diff options
Diffstat (limited to 'net/rxrpc')
-rw-r--r-- | net/rxrpc/Makefile | 37 | ||||
-rw-r--r-- | net/rxrpc/af_rxrpc.c | 287 | ||||
-rw-r--r-- | net/rxrpc/ar-internal.h | 516 | ||||
-rw-r--r-- | net/rxrpc/call_accept.c | 477 | ||||
-rw-r--r-- | net/rxrpc/call_event.c | 1302 | ||||
-rw-r--r-- | net/rxrpc/call_object.c | 801 | ||||
-rw-r--r-- | net/rxrpc/conn_client.c | 372 | ||||
-rw-r--r-- | net/rxrpc/conn_event.c | 394 | ||||
-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 | 757 | ||||
-rw-r--r-- | net/rxrpc/insecure.c | 7 | ||||
-rw-r--r-- | net/rxrpc/key.c | 1237 | ||||
-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 | 721 | ||||
-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 | 192 | ||||
-rw-r--r-- | net/rxrpc/recvmsg.c | 417 | ||||
-rw-r--r-- | net/rxrpc/rxkad.c | 263 | ||||
-rw-r--r-- | net/rxrpc/security.c | 168 | ||||
-rw-r--r-- | net/rxrpc/skbuff.c | 165 | ||||
-rw-r--r-- | net/rxrpc/sysctl.c | 12 | ||||
-rw-r--r-- | net/rxrpc/utils.c | 46 |
26 files changed, 9263 insertions, 586 deletions
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index e05a06ef2..10f3f48a1 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 e45e94ca0..88effadd4 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-internal.h b/net/rxrpc/ar-internal.h index f0b807a16..ff83fb1dd 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; @@ -405,10 +425,12 @@ struct rxrpc_call { spinlock_t lock; rwlock_t state_lock; /* lock for state transition */ atomic_t usage; + atomic_t skb_count; /* Outstanding packets on this 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 +462,12 @@ 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 +493,21 @@ 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 +515,106 @@ 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 +625,108 @@ 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 +736,19 @@ 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 +760,11 @@ 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 +839,18 @@ 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 +858,18 @@ 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 +933,6 @@ 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/call_accept.c b/net/rxrpc/call_accept.c new file mode 100644 index 000000000..9bae21e66 --- /dev/null +++ b/net/rxrpc/call_accept.c @@ -0,0 +1,477 @@ +/* incoming call handling + * + * 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/errqueue.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/icmp.h> +#include <linux/gfp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include "ar-internal.h" + +/* + * generate a connection-level abort + */ +static int rxrpc_busy(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, + struct rxrpc_wire_header *whdr) +{ + struct msghdr msg; + struct kvec iov[1]; + size_t len; + int ret; + + _enter("%d,,", local->debug_id); + + whdr->type = RXRPC_PACKET_TYPE_BUSY; + whdr->serial = htonl(1); + + msg.msg_name = &srx->transport.sin; + msg.msg_namelen = sizeof(srx->transport.sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + iov[0].iov_base = whdr; + iov[0].iov_len = sizeof(*whdr); + + len = iov[0].iov_len; + + _proto("Tx BUSY %%1"); + + ret = kernel_sendmsg(local->socket, &msg, iov, 1, len); + if (ret < 0) { + _leave(" = -EAGAIN [sendmsg failed: %d]", ret); + return -EAGAIN; + } + + _leave(" = 0"); + return 0; +} + +/* + * accept an incoming call that needs peer, transport and/or connection setting + * up + */ +static int rxrpc_accept_incoming_call(struct rxrpc_local *local, + struct rxrpc_sock *rx, + struct sk_buff *skb, + struct sockaddr_rxrpc *srx) +{ + struct rxrpc_connection *conn; + struct rxrpc_skb_priv *sp, *nsp; + struct rxrpc_call *call; + struct sk_buff *notification; + int ret; + + _enter(""); + + sp = rxrpc_skb(skb); + + /* get a notification message to send to the server app */ + notification = alloc_skb(0, GFP_NOFS); + if (!notification) { + _debug("no memory"); + ret = -ENOMEM; + goto error_nofree; + } + rxrpc_new_skb(notification); + notification->mark = RXRPC_SKB_MARK_NEW_CALL; + + 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, skb); + rxrpc_put_connection(conn); + if (IS_ERR(call)) { + _debug("no call"); + ret = PTR_ERR(call); + goto error; + } + + /* attach the call to the socket */ + read_lock_bh(&local->services_lock); + if (rx->sk.sk_state == RXRPC_CLOSE) + goto invalid_service; + + write_lock(&rx->call_lock); + if (!test_and_set_bit(RXRPC_CALL_INIT_ACCEPT, &call->flags)) { + rxrpc_get_call(call); + + spin_lock(&call->conn->state_lock); + if (sp->hdr.securityIndex > 0 && + call->conn->state == RXRPC_CONN_SERVICE_UNSECURED) { + _debug("await conn sec"); + list_add_tail(&call->accept_link, &rx->secureq); + 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"); + call->state = RXRPC_CALL_SERVER_ACCEPTING; + list_add_tail(&call->accept_link, &rx->acceptq); + rxrpc_get_call(call); + atomic_inc(&call->skb_count); + nsp = rxrpc_skb(notification); + nsp->call = call; + + ASSERTCMP(atomic_read(&call->usage), >=, 3); + + _debug("notify"); + spin_lock(&call->lock); + ret = rxrpc_queue_rcv_skb(call, notification, true, + false); + spin_unlock(&call->lock); + notification = NULL; + BUG_ON(ret < 0); + } + spin_unlock(&call->conn->state_lock); + + _debug("queued"); + } + write_unlock(&rx->call_lock); + + _debug("process"); + rxrpc_fast_process_packet(call, skb); + + _debug("done"); + read_unlock_bh(&local->services_lock); + rxrpc_free_skb(notification); + rxrpc_put_call(call); + _leave(" = 0"); + return 0; + +invalid_service: + _debug("invalid"); + read_unlock_bh(&local->services_lock); + + read_lock_bh(&call->state_lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { + rxrpc_get_call(call); + rxrpc_queue_call(call); + } + read_unlock_bh(&call->state_lock); + rxrpc_put_call(call); + ret = -ECONNREFUSED; +error: + rxrpc_free_skb(notification); +error_nofree: + _leave(" = %d", ret); + return ret; +} + +/* + * 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 rxrpc_local *local) +{ + struct rxrpc_skb_priv *sp; + struct sockaddr_rxrpc srx; + struct rxrpc_sock *rx; + struct rxrpc_wire_header whdr; + struct sk_buff *skb; + int ret; + + _enter("%d", local->debug_id); + + skb = skb_dequeue(&local->accept_queue); + if (!skb) { + _leave("\n"); + return; + } + + _net("incoming call skb %p", skb); + + sp = rxrpc_skb(skb); + + /* Set up a response packet header in case we need it */ + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.seq = htonl(sp->hdr.seq); + whdr.serial = 0; + whdr.flags = 0; + whdr.type = 0; + whdr.userStatus = 0; + whdr.securityIndex = sp->hdr.securityIndex; + whdr._rsvd = 0; + whdr.serviceId = htons(sp->hdr.serviceId); + + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) + goto drop; + + /* get the socket providing the service */ + read_lock_bh(&local->services_lock); + list_for_each_entry(rx, &local->services, listen_link) { + if (rx->srx.srx_service == sp->hdr.serviceId && + rx->sk.sk_state != RXRPC_CLOSE) + goto found_service; + } + read_unlock_bh(&local->services_lock); + goto invalid_service; + +found_service: + _debug("found service %hd", rx->srx.srx_service); + if (sk_acceptq_is_full(&rx->sk)) + goto backlog_full; + sk_acceptq_added(&rx->sk); + sock_hold(&rx->sk); + read_unlock_bh(&local->services_lock); + + ret = rxrpc_accept_incoming_call(local, rx, skb, &srx); + if (ret < 0) + sk_acceptq_removed(&rx->sk); + sock_put(&rx->sk); + switch (ret) { + case -ECONNRESET: /* old calls are ignored */ + case -ECONNABORTED: /* aborted calls are reaborted or ignored */ + case 0: + return; + case -ECONNREFUSED: + goto invalid_service; + case -EBUSY: + goto busy; + case -EKEYREJECTED: + goto security_mismatch; + default: + BUG(); + } + +backlog_full: + read_unlock_bh(&local->services_lock); +busy: + rxrpc_busy(local, &srx, &whdr); + rxrpc_free_skb(skb); + return; + +drop: + rxrpc_free_skb(skb); + return; + +invalid_service: + skb->priority = RX_INVALID_OPERATION; + rxrpc_reject_packet(local, skb); + return; + + /* can't change connection security type mid-flow */ +security_mismatch: + skb->priority = RX_PROTOCOL_ERROR; + rxrpc_reject_packet(local, skb); + return; +} + +/* + * handle acceptance of a call by userspace + * - assign the user call ID to the call at the front of the queue + */ +struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, + unsigned long user_call_ID) +{ + struct rxrpc_call *call; + struct rb_node *parent, **pp; + int ret; + + _enter(",%lx", user_call_ID); + + ASSERT(!irqs_disabled()); + + write_lock(&rx->call_lock); + + ret = -ENODATA; + if (list_empty(&rx->acceptq)) + goto out; + + /* check the user ID isn't already in use */ + ret = -EBADSLT; + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + call = rb_entry(parent, struct rxrpc_call, sock_node); + + if (user_call_ID < call->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > call->user_call_ID) + pp = &(*pp)->rb_right; + else + goto out; + } + + /* dequeue the first call and check it's still valid */ + call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); + list_del_init(&call->accept_link); + sk_acceptq_removed(&rx->sk); + + write_lock_bh(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_SERVER_ACCEPTING: + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + break; + case RXRPC_CALL_REMOTELY_ABORTED: + case RXRPC_CALL_LOCALLY_ABORTED: + ret = -ECONNABORTED; + goto out_release; + case RXRPC_CALL_NETWORK_ERROR: + ret = call->conn->error; + goto out_release; + case RXRPC_CALL_DEAD: + ret = -ETIME; + goto out_discard; + default: + BUG(); + } + + /* formalise the acceptance */ + call->user_call_ID = user_call_ID; + rb_link_node(&call->sock_node, parent, pp); + rb_insert_color(&call->sock_node, &rx->calls); + if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags)) + BUG(); + if (test_and_set_bit(RXRPC_CALL_EV_ACCEPTED, &call->events)) + BUG(); + rxrpc_queue_call(call); + + rxrpc_get_call(call); + write_unlock_bh(&call->state_lock); + write_unlock(&rx->call_lock); + _leave(" = %p{%d}", call, call->debug_id); + return call; + + /* if the call is already dying or dead, then we leave the socket's ref + * on it to be released by rxrpc_dead_call_expired() as induced by + * rxrpc_release_call() */ +out_release: + _debug("release %p", call); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) + rxrpc_queue_call(call); +out_discard: + write_unlock_bh(&call->state_lock); + _debug("discard %p", call); +out: + write_unlock(&rx->call_lock); + _leave(" = %d", ret); + return ERR_PTR(ret); +} + +/* + * Handle rejection of a call by userspace + * - reject the call at the front of the queue + */ +int rxrpc_reject_call(struct rxrpc_sock *rx) +{ + struct rxrpc_call *call; + int ret; + + _enter(""); + + ASSERT(!irqs_disabled()); + + write_lock(&rx->call_lock); + + ret = -ENODATA; + if (list_empty(&rx->acceptq)) + goto out; + + /* dequeue the first call and check it's still valid */ + call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); + list_del_init(&call->accept_link); + sk_acceptq_removed(&rx->sk); + + write_lock_bh(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_SERVER_ACCEPTING: + call->state = RXRPC_CALL_SERVER_BUSY; + if (test_and_set_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) + rxrpc_queue_call(call); + ret = 0; + goto out_release; + case RXRPC_CALL_REMOTELY_ABORTED: + case RXRPC_CALL_LOCALLY_ABORTED: + ret = -ECONNABORTED; + goto out_release; + case RXRPC_CALL_NETWORK_ERROR: + ret = call->conn->error; + goto out_release; + case RXRPC_CALL_DEAD: + ret = -ETIME; + goto out_discard; + default: + BUG(); + } + + /* if the call is already dying or dead, then we leave the socket's ref + * on it to be released by rxrpc_dead_call_expired() as induced by + * rxrpc_release_call() */ +out_release: + _debug("release %p", call); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) + rxrpc_queue_call(call); +out_discard: + write_unlock_bh(&call->state_lock); + _debug("discard %p", call); +out: + write_unlock(&rx->call_lock); + _leave(" = %d", ret); + return ret; +} + +/** + * rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call + * @sock: The socket on which the impending call is waiting + * @user_call_ID: The tag to attach to the call + * + * Allow a kernel service to accept an incoming call, assuming the incoming + * call is still valid. + */ +struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock, + unsigned long user_call_ID) +{ + struct rxrpc_call *call; + + _enter(",%lx", user_call_ID); + call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID); + _leave(" = %p", call); + return call; +} +EXPORT_SYMBOL(rxrpc_kernel_accept_call); + +/** + * rxrpc_kernel_reject_call - Allow a kernel service to reject an incoming call + * @sock: The socket on which the impending call is waiting + * + * Allow a kernel service to reject an incoming call with a BUSY message, + * assuming the incoming call is still valid. + */ +int rxrpc_kernel_reject_call(struct socket *sock) +{ + int ret; + + _enter(""); + ret = rxrpc_reject_call(rxrpc_sk(sock->sk)); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(rxrpc_kernel_reject_call); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c new file mode 100644 index 000000000..e60cf65c2 --- /dev/null +++ b/net/rxrpc/call_event.c @@ -0,0 +1,1302 @@ +/* Management of Tx window, Tx resend, ACKs and out-of-sequence reception + * + * 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/circ_buf.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/udp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * propose an ACK be sent + */ +void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, + u32 serial, bool immediate) +{ + unsigned long expiry; + s8 prior = rxrpc_ack_priority[ack_reason]; + + ASSERTCMP(prior, >, 0); + + _enter("{%d},%s,%%%x,%u", + call->debug_id, rxrpc_acks(ack_reason), serial, immediate); + + if (prior < rxrpc_ack_priority[call->ackr_reason]) { + if (immediate) + goto cancel_timer; + return; + } + + /* update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial + * numbers */ + if (prior == rxrpc_ack_priority[call->ackr_reason]) { + if (prior <= 4) + call->ackr_serial = serial; + if (immediate) + goto cancel_timer; + return; + } + + call->ackr_reason = ack_reason; + call->ackr_serial = serial; + + switch (ack_reason) { + case RXRPC_ACK_DELAY: + _debug("run delay timer"); + expiry = rxrpc_soft_ack_delay; + goto run_timer; + + case RXRPC_ACK_IDLE: + if (!immediate) { + _debug("run defer timer"); + expiry = rxrpc_idle_ack_delay; + goto run_timer; + } + goto cancel_timer; + + case RXRPC_ACK_REQUESTED: + expiry = rxrpc_requested_ack_delay; + if (!expiry) + goto cancel_timer; + if (!immediate || serial == 1) { + _debug("run defer timer"); + goto run_timer; + } + + default: + _debug("immediate ACK"); + goto cancel_timer; + } + +run_timer: + expiry += jiffies; + if (!timer_pending(&call->ack_timer) || + time_after(call->ack_timer.expires, expiry)) + mod_timer(&call->ack_timer, expiry); + return; + +cancel_timer: + _debug("cancel timer %%%u", serial); + try_to_del_timer_sync(&call->ack_timer); + read_lock_bh(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); +} + +/* + * propose an ACK be sent, locking the call structure + */ +void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, + u32 serial, bool immediate) +{ + s8 prior = rxrpc_ack_priority[ack_reason]; + + if (prior > rxrpc_ack_priority[call->ackr_reason]) { + spin_lock_bh(&call->lock); + __rxrpc_propose_ACK(call, ack_reason, serial, immediate); + spin_unlock_bh(&call->lock); + } +} + +/* + * set the resend timer + */ +static void rxrpc_set_resend(struct rxrpc_call *call, u8 resend, + unsigned long resend_at) +{ + read_lock_bh(&call->state_lock); + if (call->state >= RXRPC_CALL_COMPLETE) + resend = 0; + + if (resend & 1) { + _debug("SET RESEND"); + set_bit(RXRPC_CALL_EV_RESEND, &call->events); + } + + if (resend & 2) { + _debug("MODIFY RESEND TIMER"); + set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + mod_timer(&call->resend_timer, resend_at); + } else { + _debug("KILL RESEND TIMER"); + del_timer_sync(&call->resend_timer); + clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + } + read_unlock_bh(&call->state_lock); +} + +/* + * resend packets + */ +static void rxrpc_resend(struct rxrpc_call *call) +{ + struct rxrpc_wire_header *whdr; + struct rxrpc_skb_priv *sp; + struct sk_buff *txb; + unsigned long *p_txb, resend_at; + bool stop; + int loop; + u8 resend; + + _enter("{%d,%d,%d,%d},", + call->acks_hard, call->acks_unacked, + atomic_read(&call->sequence), + CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz)); + + stop = false; + resend = 0; + resend_at = 0; + + for (loop = call->acks_tail; + loop != call->acks_head || stop; + loop = (loop + 1) & (call->acks_winsz - 1) + ) { + p_txb = call->acks_window + loop; + smp_read_barrier_depends(); + if (*p_txb & 1) + continue; + + txb = (struct sk_buff *) *p_txb; + sp = rxrpc_skb(txb); + + if (sp->need_resend) { + sp->need_resend = false; + + /* each Tx packet has a new serial number */ + sp->hdr.serial = atomic_inc_return(&call->conn->serial); + + whdr = (struct rxrpc_wire_header *)txb->head; + whdr->serial = htonl(sp->hdr.serial); + + _proto("Tx DATA %%%u { #%d }", + sp->hdr.serial, sp->hdr.seq); + if (rxrpc_send_data_packet(call->conn, txb) < 0) { + stop = true; + sp->resend_at = jiffies + 3; + } else { + sp->resend_at = + jiffies + rxrpc_resend_timeout; + } + } + + if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = true; + resend |= 1; + } else if (resend & 2) { + if (time_before(sp->resend_at, resend_at)) + resend_at = sp->resend_at; + } else { + resend_at = sp->resend_at; + resend |= 2; + } + } + + rxrpc_set_resend(call, resend, resend_at); + _leave(""); +} + +/* + * handle resend timer expiry + */ +static void rxrpc_resend_timer(struct rxrpc_call *call) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *txb; + unsigned long *p_txb, resend_at; + int loop; + u8 resend; + + _enter("%d,%d,%d", + call->acks_tail, call->acks_unacked, call->acks_head); + + if (call->state >= RXRPC_CALL_COMPLETE) + return; + + resend = 0; + resend_at = 0; + + for (loop = call->acks_unacked; + loop != call->acks_head; + loop = (loop + 1) & (call->acks_winsz - 1) + ) { + p_txb = call->acks_window + loop; + smp_read_barrier_depends(); + txb = (struct sk_buff *) (*p_txb & ~1); + sp = rxrpc_skb(txb); + + ASSERT(!(*p_txb & 1)); + + if (sp->need_resend) { + ; + } else if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = true; + resend |= 1; + } else if (resend & 2) { + if (time_before(sp->resend_at, resend_at)) + resend_at = sp->resend_at; + } else { + resend_at = sp->resend_at; + resend |= 2; + } + } + + rxrpc_set_resend(call, resend, resend_at); + _leave(""); +} + +/* + * process soft ACKs of our transmitted packets + * - these indicate packets the peer has or has not received, but hasn't yet + * given to the consumer, and so can still be discarded and re-requested + */ +static int rxrpc_process_soft_ACKs(struct rxrpc_call *call, + struct rxrpc_ackpacket *ack, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *txb; + unsigned long *p_txb, resend_at; + int loop; + u8 sacks[RXRPC_MAXACKS], resend; + + _enter("{%d,%d},{%d},", + call->acks_hard, + CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz), + ack->nAcks); + + if (skb_copy_bits(skb, 0, sacks, ack->nAcks) < 0) + goto protocol_error; + + resend = 0; + resend_at = 0; + for (loop = 0; loop < ack->nAcks; loop++) { + p_txb = call->acks_window; + p_txb += (call->acks_tail + loop) & (call->acks_winsz - 1); + smp_read_barrier_depends(); + txb = (struct sk_buff *) (*p_txb & ~1); + sp = rxrpc_skb(txb); + + switch (sacks[loop]) { + case RXRPC_ACK_TYPE_ACK: + sp->need_resend = false; + *p_txb |= 1; + break; + case RXRPC_ACK_TYPE_NACK: + sp->need_resend = true; + *p_txb &= ~1; + resend = 1; + break; + default: + _debug("Unsupported ACK type %d", sacks[loop]); + goto protocol_error; + } + } + + smp_mb(); + call->acks_unacked = (call->acks_tail + loop) & (call->acks_winsz - 1); + + /* anything not explicitly ACK'd is implicitly NACK'd, but may just not + * have been received or processed yet by the far end */ + for (loop = call->acks_unacked; + loop != call->acks_head; + loop = (loop + 1) & (call->acks_winsz - 1) + ) { + p_txb = call->acks_window + loop; + smp_read_barrier_depends(); + txb = (struct sk_buff *) (*p_txb & ~1); + sp = rxrpc_skb(txb); + + if (*p_txb & 1) { + /* packet must have been discarded */ + sp->need_resend = true; + *p_txb &= ~1; + resend |= 1; + } else if (sp->need_resend) { + ; + } else if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = true; + resend |= 1; + } else if (resend & 2) { + if (time_before(sp->resend_at, resend_at)) + resend_at = sp->resend_at; + } else { + resend_at = sp->resend_at; + resend |= 2; + } + } + + rxrpc_set_resend(call, resend, resend_at); + _leave(" = 0"); + return 0; + +protocol_error: + _leave(" = -EPROTO"); + return -EPROTO; +} + +/* + * discard hard-ACK'd packets from the Tx window + */ +static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) +{ + unsigned long _skb; + int tail = call->acks_tail, old_tail; + int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz); + + _enter("{%u,%u},%u", call->acks_hard, win, hard); + + ASSERTCMP(hard - call->acks_hard, <=, win); + + while (call->acks_hard < hard) { + smp_read_barrier_depends(); + _skb = call->acks_window[tail] & ~1; + rxrpc_free_skb((struct sk_buff *) _skb); + old_tail = tail; + tail = (tail + 1) & (call->acks_winsz - 1); + call->acks_tail = tail; + if (call->acks_unacked == old_tail) + call->acks_unacked = tail; + call->acks_hard++; + } + + wake_up(&call->tx_waitq); +} + +/* + * clear the Tx window in the event of a failure + */ +static void rxrpc_clear_tx_window(struct rxrpc_call *call) +{ + rxrpc_rotate_tx_window(call, atomic_read(&call->sequence)); +} + +/* + * drain the out of sequence received packet queue into the packet Rx queue + */ +static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + bool terminal; + int ret; + + _enter("{%d,%d}", call->rx_data_post, call->rx_first_oos); + + spin_lock_bh(&call->lock); + + ret = -ECONNRESET; + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) + goto socket_unavailable; + + skb = skb_dequeue(&call->rx_oos_queue); + if (skb) { + sp = rxrpc_skb(skb); + + _debug("drain OOS packet %d [%d]", + sp->hdr.seq, call->rx_first_oos); + + if (sp->hdr.seq != call->rx_first_oos) { + skb_queue_head(&call->rx_oos_queue, skb); + call->rx_first_oos = rxrpc_skb(skb)->hdr.seq; + _debug("requeue %p {%u}", skb, call->rx_first_oos); + } else { + skb->mark = RXRPC_SKB_MARK_DATA; + terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && + !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); + ret = rxrpc_queue_rcv_skb(call, skb, true, terminal); + BUG_ON(ret < 0); + _debug("drain #%u", call->rx_data_post); + call->rx_data_post++; + + /* find out what the next packet is */ + skb = skb_peek(&call->rx_oos_queue); + if (skb) + call->rx_first_oos = rxrpc_skb(skb)->hdr.seq; + else + call->rx_first_oos = 0; + _debug("peek %p {%u}", skb, call->rx_first_oos); + } + } + + ret = 0; +socket_unavailable: + spin_unlock_bh(&call->lock); + _leave(" = %d", ret); + return ret; +} + +/* + * insert an out of sequence packet into the buffer + */ +static void rxrpc_insert_oos_packet(struct rxrpc_call *call, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp, *psp; + struct sk_buff *p; + u32 seq; + + sp = rxrpc_skb(skb); + seq = sp->hdr.seq; + _enter(",,{%u}", seq); + + skb->destructor = rxrpc_packet_destructor; + ASSERTCMP(sp->call, ==, NULL); + sp->call = call; + rxrpc_get_call(call); + atomic_inc(&call->skb_count); + + /* insert into the buffer in sequence order */ + spin_lock_bh(&call->lock); + + skb_queue_walk(&call->rx_oos_queue, p) { + psp = rxrpc_skb(p); + if (psp->hdr.seq > seq) { + _debug("insert oos #%u before #%u", seq, psp->hdr.seq); + skb_insert(p, skb, &call->rx_oos_queue); + goto inserted; + } + } + + _debug("append oos #%u", seq); + skb_queue_tail(&call->rx_oos_queue, skb); +inserted: + + /* we might now have a new front to the queue */ + if (call->rx_first_oos == 0 || seq < call->rx_first_oos) + call->rx_first_oos = seq; + + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE && + call->rx_data_post == call->rx_first_oos) { + _debug("drain rx oos now"); + set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events); + } + read_unlock(&call->state_lock); + + spin_unlock_bh(&call->lock); + _leave(" [stored #%u]", call->rx_first_oos); +} + +/* + * clear the Tx window on final ACK reception + */ +static void rxrpc_zap_tx_window(struct rxrpc_call *call) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + unsigned long _skb, *acks_window; + u8 winsz = call->acks_winsz; + int tail; + + acks_window = call->acks_window; + call->acks_window = NULL; + + while (CIRC_CNT(call->acks_head, call->acks_tail, winsz) > 0) { + tail = call->acks_tail; + smp_read_barrier_depends(); + _skb = acks_window[tail] & ~1; + smp_mb(); + call->acks_tail = (call->acks_tail + 1) & (winsz - 1); + + skb = (struct sk_buff *) _skb; + sp = rxrpc_skb(skb); + _debug("+++ clear Tx %u", sp->hdr.seq); + rxrpc_free_skb(skb); + } + + kfree(acks_window); +} + +/* + * process the extra information that may be appended to an ACK packet + */ +static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int latest, int nAcks) +{ + struct rxrpc_ackinfo ackinfo; + struct rxrpc_peer *peer; + unsigned int mtu; + + if (skb_copy_bits(skb, nAcks + 3, &ackinfo, sizeof(ackinfo)) < 0) { + _leave(" [no ackinfo]"); + return; + } + + _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", + latest, + ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU), + ntohl(ackinfo.rwind), ntohl(ackinfo.jumbo_max)); + + mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU)); + + peer = call->conn->params.peer; + if (mtu < peer->maxdata) { + spin_lock_bh(&peer->lock); + peer->maxdata = mtu; + peer->mtu = mtu + peer->hdrsize; + spin_unlock_bh(&peer->lock); + _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata); + } +} + +/* + * process packets in the reception queue + */ +static int rxrpc_process_rx_queue(struct rxrpc_call *call, + u32 *_abort_code) +{ + struct rxrpc_ackpacket ack; + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + bool post_ACK; + int latest; + u32 hard, tx; + + _enter(""); + +process_further: + skb = skb_dequeue(&call->rx_queue); + if (!skb) + return -EAGAIN; + + _net("deferred skb %p", skb); + + sp = rxrpc_skb(skb); + + _debug("process %s [st %d]", rxrpc_pkts[sp->hdr.type], call->state); + + post_ACK = false; + + switch (sp->hdr.type) { + /* data packets that wind up here have been received out of + * order, need security processing or are jumbo packets */ + case RXRPC_PACKET_TYPE_DATA: + _proto("OOSQ DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); + + /* secured packets must be verified and possibly decrypted */ + if (call->conn->security->verify_packet(call, skb, + _abort_code) < 0) + goto protocol_error; + + rxrpc_insert_oos_packet(call, skb); + goto process_further; + + /* partial ACK to process */ + case RXRPC_PACKET_TYPE_ACK: + if (skb_copy_bits(skb, 0, &ack, sizeof(ack)) < 0) { + _debug("extraction failure"); + goto protocol_error; + } + if (!skb_pull(skb, sizeof(ack))) + BUG(); + + latest = sp->hdr.serial; + hard = ntohl(ack.firstPacket); + tx = atomic_read(&call->sequence); + + _proto("Rx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", + latest, + ntohs(ack.maxSkew), + hard, + ntohl(ack.previousPacket), + ntohl(ack.serial), + rxrpc_acks(ack.reason), + ack.nAcks); + + rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks); + + if (ack.reason == RXRPC_ACK_PING) { + _proto("Rx ACK %%%u PING Request", latest); + rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, + sp->hdr.serial, true); + } + + /* discard any out-of-order or duplicate ACKs */ + if (latest - call->acks_latest <= 0) { + _debug("discard ACK %d <= %d", + latest, call->acks_latest); + goto discard; + } + call->acks_latest = latest; + + if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && + call->state != RXRPC_CALL_CLIENT_AWAIT_REPLY && + call->state != RXRPC_CALL_SERVER_SEND_REPLY && + call->state != RXRPC_CALL_SERVER_AWAIT_ACK) + goto discard; + + _debug("Tx=%d H=%u S=%d", tx, call->acks_hard, call->state); + + if (hard > 0) { + if (hard - 1 > tx) { + _debug("hard-ACK'd packet %d not transmitted" + " (%d top)", + hard - 1, tx); + goto protocol_error; + } + + if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY || + call->state == RXRPC_CALL_SERVER_AWAIT_ACK) && + hard > tx) { + call->acks_hard = tx; + goto all_acked; + } + + smp_rmb(); + rxrpc_rotate_tx_window(call, hard - 1); + } + + if (ack.nAcks > 0) { + if (hard - 1 + ack.nAcks > tx) { + _debug("soft-ACK'd packet %d+%d not" + " transmitted (%d top)", + hard - 1, ack.nAcks, tx); + goto protocol_error; + } + + if (rxrpc_process_soft_ACKs(call, &ack, skb) < 0) + goto protocol_error; + } + goto discard; + + /* complete ACK to process */ + case RXRPC_PACKET_TYPE_ACKALL: + goto all_acked; + + /* abort and busy are handled elsewhere */ + case RXRPC_PACKET_TYPE_BUSY: + case RXRPC_PACKET_TYPE_ABORT: + BUG(); + + /* connection level events - also handled elsewhere */ + case RXRPC_PACKET_TYPE_CHALLENGE: + case RXRPC_PACKET_TYPE_RESPONSE: + case RXRPC_PACKET_TYPE_DEBUG: + BUG(); + } + + /* if we've had a hard ACK that covers all the packets we've sent, then + * that ends that phase of the operation */ +all_acked: + write_lock_bh(&call->state_lock); + _debug("ack all %d", call->state); + + switch (call->state) { + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + call->state = RXRPC_CALL_CLIENT_RECV_REPLY; + break; + case RXRPC_CALL_SERVER_AWAIT_ACK: + _debug("srv complete"); + call->state = RXRPC_CALL_COMPLETE; + post_ACK = true; + break; + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_SERVER_RECV_REQUEST: + goto protocol_error_unlock; /* can't occur yet */ + default: + write_unlock_bh(&call->state_lock); + goto discard; /* assume packet left over from earlier phase */ + } + + write_unlock_bh(&call->state_lock); + + /* if all the packets we sent are hard-ACK'd, then we can discard + * whatever we've got left */ + _debug("clear Tx %d", + CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz)); + + del_timer_sync(&call->resend_timer); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); + + if (call->acks_window) + rxrpc_zap_tx_window(call); + + if (post_ACK) { + /* post the final ACK message for userspace to pick up */ + _debug("post ACK"); + skb->mark = RXRPC_SKB_MARK_FINAL_ACK; + sp->call = call; + rxrpc_get_call(call); + atomic_inc(&call->skb_count); + spin_lock_bh(&call->lock); + if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0) + BUG(); + spin_unlock_bh(&call->lock); + goto process_further; + } + +discard: + rxrpc_free_skb(skb); + goto process_further; + +protocol_error_unlock: + write_unlock_bh(&call->state_lock); +protocol_error: + rxrpc_free_skb(skb); + _leave(" = -EPROTO"); + return -EPROTO; +} + +/* + * post a message to the socket Rx queue for recvmsg() to pick up + */ +static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error, + bool fatal) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + int ret; + + _enter("{%d,%lx},%u,%u,%d", + call->debug_id, call->flags, mark, error, fatal); + + /* remove timers and things for fatal messages */ + if (fatal) { + del_timer_sync(&call->resend_timer); + del_timer_sync(&call->ack_timer); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + } + + if (mark != RXRPC_SKB_MARK_NEW_CALL && + !test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { + _leave("[no userid]"); + return 0; + } + + if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { + skb = alloc_skb(0, GFP_NOFS); + if (!skb) + return -ENOMEM; + + rxrpc_new_skb(skb); + + skb->mark = mark; + + sp = rxrpc_skb(skb); + memset(sp, 0, sizeof(*sp)); + sp->error = error; + sp->call = call; + rxrpc_get_call(call); + atomic_inc(&call->skb_count); + + spin_lock_bh(&call->lock); + ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); + spin_unlock_bh(&call->lock); + BUG_ON(ret < 0); + } + + return 0; +} + +/* + * handle background processing of incoming call packets and ACK / abort + * generation + */ +void rxrpc_process_call(struct work_struct *work) +{ + struct rxrpc_call *call = + container_of(work, struct rxrpc_call, processor); + struct rxrpc_wire_header whdr; + struct rxrpc_ackpacket ack; + struct rxrpc_ackinfo ackinfo; + struct msghdr msg; + struct kvec iov[5]; + enum rxrpc_call_event genbit; + unsigned long bits; + __be32 data, pad; + size_t len; + int loop, nbit, ioc, ret, mtu; + u32 serial, abort_code = RX_PROTOCOL_ERROR; + u8 *acks = NULL; + + //printk("\n--------------------\n"); + _enter("{%d,%s,%lx} [%lu]", + call->debug_id, rxrpc_call_states[call->state], call->events, + (jiffies - call->creation_jif) / (HZ / 10)); + + if (test_and_set_bit(RXRPC_CALL_PROC_BUSY, &call->flags)) { + _debug("XXXXXXXXXXXXX RUNNING ON MULTIPLE CPUS XXXXXXXXXXXXX"); + return; + } + + if (!call->conn) + goto skip_msg_init; + + /* 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->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->proto.epoch); + whdr.cid = htonl(call->cid); + whdr.callNumber = htonl(call->call_id); + whdr.seq = 0; + whdr.type = RXRPC_PACKET_TYPE_ACK; + whdr.flags = call->conn->out_clientflag; + whdr.userStatus = 0; + whdr.securityIndex = call->conn->security_ix; + whdr._rsvd = 0; + whdr.serviceId = htons(call->service_id); + + memset(iov, 0, sizeof(iov)); + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); +skip_msg_init: + + /* deal with events of a final nature */ + 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->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, mark, error, true) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events)) { + ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + + clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); + clear_bit(RXRPC_CALL_EV_ABORT, &call->events); + + _debug("post conn abort"); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + call->conn->error, true) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) { + whdr.type = RXRPC_PACKET_TYPE_BUSY; + genbit = RXRPC_CALL_EV_REJECT_BUSY; + goto send_message; + } + + if (test_bit(RXRPC_CALL_EV_ABORT, &call->events)) { + ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + ECONNABORTED, true) < 0) + goto no_mem; + whdr.type = RXRPC_PACKET_TYPE_ABORT; + data = htonl(call->local_abort); + iov[1].iov_base = &data; + iov[1].iov_len = sizeof(data); + genbit = RXRPC_CALL_EV_ABORT; + goto send_message; + } + + if (test_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events)) { + genbit = RXRPC_CALL_EV_ACK_FINAL; + + ack.bufferSpace = htons(8); + ack.maxSkew = 0; + ack.serial = 0; + ack.reason = RXRPC_ACK_IDLE; + ack.nAcks = 0; + call->ackr_reason = 0; + + spin_lock_bh(&call->lock); + ack.serial = htonl(call->ackr_serial); + ack.previousPacket = htonl(call->ackr_prev_seq); + ack.firstPacket = htonl(call->rx_data_eaten + 1); + spin_unlock_bh(&call->lock); + + pad = 0; + + iov[1].iov_base = &ack; + iov[1].iov_len = sizeof(ack); + iov[2].iov_base = &pad; + iov[2].iov_len = 3; + iov[3].iov_base = &ackinfo; + iov[3].iov_len = sizeof(ackinfo); + goto send_ACK; + } + + if (call->events & ((1 << RXRPC_CALL_EV_RCVD_BUSY) | + (1 << RXRPC_CALL_EV_RCVD_ABORT)) + ) { + u32 mark; + + if (test_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events)) + mark = RXRPC_SKB_MARK_REMOTE_ABORT; + else + mark = RXRPC_SKB_MARK_BUSY; + + _debug("post abort/busy"); + rxrpc_clear_tx_window(call); + if (rxrpc_post_message(call, mark, ECONNABORTED, true) < 0) + goto no_mem; + + clear_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events); + clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_and_clear_bit(RXRPC_CALL_EV_RCVD_ACKALL, &call->events)) { + _debug("do implicit ackall"); + rxrpc_clear_tx_window(call); + } + + if (test_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events)) { + write_lock_bh(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->local_abort = RX_CALL_TIMEOUT; + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + } + write_unlock_bh(&call->state_lock); + + _debug("post timeout"); + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + ETIME, true) < 0) + goto no_mem; + + clear_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); + goto kill_ACKs; + } + + /* deal with assorted inbound messages */ + if (!skb_queue_empty(&call->rx_queue)) { + switch (rxrpc_process_rx_queue(call, &abort_code)) { + case 0: + case -EAGAIN: + break; + case -ENOMEM: + goto no_mem; + case -EKEYEXPIRED: + case -EKEYREJECTED: + case -EPROTO: + rxrpc_abort_call(call, abort_code); + goto kill_ACKs; + } + } + + /* handle resending */ + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) + rxrpc_resend_timer(call); + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) + rxrpc_resend(call); + + /* consider sending an ordinary ACK */ + if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { + _debug("send ACK: window: %d - %d { %lx }", + call->rx_data_eaten, call->ackr_win_top, + call->ackr_window[0]); + + if (call->state > RXRPC_CALL_SERVER_ACK_REQUEST && + call->ackr_reason != RXRPC_ACK_PING_RESPONSE) { + /* ACK by sending reply DATA packet in this state */ + clear_bit(RXRPC_CALL_EV_ACK, &call->events); + goto maybe_reschedule; + } + + genbit = RXRPC_CALL_EV_ACK; + + acks = kzalloc(call->ackr_win_top - call->rx_data_eaten, + GFP_NOFS); + if (!acks) + goto no_mem; + + //hdr.flags = RXRPC_SLOW_START_OK; + ack.bufferSpace = htons(8); + ack.maxSkew = 0; + + spin_lock_bh(&call->lock); + ack.reason = call->ackr_reason; + ack.serial = htonl(call->ackr_serial); + ack.previousPacket = htonl(call->ackr_prev_seq); + ack.firstPacket = htonl(call->rx_data_eaten + 1); + + ack.nAcks = 0; + for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) { + nbit = loop * BITS_PER_LONG; + for (bits = call->ackr_window[loop]; bits; bits >>= 1 + ) { + _debug("- l=%d n=%d b=%lx", loop, nbit, bits); + if (bits & 1) { + acks[nbit] = RXRPC_ACK_TYPE_ACK; + ack.nAcks = nbit + 1; + } + nbit++; + } + } + call->ackr_reason = 0; + spin_unlock_bh(&call->lock); + + pad = 0; + + iov[1].iov_base = &ack; + iov[1].iov_len = sizeof(ack); + iov[2].iov_base = acks; + iov[2].iov_len = ack.nAcks; + iov[3].iov_base = &pad; + iov[3].iov_len = 3; + iov[4].iov_base = &ackinfo; + iov[4].iov_len = sizeof(ackinfo); + + switch (ack.reason) { + case RXRPC_ACK_REQUESTED: + case RXRPC_ACK_DUPLICATE: + case RXRPC_ACK_OUT_OF_SEQUENCE: + case RXRPC_ACK_EXCEEDS_WINDOW: + case RXRPC_ACK_NOSPACE: + case RXRPC_ACK_PING: + case RXRPC_ACK_PING_RESPONSE: + goto send_ACK_with_skew; + case RXRPC_ACK_DELAY: + case RXRPC_ACK_IDLE: + goto send_ACK; + } + } + + /* handle completion of security negotiations on an incoming + * connection */ + if (test_and_clear_bit(RXRPC_CALL_EV_SECURED, &call->events)) { + _debug("secured"); + spin_lock_bh(&call->lock); + + if (call->state == RXRPC_CALL_SERVER_SECURING) { + _debug("securing"); + 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"); + call->state = RXRPC_CALL_SERVER_ACCEPTING; + list_move_tail(&call->accept_link, + &call->socket->acceptq); + } + 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); + read_unlock(&call->state_lock); + } + + spin_unlock_bh(&call->lock); + if (!test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events)) + goto maybe_reschedule; + } + + /* post a notification of an acceptable connection to the app */ + if (test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events)) { + _debug("post accept"); + if (rxrpc_post_message(call, RXRPC_SKB_MARK_NEW_CALL, + 0, false) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events); + goto maybe_reschedule; + } + + /* handle incoming call acceptance */ + if (test_and_clear_bit(RXRPC_CALL_EV_ACCEPTED, &call->events)) { + _debug("accepted"); + ASSERTCMP(call->rx_data_post, ==, 0); + call->rx_data_post = 1; + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) + set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events); + read_unlock_bh(&call->state_lock); + } + + /* drain the out of sequence received packet queue into the packet Rx + * queue */ + if (test_and_clear_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events)) { + while (call->rx_data_post == call->rx_first_oos) + if (rxrpc_drain_rx_oos_queue(call) < 0) + break; + 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; + +send_ACK_with_skew: + ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) - + ntohl(ack.serial)); +send_ACK: + mtu = call->conn->params.peer->if_mtu; + mtu -= call->conn->params.peer->hdrsize; + ackinfo.maxMTU = htonl(mtu); + ackinfo.rwind = htonl(rxrpc_rx_window_size); + + /* permit the peer to send us jumbo packets if it wants to */ + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max); + + serial = atomic_inc_return(&call->conn->serial); + whdr.serial = htonl(serial); + _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", + serial, + ntohs(ack.maxSkew), + ntohl(ack.firstPacket), + ntohl(ack.previousPacket), + ntohl(ack.serial), + rxrpc_acks(ack.reason), + ack.nAcks); + + del_timer_sync(&call->ack_timer); + if (ack.nAcks > 0) + set_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags); + goto send_message_2; + +send_message: + _debug("send message"); + + serial = atomic_inc_return(&call->conn->serial); + whdr.serial = htonl(serial); + _proto("Tx %s %%%u", rxrpc_pkts[whdr.type], serial); +send_message_2: + + len = iov[0].iov_len; + ioc = 1; + if (iov[4].iov_len) { + ioc = 5; + len += iov[4].iov_len; + len += iov[3].iov_len; + len += iov[2].iov_len; + len += iov[1].iov_len; + } else if (iov[3].iov_len) { + ioc = 4; + len += iov[3].iov_len; + len += iov[2].iov_len; + len += iov[1].iov_len; + } else if (iov[2].iov_len) { + ioc = 3; + len += iov[2].iov_len; + len += iov[1].iov_len; + } else if (iov[1].iov_len) { + ioc = 2; + len += iov[1].iov_len; + } + + ret = kernel_sendmsg(call->conn->params.local->socket, + &msg, iov, ioc, len); + if (ret < 0) { + _debug("sendmsg failed: %d", ret); + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_DEAD) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); + goto error; + } + + switch (genbit) { + case RXRPC_CALL_EV_ABORT: + clear_bit(genbit, &call->events); + clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + goto kill_ACKs; + + case RXRPC_CALL_EV_ACK_FINAL: + write_lock_bh(&call->state_lock); + if (call->state == RXRPC_CALL_CLIENT_FINAL_ACK) + call->state = RXRPC_CALL_COMPLETE; + write_unlock_bh(&call->state_lock); + goto kill_ACKs; + + default: + clear_bit(genbit, &call->events); + switch (call->state) { + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + case RXRPC_CALL_CLIENT_RECV_REPLY: + case RXRPC_CALL_SERVER_RECV_REQUEST: + case RXRPC_CALL_SERVER_ACK_REQUEST: + _debug("start ACK timer"); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, + call->ackr_serial, false); + default: + break; + } + goto maybe_reschedule; + } + +kill_ACKs: + del_timer_sync(&call->ack_timer); + if (test_and_clear_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events)) + rxrpc_put_call(call); + clear_bit(RXRPC_CALL_EV_ACK, &call->events); + +maybe_reschedule: + if (call->events || !skb_queue_empty(&call->rx_queue)) { + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_DEAD) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); + } + + /* don't leave aborted connections on the accept queue */ + 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->proto.cid); + + read_lock_bh(&call->state_lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); + } + +error: + clear_bit(RXRPC_CALL_PROC_BUSY, &call->flags); + kfree(acks); + + /* because we don't want two CPUs both processing the work item for one + * call at the same time, we use a flag to note when it's busy; however + * 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->proto.cid); + rxrpc_queue_call(call); + } + + _leave(""); + return; + +no_mem: + _debug("out of memory"); + goto maybe_reschedule; +} diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c new file mode 100644 index 000000000..ae057e074 --- /dev/null +++ b/net/rxrpc/call_object.c @@ -0,0 +1,801 @@ +/* RxRPC individual remote procedure call handling + * + * 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/slab.h> +#include <linux/module.h> +#include <linux/circ_buf.h> +#include <linux/spinlock_types.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * Maximum lifetime of a call (in jiffies). + */ +unsigned int rxrpc_max_call_lifetime = 60 * HZ; + +/* + * Time till dead call expires after last use (in jiffies). + */ +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", + [RXRPC_CALL_CLIENT_FINAL_ACK] = "ClFnlACK", + [RXRPC_CALL_SERVER_SECURING] = "SvSecure", + [RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept", + [RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq", + [RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq", + [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", + [RXRPC_CALL_SERVER_AWAIT_ACK] = "SvAwtACK", + [RXRPC_CALL_COMPLETE] = "Complete", + [RXRPC_CALL_SERVER_BUSY] = "SvBusy ", + [RXRPC_CALL_REMOTELY_ABORTED] = "RmtAbort", + [RXRPC_CALL_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CALL_NETWORK_ERROR] = "NetError", + [RXRPC_CALL_DEAD] = "Dead ", +}; + +struct kmem_cache *rxrpc_call_jar; +LIST_HEAD(rxrpc_calls); +DEFINE_RWLOCK(rxrpc_call_lock); + +static void rxrpc_destroy_call(struct work_struct *work); +static void rxrpc_call_life_expired(unsigned long _call); +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); + +/* + * find an extant server call + * - called in process context with IRQs enabled + */ +struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, + unsigned long user_call_ID) +{ + struct rxrpc_call *call; + struct rb_node *p; + + _enter("%p,%lx", rx, user_call_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; + +found_extant_call: + rxrpc_get_call(call); + read_unlock(&rx->call_lock); + _leave(" = %p [%d]", call, atomic_read(&call->usage)); + return call; +} + +/* + * allocate a new call + */ +static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) +{ + struct rxrpc_call *call; + + call = kmem_cache_zalloc(rxrpc_call_jar, gfp); + if (!call) + return NULL; + + call->acks_winsz = 16; + call->acks_window = kmalloc(call->acks_winsz * sizeof(unsigned long), + gfp); + if (!call->acks_window) { + kmem_cache_free(rxrpc_call_jar, call); + return NULL; + } + + setup_timer(&call->lifetimer, &rxrpc_call_life_expired, + (unsigned long) call); + setup_timer(&call->deadspan, &rxrpc_dead_call_expired, + (unsigned long) call); + setup_timer(&call->ack_timer, &rxrpc_ack_time_expired, + (unsigned long) call); + setup_timer(&call->resend_timer, &rxrpc_resend_time_expired, + (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); + init_waitqueue_head(&call->tx_waitq); + spin_lock_init(&call->lock); + rwlock_init(&call->state_lock); + atomic_set(&call->usage, 1); + call->debug_id = atomic_inc_return(&rxrpc_debug_id); + + memset(&call->sock_node, 0xed, sizeof(call->sock_node)); + + call->rx_data_expect = 1; + call->rx_data_eaten = 0; + call->rx_first_oos = 0; + call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size; + call->creation_jif = jiffies; + return call; +} + +/* + * Allocate a new client call. + */ +static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + struct rxrpc_call *call; + + _enter(""); + + 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; + + call->local = rx->local; + call->service_id = srx->srx_service; + call->in_clientflag = 0; + + _leave(" = %p", call); + return call; +} + +/* + * 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); + return 0; +} + +/* + * set up a call for the given data + * - called in process context with IRQs enabled + */ +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, + gfp_t gfp) +{ + struct rxrpc_call *call, *xcall; + struct rb_node *parent, **pp; + int ret; + + _enter("%p,%lx", rx, user_call_ID); + + call = rxrpc_alloc_client_call(rx, srx, gfp); + if (IS_ERR(call)) { + _leave(" = %ld", PTR_ERR(call)); + return call; + } + + /* 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); + + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + xcall = rb_entry(parent, struct rxrpc_call, sock_node); + + if (user_call_ID < xcall->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > xcall->user_call_ID) + pp = &(*pp)->rb_right; + else + goto found_user_ID_now_present; + } + + rxrpc_get_call(call); + + rb_link_node(&call->sock_node, parent, pp); + rb_insert_color(&call->sock_node, &rx->calls); + write_unlock(&rx->call_lock); + + write_lock_bh(&rxrpc_call_lock); + 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; + +error: + write_lock(&rx->call_lock); + rb_erase(&call->sock_node, &rx->calls); + write_unlock(&rx->call_lock); + rxrpc_put_call(call); + + write_lock_bh(&rxrpc_call_lock); + list_del_init(&call->link); + write_unlock_bh(&rxrpc_call_lock); + + set_bit(RXRPC_CALL_RELEASED, &call->flags); + 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); + set_bit(RXRPC_CALL_RELEASED, &call->flags); + call->state = RXRPC_CALL_DEAD; + rxrpc_put_call(call); + _leave(" = -EEXIST [%p]", call); + return ERR_PTR(-EEXIST); +} + +/* + * set up an incoming call + * - called in process context with IRQs enabled + */ +struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, + struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_call *call, *candidate; + u32 call_id, chan; + + _enter(",%d", conn->debug_id); + + ASSERT(rx != NULL); + + candidate = rxrpc_alloc_call(GFP_NOIO); + if (!candidate) + return ERR_PTR(-EBUSY); + + 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; + + spin_lock(&conn->channel_lock); + + /* set the channel for this call */ + 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 == sp->hdr.callNumber) { + /* already set; must've been a duplicate packet */ + _debug("extant call [%d]", call->state); + ASSERTCMP(call->conn, ==, conn); + + read_lock(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_LOCALLY_ABORTED: + if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) + rxrpc_queue_call(call); + case RXRPC_CALL_REMOTELY_ABORTED: + read_unlock(&call->state_lock); + goto aborted_call; + default: + rxrpc_get_call(call); + read_unlock(&call->state_lock); + goto extant_call; + } + } + + if (call) { + /* it seems the channel is still in use from the previous call + * - ditch the old binding if its call is now complete */ + _debug("CALL: %u { %s }", + call->debug_id, rxrpc_call_states[call->state]); + + if (call->state >= RXRPC_CALL_COMPLETE) { + __rxrpc_disconnect_call(call); + } else { + spin_unlock(&conn->channel_lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = -EBUSY"); + return ERR_PTR(-EBUSY); + } + } + + /* check the call number isn't duplicate */ + _debug("check dup"); + 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; + conn->channels[chan].call_counter = call_id; + rcu_assign_pointer(conn->channels[chan].call, call); + sock_hold(&rx->sk); + rxrpc_get_connection(conn); + spin_unlock(&conn->channel_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); + + 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); + + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; + add_timer(&call->lifetimer); + _leave(" = %p {%d} [new]", call, call->debug_id); + return call; + +extant_call: + 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: + spin_unlock(&conn->channel_lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = -ECONNABORTED"); + return ERR_PTR(-ECONNABORTED); + +old_call: + spin_unlock(&conn->channel_lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = -ECONNRESET [old]"); + return ERR_PTR(-ECONNRESET); +} + +/* + * detach a call from a socket and set up for release + */ +void rxrpc_release_call(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = call->conn; + struct rxrpc_sock *rx = call->socket; + + _enter("{%d,%d,%d,%d}", + call->debug_id, atomic_read(&call->usage), + atomic_read(&call->ackr_not_idle), + call->rx_first_oos); + + spin_lock_bh(&call->lock); + if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) + BUG(); + spin_unlock_bh(&call->lock); + + /* dissociate from the socket + * - the socket's ref on the call is passed to the death timer + */ + _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 }", + call, call->events, call->flags); + ASSERT(!test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); + list_del_init(&call->accept_link); + sk_acceptq_removed(&rx->sk); + } else if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { + rb_erase(&call->sock_node, &rx->calls); + memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); + clear_bit(RXRPC_CALL_HAS_USERID, &call->flags); + } + write_unlock_bh(&rx->call_lock); + + /* free up the channel for reuse */ + 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; + } + write_unlock_bh(&call->state_lock); + + rxrpc_disconnect_call(call); + + /* clean up the Rx queue */ + if (!skb_queue_empty(&call->rx_queue) || + !skb_queue_empty(&call->rx_oos_queue)) { + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + + _debug("purge Rx queues"); + + spin_lock_bh(&call->lock); + while ((skb = skb_dequeue(&call->rx_queue)) || + (skb = skb_dequeue(&call->rx_oos_queue))) { + spin_unlock_bh(&call->lock); + + sp = rxrpc_skb(skb); + _debug("- zap %s %%%u #%u", + rxrpc_pkts[sp->hdr.type], + sp->hdr.serial, sp->hdr.seq); + rxrpc_free_skb(skb); + spin_lock_bh(&call->lock); + } + spin_unlock_bh(&call->lock); + + ASSERTCMP(call->state, !=, RXRPC_CALL_COMPLETE); + } + + del_timer_sync(&call->resend_timer); + del_timer_sync(&call->ack_timer); + del_timer_sync(&call->lifetimer); + call->deadspan.expires = jiffies + rxrpc_dead_call_expiry; + add_timer(&call->deadspan); + + _leave(""); +} + +/* + * handle a dead call being ready for reaping + */ +static void rxrpc_dead_call_expired(unsigned long _call) +{ + struct rxrpc_call *call = (struct rxrpc_call *) _call; + + _enter("{%d}", call->debug_id); + + write_lock_bh(&call->state_lock); + call->state = RXRPC_CALL_DEAD; + write_unlock_bh(&call->state_lock); + rxrpc_put_call(call); +} + +/* + * mark a call as to be released, aborting it if it's still in progress + * - called with softirqs disabled + */ +static void rxrpc_mark_call_released(struct rxrpc_call *call) +{ + bool sched; + + write_lock(&call->state_lock); + if (call->state < RXRPC_CALL_DEAD) { + sched = false; + if (call->state < RXRPC_CALL_COMPLETE) { + _debug("abort call %p", call); + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->local_abort = RX_CALL_DEAD; + if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) + sched = true; + } + if (!test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) + sched = true; + if (sched) + rxrpc_queue_call(call); + } + write_unlock(&call->state_lock); +} + +/* + * release all the calls associated with a socket + */ +void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) +{ + struct rxrpc_call *call; + struct rb_node *p; + + _enter("%p", rx); + + read_lock_bh(&rx->call_lock); + + /* mark all the calls as no longer wanting incoming packets */ + for (p = rb_first(&rx->calls); p; p = rb_next(p)) { + call = rb_entry(p, struct rxrpc_call, sock_node); + rxrpc_mark_call_released(call); + } + + /* kill the not-yet-accepted incoming calls */ + list_for_each_entry(call, &rx->secureq, accept_link) { + rxrpc_mark_call_released(call); + } + + list_for_each_entry(call, &rx->acceptq, accept_link) { + rxrpc_mark_call_released(call); + } + + read_unlock_bh(&rx->call_lock); + _leave(""); +} + +/* + * release a call + */ +void __rxrpc_put_call(struct rxrpc_call *call) +{ + ASSERT(call != NULL); + + _enter("%p{u=%d}", call, atomic_read(&call->usage)); + + ASSERTCMP(atomic_read(&call->usage), >, 0); + + if (atomic_dec_and_test(&call->usage)) { + _debug("call %d dead", call->debug_id); + WARN_ON(atomic_read(&call->skb_count) != 0); + ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); + rxrpc_queue_work(&call->destroyer); + } + _leave(""); +} + +/* + * 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) +{ + _net("DESTROY CALL %d", call->debug_id); + + ASSERT(call->socket); + + memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); + + del_timer_sync(&call->lifetimer); + del_timer_sync(&call->deadspan); + del_timer_sync(&call->ack_timer); + del_timer_sync(&call->resend_timer); + + ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); + ASSERTCMP(call->events, ==, 0); + if (work_pending(&call->processor)) { + _debug("defer destroy"); + rxrpc_queue_work(&call->destroyer); + return; + } + + ASSERTCMP(call->conn, ==, NULL); + + if (call->acks_window) { + _debug("kill Tx window %d", + CIRC_CNT(call->acks_head, call->acks_tail, + call->acks_winsz)); + smp_mb(); + while (CIRC_CNT(call->acks_head, call->acks_tail, + call->acks_winsz) > 0) { + struct rxrpc_skb_priv *sp; + unsigned long _skb; + + _skb = call->acks_window[call->acks_tail] & ~1; + sp = rxrpc_skb((struct sk_buff *)_skb); + _debug("+++ clear Tx %u", sp->hdr.seq); + rxrpc_free_skb((struct sk_buff *)_skb); + call->acks_tail = + (call->acks_tail + 1) & (call->acks_winsz - 1); + } + + kfree(call->acks_window); + } + + rxrpc_free_skb(call->tx_pending); + + rxrpc_purge_queue(&call->rx_queue); + ASSERT(skb_queue_empty(&call->rx_oos_queue)); + sock_put(&call->socket->sk); + call_rcu(&call->rcu, rxrpc_rcu_destroy_call); +} + +/* + * destroy a call + */ +static void rxrpc_destroy_call(struct work_struct *work) +{ + struct rxrpc_call *call = + container_of(work, struct rxrpc_call, destroyer); + + _enter("%p{%d,%d,%p}", + call, atomic_read(&call->usage), call->channel, call->conn); + + ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); + + write_lock_bh(&rxrpc_call_lock); + list_del_init(&call->link); + write_unlock_bh(&rxrpc_call_lock); + + rxrpc_cleanup_call(call); + _leave(""); +} + +/* + * preemptively destroy all the call records from a transport endpoint rather + * than waiting for them to time out + */ +void __exit rxrpc_destroy_all_calls(void) +{ + struct rxrpc_call *call; + + _enter(""); + write_lock_bh(&rxrpc_call_lock); + + while (!list_empty(&rxrpc_calls)) { + call = list_entry(rxrpc_calls.next, struct rxrpc_call, link); + _debug("Zapping call %p", call); + + list_del_init(&call->link); + + switch (atomic_read(&call->usage)) { + case 0: + ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); + break; + case 1: + if (del_timer_sync(&call->deadspan) != 0 && + call->state != RXRPC_CALL_DEAD) + rxrpc_dead_call_expired((unsigned long) call); + if (call->state != RXRPC_CALL_DEAD) + break; + default: + 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)) + pr_err("Rx queue occupied\n"); + if (!skb_queue_empty(&call->rx_oos_queue)) + pr_err("OOS queue occupied\n"); + break; + } + + write_unlock_bh(&rxrpc_call_lock); + cond_resched(); + write_lock_bh(&rxrpc_call_lock); + } + + write_unlock_bh(&rxrpc_call_lock); + _leave(""); +} + +/* + * handle call lifetime being exceeded + */ +static void rxrpc_call_life_expired(unsigned long _call) +{ + struct rxrpc_call *call = (struct rxrpc_call *) _call; + + if (call->state >= RXRPC_CALL_COMPLETE) + return; + + _enter("{%d}", call->debug_id); + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) { + set_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); + rxrpc_queue_call(call); + } + read_unlock_bh(&call->state_lock); +} + +/* + * handle resend timer expiry + * - may not take call->state_lock as this can deadlock against del_timer_sync() + */ +static void rxrpc_resend_time_expired(unsigned long _call) +{ + struct rxrpc_call *call = (struct rxrpc_call *) _call; + + _enter("{%d}", call->debug_id); + + if (call->state >= RXRPC_CALL_COMPLETE) + return; + + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + if (!test_and_set_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) + rxrpc_queue_call(call); +} + +/* + * handle ACK timer expiry + */ +static void rxrpc_ack_time_expired(unsigned long _call) +{ + struct rxrpc_call *call = (struct rxrpc_call *) _call; + + _enter("{%d}", call->debug_id); + + if (call->state >= RXRPC_CALL_COMPLETE) + return; + + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); +} diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c new file mode 100644 index 000000000..9e91f27b0 --- /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/conn_event.c b/net/rxrpc/conn_event.c new file mode 100644 index 000000000..cee0f35bc --- /dev/null +++ b/net/rxrpc/conn_event.c @@ -0,0 +1,394 @@ +/* connection-level event handling + * + * 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/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" + +/* + * pass a connection-level abort onto all calls on that connection + */ +static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state, + u32 abort_code) +{ + struct rxrpc_call *call; + int i; + + _enter("{%d},%x", conn->debug_id, abort_code); + + spin_lock(&conn->channel_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) { + call->local_abort = conn->local_abort; + set_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); + } else { + call->remote_abort = conn->remote_abort; + set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + } + rxrpc_queue_call(call); + } + write_unlock_bh(&call->state_lock); + } + + spin_unlock(&conn->channel_lock); + _leave(""); +} + +/* + * generate a connection-level abort + */ +static int rxrpc_abort_connection(struct rxrpc_connection *conn, + u32 error, u32 abort_code) +{ + struct rxrpc_wire_header whdr; + struct msghdr msg; + struct kvec iov[2]; + __be32 word; + size_t len; + u32 serial; + int ret; + + _enter("%d,,%u,%u", conn->debug_id, error, abort_code); + + /* generate a connection-level abort */ + spin_lock_bh(&conn->state_lock); + if (conn->state < RXRPC_CONN_REMOTELY_ABORTED) { + conn->state = RXRPC_CONN_LOCALLY_ABORTED; + conn->error = error; + spin_unlock_bh(&conn->state_lock); + } else { + spin_unlock_bh(&conn->state_lock); + _leave(" = 0 [already dead]"); + return 0; + } + + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code); + + 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->proto.epoch); + whdr.cid = htonl(conn->proto.cid); + whdr.callNumber = 0; + whdr.seq = 0; + whdr.type = RXRPC_PACKET_TYPE_ABORT; + whdr.flags = conn->out_clientflag; + whdr.userStatus = 0; + whdr.securityIndex = conn->security_ix; + whdr._rsvd = 0; + whdr.serviceId = htons(conn->params.service_id); + + word = htonl(conn->local_abort); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = &word; + iov[1].iov_len = sizeof(word); + + len = iov[0].iov_len + iov[1].iov_len; + + serial = atomic_inc_return(&conn->serial); + whdr.serial = htonl(serial); + _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort); + + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + if (ret < 0) { + _debug("sendmsg failed: %d", ret); + return -EAGAIN; + } + + _leave(" = 0"); + return 0; +} + +/* + * mark a call as being on a now-secured channel + * - must be called with softirqs disabled + */ +static void rxrpc_call_is_secure(struct rxrpc_call *call) +{ + _enter("%p", call); + if (call) { + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_EV_SECURED, &call->events)) + rxrpc_queue_call(call); + read_unlock(&call->state_lock); + } +} + +/* + * connection-level Rx packet processor + */ +static int rxrpc_process_event(struct rxrpc_connection *conn, + struct sk_buff *skb, + u32 *_abort_code) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + __be32 wtmp; + u32 abort_code; + int loop, ret; + + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + kleave(" = -ECONNABORTED [%u]", conn->state); + return -ECONNABORTED; + } + + _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_ABORT: + if (skb_copy_bits(skb, 0, &wtmp, sizeof(wtmp)) < 0) + return -EPROTO; + abort_code = ntohl(wtmp); + _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); + + conn->state = RXRPC_CONN_REMOTELY_ABORTED; + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, + abort_code); + return -ECONNABORTED; + + case RXRPC_PACKET_TYPE_CHALLENGE: + return conn->security->respond_to_challenge(conn, skb, + _abort_code); + + case RXRPC_PACKET_TYPE_RESPONSE: + ret = conn->security->verify_response(conn, skb, _abort_code); + if (ret < 0) + return ret; + + ret = conn->security->init_connection_security(conn); + if (ret < 0) + return ret; + + 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_SERVICE_CHALLENGING) { + conn->state = RXRPC_CONN_SERVICE; + for (loop = 0; loop < RXRPC_MAXCALLS; loop++) + rxrpc_call_is_secure( + rcu_dereference_protected( + conn->channels[loop].call, + lockdep_is_held(&conn->channel_lock))); + } + + spin_unlock(&conn->state_lock); + spin_unlock(&conn->channel_lock); + return 0; + + default: + _leave(" = -EPROTO [%u]", sp->hdr.type); + return -EPROTO; + } +} + +/* + * set up security and issue a challenge + */ +static void rxrpc_secure_connection(struct rxrpc_connection *conn) +{ + u32 abort_code; + int ret; + + _enter("{%d}", conn->debug_id); + + ASSERT(conn->security_ix != 0); + + if (!conn->params.key) { + _debug("set up security"); + ret = rxrpc_init_server_conn_security(conn); + switch (ret) { + case 0: + break; + case -ENOENT: + abort_code = RX_CALL_DEAD; + goto abort; + default: + abort_code = RXKADNOAUTH; + goto abort; + } + } + + if (conn->security->issue_challenge(conn) < 0) { + abort_code = RX_CALL_DEAD; + ret = -ENOMEM; + goto abort; + } + + _leave(""); + return; + +abort: + _debug("abort %d, %d", ret, abort_code); + rxrpc_abort_connection(conn, -ret, abort_code); + _leave(" [aborted]"); +} + +/* + * connection-level event processor + */ +void rxrpc_process_connection(struct work_struct *work) +{ + struct rxrpc_connection *conn = + container_of(work, struct rxrpc_connection, processor); + struct sk_buff *skb; + u32 abort_code = RX_PROTOCOL_ERROR; + int ret; + + _enter("{%d}", conn->debug_id); + + if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) + rxrpc_secure_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 */ + while ((skb = skb_dequeue(&conn->rx_queue))) { + ret = rxrpc_process_event(conn, skb, &abort_code); + switch (ret) { + case -EPROTO: + case -EKEYEXPIRED: + case -EKEYREJECTED: + goto protocol_error; + case -EAGAIN: + goto requeue_and_leave; + case -ECONNABORTED: + default: + rxrpc_free_skb(skb); + break; + } + } + +out: + rxrpc_put_connection(conn); + _leave(""); + return; + +requeue_and_leave: + skb_queue_head(&conn->rx_queue, skb); + goto out; + +protocol_error: + if (rxrpc_abort_connection(conn, -ret, abort_code) < 0) + goto requeue_and_leave; + rxrpc_free_skb(skb); + _leave(" [EPROTO]"); + goto out; +} + +/* + * put a packet up for transport-level abort + */ +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) +{ + CHECK_SLAB_OKAY(&local->usage); + + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); +} + +/* + * reject packets through the local endpoint + */ +void rxrpc_reject_packets(struct rxrpc_local *local) +{ + union { + struct sockaddr sa; + struct sockaddr_in sin; + } sa; + struct rxrpc_skb_priv *sp; + struct rxrpc_wire_header whdr; + struct sk_buff *skb; + struct msghdr msg; + struct kvec iov[2]; + size_t size; + __be32 code; + + _enter("%d", local->debug_id); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = &code; + iov[1].iov_len = sizeof(code); + size = sizeof(whdr) + sizeof(code); + + msg.msg_name = &sa; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + memset(&sa, 0, sizeof(sa)); + sa.sa.sa_family = local->srx.transport.family; + switch (sa.sa.sa_family) { + case AF_INET: + msg.msg_namelen = sizeof(sa.sin); + break; + default: + msg.msg_namelen = 0; + break; + } + + memset(&whdr, 0, sizeof(whdr)); + whdr.type = RXRPC_PACKET_TYPE_ABORT; + + while ((skb = skb_dequeue(&local->reject_queue))) { + sp = rxrpc_skb(skb); + switch (sa.sa.sa_family) { + case AF_INET: + sa.sin.sin_port = udp_hdr(skb)->source; + sa.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + code = htonl(skb->priority); + + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.serviceId = htons(sp->hdr.serviceId); + whdr.flags = sp->hdr.flags; + whdr.flags ^= RXRPC_CLIENT_INITIATED; + whdr.flags &= RXRPC_CLIENT_INITIATED; + + kernel_sendmsg(local->socket, &msg, iov, 2, size); + break; + + default: + break; + } + + rxrpc_free_skb(skb); + } + + _leave(""); +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c new file mode 100644 index 000000000..896d84493 --- /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 000000000..fd9027ccb --- /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/input.c b/net/rxrpc/input.c new file mode 100644 index 000000000..70bb77818 --- /dev/null +++ b/net/rxrpc/input.c @@ -0,0 +1,757 @@ +/* RxRPC packet reception + * + * 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/errqueue.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/icmp.h> +#include <linux/gfp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include <net/udp.h> +#include <net/net_namespace.h> +#include "ar-internal.h" + +/* + * queue a packet for recvmsg to pass to userspace + * - the caller must hold a lock on call->lock + * - must not be called with interrupts disabled (sk_filter() disables BH's) + * - eats the packet whether successful or not + * - there must be just one reference to the packet, which the caller passes to + * this function + */ +int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, + bool force, bool terminal) +{ + struct rxrpc_skb_priv *sp; + struct rxrpc_sock *rx = call->socket; + struct sock *sk; + int ret; + + _enter(",,%d,%d", force, terminal); + + ASSERT(!irqs_disabled()); + + sp = rxrpc_skb(skb); + ASSERTCMP(sp->call, ==, call); + + /* if we've already posted the terminal message for a call, then we + * don't post any more */ + if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { + _debug("already terminated"); + ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE); + rxrpc_free_skb(skb); + return 0; + } + + sk = &rx->sk; + + if (!force) { + /* cast skb->rcvbuf to unsigned... It's pointless, but + * reduces number of warnings when compiling with -W + * --ANK */ +// ret = -ENOBUFS; +// if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= +// (unsigned int) sk->sk_rcvbuf) +// goto out; + + ret = sk_filter(sk, skb); + if (ret < 0) + goto out; + } + + spin_lock_bh(&sk->sk_receive_queue.lock); + if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags) && + !test_bit(RXRPC_CALL_RELEASED, &call->flags) && + call->socket->sk.sk_state != RXRPC_CLOSE) { + skb->destructor = rxrpc_packet_destructor; + skb->dev = NULL; + skb->sk = sk; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + + if (terminal) { + _debug("<<<< TERMINAL MESSAGE >>>>"); + set_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags); + } + + /* allow interception by a kernel service */ + if (rx->interceptor) { + rx->interceptor(sk, call->user_call_ID, skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); + } else { + _net("post skb %p", skb); + __skb_queue_tail(&sk->sk_receive_queue, skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + } + skb = NULL; + } else { + spin_unlock_bh(&sk->sk_receive_queue.lock); + } + ret = 0; + +out: + rxrpc_free_skb(skb); + + _leave(" = %d", ret); + return ret; +} + +/* + * process a DATA packet, posting the packet to the appropriate queue + * - eats the packet if successful + */ +static int rxrpc_fast_process_data(struct rxrpc_call *call, + struct sk_buff *skb, u32 seq) +{ + struct rxrpc_skb_priv *sp; + bool terminal; + int ret, ackbit, ack; + u32 serial; + u8 flags; + + _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); + + sp = rxrpc_skb(skb); + ASSERTCMP(sp->call, ==, NULL); + flags = sp->hdr.flags; + serial = sp->hdr.serial; + + spin_lock(&call->lock); + + if (call->state > RXRPC_CALL_COMPLETE) + goto discard; + + ASSERTCMP(call->rx_data_expect, >=, call->rx_data_post); + ASSERTCMP(call->rx_data_post, >=, call->rx_data_recv); + ASSERTCMP(call->rx_data_recv, >=, call->rx_data_eaten); + + if (seq < call->rx_data_post) { + _debug("dup #%u [-%u]", seq, call->rx_data_post); + ack = RXRPC_ACK_DUPLICATE; + ret = -ENOBUFS; + goto discard_and_ack; + } + + /* we may already have the packet in the out of sequence queue */ + ackbit = seq - (call->rx_data_eaten + 1); + ASSERTCMP(ackbit, >=, 0); + if (__test_and_set_bit(ackbit, call->ackr_window)) { + _debug("dup oos #%u [%u,%u]", + seq, call->rx_data_eaten, call->rx_data_post); + ack = RXRPC_ACK_DUPLICATE; + goto discard_and_ack; + } + + if (seq >= call->ackr_win_top) { + _debug("exceed #%u [%u]", seq, call->ackr_win_top); + __clear_bit(ackbit, call->ackr_window); + ack = RXRPC_ACK_EXCEEDS_WINDOW; + goto discard_and_ack; + } + + if (seq == call->rx_data_expect) { + clear_bit(RXRPC_CALL_EXPECT_OOS, &call->flags); + call->rx_data_expect++; + } else if (seq > call->rx_data_expect) { + _debug("oos #%u [%u]", seq, call->rx_data_expect); + call->rx_data_expect = seq + 1; + if (test_and_set_bit(RXRPC_CALL_EXPECT_OOS, &call->flags)) { + ack = RXRPC_ACK_OUT_OF_SEQUENCE; + goto enqueue_and_ack; + } + goto enqueue_packet; + } + + if (seq != call->rx_data_post) { + _debug("ahead #%u [%u]", seq, call->rx_data_post); + goto enqueue_packet; + } + + if (test_bit(RXRPC_CALL_RCVD_LAST, &call->flags)) + goto protocol_error; + + /* if the packet need security things doing to it, then it goes down + * the slow path */ + if (call->conn->security_ix) + goto enqueue_packet; + + sp->call = call; + rxrpc_get_call(call); + atomic_inc(&call->skb_count); + terminal = ((flags & RXRPC_LAST_PACKET) && + !(flags & RXRPC_CLIENT_INITIATED)); + ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); + if (ret < 0) { + if (ret == -ENOMEM || ret == -ENOBUFS) { + __clear_bit(ackbit, call->ackr_window); + ack = RXRPC_ACK_NOSPACE; + goto discard_and_ack; + } + goto out; + } + + skb = NULL; + sp = NULL; + + _debug("post #%u", seq); + ASSERTCMP(call->rx_data_post, ==, seq); + call->rx_data_post++; + + if (flags & RXRPC_LAST_PACKET) + set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); + + /* if we've reached an out of sequence packet then we need to drain + * that queue into the socket Rx queue now */ + if (call->rx_data_post == call->rx_first_oos) { + _debug("drain rx oos now"); + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events)) + rxrpc_queue_call(call); + read_unlock(&call->state_lock); + } + + spin_unlock(&call->lock); + atomic_inc(&call->ackr_not_idle); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false); + _leave(" = 0 [posted]"); + return 0; + +protocol_error: + ret = -EBADMSG; +out: + spin_unlock(&call->lock); + _leave(" = %d", ret); + return ret; + +discard_and_ack: + _debug("discard and ACK packet %p", skb); + __rxrpc_propose_ACK(call, ack, serial, true); +discard: + spin_unlock(&call->lock); + rxrpc_free_skb(skb); + _leave(" = 0 [discarded]"); + return 0; + +enqueue_and_ack: + __rxrpc_propose_ACK(call, ack, serial, true); +enqueue_packet: + _net("defer skb %p", skb); + spin_unlock(&call->lock); + skb_queue_tail(&call->rx_queue, skb); + atomic_inc(&call->ackr_not_idle); + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_DEAD) + rxrpc_queue_call(call); + read_unlock(&call->state_lock); + _leave(" = 0 [queued]"); + return 0; +} + +/* + * assume an implicit ACKALL of the transmission phase of a client socket upon + * reception of the first reply packet + */ +static void rxrpc_assume_implicit_ackall(struct rxrpc_call *call, u32 serial) +{ + write_lock_bh(&call->state_lock); + + switch (call->state) { + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + call->state = RXRPC_CALL_CLIENT_RECV_REPLY; + call->acks_latest = serial; + + _debug("implicit ACKALL %%%u", call->acks_latest); + set_bit(RXRPC_CALL_EV_RCVD_ACKALL, &call->events); + write_unlock_bh(&call->state_lock); + + if (try_to_del_timer_sync(&call->resend_timer) >= 0) { + clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_EV_RESEND, &call->events); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + } + break; + + default: + write_unlock_bh(&call->state_lock); + break; + } +} + +/* + * post an incoming packet to the nominated call to deal with + * - must get rid of the sk_buff, either by freeing it or by queuing it + */ +void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + __be32 wtmp; + u32 hi_serial, abort_code; + + _enter("%p,%p", call, skb); + + ASSERT(!irqs_disabled()); + +#if 0 // INJECT RX ERROR + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) { + static int skip = 0; + if (++skip == 3) { + printk("DROPPED 3RD PACKET!!!!!!!!!!!!!\n"); + skip = 0; + goto free_packet; + } + } +#endif + + /* track the latest serial number on this connection for ACK packet + * information */ + hi_serial = atomic_read(&call->conn->hi_serial); + while (sp->hdr.serial > hi_serial) + hi_serial = atomic_cmpxchg(&call->conn->hi_serial, hi_serial, + sp->hdr.serial); + + /* request ACK generation for any ACK or DATA packet that requests + * it */ + if (sp->hdr.flags & RXRPC_REQUEST_ACK) { + _proto("ACK Requested on %%%u", sp->hdr.serial); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false); + } + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_ABORT: + _debug("abort"); + + if (skb_copy_bits(skb, 0, &wtmp, sizeof(wtmp)) < 0) + goto protocol_error; + + abort_code = ntohl(wtmp); + _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); + + write_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_REMOTELY_ABORTED; + call->remote_abort = abort_code; + set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + rxrpc_queue_call(call); + } + goto free_packet_unlock; + + case RXRPC_PACKET_TYPE_BUSY: + _proto("Rx BUSY %%%u", sp->hdr.serial); + + if (rxrpc_conn_is_service(call->conn)) + goto protocol_error; + + write_lock_bh(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + call->state = RXRPC_CALL_SERVER_BUSY; + set_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events); + rxrpc_queue_call(call); + case RXRPC_CALL_SERVER_BUSY: + goto free_packet_unlock; + default: + goto protocol_error_locked; + } + + default: + _proto("Rx %s %%%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial); + goto protocol_error; + + case RXRPC_PACKET_TYPE_DATA: + _proto("Rx DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); + + if (sp->hdr.seq == 0) + goto protocol_error; + + call->ackr_prev_seq = sp->hdr.seq; + + /* received data implicitly ACKs all of the request packets we + * sent when we're acting as a client */ + if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) + rxrpc_assume_implicit_ackall(call, sp->hdr.serial); + + switch (rxrpc_fast_process_data(call, skb, sp->hdr.seq)) { + case 0: + skb = NULL; + goto done; + + default: + BUG(); + + /* data packet received beyond the last packet */ + case -EBADMSG: + goto protocol_error; + } + + case RXRPC_PACKET_TYPE_ACKALL: + case RXRPC_PACKET_TYPE_ACK: + /* ACK processing is done in process context */ + read_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_DEAD) { + skb_queue_tail(&call->rx_queue, skb); + rxrpc_queue_call(call); + skb = NULL; + } + read_unlock_bh(&call->state_lock); + goto free_packet; + } + +protocol_error: + _debug("protocol error"); + write_lock_bh(&call->state_lock); +protocol_error_locked: + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->local_abort = RX_PROTOCOL_ERROR; + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + rxrpc_queue_call(call); + } +free_packet_unlock: + write_unlock_bh(&call->state_lock); +free_packet: + rxrpc_free_skb(skb); +done: + _leave(""); +} + +/* + * split up a jumbo data packet + */ +static void rxrpc_process_jumbo_packet(struct rxrpc_call *call, + struct sk_buff *jumbo) +{ + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp; + struct sk_buff *part; + + _enter(",{%u,%u}", jumbo->data_len, jumbo->len); + + sp = rxrpc_skb(jumbo); + + do { + sp->hdr.flags &= ~RXRPC_JUMBO_PACKET; + + /* make a clone to represent the first subpacket in what's left + * of the jumbo packet */ + part = skb_clone(jumbo, GFP_ATOMIC); + if (!part) { + /* simply ditch the tail in the event of ENOMEM */ + pskb_trim(jumbo, RXRPC_JUMBO_DATALEN); + break; + } + rxrpc_new_skb(part); + + pskb_trim(part, RXRPC_JUMBO_DATALEN); + + if (!pskb_pull(jumbo, RXRPC_JUMBO_DATALEN)) + goto protocol_error; + + if (skb_copy_bits(jumbo, 0, &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; + if (!pskb_pull(jumbo, sizeof(jhdr))) + BUG(); + + sp->hdr.seq += 1; + sp->hdr.serial += 1; + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + + _proto("Rx DATA Jumbo %%%u", sp->hdr.serial - 1); + + rxrpc_fast_process_packet(call, part); + part = NULL; + + } while (sp->hdr.flags & RXRPC_JUMBO_PACKET); + + rxrpc_fast_process_packet(call, jumbo); + _leave(""); + return; + +protocol_error: + _debug("protocol error"); + rxrpc_free_skb(part); + rxrpc_free_skb(jumbo); + write_lock_bh(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->local_abort = RX_PROTOCOL_ERROR; + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + rxrpc_queue_call(call); + } + write_unlock_bh(&call->state_lock); + _leave(""); +} + +/* + * post an incoming packet to the appropriate call/socket to deal with + * - must get rid of the sk_buff, either by freeing it or by queuing it + */ +static void rxrpc_post_packet_to_call(struct rxrpc_call *call, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp; + + _enter("%p,%p", call, skb); + + sp = rxrpc_skb(skb); + + _debug("extant call [%d]", call->state); + + read_lock(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_LOCALLY_ABORTED: + if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) { + rxrpc_queue_call(call); + goto free_unlock; + } + case RXRPC_CALL_REMOTELY_ABORTED: + case RXRPC_CALL_NETWORK_ERROR: + case RXRPC_CALL_DEAD: + goto dead_call; + case RXRPC_CALL_COMPLETE: + case RXRPC_CALL_CLIENT_FINAL_ACK: + /* complete server call */ + if (rxrpc_conn_is_service(call->conn)) + goto dead_call; + /* resend last packet of a completed call */ + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); + rxrpc_queue_call(call); + goto free_unlock; + default: + break; + } + + read_unlock(&call->state_lock); + rxrpc_get_call(call); + + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_process_jumbo_packet(call, skb); + else + rxrpc_fast_process_packet(call, skb); + + rxrpc_put_call(call); + goto done; + +dead_call: + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + skb->priority = RX_CALL_DEAD; + rxrpc_reject_packet(call->conn->params.local, skb); + goto unlock; + } +free_unlock: + rxrpc_free_skb(skb); +unlock: + read_unlock(&call->state_lock); +done: + _leave(""); +} + +/* + * 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, + struct sk_buff *skb) +{ + _enter("%p,%p", conn, skb); + + skb_queue_tail(&conn->rx_queue, skb); + rxrpc_queue_conn(conn); +} + +/* + * post endpoint-level events to the local endpoint + * - this includes debug and version messages + */ +static void rxrpc_post_packet_to_local(struct rxrpc_local *local, + struct sk_buff *skb) +{ + _enter("%p,%p", local, skb); + + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_local(local); +} + +/* + * Extract the wire header from a packet and translate the byte order. + */ +static noinline +int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) +{ + struct rxrpc_wire_header whdr; + + /* dig out the RxRPC connection details */ + if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) + return -EBADMSG; + if (!pskb_pull(skb, sizeof(whdr))) + BUG(); + + memset(sp, 0, sizeof(*sp)); + sp->hdr.epoch = ntohl(whdr.epoch); + sp->hdr.cid = ntohl(whdr.cid); + sp->hdr.callNumber = ntohl(whdr.callNumber); + sp->hdr.seq = ntohl(whdr.seq); + sp->hdr.serial = ntohl(whdr.serial); + sp->hdr.flags = whdr.flags; + sp->hdr.type = whdr.type; + sp->hdr.userStatus = whdr.userStatus; + sp->hdr.securityIndex = whdr.securityIndex; + sp->hdr._rsvd = ntohs(whdr._rsvd); + sp->hdr.serviceId = ntohs(whdr.serviceId); + return 0; +} + +/* + * 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 = sk->sk_user_data; + struct sk_buff *skb; + int ret; + + _enter("%p", sk); + + ASSERT(!irqs_disabled()); + + skb = skb_recv_datagram(sk, 0, 1, &ret); + if (!skb) { + if (ret == -EAGAIN) + return; + _debug("UDP socket error %d", ret); + return; + } + + rxrpc_new_skb(skb); + + _net("recv skb %p", skb); + + /* we'll probably need to checksum it (didn't call sock_recvmsg) */ + if (skb_checksum_complete(skb)) { + rxrpc_free_skb(skb); + __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0); + _leave(" [CSUM failed]"); + return; + } + + __UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0); + + /* The socket buffer we have is owned by UDP, with UDP's data all over + * it, but we really want our own data there. + */ + skb_orphan(skb); + sp = rxrpc_skb(skb); + + _net("Rx UDP packet from %08x:%04hu", + ntohl(ip_hdr(skb)->saddr), ntohs(udp_hdr(skb)->source)); + + /* dig out the RxRPC connection details */ + if (rxrpc_extract_header(sp, skb) < 0) + goto bad_message; + + _net("Rx RxRPC %s ep=%x call=%x:%x", + sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient", + sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber); + + if (sp->hdr.type >= RXRPC_N_PACKET_TYPES || + !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) { + _proto("Rx Bad Packet Type %u", sp->hdr.type); + goto bad_message; + } + + if (sp->hdr.type == RXRPC_PACKET_TYPE_VERSION) { + 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; + + rcu_read_lock(); + + 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); + } else { + /* 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); + + if (!call || atomic_read(&call->usage) == 0) + goto cant_route_call; + + rxrpc_post_packet_to_call(call, skb); + } + + rcu_read_unlock(); +out: + 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->processor); + _leave(" [incoming]"); + return; + } + skb->priority = RX_INVALID_OPERATION; + } else { + skb->priority = RX_CALL_DEAD; + } + + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + _debug("reject type %d",sp->hdr.type); + rxrpc_reject_packet(local, skb); + } else { + rxrpc_free_skb(skb); + } + _leave(" [no call]"); + return; + +bad_message: + skb->priority = RX_PROTOCOL_ERROR; + rxrpc_reject_packet(local, skb); + _leave(" [badmsg]"); +} diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index e57140361..c21ad213b 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/key.c b/net/rxrpc/key.c new file mode 100644 index 000000000..18c737a61 --- /dev/null +++ b/net/rxrpc/key.c @@ -0,0 +1,1237 @@ +/* RxRPC key 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. + * + * RxRPC keys should have a description of describing their purpose: + * "afs@CAMBRIDGE.REDHAT.COM> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <crypto/skcipher.h> +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/key-type.h> +#include <linux/ctype.h> +#include <linux/slab.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <keys/rxrpc-type.h> +#include <keys/user-type.h> +#include "ar-internal.h" + +static int rxrpc_vet_description_s(const char *); +static int rxrpc_preparse(struct key_preparsed_payload *); +static int rxrpc_preparse_s(struct key_preparsed_payload *); +static void rxrpc_free_preparse(struct key_preparsed_payload *); +static void rxrpc_free_preparse_s(struct key_preparsed_payload *); +static void rxrpc_destroy(struct key *); +static void rxrpc_destroy_s(struct key *); +static void rxrpc_describe(const struct key *, struct seq_file *); +static long rxrpc_read(const struct key *, char __user *, size_t); + +/* + * rxrpc defined keys take an arbitrary string as the description and an + * arbitrary blob of data as the payload + */ +struct key_type key_type_rxrpc = { + .name = "rxrpc", + .preparse = rxrpc_preparse, + .free_preparse = rxrpc_free_preparse, + .instantiate = generic_key_instantiate, + .destroy = rxrpc_destroy, + .describe = rxrpc_describe, + .read = rxrpc_read, +}; +EXPORT_SYMBOL(key_type_rxrpc); + +/* + * rxrpc server defined keys take "<serviceId>:<securityIndex>" as the + * description and an 8-byte decryption key as the payload + */ +struct key_type key_type_rxrpc_s = { + .name = "rxrpc_s", + .vet_description = rxrpc_vet_description_s, + .preparse = rxrpc_preparse_s, + .free_preparse = rxrpc_free_preparse_s, + .instantiate = generic_key_instantiate, + .destroy = rxrpc_destroy_s, + .describe = rxrpc_describe, +}; + +/* + * Vet the description for an RxRPC server key + */ +static int rxrpc_vet_description_s(const char *desc) +{ + unsigned long num; + char *p; + + num = simple_strtoul(desc, &p, 10); + if (*p != ':' || num > 65535) + return -EINVAL; + num = simple_strtoul(p + 1, &p, 10); + if (*p || num < 1 || num > 255) + return -EINVAL; + return 0; +} + +/* + * parse an RxKAD type XDR format token + * - the caller guarantees we have at least 4 words + */ +static int rxrpc_preparse_xdr_rxkad(struct key_preparsed_payload *prep, + size_t datalen, + const __be32 *xdr, unsigned int toklen) +{ + struct rxrpc_key_token *token, **pptoken; + size_t plen; + u32 tktlen; + + _enter(",{%x,%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + toklen); + + if (toklen <= 8 * 4) + return -EKEYREJECTED; + tktlen = ntohl(xdr[7]); + _debug("tktlen: %x", tktlen); + if (tktlen > AFSTOKEN_RK_TIX_MAX) + return -EKEYREJECTED; + if (toklen < 8 * 4 + tktlen) + return -EKEYREJECTED; + + plen = sizeof(*token) + sizeof(*token->kad) + tktlen; + prep->quotalen = datalen + plen; + + plen -= sizeof(*token); + token = kzalloc(sizeof(*token), GFP_KERNEL); + if (!token) + return -ENOMEM; + + token->kad = kzalloc(plen, GFP_KERNEL); + if (!token->kad) { + kfree(token); + return -ENOMEM; + } + + token->security_index = RXRPC_SECURITY_RXKAD; + token->kad->ticket_len = tktlen; + token->kad->vice_id = ntohl(xdr[0]); + token->kad->kvno = ntohl(xdr[1]); + token->kad->start = ntohl(xdr[4]); + token->kad->expiry = ntohl(xdr[5]); + token->kad->primary_flag = ntohl(xdr[6]); + memcpy(&token->kad->session_key, &xdr[2], 8); + memcpy(&token->kad->ticket, &xdr[8], tktlen); + + _debug("SCIX: %u", token->security_index); + _debug("TLEN: %u", token->kad->ticket_len); + _debug("EXPY: %x", token->kad->expiry); + _debug("KVNO: %u", token->kad->kvno); + _debug("PRIM: %u", token->kad->primary_flag); + _debug("SKEY: %02x%02x%02x%02x%02x%02x%02x%02x", + token->kad->session_key[0], token->kad->session_key[1], + token->kad->session_key[2], token->kad->session_key[3], + token->kad->session_key[4], token->kad->session_key[5], + token->kad->session_key[6], token->kad->session_key[7]); + if (token->kad->ticket_len >= 8) + _debug("TCKT: %02x%02x%02x%02x%02x%02x%02x%02x", + token->kad->ticket[0], token->kad->ticket[1], + token->kad->ticket[2], token->kad->ticket[3], + token->kad->ticket[4], token->kad->ticket[5], + token->kad->ticket[6], token->kad->ticket[7]); + + /* count the number of tokens attached */ + prep->payload.data[1] = (void *)((unsigned long)prep->payload.data[1] + 1); + + /* attach the data */ + for (pptoken = (struct rxrpc_key_token **)&prep->payload.data[0]; + *pptoken; + pptoken = &(*pptoken)->next) + continue; + *pptoken = token; + if (token->kad->expiry < prep->expiry) + prep->expiry = token->kad->expiry; + + _leave(" = 0"); + return 0; +} + +static void rxrpc_free_krb5_principal(struct krb5_principal *princ) +{ + int loop; + + if (princ->name_parts) { + for (loop = princ->n_name_parts - 1; loop >= 0; loop--) + kfree(princ->name_parts[loop]); + kfree(princ->name_parts); + } + kfree(princ->realm); +} + +static void rxrpc_free_krb5_tagged(struct krb5_tagged_data *td) +{ + kfree(td->data); +} + +/* + * free up an RxK5 token + */ +static void rxrpc_rxk5_free(struct rxk5_key *rxk5) +{ + int loop; + + rxrpc_free_krb5_principal(&rxk5->client); + rxrpc_free_krb5_principal(&rxk5->server); + rxrpc_free_krb5_tagged(&rxk5->session); + + if (rxk5->addresses) { + for (loop = rxk5->n_addresses - 1; loop >= 0; loop--) + rxrpc_free_krb5_tagged(&rxk5->addresses[loop]); + kfree(rxk5->addresses); + } + if (rxk5->authdata) { + for (loop = rxk5->n_authdata - 1; loop >= 0; loop--) + rxrpc_free_krb5_tagged(&rxk5->authdata[loop]); + kfree(rxk5->authdata); + } + + kfree(rxk5->ticket); + kfree(rxk5->ticket2); + kfree(rxk5); +} + +/* + * extract a krb5 principal + */ +static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, + const __be32 **_xdr, + unsigned int *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned int toklen = *_toklen, n_parts, loop, tmp; + + /* there must be at least one name, and at least #names+1 length + * words */ + if (toklen <= 12) + return -EINVAL; + + _enter(",{%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), toklen); + + n_parts = ntohl(*xdr++); + toklen -= 4; + if (n_parts <= 0 || n_parts > AFSTOKEN_K5_COMPONENTS_MAX) + return -EINVAL; + princ->n_name_parts = n_parts; + + if (toklen <= (n_parts + 1) * 4) + return -EINVAL; + + princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL); + if (!princ->name_parts) + return -ENOMEM; + + for (loop = 0; loop < n_parts; loop++) { + if (toklen < 4) + return -EINVAL; + tmp = ntohl(*xdr++); + toklen -= 4; + if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX) + return -EINVAL; + if (tmp > toklen) + return -EINVAL; + princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL); + if (!princ->name_parts[loop]) + return -ENOMEM; + memcpy(princ->name_parts[loop], xdr, tmp); + princ->name_parts[loop][tmp] = 0; + tmp = (tmp + 3) & ~3; + toklen -= tmp; + xdr += tmp >> 2; + } + + if (toklen < 4) + return -EINVAL; + tmp = ntohl(*xdr++); + toklen -= 4; + if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX) + return -EINVAL; + if (tmp > toklen) + return -EINVAL; + princ->realm = kmalloc(tmp + 1, GFP_KERNEL); + if (!princ->realm) + return -ENOMEM; + memcpy(princ->realm, xdr, tmp); + princ->realm[tmp] = 0; + tmp = (tmp + 3) & ~3; + toklen -= tmp; + xdr += tmp >> 2; + + _debug("%s/...@%s", princ->name_parts[0], princ->realm); + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract a piece of krb5 tagged data + */ +static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, + size_t max_data_size, + const __be32 **_xdr, + unsigned int *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned int toklen = *_toklen, len; + + /* there must be at least one tag and one length word */ + if (toklen <= 8) + return -EINVAL; + + _enter(",%zu,{%x,%x},%u", + max_data_size, ntohl(xdr[0]), ntohl(xdr[1]), toklen); + + td->tag = ntohl(*xdr++); + len = ntohl(*xdr++); + toklen -= 8; + if (len > max_data_size) + return -EINVAL; + td->data_len = len; + + if (len > 0) { + td->data = kmemdup(xdr, len, GFP_KERNEL); + if (!td->data) + return -ENOMEM; + len = (len + 3) & ~3; + toklen -= len; + xdr += len >> 2; + } + + _debug("tag %x len %x", td->tag, td->data_len); + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract an array of tagged data + */ +static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, + u8 *_n_elem, + u8 max_n_elem, + size_t max_elem_size, + const __be32 **_xdr, + unsigned int *_toklen) +{ + struct krb5_tagged_data *td; + const __be32 *xdr = *_xdr; + unsigned int toklen = *_toklen, n_elem, loop; + int ret; + + /* there must be at least one count */ + if (toklen < 4) + return -EINVAL; + + _enter(",,%u,%zu,{%x},%u", + max_n_elem, max_elem_size, ntohl(xdr[0]), toklen); + + n_elem = ntohl(*xdr++); + toklen -= 4; + if (n_elem > max_n_elem) + return -EINVAL; + *_n_elem = n_elem; + if (n_elem > 0) { + if (toklen <= (n_elem + 1) * 4) + return -EINVAL; + + _debug("n_elem %d", n_elem); + + td = kcalloc(n_elem, sizeof(struct krb5_tagged_data), + GFP_KERNEL); + if (!td) + return -ENOMEM; + *_td = td; + + for (loop = 0; loop < n_elem; loop++) { + ret = rxrpc_krb5_decode_tagged_data(&td[loop], + max_elem_size, + &xdr, &toklen); + if (ret < 0) + return ret; + } + } + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract a krb5 ticket + */ +static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, + const __be32 **_xdr, unsigned int *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned int toklen = *_toklen, len; + + /* there must be at least one length word */ + if (toklen <= 4) + return -EINVAL; + + _enter(",{%x},%u", ntohl(xdr[0]), toklen); + + len = ntohl(*xdr++); + toklen -= 4; + if (len > AFSTOKEN_K5_TIX_MAX) + return -EINVAL; + *_tktlen = len; + + _debug("ticket len %u", len); + + if (len > 0) { + *_ticket = kmemdup(xdr, len, GFP_KERNEL); + if (!*_ticket) + return -ENOMEM; + len = (len + 3) & ~3; + toklen -= len; + xdr += len >> 2; + } + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * parse an RxK5 type XDR format token + * - the caller guarantees we have at least 4 words + */ +static int rxrpc_preparse_xdr_rxk5(struct key_preparsed_payload *prep, + size_t datalen, + const __be32 *xdr, unsigned int toklen) +{ + struct rxrpc_key_token *token, **pptoken; + struct rxk5_key *rxk5; + const __be32 *end_xdr = xdr + (toklen >> 2); + int ret; + + _enter(",{%x,%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + toklen); + + /* reserve some payload space for this subkey - the length of the token + * is a reasonable approximation */ + prep->quotalen = datalen + toklen; + + token = kzalloc(sizeof(*token), GFP_KERNEL); + if (!token) + return -ENOMEM; + + rxk5 = kzalloc(sizeof(*rxk5), GFP_KERNEL); + if (!rxk5) { + kfree(token); + return -ENOMEM; + } + + token->security_index = RXRPC_SECURITY_RXK5; + token->k5 = rxk5; + + /* extract the principals */ + ret = rxrpc_krb5_decode_principal(&rxk5->client, &xdr, &toklen); + if (ret < 0) + goto error; + ret = rxrpc_krb5_decode_principal(&rxk5->server, &xdr, &toklen); + if (ret < 0) + goto error; + + /* extract the session key and the encoding type (the tag field -> + * ENCTYPE_xxx) */ + ret = rxrpc_krb5_decode_tagged_data(&rxk5->session, AFSTOKEN_DATA_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + if (toklen < 4 * 8 + 2 * 4) + goto inval; + rxk5->authtime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->starttime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->endtime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->renew_till = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->is_skey = ntohl(*xdr++); + rxk5->flags = ntohl(*xdr++); + toklen -= 4 * 8 + 2 * 4; + + _debug("times: a=%llx s=%llx e=%llx rt=%llx", + rxk5->authtime, rxk5->starttime, rxk5->endtime, + rxk5->renew_till); + _debug("is_skey=%x flags=%x", rxk5->is_skey, rxk5->flags); + + /* extract the permitted client addresses */ + ret = rxrpc_krb5_decode_tagged_array(&rxk5->addresses, + &rxk5->n_addresses, + AFSTOKEN_K5_ADDRESSES_MAX, + AFSTOKEN_DATA_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + /* extract the tickets */ + ret = rxrpc_krb5_decode_ticket(&rxk5->ticket, &rxk5->ticket_len, + &xdr, &toklen); + if (ret < 0) + goto error; + ret = rxrpc_krb5_decode_ticket(&rxk5->ticket2, &rxk5->ticket2_len, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + /* extract the typed auth data */ + ret = rxrpc_krb5_decode_tagged_array(&rxk5->authdata, + &rxk5->n_authdata, + AFSTOKEN_K5_AUTHDATA_MAX, + AFSTOKEN_BDATALN_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + if (toklen != 0) + goto inval; + + /* attach the payload */ + for (pptoken = (struct rxrpc_key_token **)&prep->payload.data[0]; + *pptoken; + pptoken = &(*pptoken)->next) + continue; + *pptoken = token; + if (token->kad->expiry < prep->expiry) + prep->expiry = token->kad->expiry; + + _leave(" = 0"); + return 0; + +inval: + ret = -EINVAL; +error: + rxrpc_rxk5_free(rxk5); + kfree(token); + _leave(" = %d", ret); + return ret; +} + +/* + * attempt to parse the data as the XDR format + * - the caller guarantees we have more than 7 words + */ +static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) +{ + const __be32 *xdr = prep->data, *token; + const char *cp; + unsigned int len, tmp, loop, ntoken, toklen, sec_ix; + size_t datalen = prep->datalen; + int ret; + + _enter(",{%x,%x,%x,%x},%zu", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + prep->datalen); + + if (datalen > AFSTOKEN_LENGTH_MAX) + goto not_xdr; + + /* XDR is an array of __be32's */ + if (datalen & 3) + goto not_xdr; + + /* the flags should be 0 (the setpag bit must be handled by + * userspace) */ + if (ntohl(*xdr++) != 0) + goto not_xdr; + datalen -= 4; + + /* check the cell name */ + len = ntohl(*xdr++); + if (len < 1 || len > AFSTOKEN_CELL_MAX) + goto not_xdr; + datalen -= 4; + tmp = (len + 3) & ~3; + if (tmp > datalen) + goto not_xdr; + + cp = (const char *) xdr; + for (loop = 0; loop < len; loop++) + if (!isprint(cp[loop])) + goto not_xdr; + if (len < tmp) + for (; loop < tmp; loop++) + if (cp[loop]) + goto not_xdr; + _debug("cellname: [%u/%u] '%*.*s'", + len, tmp, len, len, (const char *) xdr); + datalen -= tmp; + xdr += tmp >> 2; + + /* get the token count */ + if (datalen < 12) + goto not_xdr; + ntoken = ntohl(*xdr++); + datalen -= 4; + _debug("ntoken: %x", ntoken); + if (ntoken < 1 || ntoken > AFSTOKEN_MAX) + goto not_xdr; + + /* check each token wrapper */ + token = xdr; + loop = ntoken; + do { + if (datalen < 8) + goto not_xdr; + toklen = ntohl(*xdr++); + sec_ix = ntohl(*xdr); + datalen -= 4; + _debug("token: [%x/%zx] %x", toklen, datalen, sec_ix); + if (toklen < 20 || toklen > datalen) + goto not_xdr; + datalen -= (toklen + 3) & ~3; + xdr += (toklen + 3) >> 2; + + } while (--loop > 0); + + _debug("remainder: %zu", datalen); + if (datalen != 0) + goto not_xdr; + + /* okay: we're going to assume it's valid XDR format + * - we ignore the cellname, relying on the key to be correctly named + */ + do { + xdr = token; + toklen = ntohl(*xdr++); + token = xdr + ((toklen + 3) >> 2); + sec_ix = ntohl(*xdr++); + toklen -= 4; + + _debug("TOKEN type=%u [%p-%p]", sec_ix, xdr, token); + + switch (sec_ix) { + case RXRPC_SECURITY_RXKAD: + ret = rxrpc_preparse_xdr_rxkad(prep, datalen, xdr, toklen); + if (ret != 0) + goto error; + break; + + case RXRPC_SECURITY_RXK5: + ret = rxrpc_preparse_xdr_rxk5(prep, datalen, xdr, toklen); + if (ret != 0) + goto error; + break; + + default: + ret = -EPROTONOSUPPORT; + goto error; + } + + } while (--ntoken > 0); + + _leave(" = 0"); + return 0; + +not_xdr: + _leave(" = -EPROTO"); + return -EPROTO; +error: + _leave(" = %d", ret); + return ret; +} + +/* + * Preparse an rxrpc defined key. + * + * Data should be of the form: + * OFFSET LEN CONTENT + * 0 4 key interface version number + * 4 2 security index (type) + * 6 2 ticket length + * 8 4 key expiry time (time_t) + * 12 4 kvno + * 16 8 session key + * 24 [len] ticket + * + * if no data is provided, then a no-security key is made + */ +static int rxrpc_preparse(struct key_preparsed_payload *prep) +{ + const struct rxrpc_key_data_v1 *v1; + struct rxrpc_key_token *token, **pp; + size_t plen; + u32 kver; + int ret; + + _enter("%zu", prep->datalen); + + /* handle a no-security key */ + if (!prep->data && prep->datalen == 0) + return 0; + + /* determine if the XDR payload format is being used */ + if (prep->datalen > 7 * 4) { + ret = rxrpc_preparse_xdr(prep); + if (ret != -EPROTO) + return ret; + } + + /* get the key interface version number */ + ret = -EINVAL; + if (prep->datalen <= 4 || !prep->data) + goto error; + memcpy(&kver, prep->data, sizeof(kver)); + prep->data += sizeof(kver); + prep->datalen -= sizeof(kver); + + _debug("KEY I/F VERSION: %u", kver); + + ret = -EKEYREJECTED; + if (kver != 1) + goto error; + + /* deal with a version 1 key */ + ret = -EINVAL; + if (prep->datalen < sizeof(*v1)) + goto error; + + v1 = prep->data; + if (prep->datalen != sizeof(*v1) + v1->ticket_length) + goto error; + + _debug("SCIX: %u", v1->security_index); + _debug("TLEN: %u", v1->ticket_length); + _debug("EXPY: %x", v1->expiry); + _debug("KVNO: %u", v1->kvno); + _debug("SKEY: %02x%02x%02x%02x%02x%02x%02x%02x", + v1->session_key[0], v1->session_key[1], + v1->session_key[2], v1->session_key[3], + v1->session_key[4], v1->session_key[5], + v1->session_key[6], v1->session_key[7]); + if (v1->ticket_length >= 8) + _debug("TCKT: %02x%02x%02x%02x%02x%02x%02x%02x", + v1->ticket[0], v1->ticket[1], + v1->ticket[2], v1->ticket[3], + v1->ticket[4], v1->ticket[5], + v1->ticket[6], v1->ticket[7]); + + ret = -EPROTONOSUPPORT; + if (v1->security_index != RXRPC_SECURITY_RXKAD) + goto error; + + plen = sizeof(*token->kad) + v1->ticket_length; + prep->quotalen = plen + sizeof(*token); + + ret = -ENOMEM; + token = kzalloc(sizeof(*token), GFP_KERNEL); + if (!token) + goto error; + token->kad = kzalloc(plen, GFP_KERNEL); + if (!token->kad) + goto error_free; + + token->security_index = RXRPC_SECURITY_RXKAD; + token->kad->ticket_len = v1->ticket_length; + token->kad->expiry = v1->expiry; + token->kad->kvno = v1->kvno; + memcpy(&token->kad->session_key, &v1->session_key, 8); + memcpy(&token->kad->ticket, v1->ticket, v1->ticket_length); + + /* count the number of tokens attached */ + prep->payload.data[1] = (void *)((unsigned long)prep->payload.data[1] + 1); + + /* attach the data */ + pp = (struct rxrpc_key_token **)&prep->payload.data[0]; + while (*pp) + pp = &(*pp)->next; + *pp = token; + if (token->kad->expiry < prep->expiry) + prep->expiry = token->kad->expiry; + token = NULL; + ret = 0; + +error_free: + kfree(token); +error: + return ret; +} + +/* + * Free token list. + */ +static void rxrpc_free_token_list(struct rxrpc_key_token *token) +{ + struct rxrpc_key_token *next; + + for (; token; token = next) { + next = token->next; + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + kfree(token->kad); + break; + case RXRPC_SECURITY_RXK5: + if (token->k5) + rxrpc_rxk5_free(token->k5); + break; + default: + pr_err("Unknown token type %x on rxrpc key\n", + token->security_index); + BUG(); + } + + kfree(token); + } +} + +/* + * Clean up preparse data. + */ +static void rxrpc_free_preparse(struct key_preparsed_payload *prep) +{ + rxrpc_free_token_list(prep->payload.data[0]); +} + +/* + * Preparse a server secret key. + * + * The data should be the 8-byte secret key. + */ +static int rxrpc_preparse_s(struct key_preparsed_payload *prep) +{ + struct crypto_skcipher *ci; + + _enter("%zu", prep->datalen); + + if (prep->datalen != 8) + return -EINVAL; + + memcpy(&prep->payload.data[2], prep->data, 8); + + ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(ci)) { + _leave(" = %ld", PTR_ERR(ci)); + return PTR_ERR(ci); + } + + if (crypto_skcipher_setkey(ci, prep->data, 8) < 0) + BUG(); + + prep->payload.data[0] = ci; + _leave(" = 0"); + return 0; +} + +/* + * Clean up preparse data. + */ +static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep) +{ + if (prep->payload.data[0]) + crypto_free_skcipher(prep->payload.data[0]); +} + +/* + * dispose of the data dangling from the corpse of a rxrpc key + */ +static void rxrpc_destroy(struct key *key) +{ + rxrpc_free_token_list(key->payload.data[0]); +} + +/* + * dispose of the data dangling from the corpse of a rxrpc key + */ +static void rxrpc_destroy_s(struct key *key) +{ + if (key->payload.data[0]) { + crypto_free_skcipher(key->payload.data[0]); + key->payload.data[0] = NULL; + } +} + +/* + * describe the rxrpc key + */ +static void rxrpc_describe(const struct key *key, struct seq_file *m) +{ + seq_puts(m, key->description); +} + +/* + * grab the security key for a socket + */ +int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen) +{ + struct key *key; + char *description; + + _enter(""); + + if (optlen <= 0 || optlen > PAGE_SIZE - 1) + return -EINVAL; + + description = memdup_user_nul(optval, optlen); + if (IS_ERR(description)) + return PTR_ERR(description); + + key = request_key(&key_type_rxrpc, description, NULL); + if (IS_ERR(key)) { + kfree(description); + _leave(" = %ld", PTR_ERR(key)); + return PTR_ERR(key); + } + + rx->key = key; + kfree(description); + _leave(" = 0 [key %x]", key->serial); + return 0; +} + +/* + * grab the security keyring for a server socket + */ +int rxrpc_server_keyring(struct rxrpc_sock *rx, char __user *optval, + int optlen) +{ + struct key *key; + char *description; + + _enter(""); + + if (optlen <= 0 || optlen > PAGE_SIZE - 1) + return -EINVAL; + + description = memdup_user_nul(optval, optlen); + if (IS_ERR(description)) + return PTR_ERR(description); + + key = request_key(&key_type_keyring, description, NULL); + if (IS_ERR(key)) { + kfree(description); + _leave(" = %ld", PTR_ERR(key)); + return PTR_ERR(key); + } + + rx->securities = key; + kfree(description); + _leave(" = 0 [key %x]", key->serial); + return 0; +} + +/* + * generate a server data key + */ +int rxrpc_get_server_data_key(struct rxrpc_connection *conn, + const void *session_key, + time_t expiry, + u32 kvno) +{ + const struct cred *cred = current_cred(); + struct key *key; + int ret; + + struct { + u32 kver; + struct rxrpc_key_data_v1 v1; + } data; + + _enter(""); + + key = key_alloc(&key_type_rxrpc, "x", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, 0, + KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(key)) { + _leave(" = -ENOMEM [alloc %ld]", PTR_ERR(key)); + return -ENOMEM; + } + + _debug("key %d", key_serial(key)); + + data.kver = 1; + data.v1.security_index = RXRPC_SECURITY_RXKAD; + data.v1.ticket_length = 0; + data.v1.expiry = expiry; + data.v1.kvno = 0; + + memcpy(&data.v1.session_key, session_key, sizeof(data.v1.session_key)); + + ret = key_instantiate_and_link(key, &data, sizeof(data), NULL, NULL); + if (ret < 0) + goto error; + + conn->params.key = key; + _leave(" = 0 [%d]", key_serial(key)); + return 0; + +error: + key_revoke(key); + key_put(key); + _leave(" = -ENOMEM [ins %d]", ret); + return -ENOMEM; +} +EXPORT_SYMBOL(rxrpc_get_server_data_key); + +/** + * rxrpc_get_null_key - Generate a null RxRPC key + * @keyname: The name to give the key. + * + * Generate a null RxRPC key that can be used to indicate anonymous security is + * required for a particular domain. + */ +struct key *rxrpc_get_null_key(const char *keyname) +{ + const struct cred *cred = current_cred(); + struct key *key; + int ret; + + key = key_alloc(&key_type_rxrpc, keyname, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, + KEY_POS_SEARCH, KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(key)) + return key; + + ret = key_instantiate_and_link(key, NULL, 0, NULL, NULL); + if (ret < 0) { + key_revoke(key); + key_put(key); + return ERR_PTR(ret); + } + + return key; +} +EXPORT_SYMBOL(rxrpc_get_null_key); + +/* + * read the contents of an rxrpc key + * - this returns the result in XDR form + */ +static long rxrpc_read(const struct key *key, + char __user *buffer, size_t buflen) +{ + const struct rxrpc_key_token *token; + const struct krb5_principal *princ; + size_t size; + __be32 __user *xdr, *oldxdr; + u32 cnlen, toksize, ntoks, tok, zero; + u16 toksizes[AFSTOKEN_MAX]; + int loop; + + _enter(""); + + /* we don't know what form we should return non-AFS keys in */ + if (memcmp(key->description, "afs@", 4) != 0) + return -EOPNOTSUPP; + cnlen = strlen(key->description + 4); + +#define RND(X) (((X) + 3) & ~3) + + /* AFS keys we return in XDR form, so we need to work out the size of + * the XDR */ + size = 2 * 4; /* flags, cellname len */ + size += RND(cnlen); /* cellname */ + size += 1 * 4; /* token count */ + + ntoks = 0; + for (token = key->payload.data[0]; token; token = token->next) { + toksize = 4; /* sec index */ + + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + toksize += 8 * 4; /* viceid, kvno, key*2, begin, + * end, primary, tktlen */ + toksize += RND(token->kad->ticket_len); + break; + + case RXRPC_SECURITY_RXK5: + princ = &token->k5->client; + toksize += 4 + princ->n_name_parts * 4; + for (loop = 0; loop < princ->n_name_parts; loop++) + toksize += RND(strlen(princ->name_parts[loop])); + toksize += 4 + RND(strlen(princ->realm)); + + princ = &token->k5->server; + toksize += 4 + princ->n_name_parts * 4; + for (loop = 0; loop < princ->n_name_parts; loop++) + toksize += RND(strlen(princ->name_parts[loop])); + toksize += 4 + RND(strlen(princ->realm)); + + toksize += 8 + RND(token->k5->session.data_len); + + toksize += 4 * 8 + 2 * 4; + + toksize += 4 + token->k5->n_addresses * 8; + for (loop = 0; loop < token->k5->n_addresses; loop++) + toksize += RND(token->k5->addresses[loop].data_len); + + toksize += 4 + RND(token->k5->ticket_len); + toksize += 4 + RND(token->k5->ticket2_len); + + toksize += 4 + token->k5->n_authdata * 8; + for (loop = 0; loop < token->k5->n_authdata; loop++) + toksize += RND(token->k5->authdata[loop].data_len); + break; + + default: /* we have a ticket we can't encode */ + BUG(); + continue; + } + + _debug("token[%u]: toksize=%u", ntoks, toksize); + ASSERTCMP(toksize, <=, AFSTOKEN_LENGTH_MAX); + + toksizes[ntoks++] = toksize; + size += toksize + 4; /* each token has a length word */ + } + +#undef RND + + if (!buffer || buflen < size) + return size; + + xdr = (__be32 __user *) buffer; + zero = 0; +#define ENCODE(x) \ + do { \ + __be32 y = htonl(x); \ + if (put_user(y, xdr++) < 0) \ + goto fault; \ + } while(0) +#define ENCODE_DATA(l, s) \ + do { \ + u32 _l = (l); \ + ENCODE(l); \ + if (copy_to_user(xdr, (s), _l) != 0) \ + goto fault; \ + if (_l & 3 && \ + copy_to_user((u8 __user *)xdr + _l, &zero, 4 - (_l & 3)) != 0) \ + goto fault; \ + xdr += (_l + 3) >> 2; \ + } while(0) +#define ENCODE64(x) \ + do { \ + __be64 y = cpu_to_be64(x); \ + if (copy_to_user(xdr, &y, 8) != 0) \ + goto fault; \ + xdr += 8 >> 2; \ + } while(0) +#define ENCODE_STR(s) \ + do { \ + const char *_s = (s); \ + ENCODE_DATA(strlen(_s), _s); \ + } while(0) + + ENCODE(0); /* flags */ + ENCODE_DATA(cnlen, key->description + 4); /* cellname */ + ENCODE(ntoks); + + tok = 0; + for (token = key->payload.data[0]; token; token = token->next) { + toksize = toksizes[tok++]; + ENCODE(toksize); + oldxdr = xdr; + ENCODE(token->security_index); + + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + ENCODE(token->kad->vice_id); + ENCODE(token->kad->kvno); + ENCODE_DATA(8, token->kad->session_key); + ENCODE(token->kad->start); + ENCODE(token->kad->expiry); + ENCODE(token->kad->primary_flag); + ENCODE_DATA(token->kad->ticket_len, token->kad->ticket); + break; + + case RXRPC_SECURITY_RXK5: + princ = &token->k5->client; + ENCODE(princ->n_name_parts); + for (loop = 0; loop < princ->n_name_parts; loop++) + ENCODE_STR(princ->name_parts[loop]); + ENCODE_STR(princ->realm); + + princ = &token->k5->server; + ENCODE(princ->n_name_parts); + for (loop = 0; loop < princ->n_name_parts; loop++) + ENCODE_STR(princ->name_parts[loop]); + ENCODE_STR(princ->realm); + + ENCODE(token->k5->session.tag); + ENCODE_DATA(token->k5->session.data_len, + token->k5->session.data); + + ENCODE64(token->k5->authtime); + ENCODE64(token->k5->starttime); + ENCODE64(token->k5->endtime); + ENCODE64(token->k5->renew_till); + ENCODE(token->k5->is_skey); + ENCODE(token->k5->flags); + + ENCODE(token->k5->n_addresses); + for (loop = 0; loop < token->k5->n_addresses; loop++) { + ENCODE(token->k5->addresses[loop].tag); + ENCODE_DATA(token->k5->addresses[loop].data_len, + token->k5->addresses[loop].data); + } + + ENCODE_DATA(token->k5->ticket_len, token->k5->ticket); + ENCODE_DATA(token->k5->ticket2_len, token->k5->ticket2); + + ENCODE(token->k5->n_authdata); + for (loop = 0; loop < token->k5->n_authdata; loop++) { + ENCODE(token->k5->authdata[loop].tag); + ENCODE_DATA(token->k5->authdata[loop].data_len, + token->k5->authdata[loop].data); + } + break; + + default: + BUG(); + break; + } + + ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==, + toksize); + } + +#undef ENCODE_STR +#undef ENCODE_DATA +#undef ENCODE64 +#undef ENCODE + + ASSERTCMP(tok, ==, ntoks); + ASSERTCMP((char __user *) xdr - buffer, ==, size); + _leave(" = %zu", size); + return size; + +fault: + _leave(" = -EFAULT"); + return -EFAULT; +} diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c new file mode 100644 index 000000000..31a3f86ef --- /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 000000000..a753796fb --- /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 1afe9876e..bdc5e42fe 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/output.c b/net/rxrpc/output.c new file mode 100644 index 000000000..f4bda06b7 --- /dev/null +++ b/net/rxrpc/output.c @@ -0,0 +1,721 @@ +/* RxRPC packet transmission + * + * 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/net.h> +#include <linux/gfp.h> +#include <linux/skbuff.h> +#include <linux/circ_buf.h> +#include <linux/export.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * Time till packet resend (in jiffies). + */ +unsigned int rxrpc_resend_timeout = 4 * HZ; + +static int rxrpc_send_data(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct msghdr *msg, size_t len); + +/* + * extract control messages from the sendmsg() control buffer + */ +static int rxrpc_sendmsg_cmsg(struct msghdr *msg, + unsigned long *user_call_ID, + enum rxrpc_command *command, + u32 *abort_code, + bool *_exclusive) +{ + struct cmsghdr *cmsg; + bool got_user_ID = false; + int len; + + *command = RXRPC_CMD_SEND_DATA; + + if (msg->msg_controllen == 0) + return -EINVAL; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + len = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + _debug("CMSG %d, %d, %d", + cmsg->cmsg_level, cmsg->cmsg_type, len); + + if (cmsg->cmsg_level != SOL_RXRPC) + continue; + + switch (cmsg->cmsg_type) { + case RXRPC_USER_CALL_ID: + if (msg->msg_flags & MSG_CMSG_COMPAT) { + if (len != sizeof(u32)) + return -EINVAL; + *user_call_ID = *(u32 *) CMSG_DATA(cmsg); + } else { + if (len != sizeof(unsigned long)) + return -EINVAL; + *user_call_ID = *(unsigned long *) + CMSG_DATA(cmsg); + } + _debug("User Call ID %lx", *user_call_ID); + got_user_ID = true; + break; + + case RXRPC_ABORT: + if (*command != RXRPC_CMD_SEND_DATA) + return -EINVAL; + *command = RXRPC_CMD_SEND_ABORT; + if (len != sizeof(*abort_code)) + return -EINVAL; + *abort_code = *(unsigned int *) CMSG_DATA(cmsg); + _debug("Abort %x", *abort_code); + if (*abort_code == 0) + return -EINVAL; + break; + + case RXRPC_ACCEPT: + if (*command != RXRPC_CMD_SEND_DATA) + return -EINVAL; + *command = RXRPC_CMD_ACCEPT; + if (len != 0) + return -EINVAL; + 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; +} + +/* + * abort a call, sending an ABORT packet to the peer + */ +static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) +{ + write_lock_bh(&call->state_lock); + + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->local_abort = abort_code; + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + del_timer_sync(&call->resend_timer); + del_timer_sync(&call->ack_timer); + clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_EV_ACK, &call->events); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + rxrpc_queue_call(call); + } + + write_unlock_bh(&call->state_lock); +} + +/* + * 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_do_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; + bool exclusive = false; + u32 abort_code = 0; + int ret; + + _enter(""); + + ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code, + &exclusive); + if (ret < 0) + return ret; + + 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_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", + call->debug_id, call->user_call_ID, call->state, call->conn); + + if (call->state >= RXRPC_CALL_COMPLETE) { + /* it's too late for this call */ + 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->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); + } + + rxrpc_put_call(call); + _leave(" = %d", ret); + return ret; +} + +/** + * rxrpc_kernel_send_data - Allow a kernel service to send data on a call + * @call: The call to send data through + * @msg: The data to send + * @len: The amount of data to send + * + * Allow a kernel service to send data on a call. The call must be in an state + * appropriate to sending data. No control data should be supplied in @msg, + * nor should an address be supplied. MSG_MORE should be flagged if there's + * more data to come, otherwise this data will end the transmission phase. + */ +int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, + size_t len) +{ + int ret; + + _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]); + + ASSERTCMP(msg->msg_name, ==, NULL); + ASSERTCMP(msg->msg_control, ==, NULL); + + lock_sock(&call->socket->sk); + + _debug("CALL %d USR %lx ST %d on CONN %p", + call->debug_id, call->user_call_ID, call->state, call->conn); + + if (call->state >= RXRPC_CALL_COMPLETE) { + ret = -ESHUTDOWN; /* it's too late for this call */ + } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && + call->state != RXRPC_CALL_SERVER_ACK_REQUEST && + call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + ret = -EPROTO; /* request phase complete for this client call */ + } else { + ret = rxrpc_send_data(call->socket, call, msg, len); + } + + release_sock(&call->socket->sk); + _leave(" = %d", ret); + return ret; +} + +EXPORT_SYMBOL(rxrpc_kernel_send_data); + +/** + * rxrpc_kernel_abort_call - Allow a kernel service to abort a call + * @call: The call to be aborted + * @abort_code: The abort code to stick into the ABORT packet + * + * Allow a kernel service to abort a call, if it's still in an abortable state. + */ +void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code) +{ + _enter("{%d},%d", call->debug_id, abort_code); + + lock_sock(&call->socket->sk); + + _debug("CALL %d USR %lx ST %d on CONN %p", + call->debug_id, call->user_call_ID, call->state, call->conn); + + if (call->state < RXRPC_CALL_COMPLETE) + rxrpc_send_abort(call, abort_code); + + release_sock(&call->socket->sk); + _leave(""); +} + +EXPORT_SYMBOL(rxrpc_kernel_abort_call); + +/* + * send a packet through the transport endpoint + */ +int rxrpc_send_data_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + struct kvec iov[1]; + struct msghdr msg; + int ret, opt; + + _enter(",{%d}", skb->len); + + iov[0].iov_base = skb->head; + iov[0].iov_len = skb->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; + + /* 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) < 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(conn->params.local->socket, &msg, iov, 1, + iov[0].iov_len); + + up_read(&conn->params.local->defrag_sem); + if (ret == -EMSGSIZE) + goto send_fragmentable; + + _leave(" = %d [%u]", ret, conn->params.peer->maxdata); + return ret; + } + +send_fragmentable: + /* attempt to send this message with fragmentation enabled */ + _debug("send fragment"); + + 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(&conn->params.local->defrag_sem); + _leave(" = %d [frag %u]", ret, conn->params.peer->maxdata); + return ret; +} + +/* + * wait for space to appear in the transmit/ACK window + * - caller holds the socket locked + */ +static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, + struct rxrpc_call *call, + long *timeo) +{ + DECLARE_WAITQUEUE(myself, current); + int ret; + + _enter(",{%d},%ld", + CIRC_SPACE(call->acks_head, ACCESS_ONCE(call->acks_tail), + call->acks_winsz), + *timeo); + + add_wait_queue(&call->tx_waitq, &myself); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + ret = 0; + if (CIRC_SPACE(call->acks_head, ACCESS_ONCE(call->acks_tail), + call->acks_winsz) > 0) + break; + if (signal_pending(current)) { + ret = sock_intr_errno(*timeo); + break; + } + + release_sock(&rx->sk); + *timeo = schedule_timeout(*timeo); + lock_sock(&rx->sk); + } + + remove_wait_queue(&call->tx_waitq, &myself); + set_current_state(TASK_RUNNING); + _leave(" = %d", ret); + return ret; +} + +/* + * attempt to schedule an instant Tx resend + */ +static inline void rxrpc_instant_resend(struct rxrpc_call *call) +{ + read_lock_bh(&call->state_lock); + if (try_to_del_timer_sync(&call->resend_timer) >= 0) { + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + if (call->state < RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) + rxrpc_queue_call(call); + } + read_unlock_bh(&call->state_lock); +} + +/* + * queue a packet for transmission, set the resend timer and attempt + * to send the packet immediately + */ +static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, + bool last) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + int ret; + + _net("queue skb %p [%d]", skb, call->acks_head); + + ASSERT(call->acks_window != NULL); + call->acks_window[call->acks_head] = (unsigned long) skb; + smp_wmb(); + call->acks_head = (call->acks_head + 1) & (call->acks_winsz - 1); + + if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { + _debug("________awaiting reply/ACK__________"); + write_lock_bh(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + break; + case RXRPC_CALL_SERVER_ACK_REQUEST: + call->state = RXRPC_CALL_SERVER_SEND_REPLY; + if (!last) + break; + case RXRPC_CALL_SERVER_SEND_REPLY: + call->state = RXRPC_CALL_SERVER_AWAIT_ACK; + break; + default: + break; + } + write_unlock_bh(&call->state_lock); + } + + _proto("Tx DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); + + sp->need_resend = false; + sp->resend_at = jiffies + rxrpc_resend_timeout; + if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) { + _debug("run timer"); + call->resend_timer.expires = sp->resend_at; + add_timer(&call->resend_timer); + } + + /* attempt to cancel the rx-ACK timer, deferring reply transmission if + * we're ACK'ing the request phase of an incoming call */ + ret = -EAGAIN; + 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_data_packet(call->conn, skb); + _net("sent skb %p", skb); + } else { + _debug("failed to delete ACK timer"); + } + + if (ret < 0) { + _debug("need instant resend %d", ret); + sp->need_resend = true; + rxrpc_instant_resend(call); + } + + _leave(""); +} + +/* + * Convert a host-endian header into a network-endian header. + */ +static void rxrpc_insert_header(struct sk_buff *skb) +{ + struct rxrpc_wire_header whdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.seq = htonl(sp->hdr.seq); + whdr.serial = htonl(sp->hdr.serial); + whdr.type = sp->hdr.type; + whdr.flags = sp->hdr.flags; + whdr.userStatus = sp->hdr.userStatus; + whdr.securityIndex = sp->hdr.securityIndex; + whdr._rsvd = htons(sp->hdr._rsvd); + whdr.serviceId = htons(sp->hdr.serviceId); + + memcpy(skb->head, &whdr, sizeof(whdr)); +} + +/* + * send data through a socket + * - must be called in process context + * - caller holds the socket locked + */ +static int rxrpc_send_data(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct msghdr *msg, size_t len) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + struct sock *sk = &rx->sk; + long timeo; + bool more; + int ret, copied; + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + /* this should be in poll */ + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + return -EPIPE; + + more = msg->msg_flags & MSG_MORE; + + skb = call->tx_pending; + call->tx_pending = NULL; + + copied = 0; + do { + if (!skb) { + size_t size, chunk, max, space; + + _debug("alloc"); + + if (CIRC_SPACE(call->acks_head, + ACCESS_ONCE(call->acks_tail), + call->acks_winsz) <= 0) { + ret = -EAGAIN; + if (msg->msg_flags & MSG_DONTWAIT) + goto maybe_error; + ret = rxrpc_wait_for_tx_window(rx, call, + &timeo); + if (ret < 0) + goto maybe_error; + } + + max = call->conn->params.peer->maxdata; + max -= call->conn->security_size; + max &= ~(call->conn->size_align - 1UL); + + chunk = max; + if (chunk > msg_data_left(msg) && !more) + chunk = msg_data_left(msg); + + space = chunk + call->conn->size_align; + space &= ~(call->conn->size_align - 1UL); + + size = space + call->conn->header_size; + + _debug("SIZE: %zu/%zu/%zu", chunk, space, size); + + /* create a buffer that we can retain until it's ACK'd */ + skb = sock_alloc_send_skb( + sk, size, msg->msg_flags & MSG_DONTWAIT, &ret); + if (!skb) + goto maybe_error; + + rxrpc_new_skb(skb); + + _debug("ALLOC SEND %p", skb); + + ASSERTCMP(skb->mark, ==, 0); + + _debug("HS: %u", call->conn->header_size); + skb_reserve(skb, call->conn->header_size); + skb->len += call->conn->header_size; + + sp = rxrpc_skb(skb); + sp->remain = chunk; + if (sp->remain > skb_tailroom(skb)) + sp->remain = skb_tailroom(skb); + + _net("skb: hr %d, tr %d, hl %d, rm %d", + skb_headroom(skb), + skb_tailroom(skb), + skb_headlen(skb), + sp->remain); + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + + _debug("append"); + sp = rxrpc_skb(skb); + + /* append next segment of data to the current buffer */ + if (msg_data_left(msg) > 0) { + int copy = skb_tailroom(skb); + ASSERTCMP(copy, >, 0); + if (copy > msg_data_left(msg)) + copy = msg_data_left(msg); + if (copy > sp->remain) + copy = sp->remain; + + _debug("add"); + ret = skb_add_data(skb, &msg->msg_iter, copy); + _debug("added"); + if (ret < 0) + goto efault; + sp->remain -= copy; + skb->mark += copy; + copied += copy; + } + + /* check for the far side aborting the call or a network error + * occurring */ + if (call->state > RXRPC_CALL_COMPLETE) + goto call_aborted; + + /* add the packet to the send queue if it's now full */ + if (sp->remain <= 0 || + (msg_data_left(msg) == 0 && !more)) { + struct rxrpc_connection *conn = call->conn; + uint32_t seq; + size_t pad; + + /* pad out if we're using security */ + if (conn->security_ix) { + pad = conn->security_size + skb->mark; + pad = conn->size_align - pad; + pad &= conn->size_align - 1; + _debug("pad %zu", pad); + if (pad) + memset(skb_put(skb, pad), 0, pad); + } + + seq = atomic_inc_return(&call->sequence); + + sp->hdr.epoch = conn->proto.epoch; + sp->hdr.cid = call->cid; + sp->hdr.callNumber = call->call_id; + sp->hdr.seq = seq; + sp->hdr.serial = atomic_inc_return(&conn->serial); + sp->hdr.type = RXRPC_PACKET_TYPE_DATA; + sp->hdr.userStatus = 0; + sp->hdr.securityIndex = conn->security_ix; + sp->hdr._rsvd = 0; + sp->hdr.serviceId = call->service_id; + + sp->hdr.flags = conn->out_clientflag; + if (msg_data_left(msg) == 0 && !more) + sp->hdr.flags |= RXRPC_LAST_PACKET; + else if (CIRC_SPACE(call->acks_head, + ACCESS_ONCE(call->acks_tail), + call->acks_winsz) > 1) + sp->hdr.flags |= RXRPC_MORE_PACKETS; + if (more && seq & 1) + sp->hdr.flags |= RXRPC_REQUEST_ACK; + + ret = conn->security->secure_packet( + call, skb, skb->mark, + skb->head + sizeof(struct rxrpc_wire_header)); + if (ret < 0) + goto out; + + rxrpc_insert_header(skb); + rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more); + skb = NULL; + } + } while (msg_data_left(msg) > 0); + +success: + ret = copied; +out: + call->tx_pending = skb; + _leave(" = %d", ret); + return ret; + +call_aborted: + rxrpc_free_skb(skb); + if (call->state == RXRPC_CALL_NETWORK_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); + return ret; + +maybe_error: + if (copied) + goto success; + goto out; + +efault: + ret = -EFAULT; + goto out; +} diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c new file mode 100644 index 000000000..8940674b5 --- /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 000000000..538e9831c --- /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/proc.c b/net/rxrpc/proc.c new file mode 100644 index 000000000..ced5f0744 --- /dev/null +++ b/net/rxrpc/proc.c @@ -0,0 +1,192 @@ +/* /proc/net/ support for AF_RXRPC + * + * 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 <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +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", +}; + +/* + * generate a list of extant and dead calls in /proc/net/rxrpc_calls + */ +static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos) +{ + read_lock(&rxrpc_call_lock); + return seq_list_start_head(&rxrpc_calls, *_pos); +} + +static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + return seq_list_next(v, &rxrpc_calls, pos); +} + +static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock(&rxrpc_call_lock); +} + +static int rxrpc_call_seq_show(struct seq_file *seq, void *v) +{ + struct rxrpc_connection *conn; + struct rxrpc_call *call; + char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; + + if (v == &rxrpc_calls) { + seq_puts(seq, + "Proto Local Remote " + " SvID ConnID CallID End Use State Abort " + " UserID\n"); + return 0; + } + + call = list_entry(v, struct rxrpc_call, link); + + sprintf(lbuff, "%pI4:%u", + &call->local->srx.transport.sin.sin_addr, + ntohs(call->local->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->service_id, + call->cid, + call->call_id, + call->in_clientflag ? "Svc" : "Clt", + atomic_read(&call->usage), + rxrpc_call_states[call->state], + call->remote_abort ?: call->local_abort, + call->user_call_ID); + + return 0; +} + +static const struct seq_operations rxrpc_call_seq_ops = { + .start = rxrpc_call_seq_start, + .next = rxrpc_call_seq_next, + .stop = rxrpc_call_seq_stop, + .show = rxrpc_call_seq_show, +}; + +static int rxrpc_call_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &rxrpc_call_seq_ops); +} + +const struct file_operations rxrpc_call_seq_fops = { + .owner = THIS_MODULE, + .open = rxrpc_call_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* + * generate a list of extant virtual connections in /proc/net/rxrpc_conns + */ +static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos) +{ + read_lock(&rxrpc_connection_lock); + return seq_list_start_head(&rxrpc_connections, *_pos); +} + +static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + return seq_list_next(v, &rxrpc_connections, pos); +} + +static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock(&rxrpc_connection_lock); +} + +static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) +{ + struct rxrpc_connection *conn; + 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 End Use State Key " + " Serial ISerial\n" + ); + return 0; + } + + conn = list_entry(v, struct rxrpc_connection, link); + + sprintf(lbuff, "%pI4:%u", + &conn->params.local->srx.transport.sin.sin_addr, + ntohs(conn->params.local->srx.transport.sin.sin_port)); + + sprintf(rbuff, "%pI4:%u", + &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 %s %3u" + " %s %08x %08x %08x\n", + lbuff, + rbuff, + 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->params.key), + atomic_read(&conn->serial), + atomic_read(&conn->hi_serial)); + + return 0; +} + +static const struct seq_operations rxrpc_connection_seq_ops = { + .start = rxrpc_connection_seq_start, + .next = rxrpc_connection_seq_next, + .stop = rxrpc_connection_seq_stop, + .show = rxrpc_connection_seq_show, +}; + + +static int rxrpc_connection_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &rxrpc_connection_seq_ops); +} + +const struct file_operations rxrpc_connection_seq_fops = { + .owner = THIS_MODULE, + .open = rxrpc_connection_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c new file mode 100644 index 000000000..9ed66d533 --- /dev/null +++ b/net/rxrpc/recvmsg.c @@ -0,0 +1,417 @@ +/* RxRPC recvmsg() implementation + * + * 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/net.h> +#include <linux/skbuff.h> +#include <linux/export.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * removal a call's user ID from the socket tree to make the user ID available + * again and so that it won't be seen again in association with that call + */ +void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call) +{ + _debug("RELEASE CALL %d", call->debug_id); + + if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { + write_lock_bh(&rx->call_lock); + rb_erase(&call->sock_node, &call->socket->calls); + clear_bit(RXRPC_CALL_HAS_USERID, &call->flags); + write_unlock_bh(&rx->call_lock); + } + + read_lock_bh(&call->state_lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) + rxrpc_queue_call(call); + read_unlock_bh(&call->state_lock); +} + +/* + * receive a message from an RxRPC socket + * - we need to be careful about two or more threads calling recvmsg + * simultaneously + */ +int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + struct rxrpc_skb_priv *sp; + struct rxrpc_call *call = NULL, *continue_call = NULL; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + struct sk_buff *skb; + long timeo; + int copy, ret, ullen, offset, copied = 0; + u32 abort_code; + + DEFINE_WAIT(wait); + + _enter(",,,%zu,%d", len, flags); + + if (flags & (MSG_OOB | MSG_TRUNC)) + return -EOPNOTSUPP; + + ullen = msg->msg_flags & MSG_CMSG_COMPAT ? 4 : sizeof(unsigned long); + + timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT); + msg->msg_flags |= MSG_MORE; + + lock_sock(&rx->sk); + + for (;;) { + /* return immediately if a client socket has no outstanding + * calls */ + if (RB_EMPTY_ROOT(&rx->calls)) { + if (copied) + goto out; + if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) { + release_sock(&rx->sk); + if (continue_call) + rxrpc_put_call(continue_call); + return -ENODATA; + } + } + + /* get the next message on the Rx queue */ + skb = skb_peek(&rx->sk.sk_receive_queue); + if (!skb) { + /* nothing remains on the queue */ + if (copied && + (flags & MSG_PEEK || timeo == 0)) + goto out; + + /* wait for a message to turn up */ + release_sock(&rx->sk); + prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait, + TASK_INTERRUPTIBLE); + ret = sock_error(&rx->sk); + if (ret) + goto wait_error; + + if (skb_queue_empty(&rx->sk.sk_receive_queue)) { + if (signal_pending(current)) + goto wait_interrupted; + timeo = schedule_timeout(timeo); + } + finish_wait(sk_sleep(&rx->sk), &wait); + lock_sock(&rx->sk); + continue; + } + + peek_next_packet: + sp = rxrpc_skb(skb); + call = sp->call; + ASSERT(call != NULL); + + _debug("next pkt %s", rxrpc_pkts[sp->hdr.type]); + + /* make sure we wait for the state to be updated in this call */ + spin_lock_bh(&call->lock); + spin_unlock_bh(&call->lock); + + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + _debug("packet from released call"); + if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) + BUG(); + rxrpc_free_skb(skb); + continue; + } + + /* determine whether to continue last data receive */ + if (continue_call) { + _debug("maybe cont"); + if (call != continue_call || + skb->mark != RXRPC_SKB_MARK_DATA) { + release_sock(&rx->sk); + rxrpc_put_call(continue_call); + _leave(" = %d [noncont]", copied); + return copied; + } + } + + rxrpc_get_call(call); + + /* copy the peer address and timestamp */ + if (!continue_call) { + if (msg->msg_name) { + size_t len = + sizeof(call->conn->params.peer->srx); + memcpy(msg->msg_name, + &call->conn->params.peer->srx, len); + msg->msg_namelen = len; + } + sock_recv_timestamp(msg, &rx->sk, skb); + } + + /* receive the message */ + if (skb->mark != RXRPC_SKB_MARK_DATA) + goto receive_non_data_message; + + _debug("recvmsg DATA #%u { %d, %d }", + sp->hdr.seq, skb->len, sp->offset); + + if (!continue_call) { + /* only set the control data once per recvmsg() */ + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + ullen, &call->user_call_ID); + if (ret < 0) + goto copy_error; + ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); + } + + ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); + ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); + call->rx_data_recv = sp->hdr.seq; + + ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); + + offset = sp->offset; + copy = skb->len - offset; + if (copy > len - copied) + copy = len - copied; + + ret = skb_copy_datagram_msg(skb, offset, msg, copy); + + if (ret < 0) + goto copy_error; + + /* handle piecemeal consumption of data packets */ + _debug("copied %d+%d", copy, copied); + + offset += copy; + copied += copy; + + if (!(flags & MSG_PEEK)) + sp->offset = offset; + + if (sp->offset < skb->len) { + _debug("buffer full"); + ASSERTCMP(copied, ==, len); + break; + } + + /* we transferred the whole data packet */ + if (!(flags & MSG_PEEK)) + rxrpc_kernel_data_consumed(call, skb); + + if (sp->hdr.flags & RXRPC_LAST_PACKET) { + _debug("last"); + if (rxrpc_conn_is_client(call->conn)) { + /* last byte of reply received */ + ret = copied; + goto terminal_message; + } + + /* last bit of request received */ + if (!(flags & MSG_PEEK)) { + _debug("eat packet"); + if (skb_dequeue(&rx->sk.sk_receive_queue) != + skb) + BUG(); + rxrpc_free_skb(skb); + } + msg->msg_flags &= ~MSG_MORE; + break; + } + + /* move on to the next data message */ + _debug("next"); + if (!continue_call) + continue_call = sp->call; + else + rxrpc_put_call(call); + call = NULL; + + if (flags & MSG_PEEK) { + _debug("peek next"); + skb = skb->next; + if (skb == (struct sk_buff *) &rx->sk.sk_receive_queue) + break; + goto peek_next_packet; + } + + _debug("eat packet"); + if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) + BUG(); + rxrpc_free_skb(skb); + } + + /* end of non-terminal data packet reception for the moment */ + _debug("end rcv data"); +out: + release_sock(&rx->sk); + if (call) + rxrpc_put_call(call); + if (continue_call) + rxrpc_put_call(continue_call); + _leave(" = %d [data]", copied); + return copied; + + /* handle non-DATA messages such as aborts, incoming connections and + * final ACKs */ +receive_non_data_message: + _debug("non-data"); + + if (skb->mark == RXRPC_SKB_MARK_NEW_CALL) { + _debug("RECV NEW CALL"); + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &abort_code); + if (ret < 0) + goto copy_error; + if (!(flags & MSG_PEEK)) { + if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) + BUG(); + rxrpc_free_skb(skb); + } + goto out; + } + + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + ullen, &call->user_call_ID); + if (ret < 0) + goto copy_error; + ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); + + switch (skb->mark) { + case RXRPC_SKB_MARK_DATA: + BUG(); + case RXRPC_SKB_MARK_FINAL_ACK: + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ACK, 0, &abort_code); + break; + case RXRPC_SKB_MARK_BUSY: + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_BUSY, 0, &abort_code); + break; + case RXRPC_SKB_MARK_REMOTE_ABORT: + abort_code = call->remote_abort; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); + break; + case RXRPC_SKB_MARK_LOCAL_ABORT: + abort_code = call->local_abort; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); + break; + case RXRPC_SKB_MARK_NET_ERROR: + _debug("RECV NET ERROR %d", sp->error); + abort_code = sp->error; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &abort_code); + break; + case RXRPC_SKB_MARK_LOCAL_ERROR: + _debug("RECV LOCAL ERROR %d", sp->error); + abort_code = sp->error; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, + &abort_code); + break; + default: + pr_err("Unknown packet mark %u\n", skb->mark); + BUG(); + break; + } + + if (ret < 0) + goto copy_error; + +terminal_message: + _debug("terminal"); + msg->msg_flags &= ~MSG_MORE; + msg->msg_flags |= MSG_EOR; + + if (!(flags & MSG_PEEK)) { + _net("free terminal skb %p", skb); + if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) + BUG(); + rxrpc_free_skb(skb); + rxrpc_remove_user_ID(rx, call); + } + + release_sock(&rx->sk); + rxrpc_put_call(call); + if (continue_call) + rxrpc_put_call(continue_call); + _leave(" = %d", ret); + return ret; + +copy_error: + _debug("copy error"); + release_sock(&rx->sk); + rxrpc_put_call(call); + if (continue_call) + rxrpc_put_call(continue_call); + _leave(" = %d", ret); + return ret; + +wait_interrupted: + ret = sock_intr_errno(timeo); +wait_error: + finish_wait(sk_sleep(&rx->sk), &wait); + if (continue_call) + rxrpc_put_call(continue_call); + if (copied) + copied = ret; + _leave(" = %d [waitfail %d]", copied, ret); + return copied; + +} + +/** + * rxrpc_kernel_is_data_last - Determine if data message is last one + * @skb: Message holding data + * + * Determine if data message is last one for the parent call. + */ +bool rxrpc_kernel_is_data_last(struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_DATA); + + return sp->hdr.flags & RXRPC_LAST_PACKET; +} + +EXPORT_SYMBOL(rxrpc_kernel_is_data_last); + +/** + * rxrpc_kernel_get_abort_code - Get the abort code from an RxRPC abort message + * @skb: Message indicating an abort + * + * Get the abort code from an RxRPC abort message. + */ +u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + switch (skb->mark) { + case RXRPC_SKB_MARK_REMOTE_ABORT: + return sp->call->remote_abort; + case RXRPC_SKB_MARK_LOCAL_ABORT: + return sp->call->local_abort; + default: + BUG(); + } +} + +EXPORT_SYMBOL(rxrpc_kernel_get_abort_code); + +/** + * rxrpc_kernel_get_error - Get the error number from an RxRPC error message + * @skb: Message indicating an error + * + * Get the error number from an RxRPC error message. + */ +int rxrpc_kernel_get_error_number(struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + return sp->error; +} + +EXPORT_SYMBOL(rxrpc_kernel_get_error_number); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index bab56ed64..63afa9e9c 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/security.c b/net/rxrpc/security.c new file mode 100644 index 000000000..814d285ff --- /dev/null +++ b/net/rxrpc/security.c @@ -0,0 +1,168 @@ +/* RxRPC security handling + * + * 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/crypto.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <keys/rxrpc-type.h> +#include "ar-internal.h" + +static LIST_HEAD(rxrpc_security_methods); +static DECLARE_RWSEM(rxrpc_security_sem); + +static const struct rxrpc_security *rxrpc_security_types[] = { + [RXRPC_SECURITY_NONE] = &rxrpc_no_security, +#ifdef CONFIG_RXKAD + [RXRPC_SECURITY_RXKAD] = &rxkad, +#endif +}; + +int __init rxrpc_init_security(void) +{ + int i, ret; + + for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) { + if (rxrpc_security_types[i]) { + ret = rxrpc_security_types[i]->init(); + if (ret < 0) + goto failed; + } + } + + return 0; + +failed: + for (i--; i >= 0; i--) + if (rxrpc_security_types[i]) + rxrpc_security_types[i]->exit(); + return ret; +} + +void rxrpc_exit_security(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) + if (rxrpc_security_types[i]) + rxrpc_security_types[i]->exit(); +} + +/* + * look up an rxrpc security module + */ +static const struct rxrpc_security *rxrpc_security_lookup(u8 security_index) +{ + if (security_index >= ARRAY_SIZE(rxrpc_security_types)) + return NULL; + return rxrpc_security_types[security_index]; +} + +/* + * initialise the security on a client connection + */ +int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) +{ + const struct rxrpc_security *sec; + struct rxrpc_key_token *token; + struct key *key = conn->params.key; + int ret; + + _enter("{%d},{%x}", conn->debug_id, key_serial(key)); + + if (!key) + return 0; + + ret = key_validate(key); + if (ret < 0) + return ret; + + token = key->payload.data[0]; + if (!token) + return -EKEYREJECTED; + + sec = rxrpc_security_lookup(token->security_index); + if (!sec) + return -EKEYREJECTED; + conn->security = sec; + + ret = conn->security->init_connection_security(conn); + if (ret < 0) { + conn->security = &rxrpc_no_security; + return ret; + } + + _leave(" = 0"); + return 0; +} + +/* + * initialise the security on a server connection + */ +int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +{ + const struct rxrpc_security *sec; + struct rxrpc_local *local = conn->params.local; + struct rxrpc_sock *rx; + struct key *key; + key_ref_t kref; + char kdesc[5 + 1 + 3 + 1]; + + _enter(""); + + sprintf(kdesc, "%u:%u", conn->params.service_id, conn->security_ix); + + sec = rxrpc_security_lookup(conn->security_ix); + if (!sec) { + _leave(" = -ENOKEY [lookup]"); + return -ENOKEY; + } + + /* find the service */ + read_lock_bh(&local->services_lock); + list_for_each_entry(rx, &local->services, listen_link) { + if (rx->srx.srx_service == conn->params.service_id) + goto found_service; + } + + /* the service appears to have died */ + read_unlock_bh(&local->services_lock); + _leave(" = -ENOENT"); + return -ENOENT; + +found_service: + if (!rx->securities) { + read_unlock_bh(&local->services_lock); + _leave(" = -ENOKEY"); + return -ENOKEY; + } + + /* look through the service's keyring */ + kref = keyring_search(make_key_ref(rx->securities, 1UL), + &key_type_rxrpc_s, kdesc); + if (IS_ERR(kref)) { + read_unlock_bh(&local->services_lock); + _leave(" = %ld [search]", PTR_ERR(kref)); + return PTR_ERR(kref); + } + + key = key_ref_to_ptr(kref); + read_unlock_bh(&local->services_lock); + + conn->server_key = key; + conn->security = sec; + + _leave(" = 0"); + return 0; +} diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c new file mode 100644 index 000000000..06c51d4b6 --- /dev/null +++ b/net/rxrpc/skbuff.c @@ -0,0 +1,165 @@ +/* ar-skbuff.c: socket buffer destruction handling + * + * 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 <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * set up for the ACK at the end of the receive phase when we discard the final + * receive phase data packet + * - called with softirqs disabled + */ +static void rxrpc_request_final_ACK(struct rxrpc_call *call) +{ + /* the call may be aborted before we have a chance to ACK it */ + write_lock(&call->state_lock); + + switch (call->state) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + call->state = RXRPC_CALL_CLIENT_FINAL_ACK; + _debug("request final ACK"); + + /* get an extra ref on the call for the final-ACK generator to + * release */ + rxrpc_get_call(call); + set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); + if (try_to_del_timer_sync(&call->ack_timer) >= 0) + rxrpc_queue_call(call); + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: + call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + default: + break; + } + + write_unlock(&call->state_lock); +} + +/* + * drop the bottom ACK off of the call ACK window and advance the window + */ +static void rxrpc_hard_ACK_data(struct rxrpc_call *call, + struct rxrpc_skb_priv *sp) +{ + int loop; + u32 seq; + + spin_lock_bh(&call->lock); + + _debug("hard ACK #%u", sp->hdr.seq); + + for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) { + call->ackr_window[loop] >>= 1; + call->ackr_window[loop] |= + call->ackr_window[loop + 1] << (BITS_PER_LONG - 1); + } + + seq = sp->hdr.seq; + ASSERTCMP(seq, ==, call->rx_data_eaten + 1); + call->rx_data_eaten = seq; + + if (call->ackr_win_top < UINT_MAX) + call->ackr_win_top++; + + ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE, + call->rx_data_post, >=, call->rx_data_recv); + ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE, + call->rx_data_recv, >=, call->rx_data_eaten); + + if (sp->hdr.flags & RXRPC_LAST_PACKET) { + rxrpc_request_final_ACK(call); + } else if (atomic_dec_and_test(&call->ackr_not_idle) && + test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) { + /* We previously soft-ACK'd some received packets that have now + * been consumed, so send a hard-ACK if no more packets are + * immediately forthcoming to allow the transmitter to free up + * its Tx bufferage. + */ + _debug("send Rx idle ACK"); + __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial, + false); + } + + spin_unlock_bh(&call->lock); +} + +/** + * rxrpc_kernel_data_consumed - Record consumption of data message + * @call: The call to which the message pertains. + * @skb: Message holding data + * + * Record the consumption of a data message and generate an ACK if appropriate. + * The call state is shifted if this was the final packet. The caller must be + * in process context with no spinlocks held. + * + * TODO: Actually generate the ACK here rather than punting this to the + * workqueue. + */ +void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + _enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq); + + ASSERTCMP(sp->call, ==, call); + ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA); + + /* TODO: Fix the sequence number tracking */ + ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); + ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); + ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); + + call->rx_data_recv = sp->hdr.seq; + rxrpc_hard_ACK_data(call, sp); +} +EXPORT_SYMBOL(rxrpc_kernel_data_consumed); + +/* + * Destroy a packet that has an RxRPC control buffer + */ +void rxrpc_packet_destructor(struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_call *call = sp->call; + + _enter("%p{%p}", skb, call); + + if (call) { + if (atomic_dec_return(&call->skb_count) < 0) + BUG(); + rxrpc_put_call(call); + sp->call = NULL; + } + + if (skb->sk) + sock_rfree(skb); + _leave(""); +} + +/** + * rxrpc_kernel_free_skb - Free an RxRPC socket buffer + * @skb: The socket buffer to be freed + * + * Let RxRPC free its own socket buffer, permitting it to maintain debug + * accounting. + */ +void rxrpc_kernel_free_skb(struct sk_buff *skb) +{ + rxrpc_free_skb(skb); +} +EXPORT_SYMBOL(rxrpc_kernel_free_skb); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index d20ed575a..03ad08774 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 000000000..b88914d53 --- /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; + } +} |