// SPDX-License-Identifier: GPL-2.0-or-later/* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PF_INET protocol family socket handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h>#include <linux/errno.h>#include <linux/types.h>#include <linux/socket.h>#include <linux/in.h>#include <linux/kernel.h>#include <linux/kmod.h>#include <linux/sched.h>#include <linux/timer.h>#include <linux/string.h>#include <linux/sockios.h>#include <linux/net.h>#include <linux/capability.h>#include <linux/fcntl.h>#include <linux/mm.h>#include <linux/interrupt.h>#include <linux/stat.h>#include <linux/init.h>#include <linux/poll.h>#include <linux/netfilter_ipv4.h>#include <linux/random.h>#include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h>#include <linux/igmp.h>#include <linux/inetdevice.h>#include <linux/netdevice.h>#include <net/checksum.h>#include <net/ip.h>#include <net/protocol.h>#include <net/arp.h>#include <net/route.h>#include <net/ip_fib.h>#include <net/inet_connection_sock.h>#include <net/gro.h>#include <net/gso.h>#include <net/tcp.h>#include <net/psp.h>#include <net/udp.h>#include <net/ping.h>#include <linux/skbuff.h>#include <net/sock.h>#include <net/raw.h>#include <net/icmp.h>#include <net/inet_common.h>#include <net/ip_tunnels.h>#include <net/xfrm.h>#include <net/net_namespace.h>#include <net/secure_seq.h>#ifdef CONFIG_IP_MROUTE#include <linux/mroute.h>#endif#include <net/l3mdev.h>#include <net/compat.h>#include <net/rps.h> #include <trace/events/sock.h> /* Keep the definition of IPv6 disable here for now, to avoid annoying linker * issues in case IPv6=m */int disable_ipv6_mod;EXPORT_SYMBOL(disable_ipv6_mod); /* The inetsw table contains everything that inet_create needs to * build a new socket. */static struct list_head inetsw[SOCK_MAX];static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk){ struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); WARN_ON_ONCE(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); psp_sk_assoc_free(sk);}EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk){ struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0;} int __inet_listen_sk(struct sock *sk, int backlog){ unsigned char old_state = sk->sk_state; int err, tcp_fastopen; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk); if (err) return err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } return 0;} /* * Move a socket into listening state. */int inet_listen(struct socket *sock, int backlog){ struct sock *sk = sock->sk; int err = -EINVAL; lock_sock(sk); if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; err = __inet_listen_sk(sk, backlog); out: release_sock(sk); return err;}EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern){ struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) goto out_sk_release; } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) goto out_sk_release; } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) goto out_sk_release; }out: return err;out_rcu_unlock: rcu_read_unlock(); goto out;out_sk_release: sk_common_release(sk); sock->sk = NULL; goto out;} /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */int inet_release(struct socket *sock){ struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0;}EXPORT_SYMBOL(inet_release); int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len){ u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; return __inet_bind(sk, uaddr, addr_len, flags);} int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len){ return inet_bind_sk(sock->sk, uaddr, addr_len);}EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags){ struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);Lines 1–500 of 2056. Load more
// SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PF_INET protocol family socket handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> #include <net/gro.h> #include <net/gso.h> #include <net/tcp.h> #include <net/psp.h> #include <net/udp.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #include <net/l3mdev.h> #include <net/compat.h> #include <net/rps.h> #include <trace/events/sock.h> /* Keep the definition of IPv6 disable here for now, to avoid annoying linker * issues in case IPv6=m */ int disable_ipv6_mod; EXPORT_SYMBOL(disable_ipv6_mod); /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); WARN_ON_ONCE(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); psp_sk_assoc_free(sk); } EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk) { struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; } int __inet_listen_sk(struct sock *sk, int backlog) { unsigned char old_state = sk->sk_state; int err, tcp_fastopen; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk); if (err) return err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } return 0; } /* * Move a socket into listening state. */ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = -EINVAL; lock_sock(sk); if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; err = __inet_listen_sk(sk, backlog); out: release_sock(sk); return err; } EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) goto out_sk_release; } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) goto out_sk_release; } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) goto out_sk_release; } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; out_sk_release: sk_common_release(sk); sock->sk = NULL; goto out; } /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */ int inet_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0; } EXPORT_SYMBOL(inet_release); int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; return __inet_bind(sk, uaddr, addr_len, flags); } int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { return inet_bind_sk(sock->sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);