# linux-net-note
**Repository Path**: justfunny/linux-net-note
## Basic Information
- **Project Name**: linux-net-note
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-11-22
- **Last Updated**: 2020-12-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Linux 网络笔记
## 前记
- 分析的内核代码为 3.10.x
- 争取能从应用层面一路分析到内核驱动层面，彻底搞定linux网络
---
## linux 网络框架
用户空间 | 应用层 |
------------------------------------------------
| 系统调用接口 |
内核空间 | 协议无关接口 |
| 网络协议 |
| 设备无关接口 |
| 设备驱动 |
------------------------------------------------
| 网络物理设备|
## 数据结构
* struct socket 抽象的一个socket结构体,对应app中的socket结构体
- include/linux/net.h
* struct sock 包含在struct socket中，实现协议无关的接口
- include/net/sock.h
* struct sk_buff 用来接收或者发送的数据包，每个协议都使用该结构体封装/载运数据包
- include/linux/Sk_buff.h
* struct tcp_socket 实现tcp协议栈相关的内容
* include /linux/Tcp.h
```c
/**
* struct socket - general BSD socket
* @state: socket state (%SS_CONNECTED, etc)
* @type: socket type (%SOCK_STREAM, etc)
* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
* @ops: protocol specific socket operations
* @file: File back pointer for gc
* @sk: internal networking protocol agnostic socket representation
* @wq: wait queue for several uses
*/
struct socket {
socket_state state; //socket状态
kmemcheck_bitfield_begin(type);
short type; //socket类型
kmemcheck_bitfield_end(type);
unsigned long flags; //socket 标志位
struct socket_wq __rcu *wq; //等待队列
struct file *file; //socket关联的文件指针
struct sock *sk; //socket绑定的协议无关的结构体类型，非常庞大
const struct proto_ops *ops;//socket操作函数
};
```
```c
/**
* 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_rx_dst: receive input route used by early tcp demux
* @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_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
* @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, whether 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_cgrp_prioidx: socket group's priority map index
* @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_frag: cached page frag
* @sk_peek_off: current peek_offset value
* @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_cgrp: this socket's cgroup-specific proto data
* @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_reuseport __sk_common.skc_reuseport
#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;
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_rx_dst;
struct dst_entry __rcu *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,
#define SK_PROTOCOL_MAX U8_MAX
sk_type : 16;
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
u32 sk_pacing_rate; /* bytes per second */
netdev_features_t sk_route_caps;
netdev_features_t 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;
#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
__u32 sk_cgrp_prioidx;
#endif
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_frag sk_frag;
struct sk_buff *sk_send_head;
__s32 sk_peek_off;
int sk_write_pending;
#ifdef CONFIG_SECURITY
void *sk_security;
#endif
__u32 sk_mark;
u32 sk_classid;
struct cg_proto *sk_cgrp;
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);
}
```
```c
/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
* @tstamp: Time we arrived
* @sk: Socket we are owned by
* @dev: Device we arrived on/are leaving by
* @cb: Control buffer. Free for use by every layer. Put private vars here
* @_skb_refdst: destination entry (with norefcount bit)
* @sp: the security path, used for xfrm
* @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
* @priority: Packet queueing priority
* @local_df: allow local fragmentation
* @cloned: Head may be cloned (check refcnt to be sure)
* @ip_summed: Driver fed us an IP checksum
* @nohdr: Payload reference only, must not modify header
* @nfctinfo: Relationship of this skb to the connection
* @pkt_type: Packet class
* @fclone: skbuff clone status
* @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
* @protocol: Packet protocol from driver
* @destructor: Destruct function
* @nfct: Associated connection, if any
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
* @rxhash: the packet hash computed on receive
* @queue_mapping: Queue mapping for multiqueue devices
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
* @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport
* ports.
* @wifi_acked_valid: wifi_acked was set
* @wifi_acked: whether frame was acked on wifi or not
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
* @dma_cookie: a cookie to one of several possible DMA operations
* done by skb DMA functions
* @secmark: security marking
* @mark: Generic packet mark
* @dropcount: total number of sk_receive_queue overflows
* @vlan_proto: vlan encapsulation protocol
* @vlan_tci: vlan tag control information
* @inner_transport_header: Inner transport layer header (encapsulation)
* @inner_network_header: Network layer header (encapsulation)
* @inner_mac_header: Link layer header (encapsulation)
* @transport_header: Transport layer header
* @network_header: Network layer header
* @mac_header: Link layer header
* @tail: Tail pointer
* @end: End pointer
* @head: Head of buffer
* @data: Data head pointer
* @truesize: Buffer size
* @users: User count - see {datagram,tcp}.c
*/
struct sk_buff {
/* These two members must be first. */
struct sk_buff *next;
struct sk_buff *prev;
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 CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
#endif
int skb_iif;
__u32 rxhash;
__be16 vlan_proto;
__u16 vlan_tci;
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
__u16 tc_verd; /* traffic control verdict */
#endif
#endif
__u16 queue_mapping;
kmemcheck_bitfield_begin(flags2);
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
__u8 pfmemalloc:1;
__u8 ooo_okay:1;
__u8 l4_rxhash:1;
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
__u8 no_fcs:1;
__u8 head_frag:1;
/* Encapsulation protocol and NIC drivers should use
* this flag to indicate to each other if the skb contains
* encapsulated packet or not and maybe use the inner packet
* headers if needed
*/
__u8 encapsulation:1;
/* 7/9 bit hole (depending on ndisc_nodetype presence) */
kmemcheck_bitfield_end(flags2);
#ifdef CONFIG_NET_DMA
dma_cookie_t dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
union {
__u32 mark;
__u32 dropcount;
__u32 reserved_tailroom;
};
sk_buff_data_t inner_transport_header;
sk_buff_data_t inner_network_header;
sk_buff_data_t inner_mac_header;
sk_buff_data_t transport_header;
sk_buff_data_t network_header;
sk_buff_data_t mac_header;
/* 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;
atomic_t users;
};
```
```c
struct tcp_sock {
/* inet_connection_sock has to be the first member of tcp_sock */
struct inet_connection_sock inet_conn;
u16 tcp_header_len; /* Bytes of tcp header to send */
u16 xmit_size_goal_segs; /* Goal for segmenting output packets */
/*
* Header prediction flags
* 0x5?10 << 16 + snd_wnd in net byte order
*/
__be32 pred_flags;
/*
* RFC793 variables by their proper names. This means you can
* read the code and the spec side by side (and laugh ...)
* See RFC793 and RFC1122. The RFC writes these in capitals.
*/
u32 rcv_nxt; /* What we want to receive next */
u32 copied_seq; /* Head of yet unread data */
u32 rcv_wup; /* rcv_nxt on last window update sent */
u32 snd_nxt; /* Next sequence we send */
u32 snd_una; /* First byte we want an ack for */
u32 snd_sml; /* Last byte of the most recently transmitted small packet */
u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
u32 lsndtime; /* timestamp of last sent data packet (for restart window) */
u32 tsoffset; /* timestamp offset */
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
unsigned long tsq_flags;
/* Data for direct copy to user */
struct {
struct sk_buff_head prequeue;
struct task_struct *task;
struct iovec *iov;
int memory;
int len;
#ifdef CONFIG_NET_DMA
/* members for async copy */
struct dma_chan *dma_chan;
int wakeup;
struct dma_pinned_list *pinned_list;
dma_cookie_t dma_cookie;
#endif
} ucopy;
u32 snd_wl1; /* Sequence for window update */
u32 snd_wnd; /* The window we expect to receive */
u32 max_window; /* Maximal window ever seen from peer */
u32 mss_cache; /* Cached effective mss, not including SACKS */
u32 window_clamp; /* Maximal window to advertise */
u32 rcv_ssthresh; /* Current window clamp */
u16 advmss; /* Advertised MSS */
u8 unused;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
thin_dupack : 1,/* Fast retransmit on first dupack */
repair : 1,
frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
u8 repair_queue;
u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */
syn_data:1, /* SYN includes data */
syn_fastopen:1, /* SYN includes Fast Open option */
syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
/* RTT measurement */
u32 srtt; /* smoothed round trip time << 3 */
u32 mdev; /* medium deviation */
u32 mdev_max; /* maximal mdev for the last rtt period */
u32 rttvar; /* smoothed mdev_max */
u32 rtt_seq; /* sequence number to update rttvar */
u32 packets_out; /* Packets which are "in flight" */
u32 retrans_out; /* Retransmitted packets out */
u16 urg_data; /* Saved octet of OOB data and control flags */
u8 ecn_flags; /* ECN status bits. */
u8 reordering; /* Packet reordering metric. */
u32 snd_up; /* Urgent pointer */
u8 keepalive_probes; /* num of allowed keep alive probes */
/*
* Options received (usually on last packet, some only on SYN packets).
*/
struct tcp_options_received rx_opt;
/*
* Slow start and congestion control (see also Nagle, and Karn & Partridge)
*/
u32 snd_ssthresh; /* Slow start size threshold */
u32 snd_cwnd; /* Sending congestion window */
u32 snd_cwnd_cnt; /* Linear increase counter */
u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
u32 snd_cwnd_used;
u32 snd_cwnd_stamp;
u32 prior_cwnd; /* Congestion window at start of Recovery. */
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
u32 prr_out; /* Total number of pkts sent during Recovery. */
u32 rcv_wnd; /* Current receiver window */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */
u32 fackets_out; /* FACK'd packets */
u32 tso_deferred;
/* from STCP, retrans queue hinting */
struct sk_buff* lost_skb_hint;
struct sk_buff *scoreboard_skb_hint;
struct sk_buff *retransmit_skb_hint;
struct sk_buff_head out_of_order_queue; /* Out of order segments go here */
/* SACKs data, these 2 need to be together (see tcp_options_write) */
struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
struct tcp_sack_block recv_sack_cache[4];
struct sk_buff *highest_sack; /* skb just after the highest
* skb with SACKed bit set
* (validity guaranteed only if
* sacked_out > 0)
*/
int lost_cnt_hint;
u32 retransmit_high; /* L-bits may be on up to this seqno */
u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */
u32 prior_ssthresh; /* ssthresh saved at recovery start */
u32 high_seq; /* snd_nxt at onset of congestion */
u32 retrans_stamp; /* Timestamp of the last retransmit,
* also used in SYN-SENT to remember stamp of
* the first SYN. */
u32 undo_marker; /* tracking retrans started here. */
int undo_retrans; /* number of undoable retransmissions. */
u32 total_retrans; /* Total retransmits for entire connection */
u32 urg_seq; /* Seq of received urgent pointer */
unsigned int keepalive_time; /* time before keep alive takes place */
unsigned int keepalive_intvl; /* time interval between keep alive probes */
int linger2;
/* Receiver side RTT estimation */
struct {
u32 rtt;
u32 seq;
u32 time;
} rcv_rtt_est;
/* Receiver queue space */
struct {
int space;
u32 seq;
u32 time;
} rcvq_space;
/* TCP-specific MTU probe information. */
struct {
u32 probe_seq_start;
u32 probe_seq_end;
} mtu_probe;
u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
* while socket was owned by user.
*/
#ifdef CONFIG_TCP_MD5SIG
/* TCP AF-Specific parts; only used by MD5 Signature support so far */
const struct tcp_sock_af_ops *af_specific;
/* TCP MD5 Signature Option information */
struct tcp_md5sig_info __rcu *md5sig_info;
#endif
/* TCP fastopen related information */
struct tcp_fastopen_request *fastopen_req;
/* fastopen_rsk points to request_sock that resulted in this big
* socket. Used to retransmit SYNACKs etc.
*/
struct request_sock *fastopen_rsk;
}
```