OpenCloudOS-Kernel/net/rxrpc/ar-internal.h

941 lines
31 KiB
C
Raw Normal View History

/* 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 <linux/atomic.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#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
#define FCRYPT_BSIZE 8
struct rxrpc_crypt {
union {
u8 x[FCRYPT_BSIZE];
__be32 n[2];
};
} __attribute__((aligned(8)));
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 06:50:17 +08:00
#define rxrpc_queue_work(WS) queue_work(rxrpc_workqueue, (WS))
#define rxrpc_queue_delayed_work(WS,D) \
queue_delayed_work(rxrpc_workqueue, (WS), (D))
#define rxrpc_queue_call(CALL) rxrpc_queue_work(&(CALL)->processor)
#define rxrpc_queue_conn(CONN) rxrpc_queue_work(&(CONN)->processor)
/*
* sk_state for RxRPC sockets
*/
enum {
RXRPC_UNBOUND = 0,
RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */
RXRPC_CLIENT_BOUND, /* client local address bound */
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;
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 06:50:17 +08:00
rxrpc_interceptor_t interceptor; /* kernel service Rx interceptor function */
struct rxrpc_local *local; /* local endpoint */
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_CONNECTED 0 /* connect_srx is set */
#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 */
struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */
sa_family_t family; /* protocol family created with */
};
#define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk)
/*
* CPU-byteorder normalised Rx packet header.
*/
struct rxrpc_host_header {
u32 epoch; /* client boot timestamp */
u32 cid; /* connection and channel ID */
u32 callNumber; /* call ID (0 for connection-level packets) */
u32 seq; /* sequence number of pkt in call stream */
u32 serial; /* serial number of pkt sent to network */
u8 type; /* packet type */
u8 flags; /* packet flags */
u8 userStatus; /* app-layer defined status */
u8 securityIndex; /* security protocol ID */
union {
u16 _rsvd; /* reserved */
u16 cksum; /* kerberos security checksum */
};
u16 serviceId; /* service ID */
} __packed;
/*
* 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 int 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_host_header hdr; /* RxRPC packet header from this packet */
};
#define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb)
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 {
const char *name; /* name of this service */
u8 security_index; /* security type provided */
/* Initialise a security service */
int (*init)(void);
/* Clean up a security service */
void (*exit)(void);
/* 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: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
* RxRPC local transport endpoint description
* - owned by a single AF_RXRPC socket
* - pointed to by transport socket struct sk_user_data
*/
struct rxrpc_local {
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
struct rcu_head rcu;
atomic_t usage;
struct list_head link;
struct socket *socket; /* my UDP socket */
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
struct work_struct processor;
struct list_head services; /* services listening on this endpoint */
struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */
struct sk_buff_head accept_queue; /* incoming calls awaiting acceptance */
struct sk_buff_head reject_queue; /* packets awaiting rejection */
struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
struct mutex conn_lock; /* Client connection creation lock */
spinlock_t lock; /* access lock */
rwlock_t services_lock; /* lock for services list */
int debug_id; /* debug ID for printks */
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
bool dead;
struct sockaddr_rxrpc srx; /* local address */
};
/*
* RxRPC remote transport endpoint definition
* - matched by local endpoint, remote port, address and protocol type
*/
struct rxrpc_peer {
struct rcu_head rcu; /* This must be first */
atomic_t usage;
unsigned long hash_key;
struct hlist_node hash_link;
struct rxrpc_local *local;
struct hlist_head error_targets; /* targets for net error distribution */
struct work_struct error_distributor;
spinlock_t lock; /* access lock */
unsigned int if_mtu; /* interface MTU for this peer */
unsigned int mtu; /* network MTU for this peer */
unsigned int maxdata; /* data size (MTU - hdrsize) */
unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */
int debug_id; /* debug ID for printks */
int error_report; /* Net (+0) or local (+1000000) to distribute */
#define RXRPC_LOCAL_ERROR_OFFSET 1000000
struct sockaddr_rxrpc srx; /* remote address */
/* calculated RTT cache */
#define RXRPC_RTT_CACHE_SIZE 32
suseconds_t rtt; /* current RTT estimate (in uS) */
unsigned int rtt_point; /* next entry at which to insert */
unsigned int 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 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 */
unsigned long put_time; /* time at which to reap */
spinlock_t client_lock; /* client connection allocation lock */
rwlock_t conn_lock; /* lock for active/dead connections */
atomic_t usage;
int debug_id; /* debug ID for printks */
unsigned int conn_idcounter; /* connection ID counter (client) */
};
/*
* 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 */
u16 service_id; /* Service ID for this bundle */
u8 security_ix; /* security type */
};
/*
* Keys for matching a connection.
*/
struct rxrpc_conn_proto {
unsigned long hash_key;
struct rxrpc_local *local; /* Representation of local endpoint */
u32 epoch; /* epoch of this connection */
u32 cid; /* connection ID */
u8 in_clientflag; /* RXRPC_CLIENT_INITIATED if we are server */
u8 addr_size; /* Size of the address */
sa_family_t family; /* Transport protocol */
__be16 port; /* Peer UDP/UDP6 port */
union { /* Peer address */
struct in_addr ipv4_addr;
struct in6_addr ipv6_addr;
u32 raw_addr[0];
};
};
struct rxrpc_conn_parameters {
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
bool exclusive; /* T if conn is exclusive */
u16 service_id; /* Service ID for this connection */
u32 security_level; /* Security level selected */
};
/*
* RxRPC 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 rxrpc_conn_proto proto;
struct rxrpc_conn_parameters params;
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) */
const struct rxrpc_security *security; /* applied security module */
struct key *server_key; /* security for this service */
struct crypto_skcipher *cipher; /* encryption handle */
struct rxrpc_crypt csum_iv; /* packet checksum base */
unsigned long events;
#define RXRPC_CONN_CHALLENGE 0 /* send challenge packet */
unsigned long put_time; /* time at which to reap */
rwlock_t lock; /* access lock */
spinlock_t state_lock; /* state-change lock */
atomic_t usage;
enum { /* current state of connection */
RXRPC_CONN_UNUSED, /* - connection not yet attempted */
RXRPC_CONN_CLIENT, /* - client connection */
RXRPC_CONN_SERVER_UNSECURED, /* - server unsecured connection */
RXRPC_CONN_SERVER_CHALLENGING, /* - server challenging for security */
RXRPC_CONN_SERVER, /* - server secured connection */
RXRPC_CONN_REMOTELY_ABORTED, /* - conn aborted by peer */
RXRPC_CONN_LOCALLY_ABORTED, /* - conn aborted locally */
RXRPC_CONN_NETWORK_ERROR, /* - conn terminated by network error */
} state;
u32 local_abort; /* local abort code */
u32 remote_abort; /* remote abort code */
int error; /* local error incurred */
int debug_id; /* debug ID for printks */
unsigned int call_counter; /* call ID counter */
atomic_t serial; /* packet serial number counter */
atomic_t hi_serial; /* highest serial number received */
u8 avail_calls; /* number of calls available */
u8 size_align; /* data size alignment (for security) */
u8 header_size; /* rxrpc + security header size */
u8 security_size; /* security header size */
u32 security_nonce; /* response re-use preventer */
u8 security_ix; /* security type */
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
};
/*
* Flags in call->flags.
*/
enum rxrpc_call_flag {
RXRPC_CALL_RELEASED, /* call has been released - no more message to userspace */
RXRPC_CALL_TERMINAL_MSG, /* call has given the socket its final message */
RXRPC_CALL_RCVD_LAST, /* all packets received */
RXRPC_CALL_RUN_RTIMER, /* Tx resend timer started */
RXRPC_CALL_TX_SOFT_ACK, /* sent some soft ACKs */
RXRPC_CALL_PROC_BUSY, /* the processor is busy */
RXRPC_CALL_INIT_ACCEPT, /* acceptance was initiated */
RXRPC_CALL_HAS_USERID, /* has a user ID attached */
RXRPC_CALL_EXPECT_OOS, /* expect out of sequence packets */
};
/*
* Events that can be raised on a call.
*/
enum rxrpc_call_event {
RXRPC_CALL_EV_RCVD_ACKALL, /* ACKALL or reply received */
RXRPC_CALL_EV_RCVD_BUSY, /* busy packet received */
RXRPC_CALL_EV_RCVD_ABORT, /* abort packet received */
RXRPC_CALL_EV_RCVD_ERROR, /* network error received */
RXRPC_CALL_EV_ACK_FINAL, /* need to generate final ACK (and release call) */
RXRPC_CALL_EV_ACK, /* need to generate ACK */
RXRPC_CALL_EV_REJECT_BUSY, /* need to generate busy message */
RXRPC_CALL_EV_ABORT, /* need to generate abort */
RXRPC_CALL_EV_CONN_ABORT, /* local connection abort generated */
RXRPC_CALL_EV_RESEND_TIMER, /* Tx resend timer expired */
RXRPC_CALL_EV_RESEND, /* Tx resend required */
RXRPC_CALL_EV_DRAIN_RX_OOS, /* drain the Rx out of sequence queue */
RXRPC_CALL_EV_LIFE_TIMER, /* call's lifetimer ran out */
RXRPC_CALL_EV_ACCEPTED, /* incoming call accepted by userspace app */
RXRPC_CALL_EV_SECURED, /* incoming call's connection is now secure */
RXRPC_CALL_EV_POST_ACCEPT, /* need to post an "accept?" message to the app */
RXRPC_CALL_EV_RELEASE, /* need to release the call's resources */
};
/*
* The states that a call can be in.
*/
enum rxrpc_call_state {
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 */
NR__RXRPC_CALL_STATES
};
/*
* 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 hlist_node error_link; /* link in error distribution list */
struct list_head accept_link; /* calls awaiting acceptance */
struct rb_node sock_node; /* node in socket call tree */
struct rb_node conn_node; /* node in connection call tree */
struct sk_buff_head rx_queue; /* received packets */
struct sk_buff_head rx_oos_queue; /* packets received out of sequence */
struct sk_buff *tx_pending; /* Tx socket buffer being filled */
wait_queue_head_t tx_waitq; /* wait for Tx window space to become available */
unsigned long user_call_ID; /* user-defined call ID */
unsigned long creation_jif; /* time of call creation */
unsigned long flags;
unsigned long events;
spinlock_t lock;
rwlock_t state_lock; /* lock for state transition */
atomic_t usage;
atomic_t sequence; /* Tx data packet sequence counter */
u32 local_abort; /* local abort code */
u32 remote_abort; /* remote abort code */
int error_report; /* Network error (ICMP/local transport) */
int error; /* Local error incurred */
enum rxrpc_call_state state : 8; /* current state of call */
int debug_id; /* debug ID for printks */
u8 channel; /* connection channel occupied by this call */
/* transmission-phase ACK management */
u8 acks_head; /* offset into window of first entry */
u8 acks_tail; /* offset into window of last entry */
u8 acks_winsz; /* size of un-ACK'd window */
u8 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_t ackr_prev_seq; /* previous sequence number received */
u8 ackr_reason; /* reason to ACK */
rxrpc_serial_t 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];
struct hlist_node hash_node;
unsigned long hash_key; /* Full hash key */
u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */
struct rxrpc_local *local; /* Local endpoint. Used for hashing. */
sa_family_t family; /* Frame protocol */
u32 call_id; /* call ID on connection */
u32 cid; /* connection ID plus channel index */
u32 epoch; /* epoch of this connection */
u16 service_id; /* service ID */
union { /* Peer IP address for hashing */
__be32 ipv4_addr;
__u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */
} peer_ip;
};
/*
* 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->local_abort = abort_code;
call->state = RXRPC_CALL_LOCALLY_ABORTED;
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
}
write_unlock_bh(&call->state_lock);
}
/*
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 06:50:17 +08:00
* af_rxrpc.c
*/
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 06:50:17 +08:00
extern atomic_t rxrpc_n_skbs;
extern u32 rxrpc_epoch;
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 06:50:17 +08:00
extern atomic_t rxrpc_debug_id;
extern struct workqueue_struct *rxrpc_workqueue;
extern struct rxrpc_transport *rxrpc_name_to_transport(struct rxrpc_conn_parameters *,
struct sockaddr *,
int, gfp_t);
/*
* call_accept.c
*/
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
int rxrpc_reject_call(struct rxrpc_sock *);
/*
* call_event.c
*/
void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
void rxrpc_process_call(struct work_struct *);
/*
* call_object.c
*/
extern unsigned int rxrpc_max_call_lifetime;
extern unsigned int rxrpc_dead_call_expiry;
extern struct kmem_cache *rxrpc_call_jar;
extern struct list_head rxrpc_calls;
extern rwlock_t rxrpc_call_lock;
struct rxrpc_call *rxrpc_find_call_hash(struct rxrpc_host_header *,
void *, sa_family_t, const void *);
struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
struct rxrpc_conn_parameters *,
struct rxrpc_transport *,
struct rxrpc_conn_bundle *,
unsigned long, gfp_t);
struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *,
struct rxrpc_connection *,
struct rxrpc_host_header *);
void rxrpc_release_call(struct rxrpc_call *);
void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
void __rxrpc_put_call(struct rxrpc_call *);
void __exit rxrpc_destroy_all_calls(void);
/*
* conn_event.c
*/
void rxrpc_process_connection(struct work_struct *);
void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *);
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
void rxrpc_reject_packets(struct rxrpc_local *);
/*
* conn_object.c
*/
extern unsigned int rxrpc_connection_expiry;
extern struct list_head rxrpc_connections;
extern rwlock_t rxrpc_connection_lock;
struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *,
struct rxrpc_transport *,
struct key *, u16, gfp_t);
void rxrpc_put_bundle(struct rxrpc_transport *, struct rxrpc_conn_bundle *);
int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *,
struct rxrpc_transport *, struct rxrpc_conn_bundle *,
struct rxrpc_call *, gfp_t);
void rxrpc_put_connection(struct rxrpc_connection *);
void __exit rxrpc_destroy_all_connections(void);
struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *,
struct rxrpc_host_header *);
extern struct rxrpc_connection *
rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *);
static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn)
{
return conn->out_clientflag;
}
static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn)
{
return conn->proto.in_clientflag;
}
/*
* input.c
*/
void rxrpc_data_ready(struct sock *);
int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
/*
* insecure.c
*/
extern const struct rxrpc_security rxrpc_no_security;
/*
* key.c
*/
extern struct key_type key_type_rxrpc;
extern struct key_type key_type_rxrpc_s;
int rxrpc_request_key(struct rxrpc_sock *, char __user *, int);
int rxrpc_server_keyring(struct rxrpc_sock *, char __user *, int);
int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
u32);
/*
* local_event.c
*/
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
extern void rxrpc_process_local_events(struct rxrpc_local *);
/*
* local_object.c
*/
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *);
void __rxrpc_put_local(struct rxrpc_local *);
void __exit rxrpc_destroy_all_locals(void);
rxrpc: Rework local endpoint management Rework the local RxRPC endpoint management. Local endpoint objects are maintained in a flat list as before. This should be okay as there shouldn't be more than one per open AF_RXRPC socket (there can be fewer as local endpoints can be shared if their local service ID is 0 and they share the same local transport parameters). Changes: (1) Local endpoints may now only be shared if they have local service ID 0 (ie. they're not being used for listening). This prevents a scenario where process A is listening of the Cache Manager port and process B contacts a fileserver - which may then attempt to send CM requests back to B. But if A and B are sharing a local endpoint, A will get the CM requests meant for B. (2) We use a mutex to handle lookups and don't provide RCU-only lookups since we only expect to access the list when opening a socket or destroying an endpoint. The local endpoint object is pointed to by the transport socket's sk_user_data for the life of the transport socket - allowing us to refer to it directly from the sk_data_ready and sk_error_report callbacks. (3) atomic_inc_not_zero() now exists and can be used to only share a local endpoint if the last reference hasn't yet gone. (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with BH processing disabled given that we assume sk_user_data won't change under us. (5) The transport socket is shut down before we clear the sk_user_data pointer so that we can be sure that the transport socket's callbacks won't be invoked once the RCU destruction is scheduled. (6) Local endpoints have a work item that handles both destruction and event processing. The means that destruction doesn't then need to wait for event processing. The event queues can then be cleared after the transport socket is shut down. (7) Local endpoints are no longer available for resurrection beyond the life of the sockets that had them open. As soon as their last ref goes, they are scheduled for destruction and may not have their usage count moved from 0. Signed-off-by: David Howells <dhowells@redhat.com>
2016-04-04 21:00:35 +08:00
static inline void rxrpc_get_local(struct rxrpc_local *local)
{
atomic_inc(&local->usage);
}
static inline
struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
{
return atomic_inc_not_zero(&local->usage) ? local : NULL;
}
static inline void rxrpc_put_local(struct rxrpc_local *local)
{
if (atomic_dec_and_test(&local->usage))
__rxrpc_put_local(local);
}
/*
* misc.c
*/
extern unsigned int rxrpc_max_backlog __read_mostly;
extern unsigned int rxrpc_requested_ack_delay;
extern unsigned int rxrpc_soft_ack_delay;
extern unsigned int rxrpc_idle_ack_delay;
extern unsigned int rxrpc_rx_window_size;
extern unsigned int rxrpc_rx_mtu;
extern unsigned int rxrpc_rx_jumbo_max;
extern const char *const rxrpc_pkts[];
extern const s8 rxrpc_ack_priority[];
extern const char *rxrpc_acks(u8 reason);
/*
* output.c
*/
extern unsigned int rxrpc_resend_timeout;
int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
void rxrpc_peer_error_distributor(struct work_struct *);
/*
* peer_object.c
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
struct sockaddr_rxrpc *, gfp_t);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
static inline void rxrpc_get_peer(struct rxrpc_peer *peer)
{
atomic_inc(&peer->usage);
}
static inline
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
{
return atomic_inc_not_zero(&peer->usage) ? peer : NULL;
}
extern void __rxrpc_put_peer(struct rxrpc_peer *peer);
static inline void rxrpc_put_peer(struct rxrpc_peer *peer)
{
if (atomic_dec_and_test(&peer->usage))
__rxrpc_put_peer(peer);
}
/*
* proc.c
*/
extern const char *const rxrpc_call_states[];
extern const struct file_operations rxrpc_call_seq_fops;
extern const struct file_operations rxrpc_connection_seq_fops;
/*
* recvmsg.c
*/
void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
* rxkad.c
*/
#ifdef CONFIG_RXKAD
extern const struct rxrpc_security rxkad;
#endif
/*
* security.c
*/
int __init rxrpc_init_security(void);
void rxrpc_exit_security(void);
int rxrpc_init_client_conn_security(struct rxrpc_connection *);
int rxrpc_init_server_conn_security(struct rxrpc_connection *);
/*
* skbuff.c
*/
void rxrpc_packet_destructor(struct sk_buff *);
/*
* sysctl.c
*/
#ifdef CONFIG_SYSCTL
extern int __init rxrpc_sysctl_init(void);
extern void rxrpc_sysctl_exit(void);
#else
static inline int __init rxrpc_sysctl_init(void) { return 0; }
static inline void rxrpc_sysctl_exit(void) {}
#endif
/*
* transport.c
*/
extern unsigned int rxrpc_transport_expiry;
struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
struct rxrpc_peer *, gfp_t);
void rxrpc_put_transport(struct rxrpc_transport *);
void __exit rxrpc_destroy_all_transports(void);
struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
struct rxrpc_peer *);
/*
* utils.c
*/
void rxrpc_get_addr_from_skb(struct rxrpc_local *, const struct sk_buff *,
struct sockaddr_rxrpc *);
/*
* debug tracing
*/
extern unsigned int rxrpc_debug;
#define dbgprintk(FMT,...) \
printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__)
#define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
#define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__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,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
#define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
#define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__)
#define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__)
#define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__)
#endif
/*
* debug assertion checking
*/
#if 1 // defined(__KDEBUGALL)
#define ASSERT(X) \
do { \
if (unlikely(!(X))) { \
pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
#define ASSERTCMP(X, OP, Y) \
do { \
unsigned long _x = (unsigned long)(X); \
unsigned long _y = (unsigned long)(Y); \
if (unlikely(!(_x OP _y))) { \
pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \
_x, _x, #OP, _y, _y); \
BUG(); \
} \
} while (0)
#define ASSERTIF(C, X) \
do { \
if (unlikely((C) && !(X))) { \
pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
#define ASSERTIFCMP(C, X, OP, Y) \
do { \
unsigned long _x = (unsigned long)(X); \
unsigned long _y = (unsigned long)(Y); \
if (unlikely((C) && !(_x OP _y))) { \
pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \
_x, _x, #OP, _y, _y); \
BUG(); \
} \
} while (0)
#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);
}
#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)