linux_dsm_epyc7002/include/rxrpc/packet.h

234 lines
9.3 KiB
C
Raw Normal View History

/* packet.h: Rx packet layout and definitions
*
* Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _LINUX_RXRPC_PACKET_H
#define _LINUX_RXRPC_PACKET_H
typedef u32 rxrpc_seq_t; /* Rx message sequence number */
typedef u32 rxrpc_serial_t; /* Rx message serial number */
typedef __be32 rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */
typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */
/*****************************************************************************/
/*
* on-the-wire Rx packet header
* - all multibyte fields should be in network byte order
*/
struct rxrpc_wire_header {
__be32 epoch; /* client boot timestamp */
#define RXRPC_RANDOM_EPOCH 0x80000000 /* Random if set, date-based if not */
__be32 cid; /* connection and channel ID */
#define RXRPC_MAXCALLS 4 /* max active calls per conn */
#define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */
#define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */
#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */
#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */
__be32 callNumber; /* call ID (0 for connection-level packets) */
__be32 seq; /* sequence number of pkt in call stream */
__be32 serial; /* serial number of pkt sent to network */
uint8_t type; /* packet type */
#define RXRPC_PACKET_TYPE_DATA 1 /* data */
#define RXRPC_PACKET_TYPE_ACK 2 /* ACK */
#define RXRPC_PACKET_TYPE_BUSY 3 /* call reject */
#define RXRPC_PACKET_TYPE_ABORT 4 /* call/connection abort */
#define RXRPC_PACKET_TYPE_ACKALL 5 /* ACK all outstanding packets on call */
#define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */
#define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */
#define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */
#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */
#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */
uint8_t flags; /* packet flags */
#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */
#define RXRPC_REQUEST_ACK 0x02 /* request an unconditional ACK of this packet */
#define RXRPC_LAST_PACKET 0x04 /* the last packet from this side for this call */
#define RXRPC_MORE_PACKETS 0x08 /* more packets to come */
#define RXRPC_JUMBO_PACKET 0x20 /* [DATA] this is a jumbo packet */
#define RXRPC_SLOW_START_OK 0x20 /* [ACK] slow start supported */
uint8_t userStatus; /* app-layer defined status */
uint8_t securityIndex; /* security protocol ID */
union {
__be16 _rsvd; /* reserved */
__be16 cksum; /* kerberos security checksum */
};
__be16 serviceId; /* service ID */
} __packed;
#define RXRPC_SUPPORTED_PACKET_TYPES ( \
(1 << RXRPC_PACKET_TYPE_DATA) | \
(1 << RXRPC_PACKET_TYPE_ACK) | \
(1 << RXRPC_PACKET_TYPE_BUSY) | \
(1 << RXRPC_PACKET_TYPE_ABORT) | \
(1 << RXRPC_PACKET_TYPE_ACKALL) | \
(1 << RXRPC_PACKET_TYPE_CHALLENGE) | \
(1 << RXRPC_PACKET_TYPE_RESPONSE) | \
/*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \
(1 << RXRPC_PACKET_TYPE_VERSION))
/*****************************************************************************/
/*
* jumbo packet secondary header
* - can be mapped to read header by:
* - new_serial = serial + 1
* - new_seq = seq + 1
* - new_flags = j_flags
* - new__rsvd = j__rsvd
* - duplicating all other fields
*/
struct rxrpc_jumbo_header {
uint8_t flags; /* packet flags (as per rxrpc_header) */
uint8_t pad;
union {
__be16 _rsvd; /* reserved */
__be16 cksum; /* kerberos security checksum */
};
};
#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */
#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header))
/*****************************************************************************/
/*
* on-the-wire Rx ACK packet data payload
* - all multibyte fields should be in network byte order
*/
struct rxrpc_ackpacket {
__be16 bufferSpace; /* number of packet buffers available */
__be16 maxSkew; /* diff between serno being ACK'd and highest serial no
* received */
__be32 firstPacket; /* sequence no of first ACK'd packet in attached list */
__be32 previousPacket; /* sequence no of previous packet received */
__be32 serial; /* serial no of packet that prompted this ACK */
uint8_t reason; /* reason for ACK */
#define RXRPC_ACK_REQUESTED 1 /* ACK was requested on packet */
#define RXRPC_ACK_DUPLICATE 2 /* duplicate packet received */
#define RXRPC_ACK_OUT_OF_SEQUENCE 3 /* out of sequence packet received */
#define RXRPC_ACK_EXCEEDS_WINDOW 4 /* packet received beyond end of ACK window */
#define RXRPC_ACK_NOSPACE 5 /* packet discarded due to lack of buffer space */
#define RXRPC_ACK_PING 6 /* keep alive ACK */
#define RXRPC_ACK_PING_RESPONSE 7 /* response to RXRPC_ACK_PING */
#define RXRPC_ACK_DELAY 8 /* nothing happened since received packet */
#define RXRPC_ACK_IDLE 9 /* ACK due to fully received ACK window */
#define RXRPC_ACK__INVALID 10 /* Representation of invalid ACK reason */
uint8_t nAcks; /* number of ACKs */
#define RXRPC_MAXACKS 255
uint8_t acks[0]; /* list of ACK/NAKs */
#define RXRPC_ACK_TYPE_NACK 0
#define RXRPC_ACK_TYPE_ACK 1
} __packed;
rxrpc: Rewrite the data and ack handling code Rewrite the data and ack handling code such that: (1) Parsing of received ACK and ABORT packets and the distribution and the filing of DATA packets happens entirely within the data_ready context called from the UDP socket. This allows us to process and discard ACK and ABORT packets much more quickly (they're no longer stashed on a queue for a background thread to process). (2) We avoid calling skb_clone(), pskb_pull() and pskb_trim(). We instead keep track of the offset and length of the content of each packet in the sk_buff metadata. This means we don't do any allocation in the receive path. (3) Jumbo DATA packet parsing is now done in data_ready context. Rather than cloning the packet once for each subpacket and pulling/trimming it, we file the packet multiple times with an annotation for each indicating which subpacket is there. From that we can directly calculate the offset and length. (4) A call's receive queue can be accessed without taking locks (memory barriers do have to be used, though). (5) Incoming calls are set up from preallocated resources and immediately made live. They can than have packets queued upon them and ACKs generated. If insufficient resources exist, DATA packet #1 is given a BUSY reply and other DATA packets are discarded). (6) sk_buffs no longer take a ref on their parent call. To make this work, the following changes are made: (1) Each call's receive buffer is now a circular buffer of sk_buff pointers (rxtx_buffer) rather than a number of sk_buff_heads spread between the call and the socket. This permits each sk_buff to be in the buffer multiple times. The receive buffer is reused for the transmit buffer. (2) A circular buffer of annotations (rxtx_annotations) is kept parallel to the data buffer. Transmission phase annotations indicate whether a buffered packet has been ACK'd or not and whether it needs retransmission. Receive phase annotations indicate whether a slot holds a whole packet or a jumbo subpacket and, if the latter, which subpacket. They also note whether the packet has been decrypted in place. (3) DATA packet window tracking is much simplified. Each phase has just two numbers representing the window (rx_hard_ack/rx_top and tx_hard_ack/tx_top). The hard_ack number is the sequence number before base of the window, representing the last packet the other side says it has consumed. hard_ack starts from 0 and the first packet is sequence number 1. The top number is the sequence number of the highest-numbered packet residing in the buffer. Packets between hard_ack+1 and top are soft-ACK'd to indicate they've been received, but not yet consumed. Four macros, before(), before_eq(), after() and after_eq() are added to compare sequence numbers within the window. This allows for the top of the window to wrap when the hard-ack sequence number gets close to the limit. Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also to indicate when rx_top and tx_top point at the packets with the LAST_PACKET bit set, indicating the end of the phase. (4) Calls are queued on the socket 'receive queue' rather than packets. This means that we don't need have to invent dummy packets to queue to indicate abnormal/terminal states and we don't have to keep metadata packets (such as ABORTs) around (5) The offset and length of a (sub)packet's content are now passed to the verify_packet security op. This is currently expected to decrypt the packet in place and validate it. However, there's now nowhere to store the revised offset and length of the actual data within the decrypted blob (there may be a header and padding to skip) because an sk_buff may represent multiple packets, so a locate_data security op is added to retrieve these details from the sk_buff content when needed. (6) recvmsg() now has to handle jumbo subpackets, where each subpacket is individually secured and needs to be individually decrypted. The code to do this is broken out into rxrpc_recvmsg_data() and shared with the kernel API. It now iterates over the call's receive buffer rather than walking the socket receive queue. Additional changes: (1) The timers are condensed to a single timer that is set for the soonest of three timeouts (delayed ACK generation, DATA retransmission and call lifespan). (2) Transmission of ACK and ABORT packets is effected immediately from process-context socket ops/kernel API calls that cause them instead of them being punted off to a background work item. The data_ready handler still has to defer to the background, though. (3) A shutdown op is added to the AF_RXRPC socket so that the AFS filesystem can shut down the socket and flush its own work items before closing the socket to deal with any in-progress service calls. Future additional changes that will need to be considered: (1) Make sure that a call doesn't hog the front of the queue by receiving data from the network as fast as userspace is consuming it to the exclusion of other calls. (2) Transmit delayed ACKs from within recvmsg() when we've consumed sufficiently more packets to avoid the background work item needing to run. Signed-off-by: David Howells <dhowells@redhat.com>
2016-09-08 17:10:12 +07:00
/* Some ACKs refer to specific packets and some are general and can be updated. */
#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \
(1 << RXRPC_ACK_PING_RESPONSE) | \
(1 << RXRPC_ACK_DELAY) | \
(1 << RXRPC_ACK_IDLE))
/*
* ACK packets can have a further piece of information tagged on the end
*/
struct rxrpc_ackinfo {
__be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */
__be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */
__be32 rwind; /* Rx window size (packets) [AFS 3.4] */
__be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */
};
/*****************************************************************************/
/*
* Kerberos security type-2 challenge packet
*/
struct rxkad_challenge {
__be32 version; /* version of this challenge type */
__be32 nonce; /* encrypted random number */
__be32 min_level; /* minimum security level */
__be32 __padding; /* padding to 8-byte boundary */
} __packed;
/*****************************************************************************/
/*
* Kerberos security type-2 response packet
*/
struct rxkad_response {
__be32 version; /* version of this response type */
__be32 __pad;
/* encrypted bit of the response */
struct {
__be32 epoch; /* current epoch */
__be32 cid; /* parent connection ID */
__be32 checksum; /* checksum */
__be32 securityIndex; /* security type */
__be32 call_id[4]; /* encrypted call IDs */
__be32 inc_nonce; /* challenge nonce + 1 */
__be32 level; /* desired level */
} encrypted;
__be32 kvno; /* Kerberos key version number */
__be32 ticket_len; /* Kerberos ticket length */
} __packed;
/*****************************************************************************/
/*
* RxRPC-level abort codes
*/
#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */
#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */
#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */
#define RX_EOF -4 /* unexpected end of data on read op */
#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */
#define RX_USER_ABORT -6 /* generic user abort */
#define RX_ADDRINUSE -7 /* UDP port in use */
#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */
[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
/*
* (un)marshalling abort codes (rxgen)
*/
#define RXGEN_CC_MARSHAL -450
#define RXGEN_CC_UNMARSHAL -451
#define RXGEN_SS_MARSHAL -452
#define RXGEN_SS_UNMARSHAL -453
#define RXGEN_DECODE -454
#define RXGEN_OPCODE -455
#define RXGEN_SS_XDRFREE -456
#define RXGEN_CC_XDRFREE -457
/*
* Rx kerberos security abort codes
* - unfortunately we have no generalised security abort codes to say things
* like "unsupported security", so we have to use these instead and hope the
* other side understands
*/
#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */
#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */
#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */
#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */
#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */
#define RXKADNOAUTH 19270405 /* caller not authorised */
#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */
#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */
#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */
#define RXKADEXPIRED 19270409 /* authentication expired */
#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */
#define RXKADDATALEN 19270411 /* user data too long */
#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */
#endif /* _LINUX_RXRPC_PACKET_H */