linux网络源码分析——基本数据结构1
sock底层的数据结构
sock_common是sockets在网络层的最小表示，后面其他的结构体会用到sock_common结构体。
/**
* struct sock_common - minimal network layer representation of sockets
* @skc_daddr: Foreign IPv4 addr
* 外部ipv4地址
* @skc_rcv_saddr: Bound local IPv4 addr
* 本地IPv4 addr
* @skc_hash: hash value used with various protocol lookup tables
* 哈希值
* @skc_u16hashes: two u16 hash values used by UDP lookup tables
* @skc_family: network address family
* @skc_state: Connection state
* @skc_reuse: %SO_REUSEADDR setting
* @skc_bound_dev_if: bound device index if != 0
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
* @skc_prot: protocol handlers inside a network family
* @skc_net: reference to the network namespace of this socket
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
* @skc_refcnt: reference count
*
* This is the minimal network layer representation of sockets, the header
* for struct sock and struct inet_timewait_sock.
*/
struct sock_common {
/* skc_daddr and skc_rcv_saddr must be grouped :
* cf INET_MATCH() and INET_TW_MATCH()
*/
__be32 skc_daddr;
__be32 skc_rcv_saddr;
union {
unsigned int skc_hash;
__u16 skc_u16hashes[2];
};
unsigned short skc_family;
volatile unsigned char skc_state;
unsigned char skc_reuse;
int skc_bound_dev_if;
union {
struct hlist_node skc_bind_node;
struct hlist_nulls_node skc_portaddr_node;
};
struct proto *skc_prot;
#ifdef CONFIG_NET_NS
struct net *skc_net;
#endif
/*
* fields between dontcopy_begin/dontcopy_end
* are not copied in sock_copy()
*/
/* private: */
int skc_dontcopy_begin[0];
/* public: */
union {
struct hlist_node skc_node;
struct hlist_nulls_node skc_nulls_node;
};
int skc_tx_queue_mapping;
atomic_t skc_refcnt;
/* private: */
int skc_dontcopy_end[0];
/* public: */
};
sock
这个结构体就是sockets的表示，包含了sock_common结构体，我们后续再详细了解具体的字段。
/**
* struct sock - network layer representation of sockets
* @__sk_common: shared layout with inet_timewait_sock
* @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
* @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
* @sk_lock: synchronizer
* @sk_rcvbuf: size of receive buffer in bytes
* @sk_wq: sock wait queue and async head
* @sk_dst_cache: destination cache
* @sk_dst_lock: destination cache lock
* @sk_policy: flow policy
* @sk_receive_queue: incoming packets
* @sk_wmem_alloc: transmit queue bytes committed
* @sk_write_queue: Packet sending queue
* @sk_async_wait_queue: DMA copied packets
* @sk_omem_alloc: "o" is "option" or "other"
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
* @sk_allocation: allocation mode
* @sk_sndbuf: size of send buffer in bytes
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
* @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
* @sk_error_queue: rarely used
* @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
* IPV6_ADDRFORM for instance)
* @sk_err: last error
* @sk_err_soft: errors that don't cause failure but are the cause of a
* persistent failure not just 'timed out'
* @sk_drops: raw/udp drops counter
* @sk_ack_backlog: current listen backlog
* @sk_max_ack_backlog: listen backlog set in listen()
* @sk_priority: %SO_PRIORITY setting
* @sk_type: socket type (%SOCK_STREAM, etc)
* @sk_protocol: which protocol this socket belongs in this network family
* @sk_peer_pid: &struct pid for this socket's peer
* @sk_peer_cred: %SO_PEERCRED setting
* @sk_rcvlowat: %SO_RCVLOWAT setting
* @sk_rcvtimeo: %SO_RCVTIMEO setting
* @sk_sndtimeo: %SO_SNDTIMEO setting
* @sk_rxhash: flow hash received from netif layer
* @sk_filter: socket filtering instructions
* @sk_protinfo: private area, net family specific, when not using slab
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
* @sk_socket: Identd and reporting IO signals
* @sk_user_data: RPC layer private data
* @sk_sndmsg_page: cached page for sendmsg
* @sk_sndmsg_off: cached offset for sendmsg
* @sk_send_head: front of stuff to transmit
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_classid: this socket's cgroup classid
* @sk_write_pending: a write to stream socket waits to start
* @sk_state_change: callback to indicate change in the state of the sock
* @sk_data_ready: callback to indicate there is data to be processed
* @sk_write_space: callback to indicate there is bf sending space available
* @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
* @sk_backlog_rcv: callback to process the backlog
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
*/
struct sock {
/*
* Now struct inet_timewait_sock also uses sock_common, so please just
* don't add nothing before this first member (__sk_common) --acme
*/
struct sock_common __sk_common;
#define sk_node __sk_common.skc_node
#define sk_nulls_node __sk_common.skc_nulls_node
#define sk_refcnt __sk_common.skc_refcnt
#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
#define sk_hash __sk_common.skc_hash
#define sk_family __sk_common.skc_family
#define sk_state __sk_common.skc_state
#define sk_reuse __sk_common.skc_reuse
#define sk_bound_dev_if __sk_common.skc_bound_dev_if
#define sk_bind_node __sk_common.skc_bind_node
#define sk_prot __sk_common.skc_prot
#define sk_net __sk_common.skc_net
socket_lock_t sk_lock;
//用来同步的socket的锁
struct sk_buff_head sk_receive_queue;
/*
* The backlog queue is special, it is always used with
* the per-socket spinlock held and requires low latency
* access. Therefore we special case it's implementation.
* Note : rmem_alloc is in this structure to fill a hole
* on 64bit arches, not because its logically part of
* backlog.
*/
struct {
atomic_t rmem_alloc;
int len;
struct sk_buff *head;
struct sk_buff *tail;
} sk_backlog;
#define sk_rmem_alloc sk_backlog.rmem_alloc
int sk_forward_alloc;
#ifdef CONFIG_RPS
__u32 sk_rxhash;
#endif
atomic_t sk_drops;
int sk_rcvbuf;
struct sk_filter __rcu *sk_filter;
struct socket_wq __rcu *sk_wq;
#ifdef CONFIG_NET_DMA
struct sk_buff_head sk_async_wait_queue;
#endif
#ifdef CONFIG_XFRM
struct xfrm_policy *sk_policy[2];
#endif
unsigned long sk_flags;
struct dst_entry *sk_dst_cache;
spinlock_t sk_dst_lock;
atomic_t sk_wmem_alloc;
atomic_t sk_omem_alloc;
int sk_sndbuf;
struct sk_buff_head sk_write_queue;
kmemcheck_bitfield_begin(flags);
unsigned int sk_shutdown : 2,
sk_no_check : 2,
sk_userlocks : 4,
sk_protocol : 8,
sk_type : 16;
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
int sk_route_caps;
int sk_route_nocaps;
int sk_gso_type;
unsigned int sk_gso_max_size;
u16 sk_gso_max_segs;
int sk_rcvlowat;
unsigned long sk_lingertime;
struct sk_buff_head sk_error_queue;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
int sk_err,
sk_err_soft;
unsigned short sk_ack_backlog;
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
long sk_sndtimeo;
void *sk_protinfo;
struct timer_list sk_timer;
ktime_t sk_stamp;
struct socket *sk_socket;
void *sk_user_data;
struct page *sk_sndmsg_page;
struct sk_buff *sk_send_head;
__u32 sk_sndmsg_off;
int sk_write_pending;
#ifdef CONFIG_SECURITY
void *sk_security;
#endif
__u32 sk_mark;
u32 sk_classid;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk, int bytes);
void (*sk_write_space)(struct sock *sk);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk,
struct sk_buff *skb);
void (*sk_destruct)(struct sock *sk);
};
request_sock
request_sock表示一个简单的sock连接请求。
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
struct request_sock *dl_next; /* Must be first member! */
u16 mss;
u8 retrans;
u8 cookie_ts; /* syncookie: encode tcpopts in timestamp */
/* The following two fields can be easily recomputed I think -AK */
u32 window_clamp; /* window clamp at creation time */
u32 rcv_wnd; /* rcv_wnd offered first time */
u32 ts_recent;
unsigned long expires;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
u32 secid;
u32 peer_secid;
};
sk_buff
sk_buff,这个结构体在不同的协议中都会用到，包含了各层的头部以及payload。
/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
* @sk: Socket we are owned by
* @tstamp: Time we arrived
* @dev: Device we arrived on/are leaving by
* @transport_header: Transport layer header
* @network_header: Network layer header
* @mac_header: Link layer header
* @_skb_refdst: destination entry (with norefcount bit)
* @sp: the security path, used for xfrm
* @cb: Control buffer. Free for use by every layer. Put private vars here
* @len: Length of actual data
* @data_len: Data length
* @mac_len: Length of link layer header
* @hdr_len: writable header length of cloned skb
* @csum: Checksum (must include start/offset pair)
* @csum_start: Offset from skb->head where checksumming should start
* @csum_offset: Offset from csum_start where checksum should be stored
* @local_df: allow local fragmentation
* @cloned: Head may be cloned (check refcnt to be sure)
* @nohdr: Payload reference only, must not modify header
* @pkt_type: Packet class
* @fclone: skbuff clone status
* @ip_summed: Driver fed us an IP checksum
* @priority: Packet queueing priority
* @users: User count - see {datagram,tcp}.c
* @protocol: Packet protocol from driver
* @truesize: Buffer size
* @head: Head of buffer
* @data: Data head pointer
* @tail: Tail pointer
* @end: End pointer
* @destructor: Destruct function
* @mark: Generic packet mark
* @nfct: Associated connection, if any
* @ipvs_property: skbuff is owned by ipvs
* @peeked: this packet has been seen already, so stats have been
* done for it, don't do them again
* @nf_trace: netfilter packet trace flag
* @nfctinfo: Relationship of this skb to the connection
* @nfct_reasm: netfilter conntrack re-assembly pointer
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
* @rxhash: the packet hash computed on receive
* @queue_mapping: Queue mapping for multiqueue devices
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
* @ndisc_nodetype: router type (from link layer)
* @dma_cookie: a cookie to one of several possible DMA operations
* done by skb DMA functions
* @secmark: security marking
* @vlan_tci: vlan tag control information
*/
struct sk_buff {
/* These two members must be first. */
struct sk_buff *next;
struct sk_buff *prev;
//双向链表存储sk_buff节点。
ktime_t tstamp;
struct sock *sk;
struct net_device *dev;
/*
* This is the control buffer. It is free to use for every
* layer. Please put your private variables there. If you
* want to keep them across layers you have to do a skb_clone()
* first. This is owned by whoever has the skb queued ATM.
*/
char cb[48] __aligned(8);
unsigned long _skb_refdst;
#ifdef CONFIG_XFRM
struct sec_path *sp;
#endif
unsigned int len,
data_len;
__u16 mac_len,
hdr_len;
union {
__wsum csum;
struct {
__u16 csum_start;
__u16 csum_offset;
};
};
__u32 priority;
kmemcheck_bitfield_begin(flags1);
__u8 local_df:1,
cloned:1,
ip_summed:2,
nohdr:1,
nfctinfo:3;
__u8 pkt_type:3,
fclone:2,
ipvs_property:1,
peeked:1,
nf_trace:1;
kmemcheck_bitfield_end(flags1);
__be16 protocol;
void (*destructor)(struct sk_buff *skb);
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct nf_conntrack *nfct;
#endif
#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
struct sk_buff *nfct_reasm;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
#endif
int skb_iif;
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
__u16 tc_verd; /* traffic control verdict */
#endif
#endif
__u32 rxhash;
__u16 queue_mapping;
kmemcheck_bitfield_begin(flags2);
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
__u8 ooo_okay:1;
kmemcheck_bitfield_end(flags2);
/* 0/13 bit hole */
#ifdef CONFIG_NET_DMA
dma_cookie_t dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
union {
__u32 mark;
__u32 dropcount;
};
__u16 vlan_tci;
sk_buff_data_t transport_header;
//传输层头部
sk_buff_data_t network_header;
//网络层头部
sk_buff_data_t mac_header;
//数据链路层头部
/* These elements must be at the end, see alloc_skb() for details. */
sk_buff_data_t tail;
sk_buff_data_t end;
unsigned char *head,
*data;
unsigned int truesize;
//数据报的真实大小
atomic_t users;
};