-
socket：内核初始化及创建流(文件)详细过程
socket中文名称为套接字，属于传输协议及功能接口的封装。socket首先初始化注册(socket)文件系统，然后由使用它的模块传入具体的地址族(类型)family，如ipv4模块中的(void)sock_register(&inet_family_ops);
当调用者执行socket()函数时，会触发__sys_socket函数，完成socket文件的创建、修改模式为流模式、提供文件系统操作结构的功能接口、SELINUX策略绑定等等。目录
内容
1. 源码流程
1.1 sock_init
static int __init sock_init(void) { int err; /* 初始化网络sysctl基础结构 */ err = net_sysctl_init(); if (err) goto out;- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
net_sysctl_init分析，继续看sock_init：
/* 初始化skbuff SLAB缓存 */ skb_init(); // skbuff_head_cache // skbuff_fclone_cache // skbuff_ext_cache /* 初始化protocols模块 */ init_inodecache(); // SLAB缓存 -> sock_inode_cache err = register_filesystem(&sock_fs_type); // 注册sockft(socket)文件系统- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
sockfs_init_fs_context分析，继续看sock_init：
sock_mnt = kern_mount(&sock_fs_type); // 获取文件系统的super_block对象 // 根目录的inode与dentry对象 // 加入到链表 #ifdef CONFIG_NETFILTER err = netfilter_init(); if (err) goto out; #endif- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
netfilter_init分析，继续看sock_init：
ptp_classifier_init(); // 一个独立于任何套接字的过滤器(BPF（Berkeley Packet Filter）伯克利包过滤器,BPF允许用户空间程序将一个过滤(filter)附加到任何的套接字(socket)上面用来允许或不允许某些类型的数据通过socket) out: return err; out_mount: unregister_filesystem(&sock_fs_type); // 取消注册sockft(socket)文件系统 goto out; }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
1.2 socket文件创建
socket初始化完成之后，通过文件形式创建相关服务。当执行socket()函数时，内核通过SYSCALL_DEFINE3(socket…) -> __sys_socket进行相关内容加载，进入__sys_socket函数：
int __sys_socket(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, protocol); // 创建套接字，加入SELINUX策略等等- 1
- 2
- 3
- 4
- 5
- 6
__sys_socket_create分析，继续看sock_init：
flags = type & ~SOCK_TYPE_MASK; // 清除SOCK_TYPE_MASK标志 // #define SOCK_TYPE_MASK 0xf if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); // 创建套接字文件，设置文件为流模式，文件指针放入文件描述符表(数组，table[fd])中 }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
2. 源码结构
socket_file_ops
static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, .show_fdinfo = sock_show_fdinfo, };- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
sysctl_table_root
static struct ctl_table_root sysctl_table_root = { .default_set.dir.header = { {{.count = 1, .nreg = 1, .ctl_table = root_table }}, .ctl_table_arg = root_table, .root = &sysctl_table_root, .set = &sysctl_table_root.default_set, }, };- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
sysctl_table_root
static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, };- 1
- 2
- 3
- 4
root_table
static struct ctl_table root_table[] = { { .procname = "", .mode = S_IFDIR|S_IRUGO|S_IXUGO, }, { } };- 1
- 2
- 3
- 4
- 5
- 6
- 7
sock_fs_type
static struct file_system_type sock_fs_type = { .name = "sockfs", .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, };- 1
- 2
- 3
- 4
- 5
xattr_handler
static const struct xattr_handler *sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, NULL };- 1
- 2
- 3
- 4
- 5
sockfs_ops
static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .free_inode = sock_free_inode, .statfs = simple_statfs, };- 1
- 2
- 3
- 4
- 5
netfilter_net_ops
static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, };- 1
- 2
- 3
- 4
sockfs_inode_ops
static const struct inode_operations sockfs_inode_ops = { .listxattr = sockfs_listxattr, .setattr = sockfs_setattr, };- 1
- 2
- 3
- 4
- 5
3. 部分结构定义
ctl_table_header，用于维护ctl_table结构树的动态列表
struct ctl_table_header { union { struct { struct ctl_table *ctl_table; int used; int count; int nreg; }; struct rcu_head rcu; }; struct completion *unregistering; struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ };- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
ctl_table_header存储结构(红黑树存储结构)
struct ctl_dir { /* Header must be at the start of ctl_dir */ struct ctl_table_header header; struct rb_root root; };- 1
- 2
- 3
- 4
- 5
ctl_table_header存储结构(红黑树存储结构)
struct ctl_table_set { int (*is_seen)(struct ctl_table_set *); struct ctl_dir dir; };- 1
- 2
- 3
- 4
socket_alloc
struct socket_alloc { struct socket socket; struct inode vfs_inode; };- 1
- 2
- 3
- 4
sock_type
enum sock_type { SOCK_STREAM = 1, SOCK_DGRAM = 2, SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, SOCK_DCCP = 6, SOCK_PACKET = 10, };- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
支持的地址族
/* Supported address families. */ #define AF_UNSPEC 0 #define AF_UNIX 1 /* Unix domain sockets */ #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ #define AF_INET 2 /* Internet IP Protocol */ #define AF_AX25 3 /* Amateur Radio AX.25 */ #define AF_IPX 4 /* Novell IPX */ #define AF_APPLETALK 5 /* AppleTalk DDP */ #define AF_NETROM 6 /* Amateur Radio NET/ROM */ #define AF_BRIDGE 7 /* Multiprotocol bridge */ #define AF_ATMPVC 8 /* ATM PVCs */ #define AF_X25 9 /* Reserved for X.25 project */ #define AF_INET6 10 /* IP version 6 */ #define AF_ROSE 11 /* Amateur Radio X.25 PLP */ #define AF_DECnet 12 /* Reserved for DECnet project */ #define AF_NETBEUI 13 /* Reserved for 802.2LLC project*/ #define AF_SECURITY 14 /* Security callback pseudo AF */ #define AF_KEY 15 /* PF_KEY key management API */ #define AF_NETLINK 16 #define AF_ROUTE AF_NETLINK /* Alias to emulate 4.4BSD */ #define AF_PACKET 17 /* Packet family */ #define AF_ASH 18 /* Ash */ #define AF_ECONET 19 /* Acorn Econet */ #define AF_ATMSVC 20 /* ATM SVCs */ #define AF_RDS 21 /* RDS sockets */ #define AF_SNA 22 /* Linux SNA Project (nutters!) */ #define AF_IRDA 23 /* IRDA sockets */ #define AF_PPPOX 24 /* PPPoX sockets */ #define AF_WANPIPE 25 /* Wanpipe API Sockets */ #define AF_LLC 26 /* Linux LLC */ #define AF_IB 27 /* Native InfiniBand address */ #define AF_MPLS 28 /* MPLS */ #define AF_CAN 29 /* Controller Area Network */ #define AF_TIPC 30 /* TIPC sockets */ #define AF_BLUETOOTH 31 /* Bluetooth sockets */ #define AF_IUCV 32 /* IUCV sockets */ #define AF_RXRPC 33 /* RxRPC sockets */ #define AF_ISDN 34 /* mISDN sockets */ #define AF_PHONET 35 /* Phonet sockets */ #define AF_IEEE802154 36 /* IEEE802154 sockets */ #define AF_CAIF 37 /* CAIF sockets */ #define AF_ALG 38 /* Algorithm sockets */ #define AF_NFC 39 /* NFC sockets */ #define AF_VSOCK 40 /* vSockets */ #define AF_KCM 41 /* Kernel Connection Multiplexor*/ #define AF_QIPCRTR 42 /* Qualcomm IPC Router */ #define AF_SMC 43 /* smc sockets: reserve number for * PF_SMC protocol family that * reuses AF_INET address family */ #define AF_XDP 44 /* XDP sockets */ #define AF_MCTP 45 /* Management component * transport protocol */ #define AF_MAX 46 /* For now.. */- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
支持的SELINE class类型
#define SECCLASS_SECURITY 1 #define SECCLASS_PROCESS 2 #define SECCLASS_PROCESS2 3 #define SECCLASS_SYSTEM 4 #define SECCLASS_CAPABILITY 5 #define SECCLASS_FILESYSTEM 6 #define SECCLASS_FILE 7 #define SECCLASS_DIR 8 #define SECCLASS_FD 9 #define SECCLASS_LNK_FILE 10 #define SECCLASS_CHR_FILE 11 #define SECCLASS_BLK_FILE 12 #define SECCLASS_SOCK_FILE 13 #define SECCLASS_FIFO_FILE 14 #define SECCLASS_SOCKET 15 #define SECCLASS_TCP_SOCKET 16 #define SECCLASS_UDP_SOCKET 17 #define SECCLASS_RAWIP_SOCKET 18 #define SECCLASS_NODE 19 #define SECCLASS_NETLINK_SOCKET 21 #define SECCLASS_PACKET_SOCKET 22 #define SECCLASS_KEY_SOCKET 23 #define SECCLASS_UNIX_STREAM_SOCKET 24 #define SECCLASS_UNIX_DGRAM_SOCKET 25 #define SECCLASS_SEM 26 #define SECCLASS_MSG 27 #define SECCLASS_MSGQ 28 #define SECCLASS_SHM 29 #define SECCLASS_IPC 30 #define SECCLASS_NETLINK_ROUTE_SOCKET 31 #define SECCLASS_NETLINK_TCPDIAG_SOCKET 32 #define SECCLASS_NETLINK_NFLOG_SOCKET 33 #define SECCLASS_NETLINK_XFRM_SOCKET 34 #define SECCLASS_NETLINK_SELINUX_SOCKET 35 #define SECCLASS_NETLINK_ISCSI_SOCKET 36 #define SECCLASS_NETLINK_AUDIT_SOCKET 37 #define SECCLASS_NETLINK_FIB_LOOKUP_SOCKET 38 #define SECCLASS_NETLINK_CONNECTOR_SOCKET 39 #define SECCLASS_NETLINK_NETFILTER_SOCKET 40 #define SECCLASS_NETLINK_DNRT_SOCKET 41 #define SECCLASS_ASSOCIATION 42 #define SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET 43 #define SECCLASS_NETLINK_GENERIC_SOCKET 44 #define SECCLASS_NETLINK_SCSITRANSPORT_SOCKET 45 #define SECCLASS_NETLINK_RDMA_SOCKET 46 #define SECCLASS_NETLINK_CRYPTO_SOCKET 47 #define SECCLASS_APPLETALK_SOCKET 48 #define SECCLASS_PACKET 49 #define SECCLASS_KEY 50 #define SECCLASS_DCCP_SOCKET 51 #define SECCLASS_MEMPROTECT 52 #define SECCLASS_PEER 53 #define SECCLASS_CAPABILITY2 54 #define SECCLASS_KERNEL_SERVICE 55 #define SECCLASS_TUN_SOCKET 56 #define SECCLASS_BINDER 57 #define SECCLASS_CAP_USERNS 58 #define SECCLASS_CAP2_USERNS 59 #define SECCLASS_SCTP_SOCKET 60 #define SECCLASS_ICMP_SOCKET 61 #define SECCLASS_AX25_SOCKET 62 #define SECCLASS_IPX_SOCKET 63 #define SECCLASS_NETROM_SOCKET 64 #define SECCLASS_ATMPVC_SOCKET 65 #define SECCLASS_X25_SOCKET 66 #define SECCLASS_ROSE_SOCKET 67 #define SECCLASS_DECNET_SOCKET 68 #define SECCLASS_ATMSVC_SOCKET 69 #define SECCLASS_RDS_SOCKET 70 #define SECCLASS_IRDA_SOCKET 71 #define SECCLASS_PPPOX_SOCKET 72 #define SECCLASS_LLC_SOCKET 73 #define SECCLASS_CAN_SOCKET 74 #define SECCLASS_TIPC_SOCKET 75 #define SECCLASS_BLUETOOTH_SOCKET 76 #define SECCLASS_IUCV_SOCKET 77 #define SECCLASS_RXRPC_SOCKET 78 #define SECCLASS_ISDN_SOCKET 79 #define SECCLASS_PHONET_SOCKET 80 #define SECCLASS_IEEE802154_SOCKET 81 #define SECCLASS_CAIF_SOCKET 82 #define SECCLASS_ALG_SOCKET 83 #define SECCLASS_NFC_SOCKET 84 #define SECCLASS_VSOCK_SOCKET 85 #define SECCLASS_KCM_SOCKET 86 #define SECCLASS_QIPCRTR_SOCKET 87 #define SECCLASS_SMC_SOCKET 88 #define SECCLASS_INFINIBAND_PKEY 89 #define SECCLASS_INFINIBAND_ENDPORT 90 #define SECCLASS_BPF 91 #define SECCLASS_XDP_SOCKET 92 #define SECCLASS_MCTP_SOCKET 93 #define SECCLASS_PERF_EVENT 94 #define SECCLASS_ANON_INODE 95 #define SECCLASS_IO_URING 96- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
支持的SELINE sid类型
#define SECINITSID_KERNEL 1 #define SECINITSID_SECURITY 2 #define SECINITSID_UNLABELED 3 #define SECINITSID_FILE 5 #define SECINITSID_ANY_SOCKET 8 #define SECINITSID_PORT 9 #define SECINITSID_NETIF 10 #define SECINITSID_NETMSG 11 #define SECINITSID_NODE 12 #define SECINITSID_DEVNULL 27 #define SECINITSID_NUM 27- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
security_hook_list 安全模块挂钩列表结构，与通用列表宏一起用于常见操作
struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; char *lsm; } __randomize_layout;- 1
- 2
- 3
- 4
- 5
- 6
net_proto_family 套接字类型(家族)保存
struct net_proto_family { int family; int (*create)(struct net *net, struct socket *sock, int protocol, int kern); struct module *owner; };- 1
- 2
- 3
- 4
- 5
- 6
rlimit 对一个进程获取系统资源的数量进行限制
struct rlimit { __kernel_ulong_t rlim_cur; __kernel_ulong_t rlim_max; };- 1
- 2
- 3
- 4
sock 套接字的网络层表示
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 #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #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_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #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_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #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 #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash /* early demux fields */ struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; socket_lock_t sk_lock; atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; 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; struct llist_head defer_list; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; u32 sk_reserved_mem; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ unsigned int sk_napi_id; #endif int sk_rcvbuf; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; /* ===== cache line for TX ===== */ int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; __u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ long sk_sndtimeo; struct timer_list sk_timer; __u32 sk_priority; __u32 sk_mark; unsigned long sk_pacing_rate; /* bytes per second */ unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; __u32 sk_txhash; /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4; u8 sk_pacing_shift; u16 sk_type; u16 sk_protocol; u16 sk_gso_max_segs; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; u8 sk_shutdown; atomic_t sk_tskey; atomic_t sk_zckey; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); 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); #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; };- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
- 120
- 121
- 122
- 123
- 124
- 125
- 126
- 127
- 128
- 129
- 130
- 131
- 132
- 133
- 134
- 135
- 136
- 137
- 138
- 139
- 140
- 141
- 142
- 143
- 144
- 145
- 146
- 147
- 148
- 149
- 150
- 151
- 152
- 153
- 154
- 155
- 156
- 157
- 158
- 159
- 160
- 161
- 162
- 163
- 164
- 165
- 166
- 167
- 168
- 169
- 170
- 171
- 172
- 173
- 174
- 175
- 176
- 177
- 178
- 179
- 180
- 181
- 182
- 183
- 184
- 185
- 186
- 187
- 188
- 189
- 190
proto 我们附加到套接字的网络协议块，套接字层 -> 传输层接口
struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, int flags, int *err, bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); #endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif #if IS_ENABLED(CONFIG_MPTCP) int (*forward_alloc_get)(const struct sock *sk); #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout;- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
- 120
- 121
- 122
- 123
4. 扩展函数
net_sysctl_init
static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; net_header = register_sysctl("net", empty); // 注册"net"，插入ctl_dir结构 /* 注册网络名称空间子系统 */ ret = register_pernet_subsys(&sysctl_pernet_ops) // 注册一个子系统，该子系统在创建和销毁网络名称空间时分别调用init和exit函数 // 当注册所有网络命名空间时，将为每个现有的网络命名空间调用init函数。允许内核模块对网络名称空间集有一个竞免视图 out: return ret; out1: unregister_sysctl_table(net_header);// 取消注册sysctl表层次结构 // 注销sysctl表和所有子表 // Proc条目可能不会被实际删除，直到它们不再被任何人使用 net_header = NULL; goto out; }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
sockfs_init_fs_context
static int sockfs_init_fs_context(struct fs_context *fc) { /* 伪文件系统的常见助手（sockfs、pipefs、bdev-永远无法装载的东西）*/ struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); // 初始化伪文件系统上下文 // #define SOCKFS_MAGIC 0x534F434B ctx->ops = &sockfs_ops; // sockfs操作 // sock_alloc_inode 为指定的超级块分配一个分配socket_alloc对象 // simple_statfs 获取sockfs文件系统的状态信息 ctx->dops = &sockfs_dentry_operations; // 动态名称操作(socket:[%lu]) ctx->xattr = sockfs_xattr_handlers; // sockfs文件系统扩展属性操作 return 0; }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
netfilter_init
int __init netfilter_init(void) { int ret; /* 注册网络过滤器子系统 */ ret = register_pernet_subsys(&netfilter_net_ops); /* 注册网络过滤器日志子系统 */ ret = netfilter_log_init();- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
__sys_socket_create
static struct socket *__sys_socket_create(int family, int type, int protocol) { struct socket *sock; int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); // #define SOCK_CLOEXEC O_CLOEXEC // O_CLOEXEC 02000000 BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); // #define SOCK_MAX (SOCK_PACKET + 1) // #define SOCK_TYPE_MASK 0xf BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); // #define O_NONBLOCK 00004000 if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; /* 创建一个套接字 */ retval = sock_create(family, type, protocol, &sock); || \/ int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } || \/ int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; if (family < 0 || family >= NPROTO) // #define NPROTO AF_MAX return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; if (family == PF_INET && type == SOCK_PACKET) { // PF_INET 从INET层移到这里，以避免模块加载中的死锁 // PF_INET 互联网IP协议 pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); family = PF_PACKET; // PF_PACKET 数据包家族 } err = security_socket_create(family, type, protocol, kern); // 针对套接字家族类型检查，创建socksid(源安全标识符)，加入SELINUX策略等等 // socket_create函数是由安全模块定义的钩子，它是管理系统安全策略的众多 LSM（Linux 安全模块）挂钩之一。LSM 实际上是一个允许内核支持多种安全模型的框架。通常会有一个安全模块将自己注册到内核的 LSM 框架中 // LSM_HOOK(int, 0, socket_create, int family, int type, int protocol, int kern) // socket_create -> 执行selinux_socket_create /* 分配一个新的inode和socket对象 两者绑定在一起并初始化 然后返回套接字 */ sock = sock_alloc(); sock->type = type; // 套接字数据流类型 %SOCK_STREAM #ifdef CONFIG_MODULES /* 如果查找失败，则尝试加载协议模块 */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif ... pf = rcu_dereference(net_families[family]);// 获取套接字(类型)家族指针以解除引用 if (!try_module_get(pf->owner)) // 检查module->refcnt，它位于可加载模块中 goto out_release; err = pf->create(net, sock, protocol, kern); // net_proto_family对象由sock_register创建，在ipv4中分析 /* 为了在sock_release时拥有这个套接字的 [xxxx]模块的refcnt，我们减少它的 refcnt */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* 现在我们已经完成了 ->create 函数，[xxxx]模块可以减少module->refcnt */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); // 针对套接字家族类型检查，创建socksid(源安全标识符)，创建SELINUX class，加入SELINUX策略等等 // 尝试使用给定SID使用NetLabel机制标记套接字 // socket_post_create -> selinux_socket_post_create if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } ... if (retval < 0) return ERR_PTR(retval); return sock; }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
sock_map_fd
static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); // 分配文件描述符，flags写入相关结构体内，如果设置O_CLOEXEC标志，表示文件未打开 // # define RLIMIT_NOFILE 7 /* max number of open files */ if (unlikely(fd < 0)) { sock_release(sock); return fd; } newfile = sock_alloc_file(sock, flags, NULL); || \/ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; if (!dname) dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; // 传输层(proto)名称 file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); // 生成套接字文件，赋值文件权限，文件包括read_iter，write_iter，unlocked_ioctl等函数接口- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
alloc_file_pseudo分析，继续看sock_alloc_file：
sock->file = file; // 套接字赋值文件 file->private_data = sock; // 设置文件私有数据段 stream_open(SOCK_INODE(sock), file); // 去掉文件中的读写等标志，增加FMODE_STREAM标志 return file; } ... 回到sock_map_fd函数： if (!IS_ERR(newfile)) { fd_install(fd, newfile); // 文件指针放入文件描述符表(数组)中 return fd; } put_unused_fd(fd); return PTR_ERR(newfile); }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
alloc_file_pseudo
struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct qstr this = QSTR_INIT(name, strlen(name)); struct path path; struct file *file; path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); // 分配一个伪文件系统，文件目录存在于内存中，并且在删除最后一个引用和释放它们之间不会有RCU延迟 if (!mnt->mnt_sb->s_d_op) d_set_d_op(path.dentry, &anon_ops); // 设置目录名称及标志检查/赋值 path.mnt = mntget(mnt); // 获取vfsmount对象， vfsmount引用计数加1 d_instantiate(path.dentry, inode); // path.dentry记录inode及inode标志 file = alloc_file(&path, flags, fops); // 分配套接字文件，设置文件权限(模式)，文件路径，文件inode，读计数增加等等 // fops是file_operations结构对象socket_file_ops // 包含read_iter，write_iter，unlocked_ioctl等函数接口 if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; }- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
-
相关阅读:
一些杂题（9.23）
罗克韦尔AB PLC RSLogix5000中计数器指令使用方法介绍
临床信息去冗余 临床数据处理分组不同的GSE数据集有不同的临床信息，不同的分组技巧
Linux常用命令——builtin命令
工程制造领域：企业IT架构
重学数据库进阶
揭秘你代理商做不起来货卖不出去的原因，探讨其背后的商业逻辑
3D激光线轮廓传感器市场需求，预计2029年将达到734.86百万美元。
ElementPlus· tab切换/标签切换 + 分页
接口访问量统计
- 原文地址：https://blog.csdn.net/a29562268/article/details/126075545
