likely(sent > 0) || status == 0) { transport->xmit.offset += sent; req->rq_bytes_sent = transport->xmit.offset; @@ -989,20 +900,19 @@ static int xs_local_send_request(struct rpc_rqst *req) return 0; } status = -EAGAIN; + vm_wait = false; } switch (status) { - case -ENOBUFS: - break; case -EAGAIN: - status = xs_nospace(req); + status = xs_stream_nospace(req, vm_wait); break; default: dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); - /* fall through */ + fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -1025,7 +935,12 @@ static int xs_udp_send_request(struct rpc_rqst *req) struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; - int sent = 0; + struct msghdr msg = { + .msg_name = xs_addr(xprt), + .msg_namelen = xprt->addrlen, + .msg_flags = XS_SENDMSG_FLAGS, + }; + unsigned int sent; int status; xs_pktdump("packet data:", @@ -1038,9 +953,11 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); - status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, - xdr, 0, 0, &sent); + status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); dprintk("RPC: xs_udp_send_request(%u) = %d\n", xdr->len, status); @@ -1067,7 +984,7 @@ process_status: /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req); + status = xs_sock_nospace(req); break; case -ENETUNREACH: case -ENOBUFS: @@ -1106,9 +1023,12 @@ static int xs_tcp_send_request(struct rpc_rqst *req) struct xdr_buf *xdr = &req->rq_snd_buf; rpc_fraghdr rm = xs_stream_record_marker(xdr); unsigned int msglen = rm ? req->rq_slen + sizeof(rm) : req->rq_slen; - bool vm_wait = false; + struct msghdr msg = { + .msg_flags = XS_SENDMSG_FLAGS, + }; + bool vm_wait; + unsigned int sent; int status; - int sent; /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { @@ -1116,6 +1036,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) kernel_sock_shutdown(transport->sock, SHUT_RDWR); return -ENOTCONN; } + if (!transport->inet) + return -ENOTCONN; xs_pktdump("packet data:", req->rq_svec->iov_base, @@ -1124,14 +1046,19 @@ static int xs_tcp_send_request(struct rpc_rqst *req) if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state)) xs_tcp_set_socket_timeouts(xprt, transport->sock); + xs_set_srcport(transport, transport->sock); + /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ req->rq_xtime = ktime_get(); - while (1) { - sent = 0; - status = xs_sendpages(transport->sock, NULL, 0, xdr, - transport->xmit.offset, rm, &sent); + tcp_sock_set_cork(transport->inet, true); + + vm_wait = sk_stream_is_writeable(transport->inet) ? true : false; + + do { + status = xprt_sock_sendmsg(transport->sock, &msg, xdr, + transport->xmit.offset, rm, &sent); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - transport->xmit.offset, status); @@ -1143,36 +1070,17 @@ static int xs_tcp_send_request(struct rpc_rqst *req) if (likely(req->rq_bytes_sent >= msglen)) { req->rq_xmit_bytes_sent += transport->xmit.offset; transport->xmit.offset = 0; + if (atomic_long_read(&xprt->xmit_queuelen) == 1) + tcp_sock_set_cork(transport->inet, false); return 0; } WARN_ON_ONCE(sent == 0 && status == 0); - if (status == -EAGAIN ) { - /* - * Return EAGAIN if we're sure we're hitting the - * socket send buffer limits. - */ - if (test_bit(SOCK_NOSPACE, &transport->sock->flags)) - break; - /* - * Did we hit a memory allocation failure? - */ - if (sent == 0) { - status = -ENOBUFS; - if (vm_wait) - break; - /* Retry, knowing now that we're below the - * socket send buffer limit - */ - vm_wait = true; - } - continue; - } - if (status < 0) - break; - vm_wait = false; - } + if (sent > 0) + vm_wait = false; + + } while (status == 0); switch (status) { case -ENOTSOCK: @@ -1180,7 +1088,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req) /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req); + status = xs_stream_nospace(req, vm_wait); break; case -ECONNRESET: case -ECONNREFUSED: @@ -1221,6 +1129,7 @@ static void xs_sock_reset_state_flags(struct rpc_xprt *xprt) clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state); clear_bit(XPRT_SOCK_WAKE_WRITE, &transport->sock_state); clear_bit(XPRT_SOCK_WAKE_DISCONNECT, &transport->sock_state); + clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state); } static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr) @@ -1231,6 +1140,7 @@ static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { + xprt->connect_cookie++; smp_mb__before_atomic(); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); @@ -1250,14 +1160,13 @@ static void xs_error_report(struct sock *sk) struct sock_xprt *transport; struct rpc_xprt *xprt; - read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) - goto out; + return; transport = container_of(xprt, struct sock_xprt, xprt); transport->xprt_err = -sk->sk_err; if (transport->xprt_err == 0) - goto out; + return; dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -transport->xprt_err); trace_rpc_socket_error(xprt, sk->sk_socket, transport->xprt_err); @@ -1265,8 +1174,6 @@ static void xs_error_report(struct sock *sk) /* barrier ensures xprt_err is set before XPRT_SOCK_WAKE_ERROR */ smp_mb__before_atomic(); xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR); - out: - read_unlock_bh(&sk->sk_callback_lock); } static void xs_reset_transport(struct sock_xprt *transport) @@ -1278,6 +1185,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1285,7 +1202,7 @@ static void xs_reset_transport(struct sock_xprt *transport) kernel_sock_shutdown(sock, SHUT_RDWR); mutex_lock(&transport->recv_mutex); - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); transport->inet = NULL; transport->sock = NULL; transport->file = NULL; @@ -1294,14 +1211,14 @@ static void xs_reset_transport(struct sock_xprt *transport) xs_restore_old_callbacks(transport, sk); xprt_clear_connected(xprt); - write_unlock_bh(&sk->sk_callback_lock); xs_sock_reset_connection_flags(xprt); /* Reset stream record info */ xs_stream_reset_connect(transport); + release_sock(sk); mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -1430,7 +1347,7 @@ static void xs_udp_data_receive(struct sock_xprt *transport) if (sk == NULL) goto out; for (;;) { - skb = skb_recv_udp(sk, 0, 1, &err); + skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); if (skb == NULL) break; xs_udp_data_read_skb(&transport->xprt, sk, skb); @@ -1453,7 +1370,7 @@ static void xs_udp_data_receive_workfn(struct work_struct *work) } /** - * xs_data_ready - "data ready" callback for UDP sockets + * xs_data_ready - "data ready" callback for sockets * @sk: socket with data to read * */ @@ -1461,12 +1378,13 @@ static void xs_data_ready(struct sock *sk) { struct rpc_xprt *xprt; - read_lock_bh(&sk->sk_callback_lock); - dprintk("RPC: xs_data_ready...\n"); xprt = xprt_from_sock(sk); if (xprt != NULL) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + + trace_xs_data_ready(xprt); + transport->old_data_ready(sk); /* Any data means we had a useful conversation, so * then we don't need to delay the next reconnect @@ -1476,7 +1394,6 @@ static void xs_data_ready(struct sock *sk) if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) queue_work(xprtiod_workqueue, &transport->recv_worker); } - read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1496,6 +1413,26 @@ static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** + * xs_local_state_change - callback to handle AF_LOCAL socket state changes + * @sk: socket whose state has changed + * + */ +static void xs_local_state_change(struct sock *sk) +{ + struct rpc_xprt *xprt; + struct sock_xprt *transport; + + if (!(xprt = xprt_from_sock(sk))) + return; + transport = container_of(xprt, struct sock_xprt, xprt); + if (sk->sk_shutdown & SHUTDOWN_MASK) { + clear_bit(XPRT_CONNECTED, &xprt->state); + /* Trigger the socket release */ + xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); + } +} + +/** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed * @@ -1505,9 +1442,8 @@ static void xs_tcp_state_change(struct sock *sk) struct rpc_xprt *xprt; struct sock_xprt *transport; - read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) - goto out; + return; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); dprintk("RPC: state %x conn %d dead %d zapped %d sk_shutdown %d\n", sk->sk_state, xprt_connected(xprt), @@ -1545,7 +1481,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt->connect_cookie++; clear_bit(XPRT_CONNECTED, &xprt->state); xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); - /* fall through */ + fallthrough; case TCP_CLOSING: /* * If the server closed down the connection, make sure that @@ -1568,13 +1504,10 @@ static void xs_tcp_state_change(struct sock *sk) /* Trigger the socket release */ xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); } - out: - read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) { - struct socket_wq *wq; struct sock_xprt *transport; struct rpc_xprt *xprt; @@ -1585,15 +1518,10 @@ static void xs_write_space(struct sock *sk) if (unlikely(!(xprt = xprt_from_sock(sk)))) return; transport = container_of(xprt, struct sock_xprt, xprt); - rcu_read_lock(); - wq = rcu_dereference(sk->sk_wq); - if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) - goto out; - + if (!test_and_clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state)) + return; xs_run_error_worker(transport, XPRT_SOCK_WAKE_WRITE); sk->sk_write_pending--; -out: - rcu_read_unlock(); } /** @@ -1608,13 +1536,9 @@ out: */ static void xs_udp_write_space(struct sock *sk) { - read_lock_bh(&sk->sk_callback_lock); - /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - - read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1629,13 +1553,9 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock_bh(&sk->sk_callback_lock); - /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_is_writeable(sk)) xs_write_space(sk); - - read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) @@ -1699,25 +1619,10 @@ static int xs_get_random_port(void) if (max < min) return -EADDRINUSE; range = max - min + 1; - rand = (unsigned short) prandom_u32() % range; + rand = prandom_u32_max(range); return rand + min; } -/** - * xs_set_reuseaddr_port - set the socket's port and address reuse options - * @sock: socket - * - * Note that this function has to be called on all sockets that share the - * same port, and it must be called before binding. - */ -static void xs_sock_set_reuseport(struct socket *sock) -{ - int opt = 1; - - kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEPORT, - (char *)&opt, sizeof(opt)); -} - static unsigned short xs_sock_getport(struct socket *sock) { struct sockaddr_storage buf; @@ -1765,6 +1670,36 @@ static int xs_get_srcport(struct sock_xprt *transport) return port; } +static unsigned short xs_sock_srcport(struct rpc_xprt *xprt) +{ + struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); + unsigned short ret = 0; + mutex_lock(&sock->recv_mutex); + if (sock->sock) + ret = xs_sock_getport(sock->sock); + mutex_unlock(&sock->recv_mutex); + return ret; +} + +static int xs_sock_srcaddr(struct rpc_xprt *xprt, char *buf, size_t buflen) +{ + struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); + union { + struct sockaddr sa; + struct sockaddr_storage st; + } saddr; + int ret = -ENOTCONN; + + mutex_lock(&sock->recv_mutex); + if (sock->sock) { + ret = kernel_getsockname(sock->sock, &saddr.sa); + if (ret >= 0) + ret = snprintf(buf, buflen, "%pISc", &saddr.sa); + } + mutex_unlock(&sock->recv_mutex); + return ret; +} + static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port) { if (transport->srcport != 0) @@ -1791,7 +1726,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) * This ensures that we can continue to establish TCP * connections even when all local ephemeral ports are already * a part of some TCP connection. This makes no difference - * for UDP sockets, but also doens't harm them. + * for UDP sockets, but also doesn't harm them. * * If we're asking for any reserved port (i.e. port == 0 && * transport->xprt.resvport == 1) xs_get_srcport above will @@ -1806,7 +1741,8 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) err = kernel_bind(sock, (struct sockaddr *)&myaddr, transport->xprt.addrlen); if (err == 0) { - transport->srcport = port; + if (transport->xprt.reuseport) + transport->srcport = port; break; } last = port; @@ -1839,15 +1775,15 @@ 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 struct lock_class_key xs_key[3]; +static struct lock_class_key xs_slock_key[3]; static inline void xs_reclassify_socketu(struct socket *sock) { struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC", - &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]); + &xs_slock_key[0], "sk_lock-AF_LOCAL-RPC", &xs_key[0]); } static inline void xs_reclassify_socket4(struct socket *sock) @@ -1855,7 +1791,7 @@ static inline void xs_reclassify_socket4(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC", - &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]); + &xs_slock_key[1], "sk_lock-AF_INET-RPC", &xs_key[1]); } static inline void xs_reclassify_socket6(struct socket *sock) @@ -1863,7 +1799,7 @@ static inline void xs_reclassify_socket6(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC", - &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]); + &xs_slock_key[2], "sk_lock-AF_INET6-RPC", &xs_key[2]); } static inline void xs_reclassify_socket(int family, struct socket *sock) @@ -1910,7 +1846,7 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, xs_reclassify_socket(family, sock); if (reuseport) - xs_sock_set_reuseport(sock); + sock_set_reuseport(sock->sk); err = xs_bind(transport, sock); if (err) { @@ -1937,14 +1873,14 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, if (!transport->inet) { struct sock *sk = sock->sk; - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; - sock_set_flag(sk, SOCK_FASYNC); + sk->sk_state_change = xs_local_state_change; sk->sk_error_report = xs_error_report; xprt_clear_connected(xprt); @@ -1953,7 +1889,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, transport->sock = sock; transport->inet = sk; - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } xs_stream_start_connect(transport); @@ -1970,7 +1906,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) struct rpc_xprt *xprt = &transport->xprt; struct file *filp; struct socket *sock; - int status = -EIO; + int status; status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); @@ -2001,6 +1937,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; xprt_set_connected(xprt); + break; case -ENOBUFS: break; case -ENOENT: @@ -2028,7 +1965,10 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; - if (RPC_IS_ASYNC(task)) { + if (transport->file) + goto force_disconnect; + + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the * filesystem namespace of the process making the rpc @@ -2038,20 +1978,25 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) * we'll need to figure out how to pass a namespace to * connect. */ - task->tk_rpc_status = -ENOTCONN; - rpc_exit(task, -ENOTCONN); - return; + rpc_task_set_rpc_status(task, -ENOTCONN); + goto out_wake; } ret = xs_local_setup_socket(transport); if (ret && !RPC_IS_SOFTCONN(task)) msleep_interruptible(15000); + return; +force_disconnect: + xprt_force_disconnect(xprt); +out_wake: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, -ENOTCONN); } #if IS_ENABLED(CONFIG_SUNRPC_SWAP) /* - * Note that this should be called with XPRT_LOCKED held (or when we otherwise - * know that we have exclusive access to the socket), to guard against - * races with xs_reset_transport. + * Note that this should be called with XPRT_LOCKED held, or recv_mutex + * held, or when we otherwise know that we have exclusive access to the + * socket, to guard against races with xs_reset_transport. */ static void xs_set_memalloc(struct rpc_xprt *xprt) { @@ -2080,13 +2025,11 @@ xs_enable_swap(struct rpc_xprt *xprt) { struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt); - if (atomic_inc_return(&xprt->swapper) != 1) - return 0; - if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) - return -ERESTARTSYS; - if (xs->inet) + mutex_lock(&xs->recv_mutex); + if (atomic_inc_return(&xprt->swapper) == 1 && + xs->inet) sk_set_memalloc(xs->inet); - xprt_release_xprt(xprt, NULL); + mutex_unlock(&xs->recv_mutex); return 0; } @@ -2102,13 +2045,11 @@ xs_disable_swap(struct rpc_xprt *xprt) { struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt); - if (!atomic_dec_and_test(&xprt->swapper)) - return; - if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) - return; - if (xs->inet) + mutex_lock(&xs->recv_mutex); + if (atomic_dec_and_test(&xprt->swapper) && + xs->inet) sk_clear_memalloc(xs->inet); - xprt_release_xprt(xprt, NULL); + mutex_unlock(&xs->recv_mutex); } #else static void xs_set_memalloc(struct rpc_xprt *xprt) @@ -2134,14 +2075,13 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!transport->inet) { struct sock *sk = sock->sk; - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; - sock_set_flag(sk, SOCK_FASYNC); xprt_set_connected(xprt); @@ -2151,7 +2091,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) xs_set_memalloc(xprt); - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } xs_udp_do_set_buffer_size(xprt); @@ -2165,7 +2105,10 @@ static void xs_udp_setup_socket(struct work_struct *work) struct rpc_xprt *xprt = &transport->xprt; struct socket *sock; int status = -EIO; + unsigned int pflags = current->flags; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP, false); @@ -2185,6 +2128,7 @@ out: xprt_clear_connecting(xprt); xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -2202,13 +2146,20 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) if (sock == NULL) return; + if (!xprt->reuseport) { + xs_close(xprt); + return; + } switch (skst) { - default: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + break; + case TCP_ESTABLISHED: + case TCP_CLOSE_WAIT: kernel_sock_shutdown(sock, SHUT_RDWR); trace_rpc_socket_shutdown(xprt, sock); break; - case TCP_CLOSE: - case TCP_TIME_WAIT: + default: xs_reset_transport(transport); } } @@ -2219,7 +2170,6 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); unsigned int keepidle; unsigned int keepcnt; - unsigned int opt_on = 1; unsigned int timeo; spin_lock(&xprt->transport_lock); @@ -2231,18 +2181,13 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, spin_unlock(&xprt->transport_lock); /* TCP Keepalive options */ - kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, - (char *)&opt_on, sizeof(opt_on)); - kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, - (char *)&keepidle, sizeof(keepidle)); - kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, - (char *)&keepidle, sizeof(keepidle)); - kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, - (char *)&keepcnt, sizeof(keepcnt)); + sock_set_keepalive(sock->sk); + tcp_sock_set_keepidle(sock->sk, keepidle); + tcp_sock_set_keepintvl(sock->sk, keepidle); + tcp_sock_set_keepcnt(sock->sk, keepcnt); /* TCP user timeout (see RFC5482) */ - kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT, - (char *)&timeo, sizeof(timeo)); + tcp_sock_set_user_timeout(sock->sk, timeo); } static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt, @@ -2276,11 +2221,9 @@ static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt, 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; - unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* Avoid temporary address, they are bad for long-lived * connections such as NFS mounts. @@ -2289,12 +2232,15 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) * knowledge about the normal duration of connections, * MAY override this as appropriate. */ - kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, - (char *)&addr_pref, sizeof(addr_pref)); + if (xs_addr(xprt)->sa_family == PF_INET6) { + ip6_sock_set_addr_preferences(sk, + IPV6_PREFER_SRC_PUBLIC); + } xs_tcp_set_socket_timeouts(xprt, sock); + tcp_sock_set_nodelay(sk); - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); @@ -2302,12 +2248,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sock_set_flag(sk, SOCK_FASYNC); sk->sk_error_report = xs_error_report; /* socket options */ sock_reset_flag(sk, SOCK_LINGER); - tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; xprt_clear_connected(xprt); @@ -2315,11 +2259,11 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->sock = sock; transport->inet = sk; - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } if (!xprt_bound(xprt)) - goto out; + return -ENOTCONN; xs_set_memalloc(xprt); @@ -2327,22 +2271,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* Tell the socket layer to start connecting... */ set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); - ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); - switch (ret) { - case 0: - xs_set_srcport(transport, sock); - /* fall through */ - case -EINPROGRESS: - /* SYN_SENT! */ - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - break; - case -EADDRNOTAVAIL: - /* Source port number is unavailable. Try a new one! */ - transport->srcport = 0; - } -out: - return ret; + return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); } /** @@ -2357,14 +2286,22 @@ static void xs_tcp_setup_socket(struct work_struct *work) container_of(work, struct sock_xprt, connect_worker.work); struct socket *sock = transport->sock; struct rpc_xprt *xprt = &transport->xprt; - int status = -EIO; + int status; + unsigned int pflags = current->flags; - if (!sock) { - sock = xs_create_sock(xprt, transport, - xs_addr(xprt)->sa_family, SOCK_STREAM, - IPPROTO_TCP, true); + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; + + if (xprt_connected(xprt)) + goto out; + if (test_and_clear_bit(XPRT_SOCK_CONNECT_SENT, + &transport->sock_state) || + !sock) { + xs_reset_transport(transport); + sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, + SOCK_STREAM, IPPROTO_TCP, true); if (IS_ERR(sock)) { - status = PTR_ERR(sock); + xprt_wake_pending_tasks(xprt, PTR_ERR(sock)); goto out; } } @@ -2381,21 +2318,20 @@ static void xs_tcp_setup_socket(struct work_struct *work) xprt, -status, xprt_connected(xprt), sock->sk->sk_state); switch (status) { - default: - printk("%s: connect returned unhandled error %d\n", - __func__, status); - /* fall through */ - case -EADDRNOTAVAIL: - /* We're probably in TIME_WAIT. Get rid of existing socket, - * and retry - */ - xs_tcp_force_close(xprt); - break; case 0: case -EINPROGRESS: + /* SYN_SENT! */ + set_bit(XPRT_SOCK_CONNECT_SENT, &transport->sock_state); + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + fallthrough; case -EALREADY: - xprt_unlock_connect(xprt, transport); - return; + goto out_unlock; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; + status = -EAGAIN; + break; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. @@ -2407,20 +2343,23 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: - /* - * xs_tcp_force_close() wakes tasks with -EIO. - * We need to wake them first to ensure the - * correct error code. - */ - xprt_wake_pending_tasks(xprt, status); - xs_tcp_force_close(xprt); - goto out; + break; + default: + printk("%s: connect returned unhandled error %d\n", + __func__, status); + status = -EAGAIN; } - status = -EAGAIN; + + /* xs_tcp_force_close() wakes tasks with a fixed error code. + * We need to wake them first to ensure the correct error code. + */ + xprt_wake_pending_tasks(xprt, status); + xs_tcp_force_close(xprt); out: xprt_clear_connecting(xprt); +out_unlock: xprt_unlock_connect(xprt, transport); - xprt_wake_pending_tasks(xprt, status); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -2446,11 +2385,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) if (transport->sock != NULL) { dprintk("RPC: xs_connect delayed xprt %p for %lu " - "seconds\n", - xprt, xprt->reestablish_timeout / HZ); - - /* Start by resetting any existing state */ - xs_reset_transport(transport); + "seconds\n", xprt, xprt->reestablish_timeout / HZ); delay = xprt_reconnect_delay(xprt); xprt_reconnect_backoff(xprt, XS_TCP_INIT_REEST_TO); @@ -2511,7 +2446,7 @@ static void xs_error_handle(struct work_struct *work) } /** - * xs_local_print_stats - display AF_LOCAL socket-specifc stats + * xs_local_print_stats - display AF_LOCAL socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2540,7 +2475,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_udp_print_stats - display UDP socket-specifc stats + * xs_udp_print_stats - display UDP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2564,7 +2499,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_tcp_print_stats - display TCP socket-specifc stats + * xs_tcp_print_stats - display TCP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2612,7 +2547,7 @@ static int bc_malloc(struct rpc_task *task) return -EINVAL; } - page = alloc_page(GFP_KERNEL); + page = alloc_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (!page) return -ENOMEM; @@ -2636,50 +2571,40 @@ static void bc_free(struct rpc_task *task) 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 xdr_buf *xdr = &req->rq_snd_buf; struct sock_xprt *transport = container_of(req->rq_xprt, struct sock_xprt, xprt); - unsigned long headoff; - unsigned long tailoff; - struct page *tailpage; struct msghdr msg = { - .msg_flags = MSG_MORE + .msg_flags = 0, }; rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | - (u32)xbufp->len); - struct kvec iov = { - .iov_base = &marker, - .iov_len = sizeof(marker), - }; + (u32)xdr->len); + unsigned int sent = 0; + int err; req->rq_xtime = ktime_get(); - - len = kernel_sendmsg(transport->sock, &msg, &iov, 1, iov.iov_len); - if (len != iov.iov_len) - return -EAGAIN; - - tailpage = NULL; - if (xbufp->tail[0].iov_len) - tailpage = virt_to_page(xbufp->tail[0].iov_base); - tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK; - headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK; - len = svc_send_common(transport->sock, xbufp, - virt_to_page(xbufp->head[0].iov_base), headoff, - tailpage, tailoff); - if (len != xbufp->len) + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; + err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); + xdr_free_bvec(xdr); + if (err < 0 || sent != (xdr->len + sizeof(marker))) return -EAGAIN; - return len; + return sent; } -/* - * The send routine. Borrows from svc_send +/** + * bc_send_request - Send a backchannel Call on a TCP socket + * @req: rpc_rqst containing Call message to be sent + * + * xpt_mutex ensures @rqstp's whole message is written to the socket + * without interruption. + * + * Return values: + * %0 if the message was sent successfully + * %ENOTCONN if the message was not sent */ static int bc_send_request(struct rpc_rqst *req) { @@ -2714,6 +2639,7 @@ static int bc_send_request(struct rpc_rqst *req) static void bc_close(struct rpc_xprt *xprt) { + xprt_disconnect_done(xprt); } /* @@ -2758,6 +2684,8 @@ static const struct rpc_xprt_ops xs_udp_ops = { .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, + .get_srcaddr = xs_sock_srcaddr, + .get_srcport = xs_sock_srcport, .buf_alloc = rpc_malloc, .buf_free = rpc_free, .send_request = xs_udp_send_request, @@ -2780,6 +2708,8 @@ static const struct rpc_xprt_ops xs_tcp_ops = { .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, + .get_srcaddr = xs_sock_srcaddr, + .get_srcport = xs_sock_srcport, .buf_alloc = rpc_malloc, .buf_free = rpc_free, .prepare_request = xs_stream_prepare_request, @@ -2914,6 +2844,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) transport = container_of(xprt, struct sock_xprt, xprt); xprt->prot = 0; + xprt->xprt_class = &xs_local_transport; xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; xprt->bind_timeout = XS_BIND_TO; @@ -2937,9 +2868,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) } xprt_set_bound(xprt); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); - ret = ERR_PTR(xs_local_setup_socket(transport)); - if (ret) - goto out_err; break; default: ret = ERR_PTR(-EAFNOSUPPORT); @@ -2983,6 +2911,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) transport = container_of(xprt, struct sock_xprt, xprt); xprt->prot = IPPROTO_UDP; + xprt->xprt_class = &xs_udp_transport; /* XXX: header size can vary due to auth type, IPv6, etc. */ xprt->max_payload = (1U << 16) - (MAX_HEADER << 3); @@ -3063,6 +2992,7 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) transport = container_of(xprt, struct sock_xprt, xprt); xprt->prot = IPPROTO_TCP; + xprt->xprt_class = &xs_tcp_transport; xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; xprt->bind_timeout = XS_BIND_TO; @@ -3136,6 +3066,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) transport = container_of(xprt, struct sock_xprt, xprt); xprt->prot = IPPROTO_TCP; + xprt->xprt_class = &xs_bc_tcp_transport; xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; xprt->timeout = &xs_tcp_default_timeout; @@ -3203,6 +3134,7 @@ static struct xprt_class xs_local_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_LOCAL, .setup = xs_setup_local, + .netid = { "" }, }; static struct xprt_class xs_udp_transport = { @@ -3211,6 +3143,7 @@ static struct xprt_class xs_udp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_UDP, .setup = xs_setup_udp, + .netid = { "udp", "udp6", "" }, }; static struct xprt_class xs_tcp_transport = { @@ -3219,6 +3152,7 @@ static struct xprt_class xs_tcp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_TCP, .setup = xs_setup_tcp, + .netid = { "tcp", "tcp6", "" }, }; static struct xprt_class xs_bc_tcp_transport = { @@ -3227,6 +3161,7 @@ static struct xprt_class xs_bc_tcp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_BC_TCP, .setup = xs_setup_bc_tcp, + .netid = { "" }, }; /** @@ -3263,24 +3198,6 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_bc_tcp_transport); } -static int param_set_uint_minmax(const char *val, - const struct kernel_param *kp, - unsigned int min, unsigned int max) -{ - unsigned int num; - int ret; - - if (!val) - return -EINVAL; - ret = kstrtouint(val, 0, &num); - if (ret) - return ret; - if (num < min || num > max) - return -EINVAL; - *((unsigned int *)kp->arg) = num; - return 0; -} - static int param_set_portnr(const char *val, const struct kernel_param *kp) { return param_set_uint_minmax(val, kp, |