linux_dsm_epyc7002/net/rxrpc/ar-internal.h

1043 lines
32 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 <linux/seqlock.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 05:50:17 +07:00
#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)
struct rxrpc_connection;
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
/*
* Mark applied to socket buffers.
*/
enum rxrpc_skb_mark {
RXRPC_SKB_MARK_DATA, /* data message */
RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */
RXRPC_SKB_MARK_BUSY, /* server busy message */
RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */
RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */
RXRPC_SKB_MARK_NET_ERROR, /* network error message */
RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */
RXRPC_SKB_MARK_NEW_CALL, /* local error message */
};
/*
* 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;
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
rxrpc_notify_new_call_t notify_new_call; /* Func to notify of new call */
struct rxrpc_local *local; /* local endpoint */
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 */
rwlock_t call_lock; /* lock for calls */
u32 min_sec_level; /* minimum security level */
#define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT
bool exclusive; /* Exclusive connection for a client socket */
sa_family_t family; /* Protocol family created with */
struct sockaddr_rxrpc srx; /* local address */
struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */
};
#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)
/*
* 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 */
int (*prime_packet_security)(struct rxrpc_connection *);
/* impose security on a packet */
int (*secure_packet)(struct rxrpc_call *,
struct sk_buff *,
size_t,
void *);
/* verify the security on a received packet */
int (*verify_packet)(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 20:00:35 +07:00
* 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 20:00:35 +07:00
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 20:00:35 +07:00
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 */
struct rb_root client_conns; /* Client connections by socket params */
spinlock_t client_conns_lock; /* Lock for client_conns */
spinlock_t lock; /* access lock */
rwlock_t services_lock; /* lock for services list */
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 20:00:35 +07:00
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;
struct rb_root service_conns; /* Service connections */
seqlock_t service_conn_lock;
spinlock_t lock; /* access lock */
unsigned int if_mtu; /* interface MTU for this peer */
unsigned int mtu; /* network MTU for this peer */
unsigned int maxdata; /* data size (MTU - hdrsize) */
unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */
int debug_id; /* debug ID for printks */
int 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 */
};
/*
* Keys for matching a connection.
*/
struct rxrpc_conn_proto {
union {
struct {
u32 epoch; /* epoch of this connection */
u32 cid; /* connection ID */
};
u64 index_key;
};
};
struct rxrpc_conn_parameters {
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
bool exclusive; /* T if conn is exclusive */
u16 service_id; /* Service ID for this connection */
u32 security_level; /* Security level selected */
};
/*
* Bits in the connection flags.
*/
enum rxrpc_conn_flag {
RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */
rxrpc: Maintain an extra ref on a conn for the cache list Overhaul the usage count accounting for the rxrpc_connection struct to make it easier to implement RCU access from the data_ready handler. The problem is that currently we're using a lock to prevent the garbage collector from trying to clean up a connection that we're contemplating unidling. We could just stick incoming packets on the connection we find, but we've then got a problem that we may race when dispatching a work item to process it as we need to give that a ref to prevent the rxrpc_connection struct from disappearing in the meantime. Further, incoming packets may get discarded if attached to an rxrpc_connection struct that is going away. Whilst this is not a total disaster - the client will presumably resend - it would delay processing of the call. This would affect the AFS client filesystem's service manager operation. To this end: (1) We now maintain an extra count on the connection usage count whilst it is on the connection list. This mean it is not in use when its refcount is 1. (2) When trying to reuse an old connection, we only increment the refcount if it is greater than 0. If it is 0, we replace it in the tree with a new candidate connection. (3) Two connection flags are added to indicate whether or not a connection is in the local's client connection tree (used by sendmsg) or the peer's service connection tree (used by data_ready). This makes sure that we don't try and remove a connection if it got replaced. The flags are tested under lock with the removal operation to prevent the reaper from killing the rxrpc_connection struct whilst someone else is trying to effect a replacement. This could probably be alleviated by using memory barriers between the flag set/test and the rb_tree ops. The rb_tree op would still need to be under the lock, however. (4) When trying to reap an old connection, we try to flip the usage count from 1 to 0. If it's not 1 at that point, then it must've come back to life temporarily and we ignore it. Signed-off-by: David Howells <dhowells@redhat.com>
2016-06-30 16:45:22 +07:00
RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */
RXRPC_CONN_IN_CLIENT_CONNS, /* Conn is in local->client_conns */
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
RXRPC_CONN_EXPOSED, /* Conn has extra ref for exposure */
RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */
RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */
};
/*
* Events that can be raised upon a connection.
*/
enum rxrpc_conn_event {
RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */
};
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
/*
* The connection cache state.
*/
enum rxrpc_conn_cache_state {
RXRPC_CONN_CLIENT_INACTIVE, /* Conn is not yet listed */
RXRPC_CONN_CLIENT_WAITING, /* Conn is on wait list, waiting for capacity */
RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */
RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */
RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */
};
/*
* The connection protocol state.
*/
enum rxrpc_conn_proto_state {
RXRPC_CONN_UNUSED, /* Connection not yet attempted */
RXRPC_CONN_CLIENT, /* Client connection */
RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */
RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */
RXRPC_CONN_SERVICE, /* Service secured connection */
RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */
RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */
RXRPC_CONN__NR_STATES
};
/*
* RxRPC connection definition
* - matched by { local, peer, epoch, conn_id, direction }
* - each connection can only handle four simultaneous calls
*/
struct rxrpc_connection {
struct rxrpc_conn_proto proto;
struct rxrpc_conn_parameters params;
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
atomic_t usage;
struct rcu_head rcu;
struct list_head cache_link;
rxrpc: Call channels should have separate call number spaces Each channel on a connection has a separate, independent number space from which to allocate callNumber values. It is entirely possible, for example, to have a connection with four active calls, each with call number 1. Note that the callNumber values for any particular channel don't have to start at 1, but they are supposed to increment monotonically for that channel from a client's perspective and may not be reused once the call number is transmitted (until the epoch cycles all the way back round). Currently, however, call numbers are allocated on a per-connection basis and, further, are held in an rb-tree. The rb-tree is redundant as the four channel pointers in the rxrpc_connection struct are entirely capable of pointing to all the calls currently in progress on a connection. To this end, make the following changes: (1) Handle call number allocation independently per channel. (2) Get rid of the conn->calls rb-tree. This is overkill as a connection may have a maximum of four calls in progress at any one time. Use the pointers in the channels[] array instead, indexed by the channel number from the packet. (3) For each channel, save the result of the last call that was in progress on that channel in conn->channels[] so that the final ACK or ABORT packet can be replayed if necessary. Any call earlier than that is just ignored. If we've seen the next call number in a packet, the last one is most definitely defunct. (4) When generating a RESPONSE packet for a connection, the call number counter for each channel must be included in it. (5) When parsing a RESPONSE packet for a connection, the call number counters contained therein should be used to set the minimum expected call numbers on each channel. To do in future commits: (1) Replay terminal packets based on the last call stored in conn->channels[]. (2) Connections should be retired before the callNumber space on any channel runs out. (3) A server is expected to disregard or reject any new incoming call that has a call number less than the current call number counter. The call number counter for that channel must be advanced to the new call number. Note that the server cannot just require that the next call that it sees on a channel be exactly the call number counter + 1 because then there's a scenario that could cause a problem: The client transmits a packet to initiate a connection, the network goes out, the server sends an ACK (which gets lost), the client sends an ABORT (which also gets lost); the network then reconnects, the client then reuses the call number for the next call (it doesn't know the server already saw the call number), but the server thinks it already has the first packet of this call (it doesn't know that the client doesn't know that it saw the call number the first time). Signed-off-by: David Howells <dhowells@redhat.com>
2016-06-27 20:39:44 +07:00
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
spinlock_t channel_lock;
unsigned char active_chans; /* Mask of active channels */
#define RXRPC_ACTIVE_CHANS_MASK ((1 << RXRPC_MAXCALLS) - 1)
struct list_head waiting_calls; /* Calls waiting for channels */
rxrpc: Call channels should have separate call number spaces Each channel on a connection has a separate, independent number space from which to allocate callNumber values. It is entirely possible, for example, to have a connection with four active calls, each with call number 1. Note that the callNumber values for any particular channel don't have to start at 1, but they are supposed to increment monotonically for that channel from a client's perspective and may not be reused once the call number is transmitted (until the epoch cycles all the way back round). Currently, however, call numbers are allocated on a per-connection basis and, further, are held in an rb-tree. The rb-tree is redundant as the four channel pointers in the rxrpc_connection struct are entirely capable of pointing to all the calls currently in progress on a connection. To this end, make the following changes: (1) Handle call number allocation independently per channel. (2) Get rid of the conn->calls rb-tree. This is overkill as a connection may have a maximum of four calls in progress at any one time. Use the pointers in the channels[] array instead, indexed by the channel number from the packet. (3) For each channel, save the result of the last call that was in progress on that channel in conn->channels[] so that the final ACK or ABORT packet can be replayed if necessary. Any call earlier than that is just ignored. If we've seen the next call number in a packet, the last one is most definitely defunct. (4) When generating a RESPONSE packet for a connection, the call number counter for each channel must be included in it. (5) When parsing a RESPONSE packet for a connection, the call number counters contained therein should be used to set the minimum expected call numbers on each channel. To do in future commits: (1) Replay terminal packets based on the last call stored in conn->channels[]. (2) Connections should be retired before the callNumber space on any channel runs out. (3) A server is expected to disregard or reject any new incoming call that has a call number less than the current call number counter. The call number counter for that channel must be advanced to the new call number. Note that the server cannot just require that the next call that it sees on a channel be exactly the call number counter + 1 because then there's a scenario that could cause a problem: The client transmits a packet to initiate a connection, the network goes out, the server sends an ACK (which gets lost), the client sends an ABORT (which also gets lost); the network then reconnects, the client then reuses the call number for the next call (it doesn't know the server already saw the call number), but the server thinks it already has the first packet of this call (it doesn't know that the client doesn't know that it saw the call number the first time). Signed-off-by: David Howells <dhowells@redhat.com>
2016-06-27 20:39:44 +07:00
struct rxrpc_channel {
struct rxrpc_call __rcu *call; /* Active call */
u32 call_id; /* ID of current call */
u32 call_counter; /* Call ID counter */
u32 last_call; /* ID of last call */
u8 last_type; /* Type of last packet */
u16 last_service_id;
union {
u32 last_seq;
u32 last_abort;
};
rxrpc: Call channels should have separate call number spaces Each channel on a connection has a separate, independent number space from which to allocate callNumber values. It is entirely possible, for example, to have a connection with four active calls, each with call number 1. Note that the callNumber values for any particular channel don't have to start at 1, but they are supposed to increment monotonically for that channel from a client's perspective and may not be reused once the call number is transmitted (until the epoch cycles all the way back round). Currently, however, call numbers are allocated on a per-connection basis and, further, are held in an rb-tree. The rb-tree is redundant as the four channel pointers in the rxrpc_connection struct are entirely capable of pointing to all the calls currently in progress on a connection. To this end, make the following changes: (1) Handle call number allocation independently per channel. (2) Get rid of the conn->calls rb-tree. This is overkill as a connection may have a maximum of four calls in progress at any one time. Use the pointers in the channels[] array instead, indexed by the channel number from the packet. (3) For each channel, save the result of the last call that was in progress on that channel in conn->channels[] so that the final ACK or ABORT packet can be replayed if necessary. Any call earlier than that is just ignored. If we've seen the next call number in a packet, the last one is most definitely defunct. (4) When generating a RESPONSE packet for a connection, the call number counter for each channel must be included in it. (5) When parsing a RESPONSE packet for a connection, the call number counters contained therein should be used to set the minimum expected call numbers on each channel. To do in future commits: (1) Replay terminal packets based on the last call stored in conn->channels[]. (2) Connections should be retired before the callNumber space on any channel runs out. (3) A server is expected to disregard or reject any new incoming call that has a call number less than the current call number counter. The call number counter for that channel must be advanced to the new call number. Note that the server cannot just require that the next call that it sees on a channel be exactly the call number counter + 1 because then there's a scenario that could cause a problem: The client transmits a packet to initiate a connection, the network goes out, the server sends an ACK (which gets lost), the client sends an ABORT (which also gets lost); the network then reconnects, the client then reuses the call number for the next call (it doesn't know the server already saw the call number), but the server thinks it already has the first packet of this call (it doesn't know that the client doesn't know that it saw the call number the first time). Signed-off-by: David Howells <dhowells@redhat.com>
2016-06-27 20:39:44 +07:00
} channels[RXRPC_MAXCALLS];
struct work_struct processor; /* connection event processor */
union {
struct rb_node client_node; /* Node in local->client_conns */
struct rb_node service_node; /* Node in peer->service_conns */
};
struct list_head proc_link; /* link in procfs list */
struct list_head link; /* link in master connection list */
struct sk_buff_head rx_queue; /* received conn-level packets */
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 */
2016-04-04 20:00:37 +07:00
unsigned long flags;
unsigned long events;
unsigned long idle_timestamp; /* Time at which last became idle */
spinlock_t state_lock; /* state-change lock */
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
enum rxrpc_conn_cache_state cache_state : 8;
enum rxrpc_conn_proto_state state : 8; /* current state of connection */
u32 local_abort; /* local abort code */
u32 remote_abort; /* remote abort code */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
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_INIT_ACCEPT, /* acceptance was initiated */
RXRPC_CALL_HAS_USERID, /* has a user ID attached */
RXRPC_CALL_EXPECT_OOS, /* expect out of sequence packets */
RXRPC_CALL_IS_SERVICE, /* Call is service call */
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
RXRPC_CALL_EXPOSED, /* The call was exposed to the world */
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
RXRPC_CALL_RX_NO_MORE, /* Don't indicate MSG_MORE from recvmsg() */
};
/*
* 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_UNINITIALISED,
RXRPC_CALL_CLIENT_AWAIT_CONN, /* - client waiting for connection to become available */
RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */
RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */
RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */
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 complete */
RXRPC_CALL_DEAD, /* - call is dead */
NR__RXRPC_CALL_STATES
};
/*
* Call completion condition (state == RXRPC_CALL_COMPLETE).
*/
enum rxrpc_call_completion {
RXRPC_CALL_SUCCEEDED, /* - Normal termination */
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_LOCAL_ERROR, /* - call failed due to local error */
RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
NR__RXRPC_CALL_COMPLETIONS
};
/*
* RxRPC call definition
* - matched by { connection, call_id }
*/
struct rxrpc_call {
struct rcu_head rcu;
struct rxrpc_connection *conn; /* connection carrying call */
struct rxrpc_peer *peer; /* Peer record for remote address */
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 */
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */
struct list_head link; /* link in master call list */
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
struct list_head chan_wait_link; /* Link in conn->waiting_calls */
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 sk_buff_head rx_queue; /* received packets */
struct sk_buff_head rx_oos_queue; /* packets received out of sequence */
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
struct sk_buff_head knlrecv_queue; /* Queue for kernel_recv [TODO: replace this] */
struct sk_buff *tx_pending; /* Tx socket buffer being filled */
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
wait_queue_head_t waitq; /* Wait queue for channel or Tx */
__be32 crypto_buf[2]; /* Temporary packet crypto buffer */
unsigned long user_call_ID; /* user-defined call ID */
unsigned long creation_jif; /* time of call creation */
unsigned long flags;
unsigned long events;
spinlock_t lock;
rwlock_t state_lock; /* lock for state transition */
u32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
enum rxrpc_call_state state : 8; /* current state of call */
enum rxrpc_call_completion completion : 8; /* Call completion condition */
atomic_t usage;
rxrpc: Fix races between skb free, ACK generation and replying Inside the kafs filesystem it is possible to occasionally have a call processed and terminated before we've had a chance to check whether we need to clean up the rx queue for that call because afs_send_simple_reply() ends the call when it is done, but this is done in a workqueue item that might happen to run to completion before afs_deliver_to_call() completes. Further, it is possible for rxrpc_kernel_send_data() to be called to send a reply before the last request-phase data skb is released. The rxrpc skb destructor is where the ACK processing is done and the call state is advanced upon release of the last skb. ACK generation is also deferred to a work item because it's possible that the skb destructor is not called in a context where kernel_sendmsg() can be invoked. To this end, the following changes are made: (1) kernel_rxrpc_data_consumed() is added. This should be called whenever an skb is emptied so as to crank the ACK and call states. This does not release the skb, however. kernel_rxrpc_free_skb() must now be called to achieve that. These together replace rxrpc_kernel_data_delivered(). (2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed(). This makes afs_deliver_to_call() easier to work as the skb can simply be discarded unconditionally here without trying to work out what the return value of the ->deliver() function means. The ->deliver() functions can, via afs_data_complete(), afs_transfer_reply() and afs_extract_data() mark that an skb has been consumed (thereby cranking the state) without the need to conditionally free the skb to make sure the state is correct on an incoming call for when the call processor tries to send the reply. (3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it has finished with a packet and MSG_PEEK isn't set. (4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data(). Because of this, we no longer need to clear the destructor and put the call before we free the skb in cases where we don't want the ACK/call state to be cranked. (5) The ->deliver() call-type callbacks are made to return -EAGAIN rather than 0 if they expect more data (afs_extract_data() returns -EAGAIN to the delivery function already), and the caller is now responsible for producing an abort if that was the last packet. (6) There are many bits of unmarshalling code where: ret = afs_extract_data(call, skb, last, ...); switch (ret) { case 0: break; case -EAGAIN: return 0; default: return ret; } is to be found. As -EAGAIN can now be passed back to the caller, we now just return if ret < 0: ret = afs_extract_data(call, skb, last, ...); if (ret < 0) return ret; (7) Checks for trailing data and empty final data packets has been consolidated as afs_data_complete(). So: if (skb->len > 0) return -EBADMSG; if (!last) return 0; becomes: ret = afs_data_complete(call, skb, last); if (ret < 0) return ret; (8) afs_transfer_reply() now checks the amount of data it has against the amount of data desired and the amount of data in the skb and returns an error to induce an abort if we don't get exactly what we want. Without these changes, the following oops can occasionally be observed, particularly if some printks are inserted into the delivery path: general protection fault: 0000 [#1] SMP Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc] CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G E 4.7.0-fsdevel+ #1303 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Workqueue: kafsd afs_async_workfn [kafs] task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000 RIP: 0010:[<ffffffff8108fd3c>] [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1 RSP: 0018:ffff88040c073bc0 EFLAGS: 00010002 RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710 RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f FS: 0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0 Stack: 0000000000000006 000000000be04930 0000000000000000 ffff880400000000 ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446 ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38 Call Trace: [<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74 [<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1 [<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189 [<ffffffff810915f4>] lock_acquire+0x122/0x1b6 [<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6 [<ffffffff814c928f>] ? skb_dequeue+0x18/0x61 [<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49 [<ffffffff814c928f>] ? skb_dequeue+0x18/0x61 [<ffffffff814c928f>] skb_dequeue+0x18/0x61 [<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs] [<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs] [<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs] [<ffffffff81063a3a>] process_one_work+0x29d/0x57c [<ffffffff81064ac2>] worker_thread+0x24a/0x385 [<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0 [<ffffffff810696f5>] kthread+0xf3/0xfb [<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40 [<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-03 20:11:40 +07:00
atomic_t skb_count; /* Outstanding packets on this call */
atomic_t sequence; /* Tx data packet sequence counter */
u16 service_id; /* service ID */
u32 call_id; /* call ID on connection */
u32 cid; /* connection ID plus channel index */
int debug_id; /* debug ID for printks */
/* 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 */
u16 ackr_skew; /* skew on packet being ACK'd */
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];
};
#include <trace/events/rxrpc.h>
/*
[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 05:50:17 +07:00
* 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 05:50:17 +07:00
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 05:50:17 +07:00
extern atomic_t rxrpc_debug_id;
extern struct workqueue_struct *rxrpc_workqueue;
/*
* 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 20:00:35 +07:00
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long,
rxrpc_notify_rx_t);
int rxrpc_reject_call(struct rxrpc_sock *);
/*
* call_event.c
*/
void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool);
void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool);
void rxrpc_process_call(struct work_struct *);
/*
* call_object.c
*/
extern const char *const rxrpc_call_states[];
extern const char *const rxrpc_call_completions[];
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_by_user_ID(struct rxrpc_sock *, unsigned long);
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
struct rxrpc_conn_parameters *,
struct sockaddr_rxrpc *,
unsigned long, gfp_t);
struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *,
struct rxrpc_connection *,
struct sk_buff *);
void rxrpc_release_call(struct rxrpc_call *);
void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
void rxrpc_see_call(struct rxrpc_call *);
void rxrpc_get_call(struct rxrpc_call *);
void rxrpc_put_call(struct rxrpc_call *);
void rxrpc_get_call_for_skb(struct rxrpc_call *, struct sk_buff *);
void rxrpc_put_call_for_skb(struct rxrpc_call *, struct sk_buff *);
void __exit rxrpc_destroy_all_calls(void);
static inline bool rxrpc_is_service_call(const struct rxrpc_call *call)
{
return test_bit(RXRPC_CALL_IS_SERVICE, &call->flags);
}
static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
{
return !rxrpc_is_service_call(call);
}
/*
* Transition a call to the complete state.
*/
static inline bool __rxrpc_set_call_completion(struct rxrpc_call *call,
enum rxrpc_call_completion compl,
u32 abort_code,
int error)
{
if (call->state < RXRPC_CALL_COMPLETE) {
call->abort_code = abort_code;
call->error = error;
call->completion = compl,
call->state = RXRPC_CALL_COMPLETE;
return true;
}
return false;
}
static inline bool rxrpc_set_call_completion(struct rxrpc_call *call,
enum rxrpc_call_completion compl,
u32 abort_code,
int error)
{
int ret;
write_lock_bh(&call->state_lock);
ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
write_unlock_bh(&call->state_lock);
return ret;
}
/*
* Record that a call successfully completed.
*/
static inline void __rxrpc_call_completed(struct rxrpc_call *call)
{
__rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
}
static inline void rxrpc_call_completed(struct rxrpc_call *call)
{
write_lock_bh(&call->state_lock);
__rxrpc_call_completed(call);
write_unlock_bh(&call->state_lock);
}
/*
* Record that a call is locally aborted.
*/
static inline bool __rxrpc_abort_call(struct rxrpc_call *call,
u32 abort_code, int error)
{
if (__rxrpc_set_call_completion(call,
RXRPC_CALL_LOCALLY_ABORTED,
abort_code, error)) {
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
return true;
}
return false;
}
static inline bool rxrpc_abort_call(struct rxrpc_call *call,
u32 abort_code, int error)
{
bool ret;
write_lock_bh(&call->state_lock);
ret = __rxrpc_abort_call(call, abort_code, error);
write_unlock_bh(&call->state_lock);
return ret;
}
2016-04-04 20:00:37 +07:00
/*
* conn_client.c
*/
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
extern unsigned int rxrpc_max_client_connections;
extern unsigned int rxrpc_reap_client_connections;
extern unsigned int rxrpc_conn_idle_client_expiry;
extern unsigned int rxrpc_conn_idle_client_fast_expiry;
2016-04-04 20:00:37 +07:00
extern struct idr rxrpc_client_conn_ids;
void rxrpc_destroy_client_conn_ids(void);
int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *,
struct sockaddr_rxrpc *, gfp_t);
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_call *);
void rxrpc_put_client_conn(struct rxrpc_connection *);
void __exit rxrpc_destroy_all_client_connections(void);
2016-04-04 20:00:37 +07:00
/*
* 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 20:00:35 +07:00
void rxrpc_reject_packets(struct rxrpc_local *);
/*
* conn_object.c
*/
extern unsigned int rxrpc_connection_expiry;
extern struct list_head rxrpc_connections;
extern struct list_head rxrpc_connection_proc_list;
extern rwlock_t rxrpc_connection_lock;
int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *);
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
struct sk_buff *);
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *);
void rxrpc_disconnect_call(struct rxrpc_call *);
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
void rxrpc_kill_connection(struct rxrpc_connection *);
void __rxrpc_put_connection(struct rxrpc_connection *);
void __exit rxrpc_destroy_all_connections(void);
static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn)
{
return conn->out_clientflag;
}
static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn)
{
return !rxrpc_conn_is_client(conn);
}
static inline void rxrpc_get_connection(struct rxrpc_connection *conn)
{
atomic_inc(&conn->usage);
}
static inline
struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
{
return atomic_inc_not_zero(&conn->usage) ? conn : NULL;
}
static inline void rxrpc_put_connection(struct rxrpc_connection *conn)
{
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 13:30:52 +07:00
if (!conn)
return;
if (rxrpc_conn_is_client(conn)) {
if (atomic_dec_and_test(&conn->usage))
rxrpc_put_client_conn(conn);
} else {
if (atomic_dec_return(&conn->usage) == 1)
__rxrpc_put_connection(conn);
}
}
static inline bool rxrpc_queue_conn(struct rxrpc_connection *conn)
{
if (!rxrpc_get_connection_maybe(conn))
return false;
if (!rxrpc_queue_work(&conn->processor))
rxrpc_put_connection(conn);
return true;
}
/*
* conn_service.c
*/
struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *,
struct sk_buff *);
struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *,
struct sockaddr_rxrpc *,
struct sk_buff *);
rxrpc: Maintain an extra ref on a conn for the cache list Overhaul the usage count accounting for the rxrpc_connection struct to make it easier to implement RCU access from the data_ready handler. The problem is that currently we're using a lock to prevent the garbage collector from trying to clean up a connection that we're contemplating unidling. We could just stick incoming packets on the connection we find, but we've then got a problem that we may race when dispatching a work item to process it as we need to give that a ref to prevent the rxrpc_connection struct from disappearing in the meantime. Further, incoming packets may get discarded if attached to an rxrpc_connection struct that is going away. Whilst this is not a total disaster - the client will presumably resend - it would delay processing of the call. This would affect the AFS client filesystem's service manager operation. To this end: (1) We now maintain an extra count on the connection usage count whilst it is on the connection list. This mean it is not in use when its refcount is 1. (2) When trying to reuse an old connection, we only increment the refcount if it is greater than 0. If it is 0, we replace it in the tree with a new candidate connection. (3) Two connection flags are added to indicate whether or not a connection is in the local's client connection tree (used by sendmsg) or the peer's service connection tree (used by data_ready). This makes sure that we don't try and remove a connection if it got replaced. The flags are tested under lock with the removal operation to prevent the reaper from killing the rxrpc_connection struct whilst someone else is trying to effect a replacement. This could probably be alleviated by using memory barriers between the flag set/test and the rb_tree ops. The rb_tree op would still need to be under the lock, however. (4) When trying to reap an old connection, we try to flip the usage count from 1 to 0. If it's not 1 at that point, then it must've come back to life temporarily and we ignore it. Signed-off-by: David Howells <dhowells@redhat.com>
2016-06-30 16:45:22 +07:00
void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
/*
* 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 20:00:35 +07:00
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 20:00:35 +07:00
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 20:00:35 +07:00
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 (local && atomic_dec_and_test(&local->usage))
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 20:00:35 +07:00
__rxrpc_put_local(local);
}
static inline void rxrpc_queue_local(struct rxrpc_local *local)
{
rxrpc_queue_work(&local->processor);
}
/*
* 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 unsigned int rxrpc_resend_timeout;
extern const char *const rxrpc_pkts[];
extern const s8 rxrpc_ack_priority[];
extern const char *rxrpc_acks(u8 reason);
/*
* output.c
*/
int rxrpc_send_data_packet(struct rxrpc_connection *, struct sk_buff *);
/*
* 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 struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer)
{
atomic_inc(&peer->usage);
return peer;
}
static inline
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
{
return atomic_inc_not_zero(&peer->usage) ? peer : NULL;
}
extern void __rxrpc_put_peer(struct rxrpc_peer *peer);
static inline void rxrpc_put_peer(struct rxrpc_peer *peer)
{
if (peer && atomic_dec_and_test(&peer->usage))
__rxrpc_put_peer(peer);
}
/*
* proc.c
*/
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 *);
/*
* sendmsg.c
*/
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
* skbuff.c
*/
rxrpc: Don't expose skbs to in-kernel users [ver #2] Don't expose skbs to in-kernel users, such as the AFS filesystem, but instead provide a notification hook the indicates that a call needs attention and another that indicates that there's a new call to be collected. This makes the following possibilities more achievable: (1) Call refcounting can be made simpler if skbs don't hold refs to calls. (2) skbs referring to non-data events will be able to be freed much sooner rather than being queued for AFS to pick up as rxrpc_kernel_recv_data will be able to consult the call state. (3) We can shortcut the receive phase when a call is remotely aborted because we don't have to go through all the packets to get to the one cancelling the operation. (4) It makes it easier to do encryption/decryption directly between AFS's buffers and sk_buffs. (5) Encryption/decryption can more easily be done in the AFS's thread contexts - usually that of the userspace process that issued a syscall - rather than in one of rxrpc's background threads on a workqueue. (6) AFS will be able to wait synchronously on a call inside AF_RXRPC. To make this work, the following interface function has been added: int rxrpc_kernel_recv_data( struct socket *sock, struct rxrpc_call *call, void *buffer, size_t bufsize, size_t *_offset, bool want_more, u32 *_abort_code); This is the recvmsg equivalent. It allows the caller to find out about the state of a specific call and to transfer received data into a buffer piecemeal. afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction logic between them. They don't wait synchronously yet because the socket lock needs to be dealt with. Five interface functions have been removed: rxrpc_kernel_is_data_last() rxrpc_kernel_get_abort_code() rxrpc_kernel_get_error_number() rxrpc_kernel_free_skb() rxrpc_kernel_data_consumed() As a temporary hack, sk_buffs going to an in-kernel call are queued on the rxrpc_call struct (->knlrecv_queue) rather than being handed over to the in-kernel user. To process the queue internally, a temporary function, temp_deliver_data() has been added. This will be replaced with common code between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a future patch. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 02:42:14 +07:00
void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *);
void rxrpc_packet_destructor(struct sk_buff *);
void rxrpc_new_skb(struct sk_buff *);
void rxrpc_see_skb(struct sk_buff *);
void rxrpc_get_skb(struct sk_buff *);
void rxrpc_free_skb(struct sk_buff *);
void rxrpc_purge_queue(struct sk_buff_head *);
/*
* 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
/*
* utils.c
*/
int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *);
/*
* 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 */