VIDEOS 》 Linux Kernel struct socket and struct sock data-structure

For more details refer Linux Kernel Source:
https://wiki.linuxfoundation.org/images/1/1c/Network_data_flow_through_kernel.png
struct socket - http://elixir.free-electrons.com/linux/latest/source/include/linux/net.h
struct sock - http://elixir.free-electrons.com/linux/latest/source/include/net/sock.h
struct socket implementation and APIs - http://elixir.free-electrons.com/linux/v4.13.10/source/net/socket.c
struct sock implementation and APIs - http://elixir.free-electrons.com/linux/v4.13.10/source/net/core/sock.c
Big-picture Linux Kernel Networking subsystem - http://the-linux-channel.the-toffee-project.org/index.php?page=45-videos-linux-kernel-networking-sub-system

Socket User-space/user-side:
TUTORIALS :: UDP sample socket code for Systems and Network software developers - http://the-linux-channel.the-toffee-project.org/index.php?page=2-tutorials-udp-sample-socket-code-for-systems-and-network-software-developers

And here is the copy paste of struct socket data-structure (/include/linux/net.h) from the Kernel-source version 4.13 for quick reference:

/**
 *  struct socket - general BSD socket
 *  @state: socket state (%SS_CONNECTED, etc)
 *  @type: socket type (%SOCK_STREAM, etc)
 *  @flags: socket flags (%SOCK_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;

	kmemcheck_bitfield_begin(type);
	short			type;
	kmemcheck_bitfield_end(type);

	unsigned long		flags;

	struct socket_wq __rcu	*wq;

	struct file		*file;
	struct sock		*sk;
	const struct proto_ops	*ops;
};

And here is the copy paste of sample struct socket data-structure API in (/source/net/socket.c (struct socket implementation and APIs)) from the Kernel-source version 4.13 for quick reference:

/**
 *	sock_alloc	-	allocate a socket
 *
 *	Allocate a new inode and socket object. The two are bound together
 *	and initialised. The socket is then returned. If we are out of inodes
 *	NULL is returned.
 */

struct socket *sock_alloc(void)
{
	struct inode *inode;
	struct socket *sock;

	inode = new_inode_pseudo(sock_mnt->mnt_sb);
	if (!inode)
		return NULL;

	sock = SOCKET_I(inode);

	kmemcheck_annotate_bitfield(sock, type);
	inode->i_ino = get_next_ino();
	inode->i_mode = S_IFSOCK | S_IRWXUGO;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_op = &sockfs_inode_ops;

	this_cpu_add(sockets_in_use, 1);
	return sock;
}
EXPORT_SYMBOL(sock_alloc);

And here is the copy paste of struct sock data-structure (/include/net/sock.h) from the Kernel-source version 4.13 for quick reference:

/**
  *	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_kern_sock: True if sock is using kernel lock classes
  *	@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 demux
  *	@sk_dst_cache: destination cache
  *	@sk_dst_pending_confirm: need to confirm neighbour
  *	@sk_policy: flow policy
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_tsq_flags: TCP Small Queues flags
  *	@sk_write_queue: Packet sending queue
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_napi_id: id of the last napi context to receive data for sk
  *	@sk_ll_usec: usecs to busypoll when there is no data
  *	@sk_allocation: allocation mode
  *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
  *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
  *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
  *	@sk_sndbuf: size of send buffer in bytes
  *	@__sk_flags_offset: empty field used to determine location of bitfield
  *	@sk_padding: unused element for alignment
  *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
  *	@sk_no_check_rx: allow zero checksum in RX 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_uid: user id of owner
  *	@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_txhash: computed flow hash for use on transmit
  *	@sk_filter: socket filtering instructions
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_tsflags: SO_TIMESTAMPING socket options
  *	@sk_tskey: counter to disambiguate concurrent tstamp requests
  *	@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_cgrp_data: cgroup data for this cgroup
  *	@sk_memcg: this socket's memory cgroup association
  *	@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
  *	@sk_reuseport_cb: reuseport group container
  *	@sk_rcu: used during RCU grace period
  */
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_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

	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;
#define sk_rmem_alloc sk_backlog.rmem_alloc

	int			sk_forward_alloc;
#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;
		struct socket_wq	*sk_wq_raw;
	};
#ifdef CONFIG_XFRM
	struct xfrm_policy __rcu *sk_policy[2];
#endif
	struct dst_entry	*sk_rx_dst;
	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;
	struct sk_buff		*sk_send_head;
	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;
	u32			sk_pacing_rate; /* bytes per second */
	u32			sk_max_pacing_rate;
	struct page_frag	sk_frag;
	netdev_features_t	sk_route_caps;
	netdev_features_t	sk_route_nocaps;
	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.
	 */
	unsigned int		__sk_flags_offset[0];
#ifdef __BIG_ENDIAN_BITFIELD
#define SK_FL_PROTO_SHIFT  16
#define SK_FL_PROTO_MASK   0x00ff0000

#define SK_FL_TYPE_SHIFT   0
#define SK_FL_TYPE_MASK    0x0000ffff
#else
#define SK_FL_PROTO_SHIFT  8
#define SK_FL_PROTO_MASK   0x0000ff00

#define SK_FL_TYPE_SHIFT   16
#define SK_FL_TYPE_MASK    0xffff0000
#endif

	kmemcheck_bitfield_begin(flags);
	unsigned int		sk_padding : 1,
				sk_kern_sock : 1,
				sk_no_check_tx : 1,
				sk_no_check_rx : 1,
				sk_userlocks : 4,
				sk_protocol  : 8,
				sk_type      : 16;
#define SK_PROTOCOL_MAX U8_MAX
	kmemcheck_bitfield_end(flags);

	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;
	struct pid		*sk_peer_pid;
	const struct cred	*sk_peer_cred;
	long			sk_rcvtimeo;
	ktime_t			sk_stamp;
	u16			sk_tsflags;
	u8			sk_shutdown;
	u32			sk_tskey;
	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);
	void                    (*sk_destruct)(struct sock *sk);
	struct sock_reuseport __rcu	*sk_reuseport_cb;
	struct rcu_head		sk_rcu;
};

enum sk_pacing {
	SK_PACING_NONE		= 0,
	SK_PACING_NEEDED	= 1,
	SK_PACING_FQ		= 2,
};

Here is the Network data/API flow through kernel for quick reference:
Source: https://wiki.linuxfoundation.org/images/1/1c/Network_data_flow_through_kernel.png

And here is the copy paste of sock_sendmsg() (/net/socket.c) from the Kernel-source version 4.13 for quick reference:

static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
	int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg));
	BUG_ON(ret == -EIOCBQUEUED);
	return ret;
}

int sock_sendmsg(struct socket *sock, struct msghdr *msg)
{
	int err = security_socket_sendmsg(sock, msg,
					  msg_data_left(msg));

	return err ?: sock_sendmsg_nosec(sock, msg);
}
EXPORT_SYMBOL(sock_sendmsg);

And here is the copy paste of sock_recvmsg() (/net/socket.c) from the Kernel-source version 4.13 for quick reference:

static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
				     int flags)
{
	return sock->ops->recvmsg(sock, msg, msg_data_left(msg), flags);
}

int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags)
{
	int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags);

	return err ?: sock_recvmsg_nosec(sock, msg, flags);
}
EXPORT_SYMBOL(sock_recvmsg);

Suggested Topics:

Video Episodes :: Linux Kernel programming