diff options
Diffstat (limited to 'net/sunrpc/xprtsock.c')
| -rw-r--r-- | net/sunrpc/xprtsock.c | 925 |
1 files changed, 756 insertions, 169 deletions
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dfcab5ac65a..be8bbd5d65e 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> @@ -28,14 +29,16 @@ #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> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprtsock.h> #include <linux/file.h> -#ifdef CONFIG_NFS_V4_1 +#ifdef CONFIG_SUNRPC_BACKCHANNEL #include <linux/sunrpc/bc_xprt.h> #endif @@ -44,15 +47,21 @@ #include <net/udp.h> #include <net/tcp.h> +#include <trace/events/sunrpc.h> + #include "sunrpc.h" + +static void xs_close(struct rpc_xprt *xprt); + /* * xprtsock tunables */ -unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE; -unsigned int xprt_tcp_slot_table_entries = RPC_DEF_SLOT_TABLE; +static unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE; +static unsigned int xprt_tcp_slot_table_entries = RPC_MIN_SLOT_TABLE; +static unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE; -unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; -unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; +static unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; +static unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; #define XS_TCP_LINGER_TO (15U * HZ) static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; @@ -70,6 +79,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE; +static unsigned int max_tcp_slot_table_limit = RPC_MAX_SLOT_TABLE_LIMIT; static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT; static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT; @@ -79,7 +89,7 @@ static struct ctl_table_header *sunrpc_table_header; * FIXME: changing the UDP slot table size should also resize the UDP * socket buffers for existing UDP transports */ -static ctl_table xs_tunables_table[] = { +static struct ctl_table xs_tunables_table[] = { { .procname = "udp_slot_table_entries", .data = &xprt_udp_slot_table_entries, @@ -99,6 +109,15 @@ static ctl_table xs_tunables_table[] = { .extra2 = &max_slot_table_size }, { + .procname = "tcp_max_slot_table_entries", + .data = &xprt_max_tcp_slot_table_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_slot_table_size, + .extra2 = &max_tcp_slot_table_limit + }, + { .procname = "min_resvport", .data = &xprt_min_resvport, .maxlen = sizeof(unsigned int), @@ -126,7 +145,7 @@ static ctl_table xs_tunables_table[] = { { }, }; -static ctl_table sunrpc_table[] = { +static struct ctl_table sunrpc_table[] = { { .procname = "sunrpc", .mode = 0555, @@ -235,7 +254,7 @@ struct sock_xprt { /* * Saved socket callback addresses */ - void (*old_data_ready)(struct sock *, int); + void (*old_data_ready)(struct sock *); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); void (*old_error_report)(struct sock *); @@ -256,11 +275,21 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) +{ + return (struct rpc_xprt *) sk->sk_user_data; +} + 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 +305,34 @@ 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); } @@ -359,8 +399,10 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, return kernel_sendmsg(sock, &msg, NULL, 0, 0); } -static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more) +static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy) { + ssize_t (*do_sendpage)(struct socket *sock, struct page *page, + int offset, size_t size, int flags); struct page **ppage; unsigned int remainder; int err, sent = 0; @@ -369,6 +411,9 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i base += xdr->page_base; ppage = xdr->pages + (base >> PAGE_SHIFT); base &= ~PAGE_MASK; + do_sendpage = sock->ops->sendpage; + if (!zerocopy) + do_sendpage = sock_no_sendpage; for(;;) { unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder); int flags = XS_SENDMSG_FLAGS; @@ -376,7 +421,7 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i remainder -= len; if (remainder != 0 || more) flags |= MSG_MORE; - err = sock->ops->sendpage(sock, *ppage, base, len, flags); + err = do_sendpage(sock, *ppage, base, len, flags); if (remainder == 0 || err != len) break; sent += err; @@ -397,9 +442,10 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i * @addrlen: UDP only -- length of destination address * @xdr: buffer containing this request * @base: starting position in the buffer + * @zerocopy: true if it is safe to use sendpage() * */ -static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base) +static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy) { unsigned int remainder = xdr->len - base; int err, sent = 0; @@ -427,7 +473,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (base < xdr->page_len) { unsigned int len = xdr->page_len - base; remainder -= len; - err = xs_send_pagedata(sock, xdr, base, remainder != 0); + err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy); if (remainder == 0 || err != len) goto out; sent += err; @@ -464,7 +510,8 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - int ret = 0; + struct sock *sk = transport->inet; + int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", task->tk_pid, req->rq_slen - req->rq_bytes_sent, @@ -476,13 +523,12 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { - ret = -EAGAIN; /* * Notify TCP that we're limited by the application * window size */ set_bit(SOCK_NOSPACE, &transport->sock->flags); - transport->inet->sk_write_pending++; + sk->sk_write_pending++; /* ...and wait for more buffer space */ xprt_wait_for_buffer_space(task, xs_nospace_callback); } @@ -492,9 +538,76 @@ static int xs_nospace(struct rpc_task *task) } spin_unlock_bh(&xprt->transport_lock); + + /* Race breaker in case memory is freed before above code is called */ + sk->sk_write_space(sk); 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, true); + 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 @@ -504,7 +617,7 @@ static int xs_nospace(struct rpc_task *task) * 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_udp_send_request(struct rpc_task *task) { @@ -523,7 +636,7 @@ static int xs_udp_send_request(struct rpc_task *task) status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, - req->rq_bytes_sent); + req->rq_bytes_sent, true); dprintk("RPC: xs_udp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); @@ -570,15 +683,10 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct socket *sock = transport->sock; - if (sock != NULL) + if (sock != NULL) { kernel_sock_shutdown(sock, SHUT_WR); -} - -static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf) -{ - u32 reclen = buf->len - sizeof(rpc_fraghdr); - rpc_fraghdr *base = buf->head[0].iov_base; - *base = htonl(RPC_LAST_STREAM_FRAGMENT | reclen); + trace_rpc_socket_shutdown(xprt, sock); + } } /** @@ -590,7 +698,7 @@ static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf) * 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 * * XXX: In the case of soft timeouts, should we eventually give up * if sendmsg is not able to make progress? @@ -601,20 +709,28 @@ static int xs_tcp_send_request(struct rpc_task *task) 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; + bool zerocopy = true; 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, req->rq_svec->iov_len); + /* Don't use zero copy if this is a resend. If the RPC call + * completes while the socket holds a reference to the pages, + * then we may end up resending corrupted data. + */ + if (task->tk_flags & RPC_TASK_SENT) + zerocopy = false; /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ while (1) { status = xs_sendpages(transport->sock, - NULL, 0, xdr, req->rq_bytes_sent); + NULL, 0, xdr, req->rq_bytes_sent, + zerocopy); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); @@ -649,10 +765,10 @@ static int xs_tcp_send_request(struct rpc_task *task) dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); case -ECONNRESET: - case -EPIPE: xs_tcp_shutdown(xprt); case -ECONNREFUSED: case -ENOTCONN: + case -EPIPE: clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); } @@ -677,11 +793,13 @@ static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) if (task == NULL) goto out_release; req = task->tk_rqstp; + if (req == NULL) + goto out_release; if (req->rq_bytes_sent == 0) goto out_release; if (req->rq_bytes_sent == req->rq_snd_buf.len) goto out_release; - set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); out_release: xprt_release_xprt(xprt, task); } @@ -702,6 +820,33 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_error_report = transport->old_error_report; } +/** + * xs_error_report - callback to handle TCP socket state errors + * @sk: socket + * + * Note: we don't call sock_error() since there may be a rpc_task + * using the socket, and so we don't want to clear sk->sk_err. + */ +static void xs_error_report(struct sock *sk) +{ + struct rpc_xprt *xprt; + int err; + + read_lock_bh(&sk->sk_callback_lock); + if (!(xprt = xprt_from_sock(sk))) + goto out; + + err = -sk->sk_err; + if (err == 0) + goto out; + dprintk("RPC: xs_error_report client %p, error=%d...\n", + xprt, -err); + trace_rpc_socket_error(xprt, sk->sk_socket, err); + xprt_wake_pending_tasks(xprt, err); + out: + read_unlock_bh(&sk->sk_callback_lock); +} + static void xs_reset_transport(struct sock_xprt *transport) { struct socket *sock = transport->sock; @@ -710,6 +855,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + transport->srcport = 0; + write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; transport->sock = NULL; @@ -719,8 +866,7 @@ static void xs_reset_transport(struct sock_xprt *transport) xs_restore_old_callbacks(transport, sk); write_unlock_bh(&sk->sk_callback_lock); - sk->sk_no_check = 0; - + trace_rpc_socket_close(&transport->xprt, sock); sock_release(sock); } @@ -740,14 +886,16 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); + cancel_delayed_work_sync(&transport->connect_worker); + xs_reset_transport(transport); xprt->reestablish_timeout = 0; - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); xprt_disconnect_done(xprt); } @@ -759,6 +907,12 @@ static void xs_tcp_close(struct rpc_xprt *xprt) xs_tcp_shutdown(xprt); } +static void xs_xprt_free(struct rpc_xprt *xprt) +{ + xs_free_peer_addresses(xprt); + xprt_free(xprt); +} + /** * xs_destroy - prepare to shutdown a transport * @xprt: doomed transport @@ -766,21 +920,90 @@ static void xs_tcp_close(struct rpc_xprt *xprt) */ static void xs_destroy(struct rpc_xprt *xprt) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - dprintk("RPC: xs_destroy xprt %p\n", xprt); - cancel_rearming_delayed_work(&transport->connect_worker); - xs_close(xprt); - xs_free_peer_addresses(xprt); - xprt_free(xprt); + xs_xprt_free(xprt); module_put(THIS_MODULE); } -static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) +static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) { - return (struct rpc_xprt *) sk->sk_user_data; + 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) +{ + 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; + + 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); } /** @@ -789,7 +1012,7 @@ static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) * @len: how much data to read * */ -static void xs_udp_data_ready(struct sock *sk, int len) +static void xs_udp_data_ready(struct sock *sk) { struct rpc_task *task; struct rpc_xprt *xprt; @@ -807,9 +1030,6 @@ static void xs_udp_data_ready(struct sock *sk, int len) if ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL) goto out; - if (xprt->shutdown) - goto dropit; - repsize = skb->len - sizeof(struct udphdr); if (repsize < 4) { dprintk("RPC: impossible RPC reply size %d!\n", repsize); @@ -840,10 +1060,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS); - /* Something worked... */ - dst_confirm(skb_dst(skb)); - - xprt_adjust_cwnd(task, copied); + xprt_adjust_cwnd(xprt, task, copied); xprt_complete_rqst(task, copied); out_unlock: @@ -854,6 +1071,16 @@ static void xs_udp_data_ready(struct sock *sk, int len) read_unlock_bh(&sk->sk_callback_lock); } +/* + * Helper function to force a TCP close if the server is sending + * junk and/or it has put us in CLOSE_WAIT + */ +static void xs_tcp_force_close(struct rpc_xprt *xprt) +{ + set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); + xprt_force_disconnect(xprt); +} + static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -880,7 +1107,7 @@ static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_rea /* Sanity check of the record length */ if (unlikely(transport->tcp_reclen < 8)) { dprintk("RPC: invalid TCP record fragment length\n"); - xprt_force_disconnect(xprt); + xs_tcp_force_close(xprt); return; } dprintk("RPC: reading TCP record fragment of length %d\n", @@ -961,7 +1188,7 @@ static inline void xs_tcp_read_calldir(struct sock_xprt *transport, break; default: dprintk("RPC: invalid request message type\n"); - xprt_force_disconnect(&transport->xprt); + xs_tcp_force_close(&transport->xprt); } xs_tcp_check_fraghdr(transport); } @@ -1074,7 +1301,7 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, return 0; } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Obtains an rpc_rqst previously allocated and invokes the common * tcp read code to read the data. The result is placed in the callback @@ -1082,41 +1309,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, * If we're unable to obtain the rpc_rqst we schedule the closing of the * connection and return -1. */ -static inline int xs_tcp_read_callback(struct rpc_xprt *xprt, +static int xs_tcp_read_callback(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct rpc_rqst *req; - req = xprt_alloc_bc_request(xprt); + /* Look up and lock the request corresponding to the given XID */ + spin_lock(&xprt->transport_lock); + req = xprt_lookup_bc_request(xprt, transport->tcp_xid); if (req == NULL) { + spin_unlock(&xprt->transport_lock); printk(KERN_WARNING "Callback slot table overflowed\n"); xprt_force_disconnect(xprt); return -1; } - req->rq_xid = transport->tcp_xid; dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid)); xs_tcp_read_common(xprt, desc, req); - if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) { - struct svc_serv *bc_serv = xprt->bc_serv; - - /* - * Add callback request to callback list. The callback - * service sleeps on the sv_cb_waitq waiting for new - * requests. Wake it up after adding enqueing the - * request. - */ - dprintk("RPC: add callback request to list\n"); - spin_lock(&bc_serv->sv_cb_lock); - list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); - spin_unlock(&bc_serv->sv_cb_lock); - wake_up(&bc_serv->sv_cb_waitq); - } - - req->rq_private_buf.len = transport->tcp_copied; + if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) + xprt_complete_bc_request(req, transport->tcp_copied); + spin_unlock(&xprt->transport_lock); return 0; } @@ -1137,7 +1352,7 @@ static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, { return xs_tcp_read_reply(xprt, desc); } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * Read data off the transport. This can be either an RPC_CALL or an @@ -1220,7 +1435,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns * @bytes: how much data to read * */ -static void xs_tcp_data_ready(struct sock *sk, int bytes) +static void xs_tcp_data_ready(struct sock *sk) { struct rpc_xprt *xprt; read_descriptor_t rd_desc; @@ -1231,9 +1446,6 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; - if (xprt->shutdown) - goto out; - /* Any data means we had a useful conversation, so * the we don't need to delay the next reconnect */ @@ -1281,12 +1493,19 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt) xprt_clear_connecting(xprt); } -static void xs_sock_mark_closed(struct rpc_xprt *xprt) +static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); +} + +static void xs_sock_mark_closed(struct rpc_xprt *xprt) +{ + xs_sock_reset_connection_flags(xprt); /* Mark transport as closed and wake up all pending tasks */ xprt_disconnect_done(xprt); } @@ -1310,6 +1529,7 @@ static void xs_tcp_state_change(struct sock *sk) sock_flag(sk, SOCK_ZAPPED), sk->sk_shutdown); + trace_rpc_socket_state_change(xprt, sk->sk_socket); switch (sk->sk_state) { case TCP_ESTABLISHED: spin_lock(&xprt->transport_lock); @@ -1323,6 +1543,7 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_copied = 0; transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; + xprt->connect_cookie++; xprt_wake_pending_tasks(xprt, -EAGAIN); } @@ -1333,17 +1554,17 @@ static void xs_tcp_state_change(struct sock *sk) xprt->connect_cookie++; xprt->reestablish_timeout = 0; set_bit(XPRT_CLOSING, &xprt->state); - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(XPRT_CONNECTED, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); break; case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ - xprt_force_disconnect(xprt); - case TCP_SYN_SENT: xprt->connect_cookie++; + clear_bit(XPRT_CONNECTED, &xprt->state); + xs_tcp_force_close(xprt); case TCP_CLOSING: /* * If the server closed down the connection, make sure that @@ -1355,9 +1576,9 @@ static void xs_tcp_state_change(struct sock *sk) case TCP_LAST_ACK: set_bit(XPRT_CLOSING, &xprt->state); xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(XPRT_CONNECTED, &xprt->state); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); break; case TCP_CLOSE: xs_tcp_cancel_linger_timeout(xprt); @@ -1367,25 +1588,6 @@ static void xs_tcp_state_change(struct sock *sk) read_unlock_bh(&sk->sk_callback_lock); } -/** - * xs_error_report - callback mainly for catching socket errors - * @sk: socket - */ -static void xs_error_report(struct sock *sk) -{ - struct rpc_xprt *xprt; - - read_lock_bh(&sk->sk_callback_lock); - if (!(xprt = xprt_from_sock(sk))) - goto out; - dprintk("RPC: %s client %p...\n" - "RPC: error %d\n", - __func__, xprt, sk->sk_err); - xprt_wake_pending_tasks(xprt, -EAGAIN); -out: - read_unlock_bh(&sk->sk_callback_lock); -} - static void xs_write_space(struct sock *sk) { struct socket *sock; @@ -1439,7 +1641,7 @@ 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_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) xs_write_space(sk); read_unlock_bh(&sk->sk_callback_lock); @@ -1489,15 +1691,15 @@ static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t * * Adjust the congestion window after a retransmit timeout has occurred. */ -static void xs_udp_timer(struct rpc_task *task) +static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task) { - xprt_adjust_cwnd(task, -ETIMEDOUT); + xprt_adjust_cwnd(xprt, task, -ETIMEDOUT); } static unsigned short xs_get_random_port(void) { unsigned short range = xprt_max_resvport - xprt_min_resvport; - unsigned short rand = (unsigned short) net_random() % range; + unsigned short rand = (unsigned short) prandom_u32() % range; return rand + xprt_min_resvport; } @@ -1569,16 +1771,36 @@ 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) +{ + rcu_read_lock(); + xprt_set_bound(rcu_dereference(task->tk_client->cl_xprt)); + rcu_read_unlock(); +} + +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; + + 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; - BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC", &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]); } @@ -1587,14 +1809,20 @@ static inline void xs_reclassify_socket6(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC", &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]); } static inline void xs_reclassify_socket(int family, struct socket *sock) { + WARN_ON_ONCE(sock_owned_by_user(sock->sk)); + if (sock_owned_by_user(sock->sk)) + return; + switch (family) { + case AF_LOCAL: + xs_reclassify_socketu(sock); + break; case AF_INET: xs_reclassify_socket4(sock); break; @@ -1604,6 +1832,10 @@ 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) { } @@ -1617,6 +1849,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } #endif +static void xs_dummy_setup_socket(struct work_struct *work) +{ +} + static struct socket *xs_create_sock(struct rpc_xprt *xprt, struct sock_xprt *transport, int family, int type, int protocol) { @@ -1631,7 +1867,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, } xs_reclassify_socket(family, sock); - if (xs_bind(transport, sock)) { + err = xs_bind(transport, sock); + if (err) { sock_release(sock); goto out; } @@ -1641,6 +1878,158 @@ 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 + */ +static int xs_local_setup_socket(struct sock_xprt *transport) +{ + struct rpc_xprt *xprt = &transport->xprt; + struct socket *sock; + int status = -EIO; + + current->flags |= PF_FSTRANS; + + 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); + trace_rpc_socket_connect(xprt, sock, status); + 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; + case -ECONNREFUSED: + dprintk("RPC: xprt %p: connection refused for %s\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); + current->flags &= ~PF_FSTRANS; + return status; +} + +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)) { + /* + * We want the AF_LOCAL connect to be resolved in the + * filesystem namespace of the process making the rpc + * call. Thus we connect synchronously. + * + * If we want to support asynchronous AF_LOCAL calls, + * we'll need to figure out how to pass a namespace to + * connect. + */ + rpc_exit(task, -ENOTCONN); + return; + } + ret = xs_local_setup_socket(transport); + if (ret && !RPC_IS_SOFTCONN(task)) + msleep_interruptible(15000); +} + +#ifdef CONFIG_SUNRPC_SWAP +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + + if (xprt->swapper) + sk_set_memalloc(transport->inet); +} + +/** + * xs_swapper - Tag this transport as being used for swap. + * @xprt: transport to tag + * @enable: enable/disable + * + */ +int xs_swapper(struct rpc_xprt *xprt, int enable) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + int err = 0; + + if (enable) { + xprt->swapper++; + xs_set_memalloc(xprt); + } else if (xprt->swapper) { + xprt->swapper--; + sk_clear_memalloc(transport->inet); + } + + return err; +} +EXPORT_SYMBOL_GPL(xs_swapper); +#else +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ +} +#endif + static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1655,8 +2044,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_error_report = xs_error_report; - sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; xprt_set_connected(xprt); @@ -1665,6 +2052,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->sock = sock; transport->inet = sk; + xs_set_memalloc(xprt); + write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); @@ -1678,8 +2067,7 @@ static void xs_udp_setup_socket(struct work_struct *work) struct socket *sock = transport->sock; int status = -EIO; - if (xprt->shutdown) - goto out; + current->flags |= PF_FSTRANS; /* Start by resetting any existing state */ xs_reset_transport(transport); @@ -1695,10 +2083,12 @@ static void xs_udp_setup_socket(struct work_struct *work) xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); + trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /* @@ -1719,11 +2109,11 @@ static void xs_abort_connection(struct sock_xprt *transport) memset(&any, 0, sizeof(any)); any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); + trace_rpc_socket_reset_connection(&transport->xprt, + transport->sock, result); if (!result) - xs_sock_mark_closed(&transport->xprt); - else - dprintk("RPC: AF_UNSPEC connect return code %d\n", - result); + xs_sock_reset_connection_flags(&transport->xprt); + dprintk("RPC: AF_UNSPEC connect return code %d\n", result); } static void xs_tcp_reuse_connection(struct sock_xprt *transport) @@ -1755,9 +2145,23 @@ 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; + unsigned int keepidle = xprt->timeout->to_initval / HZ; + unsigned int keepcnt = xprt->timeout->to_retries + 1; + unsigned int opt_on = 1; + + /* 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)); write_lock_bh(&sk->sk_callback_lock); @@ -1786,12 +2190,23 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) } if (!xprt_bound(xprt)) - return -ENOTCONN; + goto out; + + xs_set_memalloc(xprt); /* 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! */ + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + } +out: + return ret; } /** @@ -1810,8 +2225,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) struct rpc_xprt *xprt = &transport->xprt; int status = -EIO; - if (xprt->shutdown) - goto out; + current->flags |= PF_FSTRANS; if (!sock) { clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); @@ -1840,6 +2254,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); + trace_rpc_socket_connect(xprt, sock, status); dprintk("RPC: %p connect status %d connected %d sock state %d\n", xprt, -status, xprt_connected(xprt), sock->sk->sk_state); @@ -1851,22 +2266,22 @@ static void xs_tcp_setup_socket(struct work_struct *work) /* We're probably in TIME_WAIT. Get rid of existing socket, * and retry */ - set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); - xprt_force_disconnect(xprt); + xs_tcp_force_close(xprt); break; - case -ECONNREFUSED: - case -ECONNRESET: - case -ENETUNREACH: - /* retry with existing socket, after a delay */ case 0: case -EINPROGRESS: case -EALREADY: xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; return; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. */ + case -ECONNREFUSED: + case -ECONNRESET: + case -ENETUNREACH: + /* retry with existing socket, after a delay */ goto out; } out_eagain: @@ -1874,10 +2289,12 @@ out_eagain: out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /** * xs_connect - connect a socket to a remote endpoint + * @xprt: pointer to transport structure * @task: address of RPC task that manages state of connect request * * TCP: If the remote end dropped the connection, delay reconnecting. @@ -1889,9 +2306,8 @@ out: * If a UDP socket connect fails, the delay behavior here prevents * retry floods (hard mounts). */ -static void xs_connect(struct rpc_task *task) +static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { @@ -1914,6 +2330,35 @@ 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 %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, + xprt->stat.max_slots, + xprt->stat.sending_u, + xprt->stat.pending_u); +} + +/** * xs_udp_print_stats - display UDP socket-specifc stats * @xprt: rpc_xprt struct containing statistics * @seq: output file @@ -1923,14 +2368,18 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n", + seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %llu %llu " + "%lu %llu %llu\n", transport->srcport, xprt->stat.bind_count, xprt->stat.sends, xprt->stat.recvs, xprt->stat.bad_xids, xprt->stat.req_u, - xprt->stat.bklog_u); + xprt->stat.bklog_u, + xprt->stat.max_slots, + xprt->stat.sending_u, + xprt->stat.pending_u); } /** @@ -1947,7 +2396,8 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) if (xprt_connected(xprt)) idle_time = (long)(jiffies - xprt->last_used) / HZ; - seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n", + seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu " + "%llu %llu %lu %llu %llu\n", transport->srcport, xprt->stat.bind_count, xprt->stat.connect_count, @@ -1957,7 +2407,10 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) xprt->stat.recvs, xprt->stat.bad_xids, xprt->stat.req_u, - xprt->stat.bklog_u); + xprt->stat.bklog_u, + xprt->stat.max_slots, + xprt->stat.sending_u, + xprt->stat.pending_u); } /* @@ -1970,9 +2423,11 @@ static void *bc_malloc(struct rpc_task *task, size_t size) struct page *page; struct rpc_buffer *buf; - BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer)); - page = alloc_page(GFP_KERNEL); + WARN_ON_ONCE(size > PAGE_SIZE - sizeof(struct rpc_buffer)); + if (size > PAGE_SIZE - sizeof(struct rpc_buffer)) + return NULL; + page = alloc_page(GFP_KERNEL); if (!page) return NULL; @@ -2011,10 +2466,7 @@ 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; @@ -2037,7 +2489,6 @@ static int bc_send_request(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct svc_xprt *xprt; - struct svc_sock *svsk; u32 len; dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid)); @@ -2045,7 +2496,6 @@ static int bc_send_request(struct rpc_task *task) * Get the server socket associated with this callback xprt */ xprt = req->rq_xprt->bc_xprt; - svsk = container_of(xprt, struct svc_sock, sk_xprt); /* * Grab the mutex to serialize data as the connection is shared @@ -2084,12 +2534,33 @@ static void bc_close(struct rpc_xprt *xprt) static void bc_destroy(struct rpc_xprt *xprt) { + dprintk("RPC: bc_destroy xprt %p\n", xprt); + + xs_xprt_free(xprt); + module_put(THIS_MODULE); } +static struct rpc_xprt_ops xs_local_ops = { + .reserve_xprt = xprt_reserve_xprt, + .release_xprt = xs_tcp_release_xprt, + .alloc_slot = xprt_alloc_slot, + .rpcbind = xs_local_rpcbind, + .set_port = xs_local_set_port, + .connect = xs_local_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, .release_xprt = xprt_release_xprt_cong, + .alloc_slot = xprt_alloc_slot, .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, @@ -2107,6 +2578,7 @@ static struct rpc_xprt_ops xs_udp_ops = { static struct rpc_xprt_ops xs_tcp_ops = { .reserve_xprt = xprt_reserve_xprt, .release_xprt = xs_tcp_release_xprt, + .alloc_slot = xprt_lock_and_alloc_slot, .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, @@ -2126,6 +2598,7 @@ static struct rpc_xprt_ops xs_tcp_ops = { static struct rpc_xprt_ops bc_tcp_ops = { .reserve_xprt = xprt_reserve_xprt, .release_xprt = xprt_release_xprt, + .alloc_slot = xprt_alloc_slot, .buf_alloc = bc_malloc, .buf_free = bc_free, .send_request = bc_send_request, @@ -2147,6 +2620,8 @@ 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; @@ -2161,7 +2636,8 @@ static int xs_init_anyaddr(const int family, struct sockaddr *sap) } static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, - unsigned int slot_table_size) + unsigned int slot_table_size, + unsigned int max_slot_table_size) { struct rpc_xprt *xprt; struct sock_xprt *new; @@ -2171,7 +2647,8 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, return ERR_PTR(-EBADF); } - xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size); + xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size, + max_slot_table_size); if (xprt == NULL) { dprintk("RPC: xs_setup_xprt: couldn't allocate " "rpc_xprt\n"); @@ -2187,13 +2664,84 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, int err; err = xs_init_anyaddr(args->dstaddr->sa_family, (struct sockaddr *)&new->srcaddr); - if (err != 0) + if (err != 0) { + xprt_free(xprt); return ERR_PTR(err); + } } 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, + xprt_max_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; + + INIT_DELAYED_WORK(&transport->connect_worker, + xs_dummy_setup_socket); + + 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); + 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); + 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: + xs_xprt_free(xprt); + return ret; +} + static const struct rpc_timeout xs_udp_default_timeout = { .to_initval = 5 * HZ, .to_maxval = 30 * HZ, @@ -2213,7 +2761,8 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) struct sock_xprt *transport; struct rpc_xprt *ret; - xprt = xs_setup_xprt(args, xprt_udp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_udp_slot_table_entries, + xprt_udp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2267,7 +2816,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) return xprt; ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } @@ -2288,8 +2837,13 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) struct rpc_xprt *xprt; struct sock_xprt *transport; struct rpc_xprt *ret; + unsigned int max_slot_table_size = xprt_max_tcp_slot_table_entries; + + if (args->flags & XPRT_CREATE_INFINITE_SLOTS) + max_slot_table_size = RPC_MAX_SLOT_TABLE_LIMIT; - xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + max_slot_table_size); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2337,12 +2891,11 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->address_strings[RPC_DISPLAY_ADDR], xprt->address_strings[RPC_DISPLAY_PROTO]); - if (try_module_get(THIS_MODULE)) return xprt; ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } @@ -2359,7 +2912,8 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) struct svc_sock *bc_sock; struct rpc_xprt *ret; - xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + xprt_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2375,16 +2929,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->reestablish_timeout = 0; xprt->idle_timeout = 0; - /* - * The backchannel uses the same socket connection as the - * forechannel - */ - xprt->bc_xprt = args->bc_xprt; - bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); - bc_sock->sk_bc_xprt = xprt; - transport->sock = bc_sock->sk_sock; - transport->inet = bc_sock->sk_sk; - xprt->ops = &bc_tcp_ops; switch (addr->sa_family) { @@ -2407,20 +2951,43 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->address_strings[RPC_DISPLAY_PROTO]); /* + * Once we've associated a backchannel xprt with a connection, + * we want to keep it around as long as the connection lasts, + * in case we need to start using it for a backchannel again; + * this reference won't be dropped until bc_xprt is destroyed. + */ + xprt_get(xprt); + args->bc_xprt->xpt_bc_xprt = xprt; + xprt->bc_xprt = args->bc_xprt; + bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); + transport->sock = bc_sock->sk_sock; + transport->inet = bc_sock->sk_sk; + + /* * Since we don't want connections for the backchannel, we set * the xprt status to connected */ xprt_set_connected(xprt); - if (try_module_get(THIS_MODULE)) return xprt; + + args->bc_xprt->xpt_bc_xprt = NULL; + xprt_put(xprt); ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); 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", @@ -2456,6 +3023,7 @@ 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); @@ -2476,6 +3044,7 @@ 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); @@ -2531,8 +3100,26 @@ static struct kernel_param_ops param_ops_slot_table_size = { #define param_check_slot_table_size(name, p) \ __param_check(name, p, unsigned int); +static int param_set_max_slot_table_size(const char *val, + const struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE_LIMIT); +} + +static struct kernel_param_ops param_ops_max_slot_table_size = { + .set = param_set_max_slot_table_size, + .get = param_get_uint, +}; + +#define param_check_max_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, slot_table_size, 0644); +module_param_named(tcp_max_slot_table_entries, xprt_max_tcp_slot_table_entries, + max_slot_table_size, 0644); module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, slot_table_size, 0644); |