SchOS/include/socket.h

#pragma once

#include "types.h"

// Unix domain sockets.
//
// These exist for Schcom. A compositor and its clients have to exchange
// messages, and a pipe cannot do it: a pipe is one-directional, has no
// notion of a connection, and gives no way for a server to be *found* by a
// client that starts later. A socket with a name in the filesystem is
// exactly the missing piece.
//
// AF_INET arrived later, and exactly as planned: underneath the same syscalls
// rather than reshaping them. A socket carries its domain and every entry point
// dispatches on it -- kernel/net/unix.c for AF_UNIX, kernel/net/inet.c (lwIP)
// for AF_INET.

#define AF_UNIX         1
#define AF_LOCAL        1
#define AF_INET         2
// Linux's number, because a musl program passes Linux's constant. getifaddrs()
// is implemented over this, which is why it exists here: enumerating interfaces
// is something every networked program does and nothing else offers.
#define AF_NETLINK      16
#define PF_NETLINK      AF_NETLINK
#define NETLINK_ROUTE   0

#define SOCK_STREAM     1
#define SOCK_DGRAM      2
#define SOCK_RAW        3

// Flags ORed into socket()'s and accept4()'s `type`/`flags` argument. Linux's
// values, because a musl program passes Linux's constants.
#define SOCK_NONBLOCK   0x800      // O_NONBLOCK
#define SOCK_CLOEXEC    0x80000    // O_CLOEXEC

// setsockopt/getsockopt levels and names, Linux's numbering.
//
// Only what is listed here is accepted; anything else is answered with
// ENOPROTOOPT rather than a success it did not earn. See the comment above
// sys_setsockopt for why that is worth the risk of failing a caller that never
// checked before.
#define SOL_SOCKET      1
#define IPPROTO_ICMP    1
#define IPPROTO_TCP     6

#define SO_REUSEADDR    2
#define SO_TYPE         3
#define SO_ERROR        4
#define SO_BROADCAST    6
#define SO_SNDBUF       7
#define SO_RCVBUF       8
#define SO_KEEPALIVE    9
#define SO_ACCEPTCONN   30

#define TCP_NODELAY     1

#define UNIX_PATH_MAX   108

#define SHUT_RD         0
#define SHUT_WR         1
#define SHUT_RDWR       2

struct sockaddr_un {
  uint16 sun_family;
  char   sun_path[UNIX_PATH_MAX];
};

// The generic form syscalls take. Same shape as Linux's, so a musl-linked
// program's struct lines up byte for byte.
struct sockaddr {
  uint16 sa_family;
  char   sa_data[UNIX_PATH_MAX];
};

// The AF_INET address. Same layout as Linux's, so a musl-linked program's
// struct lines up byte for byte. sin_port and sin_addr are network byte order
// and stay that way: lwIP wants them so, and converting on the way in and out
// again would be two swaps that cancel.
struct sockaddr_in {
  uint16 sin_family;
  uint16 sin_port;
  uint32 sin_addr;
  char   sin_zero[8];
};

// ---------------------------------------------------------------------------
// rtnetlink, enough of it for getifaddrs(3)
//
// Every structure below is Linux's, byte for byte, because musl parses what it
// is handed with Linux's own headers. They are not ours to design.
//
// What musl actually does (src/network/netlink.c) is the whole specification
// this has to meet: open PF_NETLINK/SOCK_RAW/NETLINK_ROUTE, send an
// nlmsghdr+rtgenmsg asking RTM_GETLINK with NLM_F_DUMP, read replies until
// NLMSG_DONE, then do it again for RTM_GETADDR on the same socket.
// ---------------------------------------------------------------------------

struct nlmsghdr {
  uint32 nlmsg_len;
  uint16 nlmsg_type;
  uint16 nlmsg_flags;
  uint32 nlmsg_seq;
  uint32 nlmsg_pid;
};

struct rtgenmsg { uchar rtgen_family; };

struct ifinfomsg {
  uchar  ifi_family;
  uchar  __ifi_pad;
  uint16 ifi_type;              // ARPHRD_*
  int32  ifi_index;
  uint32 ifi_flags;             // IFF_*
  uint32 ifi_change;
};

struct ifaddrmsg {
  uchar  ifa_family;
  uchar  ifa_prefixlen;
  uchar  ifa_flags;
  uchar  ifa_scope;
  uint32 ifa_index;
};

struct rtattr {
  uint16 rta_len;
  uint16 rta_type;
};

#define NLMSG_ERROR     2
#define NLMSG_DONE      3
#define NLM_F_REQUEST   0x001
#define NLM_F_MULTI     0x002
#define NLM_F_DUMP      0x300

#define RTM_NEWLINK     16
#define RTM_GETLINK     18
#define RTM_NEWADDR     20
#define RTM_GETADDR     22

#define IFLA_ADDRESS     1
#define IFLA_IFNAME      3
#define IFA_ADDRESS      1
#define IFA_LOCAL        2
#define IFA_LABEL        3

#define ARPHRD_ETHER     1
#define ARPHRD_LOOPBACK  772

#define IFF_UP           0x1
#define IFF_LOOPBACK     0x8
#define IFF_RUNNING      0x40
#define IFF_BROADCAST    0x2
#define IFF_MULTICAST    0x1000

// Both are four-byte aligned on every architecture Linux supports.
#define NLMSG_ALIGN(n)  (((n) + 3) & ~3)
#define RTA_ALIGN(n)    (((n) + 3) & ~3)

#ifdef _KERNEL_SOCKET_INTERNALS

#define NSOCK       32          // sockets in the system
#define SOCKBUF     4096        // receive buffer per connected socket
#define NBACKLOG    8

enum sockstate {
  SS_FREE = 0,
  SS_UNBOUND,
  SS_BOUND,
  SS_LISTENING,
  SS_CONNECTED,
};

// Every field here is protected by the socket table's single lock in
// kernel/net/unix.c -- there is deliberately no per-socket lock; see the
// comment at the top of that file for why.
struct socket {
  int   ref;
  int   type;
  int   state;
  int   domain;                 // AF_UNIX or AF_INET

  // For AF_INET: the lwIP-backed socket in kernel/net/inet.c. Opaque here so
  // that socket.h does not have to drag lwIP's headers into every file that
  // wants a struct socket.
  void *inet;

  char  name[UNIX_PATH_MAX];    // the bound path, for a listener

  // A connected socket's peer. Writing to a socket appends to the *peer's*
  // buffer, which is what makes one buffer per socket enough for a
  // bidirectional connection.
  struct socket *peer;
  int   peer_closed;

  char  data[SOCKBUF];
  uint  nread, nwrite;

  // Connections waiting to be accepted, on a listener.
  struct socket *queue[NBACKLOG];
  int   nqueue;

  // Socket options that are genuinely honoured. Kept here rather than only in
  // lwIP's pcb because getsockopt has to answer for an AF_UNIX socket too, and
  // because a flag set before bind() has to survive until there is a pcb to
  // apply it to.
  int   o_reuseaddr;
  int   o_keepalive;
  int   o_broadcast;
  int   o_nodelay;
};

#endif