diff options
31 files changed, 11275 insertions, 7 deletions
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt new file mode 100644 index 00000000000..fb809b738a0 --- /dev/null +++ b/Documentation/networking/rxrpc.txt @@ -0,0 +1,663 @@ + ====================== + RxRPC NETWORK PROTOCOL + ====================== + +The RxRPC protocol driver provides a reliable two-phase transport on top of UDP +that can be used to perform RxRPC remote operations. This is done over sockets +of AF_RXRPC family, using sendmsg() and recvmsg() with control data to send and +receive data, aborts and errors. + +Contents of this document: + + (*) Overview. + + (*) RxRPC protocol summary. + + (*) AF_RXRPC driver model. + + (*) Control messages. + + (*) Socket options. + + (*) Security. + + (*) Example client usage. + + (*) Example server usage. + + +======== +OVERVIEW +======== + +RxRPC is a two-layer protocol. There is a session layer which provides +reliable virtual connections using UDP over IPv4 (or IPv6) as the transport +layer, but implements a real network protocol; and there's the presentation +layer which renders structured data to binary blobs and back again using XDR +(as does SunRPC): + + +-------------+ + | Application | + +-------------+ + | XDR | Presentation + +-------------+ + | RxRPC | Session + +-------------+ + | UDP | Transport + +-------------+ + + +AF_RXRPC provides: + + (1) Part of an RxRPC facility for both kernel and userspace applications by + making the session part of it a Linux network protocol (AF_RXRPC). + + (2) A two-phase protocol. The client transmits a blob (the request) and then + receives a blob (the reply), and the server receives the request and then + transmits the reply. + + (3) Retention of the reusable bits of the transport system set up for one call + to speed up subsequent calls. + + (4) A secure protocol, using the Linux kernel's key retention facility to + manage security on the client end. The server end must of necessity be + more active in security negotiations. + +AF_RXRPC does not provide XDR marshalling/presentation facilities. That is +left to the application. AF_RXRPC only deals in blobs. Even the operation ID +is just the first four bytes of the request blob, and as such is beyond the +kernel's interest. + + +Sockets of AF_RXRPC family are: + + (1) created as type SOCK_DGRAM; + + (2) provided with a protocol of the type of underlying transport they're going + to use - currently only PF_INET is supported. + + +The Andrew File System (AFS) is an example of an application that uses this and +that has both kernel (filesystem) and userspace (utility) components. + + +====================== +RXRPC PROTOCOL SUMMARY +====================== + +An overview of the RxRPC protocol: + + (*) RxRPC sits on top of another networking protocol (UDP is the only option + currently), and uses this to provide network transport. UDP ports, for + example, provide transport endpoints. + + (*) RxRPC supports multiple virtual "connections" from any given transport + endpoint, thus allowing the endpoints to be shared, even to the same + remote endpoint. + + (*) Each connection goes to a particular "service". A connection may not go + to multiple services. A service may be considered the RxRPC equivalent of + a port number. AF_RXRPC permits multiple services to share an endpoint. + + (*) Client-originating packets are marked, thus a transport endpoint can be + shared between client and server connections (connections have a + direction). + + (*) Up to a billion connections may be supported concurrently between one + local transport endpoint and one service on one remote endpoint. An RxRPC + connection is described by seven numbers: + + Local address } + Local port } Transport (UDP) address + Remote address } + Remote port } + Direction + Connection ID + Service ID + + (*) Each RxRPC operation is a "call". A connection may make up to four + billion calls, but only up to four calls may be in progress on a + connection at any one time. + + (*) Calls are two-phase and asymmetric: the client sends its request data, + which the service receives; then the service transmits the reply data + which the client receives. + + (*) The data blobs are of indefinite size, the end of a phase is marked with a + flag in the packet. The number of packets of data making up one blob may + not exceed 4 billion, however, as this would cause the sequence number to + wrap. + + (*) The first four bytes of the request data are the service operation ID. + + (*) Security is negotiated on a per-connection basis. The connection is + initiated by the first data packet on it arriving. If security is + requested, the server then issues a "challenge" and then the client + replies with a "response". If the response is successful, the security is + set for the lifetime of that connection, and all subsequent calls made + upon it use that same security. In the event that the server lets a + connection lapse before the client, the security will be renegotiated if + the client uses the connection again. + + (*) Calls use ACK packets to handle reliability. Data packets are also + explicitly sequenced per call. + + (*) There are two types of positive acknowledgement: hard-ACKs and soft-ACKs. + A hard-ACK indicates to the far side that all the data received to a point + has been received and processed; a soft-ACK indicates that the data has + been received but may yet be discarded and re-requested. The sender may + not discard any transmittable packets until they've been hard-ACK'd. + + (*) Reception of a reply data packet implicitly hard-ACK's all the data + packets that make up the request. + + (*) An call is complete when the request has been sent, the reply has been + received and the final hard-ACK on the last packet of the reply has + reached the server. + + (*) An call may be aborted by either end at any time up to its completion. + + +===================== +AF_RXRPC DRIVER MODEL +===================== + +About the AF_RXRPC driver: + + (*) The AF_RXRPC protocol transparently uses internal sockets of the transport + protocol to represent transport endpoints. + + (*) AF_RXRPC sockets map onto RxRPC connection bundles. Actual RxRPC + connections are handled transparently. One client socket may be used to + make multiple simultaneous calls to the same service. One server socket + may handle calls from many clients. + + (*) Additional parallel client connections will be initiated to support extra + concurrent calls, up to a tunable limit. + + (*) Each connection is retained for a certain amount of time [tunable] after + the last call currently using it has completed in case a new call is made + that could reuse it. + + (*) Each internal UDP socket is retained [tunable] for a certain amount of + time [tunable] after the last connection using it discarded, in case a new + connection is made that could use it. + + (*) A client-side connection is only shared between calls if they have have + the same key struct describing their security (and assuming the calls + would otherwise share the connection). Non-secured calls would also be + able to share connections with each other. + + (*) A server-side connection is shared if the client says it is. + + (*) ACK'ing is handled by the protocol driver automatically, including ping + replying. + + (*) SO_KEEPALIVE automatically pings the other side to keep the connection + alive [TODO]. + + (*) If an ICMP error is received, all calls affected by that error will be + aborted with an appropriate network error passed through recvmsg(). + + +Interaction with the user of the RxRPC socket: + + (*) A socket is made into a server socket by binding an address with a + non-zero service ID. + + (*) In the client, sending a request is achieved with one or more sendmsgs, + followed by the reply being received with one or more recvmsgs. + + (*) The first sendmsg for a request to be sent from a client contains a tag to + be used in all other sendmsgs or recvmsgs associated with that call. The + tag is carried in the control data. + + (*) connect() is used to supply a default destination address for a client + socket. This may be overridden by supplying an alternate address to the + first sendmsg() of a call (struct msghdr::msg_name). + + (*) If connect() is called on an unbound client, a random local port will + bound before the operation takes place. + + (*) A server socket may also be used to make client calls. To do this, the + first sendmsg() of the call must specify the target address. The server's + transport endpoint is used to send the packets. + + (*) Once the application has received the last message associated with a call, + the tag is guaranteed not to be seen again, and so it can be used to pin + client resources. A new call can then be initiated with the same tag + without fear of interference. + + (*) In the server, a request is received with one or more recvmsgs, then the + the reply is transmitted with one or more sendmsgs, and then the final ACK + is received with a last recvmsg. + + (*) When sending data for a call, sendmsg is given MSG_MORE if there's more + data to come on that call. + + (*) When receiving data for a call, recvmsg flags MSG_MORE if there's more + data to come for that call. + + (*) When receiving data or messages for a call, MSG_EOR is flagged by recvmsg + to indicate the terminal message for that call. + + (*) A call may be aborted by adding an abort control message to the control + data. Issuing an abort terminates the kernel's use of that call's tag. + Any messages waiting in the receive queue for that call will be discarded. + + (*) Aborts, busy notifications and challenge packets are delivered by recvmsg, + and control data messages will be set to indicate the context. Receiving + an abort or a busy message terminates the kernel's use of that call's tag. + + (*) The control data part of the msghdr struct is used for a number of things: + + (*) The tag of the intended or affected call. + + (*) Sending or receiving errors, aborts and busy notifications. + + (*) Notifications of incoming calls. + + (*) Sending debug requests and receiving debug replies [TODO]. + + (*) When the kernel has received and set up an incoming call, it sends a + message to server application to let it know there's a new call awaiting + its acceptance [recvmsg reports a special control message]. The server + application then uses sendmsg to assign a tag to the new call. Once that + is done, the first part of the request data will be delivered by recvmsg. + + (*) The server application has to provide the server socket with a keyring of + secret keys corresponding to the security types it permits. When a secure + connection is being set up, the kernel looks up the appropriate secret key + in the keyring and then sends a challenge packet to the client and + receives a response packet. The kernel then checks the authorisation of + the packet and either aborts the connection or sets up the security. + + (*) The name of the key a client will use to secure its communications is + nominated by a socket option. + + +Notes on recvmsg: + + (*) If there's a sequence of data messages belonging to a particular call on + the receive queue, then recvmsg will keep working through them until: + + (a) it meets the end of that call's received data, + + (b) it meets a non-data message, + + (c) it meets a message belonging to a different call, or + + (d) it fills the user buffer. + + If recvmsg is called in blocking mode, it will keep sleeping, awaiting the + reception of further data, until one of the above four conditions is met. + + (2) MSG_PEEK operates similarly, but will return immediately if it has put any + data in the buffer rather than sleeping until it can fill the buffer. + + (3) If a data message is only partially consumed in filling a user buffer, + then the remainder of that message will be left on the front of the queue + for the next taker. MSG_TRUNC will never be flagged. + + (4) If there is more data to be had on a call (it hasn't copied the last byte + of the last data message in that phase yet), then MSG_MORE will be + flagged. + + +================ +CONTROL MESSAGES +================ + +AF_RXRPC makes use of control messages in sendmsg() and recvmsg() to multiplex +calls, to invoke certain actions and to report certain conditions. These are: + + MESSAGE ID SRT DATA MEANING + ======================= === =========== =============================== + RXRPC_USER_CALL_ID sr- User ID App's call specifier + RXRPC_ABORT srt Abort code Abort code to issue/received + RXRPC_ACK -rt n/a Final ACK received + RXRPC_NET_ERROR -rt error num Network error on call + RXRPC_BUSY -rt n/a Call rejected (server busy) + RXRPC_LOCAL_ERROR -rt error num Local error encountered + RXRPC_NEW_CALL -r- n/a New call received + RXRPC_ACCEPT s-- n/a Accept new call + + (SRT = usable in Sendmsg / delivered by Recvmsg / Terminal message) + + (*) RXRPC_USER_CALL_ID + + This is used to indicate the application's call ID. It's an unsigned long + that the app specifies in the client by attaching it to the first data + message or in the server by passing it in association with an RXRPC_ACCEPT + message. recvmsg() passes it in conjunction with all messages except + those of the RXRPC_NEW_CALL message. + + (*) RXRPC_ABORT + + This is can be used by an application to abort a call by passing it to + sendmsg, or it can be delivered by recvmsg to indicate a remote abort was + received. Either way, it must be associated with an RXRPC_USER_CALL_ID to + specify the call affected. If an abort is being sent, then error EBADSLT + will be returned if there is no call with that user ID. + + (*) RXRPC_ACK + + This is delivered to a server application to indicate that the final ACK + of a call was received from the client. It will be associated with an + RXRPC_USER_CALL_ID to indicate the call that's now complete. + + (*) RXRPC_NET_ERROR + + This is delivered to an application to indicate that an ICMP error message + was encountered in the process of trying to talk to the peer. An + errno-class integer value will be included in the control message data + indicating the problem, and an RXRPC_USER_CALL_ID will indicate the call + affected. + + (*) RXRPC_BUSY + + This is delivered to a client application to indicate that a call was + rejected by the server due to the server being busy. It will be + associated with an RXRPC_USER_CALL_ID to indicate the rejected call. + + (*) RXRPC_LOCAL_ERROR + + This is delivered to an application to indicate that a local error was + encountered and that a call has been aborted because of it. An + errno-class integer value will be included in the control message data + indicating the problem, and an RXRPC_USER_CALL_ID will indicate the call + affected. + + (*) RXRPC_NEW_CALL + + This is delivered to indicate to a server application that a new call has + arrived and is awaiting acceptance. No user ID is associated with this, + as a user ID must subsequently be assigned by doing an RXRPC_ACCEPT. + + (*) RXRPC_ACCEPT + + This is used by a server application to attempt to accept a call and + assign it a user ID. It should be associated with an RXRPC_USER_CALL_ID + to indicate the user ID to be assigned. If there is no call to be + accepted (it may have timed out, been aborted, etc.), then sendmsg will + return error ENODATA. If the user ID is already in use by another call, + then error EBADSLT will be returned. + + +============== +SOCKET OPTIONS +============== + +AF_RXRPC sockets support a few socket options at the SOL_RXRPC level: + + (*) RXRPC_SECURITY_KEY + + This is used to specify the description of the key to be used. The key is + extracted from the calling process's keyrings with request_key() and + should be of "rxrpc" type. + + The optval pointer points to the description string, and optlen indicates + how long the string is, without the NUL terminator. + + (*) RXRPC_SECURITY_KEYRING + + Similar to above but specifies a keyring of server secret keys to use (key + type "keyring"). See the "Security" section. + + (*) RXRPC_EXCLUSIVE_CONNECTION + + This is used to request that new connections should be used for each call + made subsequently on this socket. optval should be NULL and optlen 0. + + (*) RXRPC_MIN_SECURITY_LEVEL + + This is used to specify the minimum security level required for calls on + this socket. optval must point to an int containing one of the following + values: + + (a) RXRPC_SECURITY_PLAIN + + Encrypted checksum only. + + (b) RXRPC_SECURITY_AUTH + + Encrypted checksum plus packet padded and first eight bytes of packet + encrypted - which includes the actual packet length. + + (c) RXRPC_SECURITY_ENCRYPTED + + Encrypted checksum plus entire packet padded and encrypted, including + actual packet length. + + +======== +SECURITY +======== + +Currently, only the kerberos 4 equivalent protocol has been implemented +(security index 2 - rxkad). This requires the rxkad module to be loaded and, +on the client, tickets of the appropriate type to be obtained from the AFS +kaserver or the kerberos server and installed as "rxrpc" type keys. This is +normally done using the klog program. An example simple klog program can be +found at: + + http://people.redhat.com/~dhowells/rxrpc/klog.c + +The payload provided to add_key() on the client should be of the following +form: + + struct rxrpc_key_sec2_v1 { + uint16_t security_index; /* 2 */ + uint16_t ticket_length; /* length of ticket[] */ + uint32_t expiry; /* time at which expires */ + uint8_t kvno; /* key version number */ + uint8_t __pad[3]; + uint8_t session_key[8]; /* DES session key */ + uint8_t ticket[0]; /* the encrypted ticket */ + }; + +Where the ticket blob is just appended to the above structure. + + +For the server, keys of type "rxrpc_s" must be made available to the server. +They have a description of "<serviceID>:<securityIndex>" (eg: "52:2" for an +rxkad key for the AFS VL service). When such a key is created, it should be +given the server's secret key as the instantiation data (see the example +below). + + add_key("rxrpc_s", "52:2", secret_key, 8, keyring); + +A keyring is passed to the server socket by naming it in a sockopt. The server +socket then looks the server secret keys up in this keyring when secure +incoming connections are made. This can be seen in an example program that can +be found at: + + http://people.redhat.com/~dhowells/rxrpc/listen.c + + +==================== +EXAMPLE CLIENT USAGE +==================== + +A client would issue an operation by: + + (1) An RxRPC socket is set up by: + + client = socket(AF_RXRPC, SOCK_DGRAM, PF_INET); + + Where the third parameter indicates the protocol family of the transport + socket used - usually IPv4 but it can also be IPv6 [TODO]. + + (2) A local address can optionally be bound: + + struct sockaddr_rxrpc srx = { + .srx_family = AF_RXRPC, + .srx_service = 0, /* we're a client */ + .transport_type = SOCK_DGRAM, /* type of transport socket */ + .transport.sin_family = AF_INET, + .transport.sin_port = htons(7000), /* AFS callback */ + .transport.sin_address = 0, /* all local interfaces */ + }; + bind(client, &srx, sizeof(srx)); + + This specifies the local UDP port to be used. If not given, a random + non-privileged port will be used. A UDP port may be shared between + several unrelated RxRPC sockets. Security is handled on a basis of + per-RxRPC virtual connection. + + (3) The security is set: + + const char *key = "AFS:cambridge.redhat.com"; + setsockopt(client, SOL_RXRPC, RXRPC_SECURITY_KEY, key, strlen(key)); + + This issues a request_key() to get the key representing the security + context. The minimum security level can be set: + + unsigned int sec = RXRPC_SECURITY_ENCRYPTED; + setsockopt(client, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL, + &sec, sizeof(sec)); + + (4) The server to be contacted can then be specified (alternatively this can + be done through sendmsg): + + struct sockaddr_rxrpc srx = { + .srx_family = AF_RXRPC, + .srx_service = VL_SERVICE_ID, + .transport_type = SOCK_DGRAM, /* type of transport socket */ + .transport.sin_family = AF_INET, + .transport.sin_port = htons(7005), /* AFS volume manager */ + .transport.sin_address = ..., + }; + connect(client, &srx, sizeof(srx)); + + (5) The request data should then be posted to the server socket using a series + of sendmsg() calls, each with the following control message attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + + MSG_MORE should be set in msghdr::msg_flags on all but the last part of + the request. Multiple requests may be made simultaneously. + + If a call is intended to go to a destination other then the default + specified through connect(), then msghdr::msg_name should be set on the + first request message of that call. + + (6) The reply data will then be posted to the server socket for recvmsg() to + pick up. MSG_MORE will be flagged by recvmsg() if there's more reply data + for a particular call to be read. MSG_EOR will be set on the terminal + read for a call. + + All data will be delivered with the following control message attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + + If an abort or error occurred, this will be returned in the control data + buffer instead, and MSG_EOR will be flagged to indicate the end of that + call. + + +==================== +EXAMPLE SERVER USAGE +==================== + +A server would be set up to accept operations in the following manner: + + (1) An RxRPC socket is created by: + + server = socket(AF_RXRPC, SOCK_DGRAM, PF_INET); + + Where the third parameter indicates the address type of the transport + socket used - usually IPv4. + + (2) Security is set up if desired by giving the socket a keyring with server + secret keys in it: + + keyring = add_key("keyring", "AFSkeys", NULL, 0, + KEY_SPEC_PROCESS_KEYRING); + + const char secret_key[8] = { + 0xa7, 0x83, 0x8a, 0xcb, 0xc7, 0x83, 0xec, 0x94 }; + add_key("rxrpc_s", "52:2", secret_key, 8, keyring); + + setsockopt(server, SOL_RXRPC, RXRPC_SECURITY_KEYRING, "AFSkeys", 7); + + The keyring can be manipulated after it has been given to the socket. This + permits the server to add more keys, replace keys, etc. whilst it is live. + + (2) A local address must then be bound: + + struct sockaddr_rxrpc srx = { + .srx_family = AF_RXRPC, + .srx_service = VL_SERVICE_ID, /* RxRPC service ID */ + .transport_type = SOCK_DGRAM, /* type of transport socket */ + .transport.sin_family = AF_INET, + .transport.sin_port = htons(7000), /* AFS callback */ + .transport.sin_address = 0, /* all local interfaces */ + }; + bind(server, &srx, sizeof(srx)); + + (3) The server is then set to listen out for incoming calls: + + listen(server, 100); + + (4) The kernel notifies the server of pending incoming connections by sending + it a message for each. This is received with recvmsg() on the server + socket. It has no data, and has a single dataless control message + attached: + + RXRPC_NEW_CALL + + The address that can be passed back by recvmsg() at this point should be + ignored since the call for which the message was posted may have gone by + the time it is accepted - in which case the first call still on the queue + will be accepted. + + (5) The server then accepts the new call by issuing a sendmsg() with two + pieces of control data and no actual data: + + RXRPC_ACCEPT - indicate connection acceptance + RXRPC_USER_CALL_ID - specify user ID for this call + + (6) The first request data packet will then be posted to the server socket for + recvmsg() to pick up. At that point, the RxRPC address for the call can + be read from the address fields in the msghdr struct. + + Subsequent request data will be posted to the server socket for recvmsg() + to collect as it arrives. All but the last piece of the request data will + be delivered with MSG_MORE flagged. + + All data will be delivered with the following control message attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + + (8) The reply data should then be posted to the server socket using a series + of sendmsg() calls, each with the following control messages attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + + MSG_MORE should be set in msghdr::msg_flags on all but the last message + for a particular call. + + (9) The final ACK from the client will be posted for retrieval by recvmsg() + when it is received. It will take the form of a dataless message with two + control messages attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + RXRPC_ACK - indicates final ACK (no data) + + MSG_EOR will be flagged to indicate that this is the final message for + this call. + +(10) Up to the point the final packet of reply data is sent, the call can be + aborted by calling sendmsg() with a dataless message with the following + control messages attached: + + RXRPC_USER_CALL_ID - specifies the user ID for this call + RXRPC_ABORT - indicates abort code (4 byte data) + + Any packets waiting in the socket's receive queue will be discarded if + this is issued. + +Note that all the communications for a particular service take place through +the one server socket, using control messages on sendmsg() and recvmsg() to +determine the call affected. diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h new file mode 100644 index 00000000000..e2ee73aef0e --- /dev/null +++ b/include/keys/rxrpc-type.h @@ -0,0 +1,22 @@ +/* RxRPC key type + * + * 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. + */ + +#ifndef _KEYS_RXRPC_TYPE_H +#define _KEYS_RXRPC_TYPE_H + +#include <linux/key.h> + +/* + * key type for AF_RXRPC keys + */ +extern struct key_type key_type_rxrpc; + +#endif /* _KEYS_USER_TYPE_H */ diff --git a/include/linux/net.h b/include/linux/net.h index 4db21e63d8d..efc45177b50 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -24,7 +24,7 @@ struct poll_table_struct; struct inode; -#define NPROTO 33 /* should be enough for now.. */ +#define NPROTO 34 /* should be enough for now.. */ #define SYS_SOCKET 1 /* sys_socket(2) */ #define SYS_BIND 2 /* sys_bind(2) */ diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h new file mode 100644 index 00000000000..f7b826b565c --- /dev/null +++ b/include/linux/rxrpc.h @@ -0,0 +1,62 @@ +/* AF_RXRPC parameters + * + * 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. + */ + +#ifndef _LINUX_RXRPC_H +#define _LINUX_RXRPC_H + +#include <linux/in.h> +#include <linux/in6.h> + +/* + * RxRPC socket address + */ +struct sockaddr_rxrpc { + sa_family_t srx_family; /* address family */ + u16 srx_service; /* service desired */ + u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ + u16 transport_len; /* length of transport address */ + union { + sa_family_t family; /* transport address family */ + struct sockaddr_in sin; /* IPv4 transport address */ + struct sockaddr_in6 sin6; /* IPv6 transport address */ + } transport; +}; + +/* + * RxRPC socket options + */ +#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ +#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ +#define RXRPC_EXCLUSIVE_CONNECTION 3 /* [clnt] use exclusive RxRPC connection */ +#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ + +/* + * RxRPC control messages + * - terminal messages mean that a user call ID tag can be recycled + */ +#define RXRPC_USER_CALL_ID 1 /* user call ID specifier */ +#define RXRPC_ABORT 2 /* abort request / notification [terminal] */ +#define RXRPC_ACK 3 /* [Server] RPC op final ACK received [terminal] */ +#define RXRPC_NET_ERROR 5 /* network error received [terminal] */ +#define RXRPC_BUSY 6 /* server busy received [terminal] */ +#define RXRPC_LOCAL_ERROR 7 /* local error generated [terminal] */ +#define RXRPC_NEW_CALL 8 /* [Server] new incoming call notification */ +#define RXRPC_ACCEPT 9 /* [Server] accept request */ + +/* + * RxRPC security levels + */ +#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ +#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ +#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ + + +#endif /* _LINUX_RXRPC_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index fcd35a210e7..6e7c9483a6a 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -188,7 +188,8 @@ struct ucred { #define AF_TIPC 30 /* TIPC sockets */ #define AF_BLUETOOTH 31 /* Bluetooth sockets */ #define AF_IUCV 32 /* IUCV sockets */ -#define AF_MAX 33 /* For now.. */ +#define AF_RXRPC 33 /* RxRPC sockets */ +#define AF_MAX 34 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -222,6 +223,7 @@ struct ucred { #define PF_TIPC AF_TIPC #define PF_BLUETOOTH AF_BLUETOOTH #define PF_IUCV AF_IUCV +#define PF_RXRPC AF_RXRPC #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -284,6 +286,7 @@ struct ucred { #define SOL_DCCP 269 #define SOL_NETLINK 270 #define SOL_TIPC 271 +#define SOL_RXRPC 272 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h new file mode 100644 index 00000000000..b01ca2589d6 --- /dev/null +++ b/include/net/af_rxrpc.h @@ -0,0 +1,17 @@ +/* RxRPC definitions + * + * Copyright (C) 2006 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. + */ + +#ifndef _NET_RXRPC_H +#define _NET_RXRPC_H + +#include <linux/rxrpc.h> + +#endif /* _NET_RXRPC_H */ diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h index 1447f0aaa0e..452a9bb02d4 100644 --- a/include/rxrpc/packet.h +++ b/include/rxrpc/packet.h @@ -33,7 +33,8 @@ struct rxrpc_header #define RXRPC_MAXCALLS 4 /* max active calls per conn */ #define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */ #define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */ -#define RXRPC_CIDSHIFT 2 /* shift for connection ID */ +#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */ +#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */ __be32 callNumber; /* call ID (0 for connection-level packets) */ #define RXRPC_PROCESS_MAXCALLS (1<<2) /* maximum number of active calls per conn (power of 2) */ @@ -62,7 +63,10 @@ struct rxrpc_header uint8_t userStatus; /* app-layer defined status */ uint8_t securityIndex; /* security protocol ID */ - __be16 _rsvd; /* reserved (used by kerberos security as cksum) */ + union { + __be16 _rsvd; /* reserved */ + __be16 cksum; /* kerberos security checksum */ + }; __be16 serviceId; /* service ID */ } __attribute__((packed)); @@ -124,4 +128,81 @@ struct rxrpc_ackpacket } __attribute__((packed)); +/* + * ACK packets can have a further piece of information tagged on the end + */ +struct rxrpc_ackinfo { + __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ + __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ + __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ +}; + +/*****************************************************************************/ +/* + * Kerberos security type-2 challenge packet + */ +struct rxkad_challenge { + __be32 version; /* version of this challenge type */ + __be32 nonce; /* encrypted random number */ + __be32 min_level; /* minimum security level */ + __be32 __padding; /* padding to 8-byte boundary */ +} __attribute__((packed)); + +/*****************************************************************************/ +/* + * Kerberos security type-2 response packet + */ +struct rxkad_response { + __be32 version; /* version of this reponse type */ + __be32 __pad; + + /* encrypted bit of the response */ + struct { + __be32 epoch; /* current epoch */ + __be32 cid; /* parent connection ID */ + __be32 checksum; /* checksum */ + __be32 securityIndex; /* security type */ + __be32 call_id[4]; /* encrypted call IDs */ + __be32 inc_nonce; /* challenge nonce + 1 */ + __be32 level; /* desired level */ + } encrypted; + + __be32 kvno; /* Kerberos key version number */ + __be32 ticket_len; /* Kerberos ticket length */ +} __attribute__((packed)); + +/*****************************************************************************/ +/* + * RxRPC-level abort codes + */ +#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */ +#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */ +#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */ +#define RX_EOF -4 /* unexpected end of data on read op */ +#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */ +#define RX_USER_ABORT -6 /* generic user abort */ +#define RX_ADDRINUSE -7 /* UDP port in use */ +#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */ + +/* + * Rx kerberos security abort codes + * - unfortunately we have no generalised security abort codes to say things + * like "unsupported security", so we have to use these instead and hope the + * other side understands + */ +#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */ +#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */ +#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */ +#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */ +#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */ +#define RXKADNOAUTH 19270405 /* caller not authorised */ +#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */ +#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */ +#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */ +#define RXKADEXPIRED 19270409 /* authentication expired */ +#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */ +#define RXKADDATALEN 19270411 /* user data too long */ +#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ + #endif /* _LINUX_RXRPC_PACKET_H */ diff --git a/net/Kconfig b/net/Kconfig index ae1817dc51b..2fc8e77b1e6 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -212,6 +212,7 @@ endmenu source "net/ax25/Kconfig" source "net/irda/Kconfig" source "net/bluetooth/Kconfig" +source "net/rxrpc/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index 29bbe19d87f..6b74d4118c5 100644 --- a/net/Makefile +++ b/net/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_IRDA) += irda/ obj-$(CONFIG_BT) += bluetooth/ obj-$(CONFIG_SUNRPC) += sunrpc/ obj-$(CONFIG_RXRPC) += rxrpc/ +obj-$(CONFIG_AF_RXRPC) += rxrpc/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_DECNET) += decnet/ obj-$(CONFIG_ECONET) += econet/ diff --git a/net/core/sock.c b/net/core/sock.c index 043bdc05d21..22183c2ef28 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -154,7 +154,8 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , "sk_lock-27" , "sk_lock-28" , "sk_lock-29" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-AF_MAX" + "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , + "sk_lock-AF_RXRPC" , "sk_lock-AF_MAX" }; static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -167,7 +168,8 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" , "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , "slock-27" , "slock-28" , "slock-29" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_MAX" + "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , + "slock-AF_RXRPC" , "slock-AF_MAX" }; #endif diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig new file mode 100644 index 00000000000..d72380e304a --- /dev/null +++ b/net/rxrpc/Kconfig @@ -0,0 +1,37 @@ +# +# RxRPC session sockets +# + +config AF_RXRPC + tristate "RxRPC session sockets" + depends on EXPERIMENTAL + help + Say Y or M here to include support for RxRPC session sockets (just + the transport part, not the presentation part: (un)marshalling is + left to the application). + + These are used for AFS kernel filesystem and userspace utilities. + + This module at the moment only supports client operations and is + currently incomplete. + + See Documentation/networking/rxrpc.txt. + + +config AF_RXRPC_DEBUG + bool "RxRPC dynamic debugging" + depends on AF_RXRPC + help + Say Y here to make runtime controllable debugging messages appear. + + See Documentation/networking/rxrpc.txt. + + +config RXKAD + tristate "RxRPC Kerberos security" + depends on AF_RXRPC && KEYS + help + Provide kerberos 4 and AFS kaserver security handling for AF_RXRPC + through the use of the key retention service. + + See Documentation/networking/rxrpc.txt. diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index 6efcb6f162a..07bf82ffec6 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -4,6 +4,35 @@ #CFLAGS += -finstrument-functions +af-rxrpc-objs := \ + 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 + +ifeq ($(CONFIG_PROC_FS),y) +af-rxrpc-objs += ar-proc.o +endif + +obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o + +obj-$(CONFIG_RXKAD) += rxkad.o + +# +# obsolete RxRPC interface, still used by fs/afs/ +# rxrpc-objs := \ call.o \ connection.o \ @@ -22,4 +51,4 @@ ifeq ($(CONFIG_SYSCTL),y) rxrpc-objs += sysctl.o endif -obj-$(CONFIG_RXRPC) := rxrpc.o +obj-$(CONFIG_RXRPC) += rxrpc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c new file mode 100644 index 00000000000..bfa8822e228 --- /dev/null +++ b/net/rxrpc/af_rxrpc.c @@ -0,0 +1,754 @@ +/* AF_RXRPC 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. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/poll.h> +#include <linux/proc_fs.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +MODULE_DESCRIPTION("RxRPC network protocol"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_RXRPC); + +unsigned rxrpc_debug; // = RXRPC_DEBUG_KPROTO; +module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(rxrpc_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; + +/* local epoch for detecting local-end reset */ +__be32 rxrpc_epoch; + +/* current debugging ID */ +atomic_t rxrpc_debug_id; + +/* count of skbs currently in use */ +atomic_t rxrpc_n_skbs; + +static void rxrpc_sock_destructor(struct sock *); + +/* + * see if an RxRPC socket is currently writable + */ +static inline int rxrpc_writable(struct sock *sk) +{ + return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; +} + +/* + * wait for write bufferage to become available + */ +static void rxrpc_write_space(struct sock *sk) +{ + _enter("%p", sk); + read_lock(&sk->sk_callback_lock); + if (rxrpc_writable(sk)) { + if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + wake_up_interruptible(sk->sk_sleep); + sk_wake_async(sk, 2, POLL_OUT); + } + read_unlock(&sk->sk_callback_lock); +} + +/* + * validate an RxRPC address + */ +static int rxrpc_validate_address(struct rxrpc_sock *rx, + struct sockaddr_rxrpc *srx, + int len) +{ + if (len < sizeof(struct sockaddr_rxrpc)) + return -EINVAL; + + if (srx->srx_family != AF_RXRPC) + return -EAFNOSUPPORT; + + if (srx->transport_type != SOCK_DGRAM) + return -ESOCKTNOSUPPORT; + + len -= offsetof(struct sockaddr_rxrpc, transport); + if (srx->transport_len < sizeof(sa_family_t) || + srx->transport_len > len) + return -EINVAL; + + if (srx->transport.family != rx->proto) + return -EAFNOSUPPORT; + + switch (srx->transport.family) { + case AF_INET: + _debug("INET: %x @ %u.%u.%u.%u", + ntohs(srx->transport.sin.sin_port), + NIPQUAD(srx->transport.sin.sin_addr)); + if (srx->transport_len > 8) + memset((void *)&srx->transport + 8, 0, + srx->transport_len - 8); + break; + + case AF_INET6: + default: + return -EAFNOSUPPORT; + } + + return 0; +} + +/* + * bind a local address to an RxRPC socket + */ +static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) +{ + struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) saddr; + struct sock *sk = sock->sk; + struct rxrpc_local *local; + struct rxrpc_sock *rx = rxrpc_sk(sk), *prx; + __be16 service_id; + int ret; + + _enter("%p,%p,%d", rx, saddr, len); + + ret = rxrpc_validate_address(rx, srx, len); + if (ret < 0) + goto error; + + lock_sock(&rx->sk); + + if (rx->sk.sk_state != RXRPC_UNCONNECTED) { + ret = -EINVAL; + goto error_unlock; + } + + memcpy(&rx->srx, srx, sizeof(rx->srx)); + + /* find a local transport endpoint if we don't have one already */ + local = rxrpc_lookup_local(&rx->srx); + if (IS_ERR(local)) { + ret = PTR_ERR(local); + goto error_unlock; + } + + rx->local = local; + if (srx->srx_service) { + service_id = htons(srx->srx_service); + write_lock_bh(&local->services_lock); + list_for_each_entry(prx, &local->services, listen_link) { + if (prx->service_id == service_id) + goto service_in_use; + } + + rx->service_id = service_id; + list_add_tail(&rx->listen_link, &local->services); + write_unlock_bh(&local->services_lock); + + rx->sk.sk_state = RXRPC_SERVER_BOUND; + } else { + rx->sk.sk_state = RXRPC_CLIENT_BOUND; + } + + release_sock(&rx->sk); + _leave(" = 0"); + return 0; + +service_in_use: + ret = -EADDRINUSE; + write_unlock_bh(&local->services_lock); +error_unlock: + release_sock(&rx->sk); +error: + _leave(" = %d", ret); + return ret; +} + +/* + * set the number of pending calls permitted on a listening socket + */ +static int rxrpc_listen(struct socket *sock, int backlog) +{ + struct sock *sk = sock->sk; + struct rxrpc_sock *rx = rxrpc_sk(sk); + int ret; + + _enter("%p,%d", rx, backlog); + + lock_sock(&rx->sk); + + switch (rx->sk.sk_state) { + case RXRPC_UNCONNECTED: + ret = -EADDRNOTAVAIL; + break; + case RXRPC_CLIENT_BOUND: + case RXRPC_CLIENT_CONNECTED: + default: + ret = -EBUSY; + break; + case RXRPC_SERVER_BOUND: + ASSERT(rx->local != NULL); + sk->sk_max_ack_backlog = backlog; + rx->sk.sk_state = RXRPC_SERVER_LISTENING; + ret = 0; + break; + } + + release_sock(&rx->sk); + _leave(" = %d", ret); + 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) +{ + 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_KERNEL); + if (IS_ERR(peer)) + return ERR_PTR(PTR_ERR(peer)); + + /* find a transport */ + trans = rxrpc_get_transport(rx->local, peer, GFP_KERNEL); + rxrpc_put_peer(peer); + _leave(" = %p", trans); + return trans; +} + +/* + * connect an RxRPC socket + * - this just targets it at a specific destination; no actual connection + * negotiation takes place + */ +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); + int ret; + + _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); + + ret = rxrpc_validate_address(rx, srx, addr_len); + if (ret < 0) { + _leave(" = %d [bad addr]", ret); + return ret; + } + + lock_sock(&rx->sk); + + 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_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); + if (IS_ERR(trans)) { + release_sock(&rx->sk); + _leave(" = %ld", PTR_ERR(trans)); + return PTR_ERR(trans); + } + + rx->trans = trans; + rx->service_id = htons(srx->srx_service); + rx->sk.sk_state = RXRPC_CLIENT_CONNECTED; + + release_sock(&rx->sk); + return 0; +} + +/* + * send a message through an RxRPC socket + * - in a client this does a number of things: + * - finds/sets up a connection for the security specified (if any) + * - initiates a call (ID in control data) + * - ends the request phase of a call (if MSG_MORE is not set) + * - sends a call data packet + * - may send an abort (abort code in control data) + */ +static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t len) +{ + struct rxrpc_transport *trans; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + int ret; + + _enter(",{%d},,%zu", rx->sk.sk_state, len); + + if (m->msg_flags & MSG_OOB) + return -EOPNOTSUPP; + + if (m->msg_name) { + ret = rxrpc_validate_address(rx, m->msg_name, m->msg_namelen); + if (ret < 0) { + _leave(" = %d [bad addr]", ret); + return ret; + } + } + + 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); + 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(iocb, rx, m, len); + break; + } + case RXRPC_SERVER_BOUND: + case RXRPC_CLIENT_BOUND: + if (!m->msg_name) { + ret = -ENOTCONN; + break; + } + case RXRPC_CLIENT_CONNECTED: + ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len); + break; + default: + ret = -ENOTCONN; + break; + } + +out: + release_sock(&rx->sk); + if (trans) + rxrpc_put_transport(trans); + _leave(" = %d", ret); + return ret; +} + +/* + * set RxRPC socket options + */ +static int rxrpc_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + unsigned min_sec_level; + int ret; + + _enter(",%d,%d,,%d", level, optname, optlen); + + lock_sock(&rx->sk); + ret = -EOPNOTSUPP; + + if (level == SOL_RXRPC) { + switch (optname) { + case RXRPC_EXCLUSIVE_CONNECTION: + ret = -EINVAL; + if (optlen != 0) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_UNCONNECTED) + goto error; + set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags); + goto success; + + case RXRPC_SECURITY_KEY: + ret = -EINVAL; + if (rx->key) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_UNCONNECTED) + goto error; + ret = rxrpc_request_key(rx, optval, optlen); + goto error; + + case RXRPC_SECURITY_KEYRING: + ret = -EINVAL; + if (rx->key) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_UNCONNECTED) + goto error; + ret = rxrpc_server_keyring(rx, optval, optlen); + goto error; + + case RXRPC_MIN_SECURITY_LEVEL: + ret = -EINVAL; + if (optlen != sizeof(unsigned)) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_UNCONNECTED) + goto error; + ret = get_user(min_sec_level, + (unsigned __user *) optval); + if (ret < 0) + goto error; + ret = -EINVAL; + if (min_sec_level > RXRPC_SECURITY_MAX) + goto error; + rx->min_sec_level = min_sec_level; + goto success; + + default: + break; + } + } + +success: + ret = 0; +error: + release_sock(&rx->sk); + return ret; +} + +/* + * permit an RxRPC socket to be polled + */ +static unsigned int rxrpc_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + unsigned int mask; + struct sock *sk = sock->sk; + + poll_wait(file, sk->sk_sleep, wait); + mask = 0; + + /* the socket is readable if there are any messages waiting on the Rx + * queue */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + mask |= POLLIN | POLLRDNORM; + + /* the socket is writable if there is space to add new data to the + * socket; there is no guarantee that any particular call in progress + * on the socket may have space in the Tx ACK window */ + if (rxrpc_writable(sk)) + mask |= POLLOUT | POLLWRNORM; + + return mask; +} + +/* + * create an RxRPC socket + */ +static int rxrpc_create(struct socket *sock, int protocol) +{ + struct rxrpc_sock *rx; + struct sock *sk; + + _enter("%p,%d", sock, protocol); + + /* we support transport protocol UDP only */ + if (protocol != PF_INET) + return -EPROTONOSUPPORT; + + if (sock->type != SOCK_DGRAM) + return -ESOCKTNOSUPPORT; + + sock->ops = &rxrpc_rpc_ops; + sock->state = SS_UNCONNECTED; + + sk = sk_alloc(PF_RXRPC, GFP_KERNEL, &rxrpc_proto, 1); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + sk->sk_state = RXRPC_UNCONNECTED; + sk->sk_write_space = rxrpc_write_space; + sk->sk_max_ack_backlog = sysctl_rxrpc_max_qlen; + sk->sk_destruct = rxrpc_sock_destructor; + + rx = rxrpc_sk(sk); + rx->proto = protocol; + rx->calls = RB_ROOT; + + INIT_LIST_HEAD(&rx->listen_link); + INIT_LIST_HEAD(&rx->secureq); + INIT_LIST_HEAD(&rx->acceptq); + rwlock_init(&rx->call_lock); + memset(&rx->srx, 0, sizeof(rx->srx)); + + _leave(" = 0 [%p]", rx); + return 0; +} + +/* + * RxRPC socket destructor + */ +static void rxrpc_sock_destructor(struct sock *sk) +{ + _enter("%p", sk); + + rxrpc_purge_queue(&sk->sk_receive_queue); + + BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); + BUG_TRAP(sk_unhashed(sk)); + BUG_TRAP(!sk->sk_socket); + + if (!sock_flag(sk, SOCK_DEAD)) { + printk("Attempt to release alive rxrpc socket: %p\n", sk); + return; + } +} + +/* + * release an RxRPC socket + */ +static int rxrpc_release_sock(struct sock *sk) +{ + struct rxrpc_sock *rx = rxrpc_sk(sk); + + _enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt)); + + /* declare the socket closed for business */ + sock_orphan(sk); + sk->sk_shutdown = SHUTDOWN_MASK; + + spin_lock_bh(&sk->sk_receive_queue.lock); + sk->sk_state = RXRPC_CLOSE; + spin_unlock_bh(&sk->sk_receive_queue.lock); + + ASSERTCMP(rx->listen_link.next, !=, LIST_POISON1); + + if (!list_empty(&rx->listen_link)) { + write_lock_bh(&rx->local->services_lock); + list_del(&rx->listen_link); + write_unlock_bh(&rx->local->services_lock); + } + + /* try to flush out this socket */ + rxrpc_release_calls_on_socket(rx); + flush_scheduled_work(); + 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; + } + + key_put(rx->key); + rx->key = NULL; + key_put(rx->securities); + rx->securities = NULL; + sock_put(sk); + + _leave(" = 0"); + return 0; +} + +/* + * release an RxRPC BSD socket on close() or equivalent + */ +static int rxrpc_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + _enter("%p{%p}", sock, sk); + + if (!sk) + return 0; + + sock->sk = NULL; + + return rxrpc_release_sock(sk); +} + +/* + * RxRPC network protocol + */ +static const struct proto_ops rxrpc_rpc_ops = { + .family = PF_UNIX, + .owner = THIS_MODULE, + .release = rxrpc_release, + .bind = rxrpc_bind, + .connect = rxrpc_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = rxrpc_poll, + .ioctl = sock_no_ioctl, + .listen = rxrpc_listen, + .shutdown = sock_no_shutdown, + .setsockopt = rxrpc_setsockopt, + .getsockopt = sock_no_getsockopt, + .sendmsg = rxrpc_sendmsg, + .recvmsg = rxrpc_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static struct proto rxrpc_proto = { + .name = "RXRPC", + .owner = THIS_MODULE, + .obj_size = sizeof(struct rxrpc_sock), + .max_header = sizeof(struct rxrpc_header), +}; + +static struct net_proto_family rxrpc_family_ops = { + .family = PF_RXRPC, + .create = rxrpc_create, + .owner = THIS_MODULE, +}; + +/* + * initialise and register the RxRPC protocol + */ +static int __init af_rxrpc_init(void) +{ + struct sk_buff *dummy_skb; + int ret = -1; + + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof(dummy_skb->cb)); + + rxrpc_epoch = htonl(xtime.tv_sec); + + rxrpc_call_jar = kmem_cache_create( + "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + if (!rxrpc_call_jar) { + printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n"); + ret = -ENOMEM; + goto error_call_jar; + } + + ret = proto_register(&rxrpc_proto, 1); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: 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"); + goto error_sock; + } + + ret = register_key_type(&key_type_rxrpc); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: 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"); + goto error_key_type_s; + } + +#ifdef CONFIG_PROC_FS + proc_net_fops_create("rxrpc_calls", 0, &rxrpc_call_seq_fops); + proc_net_fops_create("rxrpc_conns", 0, &rxrpc_connection_seq_fops); +#endif + return 0; + +error_key_type_s: + unregister_key_type(&key_type_rxrpc); +error_key_type: + sock_unregister(PF_RXRPC); +error_sock: + proto_unregister(&rxrpc_proto); +error_proto: + kmem_cache_destroy(rxrpc_call_jar); +error_call_jar: + return ret; +} + +/* + * unregister the RxRPC protocol + */ +static void __exit af_rxrpc_exit(void) +{ + _enter(""); + unregister_key_type(&key_type_rxrpc_s); + unregister_key_type(&key_type_rxrpc); + sock_unregister(PF_RXRPC); + 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); + + _debug("flush scheduled work"); + flush_scheduled_work(); + proc_net_remove("rxrpc_conns"); + proc_net_remove("rxrpc_calls"); + kmem_cache_destroy(rxrpc_call_jar); + _leave(""); +} + +module_init(af_rxrpc_init); +module_exit(af_rxrpc_exit); diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c new file mode 100644 index 00000000000..e7af780cd6f --- /dev/null +++ b/net/rxrpc/ar-accept.c @@ -0,0 +1,399 @@ +/* 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. + */ + +#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" + +/* + * generate a connection-level abort + */ +static int rxrpc_busy(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, + struct rxrpc_header *hdr) +{ + struct msghdr msg; + struct kvec iov[1]; + size_t len; + int ret; + + _enter("%d,,", local->debug_id); + + 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; + + hdr->seq = 0; + hdr->type = RXRPC_PACKET_TYPE_BUSY; + hdr->flags = 0; + hdr->userStatus = 0; + hdr->_rsvd = 0; + + iov[0].iov_base = hdr; + iov[0].iov_len = sizeof(*hdr); + + len = iov[0].iov_len; + + hdr->serial = htonl(1); + _proto("Tx BUSY %%%u", ntohl(hdr->serial)); + + 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_transport *trans; + struct rxrpc_skb_priv *sp, *nsp; + struct rxrpc_peer *peer; + 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); + rxrpc_new_skb(notification); + notification->mark = RXRPC_SKB_MARK_NEW_CALL; + + peer = rxrpc_get_peer(srx, GFP_NOIO); + if (IS_ERR(peer)) { + _debug("no peer"); + ret = -EBUSY; + goto error; + } + + trans = rxrpc_get_transport(local, peer, GFP_NOIO); + rxrpc_put_peer(peer); + if (!trans) { + _debug("no trans"); + ret = -EBUSY; + goto error; + } + + conn = rxrpc_incoming_connection(trans, &sp->hdr, GFP_NOIO); + rxrpc_put_transport(trans); + if (IS_ERR(conn)) { + _debug("no conn"); + ret = PTR_ERR(conn); + goto error; + } + + call = rxrpc_incoming_call(rx, conn, &sp->hdr, GFP_NOIO); + 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_SERVER_UNSECURED) { + _debug("await conn sec"); + list_add_tail(&call->accept_link, &rx->secureq); + call->conn->state = RXRPC_CONN_SERVER_CHALLENGING; + atomic_inc(&call->conn->usage); + set_bit(RXRPC_CONN_CHALLENGE, &call->conn->events); + schedule_work(&call->conn->processor); + } else { + _debug("conn ready"); + call->state = RXRPC_CALL_SERVER_ACCEPTING; + list_add_tail(&call->accept_link, &rx->acceptq); + rxrpc_get_call(call); + 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; + if (ret < 0) + BUG(); + } + 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_RELEASE, &call->flags) && + !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events)) { + rxrpc_get_call(call); + schedule_work(&call->processor); + } + read_unlock_bh(&call->state_lock); + rxrpc_put_call(call); + ret = -ECONNREFUSED; +error: + rxrpc_free_skb(notification); + _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 work_struct *work) +{ + struct rxrpc_local *local = + container_of(work, struct rxrpc_local, acceptor); + struct rxrpc_skb_priv *sp; + struct sockaddr_rxrpc srx; + struct rxrpc_sock *rx; + struct sk_buff *skb; + __be16 service_id; + int ret; + + _enter("%d", local->debug_id); + + read_lock_bh(&rxrpc_local_lock); + if (atomic_read(&local->usage) > 0) + rxrpc_get_local(local); + else + local = NULL; + read_unlock_bh(&rxrpc_local_lock); + if (!local) { + _leave(" [local dead]"); + return; + } + +process_next_packet: + skb = skb_dequeue(&local->accept_queue); + if (!skb) { + rxrpc_put_local(local); + _leave("\n"); + return; + } + + _net("incoming call skb %p", skb); + + sp = rxrpc_skb(skb); + + /* determine the remote address */ + memset(&srx, 0, sizeof(srx)); + srx.srx_family = AF_RXRPC; + srx.transport.family = local->srx.transport.family; + srx.transport_type = local->srx.transport_type; + switch (srx.transport.family) { + case AF_INET: + srx.transport_len = sizeof(struct sockaddr_in); + srx.transport.sin.sin_port = udp_hdr(skb)->source; + srx.transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + break; + default: + goto busy; + } + + /* get the socket providing the service */ + service_id = sp->hdr.serviceId; + read_lock_bh(&local->services_lock); + list_for_each_entry(rx, &local->services, listen_link) { + if (rx->service_id == service_id && + rx->sk.sk_state != RXRPC_CLOSE) + goto found_service; + } + read_unlock_bh(&local->services_lock); + goto invalid_service; + +found_service: + _debug("found service %hd", ntohs(rx->service_id)); + 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: + goto process_next_packet; + 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, &sp->hdr); + rxrpc_free_skb(skb); + goto process_next_packet; + +invalid_service: + skb->priority = RX_INVALID_OPERATION; + rxrpc_reject_packet(local, skb); + goto process_next_packet; + + /* can't change connection security type mid-flow */ +security_mismatch: + skb->priority = RX_PROTOCOL_ERROR; + rxrpc_reject_packet(local, skb); + goto process_next_packet; +} + +/* + * handle acceptance of a call by userspace + * - assign the user call ID to the call at the front of the queue + */ +int 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_ACCEPTED, &call->events)) + BUG(); + schedule_work(&call->processor); + + write_unlock_bh(&call->state_lock); + write_unlock(&rx->call_lock); + _leave(" = 0"); + return 0; + + /* 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_RELEASE, &call->events)) + schedule_work(&call->processor); +out_discard: + write_unlock_bh(&call->state_lock); + _debug("discard %p", call); +out: + write_unlock(&rx->call_lock); + _leave(" = %d", ret); + return ret; +} diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c new file mode 100644 index 00000000000..8f7764eca96 --- /dev/null +++ b/net/rxrpc/ar-ack.c @@ -0,0 +1,1250 @@ +/* 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. + */ + +#include <linux/module.h> +#include <linux/circ_buf.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/udp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static unsigned rxrpc_ack_defer = 1; + +static const char *rxrpc_acks[] = { + "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", + "-?-" +}; + +static const s8 rxrpc_ack_priority[] = { + [0] = 0, + [RXRPC_ACK_DELAY] = 1, + [RXRPC_ACK_REQUESTED] = 2, + [RXRPC_ACK_IDLE] = 3, + [RXRPC_ACK_PING_RESPONSE] = 4, + [RXRPC_ACK_DUPLICATE] = 5, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 6, + [RXRPC_ACK_EXCEEDS_WINDOW] = 7, + [RXRPC_ACK_NOSPACE] = 8, +}; + +/* + * propose an ACK be sent + */ +void __rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, + __be32 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], ntohl(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"); + call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ; + add_timer(&call->ack_timer); + return; + + case RXRPC_ACK_IDLE: + if (!immediate) { + _debug("run defer timer"); + expiry = 1; + goto run_timer; + } + goto cancel_timer; + + case RXRPC_ACK_REQUESTED: + if (!rxrpc_ack_defer) + goto cancel_timer; + if (!immediate || serial == cpu_to_be32(1)) { + _debug("run defer timer"); + expiry = rxrpc_ack_defer; + 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", ntohl(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_ACK, &call->events)) + schedule_work(&call->processor); + read_unlock_bh(&call->state_lock); +} + +/* + * propose an ACK be sent, locking the call structure + */ +void rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, + __be32 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_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_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_skb_priv *sp; + struct rxrpc_header *hdr; + struct sk_buff *txb; + unsigned long *p_txb, resend_at; + int loop, stop; + 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 = 0; + 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 = 0; + + /* each Tx packet has a new serial number */ + sp->hdr.serial = + htonl(atomic_inc_return(&call->conn->serial)); + + hdr = (struct rxrpc_header *) txb->head; + hdr->serial = sp->hdr.serial; + + _proto("Tx DATA %%%u { #%d }", + ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); + if (rxrpc_send_packet(call->conn->trans, txb) < 0) { + stop = 0; + sp->resend_at = jiffies + 3; + } else { + sp->resend_at = + jiffies + rxrpc_resend_timeout * HZ; + } + } + + if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = 1; + 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); + + 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 = 1; + 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 = 0; + *p_txb |= 1; + break; + case RXRPC_ACK_TYPE_NACK: + sp->need_resend = 1; + *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 = 1; + *p_txb &= ~1; + resend |= 1; + } else if (sp->need_resend) { + ; + } else if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = 1; + 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) +{ + struct rxrpc_skb_priv *sp; + 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; + sp = rxrpc_skb((struct sk_buff *) _skb); + 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]", + ntohl(sp->hdr.seq), call->rx_first_oos); + + if (ntohl(sp->hdr.seq) != call->rx_first_oos) { + skb_queue_head(&call->rx_oos_queue, skb); + call->rx_first_oos = ntohl(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 = + ntohl(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 = ntohl(sp->hdr.seq); + _enter(",,{%u}", seq); + + skb->destructor = rxrpc_packet_destructor; + ASSERTCMP(sp->call, ==, NULL); + sp->call = call; + rxrpc_get_call(call); + + /* 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 (ntohl(psp->hdr.seq) > seq) { + _debug("insert oos #%u before #%u", + seq, ntohl(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_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; + uint8_t 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", ntohl(sp->hdr.seq)); + rxrpc_free_skb(skb); + } + + kfree(acks_window); +} + +/* + * 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 }", + ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); + + /* secured packets must be verified and possibly decrypted */ + if (rxrpc_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 = ntohl(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); + + 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) + 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_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); + 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); + + spin_lock_bh(&call->lock); + ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); + spin_unlock_bh(&call->lock); + if (ret < 0) + BUG(); + } + + 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_ackpacket ack; + struct rxrpc_ackinfo ackinfo; + struct rxrpc_header hdr; + struct msghdr msg; + struct kvec iov[5]; + unsigned long bits; + __be32 data; + size_t len; + int genbit, loop, nbit, ioc, ret; + u32 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; + } + + /* there's a good chance we're going to have to send a message, so set + * one up in advance */ + msg.msg_name = &call->conn->trans->peer->srx.transport.sin; + msg.msg_namelen = sizeof(call->conn->trans->peer->srx.transport.sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr.epoch = call->conn->epoch; + hdr.cid = call->cid; + hdr.callNumber = call->call_id; + hdr.seq = 0; + hdr.type = RXRPC_PACKET_TYPE_ACK; + hdr.flags = call->conn->out_clientflag; + hdr.userStatus = 0; + hdr.securityIndex = call->conn->security_ix; + hdr._rsvd = 0; + hdr.serviceId = call->conn->service_id; + + memset(iov, 0, sizeof(iov)); + iov[0].iov_base = &hdr; + iov[0].iov_len = sizeof(hdr); + + /* deal with events of a final nature */ + if (test_bit(RXRPC_CALL_RELEASE, &call->events)) { + rxrpc_release_call(call); + clear_bit(RXRPC_CALL_RELEASE, &call->events); + } + + if (test_bit(RXRPC_CALL_RCVD_ERROR, &call->events)) { + int error; + + clear_bit(RXRPC_CALL_CONN_ABORT, &call->events); + clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events); + clear_bit(RXRPC_CALL_ABORT, &call->events); + + error = call->conn->trans->peer->net_error; + _debug("post net error %d", error); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR, + error, true) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_RCVD_ERROR, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_CONN_ABORT, &call->events)) { + ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + + clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events); + clear_bit(RXRPC_CALL_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_CONN_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_REJECT_BUSY, &call->events)) { + hdr.type = RXRPC_PACKET_TYPE_BUSY; + genbit = RXRPC_CALL_REJECT_BUSY; + goto send_message; + } + + if (test_bit(RXRPC_CALL_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; + hdr.type = RXRPC_PACKET_TYPE_ABORT; + data = htonl(call->abort_code); + iov[1].iov_base = &data; + iov[1].iov_len = sizeof(data); + genbit = RXRPC_CALL_ABORT; + goto send_message; + } + + if (test_bit(RXRPC_CALL_ACK_FINAL, &call->events)) { + hdr.type = RXRPC_PACKET_TYPE_ACKALL; + genbit = RXRPC_CALL_ACK_FINAL; + goto send_message; + } + + if (call->events & ((1 << RXRPC_CALL_RCVD_BUSY) | + (1 << RXRPC_CALL_RCVD_ABORT)) + ) { + u32 mark; + + if (test_bit(RXRPC_CALL_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_RCVD_BUSY, &call->events); + clear_bit(RXRPC_CALL_RCVD_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_and_clear_bit(RXRPC_CALL_RCVD_ACKALL, &call->events)) { + _debug("do implicit ackall"); + rxrpc_clear_tx_window(call); + } + + if (test_bit(RXRPC_CALL_LIFE_TIMER, &call->events)) { + write_lock_bh(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->abort_code = RX_CALL_TIMEOUT; + set_bit(RXRPC_CALL_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_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_RESEND_TIMER, &call->events)) + rxrpc_resend_timer(call); + if (test_and_clear_bit(RXRPC_CALL_RESEND, &call->events)) + rxrpc_resend(call); + + /* consider sending an ordinary ACK */ + if (test_bit(RXRPC_CALL_ACK, &call->events)) { + __be32 pad; + + _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_ACK, &call->events); + goto maybe_reschedule; + } + + genbit = RXRPC_CALL_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; + ack.serial = 0; + ack.reason = 0; + + ackinfo.rxMTU = htonl(5692); +// ackinfo.rxMTU = htonl(call->conn->trans->peer->maxdata); + ackinfo.maxMTU = htonl(call->conn->trans->peer->maxdata); + ackinfo.rwind = htonl(32); + ackinfo.jumbo_max = htonl(4); + + spin_lock_bh(&call->lock); + ack.reason = call->ackr_reason; + ack.serial = call->ackr_serial; + ack.previousPacket = 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_SECURED, &call->events)) { + _debug("secured"); + spin_lock_bh(&call->lock); + + if (call->state == RXRPC_CALL_SERVER_SECURING) { + _debug("securing"); + write_lock(&call->conn->lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_bit(RXRPC_CALL_RELEASE, &call->events)) { + _debug("not released"); + call->state = RXRPC_CALL_SERVER_ACCEPTING; + list_move_tail(&call->accept_link, + &call->socket->acceptq); + } + write_unlock(&call->conn->lock); + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) + set_bit(RXRPC_CALL_POST_ACCEPT, &call->events); + read_unlock(&call->state_lock); + } + + spin_unlock_bh(&call->lock); + if (!test_bit(RXRPC_CALL_POST_ACCEPT, &call->events)) + goto maybe_reschedule; + } + + /* post a notification of an acceptable connection to the app */ + if (test_bit(RXRPC_CALL_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_POST_ACCEPT, &call->events); + goto maybe_reschedule; + } + + /* handle incoming call acceptance */ + if (test_and_clear_bit(RXRPC_CALL_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_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_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; + } + + /* 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: + hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); + _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", + ntohl(hdr.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"); + + hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); + _proto("Tx %s %%%u", rxrpc_pkts[hdr.type], ntohl(hdr.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->trans->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) + schedule_work(&call->processor); + read_unlock_bh(&call->state_lock); + goto error; + } + + switch (genbit) { + case RXRPC_CALL_ABORT: + clear_bit(genbit, &call->events); + clear_bit(RXRPC_CALL_RCVD_ABORT, &call->events); + goto kill_ACKs; + + case RXRPC_CALL_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_ACK_FINAL, &call->events)) + rxrpc_put_call(call); + clear_bit(RXRPC_CALL_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) + schedule_work(&call->processor); + 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, + ntohl(call->conn->cid)); + + read_lock_bh(&call->state_lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events)) + schedule_work(&call->processor); + 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", ntohl(call->conn->cid)); + schedule_work(&call->processor); + } + + _leave(""); + return; + +no_mem: + _debug("out of memory"); + goto maybe_reschedule; +} diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c new file mode 100644 index 00000000000..ac31cceda2f --- /dev/null +++ b/net/rxrpc/ar-call.c @@ -0,0 +1,787 @@ +/* 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. + */ + +#include <linux/module.h> +#include <linux/circ_buf.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +struct kmem_cache *rxrpc_call_jar; +LIST_HEAD(rxrpc_calls); +DEFINE_RWLOCK(rxrpc_call_lock); +static unsigned rxrpc_call_max_lifetime = 60; +static unsigned rxrpc_dead_call_timeout = 10; + +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); + +/* + * 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->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); + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; + + 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_MAXACKS; + call->creation_jif = jiffies; + return call; +} + +/* + * allocate a new client call and attempt to to get a connection slot for it + */ +static struct rxrpc_call *rxrpc_alloc_client_call( + struct rxrpc_sock *rx, + struct rxrpc_transport *trans, + struct rxrpc_conn_bundle *bundle, + gfp_t gfp) +{ + struct rxrpc_call *call; + int ret; + + _enter(""); + + ASSERT(rx != NULL); + ASSERT(trans != NULL); + ASSERT(bundle != NULL); + + call = rxrpc_alloc_call(gfp); + if (!call) + return ERR_PTR(-ENOMEM); + + sock_hold(&rx->sk); + call->socket = rx; + call->rx_data_post = 1; + + ret = rxrpc_connect_call(rx, trans, bundle, call, gfp); + if (ret < 0) { + kmem_cache_free(rxrpc_call_jar, call); + return ERR_PTR(ret); + } + + spin_lock(&call->conn->trans->peer->lock); + list_add(&call->error_link, &call->conn->trans->peer->error_targets); + spin_unlock(&call->conn->trans->peer->lock); + + call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + add_timer(&call->lifetimer); + + _leave(" = %p", call); + return call; +} + +/* + * set up a call for the given data + * - called in process context with IRQs enabled + */ +struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, + struct rxrpc_transport *trans, + struct rxrpc_conn_bundle *bundle, + unsigned long user_call_ID, + int create, + gfp_t gfp) +{ + struct rxrpc_call *call, *candidate; + struct rb_node *p, *parent, **pp; + + _enter("%p,%d,%d,%lx,%d", + rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1, + user_call_ID, create); + + /* search the extant calls first for one that matches the specified + * user ID */ + read_lock(&rx->call_lock); + + p = rx->calls.rb_node; + while (p) { + call = rb_entry(p, struct rxrpc_call, sock_node); + + if (user_call_ID < call->user_call_ID) + p = p->rb_left; + else if (user_call_ID > call->user_call_ID) + p = p->rb_right; + else + goto found_extant_call; + } + + read_unlock(&rx->call_lock); + + if (!create || !trans) + return ERR_PTR(-EBADSLT); + + /* not yet present - create a candidate for a new record and then + * redo the search */ + candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp); + if (IS_ERR(candidate)) { + _leave(" = %ld", PTR_ERR(candidate)); + return candidate; + } + + candidate->user_call_ID = user_call_ID; + __set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags); + + write_lock(&rx->call_lock); + + 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 found_extant_second; + } + + /* second search also failed; add the new call */ + call = candidate; + candidate = NULL; + 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); + + _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); + + _leave(" = %p [new]", call); + return call; + + /* we found the call in the list immediately */ +found_extant_call: + rxrpc_get_call(call); + read_unlock(&rx->call_lock); + _leave(" = %p [extant %d]", call, atomic_read(&call->usage)); + return call; + + /* we found the call on the second time through the list */ +found_extant_second: + rxrpc_get_call(call); + write_unlock(&rx->call_lock); + rxrpc_put_call(candidate); + _leave(" = %p [second %d]", call, atomic_read(&call->usage)); + return call; +} + +/* + * 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 rxrpc_header *hdr, + gfp_t gfp) +{ + struct rxrpc_call *call, *candidate; + struct rb_node **p, *parent; + __be32 call_id; + + _enter(",%d,,%x", conn->debug_id, gfp); + + ASSERT(rx != NULL); + + candidate = rxrpc_alloc_call(gfp); + if (!candidate) + return ERR_PTR(-EBUSY); + + candidate->socket = rx; + candidate->conn = conn; + candidate->cid = hdr->cid; + candidate->call_id = hdr->callNumber; + candidate->channel = ntohl(hdr->cid) & RXRPC_CHANNELMASK; + candidate->rx_data_post = 0; + candidate->state = RXRPC_CALL_SERVER_ACCEPTING; + if (conn->security_ix > 0) + candidate->state = RXRPC_CALL_SERVER_SECURING; + + write_lock_bh(&conn->lock); + + /* set the channel for this call */ + call = conn->channels[candidate->channel]; + _debug("channel[%u] is %p", candidate->channel, call); + if (call && call->call_id == 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_ABORT, &call->events)) + schedule_work(&call->processor); + 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) { + conn->channels[call->channel] = NULL; + } else { + write_unlock_bh(&conn->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 = hdr->callNumber; + p = &conn->calls.rb_node; + parent = NULL; + while (*p) { + parent = *p; + call = rb_entry(parent, struct rxrpc_call, conn_node); + + if (call_id < call->call_id) + p = &(*p)->rb_left; + else if (call_id > call->call_id) + p = &(*p)->rb_right; + else + goto old_call; + } + + /* make the call available */ + _debug("new call"); + call = candidate; + candidate = NULL; + rb_link_node(&call->conn_node, parent, p); + rb_insert_color(&call->conn_node, &conn->calls); + conn->channels[call->channel] = call; + sock_hold(&rx->sk); + atomic_inc(&conn->usage); + write_unlock_bh(&conn->lock); + + spin_lock(&conn->trans->peer->lock); + list_add(&call->error_link, &conn->trans->peer->error_targets); + spin_unlock(&conn->trans->peer->lock); + + write_lock_bh(&rxrpc_call_lock); + list_add_tail(&call->link, &rxrpc_calls); + write_unlock_bh(&rxrpc_call_lock); + + _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); + + call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + add_timer(&call->lifetimer); + _leave(" = %p {%d} [new]", call, call->debug_id); + return call; + +extant_call: + write_unlock_bh(&conn->lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = %p {%d} [extant]", call, call ? call->debug_id : -1); + return call; + +aborted_call: + write_unlock_bh(&conn->lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = -ECONNABORTED"); + return ERR_PTR(-ECONNABORTED); + +old_call: + write_unlock_bh(&conn->lock); + kmem_cache_free(rxrpc_call_jar, candidate); + _leave(" = -ECONNRESET [old]"); + return ERR_PTR(-ECONNRESET); +} + +/* + * find an extant server call + * - called in process context with IRQs enabled + */ +struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *rx, + unsigned long user_call_ID) +{ + struct rxrpc_call *call; + struct rb_node *p; + + _enter("%p,%lx", rx, user_call_ID); + + /* search the extant calls for one that matches the specified user + * ID */ + read_lock(&rx->call_lock); + + p = rx->calls.rb_node; + while (p) { + call = rb_entry(p, struct rxrpc_call, sock_node); + + if (user_call_ID < call->user_call_ID) + p = p->rb_left; + else if (user_call_ID > call->user_call_ID) + p = p->rb_right; + else + goto found_extant_call; + } + + read_unlock(&rx->call_lock); + _leave(" = NULL"); + return NULL; + + /* we found the call in the list immediately */ +found_extant_call: + rxrpc_get_call(call); + read_unlock(&rx->call_lock); + _leave(" = %p [%d]", call, atomic_read(&call->usage)); + return call; +} + +/* + * detach a call from a socket and set up for release + */ +void rxrpc_release_call(struct rxrpc_call *call) +{ + 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, call->conn); + + 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); + + if (call->conn->out_clientflag) + spin_lock(&call->conn->trans->client_lock); + write_lock_bh(&call->conn->lock); + + /* free up the channel for reuse */ + if (call->conn->out_clientflag) { + call->conn->avail_calls++; + if (call->conn->avail_calls == RXRPC_MAXCALLS) + list_move_tail(&call->conn->bundle_link, + &call->conn->bundle->unused_conns); + else if (call->conn->avail_calls == 1) + list_move_tail(&call->conn->bundle_link, + &call->conn->bundle->avail_conns); + } + + write_lock(&call->state_lock); + if (call->conn->channels[call->channel] == call) + call->conn->channels[call->channel] = NULL; + + 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->abort_code = RX_CALL_DEAD; + set_bit(RXRPC_CALL_ABORT, &call->events); + schedule_work(&call->processor); + } + write_unlock(&call->state_lock); + write_unlock_bh(&call->conn->lock); + if (call->conn->out_clientflag) + spin_unlock(&call->conn->trans->client_lock); + + 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))) { + sp = rxrpc_skb(skb); + if (sp->call) { + ASSERTCMP(sp->call, ==, call); + rxrpc_put_call(call); + sp->call = NULL; + } + skb->destructor = NULL; + spin_unlock_bh(&call->lock); + + _debug("- zap %s %%%u #%u", + rxrpc_pkts[sp->hdr.type], + ntohl(sp->hdr.serial), + ntohl(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_timeout * HZ; + 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->abort_code = RX_CALL_DEAD; + if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) + sched = true; + } + if (!test_and_set_bit(RXRPC_CALL_RELEASE, &call->events)) + sched = true; + if (sched) + schedule_work(&call->processor); + } + 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); + ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); + schedule_work(&call->destroyer); + } + _leave(""); +} + +/* + * 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"); + schedule_work(&call->destroyer); + return; + } + + if (call->conn) { + spin_lock(&call->conn->trans->peer->lock); + list_del(&call->error_link); + spin_unlock(&call->conn->trans->peer->lock); + + write_lock_bh(&call->conn->lock); + rb_erase(&call->conn_node, &call->conn->calls); + write_unlock_bh(&call->conn->lock); + rxrpc_put_connection(call->conn); + } + + 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", ntohl(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); + kmem_cache_free(rxrpc_call_jar, 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: + printk(KERN_ERR "RXRPC:" + " Call %p still in use (%d,%d,%s,%lx,%lx)!\n", + call, atomic_read(&call->usage), + atomic_read(&call->ackr_not_idle), + rxrpc_call_states[call->state], + call->flags, call->events); + if (!skb_queue_empty(&call->rx_queue)) + printk(KERN_ERR"RXRPC: Rx queue occupied\n"); + if (!skb_queue_empty(&call->rx_oos_queue)) + printk(KERN_ERR"RXRPC: 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_LIFE_TIMER, &call->events); + schedule_work(&call->processor); + } + read_unlock_bh(&call->state_lock); +} + +/* + * handle resend timer expiry + */ +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; + + read_lock_bh(&call->state_lock); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + if (call->state < RXRPC_CALL_COMPLETE && + !test_and_set_bit(RXRPC_CALL_RESEND_TIMER, &call->events)) + schedule_work(&call->processor); + read_unlock_bh(&call->state_lock); +} + +/* + * 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_ACK, &call->events)) + schedule_work(&call->processor); + read_unlock_bh(&call->state_lock); +} diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c new file mode 100644 index 00000000000..01eb33c3057 --- /dev/null +++ b/net/rxrpc/ar-connection.c @@ -0,0 +1,895 @@ +/* RxRPC virtual connection handler + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/crypto.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static void rxrpc_connection_reaper(struct work_struct *work); + +LIST_HEAD(rxrpc_connections); +DEFINE_RWLOCK(rxrpc_connection_lock); +static unsigned long rxrpc_connection_timeout = 10 * 60; +static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); + +/* + * allocate a new client connection bundle + */ +static struct rxrpc_conn_bundle *rxrpc_alloc_bundle(gfp_t gfp) +{ + struct rxrpc_conn_bundle *bundle; + + _enter(""); + + bundle = kzalloc(sizeof(struct rxrpc_conn_bundle), gfp); + if (bundle) { + INIT_LIST_HEAD(&bundle->unused_conns); + INIT_LIST_HEAD(&bundle->avail_conns); + INIT_LIST_HEAD(&bundle->busy_conns); + init_waitqueue_head(&bundle->chanwait); + atomic_set(&bundle->usage, 1); + } + + _leave(" = %p", bundle); + return bundle; +} + +/* + * compare bundle parameters with what we're looking for + * - return -ve, 0 or +ve + */ +static inline +int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle, + struct key *key, __be16 service_id) +{ + return (bundle->service_id - service_id) ?: + ((unsigned long) bundle->key - (unsigned long) key); +} + +/* + * get bundle of client connections that a client socket can make use of + */ +struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx, + struct rxrpc_transport *trans, + struct key *key, + __be16 service_id, + gfp_t gfp) +{ + struct rxrpc_conn_bundle *bundle, *candidate; + struct rb_node *p, *parent, **pp; + + _enter("%p{%x},%x,%hx,", + rx, key_serial(key), trans->debug_id, ntohl(service_id)); + + if (rx->trans == trans && rx->bundle) { + atomic_inc(&rx->bundle->usage); + return rx->bundle; + } + + /* search the extant bundles first for one that matches the specified + * user ID */ + spin_lock(&trans->client_lock); + + p = trans->bundles.rb_node; + while (p) { + bundle = rb_entry(p, struct rxrpc_conn_bundle, node); + + if (rxrpc_cmp_bundle(bundle, key, service_id) < 0) + p = p->rb_left; + else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0) + p = p->rb_right; + else + goto found_extant_bundle; + } + + spin_unlock(&trans->client_lock); + + /* not yet present - create a candidate for a new record and then + * redo the search */ + candidate = rxrpc_alloc_bundle(gfp); + if (!candidate) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + candidate->key = key_get(key); + candidate->service_id = service_id; + + spin_lock(&trans->client_lock); + + pp = &trans->bundles.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + bundle = rb_entry(parent, struct rxrpc_conn_bundle, node); + + if (rxrpc_cmp_bundle(bundle, key, service_id) < 0) + pp = &(*pp)->rb_left; + else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0) + pp = &(*pp)->rb_right; + else + goto found_extant_second; + } + + /* second search also failed; add the new bundle */ + bundle = candidate; + candidate = NULL; + + rb_link_node(&bundle->node, parent, pp); + rb_insert_color(&bundle->node, &trans->bundles); + spin_unlock(&trans->client_lock); + _net("BUNDLE new on trans %d", trans->debug_id); + if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { + atomic_inc(&bundle->usage); + rx->bundle = bundle; + } + _leave(" = %p [new]", bundle); + return bundle; + + /* we found the bundle in the list immediately */ +found_extant_bundle: + atomic_inc(&bundle->usage); + spin_unlock(&trans->client_lock); + _net("BUNDLE old on trans %d", trans->debug_id); + if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { + atomic_inc(&bundle->usage); + rx->bundle = bundle; + } + _leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage)); + return bundle; + + /* we found the bundle on the second time through the list */ +found_extant_second: + atomic_inc(&bundle->usage); + spin_unlock(&trans->client_lock); + kfree(candidate); + _net("BUNDLE old2 on trans %d", trans->debug_id); + if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { + atomic_inc(&bundle->usage); + rx->bundle = bundle; + } + _leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage)); + return bundle; +} + +/* + * release a bundle + */ +void rxrpc_put_bundle(struct rxrpc_transport *trans, + struct rxrpc_conn_bundle *bundle) +{ + _enter("%p,%p{%d}",trans, bundle, atomic_read(&bundle->usage)); + + if (atomic_dec_and_lock(&bundle->usage, &trans->client_lock)) { + _debug("Destroy bundle"); + rb_erase(&bundle->node, &trans->bundles); + spin_unlock(&trans->client_lock); + ASSERT(list_empty(&bundle->unused_conns)); + ASSERT(list_empty(&bundle->avail_conns)); + ASSERT(list_empty(&bundle->busy_conns)); + ASSERTCMP(bundle->num_conns, ==, 0); + key_put(bundle->key); + kfree(bundle); + } + + _leave(""); +} + +/* + * allocate a new connection + */ +static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) +{ + struct rxrpc_connection *conn; + + _enter(""); + + conn = kzalloc(sizeof(struct rxrpc_connection), gfp); + if (conn) { + INIT_WORK(&conn->processor, &rxrpc_process_connection); + INIT_LIST_HEAD(&conn->bundle_link); + conn->calls = RB_ROOT; + skb_queue_head_init(&conn->rx_queue); + rwlock_init(&conn->lock); + spin_lock_init(&conn->state_lock); + atomic_set(&conn->usage, 1); + conn->debug_id = atomic_inc_return(&rxrpc_debug_id); + conn->avail_calls = RXRPC_MAXCALLS; + conn->size_align = 4; + conn->header_size = sizeof(struct rxrpc_header); + } + + _leave(" = %p{%d}", conn, conn->debug_id); + return conn; +} + +/* + * assign a connection ID to a connection and add it to the transport's + * connection lookup tree + * - called with transport client lock held + */ +static void rxrpc_assign_connection_id(struct rxrpc_connection *conn) +{ + struct rxrpc_connection *xconn; + struct rb_node *parent, **p; + __be32 epoch; + u32 real_conn_id; + + _enter(""); + + epoch = conn->epoch; + + write_lock_bh(&conn->trans->conn_lock); + + conn->trans->conn_idcounter += RXRPC_CID_INC; + if (conn->trans->conn_idcounter < RXRPC_CID_INC) + conn->trans->conn_idcounter = RXRPC_CID_INC; + real_conn_id = conn->trans->conn_idcounter; + +attempt_insertion: + parent = NULL; + p = &conn->trans->client_conns.rb_node; + + while (*p) { + parent = *p; + xconn = rb_entry(parent, struct rxrpc_connection, node); + + if (epoch < xconn->epoch) + p = &(*p)->rb_left; + else if (epoch > xconn->epoch) + p = &(*p)->rb_right; + else if (real_conn_id < xconn->real_conn_id) + p = &(*p)->rb_left; + else if (real_conn_id > xconn->real_conn_id) + p = &(*p)->rb_right; + else + goto id_exists; + } + + /* we've found a suitable hole - arrange for this connection to occupy + * it */ + rb_link_node(&conn->node, parent, p); + rb_insert_color(&conn->node, &conn->trans->client_conns); + + conn->real_conn_id = real_conn_id; + conn->cid = htonl(real_conn_id); + write_unlock_bh(&conn->trans->conn_lock); + _leave(" [CONNID %x CID %x]", real_conn_id, ntohl(conn->cid)); + return; + + /* we found a connection with the proposed ID - walk the tree from that + * point looking for the next unused ID */ +id_exists: + for (;;) { + real_conn_id += RXRPC_CID_INC; + if (real_conn_id < RXRPC_CID_INC) { + real_conn_id = RXRPC_CID_INC; + conn->trans->conn_idcounter = real_conn_id; + goto attempt_insertion; + } + + parent = rb_next(parent); + if (!parent) + goto attempt_insertion; + + xconn = rb_entry(parent, struct rxrpc_connection, node); + if (epoch < xconn->epoch || + real_conn_id < xconn->real_conn_id) + goto attempt_insertion; + } +} + +/* + * add a call to a connection's call-by-ID tree + */ +static void rxrpc_add_call_ID_to_conn(struct rxrpc_connection *conn, + struct rxrpc_call *call) +{ + struct rxrpc_call *xcall; + struct rb_node *parent, **p; + __be32 call_id; + + write_lock_bh(&conn->lock); + + call_id = call->call_id; + p = &conn->calls.rb_node; + parent = NULL; + while (*p) { + parent = *p; + xcall = rb_entry(parent, struct rxrpc_call, conn_node); + + if (call_id < xcall->call_id) + p = &(*p)->rb_left; + else if (call_id > xcall->call_id) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&call->conn_node, parent, p); + rb_insert_color(&call->conn_node, &conn->calls); + + write_unlock_bh(&conn->lock); +} + +/* + * connect a call on an exclusive connection + */ +static int rxrpc_connect_exclusive(struct rxrpc_sock *rx, + struct rxrpc_transport *trans, + __be16 service_id, + struct rxrpc_call *call, + gfp_t gfp) +{ + struct rxrpc_connection *conn; + int chan, ret; + + _enter(""); + + conn = rx->conn; + if (!conn) { + /* not yet present - create a candidate for a new connection + * and then redo the check */ + conn = rxrpc_alloc_connection(gfp); + if (IS_ERR(conn)) { + _leave(" = %ld", PTR_ERR(conn)); + return PTR_ERR(conn); + } + + conn->trans = trans; + conn->bundle = NULL; + conn->service_id = service_id; + conn->epoch = rxrpc_epoch; + conn->in_clientflag = 0; + conn->out_clientflag = RXRPC_CLIENT_INITIATED; + conn->cid = 0; + conn->state = RXRPC_CONN_CLIENT; + conn->avail_calls = RXRPC_MAXCALLS; + conn->security_level = rx->min_sec_level; + conn->key = key_get(rx->key); + + ret = rxrpc_init_client_conn_security(conn); + if (ret < 0) { + key_put(conn->key); + kfree(conn); + _leave(" = %d [key]", ret); + return ret; + } + + write_lock_bh(&rxrpc_connection_lock); + list_add_tail(&conn->link, &rxrpc_connections); + write_unlock_bh(&rxrpc_connection_lock); + + spin_lock(&trans->client_lock); + atomic_inc(&trans->usage); + + _net("CONNECT EXCL new %d on TRANS %d", + conn->debug_id, conn->trans->debug_id); + + rxrpc_assign_connection_id(conn); + rx->conn = conn; + } + + /* we've got a connection with a free channel and we can now attach the + * call to it + * - we're holding the transport's client lock + * - we're holding a reference on the connection + */ + for (chan = 0; chan < RXRPC_MAXCALLS; chan++) + if (!conn->channels[chan]) + goto found_channel; + goto no_free_channels; + +found_channel: + atomic_inc(&conn->usage); + conn->channels[chan] = call; + call->conn = conn; + call->channel = chan; + call->cid = conn->cid | htonl(chan); + call->call_id = htonl(++conn->call_counter); + + _net("CONNECT client on conn %d chan %d as call %x", + conn->debug_id, chan, ntohl(call->call_id)); + + spin_unlock(&trans->client_lock); + + rxrpc_add_call_ID_to_conn(conn, call); + _leave(" = 0"); + return 0; + +no_free_channels: + spin_unlock(&trans->client_lock); + _leave(" = -ENOSR"); + return -ENOSR; +} + +/* + * find a connection for a call + * - called in process context with IRQs enabled + */ +int rxrpc_connect_call(struct rxrpc_sock *rx, + struct rxrpc_transport *trans, + struct rxrpc_conn_bundle *bundle, + struct rxrpc_call *call, + gfp_t gfp) +{ + struct rxrpc_connection *conn, *candidate; + int chan, ret; + + DECLARE_WAITQUEUE(myself, current); + + _enter("%p,%lx,", rx, call->user_call_ID); + + if (test_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags)) + return rxrpc_connect_exclusive(rx, trans, bundle->service_id, + call, gfp); + + spin_lock(&trans->client_lock); + for (;;) { + /* see if the bundle has a call slot available */ + if (!list_empty(&bundle->avail_conns)) { + _debug("avail"); + conn = list_entry(bundle->avail_conns.next, + struct rxrpc_connection, + bundle_link); + if (--conn->avail_calls == 0) + list_move(&conn->bundle_link, + &bundle->busy_conns); + atomic_inc(&conn->usage); + break; + } + + if (!list_empty(&bundle->unused_conns)) { + _debug("unused"); + conn = list_entry(bundle->unused_conns.next, + struct rxrpc_connection, + bundle_link); + atomic_inc(&conn->usage); + list_move(&conn->bundle_link, &bundle->avail_conns); + break; + } + + /* need to allocate a new connection */ + _debug("get new conn [%d]", bundle->num_conns); + + spin_unlock(&trans->client_lock); + + if (signal_pending(current)) + goto interrupted; + + if (bundle->num_conns >= 20) { + _debug("too many conns"); + + if (!(gfp & __GFP_WAIT)) { + _leave(" = -EAGAIN"); + return -EAGAIN; + } + + add_wait_queue(&bundle->chanwait, &myself); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (bundle->num_conns < 20 || + !list_empty(&bundle->unused_conns) || + !list_empty(&bundle->avail_conns)) + break; + if (signal_pending(current)) + goto interrupted_dequeue; + schedule(); + } + remove_wait_queue(&bundle->chanwait, &myself); + __set_current_state(TASK_RUNNING); + spin_lock(&trans->client_lock); + continue; + } + + /* not yet present - create a candidate for a new connection and then + * redo the check */ + candidate = rxrpc_alloc_connection(gfp); + if (IS_ERR(candidate)) { + _leave(" = %ld", PTR_ERR(candidate)); + return PTR_ERR(candidate); + } + + candidate->trans = trans; + candidate->bundle = bundle; + candidate->service_id = bundle->service_id; + candidate->epoch = rxrpc_epoch; + candidate->in_clientflag = 0; + candidate->out_clientflag = RXRPC_CLIENT_INITIATED; + candidate->cid = 0; + candidate->state = RXRPC_CONN_CLIENT; + candidate->avail_calls = RXRPC_MAXCALLS; + candidate->security_level = rx->min_sec_level; + candidate->key = key_get(rx->key); + + ret = rxrpc_init_client_conn_security(candidate); + if (ret < 0) { + key_put(candidate->key); + kfree(candidate); + _leave(" = %d [key]", ret); + return ret; + } + + write_lock_bh(&rxrpc_connection_lock); + list_add_tail(&candidate->link, &rxrpc_connections); + write_unlock_bh(&rxrpc_connection_lock); + + spin_lock(&trans->client_lock); + + list_add(&candidate->bundle_link, &bundle->unused_conns); + bundle->num_conns++; + atomic_inc(&bundle->usage); + atomic_inc(&trans->usage); + + _net("CONNECT new %d on TRANS %d", + candidate->debug_id, candidate->trans->debug_id); + + rxrpc_assign_connection_id(candidate); + if (candidate->security) + candidate->security->prime_packet_security(candidate); + + /* leave the candidate lurking in zombie mode attached to the + * bundle until we're ready for it */ + rxrpc_put_connection(candidate); + candidate = NULL; + } + + /* we've got a connection with a free channel and we can now attach the + * call to it + * - we're holding the transport's client lock + * - we're holding a reference on the connection + * - we're holding a reference on the bundle + */ + for (chan = 0; chan < RXRPC_MAXCALLS; chan++) + if (!conn->channels[chan]) + goto found_channel; + BUG(); + +found_channel: + conn->channels[chan] = call; + call->conn = conn; + call->channel = chan; + call->cid = conn->cid | htonl(chan); + call->call_id = htonl(++conn->call_counter); + + _net("CONNECT client on conn %d chan %d as call %x", + conn->debug_id, chan, ntohl(call->call_id)); + + spin_unlock(&trans->client_lock); + + rxrpc_add_call_ID_to_conn(conn, call); + + _leave(" = 0"); + return 0; + +interrupted_dequeue: + remove_wait_queue(&bundle->chanwait, &myself); + __set_current_state(TASK_RUNNING); +interrupted: + _leave(" = -ERESTARTSYS"); + return -ERESTARTSYS; +} + +/* + * get a record of an incoming connection + */ +struct rxrpc_connection * +rxrpc_incoming_connection(struct rxrpc_transport *trans, + struct rxrpc_header *hdr, + gfp_t gfp) +{ + struct rxrpc_connection *conn, *candidate = NULL; + struct rb_node *p, **pp; + const char *new = "old"; + __be32 epoch; + u32 conn_id; + + _enter(""); + + ASSERT(hdr->flags & RXRPC_CLIENT_INITIATED); + + epoch = hdr->epoch; + conn_id = ntohl(hdr->cid) & RXRPC_CIDMASK; + + /* search the connection list first */ + read_lock_bh(&trans->conn_lock); + + p = trans->server_conns.rb_node; + while (p) { + conn = rb_entry(p, struct rxrpc_connection, node); + + _debug("maybe %x", conn->real_conn_id); + + if (epoch < conn->epoch) + p = p->rb_left; + else if (epoch > conn->epoch) + p = p->rb_right; + else if (conn_id < conn->real_conn_id) + p = p->rb_left; + else if (conn_id > conn->real_conn_id) + p = p->rb_right; + else + goto found_extant_connection; + } + read_unlock_bh(&trans->conn_lock); + + /* not yet present - create a candidate for a new record and then + * redo the search */ + candidate = rxrpc_alloc_connection(gfp); + if (!candidate) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + candidate->trans = trans; + candidate->epoch = hdr->epoch; + candidate->cid = hdr->cid & __constant_cpu_to_be32(RXRPC_CIDMASK); + candidate->service_id = hdr->serviceId; + candidate->security_ix = hdr->securityIndex; + candidate->in_clientflag = RXRPC_CLIENT_INITIATED; + candidate->out_clientflag = 0; + candidate->real_conn_id = conn_id; + candidate->state = RXRPC_CONN_SERVER; + if (candidate->service_id) + candidate->state = RXRPC_CONN_SERVER_UNSECURED; + + write_lock_bh(&trans->conn_lock); + + pp = &trans->server_conns.rb_node; + p = NULL; + while (*pp) { + p = *pp; + conn = rb_entry(p, struct rxrpc_connection, node); + + if (epoch < conn->epoch) + pp = &(*pp)->rb_left; + else if (epoch > conn->epoch) + pp = &(*pp)->rb_right; + else if (conn_id < conn->real_conn_id) + pp = &(*pp)->rb_left; + else if (conn_id > conn->real_conn_id) + pp = &(*pp)->rb_right; + else + goto found_extant_second; + } + + /* we can now add the new candidate to the list */ + conn = candidate; + candidate = NULL; + rb_link_node(&conn->node, p, pp); + rb_insert_color(&conn->node, &trans->server_conns); + atomic_inc(&conn->trans->usage); + + write_unlock_bh(&trans->conn_lock); + + write_lock_bh(&rxrpc_connection_lock); + list_add_tail(&conn->link, &rxrpc_connections); + write_unlock_bh(&rxrpc_connection_lock); + + new = "new"; + +success: + _net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->real_conn_id); + + _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); + return conn; + + /* we found the connection in the list immediately */ +found_extant_connection: + if (hdr->securityIndex != conn->security_ix) { + read_unlock_bh(&trans->conn_lock); + goto security_mismatch; + } + atomic_inc(&conn->usage); + read_unlock_bh(&trans->conn_lock); + goto success; + + /* we found the connection on the second time through the list */ +found_extant_second: + if (hdr->securityIndex != conn->security_ix) { + write_unlock_bh(&trans->conn_lock); + goto security_mismatch; + } + atomic_inc(&conn->usage); + write_unlock_bh(&trans->conn_lock); + kfree(candidate); + goto success; + +security_mismatch: + kfree(candidate); + _leave(" = -EKEYREJECTED"); + return ERR_PTR(-EKEYREJECTED); +} + +/* + * find a connection based on transport and RxRPC connection ID for an incoming + * packet + */ +struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *trans, + struct rxrpc_header *hdr) +{ + struct rxrpc_connection *conn; + struct rb_node *p; + __be32 epoch; + u32 conn_id; + + _enter(",{%x,%x}", ntohl(hdr->cid), hdr->flags); + + read_lock_bh(&trans->conn_lock); + + conn_id = ntohl(hdr->cid) & RXRPC_CIDMASK; + epoch = hdr->epoch; + + if (hdr->flags & RXRPC_CLIENT_INITIATED) + p = trans->server_conns.rb_node; + else + p = trans->client_conns.rb_node; + + while (p) { + conn = rb_entry(p, struct rxrpc_connection, node); + + _debug("maybe %x", conn->real_conn_id); + + if (epoch < conn->epoch) + p = p->rb_left; + else if (epoch > conn->epoch) + p = p->rb_right; + else if (conn_id < conn->real_conn_id) + p = p->rb_left; + else if (conn_id > conn->real_conn_id) + p = p->rb_right; + else + goto found; + } + + read_unlock_bh(&trans->conn_lock); + _leave(" = NULL"); + return NULL; + +found: + atomic_inc(&conn->usage); + read_unlock_bh(&trans->conn_lock); + _leave(" = %p", conn); + return conn; +} + +/* + * release a virtual connection + */ +void rxrpc_put_connection(struct rxrpc_connection *conn) +{ + _enter("%p{u=%d,d=%d}", + conn, atomic_read(&conn->usage), conn->debug_id); + + ASSERTCMP(atomic_read(&conn->usage), >, 0); + + conn->put_time = xtime.tv_sec; + if (atomic_dec_and_test(&conn->usage)) { + _debug("zombie"); + schedule_delayed_work(&rxrpc_connection_reap, 0); + } + + _leave(""); +} + +/* + * destroy a virtual connection + */ +static void rxrpc_destroy_connection(struct rxrpc_connection *conn) +{ + _enter("%p{%d}", conn, atomic_read(&conn->usage)); + + ASSERTCMP(atomic_read(&conn->usage), ==, 0); + + _net("DESTROY CONN %d", conn->debug_id); + + if (conn->bundle) + rxrpc_put_bundle(conn->trans, conn->bundle); + + ASSERT(RB_EMPTY_ROOT(&conn->calls)); + rxrpc_purge_queue(&conn->rx_queue); + + rxrpc_clear_conn_security(conn); + rxrpc_put_transport(conn->trans); + kfree(conn); + _leave(""); +} + +/* + * reap dead connections + */ +void rxrpc_connection_reaper(struct work_struct *work) +{ + struct rxrpc_connection *conn, *_p; + unsigned long now, earliest, reap_time; + + LIST_HEAD(graveyard); + + _enter(""); + + now = xtime.tv_sec; + earliest = ULONG_MAX; + + write_lock_bh(&rxrpc_connection_lock); + list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) { + _debug("reap CONN %d { u=%d,t=%ld }", + conn->debug_id, atomic_read(&conn->usage), + (long) now - (long) conn->put_time); + + if (likely(atomic_read(&conn->usage) > 0)) + continue; + + spin_lock(&conn->trans->client_lock); + write_lock(&conn->trans->conn_lock); + reap_time = conn->put_time + rxrpc_connection_timeout; + + if (atomic_read(&conn->usage) > 0) { + ; + } else if (reap_time <= now) { + list_move_tail(&conn->link, &graveyard); + if (conn->out_clientflag) + rb_erase(&conn->node, + &conn->trans->client_conns); + else + rb_erase(&conn->node, + &conn->trans->server_conns); + if (conn->bundle) { + list_del_init(&conn->bundle_link); + conn->bundle->num_conns--; + } + + } else if (reap_time < earliest) { + earliest = reap_time; + } + + write_unlock(&conn->trans->conn_lock); + spin_unlock(&conn->trans->client_lock); + } + write_unlock_bh(&rxrpc_connection_lock); + + if (earliest != ULONG_MAX) { + _debug("reschedule reaper %ld", (long) earliest - now); + ASSERTCMP(earliest, >, now); + schedule_delayed_work(&rxrpc_connection_reap, + (earliest - now) * HZ); + } + + /* then destroy all those pulled out */ + while (!list_empty(&graveyard)) { + conn = list_entry(graveyard.next, struct rxrpc_connection, + link); + list_del_init(&conn->link); + + ASSERTCMP(atomic_read(&conn->usage), ==, 0); + rxrpc_destroy_connection(conn); + } + + _leave(""); +} + +/* + * preemptively destroy all the connection records rather than waiting for them + * to time out + */ +void __exit rxrpc_destroy_all_connections(void) +{ + _enter(""); + + rxrpc_connection_timeout = 0; + cancel_delayed_work(&rxrpc_connection_reap); + schedule_delayed_work(&rxrpc_connection_reap, 0); + + _leave(""); +} diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/ar-connevent.c new file mode 100644 index 00000000000..4b02815c1de --- /dev/null +++ b/net/rxrpc/ar-connevent.c @@ -0,0 +1,387 @@ +/* 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. + */ + +#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; + struct rb_node *p; + + _enter("{%d},%x", conn->debug_id, abort_code); + + read_lock_bh(&conn->lock); + + for (p = rb_first(&conn->calls); p; p = rb_next(p)) { + call = rb_entry(p, struct rxrpc_call, conn_node); + write_lock(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = state; + call->abort_code = abort_code; + if (state == RXRPC_CALL_LOCALLY_ABORTED) + set_bit(RXRPC_CALL_CONN_ABORT, &call->events); + else + set_bit(RXRPC_CALL_RCVD_ABORT, &call->events); + schedule_work(&call->processor); + } + write_unlock(&call->state_lock); + } + + read_unlock_bh(&conn->lock); + _leave(""); +} + +/* + * generate a connection-level abort + */ +static int rxrpc_abort_connection(struct rxrpc_connection *conn, + u32 error, u32 abort_code) +{ + struct rxrpc_header hdr; + struct msghdr msg; + struct kvec iov[2]; + __be32 word; + size_t len; + 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->trans->peer->srx.transport.sin; + msg.msg_namelen = sizeof(conn->trans->peer->srx.transport.sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr.epoch = conn->epoch; + hdr.cid = conn->cid; + hdr.callNumber = 0; + hdr.seq = 0; + hdr.type = RXRPC_PACKET_TYPE_ABORT; + hdr.flags = conn->out_clientflag; + hdr.userStatus = 0; + hdr.securityIndex = conn->security_ix; + hdr._rsvd = 0; + hdr.serviceId = conn->service_id; + + word = htonl(abort_code); + + iov[0].iov_base = &hdr; + iov[0].iov_len = sizeof(hdr); + iov[1].iov_base = &word; + iov[1].iov_len = sizeof(word); + + len = iov[0].iov_len + iov[1].iov_len; + + hdr.serial = htonl(atomic_inc_return(&conn->serial)); + _proto("Tx CONN ABORT %%%u { %d }", ntohl(hdr.serial), abort_code); + + ret = kernel_sendmsg(conn->trans->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 + */ +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_SECURED, &call->events)) + schedule_work(&call->processor); + 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 tmp; + u32 serial; + int loop, ret; + + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) + return -ECONNABORTED; + + serial = ntohl(sp->hdr.serial); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_ABORT: + if (skb_copy_bits(skb, 0, &tmp, sizeof(tmp)) < 0) + return -EPROTO; + _proto("Rx ABORT %%%u { ac=%d }", serial, ntohl(tmp)); + + conn->state = RXRPC_CONN_REMOTELY_ABORTED; + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, + ntohl(tmp)); + return -ECONNABORTED; + + case RXRPC_PACKET_TYPE_CHALLENGE: + if (conn->security) + return conn->security->respond_to_challenge( + conn, skb, _abort_code); + return -EPROTO; + + case RXRPC_PACKET_TYPE_RESPONSE: + if (!conn->security) + return -EPROTO; + + 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; + + conn->security->prime_packet_security(conn); + read_lock_bh(&conn->lock); + spin_lock(&conn->state_lock); + + if (conn->state == RXRPC_CONN_SERVER_CHALLENGING) { + conn->state = RXRPC_CONN_SERVER; + for (loop = 0; loop < RXRPC_MAXCALLS; loop++) + rxrpc_call_is_secure(conn->channels[loop]); + } + + spin_unlock(&conn->state_lock); + read_unlock_bh(&conn->lock); + return 0; + + default: + 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->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; + } + } + + ASSERT(conn->security != NULL); + + 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 rxrpc_skb_priv *sp; + struct sk_buff *skb; + u32 abort_code = RX_PROTOCOL_ERROR; + int ret; + + _enter("{%d}", conn->debug_id); + + atomic_inc(&conn->usage); + + if (test_and_clear_bit(RXRPC_CONN_CHALLENGE, &conn->events)) { + rxrpc_secure_connection(conn); + rxrpc_put_connection(conn); + } + + /* go through the conn-level event packets, releasing the ref on this + * connection that each one has when we've finished with it */ + while ((skb = skb_dequeue(&conn->rx_queue))) { + sp = rxrpc_skb(skb); + + 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_put_connection(conn); + 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_put_connection(conn); + rxrpc_free_skb(skb); + _leave(" [EPROTO]"); + goto out; +} + +/* + * reject packets through the local endpoint + */ +void rxrpc_reject_packets(struct work_struct *work) +{ + union { + struct sockaddr sa; + struct sockaddr_in sin; + } sa; + struct rxrpc_skb_priv *sp; + struct rxrpc_header hdr; + struct rxrpc_local *local; + struct sk_buff *skb; + struct msghdr msg; + struct kvec iov[2]; + size_t size; + __be32 code; + + local = container_of(work, struct rxrpc_local, rejecter); + rxrpc_get_local(local); + + _enter("%d", local->debug_id); + + iov[0].iov_base = &hdr; + iov[0].iov_len = sizeof(hdr); + iov[1].iov_base = &code; + iov[1].iov_len = sizeof(code); + size = sizeof(hdr) + 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(&hdr, 0, sizeof(hdr)); + hdr.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); + + hdr.epoch = sp->hdr.epoch; + hdr.cid = sp->hdr.cid; + hdr.callNumber = sp->hdr.callNumber; + hdr.serviceId = sp->hdr.serviceId; + hdr.flags = sp->hdr.flags; + hdr.flags ^= RXRPC_CLIENT_INITIATED; + hdr.flags &= RXRPC_CLIENT_INITIATED; + + kernel_sendmsg(local->socket, &msg, iov, 2, size); + break; + + default: + break; + } + + rxrpc_free_skb(skb); + rxrpc_put_local(local); + } + + rxrpc_put_local(local); + _leave(""); +} diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c new file mode 100644 index 00000000000..f5539e2f7b5 --- /dev/null +++ b/net/rxrpc/ar-error.c @@ -0,0 +1,253 @@ +/* Error message handling (ICMP) + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/errqueue.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/icmp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include "ar-internal.h" + +/* + * handle an error received on the local endpoint + */ +void rxrpc_UDP_error_report(struct sock *sk) +{ + struct sock_exterr_skb *serr; + struct rxrpc_transport *trans; + struct rxrpc_local *local = sk->sk_user_data; + struct rxrpc_peer *peer; + struct sk_buff *skb; + __be32 addr; + __be16 port; + + _enter("%p{%d}", sk, local->debug_id); + + skb = skb_dequeue(&sk->sk_error_queue); + if (!skb) { + _leave("UDP socket errqueue empty"); + return; + } + + rxrpc_new_skb(skb); + + serr = SKB_EXT_ERR(skb); + addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); + port = serr->port; + + _net("Rx UDP Error from "NIPQUAD_FMT":%hu", + NIPQUAD(addr), ntohs(port)); + _debug("Msg l:%d d:%d", skb->len, skb->data_len); + + peer = rxrpc_find_peer(local, addr, port); + if (IS_ERR(peer)) { + rxrpc_free_skb(skb); + _leave(" [no peer]"); + return; + } + + trans = rxrpc_find_transport(local, peer); + if (!trans) { + rxrpc_put_peer(peer); + rxrpc_free_skb(skb); + _leave(" [no trans]"); + return; + } + + if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && + serr->ee.ee_type == ICMP_DEST_UNREACH && + serr->ee.ee_code == ICMP_FRAG_NEEDED + ) { + u32 mtu = serr->ee.ee_info; + + _net("Rx Received ICMP Fragmentation Needed (%d)", mtu); + + /* wind down the local interface MTU */ + if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) { + peer->if_mtu = mtu; + _net("I/F MTU %u", mtu); + } + + /* ip_rt_frag_needed() may have eaten the info */ + if (mtu == 0) + mtu = ntohs(icmp_hdr(skb)->un.frag.mtu); + + if (mtu == 0) { + /* they didn't give us a size, estimate one */ + 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) { + peer->mtu = mtu; + peer->maxdata = peer->mtu - peer->hdrsize; + _net("Net MTU %u (maxdata %u)", + peer->mtu, peer->maxdata); + } + } + + rxrpc_put_peer(peer); + + /* pass the transport ref to error_handler to release */ + skb_queue_tail(&trans->error_queue, skb); + schedule_work(&trans->error_handler); + + /* reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + skb = skb_peek(&sk->sk_error_queue); + if (skb) { + sk->sk_err = SKB_EXT_ERR(skb)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else { + spin_unlock_bh(&sk->sk_error_queue.lock); + } + + _leave(""); +} + +/* + * deal with UDP error messages + */ +void rxrpc_UDP_error_handler(struct work_struct *work) +{ + struct sock_extended_err *ee; + struct sock_exterr_skb *serr; + struct rxrpc_transport *trans = + container_of(work, struct rxrpc_transport, error_handler); + struct sk_buff *skb; + int local, err; + + _enter(""); + + skb = skb_dequeue(&trans->error_queue); + if (!skb) + return; + + serr = SKB_EXT_ERR(skb); + ee = &serr->ee; + + _net("Rx Error o=%d t=%d c=%d e=%d", + ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno); + + err = ee->ee_errno; + + switch (ee->ee_origin) { + case SO_EE_ORIGIN_ICMP: + local = 0; + switch (ee->ee_type) { + case ICMP_DEST_UNREACH: + switch (ee->ee_code) { + case ICMP_NET_UNREACH: + _net("Rx Received ICMP Network Unreachable"); + err = ENETUNREACH; + break; + case ICMP_HOST_UNREACH: + _net("Rx Received ICMP Host Unreachable"); + err = EHOSTUNREACH; + break; + case ICMP_PORT_UNREACH: + _net("Rx Received ICMP Port Unreachable"); + err = ECONNREFUSED; + break; + case ICMP_FRAG_NEEDED: + _net("Rx Received ICMP Fragmentation Needed (%d)", + ee->ee_info); + err = 0; /* dealt with elsewhere */ + break; + case ICMP_NET_UNKNOWN: + _net("Rx Received ICMP Unknown Network"); + err = ENETUNREACH; + break; + case ICMP_HOST_UNKNOWN: + _net("Rx Received ICMP Unknown Host"); + err = EHOSTUNREACH; + break; + default: + _net("Rx Received ICMP DestUnreach code=%u", + ee->ee_code); + break; + } + break; + + case ICMP_TIME_EXCEEDED: + _net("Rx Received ICMP TTL Exceeded"); + break; + + default: + _proto("Rx Received ICMP error { type=%u code=%u }", + ee->ee_type, ee->ee_code); + break; + } + break; + + case SO_EE_ORIGIN_LOCAL: + _proto("Rx Received local error { error=%d }", + ee->ee_errno); + local = 1; + break; + + case SO_EE_ORIGIN_NONE: + case SO_EE_ORIGIN_ICMP6: + default: + _proto("Rx Received error report { orig=%u }", + ee->ee_origin); + local = 0; + break; + } + + /* terminate all the affected calls if there's an unrecoverable + * error */ + if (err) { + struct rxrpc_call *call, *_n; + + _debug("ISSUE ERROR %d", err); + + spin_lock_bh(&trans->peer->lock); + trans->peer->net_error = err; + + list_for_each_entry_safe(call, _n, &trans->peer->error_targets, + error_link) { + write_lock(&call->state_lock); + if (call->state != RXRPC_CALL_COMPLETE && + call->state < RXRPC_CALL_NETWORK_ERROR) { + call->state = RXRPC_CALL_NETWORK_ERROR; + set_bit(RXRPC_CALL_RCVD_ERROR, &call->events); + schedule_work(&call->processor); + } + write_unlock(&call->state_lock); + list_del_init(&call->error_link); + } + + spin_unlock_bh(&trans->peer->lock); + } + + if (!skb_queue_empty(&trans->error_queue)) + schedule_work(&trans->error_handler); + + rxrpc_free_skb(skb); + rxrpc_put_transport(trans); + _leave(""); +} diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c new file mode 100644 index 00000000000..323c3454561 --- /dev/null +++ b/net/rxrpc/ar-input.c @@ -0,0 +1,791 @@ +/* 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. + */ + +#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" + +unsigned long rxrpc_ack_timeout = 1; + +const char *rxrpc_pkts[] = { + "?00", + "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", + "?09", "?10", "?11", "?12", "?13", "?14", "?15" +}; + +/* + * 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 sock *sk; + int skb_len, 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); + skb->destructor = NULL; + sp->call = NULL; + rxrpc_put_call(call); + rxrpc_free_skb(skb); + return 0; + } + + sk = &call->socket->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) 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); + + /* Cache the SKB length before we tack it onto the receive + * queue. Once it is added it no longer belongs to us and + * may be freed by other threads of control pulling packets + * from the queue. + */ + skb_len = skb->len; + + _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_len); + + if (terminal) { + _debug("<<<< TERMINAL MESSAGE >>>>"); + set_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags); + } + + skb = NULL; + } else { + spin_unlock_bh(&sk->sk_receive_queue.lock); + } + ret = 0; + +out: + /* release the socket buffer */ + if (skb) { + skb->destructor = NULL; + sp->call = NULL; + rxrpc_put_call(call); + 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; + + _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); + + sp = rxrpc_skb(skb); + ASSERTCMP(sp->call, ==, NULL); + + 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) + goto enqueue_packet; + + sp->call = call; + rxrpc_get_call(call); + terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && + !(sp->hdr.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; + + _debug("post #%u", seq); + ASSERTCMP(call->rx_data_post, ==, seq); + call->rx_data_post++; + + if (sp->hdr.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_DRAIN_RX_OOS, &call->events)) + schedule_work(&call->processor); + read_unlock(&call->state_lock); + } + + spin_unlock(&call->lock); + atomic_inc(&call->ackr_not_idle); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.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, sp->hdr.serial, true); +discard: + spin_unlock(&call->lock); + rxrpc_free_skb(skb); + _leave(" = 0 [discarded]"); + return 0; + +enqueue_and_ack: + __rxrpc_propose_ACK(call, ack, sp->hdr.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) + schedule_work(&call->processor); + 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_RCVD_ACKALL, &call->events); + write_unlock_bh(&call->state_lock); + + if (try_to_del_timer_sync(&call->resend_timer) >= 0) { + clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_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 _abort_code; + u32 serial, hi_serial, seq, 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 */ + serial = ntohl(sp->hdr.serial); + hi_serial = atomic_read(&call->conn->hi_serial); + while (serial > hi_serial) + hi_serial = atomic_cmpxchg(&call->conn->hi_serial, hi_serial, + 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", serial); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, + !(sp->hdr.flags & RXRPC_MORE_PACKETS)); + } + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_ABORT: + _debug("abort"); + + if (skb_copy_bits(skb, 0, &_abort_code, + sizeof(_abort_code)) < 0) + goto protocol_error; + + abort_code = ntohl(_abort_code); + _proto("Rx ABORT %%%u { %x }", serial, abort_code); + + write_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_REMOTELY_ABORTED; + call->abort_code = abort_code; + set_bit(RXRPC_CALL_RCVD_ABORT, &call->events); + schedule_work(&call->processor); + } + goto free_packet_unlock; + + case RXRPC_PACKET_TYPE_BUSY: + _proto("Rx BUSY %%%u", serial); + + if (call->conn->out_clientflag) + 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_RCVD_BUSY, &call->events); + schedule_work(&call->processor); + case RXRPC_CALL_SERVER_BUSY: + goto free_packet_unlock; + default: + goto protocol_error_locked; + } + + default: + _proto("Rx %s %%%u", rxrpc_pkts[sp->hdr.type], serial); + goto protocol_error; + + case RXRPC_PACKET_TYPE_DATA: + seq = ntohl(sp->hdr.seq); + + _proto("Rx DATA %%%u { #%u }", serial, seq); + + if (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, serial); + + switch (rxrpc_fast_process_data(call, skb, 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_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); + schedule_work(&call->processor); + 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->abort_code = RX_PROTOCOL_ERROR; + set_bit(RXRPC_CALL_ABORT, &call->events); + schedule_work(&call->processor); + } +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 = htonl(ntohl(sp->hdr.seq) + 1); + sp->hdr.serial = htonl(ntohl(sp->hdr.serial) + 1); + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = jhdr._rsvd; + + _proto("Rx DATA Jumbo %%%u", ntohl(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->abort_code = RX_PROTOCOL_ERROR; + set_bit(RXRPC_CALL_ABORT, &call->events); + schedule_work(&call->processor); + } + 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_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp; + struct rxrpc_call *call; + struct rb_node *p; + __be32 call_id; + + _enter("%p,%p", conn, skb); + + read_lock_bh(&conn->lock); + + sp = rxrpc_skb(skb); + + /* look at extant calls by channel number first */ + call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK]; + if (!call || call->call_id != sp->hdr.callNumber) + goto call_not_extant; + + _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_ABORT, &call->events)) + schedule_work(&call->processor); + case RXRPC_CALL_REMOTELY_ABORTED: + case RXRPC_CALL_NETWORK_ERROR: + case RXRPC_CALL_DEAD: + goto free_unlock; + default: + break; + } + + read_unlock(&call->state_lock); + rxrpc_get_call(call); + read_unlock_bh(&conn->lock); + + 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; + +call_not_extant: + /* search the completed calls in case what we're dealing with is + * there */ + _debug("call not extant"); + + call_id = sp->hdr.callNumber; + p = conn->calls.rb_node; + while (p) { + call = rb_entry(p, struct rxrpc_call, conn_node); + + if (call_id < call->call_id) + p = p->rb_left; + else if (call_id > call->call_id) + p = p->rb_right; + else + goto found_completed_call; + } + +dead_call: + /* it's a either a really old call that we no longer remember or its a + * new incoming call */ + read_unlock_bh(&conn->lock); + + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && + sp->hdr.seq == __constant_cpu_to_be32(1)) { + _debug("incoming call"); + skb_queue_tail(&conn->trans->local->accept_queue, skb); + schedule_work(&conn->trans->local->acceptor); + goto done; + } + + _debug("dead call"); + skb->priority = RX_CALL_DEAD; + rxrpc_reject_packet(conn->trans->local, skb); + goto done; + + /* resend last packet of a completed call + * - client calls may have been aborted or ACK'd + * - server calls may have been aborted + */ +found_completed_call: + _debug("completed call"); + + if (atomic_read(&call->usage) == 0) + goto dead_call; + + /* synchronise any state changes */ + read_lock(&call->state_lock); + ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK, + call->state, >=, RXRPC_CALL_COMPLETE); + + if (call->state == RXRPC_CALL_LOCALLY_ABORTED || + call->state == RXRPC_CALL_REMOTELY_ABORTED || + call->state == RXRPC_CALL_DEAD) { + read_unlock(&call->state_lock); + goto dead_call; + } + + if (call->conn->in_clientflag) { + read_unlock(&call->state_lock); + goto dead_call; /* complete server call */ + } + + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_ACK_FINAL, &call->events); + schedule_work(&call->processor); + +free_unlock: + read_unlock(&call->state_lock); + read_unlock_bh(&conn->lock); + rxrpc_free_skb(skb); +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); + + atomic_inc(&conn->usage); + skb_queue_tail(&conn->rx_queue, skb); + schedule_work(&conn->processor); +} + +/* + * handle data received on the local endpoint + * - may be called in interrupt context + */ +void rxrpc_data_ready(struct sock *sk, int count) +{ + struct rxrpc_connection *conn; + struct rxrpc_transport *trans; + struct rxrpc_skb_priv *sp; + struct rxrpc_local *local; + struct rxrpc_peer *peer; + struct sk_buff *skb; + int ret; + + _enter("%p, %d", sk, count); + + ASSERT(!irqs_disabled()); + + read_lock_bh(&rxrpc_local_lock); + local = sk->sk_user_data; + if (local && atomic_read(&local->usage) > 0) + rxrpc_get_local(local); + else + local = NULL; + read_unlock_bh(&rxrpc_local_lock); + if (!local) { + _leave(" [local dead]"); + return; + } + + skb = skb_recv_datagram(sk, 0, 1, &ret); + if (!skb) { + rxrpc_put_local(local); + if (ret == -EAGAIN) + return; + _debug("UDP socket error %d", ret); + 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); + rxrpc_put_local(local); + _leave(" [CSUM failed]"); + return; + } + + /* the socket buffer we have is owned by UDP, with UDP's data all over + * it, but we really want our own */ + skb_orphan(skb); + sp = rxrpc_skb(skb); + memset(sp, 0, sizeof(*sp)); + + _net("Rx UDP packet from %08x:%04hu", + ntohl(ip_hdr(skb)->saddr), ntohs(udp_hdr(skb)->source)); + + /* dig out the RxRPC connection details */ + if (skb_copy_bits(skb, sizeof(struct udphdr), &sp->hdr, + sizeof(sp->hdr)) < 0) + goto bad_message; + if (!pskb_pull(skb, sizeof(struct udphdr) + sizeof(sp->hdr))) + BUG(); + + _net("Rx RxRPC %s ep=%x call=%x:%x", + sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient", + ntohl(sp->hdr.epoch), + ntohl(sp->hdr.cid), + ntohl(sp->hdr.callNumber)); + + if (sp->hdr.type == 0 || sp->hdr.type >= RXRPC_N_PACKET_TYPES) { + _proto("Rx Bad Packet Type %u", sp->hdr.type); + goto bad_message; + } + + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) + goto bad_message; + + peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source); + if (IS_ERR(peer)) + goto cant_route_call; + + trans = rxrpc_find_transport(local, peer); + rxrpc_put_peer(peer); + if (!trans) + goto cant_route_call; + + conn = rxrpc_find_connection(trans, &sp->hdr); + rxrpc_put_transport(trans); + if (!conn) + goto cant_route_call; + + _debug("CONN %p {%d}", conn, conn->debug_id); + + if (sp->hdr.callNumber == 0) + rxrpc_post_packet_to_conn(conn, skb); + else + rxrpc_post_packet_to_call(conn, skb); + rxrpc_put_connection(conn); + rxrpc_put_local(local); + return; + +cant_route_call: + _debug("can't route call"); + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && + sp->hdr.type == RXRPC_PACKET_TYPE_DATA) { + if (sp->hdr.seq == __constant_cpu_to_be32(1)) { + _debug("first packet"); + skb_queue_tail(&local->accept_queue, skb); + schedule_work(&local->acceptor); + rxrpc_put_local(local); + _leave(" [incoming]"); + return; + } + skb->priority = RX_INVALID_OPERATION; + } else { + skb->priority = RX_CALL_DEAD; + } + + _debug("reject"); + rxrpc_reject_packet(local, skb); + rxrpc_put_local(local); + _leave(" [no call]"); + return; + +bad_message: + skb->priority = RX_PROTOCOL_ERROR; + rxrpc_reject_packet(local, skb); + rxrpc_put_local(local); + _leave(" [badmsg]"); +} diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h new file mode 100644 index 00000000000..7bfbf471c81 --- /dev/null +++ b/net/rxrpc/ar-internal.h @@ -0,0 +1,842 @@ +/* AF_RXRPC internal definitions + * + * 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 <rxrpc/packet.h> + +#if 0 +#define CHECK_SLAB_OKAY(X) \ + BUG_ON(atomic_read((X)) >> (sizeof(atomic_t) - 2) == \ + (POISON_FREE << 8 | POISON_FREE)) +#else +#define CHECK_SLAB_OKAY(X) do {} while(0) +#endif + +extern atomic_t rxrpc_n_skbs; + +#define FCRYPT_BSIZE 8 +struct rxrpc_crypt { + union { + u8 x[FCRYPT_BSIZE]; + u32 n[2]; + }; +} __attribute__((aligned(8))); + +extern __be32 rxrpc_epoch; /* local epoch for detecting local-end reset */ +extern atomic_t rxrpc_debug_id; /* current debugging ID */ + +/* + * sk_state for RxRPC sockets + */ +enum { + RXRPC_UNCONNECTED = 0, + 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 */ +}; + +/* + * RxRPC socket definition + */ +struct rxrpc_sock { + /* WARNING: sk has to be the first member */ + struct sock sk; + 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 */ + struct key *key; /* security for this socket */ + 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 */ + rwlock_t call_lock; /* lock for calls */ + u32 min_sec_level; /* minimum security level */ +#define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT + struct sockaddr_rxrpc srx; /* local address */ + sa_family_t proto; /* protocol created with */ + __be16 service_id; /* service ID of local/remote service */ +}; + +#define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk) + +/* + * RxRPC socket buffer private variables + * - max 48 bytes (struct sk_buff::cb) + */ +struct rxrpc_skb_priv { + struct rxrpc_call *call; /* call with which associated */ + unsigned long resend_at; /* time in jiffies at which to resend */ + union { + unsigned offset; /* offset into buffer of next read */ + int remain; /* amount of space remaining for next write */ + u32 error; /* network error code */ + bool need_resend; /* T if needs resending */ + }; + + struct rxrpc_header hdr; /* RxRPC packet header from this packet */ +}; + +#define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) + +enum { + RXRPC_SKB_MARK_DATA, /* data message */ + RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ + RXRPC_SKB_MARK_BUSY, /* server busy message */ + RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ + RXRPC_SKB_MARK_NET_ERROR, /* network error message */ + RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ + RXRPC_SKB_MARK_NEW_CALL, /* local error message */ +}; + +enum rxrpc_command { + RXRPC_CMD_SEND_DATA, /* send data message */ + RXRPC_CMD_SEND_ABORT, /* request abort generation */ + RXRPC_CMD_ACCEPT, /* [server] accept incoming call */ + RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ +}; + +/* + * RxRPC security module interface + */ +struct rxrpc_security { + struct module *owner; /* providing module */ + struct list_head link; /* link in master list */ + const char *name; /* name of this service */ + u8 security_index; /* security type provided */ + + /* initialise a connection's security */ + int (*init_connection_security)(struct rxrpc_connection *); + + /* prime a connection's packet security */ + void (*prime_packet_security)(struct rxrpc_connection *); + + /* impose security on a packet */ + int (*secure_packet)(const 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 *); + + /* issue a challenge */ + int (*issue_challenge)(struct rxrpc_connection *); + + /* respond to a challenge */ + int (*respond_to_challenge)(struct rxrpc_connection *, + struct sk_buff *, + u32 *); + + /* verify a response */ + int (*verify_response)(struct rxrpc_connection *, + struct sk_buff *, + u32 *); + + /* clear connection security */ + void (*clear)(struct rxrpc_connection *); +}; + +/* + * RxRPC local transport endpoint definition + * - matched by local port, address and protocol type + */ +struct rxrpc_local { + 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 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 */ + 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 */ + 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 + */ +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 */ + atomic_t usage; + unsigned if_mtu; /* interface MTU for this peer */ + unsigned mtu; /* network MTU for this peer */ + unsigned 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 */ + struct sockaddr_rxrpc srx; /* remote address */ + + /* calculated RTT cache */ +#define RXRPC_RTT_CACHE_SIZE 32 + suseconds_t rtt; /* current RTT estimate (in uS) */ + unsigned rtt_point; /* next entry at which to insert */ + unsigned rtt_usage; /* amount of cache actually used */ + suseconds_t rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* calculated RTT cache */ +}; + +/* + * 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 */ + time_t 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) */ +}; + +/* + * RxRPC client connection bundle + * - matched by { transport, service_id, key } + */ +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 */ + __be16 service_id; /* service ID */ + uint8_t security_ix; /* security type */ +}; + +/* + * RxRPC connection definition + * - matched by { transport, service_id, conn_id, direction, key } + * - 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 work_struct processor; /* connection event processor */ + struct rb_node node; /* node in transport's lookup tree */ + 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) */ + 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_blkcipher *cipher; /* encryption handle */ + struct rxrpc_crypt csum_iv; /* packet checksum base */ + unsigned long events; +#define RXRPC_CONN_CHALLENGE 0 /* send challenge packet */ + time_t put_time; /* time at which to reap */ + rwlock_t lock; /* access lock */ + spinlock_t state_lock; /* state-change lock */ + atomic_t usage; + u32 real_conn_id; /* connection ID (host-endian) */ + 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; + int error; /* error code for local abort */ + int debug_id; /* debug ID for printks */ + unsigned 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 */ + 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 */ + + /* the following are all in net order */ + __be32 epoch; /* epoch of this connection */ + __be32 cid; /* connection ID */ + __be16 service_id; /* service ID */ + 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 */ +}; + +/* + * RxRPC call definition + * - matched by { connection, call_id } + */ +struct rxrpc_call { + struct rxrpc_connection *conn; /* connection carrying call */ + struct rxrpc_sock *socket; /* socket responsible */ + struct timer_list lifetimer; /* lifetime remaining on call */ + struct timer_list deadspan; /* reap timer for re-ACK'ing, etc */ + struct timer_list ack_timer; /* ACK generation timer */ + struct timer_list resend_timer; /* Tx resend timer */ + 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 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 */ + unsigned long user_call_ID; /* user-defined call ID */ + unsigned long creation_jif; /* time of call creation */ + unsigned long flags; +#define RXRPC_CALL_RELEASED 0 /* call has been released - no more message to userspace */ +#define RXRPC_CALL_TERMINAL_MSG 1 /* call has given the socket its final message */ +#define RXRPC_CALL_RCVD_LAST 2 /* all packets received */ +#define RXRPC_CALL_RUN_RTIMER 3 /* Tx resend timer started */ +#define RXRPC_CALL_TX_SOFT_ACK 4 /* sent some soft ACKs */ +#define RXRPC_CALL_PROC_BUSY 5 /* the processor is busy */ +#define RXRPC_CALL_INIT_ACCEPT 6 /* acceptance was initiated */ +#define RXRPC_CALL_HAS_USERID 7 /* has a user ID attached */ +#define RXRPC_CALL_EXPECT_OOS 8 /* expect out of sequence packets */ + unsigned long events; +#define RXRPC_CALL_RCVD_ACKALL 0 /* ACKALL or reply received */ +#define RXRPC_CALL_RCVD_BUSY 1 /* busy packet received */ +#define RXRPC_CALL_RCVD_ABORT 2 /* abort packet received */ +#define RXRPC_CALL_RCVD_ERROR 3 /* network error received */ +#define RXRPC_CALL_ACK_FINAL 4 /* need to generate final ACK (and release call) */ +#define RXRPC_CALL_ACK 5 /* need to generate ACK */ +#define RXRPC_CALL_REJECT_BUSY 6 /* need to generate busy message */ +#define RXRPC_CALL_ABORT 7 /* need to generate abort */ +#define RXRPC_CALL_CONN_ABORT 8 /* local connection abort generated */ +#define RXRPC_CALL_RESEND_TIMER 9 /* Tx resend timer expired */ +#define RXRPC_CALL_RESEND 10 /* Tx resend required */ +#define RXRPC_CALL_DRAIN_RX_OOS 11 /* drain the Rx out of sequence queue */ +#define RXRPC_CALL_LIFE_TIMER 12 /* call's lifetimer ran out */ +#define RXRPC_CALL_ACCEPTED 13 /* incoming call accepted by userspace app */ +#define RXRPC_CALL_SECURED 14 /* incoming call's connection is now secure */ +#define RXRPC_CALL_POST_ACCEPT 15 /* need to post an "accept?" message to the app */ +#define RXRPC_CALL_RELEASE 16 /* need to release the call's resources */ + + spinlock_t lock; + rwlock_t state_lock; /* lock for state transition */ + atomic_t usage; + atomic_t sequence; /* Tx data packet sequence counter */ + u32 abort_code; /* local/remote abort code */ + enum { /* current state of call */ + 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 */ + RXRPC_CALL_CLIENT_FINAL_ACK, /* - client sending final ACK phase */ + RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ + RXRPC_CALL_SERVER_ACCEPTING, /* - server accepting request */ + RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ + RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ + RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ + RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ + RXRPC_CALL_COMPLETE, /* - call completed */ + RXRPC_CALL_SERVER_BUSY, /* - call rejected by busy server */ + RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ + RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ + RXRPC_CALL_DEAD, /* - call is dead */ + } state; + int debug_id; /* debug ID for printks */ + u8 channel; /* connection channel occupied by this call */ + + /* transmission-phase ACK management */ + uint8_t acks_head; /* offset into window of first entry */ + uint8_t acks_tail; /* offset into window of last entry */ + uint8_t acks_winsz; /* size of un-ACK'd window */ + uint8_t acks_unacked; /* lowest unacked packet in last ACK received */ + int acks_latest; /* serial number of latest ACK received */ + rxrpc_seq_t acks_hard; /* highest definitively ACK'd msg seq */ + unsigned long *acks_window; /* sent packet window + * - elements are pointers with LSB set if ACK'd + */ + + /* receive-phase ACK management */ + rxrpc_seq_t rx_data_expect; /* next data seq ID expected to be received */ + rxrpc_seq_t rx_data_post; /* next data seq ID expected to be posted */ + rxrpc_seq_t rx_data_recv; /* last data seq ID encountered by recvmsg */ + rxrpc_seq_t rx_data_eaten; /* last data seq ID consumed by recvmsg */ + rxrpc_seq_t rx_first_oos; /* first packet in rx_oos_queue (or 0) */ + rxrpc_seq_t ackr_win_top; /* top of ACK window (rx_data_eaten is bottom) */ + rxrpc_seq_net_t ackr_prev_seq; /* previous sequence number received */ + uint8_t ackr_reason; /* reason to ACK */ + __be32 ackr_serial; /* serial of packet being ACK'd */ + atomic_t ackr_not_idle; /* number of packets in Rx queue */ + + /* received packet records, 1 bit per record */ +#define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) + unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; + + /* the following should all be in net order */ + __be32 cid; /* connection ID + channel index */ + __be32 call_id; /* call ID on connection */ +}; + +/* + * RxRPC key for Kerberos (type-2 security) + */ +struct rxkad_key { + u16 security_index; /* RxRPC header security index */ + u16 ticket_len; /* length of ticket[] */ + u32 expiry; /* time at which expires */ + u32 kvno; /* key version number */ + u8 session_key[8]; /* DES session key */ + u8 ticket[0]; /* the encrypted ticket */ +}; + +struct rxrpc_key_payload { + struct rxkad_key k; +}; + +/* + * locally abort an RxRPC call + */ +static inline void rxrpc_abort_call(struct rxrpc_call *call, u32 abort_code) +{ + write_lock_bh(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) { + call->abort_code = abort_code; + call->state = RXRPC_CALL_LOCALLY_ABORTED; + set_bit(RXRPC_CALL_ABORT, &call->events); + } + write_unlock_bh(&call->state_lock); +} + +/* + * put a packet up for transport-level abort + */ +static inline +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) +{ + CHECK_SLAB_OKAY(&local->usage); + if (!atomic_inc_not_zero(&local->usage)) { + printk("resurrected on reject\n"); + BUG(); + } + skb_queue_tail(&local->reject_queue, skb); + schedule_work(&local->rejecter); +} + +/* + * ar-accept.c + */ +extern void rxrpc_accept_incoming_calls(struct work_struct *); +extern int rxrpc_accept_call(struct rxrpc_sock *, unsigned long); + +/* + * ar-ack.c + */ +extern void __rxrpc_propose_ACK(struct rxrpc_call *, uint8_t, __be32, bool); +extern void rxrpc_propose_ACK(struct rxrpc_call *, uint8_t, __be32, bool); +extern void rxrpc_process_call(struct work_struct *); + +/* + * ar-call.c + */ +extern struct kmem_cache *rxrpc_call_jar; +extern struct list_head rxrpc_calls; +extern rwlock_t rxrpc_call_lock; + +extern struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, + struct rxrpc_transport *, + struct rxrpc_conn_bundle *, + unsigned long, int, gfp_t); +extern struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, + struct rxrpc_connection *, + struct rxrpc_header *, gfp_t); +extern struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, + unsigned long); +extern void rxrpc_release_call(struct rxrpc_call *); +extern void rxrpc_release_calls_on_socket(struct rxrpc_sock *); +extern void __rxrpc_put_call(struct rxrpc_call *); +extern void __exit rxrpc_destroy_all_calls(void); + +/* + * ar-connection.c + */ +extern struct list_head rxrpc_connections; +extern rwlock_t rxrpc_connection_lock; + +extern struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *, + struct rxrpc_transport *, + struct key *, + __be16, gfp_t); +extern void rxrpc_put_bundle(struct rxrpc_transport *, + struct rxrpc_conn_bundle *); +extern int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_transport *, + struct rxrpc_conn_bundle *, struct rxrpc_call *, + gfp_t); +extern void rxrpc_put_connection(struct rxrpc_connection *); +extern void __exit rxrpc_destroy_all_connections(void); +extern struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *, + struct rxrpc_header *); +extern struct rxrpc_connection * +rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_header *, + gfp_t); + +/* + * ar-connevent.c + */ +extern void rxrpc_process_connection(struct work_struct *); +extern void rxrpc_reject_packets(struct work_struct *); + +/* + * ar-error.c + */ +extern void rxrpc_UDP_error_report(struct sock *); +extern void rxrpc_UDP_error_handler(struct work_struct *); + +/* + * ar-input.c + */ +extern unsigned long rxrpc_ack_timeout; +extern const char *rxrpc_pkts[]; + +extern void rxrpc_data_ready(struct sock *, int); +extern int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, + bool); +extern void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); + +/* + * ar-local.c + */ +extern rwlock_t rxrpc_local_lock; +extern struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *); +extern void rxrpc_put_local(struct rxrpc_local *); +extern void __exit rxrpc_destroy_all_locals(void); + +/* + * ar-key.c + */ +extern struct key_type key_type_rxrpc; +extern struct key_type key_type_rxrpc_s; + +extern int rxrpc_request_key(struct rxrpc_sock *, char __user *, int); +extern int rxrpc_server_keyring(struct rxrpc_sock *, char __user *, int); +extern int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, + time_t, u32); + +/* + * ar-output.c + */ +extern int rxrpc_resend_timeout; + +extern int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); +extern int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *, + struct rxrpc_transport *, struct msghdr *, + size_t); +extern int rxrpc_server_sendmsg(struct kiocb *, struct rxrpc_sock *, + struct msghdr *, size_t); + +/* + * ar-peer.c + */ +extern struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *, gfp_t); +extern void rxrpc_put_peer(struct rxrpc_peer *); +extern struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *, + __be32, __be16); +extern void __exit rxrpc_destroy_all_peers(void); + +/* + * ar-proc.c + */ +extern const char *rxrpc_call_states[]; +extern struct file_operations rxrpc_call_seq_fops; +extern struct file_operations rxrpc_connection_seq_fops; + +/* + * ar-recvmsg.c + */ +extern int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *, + size_t, int); + +/* + * ar-security.c + */ +extern int rxrpc_register_security(struct rxrpc_security *); +extern void rxrpc_unregister_security(struct rxrpc_security *); +extern int rxrpc_init_client_conn_security(struct rxrpc_connection *); +extern int rxrpc_init_server_conn_security(struct rxrpc_connection *); +extern int rxrpc_secure_packet(const struct rxrpc_call *, struct sk_buff *, + size_t, void *); +extern int rxrpc_verify_packet(const struct rxrpc_call *, struct sk_buff *, + u32 *); +extern void rxrpc_clear_conn_security(struct rxrpc_connection *); + +/* + * ar-skbuff.c + */ +extern void rxrpc_packet_destructor(struct sk_buff *); + +/* + * ar-transport.c + */ +extern struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *, + struct rxrpc_peer *, + gfp_t); +extern void rxrpc_put_transport(struct rxrpc_transport *); +extern void __exit rxrpc_destroy_all_transports(void); +extern struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, + struct rxrpc_peer *); + +/* + * debug tracing + */ +extern unsigned rxrpc_debug; + +#define dbgprintk(FMT,...) \ + printk("[%x%-6.6s] "FMT"\n", smp_processor_id(), current->comm ,##__VA_ARGS__) + +/* make sure we maintain the format strings, even when debugging is disabled */ +static inline __attribute__((format(printf,1,2))) +void _dbprintk(const char *fmt, ...) +{ +} + +#define kenter(FMT,...) dbgprintk("==> %s("FMT")",__FUNCTION__ ,##__VA_ARGS__) +#define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__FUNCTION__ ,##__VA_ARGS__) +#define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) +#define kproto(FMT,...) dbgprintk("### "FMT ,##__VA_ARGS__) +#define knet(FMT,...) dbgprintk("@@@ "FMT ,##__VA_ARGS__) + + +#if defined(__KDEBUG) +#define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) +#define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) +#define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) +#define _proto(FMT,...) kproto(FMT,##__VA_ARGS__) +#define _net(FMT,...) knet(FMT,##__VA_ARGS__) + +#elif defined(CONFIG_AF_RXRPC_DEBUG) +#define RXRPC_DEBUG_KENTER 0x01 +#define RXRPC_DEBUG_KLEAVE 0x02 +#define RXRPC_DEBUG_KDEBUG 0x04 +#define RXRPC_DEBUG_KPROTO 0x08 +#define RXRPC_DEBUG_KNET 0x10 + +#define _enter(FMT,...) \ +do { \ + if (unlikely(rxrpc_debug & RXRPC_DEBUG_KENTER)) \ + kenter(FMT,##__VA_ARGS__); \ +} while (0) + +#define _leave(FMT,...) \ +do { \ + if (unlikely(rxrpc_debug & RXRPC_DEBUG_KLEAVE)) \ + kleave(FMT,##__VA_ARGS__); \ +} while (0) + +#define _debug(FMT,...) \ +do { \ + if (unlikely(rxrpc_debug & RXRPC_DEBUG_KDEBUG)) \ + kdebug(FMT,##__VA_ARGS__); \ +} while (0) + +#define _proto(FMT,...) \ +do { \ + if (unlikely(rxrpc_debug & RXRPC_DEBUG_KPROTO)) \ + kproto(FMT,##__VA_ARGS__); \ +} while (0) + +#define _net(FMT,...) \ +do { \ + if (unlikely(rxrpc_debug & RXRPC_DEBUG_KNET)) \ + knet(FMT,##__VA_ARGS__); \ +} while (0) + +#else +#define _enter(FMT,...) _dbprintk("==> %s("FMT")",__FUNCTION__ ,##__VA_ARGS__) +#define _leave(FMT,...) _dbprintk("<== %s()"FMT"",__FUNCTION__ ,##__VA_ARGS__) +#define _debug(FMT,...) _dbprintk(" "FMT ,##__VA_ARGS__) +#define _proto(FMT,...) _dbprintk("### "FMT ,##__VA_ARGS__) +#define _net(FMT,...) _dbprintk("@@@ "FMT ,##__VA_ARGS__) +#endif + +/* + * debug assertion checking + */ +#if 1 // defined(__KDEBUGALL) + +#define ASSERT(X) \ +do { \ + if (unlikely(!(X))) { \ + printk(KERN_ERR "\n"); \ + printk(KERN_ERR "RxRPC: 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)); \ + BUG(); \ + } \ +} while(0) + +#define ASSERTIF(C, X) \ +do { \ + if (unlikely((C) && !(X))) { \ + printk(KERN_ERR "\n"); \ + printk(KERN_ERR "RxRPC: 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)); \ + BUG(); \ + } \ +} while(0) + +#else + +#define ASSERT(X) \ +do { \ +} while(0) + +#define ASSERTCMP(X, OP, Y) \ +do { \ +} while(0) + +#define ASSERTIF(C, X) \ +do { \ +} while(0) + +#define ASSERTIFCMP(C, X, OP, Y) \ +do { \ +} while(0) + +#endif /* __KDEBUGALL */ + +/* + * socket buffer accounting / leak finding + */ +static inline void __rxrpc_new_skb(struct sk_buff *skb, const char *fn) +{ + //_net("new skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs)); + //atomic_inc(&rxrpc_n_skbs); +} + +#define rxrpc_new_skb(skb) __rxrpc_new_skb((skb), __func__) + +static inline void __rxrpc_kill_skb(struct sk_buff *skb, const char *fn) +{ + //_net("kill skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs)); + //atomic_dec(&rxrpc_n_skbs); +} + +#define rxrpc_kill_skb(skb) __rxrpc_kill_skb((skb), __func__) + +static inline void __rxrpc_free_skb(struct sk_buff *skb, const char *fn) +{ + if (skb) { + CHECK_SLAB_OKAY(&skb->users); + //_net("free skb %p %s [%d]", + // skb, fn, atomic_read(&rxrpc_n_skbs)); + //atomic_dec(&rxrpc_n_skbs); + kfree_skb(skb); + } +} + +#define rxrpc_free_skb(skb) __rxrpc_free_skb((skb), __func__) + +static inline void rxrpc_purge_queue(struct sk_buff_head *list) +{ + struct sk_buff *skb; + while ((skb = skb_dequeue((list))) != NULL) + rxrpc_free_skb(skb); +} + +static inline void __rxrpc__atomic_inc(atomic_t *v) +{ + CHECK_SLAB_OKAY(v); + atomic_inc(v); +} + +#define atomic_inc(v) __rxrpc__atomic_inc((v)) + +static inline void __rxrpc__atomic_dec(atomic_t *v) +{ + CHECK_SLAB_OKAY(v); + atomic_dec(v); +} + +#define atomic_dec(v) __rxrpc__atomic_dec((v)) + +static inline int __rxrpc__atomic_dec_and_test(atomic_t *v) +{ + CHECK_SLAB_OKAY(v); + return atomic_dec_and_test(v); +} + +#define atomic_dec_and_test(v) __rxrpc__atomic_dec_and_test((v)) + +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); \ + if (atomic_inc_return(&(CALL)->usage) == 1) \ + BUG(); \ +} while(0) + +#define rxrpc_put_call(CALL) \ +do { \ + __rxrpc_put_call(CALL); \ +} while(0) diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c new file mode 100644 index 00000000000..7e049ff6ae6 --- /dev/null +++ b/net/rxrpc/ar-key.c @@ -0,0 +1,334 @@ +/* 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> + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/key.h> +#include <linux/crypto.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_instantiate(struct key *, const void *, size_t); +static int rxrpc_instantiate_s(struct key *, const void *, size_t); +static void rxrpc_destroy(struct key *); +static void rxrpc_destroy_s(struct key *); +static void rxrpc_describe(const struct key *, struct seq_file *); + +/* + * 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", + .instantiate = rxrpc_instantiate, + .match = user_match, + .destroy = rxrpc_destroy, + .describe = rxrpc_describe, +}; + +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", + .instantiate = rxrpc_instantiate_s, + .match = user_match, + .destroy = rxrpc_destroy_s, + .describe = rxrpc_describe, +}; + +/* + * instantiate 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_instantiate(struct key *key, const void *data, size_t datalen) +{ + const struct rxkad_key *tsec; + struct rxrpc_key_payload *upayload; + size_t plen; + u32 kver; + int ret; + + _enter("{%x},,%zu", key_serial(key), datalen); + + /* handle a no-security key */ + if (!data && datalen == 0) + return 0; + + /* get the key interface version number */ + ret = -EINVAL; + if (datalen <= 4 || !data) + goto error; + memcpy(&kver, data, sizeof(kver)); + data += sizeof(kver); + 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 (datalen < sizeof(*tsec)) + goto error; + + tsec = data; + if (datalen != sizeof(*tsec) + tsec->ticket_len) + goto error; + + _debug("SCIX: %u", tsec->security_index); + _debug("TLEN: %u", tsec->ticket_len); + _debug("EXPY: %x", tsec->expiry); + _debug("KVNO: %u", tsec->kvno); + _debug("SKEY: %02x%02x%02x%02x%02x%02x%02x%02x", + tsec->session_key[0], tsec->session_key[1], + tsec->session_key[2], tsec->session_key[3], + tsec->session_key[4], tsec->session_key[5], + tsec->session_key[6], tsec->session_key[7]); + if (tsec->ticket_len >= 8) + _debug("TCKT: %02x%02x%02x%02x%02x%02x%02x%02x", + tsec->ticket[0], tsec->ticket[1], + tsec->ticket[2], tsec->ticket[3], + tsec->ticket[4], tsec->ticket[5], + tsec->ticket[6], tsec->ticket[7]); + + ret = -EPROTONOSUPPORT; + if (tsec->security_index != 2) + goto error; + + key->type_data.x[0] = tsec->security_index; + + plen = sizeof(*upayload) + tsec->ticket_len; + ret = key_payload_reserve(key, plen); + if (ret < 0) + goto error; + + ret = -ENOMEM; + upayload = kmalloc(plen, GFP_KERNEL); + if (!upayload) + goto error; + + /* attach the data */ + memcpy(&upayload->k, tsec, sizeof(*tsec)); + memcpy(&upayload->k.ticket, (void *)tsec + sizeof(*tsec), + tsec->ticket_len); + key->payload.data = upayload; + key->expiry = tsec->expiry; + ret = 0; + +error: + return ret; +} + +/* + * instantiate a server secret key + * data should be a pointer to the 8-byte secret key + */ +static int rxrpc_instantiate_s(struct key *key, const void *data, + size_t datalen) +{ + struct crypto_blkcipher *ci; + + _enter("{%x},,%zu", key_serial(key), datalen); + + if (datalen != 8) + return -EINVAL; + + memcpy(&key->type_data, data, 8); + + ci = crypto_alloc_blkcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(ci)) { + _leave(" = %ld", PTR_ERR(ci)); + return PTR_ERR(ci); + } + + if (crypto_blkcipher_setkey(ci, data, 8) < 0) + BUG(); + + key->payload.data = ci; + _leave(" = 0"); + return 0; +} + +/* + * dispose of the data dangling from the corpse of a rxrpc key + */ +static void rxrpc_destroy(struct key *key) +{ + kfree(key->payload.data); +} + +/* + * dispose of the data dangling from the corpse of a rxrpc key + */ +static void rxrpc_destroy_s(struct key *key) +{ + if (key->payload.data) { + crypto_free_blkcipher(key->payload.data); + key->payload.data = 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 = kmalloc(optlen + 1, GFP_KERNEL); + if (!description) + return -ENOMEM; + + if (copy_from_user(description, optval, optlen)) { + kfree(description); + return -EFAULT; + } + description[optlen] = 0; + + 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 = kmalloc(optlen + 1, GFP_KERNEL); + if (!description) + return -ENOMEM; + + if (copy_from_user(description, optval, optlen)) { + kfree(description); + return -EFAULT; + } + description[optlen] = 0; + + 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) +{ + struct key *key; + int ret; + + struct { + u32 kver; + struct rxkad_key tsec; + } data; + + _enter(""); + + key = key_alloc(&key_type_rxrpc, "x", 0, 0, current, 0, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(key)) { + _leave(" = -ENOMEM [alloc %ld]", PTR_ERR(key)); + return -ENOMEM; + } + + _debug("key %d", key_serial(key)); + + data.kver = 1; + data.tsec.security_index = 2; + data.tsec.ticket_len = 0; + data.tsec.expiry = expiry; + data.tsec.kvno = 0; + + memcpy(&data.tsec.session_key, session_key, + sizeof(data.tsec.session_key)); + + ret = key_instantiate_and_link(key, &data, sizeof(data), NULL, NULL); + if (ret < 0) + goto error; + + conn->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); diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c new file mode 100644 index 00000000000..a20a2c0fe10 --- /dev/null +++ b/net/rxrpc/ar-local.c @@ -0,0 +1,309 @@ +/* AF_RXRPC local endpoint management + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static LIST_HEAD(rxrpc_locals); +DEFINE_RWLOCK(rxrpc_local_lock); +static DECLARE_RWSEM(rxrpc_local_sem); +static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq); + +static void rxrpc_destroy_local(struct work_struct *work); + +/* + * allocate a new local + */ +static +struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx) +{ + struct rxrpc_local *local; + + local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); + if (local) { + INIT_WORK(&local->destroyer, &rxrpc_destroy_local); + INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls); + INIT_WORK(&local->rejecter, &rxrpc_reject_packets); + INIT_LIST_HEAD(&local->services); + INIT_LIST_HEAD(&local->link); + init_rwsem(&local->defrag_sem); + skb_queue_head_init(&local->accept_queue); + skb_queue_head_init(&local->reject_queue); + spin_lock_init(&local->lock); + rwlock_init(&local->services_lock); + atomic_set(&local->usage, 1); + local->debug_id = atomic_inc_return(&rxrpc_debug_id); + memcpy(&local->srx, srx, sizeof(*srx)); + } + + _leave(" = %p", local); + return local; +} + +/* + * create the local socket + * - must be called with rxrpc_local_sem writelocked + */ +static int rxrpc_create_local(struct rxrpc_local *local) +{ + struct sock *sock; + int ret, opt; + + _enter("%p{%d}", local, local->srx.transport_type); + + /* create a socket to represent the local endpoint */ + ret = sock_create_kern(PF_INET, local->srx.transport_type, IPPROTO_UDP, + &local->socket); + if (ret < 0) { + _leave(" = %d [socket]", ret); + return ret; + } + + /* if a local address was supplied then bind it */ + if (local->srx.transport_len > sizeof(sa_family_t)) { + _debug("bind"); + ret = kernel_bind(local->socket, + (struct sockaddr *) &local->srx.transport, + local->srx.transport_len); + if (ret < 0) { + _debug("bind failed"); + goto error; + } + } + + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + /* we want to set the don't fragment bit */ + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + write_lock_bh(&rxrpc_local_lock); + list_add(&local->link, &rxrpc_locals); + write_unlock_bh(&rxrpc_local_lock); + + /* set the socket up */ + sock = local->socket->sk; + sock->sk_user_data = local; + sock->sk_data_ready = rxrpc_data_ready; + sock->sk_error_report = rxrpc_UDP_error_report; + _leave(" = 0"); + return 0; + +error: + local->socket->ops->shutdown(local->socket, 2); + local->socket->sk->sk_user_data = NULL; + sock_release(local->socket); + local->socket = NULL; + + _leave(" = %d", ret); + return ret; +} + +/* + * create a new local endpoint using the specified UDP address + */ +struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx) +{ + struct rxrpc_local *local; + int ret; + + _enter("{%d,%u,%u.%u.%u.%u+%hu}", + srx->transport_type, + srx->transport.family, + NIPQUAD(srx->transport.sin.sin_addr), + ntohs(srx->transport.sin.sin_port)); + + down_write(&rxrpc_local_sem); + + /* see if we have a suitable local local endpoint already */ + read_lock_bh(&rxrpc_local_lock); + + list_for_each_entry(local, &rxrpc_locals, link) { + _debug("CMP {%d,%u,%u.%u.%u.%u+%hu}", + local->srx.transport_type, + local->srx.transport.family, + NIPQUAD(local->srx.transport.sin.sin_addr), + ntohs(local->srx.transport.sin.sin_port)); + + if (local->srx.transport_type != srx->transport_type || + local->srx.transport.family != srx->transport.family) + continue; + + switch (srx->transport.family) { + case AF_INET: + if (local->srx.transport.sin.sin_port != + srx->transport.sin.sin_port) + continue; + if (memcmp(&local->srx.transport.sin.sin_addr, + &srx->transport.sin.sin_addr, + sizeof(struct in_addr)) != 0) + continue; + goto found_local; + + default: + BUG(); + } + } + + read_unlock_bh(&rxrpc_local_lock); + + /* we didn't find one, so we need to create one */ + local = rxrpc_alloc_local(srx); + if (!local) { + up_write(&rxrpc_local_sem); + return ERR_PTR(-ENOMEM); + } + + ret = rxrpc_create_local(local); + if (ret < 0) { + up_write(&rxrpc_local_sem); + kfree(local); + _leave(" = %d", ret); + return ERR_PTR(ret); + } + + up_write(&rxrpc_local_sem); + + _net("LOCAL new %d {%d,%u,%u.%u.%u.%u+%hu}", + local->debug_id, + local->srx.transport_type, + local->srx.transport.family, + NIPQUAD(local->srx.transport.sin.sin_addr), + ntohs(local->srx.transport.sin.sin_port)); + + _leave(" = %p [new]", local); + return local; + +found_local: + rxrpc_get_local(local); + read_unlock_bh(&rxrpc_local_lock); + up_write(&rxrpc_local_sem); + + _net("LOCAL old %d {%d,%u,%u.%u.%u.%u+%hu}", + local->debug_id, + local->srx.transport_type, + local->srx.transport.family, + NIPQUAD(local->srx.transport.sin.sin_addr), + ntohs(local->srx.transport.sin.sin_port)); + + _leave(" = %p [reuse]", local); + return local; +} + +/* + * release a local endpoint + */ +void rxrpc_put_local(struct rxrpc_local *local) +{ + _enter("%p{u=%d}", local, atomic_read(&local->usage)); + + ASSERTCMP(atomic_read(&local->usage), >, 0); + + /* to prevent a race, the decrement and the dequeue must be effectively + * atomic */ + write_lock_bh(&rxrpc_local_lock); + if (unlikely(atomic_dec_and_test(&local->usage))) { + _debug("destroy local"); + schedule_work(&local->destroyer); + } + write_unlock_bh(&rxrpc_local_lock); + _leave(""); +} + +/* + * destroy a local endpoint + */ +static void rxrpc_destroy_local(struct work_struct *work) +{ + struct rxrpc_local *local = + container_of(work, struct rxrpc_local, destroyer); + + _enter("%p{%d}", local, atomic_read(&local->usage)); + + down_write(&rxrpc_local_sem); + + write_lock_bh(&rxrpc_local_lock); + if (atomic_read(&local->usage) > 0) { + write_unlock_bh(&rxrpc_local_lock); + up_read(&rxrpc_local_sem); + _leave(" [resurrected]"); + return; + } + + list_del(&local->link); + local->socket->sk->sk_user_data = NULL; + write_unlock_bh(&rxrpc_local_lock); + + downgrade_write(&rxrpc_local_sem); + + ASSERT(list_empty(&local->services)); + ASSERT(!work_pending(&local->acceptor)); + ASSERT(!work_pending(&local->rejecter)); + + /* finish cleaning up the local descriptor */ + rxrpc_purge_queue(&local->accept_queue); + rxrpc_purge_queue(&local->reject_queue); + local->socket->ops->shutdown(local->socket, 2); + sock_release(local->socket); + + up_read(&rxrpc_local_sem); + + _net("DESTROY LOCAL %d", local->debug_id); + kfree(local); + + if (list_empty(&rxrpc_locals)) + wake_up_all(&rxrpc_local_wq); + + _leave(""); +} + +/* + * preemptively destroy all local local endpoint rather than waiting for + * them to be destroyed + */ +void __exit rxrpc_destroy_all_locals(void) +{ + DECLARE_WAITQUEUE(myself,current); + + _enter(""); + + /* we simply have to wait for them to go away */ + if (!list_empty(&rxrpc_locals)) { + set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(&rxrpc_local_wq, &myself); + + while (!list_empty(&rxrpc_locals)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + + remove_wait_queue(&rxrpc_local_wq, &myself); + set_current_state(TASK_RUNNING); + } + + _leave(""); +} diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c new file mode 100644 index 00000000000..67aa9510f09 --- /dev/null +++ b/net/rxrpc/ar-output.c @@ -0,0 +1,658 @@ +/* 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. + */ + +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/circ_buf.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +int rxrpc_resend_timeout = 4; + +static int rxrpc_send_data(struct kiocb *iocb, + 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 rxrpc_sock *rx, struct msghdr *msg, + unsigned long *user_call_ID, + enum rxrpc_command *command, + u32 *abort_code, + bool server) +{ + struct cmsghdr *cmsg; + int len; + + *command = RXRPC_CMD_SEND_DATA; + + if (msg->msg_controllen == 0) + return -EINVAL; + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { + 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); + 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; + if (!server) + return -EISCONN; + break; + + default: + 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->abort_code = abort_code; + set_bit(RXRPC_CALL_ABORT, &call->events); + del_timer_sync(&call->resend_timer); + del_timer_sync(&call->ack_timer); + clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_ACK, &call->events); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + schedule_work(&call->processor); + } + + write_unlock_bh(&call->state_lock); +} + +/* + * send a message forming part of a client call through an RxRPC socket + * - caller holds the socket locked + * - the socket may be either a client socket or a server socket + */ +int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, + struct rxrpc_transport *trans, struct msghdr *msg, + size_t len) +{ + struct rxrpc_conn_bundle *bundle; + enum rxrpc_command cmd; + struct rxrpc_call *call; + unsigned long user_call_ID = 0; + struct key *key; + __be16 service_id; + u32 abort_code = 0; + int ret; + + _enter(""); + + ASSERT(trans != NULL); + + ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, + false); + if (ret < 0) + return ret; + + bundle = NULL; + if (trans) { + service_id = rx->service_id; + if (msg->msg_name) { + struct sockaddr_rxrpc *srx = + (struct sockaddr_rxrpc *) msg->msg_name; + service_id = htons(srx->srx_service); + } + key = rx->key; + if (key && !rx->key->payload.data) + key = NULL; + bundle = rxrpc_get_bundle(rx, trans, key, service_id, + GFP_KERNEL); + if (IS_ERR(bundle)) + return PTR_ERR(bundle); + } + + call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, + abort_code == 0, GFP_KERNEL); + if (trans) + rxrpc_put_bundle(trans, bundle); + if (IS_ERR(call)) { + _leave(" = %ld", PTR_ERR(call)); + return PTR_ERR(call); + } + + _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 = -ESHUTDOWN; + } else if (cmd == RXRPC_CMD_SEND_ABORT) { + rxrpc_send_abort(call, abort_code); + } else if (cmd != RXRPC_CMD_SEND_DATA) { + ret = -EINVAL; + } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { + /* request phase complete for this client call */ + ret = -EPROTO; + } else { + ret = rxrpc_send_data(iocb, rx, call, msg, len); + } + + rxrpc_put_call(call); + _leave(" = %d", ret); + return ret; +} + +/* + * send a message through a server socket + * - caller holds the socket locked + */ +int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, + struct msghdr *msg, size_t len) +{ + enum rxrpc_command cmd; + struct rxrpc_call *call; + unsigned long user_call_ID = 0; + u32 abort_code = 0; + int ret; + + _enter(""); + + ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, + true); + if (ret < 0) + return ret; + + if (cmd == RXRPC_CMD_ACCEPT) + return rxrpc_accept_call(rx, user_call_ID); + + call = rxrpc_find_server_call(rx, user_call_ID); + if (!call) + return -EBADSLT; + if (call->state >= RXRPC_CALL_COMPLETE) { + ret = -ESHUTDOWN; + goto out; + } + + switch (cmd) { + case RXRPC_CMD_SEND_DATA: + if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && + call->state != RXRPC_CALL_SERVER_ACK_REQUEST && + call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + /* Tx phase not yet begun for this call */ + ret = -EPROTO; + break; + } + + ret = rxrpc_send_data(iocb, rx, call, msg, len); + break; + + case RXRPC_CMD_SEND_ABORT: + rxrpc_send_abort(call, abort_code); + break; + default: + BUG(); + } + + out: + rxrpc_put_call(call); + _leave(" = %d", ret); + return ret; +} + +/* + * send a packet through the transport endpoint + */ +int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb) +{ + 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 = &trans->peer->srx.transport.sin; + msg.msg_namelen = sizeof(trans->peer->srx.transport.sin); + 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_header) < trans->peer->maxdata) { + down_read(&trans->local->defrag_sem); + /* send the packet by UDP + * - returns -EMSGSIZE if UDP would have to fragment the packet + * to go out of the interface + * - in which case, we'll have processed the ICMP error + * message and update the peer record + */ + ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1, + iov[0].iov_len); + + up_read(&trans->local->defrag_sem); + if (ret == -EMSGSIZE) + goto send_fragmentable; + + _leave(" = %d [%u]", ret, trans->peer->maxdata); + return ret; + } + +send_fragmentable: + /* attempt to send this message with fragmentation enabled */ + _debug("send fragment"); + + down_write(&trans->local->defrag_sem); + opt = IP_PMTUDISC_DONT; + ret = kernel_setsockopt(trans->local->socket, SOL_IP, IP_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret == 0) { + ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1, + iov[0].iov_len); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(trans->local->socket, SOL_IP, + IP_MTU_DISCOVER, (char *) &opt, sizeof(opt)); + } + + up_write(&trans->local->defrag_sem); + _leave(" = %d [frag %u]", ret, trans->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, 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, 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_RESEND_TIMER, &call->events)) + schedule_work(&call->processor); + } + 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 }", + ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); + + sp->need_resend = 0; + sp->resend_at = jiffies + rxrpc_resend_timeout * HZ; + 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_packet(call->conn->trans, 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 = 1; + rxrpc_instant_resend(call); + } + + _leave(""); +} + +/* + * send data through a socket + * - must be called in process context + * - caller holds the socket locked + */ +static int rxrpc_send_data(struct kiocb *iocb, + struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct msghdr *msg, size_t len) +{ + struct rxrpc_skb_priv *sp; + unsigned char __user *from; + struct sk_buff *skb; + struct iovec *iov; + struct sock *sk = &rx->sk; + long timeo; + bool more; + int ret, ioc, segment, copied; + + _enter(",,,{%zu},%zu", msg->msg_iovlen, len); + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + /* this should be in poll */ + clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + return -EPIPE; + + iov = msg->msg_iov; + ioc = msg->msg_iovlen - 1; + from = iov->iov_base; + segment = iov->iov_len; + iov++; + more = msg->msg_flags & MSG_MORE; + + skb = call->tx_pending; + call->tx_pending = NULL; + + copied = 0; + do { + int copy; + + if (segment > len) + segment = len; + + _debug("SEGMENT %d @%p", segment, from); + + if (!skb) { + size_t size, chunk, max, space; + + _debug("alloc"); + + if (CIRC_SPACE(call->acks_head, 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->trans->peer->maxdata; + max -= call->conn->security_size; + max &= ~(call->conn->size_align - 1UL); + + chunk = max; + if (chunk > len) + chunk = len; + + 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 */ + copy = skb_tailroom(skb); + ASSERTCMP(copy, >, 0); + if (copy > segment) + copy = segment; + if (copy > sp->remain) + copy = sp->remain; + + _debug("add"); + ret = skb_add_data(skb, from, copy); + _debug("added"); + if (ret < 0) + goto efault; + sp->remain -= copy; + skb->mark += copy; + + len -= copy; + segment -= copy; + from += copy; + while (segment == 0 && ioc > 0) { + from = iov->iov_base; + segment = iov->iov_len; + iov++; + ioc--; + } + if (len == 0) { + segment = 0; + ioc = 0; + } + + /* 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 || (segment == 0 && !more)) { + struct rxrpc_connection *conn = call->conn; + size_t pad; + + /* pad out if we're using security */ + if (conn->security) { + 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); + } + + sp->hdr.epoch = conn->epoch; + sp->hdr.cid = call->cid; + sp->hdr.callNumber = call->call_id; + sp->hdr.seq = + htonl(atomic_inc_return(&call->sequence)); + sp->hdr.serial = + htonl(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 = conn->service_id; + + sp->hdr.flags = conn->out_clientflag; + if (len == 0 && !more) + sp->hdr.flags |= RXRPC_LAST_PACKET; + else if (CIRC_SPACE(call->acks_head, call->acks_tail, + call->acks_winsz) > 1) + sp->hdr.flags |= RXRPC_MORE_PACKETS; + + ret = rxrpc_secure_packet( + call, skb, skb->mark, + skb->head + sizeof(struct rxrpc_header)); + if (ret < 0) + goto out; + + memcpy(skb->head, &sp->hdr, + sizeof(struct rxrpc_header)); + rxrpc_queue_packet(call, skb, segment == 0 && !more); + skb = NULL; + } + + } while (segment > 0); + +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->conn->trans->peer->net_error; + else + ret = -ECONNABORTED; + _leave(" = %d", ret); + return ret; + +maybe_error: + if (copied) + ret = copied; + goto out; + +efault: + ret = -EFAULT; + goto out; +} diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c new file mode 100644 index 00000000000..69ac355546a --- /dev/null +++ b/net/rxrpc/ar-peer.c @@ -0,0 +1,273 @@ +/* RxRPC remote transport endpoint management + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/udp.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/icmp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include <net/ip.h> +#include "ar-internal.h" + +static LIST_HEAD(rxrpc_peers); +static DEFINE_RWLOCK(rxrpc_peer_lock); +static DECLARE_WAIT_QUEUE_HEAD(rxrpc_peer_wq); + +static void rxrpc_destroy_peer(struct work_struct *work); + +/* + * allocate a new peer + */ +static struct rxrpc_peer *rxrpc_alloc_peer(struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + struct rxrpc_peer *peer; + + _enter(""); + + peer = kzalloc(sizeof(struct rxrpc_peer), gfp); + if (peer) { + INIT_WORK(&peer->destroyer, &rxrpc_destroy_peer); + INIT_LIST_HEAD(&peer->link); + INIT_LIST_HEAD(&peer->error_targets); + spin_lock_init(&peer->lock); + atomic_set(&peer->usage, 1); + peer->debug_id = atomic_inc_return(&rxrpc_debug_id); + memcpy(&peer->srx, srx, sizeof(*srx)); + + peer->mtu = peer->if_mtu = 65535; + + 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_header); + peer->maxdata = peer->mtu - peer->hdrsize; + } + + _leave(" = %p", peer); + return peer; +} + +/* + * obtain a remote transport endpoint for the specified address + */ +struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp) +{ + struct rxrpc_peer *peer, *candidate; + const char *new = "old"; + int usage; + + _enter("{%d,%d,%u.%u.%u.%u+%hu}", + srx->transport_type, + srx->transport_len, + NIPQUAD(srx->transport.sin.sin_addr), + ntohs(srx->transport.sin.sin_port)); + + /* search the peer list first */ + read_lock_bh(&rxrpc_peer_lock); + list_for_each_entry(peer, &rxrpc_peers, link) { + _debug("check PEER %d { u=%d t=%d l=%d }", + peer->debug_id, + atomic_read(&peer->usage), + peer->srx.transport_type, + peer->srx.transport_len); + + if (atomic_read(&peer->usage) > 0 && + peer->srx.transport_type == srx->transport_type && + peer->srx.transport_len == srx->transport_len && + memcmp(&peer->srx.transport, + &srx->transport, + srx->transport_len) == 0) + goto found_extant_peer; + } + read_unlock_bh(&rxrpc_peer_lock); + + /* not yet present - create a candidate for a new record and then + * redo the search */ + candidate = rxrpc_alloc_peer(srx, gfp); + if (!candidate) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + write_lock_bh(&rxrpc_peer_lock); + + list_for_each_entry(peer, &rxrpc_peers, link) { + if (atomic_read(&peer->usage) > 0 && + peer->srx.transport_type == srx->transport_type && + peer->srx.transport_len == srx->transport_len && + memcmp(&peer->srx.transport, + &srx->transport, + srx->transport_len) == 0) + goto found_extant_second; + } + + /* we can now add the new candidate to the list */ + peer = candidate; + candidate = NULL; + + list_add_tail(&peer->link, &rxrpc_peers); + write_unlock_bh(&rxrpc_peer_lock); + new = "new"; + +success: + _net("PEER %s %d {%d,%u,%u.%u.%u.%u+%hu}", + new, + peer->debug_id, + peer->srx.transport_type, + peer->srx.transport.family, + NIPQUAD(peer->srx.transport.sin.sin_addr), + ntohs(peer->srx.transport.sin.sin_port)); + + _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + return peer; + + /* we found the peer in the list immediately */ +found_extant_peer: + usage = atomic_inc_return(&peer->usage); + read_unlock_bh(&rxrpc_peer_lock); + goto success; + + /* we found the peer on the second time through the list */ +found_extant_second: + usage = atomic_inc_return(&peer->usage); + write_unlock_bh(&rxrpc_peer_lock); + kfree(candidate); + goto success; +} + +/* + * find the peer associated with a packet + */ +struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *local, + __be32 addr, __be16 port) +{ + struct rxrpc_peer *peer; + + _enter(""); + + /* search the peer list */ + read_lock_bh(&rxrpc_peer_lock); + + if (local->srx.transport.family == AF_INET && + local->srx.transport_type == SOCK_DGRAM + ) { + list_for_each_entry(peer, &rxrpc_peers, link) { + if (atomic_read(&peer->usage) > 0 && + peer->srx.transport_type == SOCK_DGRAM && + peer->srx.transport.family == AF_INET && + peer->srx.transport.sin.sin_port == port && + peer->srx.transport.sin.sin_addr.s_addr == addr) + goto found_UDP_peer; + } + + goto new_UDP_peer; + } + + read_unlock_bh(&rxrpc_peer_lock); + _leave(" = -EAFNOSUPPORT"); + return ERR_PTR(-EAFNOSUPPORT); + +found_UDP_peer: + _net("Rx UDP DGRAM from peer %d", peer->debug_id); + atomic_inc(&peer->usage); + read_unlock_bh(&rxrpc_peer_lock); + _leave(" = %p", peer); + return peer; + +new_UDP_peer: + _net("Rx UDP DGRAM from NEW peer %d", peer->debug_id); + read_unlock_bh(&rxrpc_peer_lock); + _leave(" = -EBUSY [new]"); + return ERR_PTR(-EBUSY); +} + +/* + * release a remote transport endpoint + */ +void rxrpc_put_peer(struct rxrpc_peer *peer) +{ + _enter("%p{u=%d}", peer, atomic_read(&peer->usage)); + + ASSERTCMP(atomic_read(&peer->usage), >, 0); + + if (likely(!atomic_dec_and_test(&peer->usage))) { + _leave(" [in use]"); + return; + } + + schedule_work(&peer->destroyer); + _leave(""); +} + +/* + * destroy a remote transport endpoint + */ +static void rxrpc_destroy_peer(struct work_struct *work) +{ + struct rxrpc_peer *peer = + container_of(work, struct rxrpc_peer, destroyer); + + _enter("%p{%d}", peer, atomic_read(&peer->usage)); + + write_lock_bh(&rxrpc_peer_lock); + list_del(&peer->link); + write_unlock_bh(&rxrpc_peer_lock); + + _net("DESTROY PEER %d", peer->debug_id); + kfree(peer); + + if (list_empty(&rxrpc_peers)) + wake_up_all(&rxrpc_peer_wq); + _leave(""); +} + +/* + * preemptively destroy all the peer records from a transport endpoint rather + * than waiting for them to time out + */ +void __exit rxrpc_destroy_all_peers(void) +{ + DECLARE_WAITQUEUE(myself,current); + + _enter(""); + + /* we simply have to wait for them to go away */ + if (!list_empty(&rxrpc_peers)) { + set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(&rxrpc_peer_wq, &myself); + + while (!list_empty(&rxrpc_peers)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + + remove_wait_queue(&rxrpc_peer_wq, &myself); + set_current_state(TASK_RUNNING); + } + + _leave(""); +} diff --git a/net/rxrpc/ar-proc.c b/net/rxrpc/ar-proc.c new file mode 100644 index 00000000000..58f4b4e5cec --- /dev/null +++ b/net/rxrpc/ar-proc.c @@ -0,0 +1,247 @@ +/* /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 *rxrpc_conn_states[] = { + [RXRPC_CONN_UNUSED] = "Unused ", + [RXRPC_CONN_CLIENT] = "Client ", + [RXRPC_CONN_SERVER_UNSECURED] = "SvUnsec ", + [RXRPC_CONN_SERVER_CHALLENGING] = "SvChall ", + [RXRPC_CONN_SERVER] = "SvSecure", + [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", + [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CONN_NETWORK_ERROR] = "NetError", +}; + +const char *rxrpc_call_states[] = { + [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 ", +}; + +/* + * 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) +{ + struct list_head *_p; + loff_t pos = *_pos; + + read_lock(&rxrpc_call_lock); + if (!pos) + return SEQ_START_TOKEN; + pos--; + + list_for_each(_p, &rxrpc_calls) + if (!pos--) + break; + + return _p != &rxrpc_calls ? _p : NULL; +} + +static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct list_head *_p; + + (*pos)++; + + _p = v; + _p = (v == SEQ_START_TOKEN) ? rxrpc_calls.next : _p->next; + + return _p != &rxrpc_calls ? _p : NULL; +} + +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_transport *trans; + struct rxrpc_call *call; + char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; + + if (v == SEQ_START_TOKEN) { + 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); + trans = call->conn->trans; + + sprintf(lbuff, NIPQUAD_FMT":%u", + NIPQUAD(trans->local->srx.transport.sin.sin_addr), + ntohs(trans->local->srx.transport.sin.sin_port)); + + sprintf(rbuff, NIPQUAD_FMT":%u", + NIPQUAD(trans->peer->srx.transport.sin.sin_addr), + ntohs(trans->peer->srx.transport.sin.sin_port)); + + seq_printf(seq, + "UDP %-22.22s %-22.22s %4x %08x %08x %s %3u" + " %-8.8s %08x %lx\n", + lbuff, + rbuff, + ntohs(call->conn->service_id), + ntohl(call->conn->cid), + ntohl(call->call_id), + call->conn->in_clientflag ? "Svc" : "Clt", + atomic_read(&call->usage), + rxrpc_call_states[call->state], + call->abort_code, + call->user_call_ID); + + return 0; +} + +static 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); +} + +struct file_operations rxrpc_call_seq_fops = { + .owner = THIS_MODULE, + .open = rxrpc_call_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +/* + * 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) +{ + struct list_head *_p; + loff_t pos = *_pos; + + read_lock(&rxrpc_connection_lock); + if (!pos) + return SEQ_START_TOKEN; + pos--; + + list_for_each(_p, &rxrpc_connections) + if (!pos--) + break; + + return _p != &rxrpc_connections ? _p : NULL; +} + +static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct list_head *_p; + + (*pos)++; + + _p = v; + _p = (v == SEQ_START_TOKEN) ? rxrpc_connections.next : _p->next; + + return _p != &rxrpc_connections ? _p : NULL; +} + +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; + struct rxrpc_transport *trans; + char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Proto Local Remote " + " SvID ConnID Calls End Use State Key " + " Serial ISerial\n" + ); + return 0; + } + + conn = list_entry(v, struct rxrpc_connection, link); + trans = conn->trans; + + sprintf(lbuff, NIPQUAD_FMT":%u", + NIPQUAD(trans->local->srx.transport.sin.sin_addr), + ntohs(trans->local->srx.transport.sin.sin_port)); + + sprintf(rbuff, NIPQUAD_FMT":%u", + NIPQUAD(trans->peer->srx.transport.sin.sin_addr), + ntohs(trans->peer->srx.transport.sin.sin_port)); + + seq_printf(seq, + "UDP %-22.22s %-22.22s %4x %08x %08x %s %3u" + " %s %08x %08x %08x\n", + lbuff, + rbuff, + ntohs(conn->service_id), + ntohl(conn->cid), + conn->call_counter, + conn->in_clientflag ? "Svc" : "Clt", + atomic_read(&conn->usage), + rxrpc_conn_states[conn->state], + key_serial(conn->key), + atomic_read(&conn->serial), + atomic_read(&conn->hi_serial)); + + return 0; +} + +static 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); +} + +struct file_operations rxrpc_connection_seq_fops = { + .owner = THIS_MODULE, + .open = rxrpc_connection_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c new file mode 100644 index 00000000000..e947d5c1590 --- /dev/null +++ b/net/rxrpc/ar-recvmsg.c @@ -0,0 +1,366 @@ +/* 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. + */ + +#include <linux/net.h> +#include <linux/skbuff.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 + */ +static 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_RELEASE, &call->events)) + schedule_work(&call->processor); + 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 kiocb *iocb, 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 && + (msg->msg_flags & MSG_PEEK || timeo == 0)) + goto out; + + /* wait for a message to turn up */ + release_sock(&rx->sk); + prepare_to_wait_exclusive(rx->sk.sk_sleep, &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(rx->sk.sk_sleep, &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 && msg->msg_namelen > 0) + memcpy(&msg->msg_name, &call->conn->trans->peer->srx, + sizeof(call->conn->trans->peer->srx)); + 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 }", + ntohl(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(ntohl(sp->hdr.seq), >=, call->rx_data_recv); + ASSERTCMP(ntohl(sp->hdr.seq), <=, call->rx_data_recv + 1); + call->rx_data_recv = ntohl(sp->hdr.seq); + + ASSERTCMP(ntohl(sp->hdr.seq), >, call->rx_data_eaten); + + offset = sp->offset; + copy = skb->len - offset; + if (copy > len - copied) + copy = len - copied; + + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + ret = skb_copy_datagram_iovec(skb, offset, + msg->msg_iov, copy); + } else { + ret = skb_copy_and_csum_datagram_iovec(skb, offset, + msg->msg_iov); + if (ret == -EINVAL) + goto csum_copy_error; + } + + 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 (sp->hdr.flags & RXRPC_LAST_PACKET) { + _debug("last"); + if (call->conn->out_clientflag) { + /* 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->abort_code; + 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: + 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; + +csum_copy_error: + _debug("csum error"); + release_sock(&rx->sk); + if (continue_call) + rxrpc_put_call(continue_call); + rxrpc_kill_skb(skb); + skb_kill_datagram(&rx->sk, skb, flags); + rxrpc_put_call(call); + return -EAGAIN; + +wait_interrupted: + ret = sock_intr_errno(timeo); +wait_error: + finish_wait(rx->sk.sk_sleep, &wait); + if (continue_call) + rxrpc_put_call(continue_call); + if (copied) + copied = ret; + _leave(" = %d [waitfail %d]", copied, ret); + return copied; + +} diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/ar-security.c new file mode 100644 index 00000000000..60d1d364430 --- /dev/null +++ b/net/rxrpc/ar-security.c @@ -0,0 +1,258 @@ +/* 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 "ar-internal.h" + +static LIST_HEAD(rxrpc_security_methods); +static DECLARE_RWSEM(rxrpc_security_sem); + +/* + * get an RxRPC security module + */ +static struct rxrpc_security *rxrpc_security_get(struct rxrpc_security *sec) +{ + return try_module_get(sec->owner) ? sec : NULL; +} + +/* + * release an RxRPC security module + */ +static void rxrpc_security_put(struct rxrpc_security *sec) +{ + module_put(sec->owner); +} + +/* + * look up an rxrpc security module + */ +struct rxrpc_security *rxrpc_security_lookup(u8 security_index) +{ + struct rxrpc_security *sec = NULL; + + _enter(""); + + down_read(&rxrpc_security_sem); + + list_for_each_entry(sec, &rxrpc_security_methods, link) { + if (sec->security_index == security_index) { + if (unlikely(!rxrpc_security_get(sec))) + break; + goto out; + } + } + + sec = NULL; +out: + up_read(&rxrpc_security_sem); + _leave(" = %p [%s]", sec, sec ? sec->name : ""); + return sec; +} + +/** + * rxrpc_register_security - register an RxRPC security handler + * @sec: security module + * + * register an RxRPC security handler for use by RxRPC + */ +int rxrpc_register_security(struct rxrpc_security *sec) +{ + struct rxrpc_security *psec; + int ret; + + _enter(""); + down_write(&rxrpc_security_sem); + + ret = -EEXIST; + list_for_each_entry(psec, &rxrpc_security_methods, link) { + if (psec->security_index == sec->security_index) + goto out; + } + + list_add(&sec->link, &rxrpc_security_methods); + + printk(KERN_NOTICE "RxRPC: Registered security type %d '%s'\n", + sec->security_index, sec->name); + ret = 0; + +out: + up_write(&rxrpc_security_sem); + _leave(" = %d", ret); + return ret; +} + +EXPORT_SYMBOL_GPL(rxrpc_register_security); + +/** + * rxrpc_unregister_security - unregister an RxRPC security handler + * @sec: security module + * + * unregister an RxRPC security handler + */ +void rxrpc_unregister_security(struct rxrpc_security *sec) +{ + + _enter(""); + down_write(&rxrpc_security_sem); + list_del_init(&sec->link); + up_write(&rxrpc_security_sem); + + printk(KERN_NOTICE "RxRPC: Unregistered security type %d '%s'\n", + sec->security_index, sec->name); +} + +EXPORT_SYMBOL_GPL(rxrpc_unregister_security); + +/* + * initialise the security on a client connection + */ +int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) +{ + struct rxrpc_security *sec; + struct key *key = conn->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; + + sec = rxrpc_security_lookup(key->type_data.x[0]); + if (!sec) + return -EKEYREJECTED; + conn->security = sec; + + ret = conn->security->init_connection_security(conn); + if (ret < 0) { + rxrpc_security_put(conn->security); + conn->security = NULL; + return ret; + } + + _leave(" = 0"); + return 0; +} + +/* + * initialise the security on a server connection + */ +int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +{ + struct rxrpc_security *sec; + struct rxrpc_local *local = conn->trans->local; + struct rxrpc_sock *rx; + struct key *key; + key_ref_t kref; + char kdesc[5+1+3+1]; + + _enter(""); + + sprintf(kdesc, "%u:%u", ntohs(conn->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->service_id == conn->service_id) + goto found_service; + } + + /* the service appears to have died */ + read_unlock_bh(&local->services_lock); + rxrpc_security_put(sec); + _leave(" = -ENOENT"); + return -ENOENT; + +found_service: + if (!rx->securities) { + read_unlock_bh(&local->services_lock); + rxrpc_security_put(sec); + _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); + rxrpc_security_put(sec); + _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; +} + +/* + * secure a packet prior to transmission + */ +int rxrpc_secure_packet(const struct rxrpc_call *call, + struct sk_buff *skb, + size_t data_size, + void *sechdr) +{ + if (call->conn->security) + return call->conn->security->secure_packet( + call, skb, data_size, sechdr); + return 0; +} + +/* + * secure a packet prior to transmission + */ +int rxrpc_verify_packet(const struct rxrpc_call *call, struct sk_buff *skb, + u32 *_abort_code) +{ + if (call->conn->security) + return call->conn->security->verify_packet( + call, skb, _abort_code); + return 0; +} + +/* + * clear connection security + */ +void rxrpc_clear_conn_security(struct rxrpc_connection *conn) +{ + _enter("{%d}", conn->debug_id); + + if (conn->security) { + conn->security->clear(conn); + rxrpc_security_put(conn->security); + conn->security = NULL; + } + + key_put(conn->key); + key_put(conn->server_key); +} diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c new file mode 100644 index 00000000000..d73f6fc7601 --- /dev/null +++ b/net/rxrpc/ar-skbuff.c @@ -0,0 +1,118 @@ +/* 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. + */ + +#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_ACK_FINAL, &call->events); + if (try_to_del_timer_sync(&call->ack_timer) >= 0) + schedule_work(&call->processor); + 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", ntohl(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 = ntohl(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)) { + _debug("send Rx idle ACK"); + __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial, + true); + } + + spin_unlock_bh(&call->lock); +} + +/* + * destroy a packet that has an RxRPC control buffer + * - advance the hard-ACK state of the parent call (done here in case something + * in the kernel bypasses recvmsg() and steals the packet directly off of the + * socket receive queue) + */ +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) { + /* send the final ACK on a client call */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) + rxrpc_hard_ACK_data(call, sp); + rxrpc_put_call(call); + sp->call = NULL; + } + + if (skb->sk) + sock_rfree(skb); + _leave(""); +} diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c new file mode 100644 index 00000000000..9b4e5cb545d --- /dev/null +++ b/net/rxrpc/ar-transport.c @@ -0,0 +1,276 @@ +/* RxRPC point-to-point transport session management + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static void rxrpc_transport_reaper(struct work_struct *work); + +static LIST_HEAD(rxrpc_transports); +static DEFINE_RWLOCK(rxrpc_transport_lock); +static unsigned long rxrpc_transport_timeout = 3600 * 24; +static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper); + +/* + * allocate a new transport session manager + */ +static struct rxrpc_transport *rxrpc_alloc_transport(struct rxrpc_local *local, + struct rxrpc_peer *peer, + gfp_t gfp) +{ + struct rxrpc_transport *trans; + + _enter(""); + + trans = kzalloc(sizeof(struct rxrpc_transport), gfp); + if (trans) { + trans->local = local; + trans->peer = peer; + INIT_LIST_HEAD(&trans->link); + trans->bundles = RB_ROOT; + trans->client_conns = RB_ROOT; + trans->server_conns = RB_ROOT; + skb_queue_head_init(&trans->error_queue); + spin_lock_init(&trans->client_lock); + rwlock_init(&trans->conn_lock); + atomic_set(&trans->usage, 1); + trans->debug_id = atomic_inc_return(&rxrpc_debug_id); + + if (peer->srx.transport.family == AF_INET) { + switch (peer->srx.transport_type) { + case SOCK_DGRAM: + INIT_WORK(&trans->error_handler, + rxrpc_UDP_error_handler); + break; + default: + BUG(); + break; + } + } else { + BUG(); + } + } + + _leave(" = %p", trans); + return trans; +} + +/* + * obtain a transport session for the nominated endpoints + */ +struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *local, + struct rxrpc_peer *peer, + gfp_t gfp) +{ + struct rxrpc_transport *trans, *candidate; + const char *new = "old"; + int usage; + + _enter("{%u.%u.%u.%u+%hu},{%u.%u.%u.%u+%hu},", + NIPQUAD(local->srx.transport.sin.sin_addr), + ntohs(local->srx.transport.sin.sin_port), + NIPQUAD(peer->srx.transport.sin.sin_addr), + ntohs(peer->srx.transport.sin.sin_port)); + + /* search the transport list first */ + read_lock_bh(&rxrpc_transport_lock); + list_for_each_entry(trans, &rxrpc_transports, link) { + if (trans->local == local && trans->peer == peer) + goto found_extant_transport; + } + read_unlock_bh(&rxrpc_transport_lock); + + /* not yet present - create a candidate for a new record and then + * redo the search */ + candidate = rxrpc_alloc_transport(local, peer, gfp); + if (!candidate) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + write_lock_bh(&rxrpc_transport_lock); + + list_for_each_entry(trans, &rxrpc_transports, link) { + if (trans->local == local && trans->peer == peer) + goto found_extant_second; + } + + /* we can now add the new candidate to the list */ + trans = candidate; + candidate = NULL; + + rxrpc_get_local(trans->local); + atomic_inc(&trans->peer->usage); + list_add_tail(&trans->link, &rxrpc_transports); + write_unlock_bh(&rxrpc_transport_lock); + new = "new"; + +success: + _net("TRANSPORT %s %d local %d -> peer %d", + new, + trans->debug_id, + trans->local->debug_id, + trans->peer->debug_id); + + _leave(" = %p {u=%d}", trans, atomic_read(&trans->usage)); + return trans; + + /* we found the transport in the list immediately */ +found_extant_transport: + usage = atomic_inc_return(&trans->usage); + read_unlock_bh(&rxrpc_transport_lock); + goto success; + + /* we found the transport on the second time through the list */ +found_extant_second: + usage = atomic_inc_return(&trans->usage); + write_unlock_bh(&rxrpc_transport_lock); + kfree(candidate); + goto success; +} + +/* + * find the transport connecting two endpoints + */ +struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *local, + struct rxrpc_peer *peer) +{ + struct rxrpc_transport *trans; + + _enter("{%u.%u.%u.%u+%hu},{%u.%u.%u.%u+%hu},", + NIPQUAD(local->srx.transport.sin.sin_addr), + ntohs(local->srx.transport.sin.sin_port), + NIPQUAD(peer->srx.transport.sin.sin_addr), + ntohs(peer->srx.transport.sin.sin_port)); + + /* search the transport list */ + read_lock_bh(&rxrpc_transport_lock); + + list_for_each_entry(trans, &rxrpc_transports, link) { + if (trans->local == local && trans->peer == peer) + goto found_extant_transport; + } + + read_unlock_bh(&rxrpc_transport_lock); + _leave(" = NULL"); + return NULL; + +found_extant_transport: + atomic_inc(&trans->usage); + read_unlock_bh(&rxrpc_transport_lock); + _leave(" = %p", trans); + return trans; +} + +/* + * release a transport session + */ +void rxrpc_put_transport(struct rxrpc_transport *trans) +{ + _enter("%p{u=%d}", trans, atomic_read(&trans->usage)); + + ASSERTCMP(atomic_read(&trans->usage), >, 0); + + trans->put_time = xtime.tv_sec; + if (unlikely(atomic_dec_and_test(&trans->usage))) + _debug("zombie"); + /* let the reaper determine the timeout to avoid a race with + * overextending the timeout if the reaper is running at the + * same time */ + schedule_delayed_work(&rxrpc_transport_reap, 0); + _leave(""); +} + +/* + * clean up a transport session + */ +static void rxrpc_cleanup_transport(struct rxrpc_transport *trans) +{ + _net("DESTROY TRANS %d", trans->debug_id); + + rxrpc_purge_queue(&trans->error_queue); + + rxrpc_put_local(trans->local); + rxrpc_put_peer(trans->peer); + kfree(trans); +} + +/* + * reap dead transports that have passed their expiry date + */ +static void rxrpc_transport_reaper(struct work_struct *work) +{ + struct rxrpc_transport *trans, *_p; + unsigned long now, earliest, reap_time; + + LIST_HEAD(graveyard); + + _enter(""); + + now = xtime.tv_sec; + earliest = ULONG_MAX; + + /* extract all the transports that have been dead too long */ + write_lock_bh(&rxrpc_transport_lock); + list_for_each_entry_safe(trans, _p, &rxrpc_transports, link) { + _debug("reap TRANS %d { u=%d t=%ld }", + trans->debug_id, atomic_read(&trans->usage), + (long) now - (long) trans->put_time); + + if (likely(atomic_read(&trans->usage) > 0)) + continue; + + reap_time = trans->put_time + rxrpc_transport_timeout; + if (reap_time <= now) + list_move_tail(&trans->link, &graveyard); + else if (reap_time < earliest) + earliest = reap_time; + } + write_unlock_bh(&rxrpc_transport_lock); + + if (earliest != ULONG_MAX) { + _debug("reschedule reaper %ld", (long) earliest - now); + ASSERTCMP(earliest, >, now); + schedule_delayed_work(&rxrpc_transport_reap, + (earliest - now) * HZ); + } + + /* then destroy all those pulled out */ + while (!list_empty(&graveyard)) { + trans = list_entry(graveyard.next, struct rxrpc_transport, + link); + list_del_init(&trans->link); + + ASSERTCMP(atomic_read(&trans->usage), ==, 0); + rxrpc_cleanup_transport(trans); + } + + _leave(""); +} + +/* + * preemptively destroy all the transport session records rather than waiting + * for them to time out + */ +void __exit rxrpc_destroy_all_transports(void) +{ + _enter(""); + + rxrpc_transport_timeout = 0; + cancel_delayed_work(&rxrpc_transport_reap); + schedule_delayed_work(&rxrpc_transport_reap, 0); + + _leave(""); +} diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c new file mode 100644 index 00000000000..1eaf529efac --- /dev/null +++ b/net/rxrpc/rxkad.c @@ -0,0 +1,1153 @@ +/* Kerberos-based RxRPC security + * + * 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 <linux/scatterlist.h> +#include <linux/ctype.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +#define RXKAD_VERSION 2 +#define MAXKRB5TICKETLEN 1024 +#define RXKAD_TKT_TYPE_KERBEROS_V5 256 +#define ANAME_SZ 40 /* size of authentication name */ +#define INST_SZ 40 /* size of principal's instance */ +#define REALM_SZ 40 /* size of principal's auth domain */ +#define SNAME_SZ 40 /* size of service name */ + +unsigned rxrpc_debug; +module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(rxrpc_debug, "rxkad debugging mask"); + +struct rxkad_level1_hdr { + __be32 data_size; /* true data size (excluding padding) */ +}; + +struct rxkad_level2_hdr { + __be32 data_size; /* true data size (excluding padding) */ + __be32 checksum; /* decrypted data checksum */ +}; + +MODULE_DESCRIPTION("RxRPC network protocol type-2 security (Kerberos)"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +/* + * this holds a pinned cipher so that keventd doesn't get called by the cipher + * alloc routine, but since we have it to hand, we use it to decrypt RESPONSE + * packets + */ +static struct crypto_blkcipher *rxkad_ci; +static DEFINE_MUTEX(rxkad_ci_mutex); + +/* + * initialise connection security + */ +static int rxkad_init_connection_security(struct rxrpc_connection *conn) +{ + struct rxrpc_key_payload *payload; + struct crypto_blkcipher *ci; + int ret; + + _enter("{%d},{%x}", conn->debug_id, key_serial(conn->key)); + + payload = conn->key->payload.data; + conn->security_ix = payload->k.security_index; + + ci = crypto_alloc_blkcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(ci)) { + _debug("no cipher"); + ret = PTR_ERR(ci); + goto error; + } + + if (crypto_blkcipher_setkey(ci, payload->k.session_key, + sizeof(payload->k.session_key)) < 0) + BUG(); + + switch (conn->security_level) { + case RXRPC_SECURITY_PLAIN: + break; + case RXRPC_SECURITY_AUTH: + conn->size_align = 8; + conn->security_size = sizeof(struct rxkad_level1_hdr); + conn->header_size += sizeof(struct rxkad_level1_hdr); + break; + case RXRPC_SECURITY_ENCRYPT: + conn->size_align = 8; + conn->security_size = sizeof(struct rxkad_level2_hdr); + conn->header_size += sizeof(struct rxkad_level2_hdr); + break; + default: + ret = -EKEYREJECTED; + goto error; + } + + conn->cipher = ci; + ret = 0; +error: + _leave(" = %d", ret); + return ret; +} + +/* + * prime the encryption state with the invariant parts of a connection's + * description + */ +static void rxkad_prime_packet_security(struct rxrpc_connection *conn) +{ + struct rxrpc_key_payload *payload; + struct blkcipher_desc desc; + struct scatterlist sg[2]; + struct rxrpc_crypt iv; + struct { + __be32 x[4]; + } tmpbuf __attribute__((aligned(16))); /* must all be in same page */ + + _enter(""); + + if (!conn->key) + return; + + payload = conn->key->payload.data; + memcpy(&iv, payload->k.session_key, sizeof(iv)); + + desc.tfm = conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + tmpbuf.x[0] = conn->epoch; + tmpbuf.x[1] = conn->cid; + tmpbuf.x[2] = 0; + tmpbuf.x[3] = htonl(conn->security_ix); + + memset(sg, 0, sizeof(sg)); + sg_set_buf(&sg[0], &tmpbuf, sizeof(tmpbuf)); + sg_set_buf(&sg[1], &tmpbuf, sizeof(tmpbuf)); + crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf)); + + memcpy(&conn->csum_iv, &tmpbuf.x[2], sizeof(conn->csum_iv)); + ASSERTCMP(conn->csum_iv.n[0], ==, tmpbuf.x[2]); + + _leave(""); +} + +/* + * partially encrypt a packet (level 1 security) + */ +static int rxkad_secure_packet_auth(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 data_size, + void *sechdr) +{ + struct rxrpc_skb_priv *sp; + struct blkcipher_desc desc; + 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 */ + u16 check; + + sp = rxrpc_skb(skb); + + _enter(""); + + check = ntohl(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)); + + /* start the encryption afresh */ + memset(&iv, 0, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + memset(sg, 0, sizeof(sg)); + sg_set_buf(&sg[0], &tmpbuf, sizeof(tmpbuf)); + sg_set_buf(&sg[1], &tmpbuf, sizeof(tmpbuf)); + crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf)); + + memcpy(sechdr, &tmpbuf, sizeof(tmpbuf)); + + _leave(" = 0"); + return 0; +} + +/* + * wholly encrypt a packet (level 2 security) + */ +static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 data_size, + void *sechdr) +{ + const struct rxrpc_key_payload *payload; + struct rxkad_level2_hdr rxkhdr + __attribute__((aligned(8))); /* must be all on one page */ + struct rxrpc_skb_priv *sp; + struct blkcipher_desc desc; + struct rxrpc_crypt iv; + struct scatterlist sg[16]; + struct sk_buff *trailer; + unsigned len; + u16 check; + int nsg; + + sp = rxrpc_skb(skb); + + _enter(""); + + check = ntohl(sp->hdr.seq ^ sp->hdr.callNumber); + + rxkhdr.data_size = htonl(data_size | (u32) check << 16); + rxkhdr.checksum = 0; + + /* encrypt from the session key */ + payload = call->conn->key->payload.data; + memcpy(&iv, payload->k.session_key, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + memset(sg, 0, sizeof(sg[0]) * 2); + sg_set_buf(&sg[0], sechdr, sizeof(rxkhdr)); + sg_set_buf(&sg[1], &rxkhdr, sizeof(rxkhdr)); + crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(rxkhdr)); + + /* we want to encrypt the skbuff in-place */ + nsg = skb_cow_data(skb, 0, &trailer); + if (nsg < 0 || nsg > 16) + return -ENOMEM; + + len = data_size + call->conn->size_align - 1; + len &= ~(call->conn->size_align - 1); + + skb_to_sgvec(skb, sg, 0, len); + crypto_blkcipher_encrypt_iv(&desc, sg, sg, len); + + _leave(" = 0"); + return 0; +} + +/* + * checksum an RxRPC packet header + */ +static int rxkad_secure_packet(const struct rxrpc_call *call, + struct sk_buff *skb, + size_t data_size, + void *sechdr) +{ + struct rxrpc_skb_priv *sp; + struct blkcipher_desc desc; + struct rxrpc_crypt iv; + struct scatterlist sg[2]; + struct { + __be32 x[2]; + } tmpbuf __attribute__((aligned(8))); /* must all be in same page */ + __be32 x; + int ret; + + sp = rxrpc_skb(skb); + + _enter("{%d{%x}},{#%u},%zu,", + call->debug_id, key_serial(call->conn->key), ntohl(sp->hdr.seq), + data_size); + + if (!call->conn->cipher) + return 0; + + ret = key_validate(call->conn->key); + if (ret < 0) + return ret; + + /* continue encrypting from where we left off */ + memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + /* calculate the security checksum */ + x = htonl(call->channel << (32 - RXRPC_CIDSHIFT)); + x |= sp->hdr.seq & __constant_cpu_to_be32(0x3fffffff); + tmpbuf.x[0] = sp->hdr.callNumber; + tmpbuf.x[1] = x; + + memset(&sg, 0, sizeof(sg)); + sg_set_buf(&sg[0], &tmpbuf, sizeof(tmpbuf)); + sg_set_buf(&sg[1], &tmpbuf, sizeof(tmpbuf)); + crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf)); + + x = ntohl(tmpbuf.x[1]); + x = (x >> 16) & 0xffff; + if (x == 0) + x = 1; /* zero checksums are not permitted */ + sp->hdr.cksum = htons(x); + + switch (call->conn->security_level) { + case RXRPC_SECURITY_PLAIN: + ret = 0; + break; + case RXRPC_SECURITY_AUTH: + ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr); + break; + case RXRPC_SECURITY_ENCRYPT: + ret = rxkad_secure_packet_encrypt(call, skb, data_size, + sechdr); + break; + default: + ret = -EPERM; + break; + } + + _leave(" = %d [set %hx]", ret, x); + return ret; +} + +/* + * decrypt partial encryption on a packet (level 1 security) + */ +static int rxkad_verify_packet_auth(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 *_abort_code) +{ + struct rxkad_level1_hdr sechdr; + struct rxrpc_skb_priv *sp; + struct blkcipher_desc desc; + struct rxrpc_crypt iv; + struct scatterlist sg[2]; + struct sk_buff *trailer; + u32 data_size, buf; + u16 check; + + _enter(""); + + sp = rxrpc_skb(skb); + + /* we want to decrypt the skbuff in-place */ + if (skb_cow_data(skb, 0, &trailer) < 0) + goto nomem; + + skb_to_sgvec(skb, sg, 0, 8); + + /* start the decryption afresh */ + memset(&iv, 0, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + crypto_blkcipher_decrypt_iv(&desc, sg, sg, 8); + + /* remove the decrypted packet length */ + if (skb_copy_bits(skb, 0, &sechdr, sizeof(sechdr)) < 0) + goto datalen_error; + if (!skb_pull(skb, sizeof(sechdr))) + BUG(); + + buf = ntohl(sechdr.data_size); + data_size = buf & 0xffff; + + check = buf >> 16; + check ^= ntohl(sp->hdr.seq ^ sp->hdr.callNumber); + check &= 0xffff; + if (check != 0) { + *_abort_code = RXKADSEALEDINCON; + goto protocol_error; + } + + /* shorten the packet to remove the padding */ + if (data_size > skb->len) + goto datalen_error; + else if (data_size < skb->len) + skb->len = data_size; + + _leave(" = 0 [dlen=%x]", data_size); + return 0; + +datalen_error: + *_abort_code = RXKADDATALEN; +protocol_error: + _leave(" = -EPROTO"); + return -EPROTO; + +nomem: + _leave(" = -ENOMEM"); + return -ENOMEM; +} + +/* + * wholly decrypt a packet (level 2 security) + */ +static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 *_abort_code) +{ + const struct rxrpc_key_payload *payload; + struct rxkad_level2_hdr sechdr; + struct rxrpc_skb_priv *sp; + struct blkcipher_desc desc; + struct rxrpc_crypt iv; + struct scatterlist _sg[4], *sg; + struct sk_buff *trailer; + u32 data_size, buf; + u16 check; + int nsg; + + _enter(",{%d}", skb->len); + + sp = rxrpc_skb(skb); + + /* we want to decrypt the skbuff in-place */ + nsg = skb_cow_data(skb, 0, &trailer); + if (nsg < 0) + goto nomem; + + sg = _sg; + if (unlikely(nsg > 4)) { + sg = kmalloc(sizeof(*sg) * nsg, GFP_NOIO); + if (!sg) + goto nomem; + } + + skb_to_sgvec(skb, sg, 0, skb->len); + + /* decrypt from the session key */ + payload = call->conn->key->payload.data; + memcpy(&iv, payload->k.session_key, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + crypto_blkcipher_decrypt_iv(&desc, sg, sg, skb->len); + if (sg != _sg) + kfree(sg); + + /* remove the decrypted packet length */ + if (skb_copy_bits(skb, 0, &sechdr, sizeof(sechdr)) < 0) + goto datalen_error; + if (!skb_pull(skb, sizeof(sechdr))) + BUG(); + + buf = ntohl(sechdr.data_size); + data_size = buf & 0xffff; + + check = buf >> 16; + check ^= ntohl(sp->hdr.seq ^ sp->hdr.callNumber); + check &= 0xffff; + if (check != 0) { + *_abort_code = RXKADSEALEDINCON; + goto protocol_error; + } + + /* shorten the packet to remove the padding */ + if (data_size > skb->len) + goto datalen_error; + else if (data_size < skb->len) + skb->len = data_size; + + _leave(" = 0 [dlen=%x]", data_size); + return 0; + +datalen_error: + *_abort_code = RXKADDATALEN; +protocol_error: + _leave(" = -EPROTO"); + return -EPROTO; + +nomem: + _leave(" = -ENOMEM"); + return -ENOMEM; +} + +/* + * verify the security on a received packet + */ +static int rxkad_verify_packet(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 *_abort_code) +{ + struct blkcipher_desc desc; + 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 */ + __be32 x; + __be16 cksum; + int ret; + + sp = rxrpc_skb(skb); + + _enter("{%d{%x}},{#%u}", + call->debug_id, key_serial(call->conn->key), + ntohl(sp->hdr.seq)); + + if (!call->conn->cipher) + return 0; + + if (sp->hdr.securityIndex != 2) { + *_abort_code = RXKADINCONSISTENCY; + _leave(" = -EPROTO [not rxkad]"); + return -EPROTO; + } + + /* continue encrypting from where we left off */ + memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); + desc.tfm = call->conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + /* validate the security checksum */ + x = htonl(call->channel << (32 - RXRPC_CIDSHIFT)); + x |= sp->hdr.seq & __constant_cpu_to_be32(0x3fffffff); + tmpbuf.x[0] = call->call_id; + tmpbuf.x[1] = x; + + memset(&sg, 0, sizeof(sg)); + sg_set_buf(&sg[0], &tmpbuf, sizeof(tmpbuf)); + sg_set_buf(&sg[1], &tmpbuf, sizeof(tmpbuf)); + crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf)); + + x = ntohl(tmpbuf.x[1]); + x = (x >> 16) & 0xffff; + if (x == 0) + x = 1; /* zero checksums are not permitted */ + + cksum = htons(x); + if (sp->hdr.cksum != cksum) { + *_abort_code = RXKADSEALEDINCON; + _leave(" = -EPROTO [csum failed]"); + return -EPROTO; + } + + switch (call->conn->security_level) { + case RXRPC_SECURITY_PLAIN: + ret = 0; + break; + case RXRPC_SECURITY_AUTH: + ret = rxkad_verify_packet_auth(call, skb, _abort_code); + break; + case RXRPC_SECURITY_ENCRYPT: + ret = rxkad_verify_packet_encrypt(call, skb, _abort_code); + break; + default: + ret = -ENOANO; + break; + } + + _leave(" = %d", ret); + return ret; +} + +/* + * issue a challenge + */ +static int rxkad_issue_challenge(struct rxrpc_connection *conn) +{ + struct rxkad_challenge challenge; + struct rxrpc_header hdr; + struct msghdr msg; + struct kvec iov[2]; + size_t len; + int ret; + + _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); + + ret = key_validate(conn->key); + if (ret < 0) + return ret; + + get_random_bytes(&conn->security_nonce, sizeof(conn->security_nonce)); + + challenge.version = htonl(2); + challenge.nonce = htonl(conn->security_nonce); + 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_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr.epoch = conn->epoch; + hdr.cid = conn->cid; + hdr.callNumber = 0; + hdr.seq = 0; + hdr.type = RXRPC_PACKET_TYPE_CHALLENGE; + hdr.flags = conn->out_clientflag; + hdr.userStatus = 0; + hdr.securityIndex = conn->security_ix; + hdr._rsvd = 0; + hdr.serviceId = conn->service_id; + + iov[0].iov_base = &hdr; + iov[0].iov_len = sizeof(hdr); + iov[1].iov_base = &challenge; + iov[1].iov_len = sizeof(challenge); + + len = iov[0].iov_len + iov[1].iov_len; + + hdr.serial = htonl(atomic_inc_return(&conn->serial)); + _proto("Tx CHALLENGE %%%u", ntohl(hdr.serial)); + + ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len); + if (ret < 0) { + _debug("sendmsg failed: %d", ret); + return -EAGAIN; + } + + _leave(" = 0"); + return 0; +} + +/* + * send a Kerberos security response + */ +static int rxkad_send_response(struct rxrpc_connection *conn, + struct rxrpc_header *hdr, + struct rxkad_response *resp, + const struct rxkad_key *s2) +{ + struct msghdr msg; + struct kvec iov[3]; + size_t len; + int ret; + + _enter(""); + + msg.msg_name = &conn->trans->peer->srx.transport.sin; + msg.msg_namelen = sizeof(conn->trans->peer->srx.transport.sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr->epoch = conn->epoch; + hdr->seq = 0; + hdr->type = RXRPC_PACKET_TYPE_RESPONSE; + hdr->flags = conn->out_clientflag; + hdr->userStatus = 0; + hdr->_rsvd = 0; + + iov[0].iov_base = hdr; + iov[0].iov_len = sizeof(*hdr); + iov[1].iov_base = resp; + iov[1].iov_len = sizeof(*resp); + iov[2].iov_base = (void *) s2->ticket; + iov[2].iov_len = s2->ticket_len; + + len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len; + + hdr->serial = htonl(atomic_inc_return(&conn->serial)); + _proto("Tx RESPONSE %%%u", ntohl(hdr->serial)); + + ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 3, len); + if (ret < 0) { + _debug("sendmsg failed: %d", ret); + return -EAGAIN; + } + + _leave(" = 0"); + return 0; +} + +/* + * calculate the response checksum + */ +static void rxkad_calc_response_checksum(struct rxkad_response *response) +{ + u32 csum = 1000003; + int loop; + u8 *p = (u8 *) response; + + for (loop = sizeof(*response); loop > 0; loop--) + csum = csum * 0x10204081 + *p++; + + response->encrypted.checksum = htonl(csum); +} + +/* + * load a scatterlist with a potentially split-page buffer + */ +static void rxkad_sg_set_buf2(struct scatterlist sg[2], + void *buf, size_t buflen) +{ + + memset(sg, 0, sizeof(sg)); + + 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); + } + + ASSERTCMP(sg[0].length + sg[1].length, ==, buflen); +} + +/* + * encrypt the response packet + */ +static void rxkad_encrypt_response(struct rxrpc_connection *conn, + struct rxkad_response *resp, + const struct rxkad_key *s2) +{ + struct blkcipher_desc desc; + struct rxrpc_crypt iv; + struct scatterlist ssg[2], dsg[2]; + + /* continue encrypting from where we left off */ + memcpy(&iv, s2->session_key, sizeof(iv)); + desc.tfm = conn->cipher; + desc.info = iv.x; + desc.flags = 0; + + rxkad_sg_set_buf2(ssg, &resp->encrypted, sizeof(resp->encrypted)); + memcpy(dsg, ssg, sizeof(dsg)); + crypto_blkcipher_encrypt_iv(&desc, dsg, ssg, sizeof(resp->encrypted)); +} + +/* + * respond to a challenge packet + */ +static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, + struct sk_buff *skb, + u32 *_abort_code) +{ + const struct rxrpc_key_payload *payload; + struct rxkad_challenge challenge; + struct rxkad_response resp + __attribute__((aligned(8))); /* must be aligned for crypto */ + struct rxrpc_skb_priv *sp; + u32 version, nonce, min_level, abort_code; + int ret; + + _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); + + if (!conn->key) { + _leave(" = -EPROTO [no key]"); + return -EPROTO; + } + + ret = key_validate(conn->key); + if (ret < 0) { + *_abort_code = RXKADEXPIRED; + return ret; + } + + abort_code = RXKADPACKETSHORT; + sp = rxrpc_skb(skb); + if (skb_copy_bits(skb, 0, &challenge, sizeof(challenge)) < 0) + goto protocol_error; + + version = ntohl(challenge.version); + nonce = ntohl(challenge.nonce); + min_level = ntohl(challenge.min_level); + + _proto("Rx CHALLENGE %%%u { v=%u n=%u ml=%u }", + ntohl(sp->hdr.serial), version, nonce, min_level); + + abort_code = RXKADINCONSISTENCY; + if (version != RXKAD_VERSION) + goto protocol_error; + + abort_code = RXKADLEVELFAIL; + if (conn->security_level < min_level) + goto protocol_error; + + payload = conn->key->payload.data; + + /* build the response packet */ + memset(&resp, 0, sizeof(resp)); + + resp.version = RXKAD_VERSION; + resp.encrypted.epoch = conn->epoch; + resp.encrypted.cid = conn->cid; + resp.encrypted.securityIndex = htonl(conn->security_ix); + resp.encrypted.call_id[0] = + (conn->channels[0] ? conn->channels[0]->call_id : 0); + resp.encrypted.call_id[1] = + (conn->channels[1] ? conn->channels[1]->call_id : 0); + resp.encrypted.call_id[2] = + (conn->channels[2] ? conn->channels[2]->call_id : 0); + resp.encrypted.call_id[3] = + (conn->channels[3] ? conn->channels[3]->call_id : 0); + resp.encrypted.inc_nonce = htonl(nonce + 1); + resp.encrypted.level = htonl(conn->security_level); + resp.kvno = htonl(payload->k.kvno); + resp.ticket_len = htonl(payload->k.ticket_len); + + /* calculate the response checksum and then do the encryption */ + rxkad_calc_response_checksum(&resp); + rxkad_encrypt_response(conn, &resp, &payload->k); + return rxkad_send_response(conn, &sp->hdr, &resp, &payload->k); + +protocol_error: + *_abort_code = abort_code; + _leave(" = -EPROTO [%d]", abort_code); + return -EPROTO; +} + +/* + * decrypt the kerberos IV ticket in the response + */ +static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, + void *ticket, size_t ticket_len, + struct rxrpc_crypt *_session_key, + time_t *_expiry, + u32 *_abort_code) +{ + struct blkcipher_desc desc; + struct rxrpc_crypt iv, key; + struct scatterlist ssg[1], dsg[1]; + struct in_addr addr; + unsigned life; + time_t issue, now; + bool little_endian; + int ret; + u8 *p, *q, *name, *end; + + _enter("{%d},{%x}", conn->debug_id, key_serial(conn->server_key)); + + *_expiry = 0; + + ret = key_validate(conn->server_key); + if (ret < 0) { + switch (ret) { + case -EKEYEXPIRED: + *_abort_code = RXKADEXPIRED; + goto error; + default: + *_abort_code = RXKADNOAUTH; + goto error; + } + } + + ASSERT(conn->server_key->payload.data != NULL); + ASSERTCMP((unsigned long) ticket & 7UL, ==, 0); + + memcpy(&iv, &conn->server_key->type_data, sizeof(iv)); + + desc.tfm = conn->server_key->payload.data; + desc.info = iv.x; + desc.flags = 0; + + sg_init_one(&ssg[0], ticket, ticket_len); + memcpy(dsg, ssg, sizeof(dsg)); + crypto_blkcipher_decrypt_iv(&desc, dsg, ssg, ticket_len); + + p = ticket; + end = p + ticket_len; + +#define Z(size) \ + ({ \ + u8 *__str = p; \ + q = memchr(p, 0, end - p); \ + if (!q || q - p > (size)) \ + goto bad_ticket; \ + for (; p < q; p++) \ + if (!isprint(*p)) \ + goto bad_ticket; \ + p++; \ + __str; \ + }) + + /* extract the ticket flags */ + _debug("KIV FLAGS: %x", *p); + little_endian = *p & 1; + p++; + + /* extract the authentication name */ + name = Z(ANAME_SZ); + _debug("KIV ANAME: %s", name); + + /* extract the principal's instance */ + name = Z(INST_SZ); + _debug("KIV INST : %s", name); + + /* extract the principal's authentication domain */ + name = Z(REALM_SZ); + _debug("KIV REALM: %s", name); + + if (end - p < 4 + 8 + 4 + 2) + goto bad_ticket; + + /* get the IPv4 address of the entity that requested the ticket */ + memcpy(&addr, p, sizeof(addr)); + p += 4; + _debug("KIV ADDR : "NIPQUAD_FMT, NIPQUAD(addr)); + + /* get the session key from the ticket */ + memcpy(&key, p, sizeof(key)); + p += 8; + _debug("KIV KEY : %08x %08x", ntohl(key.n[0]), ntohl(key.n[1])); + memcpy(_session_key, &key, sizeof(key)); + + /* get the ticket's lifetime */ + life = *p++ * 5 * 60; + _debug("KIV LIFE : %u", life); + + /* get the issue time of the ticket */ + if (little_endian) { + __le32 stamp; + memcpy(&stamp, p, 4); + issue = le32_to_cpu(stamp); + } else { + __be32 stamp; + memcpy(&stamp, p, 4); + issue = be32_to_cpu(stamp); + } + p += 4; + now = xtime.tv_sec; + _debug("KIV ISSUE: %lx [%lx]", issue, now); + + /* check the ticket is in date */ + if (issue > now) { + *_abort_code = RXKADNOAUTH; + ret = -EKEYREJECTED; + goto error; + } + + if (issue < now - life) { + *_abort_code = RXKADEXPIRED; + ret = -EKEYEXPIRED; + goto error; + } + + *_expiry = issue + life; + + /* get the service name */ + name = Z(SNAME_SZ); + _debug("KIV SNAME: %s", name); + + /* get the service instance name */ + name = Z(INST_SZ); + _debug("KIV SINST: %s", name); + + ret = 0; +error: + _leave(" = %d", ret); + return ret; + +bad_ticket: + *_abort_code = RXKADBADTICKET; + ret = -EBADMSG; + goto error; +} + +/* + * decrypt the response packet + */ +static void rxkad_decrypt_response(struct rxrpc_connection *conn, + struct rxkad_response *resp, + const struct rxrpc_crypt *session_key) +{ + struct blkcipher_desc desc; + struct scatterlist ssg[2], dsg[2]; + struct rxrpc_crypt iv; + + _enter(",,%08x%08x", + ntohl(session_key->n[0]), ntohl(session_key->n[1])); + + ASSERT(rxkad_ci != NULL); + + mutex_lock(&rxkad_ci_mutex); + if (crypto_blkcipher_setkey(rxkad_ci, session_key->x, + sizeof(*session_key)) < 0) + BUG(); + + memcpy(&iv, session_key, sizeof(iv)); + desc.tfm = rxkad_ci; + desc.info = iv.x; + desc.flags = 0; + + rxkad_sg_set_buf2(ssg, &resp->encrypted, sizeof(resp->encrypted)); + memcpy(dsg, ssg, sizeof(dsg)); + crypto_blkcipher_decrypt_iv(&desc, dsg, ssg, sizeof(resp->encrypted)); + mutex_unlock(&rxkad_ci_mutex); + + _leave(""); +} + +/* + * verify a response + */ +static int rxkad_verify_response(struct rxrpc_connection *conn, + struct sk_buff *skb, + u32 *_abort_code) +{ + struct rxkad_response response + __attribute__((aligned(8))); /* must be aligned for crypto */ + struct rxrpc_skb_priv *sp; + struct rxrpc_crypt session_key; + time_t expiry; + void *ticket; + u32 abort_code, version, kvno, ticket_len, csum, level; + int ret; + + _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); + + abort_code = RXKADPACKETSHORT; + if (skb_copy_bits(skb, 0, &response, sizeof(response)) < 0) + goto protocol_error; + if (!pskb_pull(skb, sizeof(response))) + BUG(); + + version = ntohl(response.version); + ticket_len = ntohl(response.ticket_len); + kvno = ntohl(response.kvno); + sp = rxrpc_skb(skb); + _proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }", + ntohl(sp->hdr.serial), version, kvno, ticket_len); + + abort_code = RXKADINCONSISTENCY; + if (version != RXKAD_VERSION) + + abort_code = RXKADTICKETLEN; + if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) + goto protocol_error; + + abort_code = RXKADUNKNOWNKEY; + if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) + goto protocol_error; + + /* extract the kerberos ticket and decrypt and decode it */ + ticket = kmalloc(ticket_len, GFP_NOFS); + if (!ticket) + return -ENOMEM; + + abort_code = RXKADPACKETSHORT; + if (skb_copy_bits(skb, 0, ticket, ticket_len) < 0) + goto protocol_error_free; + + ret = rxkad_decrypt_ticket(conn, ticket, ticket_len, &session_key, + &expiry, &abort_code); + if (ret < 0) { + *_abort_code = abort_code; + kfree(ticket); + return ret; + } + + /* use the session key from inside the ticket to decrypt the + * response */ + rxkad_decrypt_response(conn, &response, &session_key); + + abort_code = RXKADSEALEDINCON; + if (response.encrypted.epoch != conn->epoch) + goto protocol_error_free; + if (response.encrypted.cid != conn->cid) + goto protocol_error_free; + if (ntohl(response.encrypted.securityIndex) != conn->security_ix) + goto protocol_error_free; + csum = response.encrypted.checksum; + response.encrypted.checksum = 0; + rxkad_calc_response_checksum(&response); + 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; + + abort_code = RXKADOUTOFSEQUENCE; + if (response.encrypted.inc_nonce != htonl(conn->security_nonce + 1)) + goto protocol_error_free; + + abort_code = RXKADLEVELFAIL; + level = ntohl(response.encrypted.level); + if (level > RXRPC_SECURITY_ENCRYPT) + goto protocol_error_free; + conn->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 + * as for a client connection */ + ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno); + if (ret < 0) { + kfree(ticket); + return ret; + } + + kfree(ticket); + _leave(" = 0"); + return 0; + +protocol_error_free: + kfree(ticket); +protocol_error: + *_abort_code = abort_code; + _leave(" = -EPROTO [%d]", abort_code); + return -EPROTO; +} + +/* + * clear the connection security + */ +static void rxkad_clear(struct rxrpc_connection *conn) +{ + _enter(""); + + if (conn->cipher) + crypto_free_blkcipher(conn->cipher); +} + +/* + * RxRPC Kerberos-based security + */ +static struct rxrpc_security rxkad = { + .owner = THIS_MODULE, + .name = "rxkad", + .security_index = RXKAD_VERSION, + .init_connection_security = rxkad_init_connection_security, + .prime_packet_security = rxkad_prime_packet_security, + .secure_packet = rxkad_secure_packet, + .verify_packet = rxkad_verify_packet, + .issue_challenge = rxkad_issue_challenge, + .respond_to_challenge = rxkad_respond_to_challenge, + .verify_response = rxkad_verify_response, + .clear = rxkad_clear, +}; + +static __init int rxkad_init(void) +{ + _enter(""); + + /* pin the cipher we need so that the crypto layer doesn't invoke + * keventd to go get it */ + rxkad_ci = crypto_alloc_blkcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(rxkad_ci)) + return PTR_ERR(rxkad_ci); + + return rxrpc_register_security(&rxkad); +} + +module_init(rxkad_init); + +static __exit void rxkad_exit(void) +{ + _enter(""); + + rxrpc_unregister_security(&rxkad); + crypto_free_blkcipher(rxkad_ci); +} + +module_exit(rxkad_exit); |