diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-27 21:03:20 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-27 21:03:20 +0200 |
commit | 468fc7ed5537615efe671d94248446ac24679773 (patch) | |
tree | 27bc9de792e863d6ec1630927b77ac9e7dabb38a /net/rxrpc | |
parent | Merge tag 'for-linus-4.8-rc0-tag' of git://git.kernel.org/pub/scm/linux/kerne... (diff) | |
parent | xgene: Fix build warning with ACPI disabled. (diff) | |
download | linux-468fc7ed5537615efe671d94248446ac24679773.tar.xz linux-468fc7ed5537615efe671d94248446ac24679773.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Unified UDP encapsulation offload methods for drivers, from
Alexander Duyck.
2) Make DSA binding more sane, from Andrew Lunn.
3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.
4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.
5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
packets as soon as the device sees them, with the option to mirror
the packet on TX via the same interface. From Brenden Blanco and
others.
6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.
7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.
8) Simplify netlink conntrack entry layout, from Florian Westphal.
9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
Schimmel, Yotam Gigi, and Jiri Pirko.
10) Add SKB array infrastructure and convert tun and macvtap over to it.
From Michael S Tsirkin and Jason Wang.
11) Support qdisc packet injection in pktgen, from John Fastabend.
12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.
13) Add NV congestion control support to TCP, from Lawrence Brakmo.
14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.
15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.
16) Support MPLS over IPV4, from Simon Horman.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
xgene: Fix build warning with ACPI disabled.
be2net: perform temperature query in adapter regardless of its interface state
l2tp: Correctly return -EBADF from pppol2tp_getname.
net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
net: ipmr/ip6mr: update lastuse on entry change
macsec: ensure rx_sa is set when validation is disabled
tipc: dump monitor attributes
tipc: add a function to get the bearer name
tipc: get monitor threshold for the cluster
tipc: make cluster size threshold for monitoring configurable
tipc: introduce constants for tipc address validation
net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
MAINTAINERS: xgene: Add driver and documentation path
Documentation: dtb: xgene: Add MDIO node
dtb: xgene: Add MDIO node
drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
drivers: net: xgene: Use exported functions
drivers: net: xgene: Enable MDIO driver
drivers: net: xgene: Add backward compatibility
drivers: net: phy: xgene: Add MDIO driver
...
Diffstat (limited to '')
-rw-r--r-- | net/rxrpc/Makefile | 37 | ||||
-rw-r--r-- | net/rxrpc/af_rxrpc.c | 287 | ||||
-rw-r--r-- | net/rxrpc/ar-connection.c | 927 | ||||
-rw-r--r-- | net/rxrpc/ar-error.c | 230 | ||||
-rw-r--r-- | net/rxrpc/ar-internal.h | 515 | ||||
-rw-r--r-- | net/rxrpc/ar-local.c | 415 | ||||
-rw-r--r-- | net/rxrpc/ar-peer.c | 303 | ||||
-rw-r--r-- | net/rxrpc/ar-transport.c | 284 | ||||
-rw-r--r-- | net/rxrpc/call_accept.c (renamed from net/rxrpc/ar-accept.c) | 76 | ||||
-rw-r--r-- | net/rxrpc/call_event.c (renamed from net/rxrpc/ar-ack.c) | 51 | ||||
-rw-r--r-- | net/rxrpc/call_object.c (renamed from net/rxrpc/ar-call.c) | 558 | ||||
-rw-r--r-- | net/rxrpc/conn_client.c | 372 | ||||
-rw-r--r-- | net/rxrpc/conn_event.c (renamed from net/rxrpc/ar-connevent.c) | 73 | ||||
-rw-r--r-- | net/rxrpc/conn_object.c | 340 | ||||
-rw-r--r-- | net/rxrpc/conn_service.c | 230 | ||||
-rw-r--r-- | net/rxrpc/input.c (renamed from net/rxrpc/ar-input.c) | 110 | ||||
-rw-r--r-- | net/rxrpc/insecure.c | 7 | ||||
-rw-r--r-- | net/rxrpc/key.c (renamed from net/rxrpc/ar-key.c) | 6 | ||||
-rw-r--r-- | net/rxrpc/local_event.c | 116 | ||||
-rw-r--r-- | net/rxrpc/local_object.c | 390 | ||||
-rw-r--r-- | net/rxrpc/misc.c | 6 | ||||
-rw-r--r-- | net/rxrpc/output.c (renamed from net/rxrpc/ar-output.c) | 233 | ||||
-rw-r--r-- | net/rxrpc/peer_event.c | 281 | ||||
-rw-r--r-- | net/rxrpc/peer_object.c | 315 | ||||
-rw-r--r-- | net/rxrpc/proc.c (renamed from net/rxrpc/ar-proc.c) | 62 | ||||
-rw-r--r-- | net/rxrpc/recvmsg.c (renamed from net/rxrpc/ar-recvmsg.c) | 10 | ||||
-rw-r--r-- | net/rxrpc/rxkad.c | 263 | ||||
-rw-r--r-- | net/rxrpc/security.c (renamed from net/rxrpc/ar-security.c) | 8 | ||||
-rw-r--r-- | net/rxrpc/skbuff.c (renamed from net/rxrpc/ar-skbuff.c) | 2 | ||||
-rw-r--r-- | net/rxrpc/sysctl.c | 12 | ||||
-rw-r--r-- | net/rxrpc/utils.c | 46 |
31 files changed, 3079 insertions, 3486 deletions
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index e05a06ef2254..10f3f48a16a8 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -4,25 +4,28 @@ af-rxrpc-y := \ af_rxrpc.o \ - ar-accept.o \ - ar-ack.o \ - ar-call.o \ - ar-connection.o \ - ar-connevent.o \ - ar-error.o \ - ar-input.o \ - ar-key.o \ - ar-local.o \ - ar-output.o \ - ar-peer.o \ - ar-recvmsg.o \ - ar-security.o \ - ar-skbuff.o \ - ar-transport.o \ + call_accept.o \ + call_event.o \ + call_object.o \ + conn_client.o \ + conn_event.o \ + conn_object.o \ + conn_service.o \ + input.o \ insecure.o \ - misc.o + key.o \ + local_event.o \ + local_object.o \ + misc.o \ + output.o \ + peer_event.o \ + peer_object.o \ + recvmsg.o \ + security.o \ + skbuff.o \ + utils.o -af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o +af-rxrpc-$(CONFIG_PROC_FS) += proc.o af-rxrpc-$(CONFIG_RXKAD) += rxkad.o af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e45e94ca030f..88effadd4b16 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/net.h> @@ -31,8 +33,6 @@ unsigned int rxrpc_debug; // = RXRPC_DEBUG_KPROTO; module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(debug, "RxRPC debugging mask"); -static int sysctl_rxrpc_max_qlen __read_mostly = 10; - static struct proto rxrpc_proto; static const struct proto_ops rxrpc_rpc_ops; @@ -97,11 +97,13 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, srx->transport_len > len) return -EINVAL; - if (srx->transport.family != rx->proto) + if (srx->transport.family != rx->family) return -EAFNOSUPPORT; switch (srx->transport.family) { case AF_INET: + if (srx->transport_len < sizeof(struct sockaddr_in)) + return -EINVAL; _debug("INET: %x @ %pI4", ntohs(srx->transport.sin.sin_port), &srx->transport.sin.sin_addr); @@ -137,33 +139,33 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) lock_sock(&rx->sk); - if (rx->sk.sk_state != RXRPC_UNCONNECTED) { + if (rx->sk.sk_state != RXRPC_UNBOUND) { ret = -EINVAL; goto error_unlock; } memcpy(&rx->srx, srx, sizeof(rx->srx)); - /* Find or create a local transport endpoint to use */ local = rxrpc_lookup_local(&rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); goto error_unlock; } - rx->local = local; - if (srx->srx_service) { + if (rx->srx.srx_service) { write_lock_bh(&local->services_lock); list_for_each_entry(prx, &local->services, listen_link) { - if (prx->srx.srx_service == srx->srx_service) + if (prx->srx.srx_service == rx->srx.srx_service) goto service_in_use; } + rx->local = local; list_add_tail(&rx->listen_link, &local->services); write_unlock_bh(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; } else { + rx->local = local; rx->sk.sk_state = RXRPC_CLIENT_BOUND; } @@ -172,8 +174,9 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) return 0; service_in_use: - ret = -EADDRINUSE; write_unlock_bh(&local->services_lock); + rxrpc_put_local(local); + ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); error: @@ -188,6 +191,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct rxrpc_sock *rx = rxrpc_sk(sk); + unsigned int max; int ret; _enter("%p,%d", rx, backlog); @@ -195,20 +199,24 @@ static int rxrpc_listen(struct socket *sock, int backlog) lock_sock(&rx->sk); switch (rx->sk.sk_state) { - case RXRPC_UNCONNECTED: + case RXRPC_UNBOUND: ret = -EADDRNOTAVAIL; break; - case RXRPC_CLIENT_BOUND: - case RXRPC_CLIENT_CONNECTED: - default: - ret = -EBUSY; - break; case RXRPC_SERVER_BOUND: ASSERT(rx->local != NULL); + max = READ_ONCE(rxrpc_max_backlog); + ret = -EINVAL; + if (backlog == INT_MAX) + backlog = max; + else if (backlog < 0 || backlog > max) + break; sk->sk_max_ack_backlog = backlog; rx->sk.sk_state = RXRPC_SERVER_LISTENING; ret = 0; break; + default: + ret = -EBUSY; + break; } release_sock(&rx->sk); @@ -216,45 +224,10 @@ static int rxrpc_listen(struct socket *sock, int backlog) return ret; } -/* - * find a transport by address - */ -static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock, - struct sockaddr *addr, - int addr_len, int flags, - gfp_t gfp) -{ - struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr; - struct rxrpc_transport *trans; - struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - struct rxrpc_peer *peer; - - _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); - - ASSERT(rx->local != NULL); - ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED); - - if (rx->srx.transport_type != srx->transport_type) - return ERR_PTR(-ESOCKTNOSUPPORT); - if (rx->srx.transport.family != srx->transport.family) - return ERR_PTR(-EAFNOSUPPORT); - - /* find a remote transport endpoint from the local one */ - peer = rxrpc_get_peer(srx, gfp); - if (IS_ERR(peer)) - return ERR_CAST(peer); - - /* find a transport */ - trans = rxrpc_get_transport(rx->local, peer, gfp); - rxrpc_put_peer(peer); - _leave(" = %p", trans); - return trans; -} - /** * rxrpc_kernel_begin_call - Allow a kernel service to begin a call * @sock: The socket on which to make the call - * @srx: The address of the peer to contact (defaults to socket setting) + * @srx: The address of the peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use * @@ -271,51 +244,32 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, unsigned long user_call_ID, gfp_t gfp) { - struct rxrpc_conn_bundle *bundle; - struct rxrpc_transport *trans; + struct rxrpc_conn_parameters cp; struct rxrpc_call *call; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + int ret; _enter(",,%x,%lx", key_serial(key), user_call_ID); - lock_sock(&rx->sk); + ret = rxrpc_validate_address(rx, srx, sizeof(*srx)); + if (ret < 0) + return ERR_PTR(ret); - if (srx) { - trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx, - sizeof(*srx), 0, gfp); - if (IS_ERR(trans)) { - call = ERR_CAST(trans); - trans = NULL; - goto out_notrans; - } - } else { - trans = rx->trans; - if (!trans) { - call = ERR_PTR(-ENOTCONN); - goto out_notrans; - } - atomic_inc(&trans->usage); - } + lock_sock(&rx->sk); - if (!srx) - srx = &rx->srx; if (!key) key = rx->key; if (key && !key->payload.data[0]) key = NULL; /* a no-security key */ - bundle = rxrpc_get_bundle(rx, trans, key, srx->srx_service, gfp); - if (IS_ERR(bundle)) { - call = ERR_CAST(bundle); - goto out; - } + memset(&cp, 0, sizeof(cp)); + cp.local = rx->local; + cp.key = key; + cp.security_level = 0; + cp.exclusive = false; + cp.service_id = srx->srx_service; + call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp); - call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true, - gfp); - rxrpc_put_bundle(trans, bundle); -out: - rxrpc_put_transport(trans); -out_notrans: release_sock(&rx->sk); _leave(" = %p", call); return call; @@ -367,11 +321,8 @@ EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages); static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { - struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr; - struct sock *sk = sock->sk; - struct rxrpc_transport *trans; - struct rxrpc_local *local; - struct rxrpc_sock *rx = rxrpc_sk(sk); + struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); @@ -384,45 +335,28 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, lock_sock(&rx->sk); + ret = -EISCONN; + if (test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) + goto error; + switch (rx->sk.sk_state) { - case RXRPC_UNCONNECTED: - /* find a local transport endpoint if we don't have one already */ - ASSERTCMP(rx->local, ==, NULL); - rx->srx.srx_family = AF_RXRPC; - rx->srx.srx_service = 0; - rx->srx.transport_type = srx->transport_type; - rx->srx.transport_len = sizeof(sa_family_t); - rx->srx.transport.family = srx->transport.family; - local = rxrpc_lookup_local(&rx->srx); - if (IS_ERR(local)) { - release_sock(&rx->sk); - return PTR_ERR(local); - } - rx->local = local; - rx->sk.sk_state = RXRPC_CLIENT_BOUND; + case RXRPC_UNBOUND: + rx->sk.sk_state = RXRPC_CLIENT_UNBOUND; + case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: break; - case RXRPC_CLIENT_CONNECTED: - release_sock(&rx->sk); - return -EISCONN; default: - release_sock(&rx->sk); - return -EBUSY; /* server sockets can't connect as well */ - } - - trans = rxrpc_name_to_transport(sock, addr, addr_len, flags, - GFP_KERNEL); - if (IS_ERR(trans)) { - release_sock(&rx->sk); - _leave(" = %ld", PTR_ERR(trans)); - return PTR_ERR(trans); + ret = -EBUSY; + goto error; } - rx->trans = trans; - rx->sk.sk_state = RXRPC_CLIENT_CONNECTED; + rx->connect_srx = *srx; + set_bit(RXRPC_SOCK_CONNECTED, &rx->flags); + ret = 0; +error: release_sock(&rx->sk); - return 0; + return ret; } /* @@ -436,7 +370,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, */ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { - struct rxrpc_transport *trans; + struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; @@ -453,48 +387,38 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) } } - trans = NULL; lock_sock(&rx->sk); - if (m->msg_name) { - ret = -EISCONN; - trans = rxrpc_name_to_transport(sock, m->msg_name, - m->msg_namelen, 0, GFP_KERNEL); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - } else { - trans = rx->trans; - if (trans) - atomic_inc(&trans->usage); - } - switch (rx->sk.sk_state) { - case RXRPC_SERVER_LISTENING: - if (!m->msg_name) { - ret = rxrpc_server_sendmsg(rx, m, len); - break; + case RXRPC_UNBOUND: + local = rxrpc_lookup_local(&rx->srx); + if (IS_ERR(local)) { + ret = PTR_ERR(local); + goto error_unlock; } - case RXRPC_SERVER_BOUND: + + rx->local = local; + rx->sk.sk_state = RXRPC_CLIENT_UNBOUND; + /* Fall through */ + + case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: - if (!m->msg_name) { - ret = -ENOTCONN; - break; + if (!m->msg_name && + test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) { + m->msg_name = &rx->connect_srx; + m->msg_namelen = sizeof(rx->connect_srx); } - case RXRPC_CLIENT_CONNECTED: - ret = rxrpc_client_sendmsg(rx, trans, m, len); + case RXRPC_SERVER_BOUND: + case RXRPC_SERVER_LISTENING: + ret = rxrpc_do_sendmsg(rx, m, len); break; default: - ret = -ENOTCONN; + ret = -EINVAL; break; } -out: +error_unlock: release_sock(&rx->sk); - if (trans) - rxrpc_put_transport(trans); _leave(" = %d", ret); return ret; } @@ -521,9 +445,9 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (optlen != 0) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; - set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags); + rx->exclusive = true; goto success; case RXRPC_SECURITY_KEY: @@ -531,7 +455,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (rx->key) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_request_key(rx, optval, optlen); goto error; @@ -541,7 +465,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (rx->key) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_server_keyring(rx, optval, optlen); goto error; @@ -551,7 +475,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (optlen != sizeof(unsigned int)) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = get_user(min_sec_level, (unsigned int __user *) optval); @@ -630,13 +554,13 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, return -ENOMEM; sock_init_data(sock, sk); - sk->sk_state = RXRPC_UNCONNECTED; + sk->sk_state = RXRPC_UNBOUND; sk->sk_write_space = rxrpc_write_space; - sk->sk_max_ack_backlog = sysctl_rxrpc_max_qlen; + sk->sk_max_ack_backlog = 0; sk->sk_destruct = rxrpc_sock_destructor; rx = rxrpc_sk(sk); - rx->proto = protocol; + rx->family = protocol; rx->calls = RB_ROOT; INIT_LIST_HEAD(&rx->listen_link); @@ -698,24 +622,8 @@ static int rxrpc_release_sock(struct sock *sk) flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - if (rx->conn) { - rxrpc_put_connection(rx->conn); - rx->conn = NULL; - } - - if (rx->bundle) { - rxrpc_put_bundle(rx->trans, rx->bundle); - rx->bundle = NULL; - } - if (rx->trans) { - rxrpc_put_transport(rx->trans); - rx->trans = NULL; - } - if (rx->local) { - rxrpc_put_local(rx->local); - rx->local = NULL; - } - + rxrpc_put_local(rx->local); + rx->local = NULL; key_put(rx->key); rx->key = NULL; key_put(rx->securities); @@ -796,49 +704,49 @@ static int __init af_rxrpc_init(void) "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); if (!rxrpc_call_jar) { - printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n"); + pr_notice("Failed to allocate call jar\n"); goto error_call_jar; } rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); if (!rxrpc_workqueue) { - printk(KERN_NOTICE "RxRPC: Failed to allocate work queue\n"); + pr_notice("Failed to allocate work queue\n"); goto error_work_queue; } ret = rxrpc_init_security(); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot initialise security\n"); + pr_crit("Cannot initialise security\n"); goto error_security; } ret = proto_register(&rxrpc_proto, 1); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register protocol\n"); + pr_crit("Cannot register protocol\n"); goto error_proto; } ret = sock_register(&rxrpc_family_ops); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register socket family\n"); + pr_crit("Cannot register socket family\n"); goto error_sock; } ret = register_key_type(&key_type_rxrpc); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register client key type\n"); + pr_crit("Cannot register client key type\n"); goto error_key_type; } ret = register_key_type(&key_type_rxrpc_s); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register server key type\n"); + pr_crit("Cannot register server key type\n"); goto error_key_type_s; } ret = rxrpc_sysctl_init(); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register sysctls\n"); + pr_crit("Cannot register sysctls\n"); goto error_sysctls; } @@ -858,9 +766,9 @@ error_key_type: error_sock: proto_unregister(&rxrpc_proto); error_proto: - destroy_workqueue(rxrpc_workqueue); -error_security: rxrpc_exit_security(); +error_security: + destroy_workqueue(rxrpc_workqueue); error_work_queue: kmem_cache_destroy(rxrpc_call_jar); error_call_jar: @@ -880,14 +788,9 @@ static void __exit af_rxrpc_exit(void) proto_unregister(&rxrpc_proto); rxrpc_destroy_all_calls(); rxrpc_destroy_all_connections(); - rxrpc_destroy_all_transports(); - rxrpc_destroy_all_peers(); - rxrpc_destroy_all_locals(); - ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0); + rxrpc_destroy_all_locals(); - _debug("flush scheduled work"); - flush_workqueue(rxrpc_workqueue); remove_proc_entry("rxrpc_conns", init_net.proc_net); remove_proc_entry("rxrpc_calls", init_net.proc_net); destroy_workqueue(rxrpc_workqueue); diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c deleted file mode 100644 index 97f4fae74bca..000000000000 --- a/net/rxrpc/ar-connection.c +++ /dev/null @@ -1,927 +0,0 @@ -/* RxRPC virtual connection handler - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/crypto.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include "ar-internal.h" - -/* - * Time till a connection expires after last use (in seconds). - */ -unsigned int rxrpc_connection_expiry = 10 * 60; - -static void rxrpc_connection_reaper(struct work_struct *work); - -LIST_HEAD(rxrpc_connections); -DEFINE_RWLOCK(rxrpc_connection_lock); -static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); - -/* - * allocate a new client connection bundle - */ -static struct rxrpc_conn_bundle *rxrpc_alloc_bundle(gfp_t gfp) -{ - struct rxrpc_conn_bundle *bundle; - - _enter(""); - - bundle = kzalloc(sizeof(struct rxrpc_conn_bundle), gfp); - if (bundle) { - INIT_LIST_HEAD(&bundle->unused_conns); - INIT_LIST_HEAD(&bundle->avail_conns); - INIT_LIST_HEAD(&bundle->busy_conns); - init_waitqueue_head(&bundle->chanwait); - atomic_set(&bundle->usage, 1); - } - - _leave(" = %p", bundle); - return bundle; -} - -/* - * compare bundle parameters with what we're looking for - * - return -ve, 0 or +ve - */ -static inline -int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle, - struct key *key, u16 service_id) -{ - return (bundle->service_id - service_id) ?: - ((unsigned long)bundle->key - (unsigned long)key); -} - -/* - * get bundle of client connections that a client socket can make use of - */ -struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx, - struct rxrpc_transport *trans, - struct key *key, - u16 service_id, - gfp_t gfp) -{ - struct rxrpc_conn_bundle *bundle, *candidate; - struct rb_node *p, *parent, **pp; - - _enter("%p{%x},%x,%hx,", - rx, key_serial(key), trans->debug_id, service_id); - - if (rx->trans == trans && rx->bundle) { - atomic_inc(&rx->bundle->usage); - return rx->bundle; - } - - /* search the extant bundles first for one that matches the specified - * user ID */ - spin_lock(&trans->client_lock); - - p = trans->bundles.rb_node; - while (p) { - bundle = rb_entry(p, struct rxrpc_conn_bundle, node); - - if (rxrpc_cmp_bundle(bundle, key, service_id) < 0) - p = p->rb_left; - else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0) - p = p->rb_right; - else - goto found_extant_bundle; - } - - spin_unlock(&trans->client_lock); - - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_bundle(gfp); - if (!candidate) { - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - - candidate->key = key_get(key); - candidate->service_id = service_id; - - spin_lock(&trans->client_lock); - - pp = &trans->bundles.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - bundle = rb_entry(parent, struct rxrpc_conn_bundle, node); - - if (rxrpc_cmp_bundle(bundle, key, service_id) < 0) - pp = &(*pp)->rb_left; - else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0) - pp = &(*pp)->rb_right; - else - goto found_extant_second; - } - - /* second search also failed; add the new bundle */ - bundle = candidate; - candidate = NULL; - - rb_link_node(&bundle->node, parent, pp); - rb_insert_color(&bundle->node, &trans->bundles); - spin_unlock(&trans->client_lock); - _net("BUNDLE new on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } - _leave(" = %p [new]", bundle); - return bundle; - - /* we found the bundle in the list immediately */ -found_extant_bundle: - atomic_inc(&bundle->usage); - spin_unlock(&trans->client_lock); - _net("BUNDLE old on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } - _leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage)); - return bundle; - - /* we found the bundle on the second time through the list */ -found_extant_second: - atomic_inc(&bundle->usage); - spin_unlock(&trans->client_lock); - kfree(candidate); - _net("BUNDLE old2 on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } - _leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage)); - return bundle; -} - -/* - * release a bundle - */ -void rxrpc_put_bundle(struct rxrpc_transport *trans, - struct rxrpc_conn_bundle *bundle) -{ - _enter("%p,%p{%d}",trans, bundle, atomic_read(&bundle->usage)); - - if (atomic_dec_and_lock(&bundle->usage, &trans->client_lock)) { - _debug("Destroy bundle"); - rb_erase(&bundle->node, &trans->bundles); - spin_unlock(&trans->client_lock); - ASSERT(list_empty(&bundle->unused_conns)); - ASSERT(list_empty(&bundle->avail_conns)); - ASSERT(list_empty(&bundle->busy_conns)); - ASSERTCMP(bundle->num_conns, ==, 0); - key_put(bundle->key); - kfree(bundle); - } - - _leave(""); -} - -/* - * allocate a new connection - */ -static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) -{ - struct rxrpc_connection *conn; - - _enter(""); - - conn = kzalloc(sizeof(struct rxrpc_connection), gfp); - if (conn) { - INIT_WORK(&conn->processor, &rxrpc_process_connection); - INIT_LIST_HEAD(&conn->bundle_link); - conn->calls = RB_ROOT; - skb_queue_head_init(&conn->rx_queue); - conn->security = &rxrpc_no_security; - rwlock_init(&conn->lock); - spin_lock_init(&conn->state_lock); - atomic_set(&conn->usage, 1); - conn->debug_id = atomic_inc_return(&rxrpc_debug_id); - conn->avail_calls = RXRPC_MAXCALLS; - conn->size_align = 4; - conn->header_size = sizeof(struct rxrpc_wire_header); - } - - _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); - return conn; -} - -/* - * assign a connection ID to a connection and add it to the transport's - * connection lookup tree - * - called with transport client lock held - */ -static void rxrpc_assign_connection_id(struct rxrpc_connection *conn) -{ - struct rxrpc_connection *xconn; - struct rb_node *parent, **p; - __be32 epoch; - u32 cid; - - _enter(""); - - epoch = conn->epoch; - - write_lock_bh(&conn->trans->conn_lock); - - conn->trans->conn_idcounter += RXRPC_CID_INC; - if (conn->trans->conn_idcounter < RXRPC_CID_INC) - conn->trans->conn_idcounter = RXRPC_CID_INC; - cid = conn->trans->conn_idcounter; - -attempt_insertion: - parent = NULL; - p = &conn->trans->client_conns.rb_node; - - while (*p) { - parent = *p; - xconn = rb_entry(parent, struct rxrpc_connection, node); - - if (epoch < xconn->epoch) - p = &(*p)->rb_left; - else if (epoch > xconn->epoch) - p = &(*p)->rb_right; - else if (cid < xconn->cid) - p = &(*p)->rb_left; - else if (cid > xconn->cid) - p = &(*p)->rb_right; - else - goto id_exists; - } - - /* we've found a suitable hole - arrange for this connection to occupy - * it */ - rb_link_node(&conn->node, parent, p); - rb_insert_color(&conn->node, &conn->trans->client_conns); - - conn->cid = cid; - write_unlock_bh(&conn->trans->conn_lock); - _leave(" [CID %x]", cid); - return; - - /* we found a connection with the proposed ID - walk the tree from that - * point looking for the next unused ID */ -id_exists: - for (;;) { - cid += RXRPC_CID_INC; - if (cid < RXRPC_CID_INC) { - cid = RXRPC_CID_INC; - conn->trans->conn_idcounter = cid; - goto attempt_insertion; - } - - parent = rb_next(parent); - if (!parent) - goto attempt_insertion; - - xconn = rb_entry(parent, struct rxrpc_connection, node); - if (epoch < xconn->epoch || - cid < xconn->cid) - goto attempt_insertion; - } -} - -/* - * add a call to a connection's call-by-ID tree - */ -static void rxrpc_add_call_ID_to_conn(struct rxrpc_connection *conn, - struct rxrpc_call *call) -{ - struct rxrpc_call *xcall; - struct rb_node *parent, **p; - __be32 call_id; - - write_lock_bh(&conn->lock); - - call_id = call->call_id; - p = &conn->calls.rb_node; - parent = NULL; - while (*p) { - parent = *p; - xcall = rb_entry(parent, struct rxrpc_call, conn_node); - - if (call_id < xcall->call_id) - p = &(*p)->rb_left; - else if (call_id > xcall->call_id) - p = &(*p)->rb_right; - else - BUG(); - } - - rb_link_node(&call->conn_node, parent, p); - rb_insert_color(&call->conn_node, &conn->calls); - - write_unlock_bh(&conn->lock); -} - -/* - * connect a call on an exclusive connection - */ -static int rxrpc_connect_exclusive(struct rxrpc_sock *rx, - struct rxrpc_transport *trans, - u16 service_id, - struct rxrpc_call *call, - gfp_t gfp) -{ - struct rxrpc_connection *conn; - int chan, ret; - - _enter(""); - - conn = rx->conn; - if (!conn) { - /* not yet present - create a candidate for a new connection - * and then redo the check */ - conn = rxrpc_alloc_connection(gfp); - if (!conn) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - conn->trans = trans; - conn->bundle = NULL; - conn->service_id = service_id; - conn->epoch = rxrpc_epoch; - conn->in_clientflag = 0; - conn->out_clientflag = RXRPC_CLIENT_INITIATED; - conn->cid = 0; - conn->state = RXRPC_CONN_CLIENT; - conn->avail_calls = RXRPC_MAXCALLS - 1; - conn->security_level = rx->min_sec_level; - conn->key = key_get(rx->key); - - ret = rxrpc_init_client_conn_security(conn); - if (ret < 0) { - key_put(conn->key); - kfree(conn); - _leave(" = %d [key]", ret); - return ret; - } - - write_lock_bh(&rxrpc_connection_lock); - list_add_tail(&conn->link, &rxrpc_connections); - write_unlock_bh(&rxrpc_connection_lock); - - spin_lock(&trans->client_lock); - atomic_inc(&trans->usage); - - _net("CONNECT EXCL new %d on TRANS %d", - conn->debug_id, conn->trans->debug_id); - - rxrpc_assign_connection_id(conn); - rx->conn = conn; - } else { - spin_lock(&trans->client_lock); - } - - /* we've got a connection with a free channel and we can now attach the - * call to it - * - we're holding the transport's client lock - * - we're holding a reference on the connection - */ - for (chan = 0; chan < RXRPC_MAXCALLS; chan++) - if (!conn->channels[chan]) - goto found_channel; - goto no_free_channels; - -found_channel: - atomic_inc(&conn->usage); - conn->channels[chan] = call; - call->conn = conn; - call->channel = chan; - call->cid = conn->cid | chan; - call->call_id = ++conn->call_counter; - - _net("CONNECT client on conn %d chan %d as call %x", - conn->debug_id, chan, call->call_id); - - spin_unlock(&trans->client_lock); - - rxrpc_add_call_ID_to_conn(conn, call); - _leave(" = 0"); - return 0; - -no_free_channels: - spin_unlock(&trans->client_lock); - _leave(" = -ENOSR"); - return -ENOSR; -} - -/* - * find a connection for a call - * - called in process context with IRQs enabled - */ -int rxrpc_connect_call(struct rxrpc_sock *rx, - struct rxrpc_transport *trans, - struct rxrpc_conn_bundle *bundle, - struct rxrpc_call *call, - gfp_t gfp) -{ - struct rxrpc_connection *conn, *candidate; - int chan, ret; - - DECLARE_WAITQUEUE(myself, current); - - _enter("%p,%lx,", rx, call->user_call_ID); - - if (test_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags)) - return rxrpc_connect_exclusive(rx, trans, bundle->service_id, - call, gfp); - - spin_lock(&trans->client_lock); - for (;;) { - /* see if the bundle has a call slot available */ - if (!list_empty(&bundle->avail_conns)) { - _debug("avail"); - conn = list_entry(bundle->avail_conns.next, - struct rxrpc_connection, - bundle_link); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - list_del_init(&conn->bundle_link); - bundle->num_conns--; - continue; - } - if (--conn->avail_calls == 0) - list_move(&conn->bundle_link, - &bundle->busy_conns); - ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS); - ASSERT(conn->channels[0] == NULL || - conn->channels[1] == NULL || - conn->channels[2] == NULL || - conn->channels[3] == NULL); - atomic_inc(&conn->usage); - break; - } - - if (!list_empty(&bundle->unused_conns)) { - _debug("unused"); - conn = list_entry(bundle->unused_conns.next, - struct rxrpc_connection, - bundle_link); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - list_del_init(&conn->bundle_link); - bundle->num_conns--; - continue; - } - ASSERTCMP(conn->avail_calls, ==, RXRPC_MAXCALLS); - conn->avail_calls = RXRPC_MAXCALLS - 1; - ASSERT(conn->channels[0] == NULL && - conn->channels[1] == NULL && - conn->channels[2] == NULL && - conn->channels[3] == NULL); - atomic_inc(&conn->usage); - list_move(&conn->bundle_link, &bundle->avail_conns); - break; - } - - /* need to allocate a new connection */ - _debug("get new conn [%d]", bundle->num_conns); - - spin_unlock(&trans->client_lock); - - if (signal_pending(current)) - goto interrupted; - - if (bundle->num_conns >= 20) { - _debug("too many conns"); - - if (!gfpflags_allow_blocking(gfp)) { - _leave(" = -EAGAIN"); - return -EAGAIN; - } - - add_wait_queue(&bundle->chanwait, &myself); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - if (bundle->num_conns < 20 || - !list_empty(&bundle->unused_conns) || - !list_empty(&bundle->avail_conns)) - break; - if (signal_pending(current)) - goto interrupted_dequeue; - schedule(); - } - remove_wait_queue(&bundle->chanwait, &myself); - __set_current_state(TASK_RUNNING); - spin_lock(&trans->client_lock); - continue; - } - - /* not yet present - create a candidate for a new connection and then - * redo the check */ - candidate = rxrpc_alloc_connection(gfp); - if (!candidate) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - candidate->trans = trans; - candidate->bundle = bundle; - candidate->service_id = bundle->service_id; - candidate->epoch = rxrpc_epoch; - candidate->in_clientflag = 0; - candidate->out_clientflag = RXRPC_CLIENT_INITIATED; - candidate->cid = 0; - candidate->state = RXRPC_CONN_CLIENT; - candidate->avail_calls = RXRPC_MAXCALLS; - candidate->security_level = rx->min_sec_level; - candidate->key = key_get(bundle->key); - - ret = rxrpc_init_client_conn_security(candidate); - if (ret < 0) { - key_put(candidate->key); - kfree(candidate); - _leave(" = %d [key]", ret); - return ret; - } - - write_lock_bh(&rxrpc_connection_lock); - list_add_tail(&candidate->link, &rxrpc_connections); - write_unlock_bh(&rxrpc_connection_lock); - - spin_lock(&trans->client_lock); - - list_add(&candidate->bundle_link, &bundle->unused_conns); - bundle->num_conns++; - atomic_inc(&bundle->usage); - atomic_inc(&trans->usage); - - _net("CONNECT new %d on TRANS %d", - candidate->debug_id, candidate->trans->debug_id); - - rxrpc_assign_connection_id(candidate); - candidate->security->prime_packet_security(candidate); - - /* leave the candidate lurking in zombie mode attached to the - * bundle until we're ready for it */ - rxrpc_put_connection(candidate); - candidate = NULL; - } - - /* we've got a connection with a free channel and we can now attach the - * call to it - * - we're holding the transport's client lock - * - we're holding a reference on the connection - * - we're holding a reference on the bundle - */ - for (chan = 0; chan < RXRPC_MAXCALLS; chan++) - if (!conn->channels[chan]) - goto found_channel; - ASSERT(conn->channels[0] == NULL || - conn->channels[1] == NULL || - conn->channels[2] == NULL || - conn->channels[3] == NULL); - BUG(); - -found_channel: - conn->channels[chan] = call; - call->conn = conn; - call->channel = chan; - call->cid = conn->cid | chan; - call->call_id = ++conn->call_counter; - - _net("CONNECT client on conn %d chan %d as call %x", - conn->debug_id, chan, call->call_id); - - ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS); - spin_unlock(&trans->client_lock); - - rxrpc_add_call_ID_to_conn(conn, call); - - _leave(" = 0"); - return 0; - -interrupted_dequeue: - remove_wait_queue(&bundle->chanwait, &myself); - __set_current_state(TASK_RUNNING); -interrupted: - _leave(" = -ERESTARTSYS"); - return -ERESTARTSYS; -} - -/* - * get a record of an incoming connection - */ -struct rxrpc_connection * -rxrpc_incoming_connection(struct rxrpc_transport *trans, - struct rxrpc_host_header *hdr) -{ - struct rxrpc_connection *conn, *candidate = NULL; - struct rb_node *p, **pp; - const char *new = "old"; - __be32 epoch; - u32 cid; - - _enter(""); - - ASSERT(hdr->flags & RXRPC_CLIENT_INITIATED); - - epoch = hdr->epoch; - cid = hdr->cid & RXRPC_CIDMASK; - - /* search the connection list first */ - read_lock_bh(&trans->conn_lock); - - p = trans->server_conns.rb_node; - while (p) { - conn = rb_entry(p, struct rxrpc_connection, node); - - _debug("maybe %x", conn->cid); - - if (epoch < conn->epoch) - p = p->rb_left; - else if (epoch > conn->epoch) - p = p->rb_right; - else if (cid < conn->cid) - p = p->rb_left; - else if (cid > conn->cid) - p = p->rb_right; - else - goto found_extant_connection; - } - read_unlock_bh(&trans->conn_lock); - - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_connection(GFP_NOIO); - if (!candidate) { - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - - candidate->trans = trans; - candidate->epoch = hdr->epoch; - candidate->cid = hdr->cid & RXRPC_CIDMASK; - candidate->service_id = hdr->serviceId; - candidate->security_ix = hdr->securityIndex; - candidate->in_clientflag = RXRPC_CLIENT_INITIATED; - candidate->out_clientflag = 0; - candidate->state = RXRPC_CONN_SERVER; - if (candidate->service_id) - candidate->state = RXRPC_CONN_SERVER_UNSECURED; - - write_lock_bh(&trans->conn_lock); - - pp = &trans->server_conns.rb_node; - p = NULL; - while (*pp) { - p = *pp; - conn = rb_entry(p, struct rxrpc_connection, node); - - if (epoch < conn->epoch) - pp = &(*pp)->rb_left; - else if (epoch > conn->epoch) - pp = &(*pp)->rb_right; - else if (cid < conn->cid) - pp = &(*pp)->rb_left; - else if (cid > conn->cid) - pp = &(*pp)->rb_right; - else - goto found_extant_second; - } - - /* we can now add the new candidate to the list */ - conn = candidate; - candidate = NULL; - rb_link_node(&conn->node, p, pp); - rb_insert_color(&conn->node, &trans->server_conns); - atomic_inc(&conn->trans->usage); - - write_unlock_bh(&trans->conn_lock); - - write_lock_bh(&rxrpc_connection_lock); - list_add_tail(&conn->link, &rxrpc_connections); - write_unlock_bh(&rxrpc_connection_lock); - - new = "new"; - -success: - _net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->cid); - - _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); - return conn; - - /* we found the connection in the list immediately */ -found_extant_connection: - if (hdr->securityIndex != conn->security_ix) { - read_unlock_bh(&trans->conn_lock); - goto security_mismatch; - } - atomic_inc(&conn->usage); - read_unlock_bh(&trans->conn_lock); - goto success; - - /* we found the connection on the second time through the list */ -found_extant_second: - if (hdr->securityIndex != conn->security_ix) { - write_unlock_bh(&trans->conn_lock); - goto security_mismatch; - } - atomic_inc(&conn->usage); - write_unlock_bh(&trans->conn_lock); - kfree(candidate); - goto success; - -security_mismatch: - kfree(candidate); - _leave(" = -EKEYREJECTED"); - return ERR_PTR(-EKEYREJECTED); -} - -/* - * find a connection based on transport and RxRPC connection ID for an incoming - * packet - */ -struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *trans, - struct rxrpc_host_header *hdr) -{ - struct rxrpc_connection *conn; - struct rb_node *p; - u32 epoch, cid; - - _enter(",{%x,%x}", hdr->cid, hdr->flags); - - read_lock_bh(&trans->conn_lock); - - cid = hdr->cid & RXRPC_CIDMASK; - epoch = hdr->epoch; - - if (hdr->flags & RXRPC_CLIENT_INITIATED) - p = trans->server_conns.rb_node; - else - p = trans->client_conns.rb_node; - - while (p) { - conn = rb_entry(p, struct rxrpc_connection, node); - - _debug("maybe %x", conn->cid); - - if (epoch < conn->epoch) - p = p->rb_left; - else if (epoch > conn->epoch) - p = p->rb_right; - else if (cid < conn->cid) - p = p->rb_left; - else if (cid > conn->cid) - p = p->rb_right; - else - goto found; - } - - read_unlock_bh(&trans->conn_lock); - _leave(" = NULL"); - return NULL; - -found: - atomic_inc(&conn->usage); - read_unlock_bh(&trans->conn_lock); - _leave(" = %p", conn); - return conn; -} - -/* - * release a virtual connection - */ -void rxrpc_put_connection(struct rxrpc_connection *conn) -{ - _enter("%p{u=%d,d=%d}", - conn, atomic_read(&conn->usage), conn->debug_id); - - ASSERTCMP(atomic_read(&conn->usage), >, 0); - - conn->put_time = ktime_get_seconds(); - if (atomic_dec_and_test(&conn->usage)) { - _debug("zombie"); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); - } - - _leave(""); -} - -/* - * destroy a virtual connection - */ -static void rxrpc_destroy_connection(struct rxrpc_connection *conn) -{ - _enter("%p{%d}", conn, atomic_read(&conn->usage)); - - ASSERTCMP(atomic_read(&conn->usage), ==, 0); - - _net("DESTROY CONN %d", conn->debug_id); - - if (conn->bundle) - rxrpc_put_bundle(conn->trans, conn->bundle); - - ASSERT(RB_EMPTY_ROOT(&conn->calls)); - rxrpc_purge_queue(&conn->rx_queue); - - conn->security->clear(conn); - key_put(conn->key); - key_put(conn->server_key); - - rxrpc_put_transport(conn->trans); - kfree(conn); - _leave(""); -} - -/* - * reap dead connections - */ -static void rxrpc_connection_reaper(struct work_struct *work) -{ - struct rxrpc_connection *conn, *_p; - unsigned long now, earliest, reap_time; - - LIST_HEAD(graveyard); - - _enter(""); - - now = ktime_get_seconds(); - earliest = ULONG_MAX; - - write_lock_bh(&rxrpc_connection_lock); - list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { - _debug("reap CONN %d { u=%d,t=%ld }", - conn->debug_id, atomic_read(&conn->usage), - (long) now - (long) conn->put_time); - - if (likely(atomic_read(&conn->usage) > 0)) - continue; - - spin_lock(&conn->trans->client_lock); - write_lock(&conn->trans->conn_lock); - reap_time = conn->put_time + rxrpc_connection_expiry; - - if (atomic_read(&conn->usage) > 0) { - ; - } else if (reap_time <= now) { - list_move_tail(&conn->link, &graveyard); - if (conn->out_clientflag) - rb_erase(&conn->node, - &conn->trans->client_conns); - else - rb_erase(&conn->node, - &conn->trans->server_conns); - if (conn->bundle) { - list_del_init(&conn->bundle_link); - conn->bundle->num_conns--; - } - - } else if (reap_time < earliest) { - earliest = reap_time; - } - - write_unlock(&conn->trans->conn_lock); - spin_unlock(&conn->trans->client_lock); - } - write_unlock_bh(&rxrpc_connection_lock); - - if (earliest != ULONG_MAX) { - _debug("reschedule reaper %ld", (long) earliest - now); - ASSERTCMP(earliest, >, now); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, - (earliest - now) * HZ); - } - - /* then destroy all those pulled out */ - while (!list_empty(&graveyard)) { - conn = list_entry(graveyard.next, struct rxrpc_connection, - link); - list_del_init(&conn->link); - - ASSERTCMP(atomic_read(&conn->usage), ==, 0); - rxrpc_destroy_connection(conn); - } - - _leave(""); -} - -/* - * preemptively destroy all the connection records rather than waiting for them - * to time out - */ -void __exit rxrpc_destroy_all_connections(void) -{ - _enter(""); - - rxrpc_connection_expiry = 0; - cancel_delayed_work(&rxrpc_connection_reap); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); - - _leave(""); -} diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c deleted file mode 100644 index 3e82d6f0313c..000000000000 --- a/net/rxrpc/ar-error.c +++ /dev/null @@ -1,230 +0,0 @@ -/* Error message handling (ICMP) - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/errqueue.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <net/ip.h> -#include "ar-internal.h" - -/* - * handle an error received on the local endpoint - */ -void rxrpc_UDP_error_report(struct sock *sk) -{ - struct sock_exterr_skb *serr; - struct rxrpc_transport *trans; - struct rxrpc_local *local = sk->sk_user_data; - struct rxrpc_peer *peer; - struct sk_buff *skb; - __be32 addr; - __be16 port; - - _enter("%p{%d}", sk, local->debug_id); - - skb = sock_dequeue_err_skb(sk); - if (!skb) { - _leave("UDP socket errqueue empty"); - return; - } - serr = SKB_EXT_ERR(skb); - if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { - _leave("UDP empty message"); - kfree_skb(skb); - return; - } - - rxrpc_new_skb(skb); - - addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); - port = serr->port; - - _net("Rx UDP Error from %pI4:%hu", &addr, ntohs(port)); - _debug("Msg l:%d d:%d", skb->len, skb->data_len); - - peer = rxrpc_find_peer(local, addr, port); - if (IS_ERR(peer)) { - rxrpc_free_skb(skb); - _leave(" [no peer]"); - return; - } - - trans = rxrpc_find_transport(local, peer); - if (!trans) { - rxrpc_put_peer(peer); - rxrpc_free_skb(skb); - _leave(" [no trans]"); - return; - } - - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && - serr->ee.ee_type == ICMP_DEST_UNREACH && - serr->ee.ee_code == ICMP_FRAG_NEEDED - ) { - u32 mtu = serr->ee.ee_info; - - _net("Rx Received ICMP Fragmentation Needed (%d)", mtu); - - /* wind down the local interface MTU */ - if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) { - peer->if_mtu = mtu; - _net("I/F MTU %u", mtu); - } - - if (mtu == 0) { - /* they didn't give us a size, estimate one */ - mtu = peer->if_mtu; - if (mtu > 1500) { - mtu >>= 1; - if (mtu < 1500) - mtu = 1500; - } else { - mtu -= 100; - if (mtu < peer->hdrsize) - mtu = peer->hdrsize + 4; - } - } - - if (mtu < peer->mtu) { - spin_lock_bh(&peer->lock); - peer->mtu = mtu; - peer->maxdata = peer->mtu - peer->hdrsize; - spin_unlock_bh(&peer->lock); - _net("Net MTU %u (maxdata %u)", - peer->mtu, peer->maxdata); - } - } - - rxrpc_put_peer(peer); - - /* pass the transport ref to error_handler to release */ - skb_queue_tail(&trans->error_queue, skb); - rxrpc_queue_work(&trans->error_handler); - _leave(""); -} - -/* - * deal with UDP error messages - */ -void rxrpc_UDP_error_handler(struct work_struct *work) -{ - struct sock_extended_err *ee; - struct sock_exterr_skb *serr; - struct rxrpc_transport *trans = - container_of(work, struct rxrpc_transport, error_handler); - struct sk_buff *skb; - int err; - - _enter(""); - - skb = skb_dequeue(&trans->error_queue); - if (!skb) - return; - - serr = SKB_EXT_ERR(skb); - ee = &serr->ee; - - _net("Rx Error o=%d t=%d c=%d e=%d", - ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno); - - err = ee->ee_errno; - - switch (ee->ee_origin) { - case SO_EE_ORIGIN_ICMP: - switch (ee->ee_type) { - case ICMP_DEST_UNREACH: - switch (ee->ee_code) { - case ICMP_NET_UNREACH: - _net("Rx Received ICMP Network Unreachable"); - break; - case ICMP_HOST_UNREACH: - _net("Rx Received ICMP Host Unreachable"); - break; - case ICMP_PORT_UNREACH: - _net("Rx Received ICMP Port Unreachable"); - break; - case ICMP_NET_UNKNOWN: - _net("Rx Received ICMP Unknown Network"); - break; - case ICMP_HOST_UNKNOWN: - _net("Rx Received ICMP Unknown Host"); - break; - default: - _net("Rx Received ICMP DestUnreach code=%u", - ee->ee_code); - break; - } - break; - - case ICMP_TIME_EXCEEDED: - _net("Rx Received ICMP TTL Exceeded"); - break; - - default: - _proto("Rx Received ICMP error { type=%u code=%u }", - ee->ee_type, ee->ee_code); - break; - } - break; - - case SO_EE_ORIGIN_LOCAL: - _proto("Rx Received local error { error=%d }", - ee->ee_errno); - break; - - case SO_EE_ORIGIN_NONE: - case SO_EE_ORIGIN_ICMP6: - default: - _proto("Rx Received error report { orig=%u }", - ee->ee_origin); - break; - } - - /* terminate all the affected calls if there's an unrecoverable - * error */ - if (err) { - struct rxrpc_call *call, *_n; - - _debug("ISSUE ERROR %d", err); - - spin_lock_bh(&trans->peer->lock); - trans->peer->net_error = err; - - list_for_each_entry_safe(call, _n, &trans->peer->error_targets, - error_link) { - write_lock(&call->state_lock); - if (call->state != RXRPC_CALL_COMPLETE && - call->state < RXRPC_CALL_NETWORK_ERROR) { - call->state = RXRPC_CALL_NETWORK_ERROR; - set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); - rxrpc_queue_call(call); - } - write_unlock(&call->state_lock); - list_del_init(&call->error_link); - } - - spin_unlock_bh(&trans->peer->lock); - } - - if (!skb_queue_empty(&trans->error_queue)) - rxrpc_queue_work(&trans->error_handler); - - rxrpc_free_skb(skb); - rxrpc_put_transport(trans); - _leave(""); -} diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index f0b807a163fa..1bb9e7ac9e14 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -9,7 +9,10 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/atomic.h> +#include <linux/seqlock.h> #include <net/sock.h> +#include <net/af_rxrpc.h> #include <rxrpc/packet.h> #if 0 @@ -33,15 +36,16 @@ struct rxrpc_crypt { queue_delayed_work(rxrpc_workqueue, (WS), (D)) #define rxrpc_queue_call(CALL) rxrpc_queue_work(&(CALL)->processor) -#define rxrpc_queue_conn(CONN) rxrpc_queue_work(&(CONN)->processor) + +struct rxrpc_connection; /* * sk_state for RxRPC sockets */ enum { - RXRPC_UNCONNECTED = 0, + RXRPC_UNBOUND = 0, + RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ - RXRPC_CLIENT_CONNECTED, /* client is connected */ RXRPC_SERVER_BOUND, /* server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_CLOSE, /* socket is being closed */ @@ -55,9 +59,6 @@ struct rxrpc_sock { struct sock sk; rxrpc_interceptor_t interceptor; /* kernel service Rx interceptor function */ struct rxrpc_local *local; /* local endpoint */ - struct rxrpc_transport *trans; /* transport handler */ - struct rxrpc_conn_bundle *bundle; /* virtual connection bundle */ - struct rxrpc_connection *conn; /* exclusive virtual connection */ struct list_head listen_link; /* link in the local endpoint's listen list */ struct list_head secureq; /* calls awaiting connection security clearance */ struct list_head acceptq; /* calls awaiting acceptance */ @@ -65,12 +66,14 @@ struct rxrpc_sock { struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* outstanding calls on this socket */ unsigned long flags; -#define RXRPC_SOCK_EXCLUSIVE_CONN 1 /* exclusive connection for a client socket */ +#define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT + bool exclusive; /* Exclusive connection for a client socket */ + sa_family_t family; /* Protocol family created with */ struct sockaddr_rxrpc srx; /* local address */ - sa_family_t proto; /* protocol created with */ + struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ }; #define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk) @@ -138,17 +141,16 @@ struct rxrpc_security { int (*init_connection_security)(struct rxrpc_connection *); /* prime a connection's packet security */ - void (*prime_packet_security)(struct rxrpc_connection *); + int (*prime_packet_security)(struct rxrpc_connection *); /* impose security on a packet */ - int (*secure_packet)(const struct rxrpc_call *, + int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t, void *); /* verify the security on a received packet */ - int (*verify_packet)(const struct rxrpc_call *, struct sk_buff *, - u32 *); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, u32 *); /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -168,46 +170,52 @@ struct rxrpc_security { }; /* - * RxRPC local transport endpoint definition - * - matched by local port, address and protocol type + * RxRPC local transport endpoint description + * - owned by a single AF_RXRPC socket + * - pointed to by transport socket struct sk_user_data */ struct rxrpc_local { + struct rcu_head rcu; + atomic_t usage; + struct list_head link; struct socket *socket; /* my UDP socket */ - struct work_struct destroyer; /* endpoint destroyer */ - struct work_struct acceptor; /* incoming call processor */ - struct work_struct rejecter; /* packet reject writer */ - struct work_struct event_processor; /* endpoint event processor */ + struct work_struct processor; struct list_head services; /* services listening on this endpoint */ - struct list_head link; /* link in endpoint list */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head accept_queue; /* incoming calls awaiting acceptance */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ + struct rb_root client_conns; /* Client connections by socket params */ + spinlock_t client_conns_lock; /* Lock for client_conns */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ - atomic_t usage; int debug_id; /* debug ID for printks */ - volatile char error_rcvd; /* T if received ICMP error outstanding */ + bool dead; struct sockaddr_rxrpc srx; /* local address */ }; /* * RxRPC remote transport endpoint definition - * - matched by remote port, address and protocol type - * - holds the connection ID counter for connections between the two endpoints + * - matched by local endpoint, remote port, address and protocol type */ struct rxrpc_peer { - struct work_struct destroyer; /* peer destroyer */ - struct list_head link; /* link in master peer list */ - struct list_head error_targets; /* targets for net error distribution */ - spinlock_t lock; /* access lock */ + struct rcu_head rcu; /* This must be first */ atomic_t usage; + unsigned long hash_key; + struct hlist_node hash_link; + struct rxrpc_local *local; + struct hlist_head error_targets; /* targets for net error distribution */ + struct work_struct error_distributor; + struct rb_root service_conns; /* Service connections */ + seqlock_t service_conn_lock; + spinlock_t lock; /* access lock */ unsigned int if_mtu; /* interface MTU for this peer */ unsigned int mtu; /* network MTU for this peer */ unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ - int net_error; /* network error distributed */ + int error_report; /* Net (+0) or local (+1000000) to distribute */ +#define RXRPC_LOCAL_ERROR_OFFSET 1000000 struct sockaddr_rxrpc srx; /* remote address */ /* calculated RTT cache */ @@ -219,99 +227,108 @@ struct rxrpc_peer { }; /* - * RxRPC point-to-point transport / connection manager definition - * - handles a bundle of connections between two endpoints - * - matched by { local, peer } - */ -struct rxrpc_transport { - struct rxrpc_local *local; /* local transport endpoint */ - struct rxrpc_peer *peer; /* remote transport endpoint */ - struct work_struct error_handler; /* network error distributor */ - struct rb_root bundles; /* client connection bundles on this transport */ - struct rb_root client_conns; /* client connections on this transport */ - struct rb_root server_conns; /* server connections on this transport */ - struct list_head link; /* link in master session list */ - struct sk_buff_head error_queue; /* error packets awaiting processing */ - unsigned long put_time; /* time at which to reap */ - spinlock_t client_lock; /* client connection allocation lock */ - rwlock_t conn_lock; /* lock for active/dead connections */ - atomic_t usage; - int debug_id; /* debug ID for printks */ - unsigned int conn_idcounter; /* connection ID counter (client) */ + * Keys for matching a connection. + */ +struct rxrpc_conn_proto { + union { + struct { + u32 epoch; /* epoch of this connection */ + u32 cid; /* connection ID */ + }; + u64 index_key; + }; +}; + +struct rxrpc_conn_parameters { + struct rxrpc_local *local; /* Representation of local endpoint */ + struct rxrpc_peer *peer; /* Remote endpoint */ + struct key *key; /* Security details */ + bool exclusive; /* T if conn is exclusive */ + u16 service_id; /* Service ID for this connection */ + u32 security_level; /* Security level selected */ }; /* - * RxRPC client connection bundle - * - matched by { transport, service_id, key } + * Bits in the connection flags. */ -struct rxrpc_conn_bundle { - struct rb_node node; /* node in transport's lookup tree */ - struct list_head unused_conns; /* unused connections in this bundle */ - struct list_head avail_conns; /* available connections in this bundle */ - struct list_head busy_conns; /* busy connections in this bundle */ - struct key *key; /* security for this bundle */ - wait_queue_head_t chanwait; /* wait for channel to become available */ - atomic_t usage; - int debug_id; /* debug ID for printks */ - unsigned short num_conns; /* number of connections in this bundle */ - u16 service_id; /* Service ID for this bundle */ - u8 security_ix; /* security type */ +enum rxrpc_conn_flag { + RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ + RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ + RXRPC_CONN_IN_CLIENT_CONNS, /* Conn is in local->client_conns */ +}; + +/* + * Events that can be raised upon a connection. + */ +enum rxrpc_conn_event { + RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ +}; + +/* + * The connection protocol state. + */ +enum rxrpc_conn_proto_state { + RXRPC_CONN_UNUSED, /* Connection not yet attempted */ + RXRPC_CONN_CLIENT, /* Client connection */ + RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ + RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ + RXRPC_CONN_SERVICE, /* Service secured connection */ + RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */ + RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */ + RXRPC_CONN_NETWORK_ERROR, /* Conn terminated by network error */ + RXRPC_CONN__NR_STATES }; /* * RxRPC connection definition - * - matched by { transport, service_id, conn_id, direction, key } + * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls */ struct rxrpc_connection { - struct rxrpc_transport *trans; /* transport session */ - struct rxrpc_conn_bundle *bundle; /* connection bundle (client) */ + struct rxrpc_conn_proto proto; + struct rxrpc_conn_parameters params; + + spinlock_t channel_lock; + + struct rxrpc_channel { + struct rxrpc_call __rcu *call; /* Active call */ + u32 call_id; /* ID of current call */ + u32 call_counter; /* Call ID counter */ + u32 last_call; /* ID of last call */ + u32 last_result; /* Result of last call (0/abort) */ + } channels[RXRPC_MAXCALLS]; + wait_queue_head_t channel_wq; /* queue to wait for channel to become available */ + + struct rcu_head rcu; struct work_struct processor; /* connection event processor */ - struct rb_node node; /* node in transport's lookup tree */ + union { + struct rb_node client_node; /* Node in local->client_conns */ + struct rb_node service_node; /* Node in peer->service_conns */ + }; struct list_head link; /* link in master connection list */ - struct list_head bundle_link; /* link in bundle */ - struct rb_root calls; /* calls on this connection */ struct sk_buff_head rx_queue; /* received conn-level packets */ - struct rxrpc_call *channels[RXRPC_MAXCALLS]; /* channels (active calls) */ const struct rxrpc_security *security; /* applied security module */ - struct key *key; /* security for this connection (client) */ struct key *server_key; /* security for this service */ struct crypto_skcipher *cipher; /* encryption handle */ struct rxrpc_crypt csum_iv; /* packet checksum base */ + unsigned long flags; unsigned long events; -#define RXRPC_CONN_CHALLENGE 0 /* send challenge packet */ - unsigned long put_time; /* time at which to reap */ - rwlock_t lock; /* access lock */ + unsigned long put_time; /* Time at which last put */ spinlock_t state_lock; /* state-change lock */ atomic_t usage; - enum { /* current state of connection */ - RXRPC_CONN_UNUSED, /* - connection not yet attempted */ - RXRPC_CONN_CLIENT, /* - client connection */ - RXRPC_CONN_SERVER_UNSECURED, /* - server unsecured connection */ - RXRPC_CONN_SERVER_CHALLENGING, /* - server challenging for security */ - RXRPC_CONN_SERVER, /* - server secured connection */ - RXRPC_CONN_REMOTELY_ABORTED, /* - conn aborted by peer */ - RXRPC_CONN_LOCALLY_ABORTED, /* - conn aborted locally */ - RXRPC_CONN_NETWORK_ERROR, /* - conn terminated by network error */ - } state; + enum rxrpc_conn_proto_state state : 8; /* current state of connection */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ int error; /* local error incurred */ int debug_id; /* debug ID for printks */ - unsigned int call_counter; /* call ID counter */ atomic_t serial; /* packet serial number counter */ atomic_t hi_serial; /* highest serial number received */ - u8 avail_calls; /* number of calls available */ + atomic_t avail_chans; /* number of channels available */ u8 size_align; /* data size alignment (for security) */ u8 header_size; /* rxrpc + security header size */ u8 security_size; /* security header size */ - u32 security_level; /* security level negotiated */ u32 security_nonce; /* response re-use preventer */ - u32 epoch; /* epoch of this connection */ - u32 cid; /* connection ID */ - u16 service_id; /* service ID for this connection */ u8 security_ix; /* security type */ - u8 in_clientflag; /* RXRPC_CLIENT_INITIATED if we are server */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ }; @@ -357,6 +374,8 @@ enum rxrpc_call_event { * The states that a call can be in. */ enum rxrpc_call_state { + RXRPC_CALL_UNINITIALISED, + RXRPC_CALL_CLIENT_AWAIT_CONN, /* - client waiting for connection to become available */ RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */ RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ @@ -381,6 +400,7 @@ enum rxrpc_call_state { * - matched by { connection, call_id } */ struct rxrpc_call { + struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_sock *socket; /* socket responsible */ struct timer_list lifetimer; /* lifetime remaining on call */ @@ -390,14 +410,14 @@ struct rxrpc_call { struct work_struct destroyer; /* call destroyer */ struct work_struct processor; /* packet processor and ACK generator */ struct list_head link; /* link in master call list */ - struct list_head error_link; /* link in error distribution list */ + struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* calls awaiting acceptance */ struct rb_node sock_node; /* node in socket call tree */ - struct rb_node conn_node; /* node in connection call tree */ struct sk_buff_head rx_queue; /* received packets */ struct sk_buff_head rx_oos_queue; /* packets received out of sequence */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ wait_queue_head_t tx_waitq; /* wait for Tx window space to become available */ + __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long creation_jif; /* time of call creation */ unsigned long flags; @@ -408,7 +428,8 @@ struct rxrpc_call { atomic_t sequence; /* Tx data packet sequence counter */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ - int error; /* local error incurred */ + int error_report; /* Network error (ICMP/local transport) */ + int error; /* Local error incurred */ enum rxrpc_call_state state : 8; /* current state of call */ int debug_id; /* debug ID for printks */ u8 channel; /* connection channel occupied by this call */ @@ -440,19 +461,12 @@ struct rxrpc_call { #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; - struct hlist_node hash_node; - unsigned long hash_key; /* Full hash key */ - u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */ - struct rxrpc_local *local; /* Local endpoint. Used for hashing. */ - sa_family_t proto; /* Frame protocol */ + u8 in_clientflag; /* Copy of conn->in_clientflag */ + struct rxrpc_local *local; /* Local endpoint. */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ u32 epoch; /* epoch of this connection */ u16 service_id; /* service ID */ - union { /* Peer IP address for hashing */ - __be32 ipv4_addr; - __u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */ - } peer_ip; }; /* @@ -478,21 +492,21 @@ extern atomic_t rxrpc_debug_id; extern struct workqueue_struct *rxrpc_workqueue; /* - * ar-accept.c + * call_accept.c */ -void rxrpc_accept_incoming_calls(struct work_struct *); +void rxrpc_accept_incoming_calls(struct rxrpc_local *); struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long); int rxrpc_reject_call(struct rxrpc_sock *); /* - * ar-ack.c + * call_event.c */ void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); void rxrpc_process_call(struct work_struct *); /* - * ar-call.c + * call_object.c */ extern unsigned int rxrpc_max_call_lifetime; extern unsigned int rxrpc_dead_call_expiry; @@ -500,72 +514,106 @@ extern struct kmem_cache *rxrpc_call_jar; extern struct list_head rxrpc_calls; extern rwlock_t rxrpc_call_lock; -struct rxrpc_call *rxrpc_find_call_hash(struct rxrpc_host_header *, - void *, sa_family_t, const void *); -struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, - struct rxrpc_transport *, - struct rxrpc_conn_bundle *, - unsigned long, int, gfp_t); +struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); +struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, + struct rxrpc_conn_parameters *, + struct sockaddr_rxrpc *, + unsigned long, gfp_t); struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_connection *, - struct rxrpc_host_header *); -struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long); + struct sk_buff *); void rxrpc_release_call(struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); void __rxrpc_put_call(struct rxrpc_call *); void __exit rxrpc_destroy_all_calls(void); /* - * ar-connection.c + * conn_client.c + */ +extern struct idr rxrpc_client_conn_ids; + +void rxrpc_destroy_client_conn_ids(void); +int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *, + struct sockaddr_rxrpc *, gfp_t); +void rxrpc_unpublish_client_conn(struct rxrpc_connection *); + +/* + * conn_event.c + */ +void rxrpc_process_connection(struct work_struct *); +void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *); +void rxrpc_reject_packets(struct rxrpc_local *); + +/* + * conn_object.c */ extern unsigned int rxrpc_connection_expiry; extern struct list_head rxrpc_connections; extern rwlock_t rxrpc_connection_lock; -struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *, - struct rxrpc_transport *, - struct key *, u16, gfp_t); -void rxrpc_put_bundle(struct rxrpc_transport *, struct rxrpc_conn_bundle *); -int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_transport *, - struct rxrpc_conn_bundle *, struct rxrpc_call *, gfp_t); +int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); +struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); +struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, + struct sk_buff *); +void __rxrpc_disconnect_call(struct rxrpc_call *); +void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_put_connection(struct rxrpc_connection *); void __exit rxrpc_destroy_all_connections(void); -struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *, - struct rxrpc_host_header *); -extern struct rxrpc_connection * -rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *); -/* - * ar-connevent.c - */ -void rxrpc_process_connection(struct work_struct *); -void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *); -void rxrpc_reject_packets(struct work_struct *); +static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) +{ + return conn->out_clientflag; +} + +static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) +{ + return !rxrpc_conn_is_client(conn); +} + +static inline void rxrpc_get_connection(struct rxrpc_connection *conn) +{ + atomic_inc(&conn->usage); +} + +static inline +struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *conn) +{ + return atomic_inc_not_zero(&conn->usage) ? conn : NULL; +} + +static inline bool rxrpc_queue_conn(struct rxrpc_connection *conn) +{ + if (!rxrpc_get_connection_maybe(conn)) + return false; + if (!rxrpc_queue_work(&conn->processor)) + rxrpc_put_connection(conn); + return true; +} /* - * ar-error.c + * conn_service.c */ -void rxrpc_UDP_error_report(struct sock *); -void rxrpc_UDP_error_handler(struct work_struct *); +struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, + struct sk_buff *); +struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *, + struct sockaddr_rxrpc *, + struct sk_buff *); +void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* - * ar-input.c + * input.c */ void rxrpc_data_ready(struct sock *); int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool); void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); /* - * ar-local.c + * insecure.c */ -extern rwlock_t rxrpc_local_lock; - -struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *); -void rxrpc_put_local(struct rxrpc_local *); -void __exit rxrpc_destroy_all_locals(void); +extern const struct rxrpc_security rxrpc_no_security; /* - * ar-key.c + * key.c */ extern struct key_type key_type_rxrpc; extern struct key_type key_type_rxrpc_s; @@ -576,80 +624,108 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, u32); /* - * ar-output.c + * local_event.c */ -extern unsigned int rxrpc_resend_timeout; - -int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); -int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *, - struct msghdr *, size_t); -int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); +extern void rxrpc_process_local_events(struct rxrpc_local *); /* - * ar-peer.c + * local_object.c */ -struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *, gfp_t); -void rxrpc_put_peer(struct rxrpc_peer *); -struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *, __be32, __be16); -void __exit rxrpc_destroy_all_peers(void); +struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *); +void __rxrpc_put_local(struct rxrpc_local *); +void __exit rxrpc_destroy_all_locals(void); -/* - * ar-proc.c - */ -extern const char *const rxrpc_call_states[]; -extern const struct file_operations rxrpc_call_seq_fops; -extern const struct file_operations rxrpc_connection_seq_fops; +static inline void rxrpc_get_local(struct rxrpc_local *local) +{ + atomic_inc(&local->usage); +} + +static inline +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) +{ + return atomic_inc_not_zero(&local->usage) ? local : NULL; +} + +static inline void rxrpc_put_local(struct rxrpc_local *local) +{ + if (local && atomic_dec_and_test(&local->usage)) + __rxrpc_put_local(local); +} + +static inline void rxrpc_queue_local(struct rxrpc_local *local) +{ + rxrpc_queue_work(&local->processor); +} /* - * ar-recvmsg.c + * misc.c */ -void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *); -int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); +extern unsigned int rxrpc_max_backlog __read_mostly; +extern unsigned int rxrpc_requested_ack_delay; +extern unsigned int rxrpc_soft_ack_delay; +extern unsigned int rxrpc_idle_ack_delay; +extern unsigned int rxrpc_rx_window_size; +extern unsigned int rxrpc_rx_mtu; +extern unsigned int rxrpc_rx_jumbo_max; + +extern const char *const rxrpc_pkts[]; +extern const s8 rxrpc_ack_priority[]; + +extern const char *rxrpc_acks(u8 reason); /* - * ar-security.c + * output.c */ -int __init rxrpc_init_security(void); -void rxrpc_exit_security(void); -int rxrpc_init_client_conn_security(struct rxrpc_connection *); -int rxrpc_init_server_conn_security(struct rxrpc_connection *); +extern unsigned int rxrpc_resend_timeout; + +int rxrpc_send_data_packet(struct rxrpc_connection *, struct sk_buff *); +int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* - * ar-skbuff.c + * peer_event.c */ -void rxrpc_packet_destructor(struct sk_buff *); +void rxrpc_error_report(struct sock *); +void rxrpc_peer_error_distributor(struct work_struct *); /* - * ar-transport.c + * peer_object.c */ -extern unsigned int rxrpc_transport_expiry; +struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, + const struct sockaddr_rxrpc *); +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, + struct sockaddr_rxrpc *, gfp_t); +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); -struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *, - struct rxrpc_peer *, gfp_t); -void rxrpc_put_transport(struct rxrpc_transport *); -void __exit rxrpc_destroy_all_transports(void); -struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, - struct rxrpc_peer *); +static inline void rxrpc_get_peer(struct rxrpc_peer *peer) +{ + atomic_inc(&peer->usage); +} + +static inline +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) +{ + return atomic_inc_not_zero(&peer->usage) ? peer : NULL; +} + +extern void __rxrpc_put_peer(struct rxrpc_peer *peer); +static inline void rxrpc_put_peer(struct rxrpc_peer *peer) +{ + if (peer && atomic_dec_and_test(&peer->usage)) + __rxrpc_put_peer(peer); +} /* - * insecure.c + * proc.c */ -extern const struct rxrpc_security rxrpc_no_security; +extern const char *const rxrpc_call_states[]; +extern const struct file_operations rxrpc_call_seq_fops; +extern const struct file_operations rxrpc_connection_seq_fops; /* - * misc.c + * recvmsg.c */ -extern unsigned int rxrpc_requested_ack_delay; -extern unsigned int rxrpc_soft_ack_delay; -extern unsigned int rxrpc_idle_ack_delay; -extern unsigned int rxrpc_rx_window_size; -extern unsigned int rxrpc_rx_mtu; -extern unsigned int rxrpc_rx_jumbo_max; - -extern const char *const rxrpc_pkts[]; -extern const s8 rxrpc_ack_priority[]; - -extern const char *rxrpc_acks(u8 reason); +void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *); +int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * rxkad.c @@ -659,6 +735,19 @@ extern const struct rxrpc_security rxkad; #endif /* + * security.c + */ +int __init rxrpc_init_security(void); +void rxrpc_exit_security(void); +int rxrpc_init_client_conn_security(struct rxrpc_connection *); +int rxrpc_init_server_conn_security(struct rxrpc_connection *); + +/* + * skbuff.c + */ +void rxrpc_packet_destructor(struct sk_buff *); + +/* * sysctl.c */ #ifdef CONFIG_SYSCTL @@ -670,6 +759,11 @@ static inline void rxrpc_sysctl_exit(void) {} #endif /* + * utils.c + */ +int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); + +/* * debug tracing */ extern unsigned int rxrpc_debug; @@ -744,21 +838,18 @@ do { \ #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ - if (unlikely(!((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ - printk(KERN_ERR "%lu " #OP " %lu is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ + unsigned long _x = (unsigned long)(X); \ + unsigned long _y = (unsigned long)(Y); \ + if (unlikely(!(_x OP _y))) { \ + pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ + _x, _x, #OP, _y, _y); \ BUG(); \ } \ } while (0) @@ -766,21 +857,18 @@ do { \ #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ - if (unlikely((C) && !((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ - printk(KERN_ERR "%lu " #OP " %lu is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ + unsigned long _x = (unsigned long)(X); \ + unsigned long _y = (unsigned long)(Y); \ + if (unlikely((C) && !(_x OP _y))) { \ + pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ + _x, _x, #OP, _y, _y); \ BUG(); \ } \ } while (0) @@ -844,15 +932,6 @@ static inline void rxrpc_purge_queue(struct sk_buff_head *list) rxrpc_free_skb(skb); } -static inline void __rxrpc_get_local(struct rxrpc_local *local, const char *f) -{ - CHECK_SLAB_OKAY(&local->usage); - if (atomic_inc_return(&local->usage) == 1) - printk("resurrected (%s)\n", f); -} - -#define rxrpc_get_local(LOCAL) __rxrpc_get_local((LOCAL), __func__) - #define rxrpc_get_call(CALL) \ do { \ CHECK_SLAB_OKAY(&(CALL)->usage); \ diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c deleted file mode 100644 index 4e1e6db0050b..000000000000 --- a/net/rxrpc/ar-local.c +++ /dev/null @@ -1,415 +0,0 @@ -/* AF_RXRPC local endpoint management - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/slab.h> -#include <linux/udp.h> -#include <linux/ip.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <generated/utsrelease.h> -#include "ar-internal.h" - -static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; - -static LIST_HEAD(rxrpc_locals); -DEFINE_RWLOCK(rxrpc_local_lock); -static DECLARE_RWSEM(rxrpc_local_sem); -static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq); - -static void rxrpc_destroy_local(struct work_struct *work); -static void rxrpc_process_local_events(struct work_struct *work); - -/* - * allocate a new local - */ -static -struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx) -{ - struct rxrpc_local *local; - - local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); - if (local) { - INIT_WORK(&local->destroyer, &rxrpc_destroy_local); - INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls); - INIT_WORK(&local->rejecter, &rxrpc_reject_packets); - INIT_WORK(&local->event_processor, &rxrpc_process_local_events); - INIT_LIST_HEAD(&local->services); - INIT_LIST_HEAD(&local->link); - init_rwsem(&local->defrag_sem); - skb_queue_head_init(&local->accept_queue); - skb_queue_head_init(&local->reject_queue); - skb_queue_head_init(&local->event_queue); - spin_lock_init(&local->lock); - rwlock_init(&local->services_lock); - atomic_set(&local->usage, 1); - local->debug_id = atomic_inc_return(&rxrpc_debug_id); - memcpy(&local->srx, srx, sizeof(*srx)); - } - - _leave(" = %p", local); - return local; -} - -/* - * create the local socket - * - must be called with rxrpc_local_sem writelocked - */ -static int rxrpc_create_local(struct rxrpc_local *local) -{ - struct sock *sock; - int ret, opt; - - _enter("%p{%d}", local, local->srx.transport_type); - - /* create a socket to represent the local endpoint */ - ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type, - IPPROTO_UDP, &local->socket); - if (ret < 0) { - _leave(" = %d [socket]", ret); - return ret; - } - - /* if a local address was supplied then bind it */ - if (local->srx.transport_len > sizeof(sa_family_t)) { - _debug("bind"); - ret = kernel_bind(local->socket, - (struct sockaddr *) &local->srx.transport, - local->srx.transport_len); - if (ret < 0) { - _debug("bind failed"); - goto error; - } - } - - /* we want to receive ICMP errors */ - opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - - /* we want to set the don't fragment bit */ - opt = IP_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - - write_lock_bh(&rxrpc_local_lock); - list_add(&local->link, &rxrpc_locals); - write_unlock_bh(&rxrpc_local_lock); - - /* set the socket up */ - sock = local->socket->sk; - sock->sk_user_data = local; - sock->sk_data_ready = rxrpc_data_ready; - sock->sk_error_report = rxrpc_UDP_error_report; - _leave(" = 0"); - return 0; - -error: - kernel_sock_shutdown(local->socket, SHUT_RDWR); - local->socket->sk->sk_user_data = NULL; - sock_release(local->socket); - local->socket = NULL; - - _leave(" = %d", ret); - return ret; -} - -/* - * create a new local endpoint using the specified UDP address - */ -struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx) -{ - struct rxrpc_local *local; - int ret; - - _enter("{%d,%u,%pI4+%hu}", - srx->transport_type, - srx->transport.family, - &srx->transport.sin.sin_addr, - ntohs(srx->transport.sin.sin_port)); - - down_write(&rxrpc_local_sem); - - /* see if we have a suitable local local endpoint already */ - read_lock_bh(&rxrpc_local_lock); - - list_for_each_entry(local, &rxrpc_locals, link) { - _debug("CMP {%d,%u,%pI4+%hu}", - local->srx.transport_type, - local->srx.transport.family, - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port)); - - if (local->srx.transport_type != srx->transport_type || - local->srx.transport.family != srx->transport.family) - continue; - - switch (srx->transport.family) { - case AF_INET: - if (local->srx.transport.sin.sin_port != - srx->transport.sin.sin_port) - continue; - if (memcmp(&local->srx.transport.sin.sin_addr, - &srx->transport.sin.sin_addr, - sizeof(struct in_addr)) != 0) - continue; - goto found_local; - - default: - BUG(); - } - } - - read_unlock_bh(&rxrpc_local_lock); - - /* we didn't find one, so we need to create one */ - local = rxrpc_alloc_local(srx); - if (!local) { - up_write(&rxrpc_local_sem); - return ERR_PTR(-ENOMEM); - } - - ret = rxrpc_create_local(local); - if (ret < 0) { - up_write(&rxrpc_local_sem); - kfree(local); - _leave(" = %d", ret); - return ERR_PTR(ret); - } - - up_write(&rxrpc_local_sem); - - _net("LOCAL new %d {%d,%u,%pI4+%hu}", - local->debug_id, - local->srx.transport_type, - local->srx.transport.family, - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port)); - - _leave(" = %p [new]", local); - return local; - -found_local: - rxrpc_get_local(local); - read_unlock_bh(&rxrpc_local_lock); - up_write(&rxrpc_local_sem); - - _net("LOCAL old %d {%d,%u,%pI4+%hu}", - local->debug_id, - local->srx.transport_type, - local->srx.transport.family, - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port)); - - _leave(" = %p [reuse]", local); - return local; -} - -/* - * release a local endpoint - */ -void rxrpc_put_local(struct rxrpc_local *local) -{ - _enter("%p{u=%d}", local, atomic_read(&local->usage)); - - ASSERTCMP(atomic_read(&local->usage), >, 0); - - /* to prevent a race, the decrement and the dequeue must be effectively - * atomic */ - write_lock_bh(&rxrpc_local_lock); - if (unlikely(atomic_dec_and_test(&local->usage))) { - _debug("destroy local"); - rxrpc_queue_work(&local->destroyer); - } - write_unlock_bh(&rxrpc_local_lock); - _leave(""); -} - -/* - * destroy a local endpoint - */ -static void rxrpc_destroy_local(struct work_struct *work) -{ - struct rxrpc_local *local = - container_of(work, struct rxrpc_local, destroyer); - - _enter("%p{%d}", local, atomic_read(&local->usage)); - - down_write(&rxrpc_local_sem); - - write_lock_bh(&rxrpc_local_lock); - if (atomic_read(&local->usage) > 0) { - write_unlock_bh(&rxrpc_local_lock); - up_read(&rxrpc_local_sem); - _leave(" [resurrected]"); - return; - } - - list_del(&local->link); - local->socket->sk->sk_user_data = NULL; - write_unlock_bh(&rxrpc_local_lock); - - downgrade_write(&rxrpc_local_sem); - - ASSERT(list_empty(&local->services)); - ASSERT(!work_pending(&local->acceptor)); - ASSERT(!work_pending(&local->rejecter)); - ASSERT(!work_pending(&local->event_processor)); - - /* finish cleaning up the local descriptor */ - rxrpc_purge_queue(&local->accept_queue); - rxrpc_purge_queue(&local->reject_queue); - rxrpc_purge_queue(&local->event_queue); - kernel_sock_shutdown(local->socket, SHUT_RDWR); - sock_release(local->socket); - - up_read(&rxrpc_local_sem); - - _net("DESTROY LOCAL %d", local->debug_id); - kfree(local); - - if (list_empty(&rxrpc_locals)) - wake_up_all(&rxrpc_local_wq); - - _leave(""); -} - -/* - * preemptively destroy all local local endpoint rather than waiting for - * them to be destroyed - */ -void __exit rxrpc_destroy_all_locals(void) -{ - DECLARE_WAITQUEUE(myself,current); - - _enter(""); - - /* we simply have to wait for them to go away */ - if (!list_empty(&rxrpc_locals)) { - set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(&rxrpc_local_wq, &myself); - - while (!list_empty(&rxrpc_locals)) { - schedule(); - set_current_state(TASK_UNINTERRUPTIBLE); - } - - remove_wait_queue(&rxrpc_local_wq, &myself); - set_current_state(TASK_RUNNING); - } - - _leave(""); -} - -/* - * Reply to a version request - */ -static void rxrpc_send_version_request(struct rxrpc_local *local, - struct rxrpc_host_header *hdr, - struct sk_buff *skb) -{ - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct sockaddr_in sin; - struct msghdr msg; - struct kvec iov[2]; - size_t len; - int ret; - - _enter(""); - - sin.sin_family = AF_INET; - sin.sin_port = udp_hdr(skb)->source; - sin.sin_addr.s_addr = ip_hdr(skb)->saddr; - - msg.msg_name = &sin; - msg.msg_namelen = sizeof(sin); - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; - - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.seq = 0; - whdr.serial = 0; - whdr.type = RXRPC_PACKET_TYPE_VERSION; - whdr.flags = RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED); - whdr.userStatus = 0; - whdr.securityIndex = 0; - whdr._rsvd = 0; - whdr.serviceId = htons(sp->hdr.serviceId); - - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = (char *)rxrpc_version_string; - iov[1].iov_len = sizeof(rxrpc_version_string); - - len = iov[0].iov_len + iov[1].iov_len; - - _proto("Tx VERSION (reply)"); - - ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); - if (ret < 0) - _debug("sendmsg failed: %d", ret); - - _leave(""); -} - -/* - * Process event packets targetted at a local endpoint. - */ -static void rxrpc_process_local_events(struct work_struct *work) -{ - struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor); - struct sk_buff *skb; - char v; - - _enter(""); - - atomic_inc(&local->usage); - - while ((skb = skb_dequeue(&local->event_queue))) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - _debug("{%d},{%u}", local->debug_id, sp->hdr.type); - - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_VERSION: - if (skb_copy_bits(skb, 0, &v, 1) < 0) - return; - _proto("Rx VERSION { %02x }", v); - if (v == 0) - rxrpc_send_version_request(local, &sp->hdr, skb); - break; - - default: - /* Just ignore anything we don't understand */ - break; - } - - rxrpc_put_local(local); - rxrpc_free_skb(skb); - } - - rxrpc_put_local(local); - _leave(""); -} diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c deleted file mode 100644 index dc089b1976aa..000000000000 --- a/net/rxrpc/ar-peer.c +++ /dev/null @@ -1,303 +0,0 @@ -/* RxRPC remote transport endpoint management - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> -#include <linux/slab.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <net/ip.h> -#include <net/route.h> -#include "ar-internal.h" - -static LIST_HEAD(rxrpc_peers); -static DEFINE_RWLOCK(rxrpc_peer_lock); -static DECLARE_WAIT_QUEUE_HEAD(rxrpc_peer_wq); - -static void rxrpc_destroy_peer(struct work_struct *work); - -/* - * assess the MTU size for the network interface through which this peer is - * reached - */ -static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) -{ - struct rtable *rt; - struct flowi4 fl4; - - peer->if_mtu = 1500; - - rt = ip_route_output_ports(&init_net, &fl4, NULL, - peer->srx.transport.sin.sin_addr.s_addr, 0, - htons(7000), htons(7001), - IPPROTO_UDP, 0, 0); - if (IS_ERR(rt)) { - _leave(" [route err %ld]", PTR_ERR(rt)); - return; - } - - peer->if_mtu = dst_mtu(&rt->dst); - dst_release(&rt->dst); - - _leave(" [if_mtu %u]", peer->if_mtu); -} - -/* - * allocate a new peer - */ -static struct rxrpc_peer *rxrpc_alloc_peer(struct sockaddr_rxrpc *srx, - gfp_t gfp) -{ - struct rxrpc_peer *peer; - - _enter(""); - - peer = kzalloc(sizeof(struct rxrpc_peer), gfp); - if (peer) { - INIT_WORK(&peer->destroyer, &rxrpc_destroy_peer); - INIT_LIST_HEAD(&peer->link); - INIT_LIST_HEAD(&peer->error_targets); - spin_lock_init(&peer->lock); - atomic_set(&peer->usage, 1); - peer->debug_id = atomic_inc_return(&rxrpc_debug_id); - memcpy(&peer->srx, srx, sizeof(*srx)); - - rxrpc_assess_MTU_size(peer); - peer->mtu = peer->if_mtu; - - if (srx->transport.family == AF_INET) { - peer->hdrsize = sizeof(struct iphdr); - switch (srx->transport_type) { - case SOCK_DGRAM: - peer->hdrsize += sizeof(struct udphdr); - break; - default: - BUG(); - break; - } - } else { - BUG(); - } - - peer->hdrsize += sizeof(struct rxrpc_wire_header); - peer->maxdata = peer->mtu - peer->hdrsize; - } - - _leave(" = %p", peer); - return peer; -} - -/* - * obtain a remote transport endpoint for the specified address - */ -struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp) -{ - struct rxrpc_peer *peer, *candidate; - const char *new = "old"; - int usage; - - _enter("{%d,%d,%pI4+%hu}", - srx->transport_type, - srx->transport_len, - &srx->transport.sin.sin_addr, - ntohs(srx->transport.sin.sin_port)); - - /* search the peer list first */ - read_lock_bh(&rxrpc_peer_lock); - list_for_each_entry(peer, &rxrpc_peers, link) { - _debug("check PEER %d { u=%d t=%d l=%d }", - peer->debug_id, - atomic_read(&peer->usage), - peer->srx.transport_type, - peer->srx.transport_len); - - if (atomic_read(&peer->usage) > 0 && - peer->srx.transport_type == srx->transport_type && - peer->srx.transport_len == srx->transport_len && - memcmp(&peer->srx.transport, - &srx->transport, - srx->transport_len) == 0) - goto found_extant_peer; - } - read_unlock_bh(&rxrpc_peer_lock); - - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_peer(srx, gfp); - if (!candidate) { - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - - write_lock_bh(&rxrpc_peer_lock); - - list_for_each_entry(peer, &rxrpc_peers, link) { - if (atomic_read(&peer->usage) > 0 && - peer->srx.transport_type == srx->transport_type && - peer->srx.transport_len == srx->transport_len && - memcmp(&peer->srx.transport, - &srx->transport, - srx->transport_len) == 0) - goto found_extant_second; - } - - /* we can now add the new candidate to the list */ - peer = candidate; - candidate = NULL; - usage = atomic_read(&peer->usage); - - list_add_tail(&peer->link, &rxrpc_peers); - write_unlock_bh(&rxrpc_peer_lock); - new = "new"; - -success: - _net("PEER %s %d {%d,%u,%pI4+%hu}", - new, - peer->debug_id, - peer->srx.transport_type, - peer->srx.transport.family, - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); - - _leave(" = %p {u=%d}", peer, usage); - return peer; - - /* we found the peer in the list immediately */ -found_extant_peer: - usage = atomic_inc_return(&peer->usage); - read_unlock_bh(&rxrpc_peer_lock); - goto success; - - /* we found the peer on the second time through the list */ -found_extant_second: - usage = atomic_inc_return(&peer->usage); - write_unlock_bh(&rxrpc_peer_lock); - kfree(candidate); - goto success; -} - -/* - * find the peer associated with a packet - */ -struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *local, - __be32 addr, __be16 port) -{ - struct rxrpc_peer *peer; - - _enter(""); - - /* search the peer list */ - read_lock_bh(&rxrpc_peer_lock); - - if (local->srx.transport.family == AF_INET && - local->srx.transport_type == SOCK_DGRAM - ) { - list_for_each_entry(peer, &rxrpc_peers, link) { - if (atomic_read(&peer->usage) > 0 && - peer->srx.transport_type == SOCK_DGRAM && - peer->srx.transport.family == AF_INET && - peer->srx.transport.sin.sin_port == port && - peer->srx.transport.sin.sin_addr.s_addr == addr) - goto found_UDP_peer; - } - - goto new_UDP_peer; - } - - read_unlock_bh(&rxrpc_peer_lock); - _leave(" = -EAFNOSUPPORT"); - return ERR_PTR(-EAFNOSUPPORT); - -found_UDP_peer: - _net("Rx UDP DGRAM from peer %d", peer->debug_id); - atomic_inc(&peer->usage); - read_unlock_bh(&rxrpc_peer_lock); - _leave(" = %p", peer); - return peer; - -new_UDP_peer: - _net("Rx UDP DGRAM from NEW peer"); - read_unlock_bh(&rxrpc_peer_lock); - _leave(" = -EBUSY [new]"); - return ERR_PTR(-EBUSY); -} - -/* - * release a remote transport endpoint - */ -void rxrpc_put_peer(struct rxrpc_peer *peer) -{ - _enter("%p{u=%d}", peer, atomic_read(&peer->usage)); - - ASSERTCMP(atomic_read(&peer->usage), >, 0); - - if (likely(!atomic_dec_and_test(&peer->usage))) { - _leave(" [in use]"); - return; - } - - rxrpc_queue_work(&peer->destroyer); - _leave(""); -} - -/* - * destroy a remote transport endpoint - */ -static void rxrpc_destroy_peer(struct work_struct *work) -{ - struct rxrpc_peer *peer = - container_of(work, struct rxrpc_peer, destroyer); - - _enter("%p{%d}", peer, atomic_read(&peer->usage)); - - write_lock_bh(&rxrpc_peer_lock); - list_del(&peer->link); - write_unlock_bh(&rxrpc_peer_lock); - - _net("DESTROY PEER %d", peer->debug_id); - kfree(peer); - - if (list_empty(&rxrpc_peers)) - wake_up_all(&rxrpc_peer_wq); - _leave(""); -} - -/* - * preemptively destroy all the peer records from a transport endpoint rather - * than waiting for them to time out - */ -void __exit rxrpc_destroy_all_peers(void) -{ - DECLARE_WAITQUEUE(myself,current); - - _enter(""); - - /* we simply have to wait for them to go away */ - if (!list_empty(&rxrpc_peers)) { - set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(&rxrpc_peer_wq, &myself); - - while (!list_empty(&rxrpc_peers)) { - schedule(); - set_current_state(TASK_UNINTERRUPTIBLE); - } - - remove_wait_queue(&rxrpc_peer_wq, &myself); - set_current_state(TASK_RUNNING); - } - - _leave(""); -} diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c deleted file mode 100644 index 66a1a5676446..000000000000 --- a/net/rxrpc/ar-transport.c +++ /dev/null @@ -1,284 +0,0 @@ -/* RxRPC point-to-point transport session management - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/slab.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include "ar-internal.h" - -/* - * Time after last use at which transport record is cleaned up. - */ -unsigned int rxrpc_transport_expiry = 3600 * 24; - -static void rxrpc_transport_reaper(struct work_struct *work); - -static LIST_HEAD(rxrpc_transports); -static DEFINE_RWLOCK(rxrpc_transport_lock); -static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper); - -/* - * allocate a new transport session manager - */ -static struct rxrpc_transport *rxrpc_alloc_transport(struct rxrpc_local *local, - struct rxrpc_peer *peer, - gfp_t gfp) -{ - struct rxrpc_transport *trans; - - _enter(""); - - trans = kzalloc(sizeof(struct rxrpc_transport), gfp); - if (trans) { - trans->local = local; - trans->peer = peer; - INIT_LIST_HEAD(&trans->link); - trans->bundles = RB_ROOT; - trans->client_conns = RB_ROOT; - trans->server_conns = RB_ROOT; - skb_queue_head_init(&trans->error_queue); - spin_lock_init(&trans->client_lock); - rwlock_init(&trans->conn_lock); - atomic_set(&trans->usage, 1); - trans->conn_idcounter = peer->srx.srx_service << 16; - trans->debug_id = atomic_inc_return(&rxrpc_debug_id); - - if (peer->srx.transport.family == AF_INET) { - switch (peer->srx.transport_type) { - case SOCK_DGRAM: - INIT_WORK(&trans->error_handler, - rxrpc_UDP_error_handler); - break; - default: - BUG(); - break; - } - } else { - BUG(); - } - } - - _leave(" = %p", trans); - return trans; -} - -/* - * obtain a transport session for the nominated endpoints - */ -struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *local, - struct rxrpc_peer *peer, - gfp_t gfp) -{ - struct rxrpc_transport *trans, *candidate; - const char *new = "old"; - int usage; - - _enter("{%pI4+%hu},{%pI4+%hu},", - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port), - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); - - /* search the transport list first */ - read_lock_bh(&rxrpc_transport_lock); - list_for_each_entry(trans, &rxrpc_transports, link) { - if (trans->local == local && trans->peer == peer) - goto found_extant_transport; - } - read_unlock_bh(&rxrpc_transport_lock); - - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_transport(local, peer, gfp); - if (!candidate) { - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - - write_lock_bh(&rxrpc_transport_lock); - - list_for_each_entry(trans, &rxrpc_transports, link) { - if (trans->local == local && trans->peer == peer) - goto found_extant_second; - } - - /* we can now add the new candidate to the list */ - trans = candidate; - candidate = NULL; - usage = atomic_read(&trans->usage); - - rxrpc_get_local(trans->local); - atomic_inc(&trans->peer->usage); - list_add_tail(&trans->link, &rxrpc_transports); - write_unlock_bh(&rxrpc_transport_lock); - new = "new"; - -success: - _net("TRANSPORT %s %d local %d -> peer %d", - new, - trans->debug_id, - trans->local->debug_id, - trans->peer->debug_id); - - _leave(" = %p {u=%d}", trans, usage); - return trans; - - /* we found the transport in the list immediately */ -found_extant_transport: - usage = atomic_inc_return(&trans->usage); - read_unlock_bh(&rxrpc_transport_lock); - goto success; - - /* we found the transport on the second time through the list */ -found_extant_second: - usage = atomic_inc_return(&trans->usage); - write_unlock_bh(&rxrpc_transport_lock); - kfree(candidate); - goto success; -} - -/* - * find the transport connecting two endpoints - */ -struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *local, - struct rxrpc_peer *peer) -{ - struct rxrpc_transport *trans; - - _enter("{%pI4+%hu},{%pI4+%hu},", - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port), - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); - - /* search the transport list */ - read_lock_bh(&rxrpc_transport_lock); - - list_for_each_entry(trans, &rxrpc_transports, link) { - if (trans->local == local && trans->peer == peer) - goto found_extant_transport; - } - - read_unlock_bh(&rxrpc_transport_lock); - _leave(" = NULL"); - return NULL; - -found_extant_transport: - atomic_inc(&trans->usage); - read_unlock_bh(&rxrpc_transport_lock); - _leave(" = %p", trans); - return trans; -} - -/* - * release a transport session - */ -void rxrpc_put_transport(struct rxrpc_transport *trans) -{ - _enter("%p{u=%d}", trans, atomic_read(&trans->usage)); - - ASSERTCMP(atomic_read(&trans->usage), >, 0); - - trans->put_time = ktime_get_seconds(); - if (unlikely(atomic_dec_and_test(&trans->usage))) { - _debug("zombie"); - /* let the reaper determine the timeout to avoid a race with - * overextending the timeout if the reaper is running at the - * same time */ - rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0); - } - _leave(""); -} - -/* - * clean up a transport session - */ -static void rxrpc_cleanup_transport(struct rxrpc_transport *trans) -{ - _net("DESTROY TRANS %d", trans->debug_id); - - rxrpc_purge_queue(&trans->error_queue); - - rxrpc_put_local(trans->local); - rxrpc_put_peer(trans->peer); - kfree(trans); -} - -/* - * reap dead transports that have passed their expiry date - */ -static void rxrpc_transport_reaper(struct work_struct *work) -{ - struct rxrpc_transport *trans, *_p; - unsigned long now, earliest, reap_time; - - LIST_HEAD(graveyard); - - _enter(""); - - now = ktime_get_seconds(); - earliest = ULONG_MAX; - - /* extract all the transports that have been dead too long */ - write_lock_bh(&rxrpc_transport_lock); - list_for_each_entry_safe(trans, _p, &rxrpc_transports, link) { - _debug("reap TRANS %d { u=%d t=%ld }", - trans->debug_id, atomic_read(&trans->usage), - (long) now - (long) trans->put_time); - - if (likely(atomic_read(&trans->usage) > 0)) - continue; - - reap_time = trans->put_time + rxrpc_transport_expiry; - if (reap_time <= now) - list_move_tail(&trans->link, &graveyard); - else if (reap_time < earliest) - earliest = reap_time; - } - write_unlock_bh(&rxrpc_transport_lock); - - if (earliest != ULONG_MAX) { - _debug("reschedule reaper %ld", (long) earliest - now); - ASSERTCMP(earliest, >, now); - rxrpc_queue_delayed_work(&rxrpc_transport_reap, - (earliest - now) * HZ); - } - - /* then destroy all those pulled out */ - while (!list_empty(&graveyard)) { - trans = list_entry(graveyard.next, struct rxrpc_transport, - link); - list_del_init(&trans->link); - - ASSERTCMP(atomic_read(&trans->usage), ==, 0); - rxrpc_cleanup_transport(trans); - } - - _leave(""); -} - -/* - * preemptively destroy all the transport session records rather than waiting - * for them to time out - */ -void __exit rxrpc_destroy_all_transports(void) -{ - _enter(""); - - rxrpc_transport_expiry = 0; - cancel_delayed_work(&rxrpc_transport_reap); - rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0); - - _leave(""); -} diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/call_accept.c index e7a7f05f13e2..0b2832141bd0 100644 --- a/net/rxrpc/ar-accept.c +++ b/net/rxrpc/call_accept.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> @@ -72,9 +74,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, struct sockaddr_rxrpc *srx) { struct rxrpc_connection *conn; - struct rxrpc_transport *trans; struct rxrpc_skb_priv *sp, *nsp; - struct rxrpc_peer *peer; struct rxrpc_call *call; struct sk_buff *notification; int ret; @@ -93,30 +93,14 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, rxrpc_new_skb(notification); notification->mark = RXRPC_SKB_MARK_NEW_CALL; - peer = rxrpc_get_peer(srx, GFP_NOIO); - if (IS_ERR(peer)) { - _debug("no peer"); - ret = -EBUSY; - goto error; - } - - trans = rxrpc_get_transport(local, peer, GFP_NOIO); - rxrpc_put_peer(peer); - if (IS_ERR(trans)) { - _debug("no trans"); - ret = -EBUSY; - goto error; - } - - conn = rxrpc_incoming_connection(trans, &sp->hdr); - rxrpc_put_transport(trans); + conn = rxrpc_incoming_connection(local, srx, skb); if (IS_ERR(conn)) { _debug("no conn"); ret = PTR_ERR(conn); goto error; } - call = rxrpc_incoming_call(rx, conn, &sp->hdr); + call = rxrpc_incoming_call(rx, conn, skb); rxrpc_put_connection(conn); if (IS_ERR(call)) { _debug("no call"); @@ -135,12 +119,11 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, spin_lock(&call->conn->state_lock); if (sp->hdr.securityIndex > 0 && - call->conn->state == RXRPC_CONN_SERVER_UNSECURED) { + call->conn->state == RXRPC_CONN_SERVICE_UNSECURED) { _debug("await conn sec"); list_add_tail(&call->accept_link, &rx->secureq); - call->conn->state = RXRPC_CONN_SERVER_CHALLENGING; - atomic_inc(&call->conn->usage); - set_bit(RXRPC_CONN_CHALLENGE, &call->conn->events); + call->conn->state = RXRPC_CONN_SERVICE_CHALLENGING; + set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); rxrpc_queue_conn(call->conn); } else { _debug("conn ready"); @@ -200,10 +183,8 @@ error_nofree: * accept incoming calls that need peer, transport and/or connection setting up * - the packets we get are all incoming client DATA packets that have seq == 1 */ -void rxrpc_accept_incoming_calls(struct work_struct *work) +void rxrpc_accept_incoming_calls(struct rxrpc_local *local) { - struct rxrpc_local *local = - container_of(work, struct rxrpc_local, acceptor); struct rxrpc_skb_priv *sp; struct sockaddr_rxrpc srx; struct rxrpc_sock *rx; @@ -213,21 +194,8 @@ void rxrpc_accept_incoming_calls(struct work_struct *work) _enter("%d", local->debug_id); - read_lock_bh(&rxrpc_local_lock); - if (atomic_read(&local->usage) > 0) - rxrpc_get_local(local); - else - local = NULL; - read_unlock_bh(&rxrpc_local_lock); - if (!local) { - _leave(" [local dead]"); - return; - } - -process_next_packet: skb = skb_dequeue(&local->accept_queue); if (!skb) { - rxrpc_put_local(local); _leave("\n"); return; } @@ -249,20 +217,8 @@ process_next_packet: whdr._rsvd = 0; whdr.serviceId = htons(sp->hdr.serviceId); - /* determine the remote address */ - memset(&srx, 0, sizeof(srx)); - srx.srx_family = AF_RXRPC; - srx.transport.family = local->srx.transport.family; - srx.transport_type = local->srx.transport_type; - switch (srx.transport.family) { - case AF_INET: - srx.transport_len = sizeof(struct sockaddr_in); - srx.transport.sin.sin_port = udp_hdr(skb)->source; - srx.transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; - break; - default: - goto busy; - } + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) + goto drop; /* get the socket providing the service */ read_lock_bh(&local->services_lock); @@ -290,7 +246,7 @@ found_service: case -ECONNRESET: /* old calls are ignored */ case -ECONNABORTED: /* aborted calls are reaborted or ignored */ case 0: - goto process_next_packet; + return; case -ECONNREFUSED: goto invalid_service; case -EBUSY: @@ -306,18 +262,22 @@ backlog_full: busy: rxrpc_busy(local, &srx, &whdr); rxrpc_free_skb(skb); - goto process_next_packet; + return; + +drop: + rxrpc_free_skb(skb); + return; invalid_service: skb->priority = RX_INVALID_OPERATION; rxrpc_reject_packet(local, skb); - goto process_next_packet; + return; /* can't change connection security type mid-flow */ security_mismatch: skb->priority = RX_PROTOCOL_ERROR; rxrpc_reject_packet(local, skb); - goto process_next_packet; + return; } /* diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/call_event.c index 374478e006e7..fc32aa5764a2 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/call_event.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/circ_buf.h> #include <linux/net.h> @@ -185,7 +187,7 @@ static void rxrpc_resend(struct rxrpc_call *call) _proto("Tx DATA %%%u { #%d }", sp->hdr.serial, sp->hdr.seq); - if (rxrpc_send_packet(call->conn->trans, txb) < 0) { + if (rxrpc_send_data_packet(call->conn, txb) < 0) { stop = true; sp->resend_at = jiffies + 3; } else { @@ -543,7 +545,7 @@ static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU)); - peer = call->conn->trans->peer; + peer = call->conn->params.peer; if (mtu < peer->maxdata) { spin_lock_bh(&peer->lock); peer->maxdata = mtu; @@ -834,13 +836,13 @@ void rxrpc_process_call(struct work_struct *work) /* there's a good chance we're going to have to send a message, so set * one up in advance */ - msg.msg_name = &call->conn->trans->peer->srx.transport; - msg.msg_namelen = call->conn->trans->peer->srx.transport_len; + msg.msg_name = &call->conn->params.peer->srx.transport; + msg.msg_namelen = call->conn->params.peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; - whdr.epoch = htonl(call->conn->epoch); + whdr.epoch = htonl(call->conn->proto.epoch); whdr.cid = htonl(call->cid); whdr.callNumber = htonl(call->call_id); whdr.seq = 0; @@ -856,23 +858,25 @@ void rxrpc_process_call(struct work_struct *work) iov[0].iov_len = sizeof(whdr); /* deal with events of a final nature */ - if (test_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { - rxrpc_release_call(call); - clear_bit(RXRPC_CALL_EV_RELEASE, &call->events); - } - if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { + enum rxrpc_skb_mark mark; int error; clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); clear_bit(RXRPC_CALL_EV_ABORT, &call->events); - error = call->conn->trans->peer->net_error; - _debug("post net error %d", error); + error = call->error_report; + if (error < RXRPC_LOCAL_ERROR_OFFSET) { + mark = RXRPC_SKB_MARK_NET_ERROR; + _debug("post net error %d", error); + } else { + mark = RXRPC_SKB_MARK_LOCAL_ERROR; + error -= RXRPC_LOCAL_ERROR_OFFSET; + _debug("post net local error %d", error); + } - if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR, - error, true) < 0) + if (rxrpc_post_message(call, mark, error, true) < 0) goto no_mem; clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); goto kill_ACKs; @@ -1085,7 +1089,7 @@ void rxrpc_process_call(struct work_struct *work) if (call->state == RXRPC_CALL_SERVER_SECURING) { _debug("securing"); - write_lock(&call->conn->lock); + write_lock(&call->socket->call_lock); if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && !test_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { _debug("not released"); @@ -1093,7 +1097,7 @@ void rxrpc_process_call(struct work_struct *work) list_move_tail(&call->accept_link, &call->socket->acceptq); } - write_unlock(&call->conn->lock); + write_unlock(&call->socket->call_lock); read_lock(&call->state_lock); if (call->state < RXRPC_CALL_COMPLETE) set_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events); @@ -1135,6 +1139,11 @@ void rxrpc_process_call(struct work_struct *work) goto maybe_reschedule; } + if (test_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { + rxrpc_release_call(call); + clear_bit(RXRPC_CALL_EV_RELEASE, &call->events); + } + /* other events may have been raised since we started checking */ goto maybe_reschedule; @@ -1142,8 +1151,8 @@ send_ACK_with_skew: ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) - ntohl(ack.serial)); send_ACK: - mtu = call->conn->trans->peer->if_mtu; - mtu -= call->conn->trans->peer->hdrsize; + mtu = call->conn->params.peer->if_mtu; + mtu -= call->conn->params.peer->hdrsize; ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(rxrpc_rx_window_size); @@ -1197,7 +1206,7 @@ send_message_2: len += iov[1].iov_len; } - ret = kernel_sendmsg(call->conn->trans->local->socket, + ret = kernel_sendmsg(call->conn->params.local->socket, &msg, iov, ioc, len); if (ret < 0) { _debug("sendmsg failed: %d", ret); @@ -1255,7 +1264,7 @@ maybe_reschedule: if (call->state >= RXRPC_CALL_COMPLETE && !list_empty(&call->accept_link)) { _debug("X unlinking once-pending call %p { e=%lx f=%lx c=%x }", - call, call->events, call->flags, call->conn->cid); + call, call->events, call->flags, call->conn->proto.cid); read_lock_bh(&call->state_lock); if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && @@ -1273,7 +1282,7 @@ error: * this means there's a race between clearing the flag and setting the * work pending bit and the work item being processed again */ if (call->events && !work_pending(&call->processor)) { - _debug("jumpstart %x", call->conn->cid); + _debug("jumpstart %x", call->conn->proto.cid); rxrpc_queue_call(call); } diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/call_object.c index 571a41fd5a32..91287c9d01bb 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/call_object.c @@ -9,10 +9,11 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/module.h> #include <linux/circ_buf.h> -#include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <net/sock.h> #include <net/af_rxrpc.h> @@ -29,6 +30,8 @@ unsigned int rxrpc_max_call_lifetime = 60 * HZ; unsigned int rxrpc_dead_call_expiry = 2 * HZ; const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { + [RXRPC_CALL_UNINITIALISED] = "Uninit", + [RXRPC_CALL_CLIENT_AWAIT_CONN] = "ClWtConn", [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", [RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl", @@ -57,140 +60,41 @@ static void rxrpc_dead_call_expired(unsigned long _call); static void rxrpc_ack_time_expired(unsigned long _call); static void rxrpc_resend_time_expired(unsigned long _call); -static DEFINE_SPINLOCK(rxrpc_call_hash_lock); -static DEFINE_HASHTABLE(rxrpc_call_hash, 10); - /* - * Hash function for rxrpc_call_hash + * find an extant server call + * - called in process context with IRQs enabled */ -static unsigned long rxrpc_call_hashfunc( - u8 in_clientflag, - u32 cid, - u32 call_id, - u32 epoch, - u16 service_id, - sa_family_t proto, - void *localptr, - unsigned int addr_size, - const u8 *peer_addr) +struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, + unsigned long user_call_ID) { - const u16 *p; - unsigned int i; - unsigned long key; + struct rxrpc_call *call; + struct rb_node *p; - _enter(""); + _enter("%p,%lx", rx, user_call_ID); - key = (unsigned long)localptr; - /* We just want to add up the __be32 values, so forcing the - * cast should be okay. - */ - key += epoch; - key += service_id; - key += call_id; - key += (cid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT; - key += cid & RXRPC_CHANNELMASK; - key += in_clientflag; - key += proto; - /* Step through the peer address in 16-bit portions for speed */ - for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++) - key += *p; - _leave(" key = 0x%lx", key); - return key; -} + read_lock(&rx->call_lock); -/* - * Add a call to the hashtable - */ -static void rxrpc_call_hash_add(struct rxrpc_call *call) -{ - unsigned long key; - unsigned int addr_size = 0; + p = rx->calls.rb_node; + while (p) { + call = rb_entry(p, struct rxrpc_call, sock_node); - _enter(""); - switch (call->proto) { - case AF_INET: - addr_size = sizeof(call->peer_ip.ipv4_addr); - break; - case AF_INET6: - addr_size = sizeof(call->peer_ip.ipv6_addr); - break; - default: - break; + if (user_call_ID < call->user_call_ID) + p = p->rb_left; + else if (user_call_ID > call->user_call_ID) + p = p->rb_right; + else + goto found_extant_call; } - key = rxrpc_call_hashfunc(call->in_clientflag, call->cid, - call->call_id, call->epoch, - call->service_id, call->proto, - call->conn->trans->local, addr_size, - call->peer_ip.ipv6_addr); - /* Store the full key in the call */ - call->hash_key = key; - spin_lock(&rxrpc_call_hash_lock); - hash_add_rcu(rxrpc_call_hash, &call->hash_node, key); - spin_unlock(&rxrpc_call_hash_lock); - _leave(""); -} - -/* - * Remove a call from the hashtable - */ -static void rxrpc_call_hash_del(struct rxrpc_call *call) -{ - _enter(""); - spin_lock(&rxrpc_call_hash_lock); - hash_del_rcu(&call->hash_node); - spin_unlock(&rxrpc_call_hash_lock); - _leave(""); -} -/* - * Find a call in the hashtable and return it, or NULL if it - * isn't there. - */ -struct rxrpc_call *rxrpc_find_call_hash( - struct rxrpc_host_header *hdr, - void *localptr, - sa_family_t proto, - const void *peer_addr) -{ - unsigned long key; - unsigned int addr_size = 0; - struct rxrpc_call *call = NULL; - struct rxrpc_call *ret = NULL; - u8 in_clientflag = hdr->flags & RXRPC_CLIENT_INITIATED; - - _enter(""); - switch (proto) { - case AF_INET: - addr_size = sizeof(call->peer_ip.ipv4_addr); - break; - case AF_INET6: - addr_size = sizeof(call->peer_ip.ipv6_addr); - break; - default: - break; - } + read_unlock(&rx->call_lock); + _leave(" = NULL"); + return NULL; - key = rxrpc_call_hashfunc(in_clientflag, hdr->cid, hdr->callNumber, - hdr->epoch, hdr->serviceId, - proto, localptr, addr_size, - peer_addr); - hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) { - if (call->hash_key == key && - call->call_id == hdr->callNumber && - call->cid == hdr->cid && - call->in_clientflag == in_clientflag && - call->service_id == hdr->serviceId && - call->proto == proto && - call->local == localptr && - memcmp(call->peer_ip.ipv6_addr, peer_addr, - addr_size) == 0 && - call->epoch == hdr->epoch) { - ret = call; - break; - } - } - _leave(" = %p", ret); - return ret; +found_extant_call: + rxrpc_get_call(call); + read_unlock(&rx->call_lock); + _leave(" = %p [%d]", call, atomic_read(&call->usage)); + return call; } /* @@ -222,6 +126,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) (unsigned long) call); INIT_WORK(&call->destroyer, &rxrpc_destroy_call); INIT_WORK(&call->processor, &rxrpc_process_call); + INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->accept_link); skb_queue_head_init(&call->rx_queue); skb_queue_head_init(&call->rx_oos_queue); @@ -230,7 +135,6 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = atomic_inc_return(&rxrpc_debug_id); - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -243,117 +147,88 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) } /* - * allocate a new client call and attempt to get a connection slot for it + * Allocate a new client call. */ -static struct rxrpc_call *rxrpc_alloc_client_call( - struct rxrpc_sock *rx, - struct rxrpc_transport *trans, - struct rxrpc_conn_bundle *bundle, - gfp_t gfp) +static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, + struct sockaddr_rxrpc *srx, + gfp_t gfp) { struct rxrpc_call *call; - int ret; _enter(""); - ASSERT(rx != NULL); - ASSERT(trans != NULL); - ASSERT(bundle != NULL); + ASSERT(rx->local != NULL); call = rxrpc_alloc_call(gfp); if (!call) return ERR_PTR(-ENOMEM); + call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; sock_hold(&rx->sk); call->socket = rx; call->rx_data_post = 1; - ret = rxrpc_connect_call(rx, trans, bundle, call, gfp); - if (ret < 0) { - kmem_cache_free(rxrpc_call_jar, call); - return ERR_PTR(ret); - } + call->local = rx->local; + call->service_id = srx->srx_service; + call->in_clientflag = 0; - /* Record copies of information for hashtable lookup */ - call->proto = rx->proto; - call->local = trans->local; - switch (call->proto) { - case AF_INET: - call->peer_ip.ipv4_addr = - trans->peer->srx.transport.sin.sin_addr.s_addr; - break; - case AF_INET6: - memcpy(call->peer_ip.ipv6_addr, - trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, - sizeof(call->peer_ip.ipv6_addr)); - break; - } - call->epoch = call->conn->epoch; - call->service_id = call->conn->service_id; - call->in_clientflag = call->conn->in_clientflag; - /* Add the new call to the hashtable */ - rxrpc_call_hash_add(call); + _leave(" = %p", call); + return call; +} - spin_lock(&call->conn->trans->peer->lock); - list_add(&call->error_link, &call->conn->trans->peer->error_targets); - spin_unlock(&call->conn->trans->peer->lock); +/* + * Begin client call. + */ +static int rxrpc_begin_client_call(struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + int ret; + + /* Set up or get a connection record and set the protocol parameters, + * including channel number and call ID. + */ + ret = rxrpc_connect_call(call, cp, srx, gfp); + if (ret < 0) + return ret; + + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; + + spin_lock(&call->conn->params.peer->lock); + hlist_add_head(&call->error_link, &call->conn->params.peer->error_targets); + spin_unlock(&call->conn->params.peer->lock); call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); - - _leave(" = %p", call); - return call; + return 0; } /* * set up a call for the given data * - called in process context with IRQs enabled */ -struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, - struct rxrpc_transport *trans, - struct rxrpc_conn_bundle *bundle, +struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, unsigned long user_call_ID, - int create, gfp_t gfp) { - struct rxrpc_call *call, *candidate; - struct rb_node *p, *parent, **pp; - - _enter("%p,%d,%d,%lx,%d", - rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1, - user_call_ID, create); - - /* search the extant calls first for one that matches the specified - * user ID */ - read_lock(&rx->call_lock); - - p = rx->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - p = p->rb_left; - else if (user_call_ID > call->user_call_ID) - p = p->rb_right; - else - goto found_extant_call; - } - - read_unlock(&rx->call_lock); + struct rxrpc_call *call, *xcall; + struct rb_node *parent, **pp; + int ret; - if (!create || !trans) - return ERR_PTR(-EBADSLT); + _enter("%p,%lx", rx, user_call_ID); - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp); - if (IS_ERR(candidate)) { - _leave(" = %ld", PTR_ERR(candidate)); - return candidate; + call = rxrpc_alloc_client_call(rx, srx, gfp); + if (IS_ERR(call)) { + _leave(" = %ld", PTR_ERR(call)); + return call; } - candidate->user_call_ID = user_call_ID; - __set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags); + /* Publish the call, even though it is incompletely set up as yet */ + call->user_call_ID = user_call_ID; + __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); write_lock(&rx->call_lock); @@ -361,19 +236,16 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, parent = NULL; while (*pp) { parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); + xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else - goto found_extant_second; + goto found_user_ID_now_present; } - /* second search also failed; add the new call */ - call = candidate; - candidate = NULL; rxrpc_get_call(call); rb_link_node(&call->sock_node, parent, pp); @@ -384,25 +256,41 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); + ret = rxrpc_begin_client_call(call, cp, srx, gfp); + if (ret < 0) + goto error; + _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); _leave(" = %p [new]", call); return call; - /* we found the call in the list immediately */ -found_extant_call: - rxrpc_get_call(call); - read_unlock(&rx->call_lock); - _leave(" = %p [extant %d]", call, atomic_read(&call->usage)); - return call; +error: + write_lock(&rx->call_lock); + rb_erase(&call->sock_node, &rx->calls); + write_unlock(&rx->call_lock); + rxrpc_put_call(call); - /* we found the call on the second time through the list */ -found_extant_second: - rxrpc_get_call(call); + write_lock_bh(&rxrpc_call_lock); + list_del_init(&call->link); + write_unlock_bh(&rxrpc_call_lock); + + call->state = RXRPC_CALL_DEAD; + rxrpc_put_call(call); + _leave(" = %d", ret); + return ERR_PTR(ret); + + /* We unexpectedly found the user ID in the list after taking + * the call_lock. This shouldn't happen unless the user races + * with itself and tries to add the same user ID twice at the + * same time in different threads. + */ +found_user_ID_now_present: write_unlock(&rx->call_lock); - rxrpc_put_call(candidate); - _leave(" = %p [second %d]", call, atomic_read(&call->usage)); - return call; + call->state = RXRPC_CALL_DEAD; + rxrpc_put_call(call); + _leave(" = -EEXIST [%p]", call); + return ERR_PTR(-EEXIST); } /* @@ -411,11 +299,11 @@ found_extant_second: */ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_connection *conn, - struct rxrpc_host_header *hdr) + struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_call *call, *candidate; - struct rb_node **p, *parent; - u32 call_id; + u32 call_id, chan; _enter(",%d", conn->debug_id); @@ -425,22 +313,25 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, if (!candidate) return ERR_PTR(-EBUSY); - candidate->socket = rx; - candidate->conn = conn; - candidate->cid = hdr->cid; - candidate->call_id = hdr->callNumber; - candidate->channel = hdr->cid & RXRPC_CHANNELMASK; - candidate->rx_data_post = 0; - candidate->state = RXRPC_CALL_SERVER_ACCEPTING; + chan = sp->hdr.cid & RXRPC_CHANNELMASK; + candidate->socket = rx; + candidate->conn = conn; + candidate->cid = sp->hdr.cid; + candidate->call_id = sp->hdr.callNumber; + candidate->channel = chan; + candidate->rx_data_post = 0; + candidate->state = RXRPC_CALL_SERVER_ACCEPTING; if (conn->security_ix > 0) candidate->state = RXRPC_CALL_SERVER_SECURING; - write_lock_bh(&conn->lock); + spin_lock(&conn->channel_lock); /* set the channel for this call */ - call = conn->channels[candidate->channel]; + call = rcu_dereference_protected(conn->channels[chan].call, + lockdep_is_held(&conn->channel_lock)); + _debug("channel[%u] is %p", candidate->channel, call); - if (call && call->call_id == hdr->callNumber) { + if (call && call->call_id == sp->hdr.callNumber) { /* already set; must've been a duplicate packet */ _debug("extant call [%d]", call->state); ASSERTCMP(call->conn, ==, conn); @@ -467,9 +358,9 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, call->debug_id, rxrpc_call_states[call->state]); if (call->state >= RXRPC_CALL_COMPLETE) { - conn->channels[call->channel] = NULL; + __rxrpc_disconnect_call(call); } else { - write_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); kmem_cache_free(rxrpc_call_jar, candidate); _leave(" = -EBUSY"); return ERR_PTR(-EBUSY); @@ -478,64 +369,36 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, /* check the call number isn't duplicate */ _debug("check dup"); - call_id = hdr->callNumber; - p = &conn->calls.rb_node; - parent = NULL; - while (*p) { - parent = *p; - call = rb_entry(parent, struct rxrpc_call, conn_node); - - /* The tree is sorted in order of the __be32 value without - * turning it into host order. - */ - if (call_id < call->call_id) - p = &(*p)->rb_left; - else if (call_id > call->call_id) - p = &(*p)->rb_right; - else - goto old_call; - } + call_id = sp->hdr.callNumber; + + /* We just ignore calls prior to the current call ID. Terminated calls + * are handled via the connection. + */ + if (call_id <= conn->channels[chan].call_counter) + goto old_call; /* TODO: Just drop packet */ /* make the call available */ _debug("new call"); call = candidate; candidate = NULL; - rb_link_node(&call->conn_node, parent, p); - rb_insert_color(&call->conn_node, &conn->calls); - conn->channels[call->channel] = call; + conn->channels[chan].call_counter = call_id; + rcu_assign_pointer(conn->channels[chan].call, call); sock_hold(&rx->sk); - atomic_inc(&conn->usage); - write_unlock_bh(&conn->lock); + rxrpc_get_connection(conn); + spin_unlock(&conn->channel_lock); - spin_lock(&conn->trans->peer->lock); - list_add(&call->error_link, &conn->trans->peer->error_targets); - spin_unlock(&conn->trans->peer->lock); + spin_lock(&conn->params.peer->lock); + hlist_add_head(&call->error_link, &conn->params.peer->error_targets); + spin_unlock(&conn->params.peer->lock); write_lock_bh(&rxrpc_call_lock); list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); - /* Record copies of information for hashtable lookup */ - call->proto = rx->proto; - call->local = conn->trans->local; - switch (call->proto) { - case AF_INET: - call->peer_ip.ipv4_addr = - conn->trans->peer->srx.transport.sin.sin_addr.s_addr; - break; - case AF_INET6: - memcpy(call->peer_ip.ipv6_addr, - conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, - sizeof(call->peer_ip.ipv6_addr)); - break; - default: - break; - } - call->epoch = conn->epoch; - call->service_id = conn->service_id; - call->in_clientflag = conn->in_clientflag; - /* Add the new call to the hashtable */ - rxrpc_call_hash_add(call); + call->local = conn->params.local; + call->epoch = conn->proto.epoch; + call->service_id = conn->params.service_id; + call->in_clientflag = RXRPC_CLIENT_INITIATED; _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); @@ -545,65 +408,25 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, return call; extant_call: - write_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); kmem_cache_free(rxrpc_call_jar, candidate); _leave(" = %p {%d} [extant]", call, call ? call->debug_id : -1); return call; aborted_call: - write_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); kmem_cache_free(rxrpc_call_jar, candidate); _leave(" = -ECONNABORTED"); return ERR_PTR(-ECONNABORTED); old_call: - write_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); kmem_cache_free(rxrpc_call_jar, candidate); _leave(" = -ECONNRESET [old]"); return ERR_PTR(-ECONNRESET); } /* - * find an extant server call - * - called in process context with IRQs enabled - */ -struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *rx, - unsigned long user_call_ID) -{ - struct rxrpc_call *call; - struct rb_node *p; - - _enter("%p,%lx", rx, user_call_ID); - - /* search the extant calls for one that matches the specified user - * ID */ - read_lock(&rx->call_lock); - - p = rx->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - p = p->rb_left; - else if (user_call_ID > call->user_call_ID) - p = p->rb_right; - else - goto found_extant_call; - } - - read_unlock(&rx->call_lock); - _leave(" = NULL"); - return NULL; - - /* we found the call in the list immediately */ -found_extant_call: - rxrpc_get_call(call); - read_unlock(&rx->call_lock); - _leave(" = %p [%d]", call, atomic_read(&call->usage)); - return call; -} - -/* * detach a call from a socket and set up for release */ void rxrpc_release_call(struct rxrpc_call *call) @@ -626,6 +449,10 @@ void rxrpc_release_call(struct rxrpc_call *call) */ _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); + spin_lock(&conn->params.peer->lock); + hlist_del_init(&call->error_link); + spin_unlock(&conn->params.peer->lock); + write_lock_bh(&rx->call_lock); if (!list_empty(&call->accept_link)) { _debug("unlinking once-pending call %p { e=%lx f=%lx }", @@ -641,52 +468,17 @@ void rxrpc_release_call(struct rxrpc_call *call) write_unlock_bh(&rx->call_lock); /* free up the channel for reuse */ - spin_lock(&conn->trans->client_lock); - write_lock_bh(&conn->lock); - write_lock(&call->state_lock); - - if (conn->channels[call->channel] == call) - conn->channels[call->channel] = NULL; - - if (conn->out_clientflag && conn->bundle) { - conn->avail_calls++; - switch (conn->avail_calls) { - case 1: - list_move_tail(&conn->bundle_link, - &conn->bundle->avail_conns); - case 2 ... RXRPC_MAXCALLS - 1: - ASSERT(conn->channels[0] == NULL || - conn->channels[1] == NULL || - conn->channels[2] == NULL || - conn->channels[3] == NULL); - break; - case RXRPC_MAXCALLS: - list_move_tail(&conn->bundle_link, - &conn->bundle->unused_conns); - ASSERT(conn->channels[0] == NULL && - conn->channels[1] == NULL && - conn->channels[2] == NULL && - conn->channels[3] == NULL); - break; - default: - printk(KERN_ERR "RxRPC: conn->avail_calls=%d\n", - conn->avail_calls); - BUG(); - } - } - - spin_unlock(&conn->trans->client_lock); + write_lock_bh(&call->state_lock); if (call->state < RXRPC_CALL_COMPLETE && call->state != RXRPC_CALL_CLIENT_FINAL_ACK) { _debug("+++ ABORTING STATE %d +++\n", call->state); call->state = RXRPC_CALL_LOCALLY_ABORTED; call->local_abort = RX_CALL_DEAD; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); } - write_unlock(&call->state_lock); - write_unlock_bh(&conn->lock); + write_unlock_bh(&call->state_lock); + + rxrpc_disconnect_call(call); /* clean up the Rx queue */ if (!skb_queue_empty(&call->rx_queue) || @@ -820,6 +612,17 @@ void __rxrpc_put_call(struct rxrpc_call *call) } /* + * Final call destruction under RCU. + */ +static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +{ + struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + + rxrpc_purge_queue(&call->rx_queue); + kmem_cache_free(rxrpc_call_jar, call); +} + +/* * clean up a call */ static void rxrpc_cleanup_call(struct rxrpc_call *call) @@ -843,19 +646,7 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) return; } - if (call->conn) { - spin_lock(&call->conn->trans->peer->lock); - list_del(&call->error_link); - spin_unlock(&call->conn->trans->peer->lock); - - write_lock_bh(&call->conn->lock); - rb_erase(&call->conn_node, &call->conn->calls); - write_unlock_bh(&call->conn->lock); - rxrpc_put_connection(call->conn); - } - - /* Remove the call from the hash */ - rxrpc_call_hash_del(call); + ASSERTCMP(call->conn, ==, NULL); if (call->acks_window) { _debug("kill Tx window %d", @@ -883,7 +674,7 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_purge_queue(&call->rx_queue); ASSERT(skb_queue_empty(&call->rx_oos_queue)); sock_put(&call->socket->sk); - kmem_cache_free(rxrpc_call_jar, call); + call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } /* @@ -935,16 +726,15 @@ void __exit rxrpc_destroy_all_calls(void) if (call->state != RXRPC_CALL_DEAD) break; default: - printk(KERN_ERR "RXRPC:" - " Call %p still in use (%d,%d,%s,%lx,%lx)!\n", + pr_err("Call %p still in use (%d,%d,%s,%lx,%lx)!\n", call, atomic_read(&call->usage), atomic_read(&call->ackr_not_idle), rxrpc_call_states[call->state], call->flags, call->events); if (!skb_queue_empty(&call->rx_queue)) - printk(KERN_ERR"RXRPC: Rx queue occupied\n"); + pr_err("Rx queue occupied\n"); if (!skb_queue_empty(&call->rx_oos_queue)) - printk(KERN_ERR"RXRPC: OOS queue occupied\n"); + pr_err("OOS queue occupied\n"); break; } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c new file mode 100644 index 000000000000..9e91f27b0d0f --- /dev/null +++ b/net/rxrpc/conn_client.c @@ -0,0 +1,372 @@ +/* Client connection-specific management code. + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include <linux/idr.h> +#include <linux/timer.h> +#include "ar-internal.h" + +/* + * We use machine-unique IDs for our client connections. + */ +DEFINE_IDR(rxrpc_client_conn_ids); +static DEFINE_SPINLOCK(rxrpc_conn_id_lock); + +/* + * Get a connection ID and epoch for a client connection from the global pool. + * The connection struct pointer is then recorded in the idr radix tree. The + * epoch is changed if this wraps. + * + * TODO: The IDR tree gets very expensive on memory if the connection IDs are + * widely scattered throughout the number space, so we shall need to retire + * connections that have, say, an ID more than four times the maximum number of + * client conns away from the current allocation point to try and keep the IDs + * concentrated. We will also need to retire connections from an old epoch. + */ +static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, + gfp_t gfp) +{ + u32 epoch; + int id; + + _enter(""); + + idr_preload(gfp); + spin_lock(&rxrpc_conn_id_lock); + + epoch = rxrpc_epoch; + + /* We could use idr_alloc_cyclic() here, but we really need to know + * when the thing wraps so that we can advance the epoch. + */ + if (rxrpc_client_conn_ids.cur == 0) + rxrpc_client_conn_ids.cur = 1; + id = idr_alloc(&rxrpc_client_conn_ids, conn, + rxrpc_client_conn_ids.cur, 0x40000000, GFP_NOWAIT); + if (id < 0) { + if (id != -ENOSPC) + goto error; + id = idr_alloc(&rxrpc_client_conn_ids, conn, + 1, 0x40000000, GFP_NOWAIT); + if (id < 0) + goto error; + epoch++; + rxrpc_epoch = epoch; + } + rxrpc_client_conn_ids.cur = id + 1; + + spin_unlock(&rxrpc_conn_id_lock); + idr_preload_end(); + + conn->proto.epoch = epoch; + conn->proto.cid = id << RXRPC_CIDSHIFT; + set_bit(RXRPC_CONN_HAS_IDR, &conn->flags); + _leave(" [CID %x:%x]", epoch, conn->proto.cid); + return 0; + +error: + spin_unlock(&rxrpc_conn_id_lock); + idr_preload_end(); + _leave(" = %d", id); + return id; +} + +/* + * Release a connection ID for a client connection from the global pool. + */ +static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn) +{ + if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) { + spin_lock(&rxrpc_conn_id_lock); + idr_remove(&rxrpc_client_conn_ids, + conn->proto.cid >> RXRPC_CIDSHIFT); + spin_unlock(&rxrpc_conn_id_lock); + } +} + +/* + * Destroy the client connection ID tree. + */ +void rxrpc_destroy_client_conn_ids(void) +{ + struct rxrpc_connection *conn; + int id; + + if (!idr_is_empty(&rxrpc_client_conn_ids)) { + idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) { + pr_err("AF_RXRPC: Leaked client conn %p {%d}\n", + conn, atomic_read(&conn->usage)); + } + BUG(); + } + + idr_destroy(&rxrpc_client_conn_ids); +} + +/* + * Allocate a client connection. The caller must take care to clear any + * padding bytes in *cp. + */ +static struct rxrpc_connection * +rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) +{ + struct rxrpc_connection *conn; + int ret; + + _enter(""); + + conn = rxrpc_alloc_connection(gfp); + if (!conn) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + conn->params = *cp; + conn->out_clientflag = RXRPC_CLIENT_INITIATED; + conn->state = RXRPC_CONN_CLIENT; + + ret = rxrpc_get_client_connection_id(conn, gfp); + if (ret < 0) + goto error_0; + + ret = rxrpc_init_client_conn_security(conn); + if (ret < 0) + goto error_1; + + ret = conn->security->prime_packet_security(conn); + if (ret < 0) + goto error_2; + + write_lock(&rxrpc_connection_lock); + list_add_tail(&conn->link, &rxrpc_connections); + write_unlock(&rxrpc_connection_lock); + + /* We steal the caller's peer ref. */ + cp->peer = NULL; + rxrpc_get_local(conn->params.local); + key_get(conn->params.key); + + _leave(" = %p", conn); + return conn; + +error_2: + conn->security->clear(conn); +error_1: + rxrpc_put_client_connection_id(conn); +error_0: + kfree(conn); + _leave(" = %d", ret); + return ERR_PTR(ret); +} + +/* + * find a connection for a call + * - called in process context with IRQs enabled + */ +int rxrpc_connect_call(struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + struct rxrpc_connection *conn, *candidate = NULL; + struct rxrpc_local *local = cp->local; + struct rb_node *p, **pp, *parent; + long diff; + int chan; + + DECLARE_WAITQUEUE(myself, current); + + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + + cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); + if (!cp->peer) + return -ENOMEM; + + if (!cp->exclusive) { + /* Search for a existing client connection unless this is going + * to be a connection that's used exclusively for a single call. + */ + _debug("search 1"); + spin_lock(&local->client_conns_lock); + p = local->client_conns.rb_node; + while (p) { + conn = rb_entry(p, struct rxrpc_connection, client_node); + +#define cmp(X) ((long)conn->params.X - (long)cp->X) + diff = (cmp(peer) ?: + cmp(key) ?: + cmp(security_level)); + if (diff < 0) + p = p->rb_left; + else if (diff > 0) + p = p->rb_right; + else + goto found_extant_conn; + } + spin_unlock(&local->client_conns_lock); + } + + /* We didn't find a connection or we want an exclusive one. */ + _debug("get new conn"); + candidate = rxrpc_alloc_client_connection(cp, gfp); + if (!candidate) { + _leave(" = -ENOMEM"); + return -ENOMEM; + } + + if (cp->exclusive) { + /* Assign the call on an exclusive connection to channel 0 and + * don't add the connection to the endpoint's shareable conn + * lookup tree. + */ + _debug("exclusive chan 0"); + conn = candidate; + atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1); + spin_lock(&conn->channel_lock); + chan = 0; + goto found_channel; + } + + /* We need to redo the search before attempting to add a new connection + * lest we race with someone else adding a conflicting instance. + */ + _debug("search 2"); + spin_lock(&local->client_conns_lock); + + pp = &local->client_conns.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + conn = rb_entry(parent, struct rxrpc_connection, client_node); + + diff = (cmp(peer) ?: + cmp(key) ?: + cmp(security_level)); + if (diff < 0) + pp = &(*pp)->rb_left; + else if (diff > 0) + pp = &(*pp)->rb_right; + else + goto found_extant_conn; + } + + /* The second search also failed; simply add the new connection with + * the new call in channel 0. Note that we need to take the channel + * lock before dropping the client conn lock. + */ + _debug("new conn"); + set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); + rb_link_node(&candidate->client_node, parent, pp); + rb_insert_color(&candidate->client_node, &local->client_conns); +attached: + conn = candidate; + candidate = NULL; + + atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1); + spin_lock(&conn->channel_lock); + spin_unlock(&local->client_conns_lock); + chan = 0; + +found_channel: + _debug("found chan"); + call->conn = conn; + call->channel = chan; + call->epoch = conn->proto.epoch; + call->cid = conn->proto.cid | chan; + call->call_id = ++conn->channels[chan].call_counter; + conn->channels[chan].call_id = call->call_id; + rcu_assign_pointer(conn->channels[chan].call, call); + + _net("CONNECT call %d on conn %d", call->debug_id, conn->debug_id); + + spin_unlock(&conn->channel_lock); + rxrpc_put_peer(cp->peer); + cp->peer = NULL; + _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); + return 0; + + /* We found a potentially suitable connection already in existence. If + * we can reuse it (ie. its usage count hasn't been reduced to 0 by the + * reaper), discard any candidate we may have allocated, and try to get + * a channel on this one, otherwise we have to replace it. + */ +found_extant_conn: + _debug("found conn"); + if (!rxrpc_get_connection_maybe(conn)) { + set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); + rb_replace_node(&conn->client_node, + &candidate->client_node, + &local->client_conns); + clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags); + goto attached; + } + + spin_unlock(&local->client_conns_lock); + + rxrpc_put_connection(candidate); + + if (!atomic_add_unless(&conn->avail_chans, -1, 0)) { + if (!gfpflags_allow_blocking(gfp)) { + rxrpc_put_connection(conn); + _leave(" = -EAGAIN"); + return -EAGAIN; + } + + add_wait_queue(&conn->channel_wq, &myself); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (atomic_add_unless(&conn->avail_chans, -1, 0)) + break; + if (signal_pending(current)) + goto interrupted; + schedule(); + } + remove_wait_queue(&conn->channel_wq, &myself); + __set_current_state(TASK_RUNNING); + } + + /* The connection allegedly now has a free channel and we can now + * attach the call to it. + */ + spin_lock(&conn->channel_lock); + + for (chan = 0; chan < RXRPC_MAXCALLS; chan++) + if (!conn->channels[chan].call) + goto found_channel; + BUG(); + +interrupted: + remove_wait_queue(&conn->channel_wq, &myself); + __set_current_state(TASK_RUNNING); + rxrpc_put_connection(conn); + rxrpc_put_peer(cp->peer); + cp->peer = NULL; + _leave(" = -ERESTARTSYS"); + return -ERESTARTSYS; +} + +/* + * Remove a client connection from the local endpoint's tree, thereby removing + * it as a target for reuse for new client calls. + */ +void rxrpc_unpublish_client_conn(struct rxrpc_connection *conn) +{ + struct rxrpc_local *local = conn->params.local; + + spin_lock(&local->client_conns_lock); + if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) + rb_erase(&conn->client_node, &local->client_conns); + spin_unlock(&local->client_conns_lock); + + rxrpc_put_client_connection_id(conn); +} diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/conn_event.c index 5f9563968a5b..cee0f35bc1cf 100644 --- a/net/rxrpc/ar-connevent.c +++ b/net/rxrpc/conn_event.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> @@ -29,15 +31,17 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state, u32 abort_code) { struct rxrpc_call *call; - struct rb_node *p; + int i; _enter("{%d},%x", conn->debug_id, abort_code); - read_lock_bh(&conn->lock); + spin_lock(&conn->channel_lock); - for (p = rb_first(&conn->calls); p; p = rb_next(p)) { - call = rb_entry(p, struct rxrpc_call, conn_node); - write_lock(&call->state_lock); + for (i = 0; i < RXRPC_MAXCALLS; i++) { + call = rcu_dereference_protected( + conn->channels[i].call, + lockdep_is_held(&conn->channel_lock)); + write_lock_bh(&call->state_lock); if (call->state <= RXRPC_CALL_COMPLETE) { call->state = state; if (state == RXRPC_CALL_LOCALLY_ABORTED) { @@ -49,10 +53,10 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state, } rxrpc_queue_call(call); } - write_unlock(&call->state_lock); + write_unlock_bh(&call->state_lock); } - read_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); _leave(""); } @@ -86,14 +90,14 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code); - msg.msg_name = &conn->trans->peer->srx.transport; - msg.msg_namelen = conn->trans->peer->srx.transport_len; + msg.msg_name = &conn->params.peer->srx.transport; + msg.msg_namelen = conn->params.peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; - whdr.epoch = htonl(conn->epoch); - whdr.cid = htonl(conn->cid); + whdr.epoch = htonl(conn->proto.epoch); + whdr.cid = htonl(conn->proto.cid); whdr.callNumber = 0; whdr.seq = 0; whdr.type = RXRPC_PACKET_TYPE_ABORT; @@ -101,7 +105,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr.userStatus = 0; whdr.securityIndex = conn->security_ix; whdr._rsvd = 0; - whdr.serviceId = htons(conn->service_id); + whdr.serviceId = htons(conn->params.service_id); word = htonl(conn->local_abort); @@ -116,7 +120,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr.serial = htonl(serial); _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort); - ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { _debug("sendmsg failed: %d", ret); return -EAGAIN; @@ -186,18 +190,24 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - conn->security->prime_packet_security(conn); - read_lock_bh(&conn->lock); + ret = conn->security->prime_packet_security(conn); + if (ret < 0) + return ret; + + spin_lock(&conn->channel_lock); spin_lock(&conn->state_lock); - if (conn->state == RXRPC_CONN_SERVER_CHALLENGING) { - conn->state = RXRPC_CONN_SERVER; + if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { + conn->state = RXRPC_CONN_SERVICE; for (loop = 0; loop < RXRPC_MAXCALLS; loop++) - rxrpc_call_is_secure(conn->channels[loop]); + rxrpc_call_is_secure( + rcu_dereference_protected( + conn->channels[loop].call, + lockdep_is_held(&conn->channel_lock))); } spin_unlock(&conn->state_lock); - read_unlock_bh(&conn->lock); + spin_unlock(&conn->channel_lock); return 0; default: @@ -218,7 +228,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) ASSERT(conn->security_ix != 0); - if (!conn->key) { + if (!conn->params.key) { _debug("set up security"); ret = rxrpc_init_server_conn_security(conn); switch (ret) { @@ -261,12 +271,8 @@ void rxrpc_process_connection(struct work_struct *work) _enter("{%d}", conn->debug_id); - atomic_inc(&conn->usage); - - if (test_and_clear_bit(RXRPC_CONN_CHALLENGE, &conn->events)) { + if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) rxrpc_secure_connection(conn); - rxrpc_put_connection(conn); - } /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ @@ -281,7 +287,6 @@ void rxrpc_process_connection(struct work_struct *work) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_put_connection(conn); rxrpc_free_skb(skb); break; } @@ -299,7 +304,6 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, -ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_put_connection(conn); rxrpc_free_skb(skb); _leave(" [EPROTO]"); goto out; @@ -312,19 +316,14 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { CHECK_SLAB_OKAY(&local->usage); - if (!atomic_inc_not_zero(&local->usage)) { - printk("resurrected on reject\n"); - BUG(); - } - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_work(&local->rejecter); + rxrpc_queue_local(local); } /* * reject packets through the local endpoint */ -void rxrpc_reject_packets(struct work_struct *work) +void rxrpc_reject_packets(struct rxrpc_local *local) { union { struct sockaddr sa; @@ -332,16 +331,12 @@ void rxrpc_reject_packets(struct work_struct *work) } sa; struct rxrpc_skb_priv *sp; struct rxrpc_wire_header whdr; - struct rxrpc_local *local; struct sk_buff *skb; struct msghdr msg; struct kvec iov[2]; size_t size; __be32 code; - local = container_of(work, struct rxrpc_local, rejecter); - rxrpc_get_local(local); - _enter("%d", local->debug_id); iov[0].iov_base = &whdr; @@ -393,9 +388,7 @@ void rxrpc_reject_packets(struct work_struct *work) } rxrpc_free_skb(skb); - rxrpc_put_local(local); } - rxrpc_put_local(local); _leave(""); } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c new file mode 100644 index 000000000000..896d84493a05 --- /dev/null +++ b/net/rxrpc/conn_object.c @@ -0,0 +1,340 @@ +/* RxRPC virtual connection handler + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * Time till a connection expires after last use (in seconds). + */ +unsigned int rxrpc_connection_expiry = 10 * 60; + +static void rxrpc_connection_reaper(struct work_struct *work); + +LIST_HEAD(rxrpc_connections); +DEFINE_RWLOCK(rxrpc_connection_lock); +static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); + +/* + * allocate a new connection + */ +struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) +{ + struct rxrpc_connection *conn; + + _enter(""); + + conn = kzalloc(sizeof(struct rxrpc_connection), gfp); + if (conn) { + spin_lock_init(&conn->channel_lock); + init_waitqueue_head(&conn->channel_wq); + INIT_WORK(&conn->processor, &rxrpc_process_connection); + INIT_LIST_HEAD(&conn->link); + skb_queue_head_init(&conn->rx_queue); + conn->security = &rxrpc_no_security; + spin_lock_init(&conn->state_lock); + /* We maintain an extra ref on the connection whilst it is + * on the rxrpc_connections list. + */ + atomic_set(&conn->usage, 2); + conn->debug_id = atomic_inc_return(&rxrpc_debug_id); + atomic_set(&conn->avail_chans, RXRPC_MAXCALLS); + conn->size_align = 4; + conn->header_size = sizeof(struct rxrpc_wire_header); + } + + _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); + return conn; +} + +/* + * Look up a connection in the cache by protocol parameters. + * + * If successful, a pointer to the connection is returned, but no ref is taken. + * NULL is returned if there is no match. + * + * The caller must be holding the RCU read lock. + */ +struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, + struct sk_buff *skb) +{ + struct rxrpc_connection *conn; + struct rxrpc_conn_proto k; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sockaddr_rxrpc srx; + struct rxrpc_peer *peer; + + _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); + + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) + goto not_found; + + k.epoch = sp->hdr.epoch; + k.cid = sp->hdr.cid & RXRPC_CIDMASK; + + /* We may have to handle mixing IPv4 and IPv6 */ + if (srx.transport.family != local->srx.transport.family) { + pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", + srx.transport.family, + local->srx.transport.family); + goto not_found; + } + + k.epoch = sp->hdr.epoch; + k.cid = sp->hdr.cid & RXRPC_CIDMASK; + + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) { + /* We need to look up service connections by the full protocol + * parameter set. We look up the peer first as an intermediate + * step and then the connection from the peer's tree. + */ + peer = rxrpc_lookup_peer_rcu(local, &srx); + if (!peer) + goto not_found; + conn = rxrpc_find_service_conn_rcu(peer, skb); + if (!conn || atomic_read(&conn->usage) == 0) + goto not_found; + _leave(" = %p", conn); + return conn; + } else { + /* Look up client connections by connection ID alone as their + * IDs are unique for this machine. + */ + conn = idr_find(&rxrpc_client_conn_ids, + sp->hdr.cid >> RXRPC_CIDSHIFT); + if (!conn || atomic_read(&conn->usage) == 0) { + _debug("no conn"); + goto not_found; + } + + if (conn->proto.epoch != k.epoch || + conn->params.local != local) + goto not_found; + + peer = conn->params.peer; + switch (srx.transport.family) { + case AF_INET: + if (peer->srx.transport.sin.sin_port != + srx.transport.sin.sin_port || + peer->srx.transport.sin.sin_addr.s_addr != + srx.transport.sin.sin_addr.s_addr) + goto not_found; + break; + default: + BUG(); + } + + _leave(" = %p", conn); + return conn; + } + +not_found: + _leave(" = NULL"); + return NULL; +} + +/* + * Disconnect a call and clear any channel it occupies when that call + * terminates. The caller must hold the channel_lock and must release the + * call's ref on the connection. + */ +void __rxrpc_disconnect_call(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = call->conn; + struct rxrpc_channel *chan = &conn->channels[call->channel]; + + _enter("%d,%d", conn->debug_id, call->channel); + + if (rcu_access_pointer(chan->call) == call) { + /* Save the result of the call so that we can repeat it if necessary + * through the channel, whilst disposing of the actual call record. + */ + chan->last_result = call->local_abort; + smp_wmb(); + chan->last_call = chan->call_id; + chan->call_id = chan->call_counter; + + rcu_assign_pointer(chan->call, NULL); + atomic_inc(&conn->avail_chans); + wake_up(&conn->channel_wq); + } + + _leave(""); +} + +/* + * Disconnect a call and clear any channel it occupies when that call + * terminates. + */ +void rxrpc_disconnect_call(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = call->conn; + + spin_lock(&conn->channel_lock); + __rxrpc_disconnect_call(call); + spin_unlock(&conn->channel_lock); + + call->conn = NULL; + rxrpc_put_connection(conn); +} + +/* + * release a virtual connection + */ +void rxrpc_put_connection(struct rxrpc_connection *conn) +{ + if (!conn) + return; + + _enter("%p{u=%d,d=%d}", + conn, atomic_read(&conn->usage), conn->debug_id); + + ASSERTCMP(atomic_read(&conn->usage), >, 1); + + conn->put_time = ktime_get_seconds(); + if (atomic_dec_return(&conn->usage) == 1) { + _debug("zombie"); + rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); + } + + _leave(""); +} + +/* + * destroy a virtual connection + */ +static void rxrpc_destroy_connection(struct rcu_head *rcu) +{ + struct rxrpc_connection *conn = + container_of(rcu, struct rxrpc_connection, rcu); + + _enter("{%d,u=%d}", conn->debug_id, atomic_read(&conn->usage)); + + ASSERTCMP(atomic_read(&conn->usage), ==, 0); + + _net("DESTROY CONN %d", conn->debug_id); + + rxrpc_purge_queue(&conn->rx_queue); + + conn->security->clear(conn); + key_put(conn->params.key); + key_put(conn->server_key); + rxrpc_put_peer(conn->params.peer); + rxrpc_put_local(conn->params.local); + + kfree(conn); + _leave(""); +} + +/* + * reap dead connections + */ +static void rxrpc_connection_reaper(struct work_struct *work) +{ + struct rxrpc_connection *conn, *_p; + unsigned long reap_older_than, earliest, put_time, now; + + LIST_HEAD(graveyard); + + _enter(""); + + now = ktime_get_seconds(); + reap_older_than = now - rxrpc_connection_expiry; + earliest = ULONG_MAX; + + write_lock(&rxrpc_connection_lock); + list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { + ASSERTCMP(atomic_read(&conn->usage), >, 0); + if (likely(atomic_read(&conn->usage) > 1)) + continue; + + put_time = READ_ONCE(conn->put_time); + if (time_after(put_time, reap_older_than)) { + if (time_before(put_time, earliest)) + earliest = put_time; + continue; + } + + /* The usage count sits at 1 whilst the object is unused on the + * list; we reduce that to 0 to make the object unavailable. + */ + if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) + continue; + + if (rxrpc_conn_is_client(conn)) + rxrpc_unpublish_client_conn(conn); + else + rxrpc_unpublish_service_conn(conn); + + list_move_tail(&conn->link, &graveyard); + } + write_unlock(&rxrpc_connection_lock); + + if (earliest != ULONG_MAX) { + _debug("reschedule reaper %ld", (long) earliest - now); + ASSERTCMP(earliest, >, now); + rxrpc_queue_delayed_work(&rxrpc_connection_reap, + (earliest - now) * HZ); + } + + while (!list_empty(&graveyard)) { + conn = list_entry(graveyard.next, struct rxrpc_connection, + link); + list_del_init(&conn->link); + + ASSERTCMP(atomic_read(&conn->usage), ==, 0); + skb_queue_purge(&conn->rx_queue); + call_rcu(&conn->rcu, rxrpc_destroy_connection); + } + + _leave(""); +} + +/* + * preemptively destroy all the connection records rather than waiting for them + * to time out + */ +void __exit rxrpc_destroy_all_connections(void) +{ + struct rxrpc_connection *conn, *_p; + bool leak = false; + + _enter(""); + + rxrpc_connection_expiry = 0; + cancel_delayed_work(&rxrpc_connection_reap); + rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); + flush_workqueue(rxrpc_workqueue); + + write_lock(&rxrpc_connection_lock); + list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { + pr_err("AF_RXRPC: Leaked conn %p {%d}\n", + conn, atomic_read(&conn->usage)); + leak = true; + } + write_unlock(&rxrpc_connection_lock); + BUG_ON(leak); + + /* Make sure the local and peer records pinned by any dying connections + * are released. + */ + rcu_barrier(); + rxrpc_destroy_client_conn_ids(); + + _leave(""); +} diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c new file mode 100644 index 000000000000..fd9027ccba8f --- /dev/null +++ b/net/rxrpc/conn_service.c @@ -0,0 +1,230 @@ +/* Service connection management + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/slab.h> +#include "ar-internal.h" + +/* + * Find a service connection under RCU conditions. + * + * We could use a hash table, but that is subject to bucket stuffing by an + * attacker as the client gets to pick the epoch and cid values and would know + * the hash function. So, instead, we use a hash table for the peer and from + * that an rbtree to find the service connection. Under ordinary circumstances + * it might be slower than a large hash table, but it is at least limited in + * depth. + */ +struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, + struct sk_buff *skb) +{ + struct rxrpc_connection *conn = NULL; + struct rxrpc_conn_proto k; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rb_node *p; + unsigned int seq = 0; + + k.epoch = sp->hdr.epoch; + k.cid = sp->hdr.cid & RXRPC_CIDMASK; + + do { + /* Unfortunately, rbtree walking doesn't give reliable results + * under just the RCU read lock, so we have to check for + * changes. + */ + read_seqbegin_or_lock(&peer->service_conn_lock, &seq); + + p = rcu_dereference_raw(peer->service_conns.rb_node); + while (p) { + conn = rb_entry(p, struct rxrpc_connection, service_node); + + if (conn->proto.index_key < k.index_key) + p = rcu_dereference_raw(p->rb_left); + else if (conn->proto.index_key > k.index_key) + p = rcu_dereference_raw(p->rb_right); + else + goto done; + conn = NULL; + } + } while (need_seqretry(&peer->service_conn_lock, seq)); + +done: + done_seqretry(&peer->service_conn_lock, seq); + _leave(" = %d", conn ? conn->debug_id : -1); + return conn; +} + +/* + * Insert a service connection into a peer's tree, thereby making it a target + * for incoming packets. + */ +static struct rxrpc_connection * +rxrpc_publish_service_conn(struct rxrpc_peer *peer, + struct rxrpc_connection *conn) +{ + struct rxrpc_connection *cursor = NULL; + struct rxrpc_conn_proto k = conn->proto; + struct rb_node **pp, *parent; + + write_seqlock_bh(&peer->service_conn_lock); + + pp = &peer->service_conns.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + cursor = rb_entry(parent, + struct rxrpc_connection, service_node); + + if (cursor->proto.index_key < k.index_key) + pp = &(*pp)->rb_left; + else if (cursor->proto.index_key > k.index_key) + pp = &(*pp)->rb_right; + else + goto found_extant_conn; + } + + rb_link_node_rcu(&conn->service_node, parent, pp); + rb_insert_color(&conn->service_node, &peer->service_conns); +conn_published: + set_bit(RXRPC_CONN_IN_SERVICE_CONNS, &conn->flags); + write_sequnlock_bh(&peer->service_conn_lock); + _leave(" = %d [new]", conn->debug_id); + return conn; + +found_extant_conn: + if (atomic_read(&cursor->usage) == 0) + goto replace_old_connection; + write_sequnlock_bh(&peer->service_conn_lock); + /* We should not be able to get here. rxrpc_incoming_connection() is + * called in a non-reentrant context, so there can't be a race to + * insert a new connection. + */ + BUG(); + +replace_old_connection: + /* The old connection is from an outdated epoch. */ + _debug("replace conn"); + rb_replace_node_rcu(&cursor->service_node, + &conn->service_node, + &peer->service_conns); + clear_bit(RXRPC_CONN_IN_SERVICE_CONNS, &cursor->flags); + goto conn_published; +} + +/* + * get a record of an incoming connection + */ +struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, + struct sk_buff *skb) +{ + struct rxrpc_connection *conn; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_peer *peer; + const char *new = "old"; + + _enter(""); + + peer = rxrpc_lookup_peer(local, srx, GFP_NOIO); + if (!peer) { + _debug("no peer"); + return ERR_PTR(-EBUSY); + } + + ASSERT(sp->hdr.flags & RXRPC_CLIENT_INITIATED); + + rcu_read_lock(); + peer = rxrpc_lookup_peer_rcu(local, srx); + if (peer) { + conn = rxrpc_find_service_conn_rcu(peer, skb); + if (conn) { + if (sp->hdr.securityIndex != conn->security_ix) + goto security_mismatch_rcu; + if (rxrpc_get_connection_maybe(conn)) + goto found_extant_connection_rcu; + + /* The conn has expired but we can't remove it without + * the appropriate lock, so we attempt to replace it + * when we have a new candidate. + */ + } + + if (!rxrpc_get_peer_maybe(peer)) + peer = NULL; + } + rcu_read_unlock(); + + if (!peer) { + peer = rxrpc_lookup_peer(local, srx, GFP_NOIO); + if (!peer) + goto enomem; + } + + /* We don't have a matching record yet. */ + conn = rxrpc_alloc_connection(GFP_NOIO); + if (!conn) + goto enomem_peer; + + conn->proto.epoch = sp->hdr.epoch; + conn->proto.cid = sp->hdr.cid & RXRPC_CIDMASK; + conn->params.local = local; + conn->params.peer = peer; + conn->params.service_id = sp->hdr.serviceId; + conn->security_ix = sp->hdr.securityIndex; + conn->out_clientflag = 0; + conn->state = RXRPC_CONN_SERVICE; + if (conn->params.service_id) + conn->state = RXRPC_CONN_SERVICE_UNSECURED; + + rxrpc_get_local(local); + + write_lock(&rxrpc_connection_lock); + list_add_tail(&conn->link, &rxrpc_connections); + write_unlock(&rxrpc_connection_lock); + + /* Make the connection a target for incoming packets. */ + rxrpc_publish_service_conn(peer, conn); + + new = "new"; + +success: + _net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->proto.cid); + _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); + return conn; + +found_extant_connection_rcu: + rcu_read_unlock(); + goto success; + +security_mismatch_rcu: + rcu_read_unlock(); + _leave(" = -EKEYREJECTED"); + return ERR_PTR(-EKEYREJECTED); + +enomem_peer: + rxrpc_put_peer(peer); +enomem: + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); +} + +/* + * Remove the service connection from the peer's tree, thereby removing it as a + * target for incoming packets. + */ +void rxrpc_unpublish_service_conn(struct rxrpc_connection *conn) +{ + struct rxrpc_peer *peer = conn->params.peer; + + write_seqlock_bh(&peer->service_conn_lock); + if (test_and_clear_bit(RXRPC_CONN_IN_SERVICE_CONNS, &conn->flags)) + rb_erase(&conn->service_node, &peer->service_conns); + write_sequnlock_bh(&peer->service_conn_lock); +} diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/input.c index 6ff97412a0bb..991a20d25093 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/input.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> @@ -358,7 +360,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); - if (call->conn->out_clientflag) + if (rxrpc_conn_is_service(call->conn)) goto protocol_error; write_lock_bh(&call->state_lock); @@ -474,7 +476,7 @@ static void rxrpc_process_jumbo_packet(struct rxrpc_call *call, sp->hdr.seq += 1; sp->hdr.serial += 1; sp->hdr.flags = jhdr.flags; - sp->hdr._rsvd = jhdr._rsvd; + sp->hdr._rsvd = ntohs(jhdr._rsvd); _proto("Rx DATA Jumbo %%%u", sp->hdr.serial - 1); @@ -531,7 +533,7 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call, case RXRPC_CALL_COMPLETE: case RXRPC_CALL_CLIENT_FINAL_ACK: /* complete server call */ - if (call->conn->in_clientflag) + if (rxrpc_conn_is_service(call->conn)) goto dead_call; /* resend last packet of a completed call */ _debug("final ack again"); @@ -558,7 +560,7 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call, dead_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { skb->priority = RX_CALL_DEAD; - rxrpc_reject_packet(call->conn->trans->local, skb); + rxrpc_reject_packet(call->conn->params.local, skb); goto unlock; } free_unlock: @@ -573,14 +575,13 @@ done: * post connection-level events to the connection * - this includes challenges, responses and some aborts */ -static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, +static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, struct sk_buff *skb) { _enter("%p,%p", conn, skb); - atomic_inc(&conn->usage); skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn); + return rxrpc_queue_conn(conn); } /* @@ -592,9 +593,8 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb); - atomic_inc(&local->usage); skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_work(&local->event_processor); + rxrpc_queue_local(local); } /* @@ -626,42 +626,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) return 0; } -static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local, - struct sk_buff *skb, - struct rxrpc_skb_priv *sp) -{ - struct rxrpc_peer *peer; - struct rxrpc_transport *trans; - struct rxrpc_connection *conn; - - peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, - udp_hdr(skb)->source); - if (IS_ERR(peer)) - goto cant_find_conn; - - trans = rxrpc_find_transport(local, peer); - rxrpc_put_peer(peer); - if (!trans) - goto cant_find_conn; - - conn = rxrpc_find_connection(trans, &sp->hdr); - rxrpc_put_transport(trans); - if (!conn) - goto cant_find_conn; - - return conn; -cant_find_conn: - return NULL; -} - /* * handle data received on the local endpoint * - may be called in interrupt context + * + * The socket is locked by the caller and this prevents the socket from being + * shut down and the local endpoint from going away, thus sk_user_data will not + * be cleared until this function returns. */ void rxrpc_data_ready(struct sock *sk) { + struct rxrpc_connection *conn; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local; + struct rxrpc_local *local = sk->sk_user_data; struct sk_buff *skb; int ret; @@ -669,21 +646,8 @@ void rxrpc_data_ready(struct sock *sk) ASSERT(!irqs_disabled()); - read_lock_bh(&rxrpc_local_lock); - local = sk->sk_user_data; - if (local && atomic_read(&local->usage) > 0) - rxrpc_get_local(local); - else - local = NULL; - read_unlock_bh(&rxrpc_local_lock); - if (!local) { - _leave(" [local dead]"); - return; - } - skb = skb_recv_datagram(sk, 0, 1, &ret); if (!skb) { - rxrpc_put_local(local); if (ret == -EAGAIN) return; _debug("UDP socket error %d", ret); @@ -697,7 +661,6 @@ void rxrpc_data_ready(struct sock *sk) /* we'll probably need to checksum it (didn't call sock_recvmsg) */ if (skb_checksum_complete(skb)) { rxrpc_free_skb(skb); - rxrpc_put_local(local); __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0); _leave(" [CSUM failed]"); return; @@ -732,48 +695,49 @@ void rxrpc_data_ready(struct sock *sk) rxrpc_post_packet_to_local(local, skb); goto out; } - + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) goto bad_message; - if (sp->hdr.callNumber == 0) { - /* This is a connection-level packet. These should be - * fairly rare, so the extra overhead of looking them up the - * old-fashioned way doesn't really hurt */ - struct rxrpc_connection *conn; + rcu_read_lock(); - conn = rxrpc_conn_from_local(local, skb, sp); - if (!conn) - goto cant_route_call; +retry_find_conn: + conn = rxrpc_find_connection_rcu(local, skb); + if (!conn) + goto cant_route_call; + if (sp->hdr.callNumber == 0) { + /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); - rxrpc_post_packet_to_conn(conn, skb); - rxrpc_put_connection(conn); + if (!rxrpc_post_packet_to_conn(conn, skb)) + goto retry_find_conn; } else { - struct rxrpc_call *call; + /* Call-bound packets are routed by connection channel. */ + unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; + struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_call *call = rcu_dereference(chan->call); - call = rxrpc_find_call_hash(&sp->hdr, local, - AF_INET, &ip_hdr(skb)->saddr); - if (call) - rxrpc_post_packet_to_call(call, skb); - else + if (!call || atomic_read(&call->usage) == 0) goto cant_route_call; + + rxrpc_post_packet_to_call(call, skb); } + rcu_read_unlock(); out: - rxrpc_put_local(local); return; cant_route_call: + rcu_read_unlock(); + _debug("can't route call"); if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && sp->hdr.type == RXRPC_PACKET_TYPE_DATA) { if (sp->hdr.seq == 1) { _debug("first packet"); skb_queue_tail(&local->accept_queue, skb); - rxrpc_queue_work(&local->acceptor); - rxrpc_put_local(local); + rxrpc_queue_work(&local->processor); _leave(" [incoming]"); return; } @@ -786,13 +750,11 @@ cant_route_call: _debug("reject type %d",sp->hdr.type); rxrpc_reject_packet(local, skb); } - rxrpc_put_local(local); _leave(" [no call]"); return; bad_message: skb->priority = RX_PROTOCOL_ERROR; rxrpc_reject_packet(local, skb); - rxrpc_put_local(local); _leave(" [badmsg]"); } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index e571403613c1..c21ad213b337 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -17,11 +17,12 @@ static int none_init_connection_security(struct rxrpc_connection *conn) return 0; } -static void none_prime_packet_security(struct rxrpc_connection *conn) +static int none_prime_packet_security(struct rxrpc_connection *conn) { + return 0; } -static int none_secure_packet(const struct rxrpc_call *call, +static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, size_t data_size, void *sechdr) @@ -29,7 +30,7 @@ static int none_secure_packet(const struct rxrpc_call *call, return 0; } -static int none_verify_packet(const struct rxrpc_call *call, +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, u32 *_abort_code) { diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/key.c index 1021b4c0bdd2..18c737a61d80 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/key.c @@ -12,6 +12,8 @@ * "afs@CAMBRIDGE.REDHAT.COM> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> @@ -800,7 +802,7 @@ static void rxrpc_free_token_list(struct rxrpc_key_token *token) rxrpc_rxk5_free(token->k5); break; default: - printk(KERN_ERR "Unknown token type %x on rxrpc key\n", + pr_err("Unknown token type %x on rxrpc key\n", token->security_index); BUG(); } @@ -985,7 +987,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn, if (ret < 0) goto error; - conn->key = key; + conn->params.key = key; _leave(" = 0 [%d]", key_serial(key)); return 0; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c new file mode 100644 index 000000000000..31a3f86ef2f6 --- /dev/null +++ b/net/rxrpc/local_event.c @@ -0,0 +1,116 @@ +/* AF_RXRPC local endpoint management + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/udp.h> +#include <linux/ip.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <generated/utsrelease.h> +#include "ar-internal.h" + +static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; + +/* + * Reply to a version request + */ +static void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_host_header *hdr, + struct sk_buff *skb) +{ + struct rxrpc_wire_header whdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sockaddr_in sin; + struct msghdr msg; + struct kvec iov[2]; + size_t len; + int ret; + + _enter(""); + + sin.sin_family = AF_INET; + sin.sin_port = udp_hdr(skb)->source; + sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + + msg.msg_name = &sin; + msg.msg_namelen = sizeof(sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.seq = 0; + whdr.serial = 0; + whdr.type = RXRPC_PACKET_TYPE_VERSION; + whdr.flags = RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED); + whdr.userStatus = 0; + whdr.securityIndex = 0; + whdr._rsvd = 0; + whdr.serviceId = htons(sp->hdr.serviceId); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = (char *)rxrpc_version_string; + iov[1].iov_len = sizeof(rxrpc_version_string); + + len = iov[0].iov_len + iov[1].iov_len; + + _proto("Tx VERSION (reply)"); + + ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); + if (ret < 0) + _debug("sendmsg failed: %d", ret); + + _leave(""); +} + +/* + * Process event packets targetted at a local endpoint. + */ +void rxrpc_process_local_events(struct rxrpc_local *local) +{ + struct sk_buff *skb; + char v; + + _enter(""); + + skb = skb_dequeue(&local->event_queue); + if (skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + _debug("{%d},{%u}", local->debug_id, sp->hdr.type); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_VERSION: + if (skb_copy_bits(skb, 0, &v, 1) < 0) + return; + _proto("Rx VERSION { %02x }", v); + if (v == 0) + rxrpc_send_version_request(local, &sp->hdr, skb); + break; + + default: + /* Just ignore anything we don't understand */ + break; + } + + rxrpc_free_skb(skb); + } + + _leave(""); +} diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c new file mode 100644 index 000000000000..a753796fbe8f --- /dev/null +++ b/net/rxrpc/local_object.c @@ -0,0 +1,390 @@ +/* Local endpoint object management + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/udp.h> +#include <linux/ip.h> +#include <linux/hashtable.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static void rxrpc_local_processor(struct work_struct *); +static void rxrpc_local_rcu(struct rcu_head *); + +static DEFINE_MUTEX(rxrpc_local_mutex); +static LIST_HEAD(rxrpc_local_endpoints); + +/* + * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, + * same or greater than. + * + * We explicitly don't compare the RxRPC service ID as we want to reject + * conflicting uses by differing services. Further, we don't want to share + * addresses with different options (IPv6), so we don't compare those bits + * either. + */ +static long rxrpc_local_cmp_key(const struct rxrpc_local *local, + const struct sockaddr_rxrpc *srx) +{ + long diff; + + diff = ((local->srx.transport_type - srx->transport_type) ?: + (local->srx.transport_len - srx->transport_len) ?: + (local->srx.transport.family - srx->transport.family)); + if (diff != 0) + return diff; + + switch (srx->transport.family) { + case AF_INET: + /* If the choice of UDP port is left up to the transport, then + * the endpoint record doesn't match. + */ + return ((u16 __force)local->srx.transport.sin.sin_port - + (u16 __force)srx->transport.sin.sin_port) ?: + memcmp(&local->srx.transport.sin.sin_addr, + &srx->transport.sin.sin_addr, + sizeof(struct in_addr)); + default: + BUG(); + } +} + +/* + * Allocate a new local endpoint. + */ +static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx) +{ + struct rxrpc_local *local; + + local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); + if (local) { + atomic_set(&local->usage, 1); + INIT_LIST_HEAD(&local->link); + INIT_WORK(&local->processor, rxrpc_local_processor); + INIT_LIST_HEAD(&local->services); + init_rwsem(&local->defrag_sem); + skb_queue_head_init(&local->accept_queue); + skb_queue_head_init(&local->reject_queue); + skb_queue_head_init(&local->event_queue); + local->client_conns = RB_ROOT; + spin_lock_init(&local->client_conns_lock); + spin_lock_init(&local->lock); + rwlock_init(&local->services_lock); + local->debug_id = atomic_inc_return(&rxrpc_debug_id); + memcpy(&local->srx, srx, sizeof(*srx)); + } + + _leave(" = %p", local); + return local; +} + +/* + * create the local socket + * - must be called with rxrpc_local_mutex locked + */ +static int rxrpc_open_socket(struct rxrpc_local *local) +{ + struct sock *sock; + int ret, opt; + + _enter("%p{%d}", local, local->srx.transport_type); + + /* create a socket to represent the local endpoint */ + ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type, + IPPROTO_UDP, &local->socket); + if (ret < 0) { + _leave(" = %d [socket]", ret); + return ret; + } + + /* if a local address was supplied then bind it */ + if (local->srx.transport_len > sizeof(sa_family_t)) { + _debug("bind"); + ret = kernel_bind(local->socket, + (struct sockaddr *)&local->srx.transport, + local->srx.transport_len); + if (ret < 0) { + _debug("bind failed %d", ret); + goto error; + } + } + + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + /* we want to set the don't fragment bit */ + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + /* set the socket up */ + sock = local->socket->sk; + sock->sk_user_data = local; + sock->sk_data_ready = rxrpc_data_ready; + sock->sk_error_report = rxrpc_error_report; + _leave(" = 0"); + return 0; + +error: + kernel_sock_shutdown(local->socket, SHUT_RDWR); + local->socket->sk->sk_user_data = NULL; + sock_release(local->socket); + local->socket = NULL; + + _leave(" = %d", ret); + return ret; +} + +/* + * Look up or create a new local endpoint using the specified local address. + */ +struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) +{ + struct rxrpc_local *local; + struct list_head *cursor; + const char *age; + long diff; + int ret; + + if (srx->transport.family == AF_INET) { + _enter("{%d,%u,%pI4+%hu}", + srx->transport_type, + srx->transport.family, + &srx->transport.sin.sin_addr, + ntohs(srx->transport.sin.sin_port)); + } else { + _enter("{%d,%u}", + srx->transport_type, + srx->transport.family); + return ERR_PTR(-EAFNOSUPPORT); + } + + mutex_lock(&rxrpc_local_mutex); + + for (cursor = rxrpc_local_endpoints.next; + cursor != &rxrpc_local_endpoints; + cursor = cursor->next) { + local = list_entry(cursor, struct rxrpc_local, link); + + diff = rxrpc_local_cmp_key(local, srx); + if (diff < 0) + continue; + if (diff > 0) + break; + + /* Services aren't allowed to share transport sockets, so + * reject that here. It is possible that the object is dying - + * but it may also still have the local transport address that + * we want bound. + */ + if (srx->srx_service) { + local = NULL; + goto addr_in_use; + } + + /* Found a match. We replace a dying object. Attempting to + * bind the transport socket may still fail if we're attempting + * to use a local address that the dying object is still using. + */ + if (!rxrpc_get_local_maybe(local)) { + cursor = cursor->next; + list_del_init(&local->link); + break; + } + + age = "old"; + goto found; + } + + local = rxrpc_alloc_local(srx); + if (!local) + goto nomem; + + ret = rxrpc_open_socket(local); + if (ret < 0) + goto sock_error; + + list_add_tail(&local->link, cursor); + age = "new"; + +found: + mutex_unlock(&rxrpc_local_mutex); + + _net("LOCAL %s %d {%d,%u,%pI4+%hu}", + age, + local->debug_id, + local->srx.transport_type, + local->srx.transport.family, + &local->srx.transport.sin.sin_addr, + ntohs(local->srx.transport.sin.sin_port)); + + _leave(" = %p", local); + return local; + +nomem: + ret = -ENOMEM; +sock_error: + mutex_unlock(&rxrpc_local_mutex); + kfree(local); + _leave(" = %d", ret); + return ERR_PTR(ret); + +addr_in_use: + mutex_unlock(&rxrpc_local_mutex); + _leave(" = -EADDRINUSE"); + return ERR_PTR(-EADDRINUSE); +} + +/* + * A local endpoint reached its end of life. + */ +void __rxrpc_put_local(struct rxrpc_local *local) +{ + _enter("%d", local->debug_id); + rxrpc_queue_work(&local->processor); +} + +/* + * Destroy a local endpoint's socket and then hand the record to RCU to dispose + * of. + * + * Closing the socket cannot be done from bottom half context or RCU callback + * context because it might sleep. + */ +static void rxrpc_local_destroyer(struct rxrpc_local *local) +{ + struct socket *socket = local->socket; + + _enter("%d", local->debug_id); + + /* We can get a race between an incoming call packet queueing the + * processor again and the work processor starting the destruction + * process which will shut down the UDP socket. + */ + if (local->dead) { + _leave(" [already dead]"); + return; + } + local->dead = true; + + mutex_lock(&rxrpc_local_mutex); + list_del_init(&local->link); + mutex_unlock(&rxrpc_local_mutex); + + ASSERT(RB_EMPTY_ROOT(&local->client_conns)); + ASSERT(list_empty(&local->services)); + + if (socket) { + local->socket = NULL; + kernel_sock_shutdown(socket, SHUT_RDWR); + socket->sk->sk_user_data = NULL; + sock_release(socket); + } + + /* At this point, there should be no more packets coming in to the + * local endpoint. + */ + rxrpc_purge_queue(&local->accept_queue); + rxrpc_purge_queue(&local->reject_queue); + rxrpc_purge_queue(&local->event_queue); + + _debug("rcu local %d", local->debug_id); + call_rcu(&local->rcu, rxrpc_local_rcu); +} + +/* + * Process events on an endpoint + */ +static void rxrpc_local_processor(struct work_struct *work) +{ + struct rxrpc_local *local = + container_of(work, struct rxrpc_local, processor); + bool again; + + _enter("%d", local->debug_id); + + do { + again = false; + if (atomic_read(&local->usage) == 0) + return rxrpc_local_destroyer(local); + + if (!skb_queue_empty(&local->accept_queue)) { + rxrpc_accept_incoming_calls(local); + again = true; + } + + if (!skb_queue_empty(&local->reject_queue)) { + rxrpc_reject_packets(local); + again = true; + } + + if (!skb_queue_empty(&local->event_queue)) { + rxrpc_process_local_events(local); + again = true; + } + } while (again); +} + +/* + * Destroy a local endpoint after the RCU grace period expires. + */ +static void rxrpc_local_rcu(struct rcu_head *rcu) +{ + struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu); + + _enter("%d", local->debug_id); + + ASSERT(!work_pending(&local->processor)); + + _net("DESTROY LOCAL %d", local->debug_id); + kfree(local); + _leave(""); +} + +/* + * Verify the local endpoint list is empty by this point. + */ +void __exit rxrpc_destroy_all_locals(void) +{ + struct rxrpc_local *local; + + _enter(""); + + flush_workqueue(rxrpc_workqueue); + + if (!list_empty(&rxrpc_local_endpoints)) { + mutex_lock(&rxrpc_local_mutex); + list_for_each_entry(local, &rxrpc_local_endpoints, link) { + pr_err("AF_RXRPC: Leaked local %p {%d}\n", + local, atomic_read(&local->usage)); + } + mutex_unlock(&rxrpc_local_mutex); + BUG(); + } + + rcu_barrier(); +} diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 1afe9876e79f..bdc5e42fe600 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -15,6 +15,12 @@ #include "ar-internal.h" /* + * The maximum listening backlog queue size that may be set on a socket by + * listen(). + */ +unsigned int rxrpc_max_backlog __read_mostly = 10; + +/* * How long to wait before scheduling ACK generation after seeing a * packet with RXRPC_REQUEST_ACK set (in jiffies). */ diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/output.c index 51cb10062a8d..f4bda06b7d2d 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/output.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/net.h> #include <linux/gfp.h> #include <linux/skbuff.h> @@ -30,13 +32,14 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* * extract control messages from the sendmsg() control buffer */ -static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, +static int rxrpc_sendmsg_cmsg(struct msghdr *msg, unsigned long *user_call_ID, enum rxrpc_command *command, u32 *abort_code, - bool server) + bool *_exclusive) { struct cmsghdr *cmsg; + bool got_user_ID = false; int len; *command = RXRPC_CMD_SEND_DATA; @@ -68,6 +71,7 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, CMSG_DATA(cmsg); } _debug("User Call ID %lx", *user_call_ID); + got_user_ID = true; break; case RXRPC_ABORT: @@ -88,15 +92,20 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, *command = RXRPC_CMD_ACCEPT; if (len != 0) return -EINVAL; - if (!server) - return -EISCONN; break; + case RXRPC_EXCLUSIVE_CALL: + *_exclusive = true; + if (len != 0) + return -EINVAL; + break; default: return -EINVAL; } } + if (!got_user_ID) + return -EINVAL; _leave(" = 0"); return 0; } @@ -124,55 +133,78 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) } /* + * Create a new client call for sendmsg(). + */ +static struct rxrpc_call * +rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, + unsigned long user_call_ID, bool exclusive) +{ + struct rxrpc_conn_parameters cp; + struct rxrpc_call *call; + struct key *key; + + DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name); + + _enter(""); + + if (!msg->msg_name) + return ERR_PTR(-EDESTADDRREQ); + + key = rx->key; + if (key && !rx->key->payload.data[0]) + key = NULL; + + memset(&cp, 0, sizeof(cp)); + cp.local = rx->local; + cp.key = rx->key; + cp.security_level = rx->min_sec_level; + cp.exclusive = rx->exclusive | exclusive; + cp.service_id = srx->srx_service; + call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL); + + _leave(" = %p\n", call); + return call; +} + +/* * send a message forming part of a client call through an RxRPC socket * - caller holds the socket locked * - the socket may be either a client socket or a server socket */ -int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans, - struct msghdr *msg, size_t len) +int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) { - struct rxrpc_conn_bundle *bundle; enum rxrpc_command cmd; struct rxrpc_call *call; unsigned long user_call_ID = 0; - struct key *key; - u16 service_id; + bool exclusive = false; u32 abort_code = 0; int ret; _enter(""); - ASSERT(trans != NULL); - - ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, - false); + ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code, + &exclusive); if (ret < 0) return ret; - bundle = NULL; - if (trans) { - service_id = rx->srx.srx_service; - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, - msg->msg_name); - service_id = srx->srx_service; - } - key = rx->key; - if (key && !rx->key->payload.data[0]) - key = NULL; - bundle = rxrpc_get_bundle(rx, trans, key, service_id, - GFP_KERNEL); - if (IS_ERR(bundle)) - return PTR_ERR(bundle); + if (cmd == RXRPC_CMD_ACCEPT) { + if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) + return -EINVAL; + call = rxrpc_accept_call(rx, user_call_ID); + if (IS_ERR(call)) + return PTR_ERR(call); + rxrpc_put_call(call); + return 0; } - call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, - abort_code == 0, GFP_KERNEL); - if (trans) - rxrpc_put_bundle(trans, bundle); - if (IS_ERR(call)) { - _leave(" = %ld", PTR_ERR(call)); - return PTR_ERR(call); + call = rxrpc_find_call_by_user_ID(rx, user_call_ID); + if (!call) { + if (cmd != RXRPC_CMD_SEND_DATA) + return -EBADSLT; + call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID, + exclusive); + if (IS_ERR(call)) + return PTR_ERR(call); } _debug("CALL %d USR %lx ST %d on CONN %p", @@ -180,14 +212,21 @@ int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans, if (call->state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ - ret = -ESHUTDOWN; + ret = -ECONNRESET; } else if (cmd == RXRPC_CMD_SEND_ABORT) { rxrpc_send_abort(call, abort_code); + ret = 0; } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; - } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { + } else if (!call->in_clientflag && + call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { /* request phase complete for this client call */ ret = -EPROTO; + } else if (call->in_clientflag && + call->state != RXRPC_CALL_SERVER_ACK_REQUEST && + call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + /* Reply phase not begun or not complete for service call. */ + ret = -EPROTO; } else { ret = rxrpc_send_data(rx, call, msg, len); } @@ -266,70 +305,9 @@ void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code) EXPORT_SYMBOL(rxrpc_kernel_abort_call); /* - * send a message through a server socket - * - caller holds the socket locked - */ -int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) -{ - enum rxrpc_command cmd; - struct rxrpc_call *call; - unsigned long user_call_ID = 0; - u32 abort_code = 0; - int ret; - - _enter(""); - - ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, - true); - if (ret < 0) - return ret; - - if (cmd == RXRPC_CMD_ACCEPT) { - call = rxrpc_accept_call(rx, user_call_ID); - if (IS_ERR(call)) - return PTR_ERR(call); - rxrpc_put_call(call); - return 0; - } - - call = rxrpc_find_server_call(rx, user_call_ID); - if (!call) - return -EBADSLT; - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = -ESHUTDOWN; - goto out; - } - - switch (cmd) { - case RXRPC_CMD_SEND_DATA: - if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { - /* Tx phase not yet begun for this call */ - ret = -EPROTO; - break; - } - - ret = rxrpc_send_data(rx, call, msg, len); - break; - - case RXRPC_CMD_SEND_ABORT: - rxrpc_send_abort(call, abort_code); - break; - default: - BUG(); - } - - out: - rxrpc_put_call(call); - _leave(" = %d", ret); - return ret; -} - -/* * send a packet through the transport endpoint */ -int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb) +int rxrpc_send_data_packet(struct rxrpc_connection *conn, struct sk_buff *skb) { struct kvec iov[1]; struct msghdr msg; @@ -340,30 +318,30 @@ int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb) iov[0].iov_base = skb->head; iov[0].iov_len = skb->len; - msg.msg_name = &trans->peer->srx.transport.sin; - msg.msg_namelen = sizeof(trans->peer->srx.transport.sin); + msg.msg_name = &conn->params.peer->srx.transport; + msg.msg_namelen = conn->params.peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (skb->len - sizeof(struct rxrpc_wire_header) < trans->peer->maxdata) { - down_read(&trans->local->defrag_sem); + if (skb->len - sizeof(struct rxrpc_wire_header) < conn->params.peer->maxdata) { + down_read(&conn->params.local->defrag_sem); /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface * - in which case, we'll have processed the ICMP error * message and update the peer record */ - ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1, + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, iov[0].iov_len); - up_read(&trans->local->defrag_sem); + up_read(&conn->params.local->defrag_sem); if (ret == -EMSGSIZE) goto send_fragmentable; - _leave(" = %d [%u]", ret, trans->peer->maxdata); + _leave(" = %d [%u]", ret, conn->params.peer->maxdata); return ret; } @@ -371,21 +349,28 @@ send_fragmentable: /* attempt to send this message with fragmentation enabled */ _debug("send fragment"); - down_write(&trans->local->defrag_sem); - opt = IP_PMTUDISC_DONT; - ret = kernel_setsockopt(trans->local->socket, SOL_IP, IP_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1, - iov[0].iov_len); - - opt = IP_PMTUDISC_DO; - kernel_setsockopt(trans->local->socket, SOL_IP, - IP_MTU_DISCOVER, (char *) &opt, sizeof(opt)); + down_write(&conn->params.local->defrag_sem); + + switch (conn->params.local->srx.transport.family) { + case AF_INET: + opt = IP_PMTUDISC_DONT; + ret = kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + if (ret == 0) { + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, + iov[0].iov_len); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, SOL_IP, + IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + } + break; } - up_write(&trans->local->defrag_sem); - _leave(" = %d [frag %u]", ret, trans->peer->maxdata); + up_write(&conn->params.local->defrag_sem); + _leave(" = %d [frag %u]", ret, conn->params.peer->maxdata); return ret; } @@ -497,7 +482,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, if (try_to_del_timer_sync(&call->ack_timer) >= 0) { /* the packet may be freed by rxrpc_process_call() before this * returns */ - ret = rxrpc_send_packet(call->conn->trans, skb); + ret = rxrpc_send_data_packet(call->conn, skb); _net("sent skb %p", skb); } else { _debug("failed to delete ACK timer"); @@ -583,7 +568,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, goto maybe_error; } - max = call->conn->trans->peer->maxdata; + max = call->conn->params.peer->maxdata; max -= call->conn->security_size; max &= ~(call->conn->size_align - 1UL); @@ -674,7 +659,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, seq = atomic_inc_return(&call->sequence); - sp->hdr.epoch = conn->epoch; + sp->hdr.epoch = conn->proto.epoch; sp->hdr.cid = call->cid; sp->hdr.callNumber = call->call_id; sp->hdr.seq = seq; @@ -717,7 +702,9 @@ out: call_aborted: rxrpc_free_skb(skb); if (call->state == RXRPC_CALL_NETWORK_ERROR) - ret = call->conn->trans->peer->net_error; + ret = call->error_report < RXRPC_LOCAL_ERROR_OFFSET ? + call->error_report : + call->error_report - RXRPC_LOCAL_ERROR_OFFSET; else ret = -ECONNABORTED; _leave(" = %d", ret); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c new file mode 100644 index 000000000000..8940674b5e08 --- /dev/null +++ b/net/rxrpc/peer_event.c @@ -0,0 +1,281 @@ +/* Peer event handling, typically ICMP messages. + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/errqueue.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/icmp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include "ar-internal.h" + +static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); + +/* + * Find the peer associated with an ICMP packet. + */ +static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, + const struct sk_buff *skb) +{ + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + struct sockaddr_rxrpc srx; + + _enter(""); + + memset(&srx, 0, sizeof(srx)); + srx.transport_type = local->srx.transport_type; + srx.transport.family = local->srx.transport.family; + + /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice + * versa? + */ + switch (srx.transport.family) { + case AF_INET: + srx.transport.sin.sin_port = serr->port; + srx.transport_len = sizeof(struct sockaddr_in); + switch (serr->ee.ee_origin) { + case SO_EE_ORIGIN_ICMP: + _net("Rx ICMP"); + memcpy(&srx.transport.sin.sin_addr, + skb_network_header(skb) + serr->addr_offset, + sizeof(struct in_addr)); + break; + case SO_EE_ORIGIN_ICMP6: + _net("Rx ICMP6 on v4 sock"); + memcpy(&srx.transport.sin.sin_addr, + skb_network_header(skb) + serr->addr_offset + 12, + sizeof(struct in_addr)); + break; + default: + memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr, + sizeof(struct in_addr)); + break; + } + break; + + default: + BUG(); + } + + return rxrpc_lookup_peer_rcu(local, &srx); +} + +/* + * Handle an MTU/fragmentation problem. + */ +static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr) +{ + u32 mtu = serr->ee.ee_info; + + _net("Rx ICMP Fragmentation Needed (%d)", mtu); + + /* wind down the local interface MTU */ + if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) { + peer->if_mtu = mtu; + _net("I/F MTU %u", mtu); + } + + if (mtu == 0) { + /* they didn't give us a size, estimate one */ + mtu = peer->if_mtu; + if (mtu > 1500) { + mtu >>= 1; + if (mtu < 1500) + mtu = 1500; + } else { + mtu -= 100; + if (mtu < peer->hdrsize) + mtu = peer->hdrsize + 4; + } + } + + if (mtu < peer->mtu) { + spin_lock_bh(&peer->lock); + peer->mtu = mtu; + peer->maxdata = peer->mtu - peer->hdrsize; + spin_unlock_bh(&peer->lock); + _net("Net MTU %u (maxdata %u)", + peer->mtu, peer->maxdata); + } +} + +/* + * Handle an error received on the local endpoint. + */ +void rxrpc_error_report(struct sock *sk) +{ + struct sock_exterr_skb *serr; + struct rxrpc_local *local = sk->sk_user_data; + struct rxrpc_peer *peer; + struct sk_buff *skb; + + _enter("%p{%d}", sk, local->debug_id); + + skb = sock_dequeue_err_skb(sk); + if (!skb) { + _leave("UDP socket errqueue empty"); + return; + } + serr = SKB_EXT_ERR(skb); + if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { + _leave("UDP empty message"); + kfree_skb(skb); + return; + } + + rxrpc_new_skb(skb); + + rcu_read_lock(); + peer = rxrpc_lookup_peer_icmp_rcu(local, skb); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + rcu_read_unlock(); + rxrpc_free_skb(skb); + _leave(" [no peer]"); + return; + } + + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && + serr->ee.ee_type == ICMP_DEST_UNREACH && + serr->ee.ee_code == ICMP_FRAG_NEEDED)) { + rxrpc_adjust_mtu(peer, serr); + rcu_read_unlock(); + rxrpc_free_skb(skb); + rxrpc_put_peer(peer); + _leave(" [MTU update]"); + return; + } + + rxrpc_store_error(peer, serr); + rcu_read_unlock(); + rxrpc_free_skb(skb); + + /* The ref we obtained is passed off to the work item */ + rxrpc_queue_work(&peer->error_distributor); + _leave(""); +} + +/* + * Map an error report to error codes on the peer record. + */ +static void rxrpc_store_error(struct rxrpc_peer *peer, + struct sock_exterr_skb *serr) +{ + struct sock_extended_err *ee; + int err; + + _enter(""); + + ee = &serr->ee; + + _net("Rx Error o=%d t=%d c=%d e=%d", + ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno); + + err = ee->ee_errno; + + switch (ee->ee_origin) { + case SO_EE_ORIGIN_ICMP: + switch (ee->ee_type) { + case ICMP_DEST_UNREACH: + switch (ee->ee_code) { + case ICMP_NET_UNREACH: + _net("Rx Received ICMP Network Unreachable"); + break; + case ICMP_HOST_UNREACH: + _net("Rx Received ICMP Host Unreachable"); + break; + case ICMP_PORT_UNREACH: + _net("Rx Received ICMP Port Unreachable"); + break; + case ICMP_NET_UNKNOWN: + _net("Rx Received ICMP Unknown Network"); + break; + case ICMP_HOST_UNKNOWN: + _net("Rx Received ICMP Unknown Host"); + break; + default: + _net("Rx Received ICMP DestUnreach code=%u", + ee->ee_code); + break; + } + break; + + case ICMP_TIME_EXCEEDED: + _net("Rx Received ICMP TTL Exceeded"); + break; + + default: + _proto("Rx Received ICMP error { type=%u code=%u }", + ee->ee_type, ee->ee_code); + break; + } + break; + + case SO_EE_ORIGIN_NONE: + case SO_EE_ORIGIN_LOCAL: + _proto("Rx Received local error { error=%d }", err); + err += RXRPC_LOCAL_ERROR_OFFSET; + break; + + case SO_EE_ORIGIN_ICMP6: + default: + _proto("Rx Received error report { orig=%u }", ee->ee_origin); + break; + } + + peer->error_report = err; +} + +/* + * Distribute an error that occurred on a peer + */ +void rxrpc_peer_error_distributor(struct work_struct *work) +{ + struct rxrpc_peer *peer = + container_of(work, struct rxrpc_peer, error_distributor); + struct rxrpc_call *call; + int error_report; + + _enter(""); + + error_report = READ_ONCE(peer->error_report); + + _debug("ISSUE ERROR %d", error_report); + + spin_lock_bh(&peer->lock); + + while (!hlist_empty(&peer->error_targets)) { + call = hlist_entry(peer->error_targets.first, + struct rxrpc_call, error_link); + hlist_del_init(&call->error_link); + + write_lock(&call->state_lock); + if (call->state != RXRPC_CALL_COMPLETE && + call->state < RXRPC_CALL_NETWORK_ERROR) { + call->error_report = error_report; + call->state = RXRPC_CALL_NETWORK_ERROR; + set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); + rxrpc_queue_call(call); + } + write_unlock(&call->state_lock); + } + + spin_unlock_bh(&peer->lock); + + rxrpc_put_peer(peer); + _leave(""); +} diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c new file mode 100644 index 000000000000..538e9831c699 --- /dev/null +++ b/net/rxrpc/peer_object.c @@ -0,0 +1,315 @@ +/* RxRPC remote transport endpoint record management + * + * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/slab.h> +#include <linux/hashtable.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include <net/route.h> +#include "ar-internal.h" + +static DEFINE_HASHTABLE(rxrpc_peer_hash, 10); +static DEFINE_SPINLOCK(rxrpc_peer_hash_lock); + +/* + * Hash a peer key. + */ +static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local, + const struct sockaddr_rxrpc *srx) +{ + const u16 *p; + unsigned int i, size; + unsigned long hash_key; + + _enter(""); + + hash_key = (unsigned long)local / __alignof__(*local); + hash_key += srx->transport_type; + hash_key += srx->transport_len; + hash_key += srx->transport.family; + + switch (srx->transport.family) { + case AF_INET: + hash_key += (u16 __force)srx->transport.sin.sin_port; + size = sizeof(srx->transport.sin.sin_addr); + p = (u16 *)&srx->transport.sin.sin_addr; + break; + default: + WARN(1, "AF_RXRPC: Unsupported transport address family\n"); + return 0; + } + + /* Step through the peer address in 16-bit portions for speed */ + for (i = 0; i < size; i += sizeof(*p), p++) + hash_key += *p; + + _leave(" 0x%lx", hash_key); + return hash_key; +} + +/* + * Compare a peer to a key. Return -ve, 0 or +ve to indicate less than, same + * or greater than. + * + * Unfortunately, the primitives in linux/hashtable.h don't allow for sorted + * buckets and mid-bucket insertion, so we don't make full use of this + * information at this point. + */ +static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer, + struct rxrpc_local *local, + const struct sockaddr_rxrpc *srx, + unsigned long hash_key) +{ + long diff; + + diff = ((peer->hash_key - hash_key) ?: + ((unsigned long)peer->local - (unsigned long)local) ?: + (peer->srx.transport_type - srx->transport_type) ?: + (peer->srx.transport_len - srx->transport_len) ?: + (peer->srx.transport.family - srx->transport.family)); + if (diff != 0) + return diff; + + switch (srx->transport.family) { + case AF_INET: + return ((u16 __force)peer->srx.transport.sin.sin_port - + (u16 __force)srx->transport.sin.sin_port) ?: + memcmp(&peer->srx.transport.sin.sin_addr, + &srx->transport.sin.sin_addr, + sizeof(struct in_addr)); + default: + BUG(); + } +} + +/* + * Look up a remote transport endpoint for the specified address using RCU. + */ +static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( + struct rxrpc_local *local, + const struct sockaddr_rxrpc *srx, + unsigned long hash_key) +{ + struct rxrpc_peer *peer; + + hash_for_each_possible_rcu(rxrpc_peer_hash, peer, hash_link, hash_key) { + if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) { + if (atomic_read(&peer->usage) == 0) + return NULL; + return peer; + } + } + + return NULL; +} + +/* + * Look up a remote transport endpoint for the specified address using RCU. + */ +struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, + const struct sockaddr_rxrpc *srx) +{ + struct rxrpc_peer *peer; + unsigned long hash_key = rxrpc_peer_hash_key(local, srx); + + peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); + if (peer) { + switch (srx->transport.family) { + case AF_INET: + _net("PEER %d {%d,%u,%pI4+%hu}", + peer->debug_id, + peer->srx.transport_type, + peer->srx.transport.family, + &peer->srx.transport.sin.sin_addr, + ntohs(peer->srx.transport.sin.sin_port)); + break; + } + + _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + } + return peer; +} + +/* + * assess the MTU size for the network interface through which this peer is + * reached + */ +static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) +{ + struct rtable *rt; + struct flowi4 fl4; + + peer->if_mtu = 1500; + + rt = ip_route_output_ports(&init_net, &fl4, NULL, + peer->srx.transport.sin.sin_addr.s_addr, 0, + htons(7000), htons(7001), + IPPROTO_UDP, 0, 0); + if (IS_ERR(rt)) { + _leave(" [route err %ld]", PTR_ERR(rt)); + return; + } + + peer->if_mtu = dst_mtu(&rt->dst); + dst_release(&rt->dst); + + _leave(" [if_mtu %u]", peer->if_mtu); +} + +/* + * Allocate a peer. + */ +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) +{ + struct rxrpc_peer *peer; + + _enter(""); + + peer = kzalloc(sizeof(struct rxrpc_peer), gfp); + if (peer) { + atomic_set(&peer->usage, 1); + peer->local = local; + INIT_HLIST_HEAD(&peer->error_targets); + INIT_WORK(&peer->error_distributor, + &rxrpc_peer_error_distributor); + peer->service_conns = RB_ROOT; + seqlock_init(&peer->service_conn_lock); + spin_lock_init(&peer->lock); + peer->debug_id = atomic_inc_return(&rxrpc_debug_id); + } + + _leave(" = %p", peer); + return peer; +} + +/* + * Set up a new peer. + */ +static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, + unsigned long hash_key, + gfp_t gfp) +{ + struct rxrpc_peer *peer; + + _enter(""); + + peer = rxrpc_alloc_peer(local, gfp); + if (peer) { + peer->hash_key = hash_key; + memcpy(&peer->srx, srx, sizeof(*srx)); + + rxrpc_assess_MTU_size(peer); + peer->mtu = peer->if_mtu; + + if (srx->transport.family == AF_INET) { + peer->hdrsize = sizeof(struct iphdr); + switch (srx->transport_type) { + case SOCK_DGRAM: + peer->hdrsize += sizeof(struct udphdr); + break; + default: + BUG(); + break; + } + } else { + BUG(); + } + + peer->hdrsize += sizeof(struct rxrpc_wire_header); + peer->maxdata = peer->mtu - peer->hdrsize; + } + + _leave(" = %p", peer); + return peer; +} + +/* + * obtain a remote transport endpoint for the specified address + */ +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, gfp_t gfp) +{ + struct rxrpc_peer *peer, *candidate; + unsigned long hash_key = rxrpc_peer_hash_key(local, srx); + + _enter("{%d,%d,%pI4+%hu}", + srx->transport_type, + srx->transport_len, + &srx->transport.sin.sin_addr, + ntohs(srx->transport.sin.sin_port)); + + /* search the peer list first */ + rcu_read_lock(); + peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + rcu_read_unlock(); + + if (!peer) { + /* The peer is not yet present in hash - create a candidate + * for a new record and then redo the search. + */ + candidate = rxrpc_create_peer(local, srx, hash_key, gfp); + if (!candidate) { + _leave(" = NULL [nomem]"); + return NULL; + } + + spin_lock(&rxrpc_peer_hash_lock); + + /* Need to check that we aren't racing with someone else */ + peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) + hash_add_rcu(rxrpc_peer_hash, + &candidate->hash_link, hash_key); + + spin_unlock(&rxrpc_peer_hash_lock); + + if (peer) + kfree(candidate); + else + peer = candidate; + } + + _net("PEER %d {%d,%pI4+%hu}", + peer->debug_id, + peer->srx.transport_type, + &peer->srx.transport.sin.sin_addr, + ntohs(peer->srx.transport.sin.sin_port)); + + _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + return peer; +} + +/* + * Discard a ref on a remote peer record. + */ +void __rxrpc_put_peer(struct rxrpc_peer *peer) +{ + ASSERT(hlist_empty(&peer->error_targets)); + + spin_lock(&rxrpc_peer_hash_lock); + hash_del_rcu(&peer->hash_link); + spin_unlock(&rxrpc_peer_hash_lock); + + kfree_rcu(peer, rcu); +} diff --git a/net/rxrpc/ar-proc.c b/net/rxrpc/proc.c index 225163bc658d..ced5f07444e5 100644 --- a/net/rxrpc/ar-proc.c +++ b/net/rxrpc/proc.c @@ -14,15 +14,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -static const char *const rxrpc_conn_states[] = { - [RXRPC_CONN_UNUSED] = "Unused ", - [RXRPC_CONN_CLIENT] = "Client ", - [RXRPC_CONN_SERVER_UNSECURED] = "SvUnsec ", - [RXRPC_CONN_SERVER_CHALLENGING] = "SvChall ", - [RXRPC_CONN_SERVER] = "SvSecure", - [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", - [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", - [RXRPC_CONN_NETWORK_ERROR] = "NetError", +static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { + [RXRPC_CONN_UNUSED] = "Unused ", + [RXRPC_CONN_CLIENT] = "Client ", + [RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ", + [RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ", + [RXRPC_CONN_SERVICE] = "SvSecure", + [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", + [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CONN_NETWORK_ERROR] = "NetError", }; /* @@ -46,7 +46,7 @@ static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) static int rxrpc_call_seq_show(struct seq_file *seq, void *v) { - struct rxrpc_transport *trans; + struct rxrpc_connection *conn; struct rxrpc_call *call; char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; @@ -59,25 +59,28 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) } call = list_entry(v, struct rxrpc_call, link); - trans = call->conn->trans; sprintf(lbuff, "%pI4:%u", - &trans->local->srx.transport.sin.sin_addr, - ntohs(trans->local->srx.transport.sin.sin_port)); + &call->local->srx.transport.sin.sin_addr, + ntohs(call->local->srx.transport.sin.sin_port)); - sprintf(rbuff, "%pI4:%u", - &trans->peer->srx.transport.sin.sin_addr, - ntohs(trans->peer->srx.transport.sin.sin_port)); + conn = call->conn; + if (conn) + sprintf(rbuff, "%pI4:%u", + &conn->params.peer->srx.transport.sin.sin_addr, + ntohs(conn->params.peer->srx.transport.sin.sin_port)); + else + strcpy(rbuff, "no_connection"); seq_printf(seq, "UDP %-22.22s %-22.22s %4x %08x %08x %s %3u" " %-8.8s %08x %lx\n", lbuff, rbuff, - call->conn->service_id, + call->service_id, call->cid, call->call_id, - call->conn->in_clientflag ? "Svc" : "Clt", + call->in_clientflag ? "Svc" : "Clt", atomic_read(&call->usage), rxrpc_call_states[call->state], call->remote_abort ?: call->local_abort, @@ -129,41 +132,38 @@ static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) { struct rxrpc_connection *conn; - struct rxrpc_transport *trans; char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; if (v == &rxrpc_connections) { seq_puts(seq, "Proto Local Remote " - " SvID ConnID Calls End Use State Key " + " SvID ConnID End Use State Key " " Serial ISerial\n" ); return 0; } conn = list_entry(v, struct rxrpc_connection, link); - trans = conn->trans; sprintf(lbuff, "%pI4:%u", - &trans->local->srx.transport.sin.sin_addr, - ntohs(trans->local->srx.transport.sin.sin_port)); + &conn->params.local->srx.transport.sin.sin_addr, + ntohs(conn->params.local->srx.transport.sin.sin_port)); sprintf(rbuff, "%pI4:%u", - &trans->peer->srx.transport.sin.sin_addr, - ntohs(trans->peer->srx.transport.sin.sin_port)); + &conn->params.peer->srx.transport.sin.sin_addr, + ntohs(conn->params.peer->srx.transport.sin.sin_port)); seq_printf(seq, - "UDP %-22.22s %-22.22s %4x %08x %08x %s %3u" + "UDP %-22.22s %-22.22s %4x %08x %s %3u" " %s %08x %08x %08x\n", lbuff, rbuff, - conn->service_id, - conn->cid, - conn->call_counter, - conn->in_clientflag ? "Svc" : "Clt", + conn->params.service_id, + conn->proto.cid, + rxrpc_conn_is_service(conn) ? "Svc" : "Clt", atomic_read(&conn->usage), rxrpc_conn_states[conn->state], - key_serial(conn->key), + key_serial(conn->params.key), atomic_read(&conn->serial), atomic_read(&conn->hi_serial)); diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/recvmsg.c index 160f0927aa3e..a3fa2ed85d63 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/net.h> #include <linux/skbuff.h> #include <linux/export.h> @@ -145,9 +147,9 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (!continue_call) { if (msg->msg_name) { size_t len = - sizeof(call->conn->trans->peer->srx); + sizeof(call->conn->params.peer->srx); memcpy(msg->msg_name, - &call->conn->trans->peer->srx, len); + &call->conn->params.peer->srx, len); msg->msg_namelen = len; } sock_recv_timestamp(msg, &rx->sk, skb); @@ -203,7 +205,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* we transferred the whole data packet */ if (sp->hdr.flags & RXRPC_LAST_PACKET) { _debug("last"); - if (call->conn->out_clientflag) { + if (rxrpc_conn_is_client(call->conn)) { /* last byte of reply received */ ret = copied; goto terminal_message; @@ -307,7 +309,7 @@ receive_non_data_message: &abort_code); break; default: - pr_err("RxRPC: Unknown packet mark %u\n", skb->mark); + pr_err("Unknown packet mark %u\n", skb->mark); BUG(); break; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index bab56ed649ba..63afa9e9cc08 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> @@ -56,9 +58,9 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn) struct rxrpc_key_token *token; int ret; - _enter("{%d},{%x}", conn->debug_id, key_serial(conn->key)); + _enter("{%d},{%x}", conn->debug_id, key_serial(conn->params.key)); - token = conn->key->payload.data[0]; + token = conn->params.key->payload.data[0]; conn->security_ix = token->security_index; ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); @@ -72,7 +74,7 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn) sizeof(token->kad->session_key)) < 0) BUG(); - switch (conn->security_level) { + switch (conn->params.security_level) { case RXRPC_SECURITY_PLAIN: break; case RXRPC_SECURITY_AUTH: @@ -101,43 +103,43 @@ error: * prime the encryption state with the invariant parts of a connection's * description */ -static void rxkad_prime_packet_security(struct rxrpc_connection *conn) +static int rxkad_prime_packet_security(struct rxrpc_connection *conn) { struct rxrpc_key_token *token; SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); - struct scatterlist sg[2]; + struct scatterlist sg; struct rxrpc_crypt iv; - struct { - __be32 x[4]; - } tmpbuf __attribute__((aligned(16))); /* must all be in same page */ + __be32 *tmpbuf; + size_t tmpsize = 4 * sizeof(__be32); _enter(""); - if (!conn->key) - return; + if (!conn->params.key) + return 0; - token = conn->key->payload.data[0]; - memcpy(&iv, token->kad->session_key, sizeof(iv)); + tmpbuf = kmalloc(tmpsize, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; - tmpbuf.x[0] = htonl(conn->epoch); - tmpbuf.x[1] = htonl(conn->cid); - tmpbuf.x[2] = 0; - tmpbuf.x[3] = htonl(conn->security_ix); + token = conn->params.key->payload.data[0]; + memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf)); - sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf)); + tmpbuf[0] = htonl(conn->proto.epoch); + tmpbuf[1] = htonl(conn->proto.cid); + tmpbuf[2] = 0; + tmpbuf[3] = htonl(conn->security_ix); + sg_init_one(&sg, tmpbuf, tmpsize); skcipher_request_set_tfm(req, conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x); - + skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - memcpy(&conn->csum_iv, &tmpbuf.x[2], sizeof(conn->csum_iv)); - ASSERTCMP((u32 __force)conn->csum_iv.n[0], ==, (u32 __force)tmpbuf.x[2]); - - _leave(""); + memcpy(&conn->csum_iv, tmpbuf + 2, sizeof(conn->csum_iv)); + kfree(tmpbuf); + _leave(" = 0"); + return 0; } /* @@ -150,12 +152,9 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); + struct rxkad_level1_hdr hdr; struct rxrpc_crypt iv; - struct scatterlist sg[2]; - struct { - struct rxkad_level1_hdr hdr; - __be32 first; /* first four bytes of data and padding */ - } tmpbuf __attribute__((aligned(8))); /* must all be in same page */ + struct scatterlist sg; u16 check; sp = rxrpc_skb(skb); @@ -165,24 +164,19 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, check = sp->hdr.seq ^ sp->hdr.callNumber; data_size |= (u32)check << 16; - tmpbuf.hdr.data_size = htonl(data_size); - memcpy(&tmpbuf.first, sechdr + 4, sizeof(tmpbuf.first)); + hdr.data_size = htonl(data_size); + memcpy(sechdr, &hdr, sizeof(hdr)); /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf)); - sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf)); - + sg_init_one(&sg, sechdr, 8); skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x); - + skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - memcpy(sechdr, &tmpbuf, sizeof(tmpbuf)); - _leave(" = 0"); return 0; } @@ -196,8 +190,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, void *sechdr) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr rxkhdr - __attribute__((aligned(8))); /* must be all on one page */ + struct rxkad_level2_hdr rxkhdr; struct rxrpc_skb_priv *sp; SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; @@ -216,18 +209,16 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, rxkhdr.data_size = htonl(data_size | (u32)check << 16); rxkhdr.checksum = 0; + memcpy(sechdr, &rxkhdr, sizeof(rxkhdr)); /* encrypt from the session key */ - token = call->conn->key->payload.data[0]; + token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); sg_init_one(&sg[0], sechdr, sizeof(rxkhdr)); - sg_init_one(&sg[1], &rxkhdr, sizeof(rxkhdr)); - skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(rxkhdr), iv.x); - + skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x); crypto_skcipher_encrypt(req); /* we want to encrypt the skbuff in-place */ @@ -241,9 +232,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, sg_init_table(sg, nsg); skb_to_sgvec(skb, sg, 0, len); - skcipher_request_set_crypt(req, sg, sg, len, iv.x); - crypto_skcipher_encrypt(req); _leave(" = 0"); @@ -257,7 +246,7 @@ out: /* * checksum an RxRPC packet header */ -static int rxkad_secure_packet(const struct rxrpc_call *call, +static int rxkad_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, size_t data_size, void *sechdr) @@ -265,23 +254,20 @@ static int rxkad_secure_packet(const struct rxrpc_call *call, struct rxrpc_skb_priv *sp; SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; - struct scatterlist sg[2]; - struct { - __be32 x[2]; - } tmpbuf __attribute__((aligned(8))); /* must all be in same page */ + struct scatterlist sg; u32 x, y; int ret; sp = rxrpc_skb(skb); _enter("{%d{%x}},{#%u},%zu,", - call->debug_id, key_serial(call->conn->key), sp->hdr.seq, - data_size); + call->debug_id, key_serial(call->conn->params.key), + sp->hdr.seq, data_size); if (!call->conn->cipher) return 0; - ret = key_validate(call->conn->key); + ret = key_validate(call->conn->params.key); if (ret < 0) return ret; @@ -291,26 +277,23 @@ static int rxkad_secure_packet(const struct rxrpc_call *call, /* calculate the security checksum */ x = call->channel << (32 - RXRPC_CIDSHIFT); x |= sp->hdr.seq & 0x3fffffff; - tmpbuf.x[0] = htonl(sp->hdr.callNumber); - tmpbuf.x[1] = htonl(x); - - sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf)); - sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf)); + call->crypto_buf[0] = htonl(sp->hdr.callNumber); + call->crypto_buf[1] = htonl(x); + sg_init_one(&sg, call->crypto_buf, 8); skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x); - + skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(tmpbuf.x[1]); + y = ntohl(call->crypto_buf[1]); y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ sp->hdr.cksum = y; - switch (call->conn->security_level) { + switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; @@ -365,7 +348,6 @@ static int rxkad_verify_packet_auth(const struct rxrpc_call *call, skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, 8, iv.x); - crypto_skcipher_decrypt(req); skcipher_request_zero(req); @@ -444,13 +426,12 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, skb_to_sgvec(skb, sg, 0, skb->len); /* decrypt from the session key */ - token = call->conn->key->payload.data[0]; + token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, skb->len, iv.x); - crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) @@ -496,17 +477,14 @@ nomem: /* * verify the security on a received packet */ -static int rxkad_verify_packet(const struct rxrpc_call *call, +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, u32 *_abort_code) { SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_skb_priv *sp; struct rxrpc_crypt iv; - struct scatterlist sg[2]; - struct { - __be32 x[2]; - } tmpbuf __attribute__((aligned(8))); /* must all be in same page */ + struct scatterlist sg; u16 cksum; u32 x, y; int ret; @@ -514,7 +492,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call, sp = rxrpc_skb(skb); _enter("{%d{%x}},{#%u}", - call->debug_id, key_serial(call->conn->key), sp->hdr.seq); + call->debug_id, key_serial(call->conn->params.key), sp->hdr.seq); if (!call->conn->cipher) return 0; @@ -531,20 +509,17 @@ static int rxkad_verify_packet(const struct rxrpc_call *call, /* validate the security checksum */ x = call->channel << (32 - RXRPC_CIDSHIFT); x |= sp->hdr.seq & 0x3fffffff; - tmpbuf.x[0] = htonl(call->call_id); - tmpbuf.x[1] = htonl(x); - - sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf)); - sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf)); + call->crypto_buf[0] = htonl(call->call_id); + call->crypto_buf[1] = htonl(x); + sg_init_one(&sg, call->crypto_buf, 8); skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x); - + skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(tmpbuf.x[1]); + y = ntohl(call->crypto_buf[1]); cksum = (y >> 16) & 0xffff; if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ @@ -555,7 +530,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call, return -EPROTO; } - switch (call->conn->security_level) { + switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; @@ -587,9 +562,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) u32 serial; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); - ret = key_validate(conn->key); + ret = key_validate(conn->params.key); if (ret < 0) return ret; @@ -600,14 +575,14 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) challenge.min_level = htonl(0); challenge.__padding = 0; - msg.msg_name = &conn->trans->peer->srx.transport.sin; - msg.msg_namelen = sizeof(conn->trans->peer->srx.transport.sin); + msg.msg_name = &conn->params.peer->srx.transport.sin; + msg.msg_namelen = sizeof(conn->params.peer->srx.transport.sin); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; - whdr.epoch = htonl(conn->epoch); - whdr.cid = htonl(conn->cid); + whdr.epoch = htonl(conn->proto.epoch); + whdr.cid = htonl(conn->proto.cid); whdr.callNumber = 0; whdr.seq = 0; whdr.type = RXRPC_PACKET_TYPE_CHALLENGE; @@ -615,7 +590,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) whdr.userStatus = 0; whdr.securityIndex = conn->security_ix; whdr._rsvd = 0; - whdr.serviceId = htons(conn->service_id); + whdr.serviceId = htons(conn->params.service_id); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -628,7 +603,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) whdr.serial = htonl(serial); _proto("Tx CHALLENGE %%%u", serial); - ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { _debug("sendmsg failed: %d", ret); return -EAGAIN; @@ -655,8 +630,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn, _enter(""); - msg.msg_name = &conn->trans->peer->srx.transport.sin; - msg.msg_namelen = sizeof(conn->trans->peer->srx.transport.sin); + msg.msg_name = &conn->params.peer->srx.transport.sin; + msg.msg_namelen = sizeof(conn->params.peer->srx.transport.sin); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -682,7 +657,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn, whdr.serial = htonl(serial); _proto("Tx RESPONSE %%%u", serial); - ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 3, len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { _debug("sendmsg failed: %d", ret); return -EAGAIN; @@ -708,29 +683,6 @@ static void rxkad_calc_response_checksum(struct rxkad_response *response) } /* - * load a scatterlist with a potentially split-page buffer - */ -static void rxkad_sg_set_buf2(struct scatterlist sg[2], - void *buf, size_t buflen) -{ - int nsg = 1; - - sg_init_table(sg, 2); - - sg_set_buf(&sg[0], buf, buflen); - if (sg[0].offset + buflen > PAGE_SIZE) { - /* the buffer was split over two pages */ - sg[0].length = PAGE_SIZE - sg[0].offset; - sg_set_buf(&sg[1], buf + sg[0].length, buflen - sg[0].length); - nsg++; - } - - sg_mark_end(&sg[nsg - 1]); - - ASSERTCMP(sg[0].length + sg[1].length, ==, buflen); -} - -/* * encrypt the response packet */ static void rxkad_encrypt_response(struct rxrpc_connection *conn, @@ -739,17 +691,16 @@ static void rxkad_encrypt_response(struct rxrpc_connection *conn, { SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); struct rxrpc_crypt iv; - struct scatterlist sg[2]; + struct scatterlist sg[1]; /* continue encrypting from where we left off */ memcpy(&iv, s2->session_key, sizeof(iv)); - rxkad_sg_set_buf2(sg, &resp->encrypted, sizeof(resp->encrypted)); - + sg_init_table(sg, 1); + sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted)); skcipher_request_set_tfm(req, conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); - crypto_skcipher_encrypt(req); skcipher_request_zero(req); } @@ -769,14 +720,14 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, u32 version, nonce, min_level, abort_code; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); - if (!conn->key) { + if (!conn->params.key) { _leave(" = -EPROTO [no key]"); return -EPROTO; } - ret = key_validate(conn->key); + ret = key_validate(conn->params.key); if (ret < 0) { *_abort_code = RXKADEXPIRED; return ret; @@ -799,31 +750,27 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, goto protocol_error; abort_code = RXKADLEVELFAIL; - if (conn->security_level < min_level) + if (conn->params.security_level < min_level) goto protocol_error; - token = conn->key->payload.data[0]; + token = conn->params.key->payload.data[0]; /* build the response packet */ memset(&resp, 0, sizeof(resp)); resp.version = htonl(RXKAD_VERSION); - resp.encrypted.epoch = htonl(conn->epoch); - resp.encrypted.cid = htonl(conn->cid); + resp.encrypted.epoch = htonl(conn->proto.epoch); + resp.encrypted.cid = htonl(conn->proto.cid); resp.encrypted.securityIndex = htonl(conn->security_ix); resp.encrypted.inc_nonce = htonl(nonce + 1); - resp.encrypted.level = htonl(conn->security_level); + resp.encrypted.level = htonl(conn->params.security_level); resp.kvno = htonl(token->kad->kvno); resp.ticket_len = htonl(token->kad->ticket_len); - resp.encrypted.call_id[0] = - htonl(conn->channels[0] ? conn->channels[0]->call_id : 0); - resp.encrypted.call_id[1] = - htonl(conn->channels[1] ? conn->channels[1]->call_id : 0); - resp.encrypted.call_id[2] = - htonl(conn->channels[2] ? conn->channels[2]->call_id : 0); - resp.encrypted.call_id[3] = - htonl(conn->channels[3] ? conn->channels[3]->call_id : 0); + resp.encrypted.call_id[0] = htonl(conn->channels[0].call_counter); + resp.encrypted.call_id[1] = htonl(conn->channels[1].call_counter); + resp.encrypted.call_id[2] = htonl(conn->channels[2].call_counter); + resp.encrypted.call_id[3] = htonl(conn->channels[3].call_counter); /* calculate the response checksum and then do the encryption */ rxkad_calc_response_checksum(&resp); @@ -885,10 +832,8 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, } sg_init_one(&sg[0], ticket, ticket_len); - skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, ticket_len, iv.x); - crypto_skcipher_decrypt(req); skcipher_request_free(req); @@ -999,7 +944,7 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, const struct rxrpc_crypt *session_key) { SKCIPHER_REQUEST_ON_STACK(req, rxkad_ci); - struct scatterlist sg[2]; + struct scatterlist sg[1]; struct rxrpc_crypt iv; _enter(",,%08x%08x", @@ -1014,12 +959,11 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, memcpy(&iv, session_key, sizeof(iv)); - rxkad_sg_set_buf2(sg, &resp->encrypted, sizeof(resp->encrypted)); - + sg_init_table(sg, 1); + sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted)); skcipher_request_set_tfm(req, rxkad_ci); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); - crypto_skcipher_decrypt(req); skcipher_request_zero(req); @@ -1043,7 +987,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, void *ticket; u32 abort_code, version, kvno, ticket_len, level; __be32 csum; - int ret; + int ret, i; _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); @@ -1094,9 +1038,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, rxkad_decrypt_response(conn, &response, &session_key); abort_code = RXKADSEALEDINCON; - if (ntohl(response.encrypted.epoch) != conn->epoch) + if (ntohl(response.encrypted.epoch) != conn->proto.epoch) goto protocol_error_free; - if (ntohl(response.encrypted.cid) != conn->cid) + if (ntohl(response.encrypted.cid) != conn->proto.cid) goto protocol_error_free; if (ntohl(response.encrypted.securityIndex) != conn->security_ix) goto protocol_error_free; @@ -1106,11 +1050,26 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (response.encrypted.checksum != csum) goto protocol_error_free; - if (ntohl(response.encrypted.call_id[0]) > INT_MAX || - ntohl(response.encrypted.call_id[1]) > INT_MAX || - ntohl(response.encrypted.call_id[2]) > INT_MAX || - ntohl(response.encrypted.call_id[3]) > INT_MAX) - goto protocol_error_free; + spin_lock(&conn->channel_lock); + for (i = 0; i < RXRPC_MAXCALLS; i++) { + struct rxrpc_call *call; + u32 call_id = ntohl(response.encrypted.call_id[i]); + + if (call_id > INT_MAX) + goto protocol_error_unlock; + + if (call_id < conn->channels[i].call_counter) + goto protocol_error_unlock; + if (call_id > conn->channels[i].call_counter) { + call = rcu_dereference_protected( + conn->channels[i].call, + lockdep_is_held(&conn->channel_lock)); + if (call && call->state < RXRPC_CALL_COMPLETE) + goto protocol_error_unlock; + conn->channels[i].call_counter = call_id; + } + } + spin_unlock(&conn->channel_lock); abort_code = RXKADOUTOFSEQUENCE; if (ntohl(response.encrypted.inc_nonce) != conn->security_nonce + 1) @@ -1120,7 +1079,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, level = ntohl(response.encrypted.level); if (level > RXRPC_SECURITY_ENCRYPT) goto protocol_error_free; - conn->security_level = level; + conn->params.security_level = level; /* create a key to hold the security data and expiration time - after * this the connection security can be handled in exactly the same way @@ -1135,6 +1094,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, _leave(" = 0"); return 0; +protocol_error_unlock: + spin_unlock(&conn->channel_lock); protocol_error_free: kfree(ticket); protocol_error: diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/security.c index d223253b22fa..814d285ff802 100644 --- a/net/rxrpc/ar-security.c +++ b/net/rxrpc/security.c @@ -76,7 +76,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { const struct rxrpc_security *sec; struct rxrpc_key_token *token; - struct key *key = conn->key; + struct key *key = conn->params.key; int ret; _enter("{%d},{%x}", conn->debug_id, key_serial(key)); @@ -113,7 +113,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) { const struct rxrpc_security *sec; - struct rxrpc_local *local = conn->trans->local; + struct rxrpc_local *local = conn->params.local; struct rxrpc_sock *rx; struct key *key; key_ref_t kref; @@ -121,7 +121,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) _enter(""); - sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", conn->params.service_id, conn->security_ix); sec = rxrpc_security_lookup(conn->security_ix); if (!sec) { @@ -132,7 +132,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) /* find the service */ read_lock_bh(&local->services_lock); list_for_each_entry(rx, &local->services, listen_link) { - if (rx->srx.srx_service == conn->service_id) + if (rx->srx.srx_service == conn->params.service_id) goto found_service; } diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/skbuff.c index 62a267472fce..eee0cfd9ac8c 100644 --- a/net/rxrpc/ar-skbuff.c +++ b/net/rxrpc/skbuff.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index d20ed575acf4..03ad08774d4e 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -18,6 +18,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int zero = 0; static const unsigned int one = 1; static const unsigned int four = 4; +static const unsigned int thirtytwo = 32; static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = RXRPC_MAXACKS; @@ -89,16 +90,17 @@ static struct ctl_table rxrpc_sysctl_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&one, }, + + /* Non-time values */ { - .procname = "transport_expiry", - .data = &rxrpc_transport_expiry, + .procname = "max_backlog", + .data = &rxrpc_max_backlog, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)&one, + .extra1 = (void *)&four, + .extra2 = (void *)&thirtytwo, }, - - /* Non-time values */ { .procname = "rx_window_size", .data = &rxrpc_rx_window_size, diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c new file mode 100644 index 000000000000..b88914d53ca5 --- /dev/null +++ b/net/rxrpc/utils.c @@ -0,0 +1,46 @@ +/* Utility routines + * + * Copyright (C) 2015 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include "ar-internal.h" + +/* + * Fill out a peer address from a socket buffer containing a packet. + */ +int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb) +{ + memset(srx, 0, sizeof(*srx)); + + switch (ntohs(skb->protocol)) { + case ETH_P_IP: + srx->transport_type = SOCK_DGRAM; + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.sin.sin_family = AF_INET; + srx->transport.sin.sin_port = udp_hdr(skb)->source; + srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + return 0; + + case ETH_P_IPV6: + srx->transport_type = SOCK_DGRAM; + srx->transport_len = sizeof(srx->transport.sin6); + srx->transport.sin6.sin6_family = AF_INET6; + srx->transport.sin6.sin6_port = udp_hdr(skb)->source; + srx->transport.sin6.sin6_addr = ipv6_hdr(skb)->saddr; + return 0; + + default: + pr_warn_ratelimited("AF_RXRPC: Unknown eth protocol %u\n", + ntohs(skb->protocol)); + return -EAFNOSUPPORT; + } +} |