^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) /* SPDX-License-Identifier: GPL-2.0-or-later */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) * INET An implementation of the TCP/IP protocol suite for the LINUX
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) * operating system. INET is implemented using the BSD Socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) * interface as the means of communication with the user level.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) * Definitions for the AF_INET socket handler.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) * Version: @(#)sock.h 1.0.4 05/13/93
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) * Authors: Ross Biro
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) * Corey Minyard <wf-rch!minyard@relay.EU.net>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) * Florian La Roche <flla@stud.uni-sb.de>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) * Fixes:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) * Alan Cox : Volatiles in skbuff pointers. See
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) * skbuff comments. May be overdone,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) * better to prove they can be removed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) * than the reverse.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) * Alan Cox : Added a zapped field for tcp to note
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) * a socket is reset and must stay shut up
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) * Alan Cox : New fields for options
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) * Pauline Middelink : identd support
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) * Alan Cox : Eliminate low level recv/recvfrom
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) * David S. Miller : New socket lookup architecture.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) * Steve Whitehouse: Default routines for sock_ops
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) * protinfo be just a void pointer, as the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) * protocol specific parts were moved to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) * respective headers and ipv4/v6, etc now
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) * use private slabcaches for its socks
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) * Pedro Hortas : New flags field for socket options
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) #ifndef _SOCK_H
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) #define _SOCK_H
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) #include <linux/hardirq.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) #include <linux/kernel.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) #include <linux/list.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) #include <linux/list_nulls.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) #include <linux/timer.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) #include <linux/cache.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) #include <linux/bitops.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) #include <linux/lockdep.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) #include <linux/netdevice.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) #include <linux/skbuff.h> /* struct sk_buff */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) #include <linux/mm.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) #include <linux/security.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) #include <linux/slab.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51) #include <linux/uaccess.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) #include <linux/page_counter.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) #include <linux/memcontrol.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) #include <linux/static_key.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) #include <linux/sched.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) #include <linux/wait.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) #include <linux/cgroup-defs.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) #include <linux/rbtree.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) #include <linux/filter.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) #include <linux/rculist_nulls.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) #include <linux/poll.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) #include <linux/sockptr.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) #include <linux/atomic.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) #include <linux/refcount.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) #include <net/dst.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) #include <net/checksum.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) #include <net/tcp_states.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) #include <linux/net_tstamp.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) #include <net/l3mdev.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) #include <linux/android_kabi.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) #include <linux/android_vendor.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) * This structure really needs to be cleaned up.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) * Most of it is for TCP, and not used by any of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) * the other protocols.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) /* Define this to get the SOCK_DBG debugging facility. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) #define SOCK_DEBUGGING
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) #ifdef SOCK_DEBUGGING
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) printk(KERN_DEBUG msg); } while (0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) /* Validate arguments and do nothing */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87) static inline __printf(2, 3)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) void SOCK_DEBUG(const struct sock *sk, const char *msg, ...)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93) /* This is the per-socket lock. The spinlock provides a synchronization
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) * between user contexts and software interrupt processing, whereas the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) * mini-semaphore synchronizes multiple users amongst themselves.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) typedef struct {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) spinlock_t slock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) int owned;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) wait_queue_head_t wq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) * We express the mutex-alike socket_lock semantics
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) * to the lock validator by explicitly managing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) * the slock as a lock variant (in addition to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) * the slock itself):
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) #ifdef CONFIG_DEBUG_LOCK_ALLOC
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) struct lockdep_map dep_map;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) } socket_lock_t;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) struct sock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) struct proto;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) struct net;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) typedef __u32 __bitwise __portpair;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) typedef __u64 __bitwise __addrpair;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) * struct sock_common - minimal network layer representation of sockets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) * @skc_daddr: Foreign IPv4 addr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) * @skc_rcv_saddr: Bound local IPv4 addr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) * @skc_hash: hash value used with various protocol lookup tables
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) * @skc_u16hashes: two u16 hash values used by UDP lookup tables
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) * @skc_dport: placeholder for inet_dport/tw_dport
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) * @skc_num: placeholder for inet_num/tw_num
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) * @skc_portpair: __u32 union of @skc_dport & @skc_num
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) * @skc_family: network address family
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) * @skc_state: Connection state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) * @skc_reuse: %SO_REUSEADDR setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) * @skc_reuseport: %SO_REUSEPORT setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) * @skc_ipv6only: socket is IPV6 only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) * @skc_net_refcnt: socket is using net ref counting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) * @skc_bound_dev_if: bound device index if != 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) * @skc_bind_node: bind hash linkage for various protocol lookup tables
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) * @skc_prot: protocol handlers inside a network family
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) * @skc_net: reference to the network namespace of this socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) * @skc_v6_daddr: IPV6 destination address
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) * @skc_v6_rcv_saddr: IPV6 source address
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) * @skc_cookie: socket's cookie value
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) * @skc_node: main hash linkage for various protocol lookup tables
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) * @skc_tx_queue_mapping: tx queue number for this connection
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) * @skc_rx_queue_mapping: rx queue number for this connection
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) * @skc_flags: place holder for sk_flags
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) * @skc_listener: connection request listener socket (aka rsk_listener)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) * [union with @skc_flags]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) * [union with @skc_flags]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) * @skc_incoming_cpu: record/match cpu processing incoming packets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) * [union with @skc_incoming_cpu]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) * [union with @skc_incoming_cpu]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) * @skc_refcnt: reference count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) * This is the minimal network layer representation of sockets, the header
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) * for struct sock and struct inet_timewait_sock.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) struct sock_common {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) * address on 64bit arches : cf INET_MATCH()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) __addrpair skc_addrpair;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) struct {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) __be32 skc_daddr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) __be32 skc_rcv_saddr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) unsigned int skc_hash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) __u16 skc_u16hashes[2];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) /* skc_dport && skc_num must be grouped as well */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) __portpair skc_portpair;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) struct {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) __be16 skc_dport;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) __u16 skc_num;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) unsigned short skc_family;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) volatile unsigned char skc_state;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) unsigned char skc_reuse:4;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) unsigned char skc_reuseport:1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) unsigned char skc_ipv6only:1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) unsigned char skc_net_refcnt:1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) int skc_bound_dev_if;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) struct hlist_node skc_bind_node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) struct hlist_node skc_portaddr_node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) struct proto *skc_prot;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) possible_net_t skc_net;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) #if IS_ENABLED(CONFIG_IPV6)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) struct in6_addr skc_v6_daddr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) struct in6_addr skc_v6_rcv_saddr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) atomic64_t skc_cookie;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) /* following fields are padding to force
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) * offset(struct sock, sk_refcnt) == 128 on 64bit arches
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) * assuming IPV6 is enabled. We use this padding differently
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) * for different kind of 'sockets'
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) unsigned long skc_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) struct sock *skc_listener; /* request_sock */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) * fields between dontcopy_begin/dontcopy_end
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) * are not copied in sock_copy()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) /* private: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) int skc_dontcopy_begin[0];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) /* public: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) struct hlist_node skc_node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) struct hlist_nulls_node skc_nulls_node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) unsigned short skc_tx_queue_mapping;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) #ifdef CONFIG_XPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) unsigned short skc_rx_queue_mapping;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) int skc_incoming_cpu;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) u32 skc_rcv_wnd;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) refcount_t skc_refcnt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) /* private: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) int skc_dontcopy_end[0];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) u32 skc_rxhash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) u32 skc_window_clamp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) /* public: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) struct bpf_local_storage;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) * struct sock - network layer representation of sockets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) * @__sk_common: shared layout with inet_timewait_sock
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) * @sk_lock: synchronizer
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) * @sk_kern_sock: True if sock is using kernel lock classes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) * @sk_rcvbuf: size of receive buffer in bytes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) * @sk_wq: sock wait queue and async head
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) * @sk_rx_dst: receive input route used by early demux
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) * @sk_dst_cache: destination cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) * @sk_dst_pending_confirm: need to confirm neighbour
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) * @sk_policy: flow policy
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) * @sk_rx_skb_cache: cache copy of recently accessed RX skb
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) * @sk_receive_queue: incoming packets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) * @sk_wmem_alloc: transmit queue bytes committed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) * @sk_tsq_flags: TCP Small Queues flags
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) * @sk_write_queue: Packet sending queue
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) * @sk_omem_alloc: "o" is "option" or "other"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) * @sk_wmem_queued: persistent queue size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) * @sk_forward_alloc: space allocated forward
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) * @sk_napi_id: id of the last napi context to receive data for sk
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) * @sk_ll_usec: usecs to busypoll when there is no data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) * @sk_allocation: allocation mode
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) * @sk_pacing_status: Pacing status (requested, handled by sch_fq)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) * @sk_sndbuf: size of send buffer in bytes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) * @__sk_flags_offset: empty field used to determine location of bitfield
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) * @sk_padding: unused element for alignment
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) * @sk_no_check_rx: allow zero checksum in RX packets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) * @sk_route_forced_caps: static, forced route capabilities
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) * (set in tcp_init_sock())
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) * @sk_gso_max_size: Maximum GSO segment size to build
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) * @sk_gso_max_segs: Maximum number of GSO segments
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) * @sk_pacing_shift: scaling factor for TCP Small Queues
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) * @sk_lingertime: %SO_LINGER l_linger setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) * @sk_backlog: always used with the per-socket spinlock held
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) * @sk_callback_lock: used with the callbacks in the end of this struct
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) * @sk_error_queue: rarely used
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) * IPV6_ADDRFORM for instance)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) * @sk_err: last error
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) * @sk_err_soft: errors that don't cause failure but are the cause of a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) * persistent failure not just 'timed out'
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) * @sk_drops: raw/udp drops counter
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) * @sk_ack_backlog: current listen backlog
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) * @sk_max_ack_backlog: listen backlog set in listen()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) * @sk_uid: user id of owner
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) * @sk_priority: %SO_PRIORITY setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) * @sk_type: socket type (%SOCK_STREAM, etc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) * @sk_protocol: which protocol this socket belongs in this network family
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) * @sk_peer_pid: &struct pid for this socket's peer
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) * @sk_peer_cred: %SO_PEERCRED setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) * @sk_rcvlowat: %SO_RCVLOWAT setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) * @sk_rcvtimeo: %SO_RCVTIMEO setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) * @sk_sndtimeo: %SO_SNDTIMEO setting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) * @sk_txhash: computed flow hash for use on transmit
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) * @sk_filter: socket filtering instructions
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) * @sk_timer: sock cleanup timer
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) * @sk_stamp: time stamp of last packet received
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) * @sk_tsflags: SO_TIMESTAMPING socket options
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) * @sk_tskey: counter to disambiguate concurrent tstamp requests
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) * @sk_zckey: counter to order MSG_ZEROCOPY notifications
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) * @sk_socket: Identd and reporting IO signals
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) * @sk_user_data: RPC layer private data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) * @sk_frag: cached page frag
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) * @sk_peek_off: current peek_offset value
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) * @sk_send_head: front of stuff to transmit
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) * @sk_tx_skb_cache: cache copy of recently accessed TX skb
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) * @sk_security: used by security modules
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) * @sk_mark: generic packet mark
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) * @sk_cgrp_data: cgroup data for this cgroup
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) * @sk_memcg: this socket's memory cgroup association
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) * @sk_write_pending: a write to stream socket waits to start
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) * @sk_state_change: callback to indicate change in the state of the sock
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) * @sk_data_ready: callback to indicate there is data to be processed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) * @sk_write_space: callback to indicate there is bf sending space available
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) * @sk_backlog_rcv: callback to process the backlog
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) * @sk_validate_xmit_skb: ptr to an optional validate function
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) * @sk_reuseport_cb: reuseport group container
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) * @sk_rcu: used during RCU grace period
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) * @sk_txtime_report_errors: set report errors mode for SO_TXTIME
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) * @sk_txtime_unused: unused txtime flags
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) struct sock {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) * Now struct inet_timewait_sock also uses sock_common, so please just
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) * don't add nothing before this first member (__sk_common) --acme
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) struct sock_common __sk_common;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) #define sk_node __sk_common.skc_node
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) #define sk_nulls_node __sk_common.skc_nulls_node
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) #define sk_refcnt __sk_common.skc_refcnt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) #ifdef CONFIG_XPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) #define sk_dontcopy_end __sk_common.skc_dontcopy_end
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) #define sk_hash __sk_common.skc_hash
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) #define sk_portpair __sk_common.skc_portpair
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) #define sk_num __sk_common.skc_num
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) #define sk_dport __sk_common.skc_dport
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) #define sk_addrpair __sk_common.skc_addrpair
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) #define sk_daddr __sk_common.skc_daddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) #define sk_rcv_saddr __sk_common.skc_rcv_saddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) #define sk_family __sk_common.skc_family
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) #define sk_state __sk_common.skc_state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) #define sk_reuse __sk_common.skc_reuse
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) #define sk_reuseport __sk_common.skc_reuseport
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) #define sk_ipv6only __sk_common.skc_ipv6only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) #define sk_net_refcnt __sk_common.skc_net_refcnt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) #define sk_bound_dev_if __sk_common.skc_bound_dev_if
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) #define sk_bind_node __sk_common.skc_bind_node
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) #define sk_prot __sk_common.skc_prot
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) #define sk_net __sk_common.skc_net
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382) #define sk_v6_daddr __sk_common.skc_v6_daddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) #define sk_cookie __sk_common.skc_cookie
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) #define sk_incoming_cpu __sk_common.skc_incoming_cpu
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) #define sk_flags __sk_common.skc_flags
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) #define sk_rxhash __sk_common.skc_rxhash
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) socket_lock_t sk_lock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390) atomic_t sk_drops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) int sk_rcvlowat;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) struct sk_buff_head sk_error_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) struct sk_buff *sk_rx_skb_cache;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394) struct sk_buff_head sk_receive_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) * The backlog queue is special, it is always used with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) * the per-socket spinlock held and requires low latency
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) * access. Therefore we special case it's implementation.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) * Note : rmem_alloc is in this structure to fill a hole
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) * on 64bit arches, not because its logically part of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401) * backlog.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) struct {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) atomic_t rmem_alloc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405) int len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) struct sk_buff *head;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) struct sk_buff *tail;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408) } sk_backlog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) #define sk_rmem_alloc sk_backlog.rmem_alloc
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) int sk_forward_alloc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) #ifdef CONFIG_NET_RX_BUSY_POLL
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) unsigned int sk_ll_usec;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) /* ===== mostly read cache line ===== */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415) unsigned int sk_napi_id;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) int sk_rcvbuf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) struct sk_filter __rcu *sk_filter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) struct socket_wq __rcu *sk_wq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422) /* private: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) struct socket_wq *sk_wq_raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) /* public: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426) #ifdef CONFIG_XFRM
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) struct xfrm_policy __rcu *sk_policy[2];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) struct dst_entry *sk_rx_dst;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430) struct dst_entry __rcu *sk_dst_cache;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431) atomic_t sk_omem_alloc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) int sk_sndbuf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434) /* ===== cache line for TX ===== */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) int sk_wmem_queued;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) refcount_t sk_wmem_alloc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) unsigned long sk_tsq_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) struct sk_buff *sk_send_head;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) struct rb_root tcp_rtx_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) struct sk_buff *sk_tx_skb_cache;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443) struct sk_buff_head sk_write_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) __s32 sk_peek_off;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445) int sk_write_pending;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) __u32 sk_dst_pending_confirm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) u32 sk_pacing_status; /* see enum sk_pacing */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) long sk_sndtimeo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449) struct timer_list sk_timer;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) __u32 sk_priority;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451) __u32 sk_mark;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) unsigned long sk_pacing_rate; /* bytes per second */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) unsigned long sk_max_pacing_rate;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454) struct page_frag sk_frag;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455) netdev_features_t sk_route_caps;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) netdev_features_t sk_route_nocaps;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457) netdev_features_t sk_route_forced_caps;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) int sk_gso_type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459) unsigned int sk_gso_max_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460) gfp_t sk_allocation;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461) __u32 sk_txhash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) * Because of non atomicity rules, all
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) * changes are protected by socket lock.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) u8 sk_padding : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) sk_kern_sock : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) sk_no_check_tx : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) sk_no_check_rx : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) sk_userlocks : 4;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) u8 sk_pacing_shift;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473) u16 sk_type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) u16 sk_protocol;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) u16 sk_gso_max_segs;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) unsigned long sk_lingertime;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477) struct proto *sk_prot_creator;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478) rwlock_t sk_callback_lock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) int sk_err,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) sk_err_soft;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) u32 sk_ack_backlog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) u32 sk_max_ack_backlog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) kuid_t sk_uid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) #if IS_ENABLED(CONFIG_DEBUG_SPINLOCK) || IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) spinlock_t sk_peer_lock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487) /* sk_peer_lock is in the ANDROID_KABI_RESERVE(1) field below */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489) struct pid *sk_peer_pid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) const struct cred *sk_peer_cred;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) long sk_rcvtimeo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) ktime_t sk_stamp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494) #if BITS_PER_LONG==32
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) seqlock_t sk_stamp_seq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) u16 sk_tsflags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) u8 sk_shutdown;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) u32 sk_tskey;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) atomic_t sk_zckey;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) u8 sk_clockid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) u8 sk_txtime_deadline_mode : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) sk_txtime_report_errors : 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505) sk_txtime_unused : 6;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) struct socket *sk_socket;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) void *sk_user_data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) #ifdef CONFIG_SECURITY
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) void *sk_security;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) struct sock_cgroup_data sk_cgrp_data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513) struct mem_cgroup *sk_memcg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) void (*sk_state_change)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515) void (*sk_data_ready)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516) void (*sk_write_space)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517) void (*sk_error_report)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518) int (*sk_backlog_rcv)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) #ifdef CONFIG_SOCK_VALIDATE_XMIT
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521) struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) struct net_device *dev,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) void (*sk_destruct)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) struct sock_reuseport __rcu *sk_reuseport_cb;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527) #ifdef CONFIG_BPF_SYSCALL
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) struct bpf_local_storage __rcu *sk_bpf_storage;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530) struct rcu_head sk_rcu;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) #if IS_ENABLED(CONFIG_DEBUG_SPINLOCK) || IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533) ANDROID_KABI_RESERVE(1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) ANDROID_KABI_USE(1, spinlock_t sk_peer_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) ANDROID_KABI_RESERVE(2);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) ANDROID_KABI_RESERVE(3);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) ANDROID_KABI_RESERVE(4);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) ANDROID_KABI_RESERVE(5);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) ANDROID_KABI_RESERVE(6);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542) ANDROID_KABI_RESERVE(7);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) ANDROID_KABI_RESERVE(8);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545) ANDROID_OEM_DATA(1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) enum sk_pacing {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) SK_PACING_NONE = 0,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) SK_PACING_NEEDED = 1,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) SK_PACING_FQ = 2,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) /* Pointer stored in sk_user_data might not be suitable for copying
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) * when cloning the socket. For instance, it can point to a reference
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) * counted object. sk_user_data bottom bit is set if pointer must not
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557) * be copied.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) #define SK_USER_DATA_NOCOPY 1UL
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) #define SK_USER_DATA_BPF 2UL /* Managed by BPF */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) static inline bool sk_user_data_is_nocopy(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572) #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574) #define rcu_dereference_sk_user_data(sk) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575) ({ \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576) void *__tmp = rcu_dereference(__sk_user_data((sk))); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577) (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578) })
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579) #define rcu_assign_sk_user_data(sk, ptr) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580) ({ \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581) uintptr_t __tmp = (uintptr_t)(ptr); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582) WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583) rcu_assign_pointer(__sk_user_data((sk)), __tmp); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584) })
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585) #define rcu_assign_sk_user_data_nocopy(sk, ptr) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586) ({ \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587) uintptr_t __tmp = (uintptr_t)(ptr); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589) rcu_assign_pointer(__sk_user_data((sk)), \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590) __tmp | SK_USER_DATA_NOCOPY); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) })
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595) * or not whether his port will be reused by someone else. SK_FORCE_REUSE
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596) * on a socket means that the socket will reuse everybody else's port
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597) * without looking at the other's sk_reuse value.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600) #define SK_NO_REUSE 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) #define SK_CAN_REUSE 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) #define SK_FORCE_REUSE 2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) int sk_set_peek_off(struct sock *sk, int val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606) static inline int sk_peek_offset(struct sock *sk, int flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) if (unlikely(flags & MSG_PEEK)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609) return READ_ONCE(sk->sk_peek_off);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615) static inline void sk_peek_offset_bwd(struct sock *sk, int val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617) s32 off = READ_ONCE(sk->sk_peek_off);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619) if (unlikely(off >= 0)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620) off = max_t(s32, off - val, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621) WRITE_ONCE(sk->sk_peek_off, off);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) static inline void sk_peek_offset_fwd(struct sock *sk, int val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627) sk_peek_offset_bwd(sk, -val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631) * Hashed lists helper routines
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633) static inline struct sock *sk_entry(const struct hlist_node *node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635) return hlist_entry(node, struct sock, sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638) static inline struct sock *__sk_head(const struct hlist_head *head)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640) return hlist_entry(head->first, struct sock, sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643) static inline struct sock *sk_head(const struct hlist_head *head)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645) return hlist_empty(head) ? NULL : __sk_head(head);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648) static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650) return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653) static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 657)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 658) static inline struct sock *sk_next(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 659) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 660) return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 661) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 662)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 663) static inline struct sock *sk_nulls_next(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 664) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 665) return (!is_a_nulls(sk->sk_nulls_node.next)) ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 666) hlist_nulls_entry(sk->sk_nulls_node.next,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 667) struct sock, sk_nulls_node) :
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 668) NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 669) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 670)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 671) static inline bool sk_unhashed(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 672) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 673) return hlist_unhashed(&sk->sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 674) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 675)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 676) static inline bool sk_hashed(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 677) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 678) return !sk_unhashed(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 679) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 680)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 681) static inline void sk_node_init(struct hlist_node *node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 682) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 683) node->pprev = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 684) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 685)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 686) static inline void sk_nulls_node_init(struct hlist_nulls_node *node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 687) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 688) node->pprev = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 689) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 690)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 691) static inline void __sk_del_node(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 692) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 693) __hlist_del(&sk->sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 694) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 695)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 696) /* NB: equivalent to hlist_del_init_rcu */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 697) static inline bool __sk_del_node_init(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 698) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 699) if (sk_hashed(sk)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 700) __sk_del_node(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 701) sk_node_init(&sk->sk_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 702) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 703) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 704) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 705) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 706)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 707) /* Grab socket reference count. This operation is valid only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 708) when sk is ALREADY grabbed f.e. it is found in hash table
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 709) or a list and the lookup is made under lock preventing hash table
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 710) modifications.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 711) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 712)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 713) static __always_inline void sock_hold(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 714) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 715) refcount_inc(&sk->sk_refcnt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 716) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 717)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 718) /* Ungrab socket in the context, which assumes that socket refcnt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 719) cannot hit zero, f.e. it is true in context of any socketcall.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 720) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 721) static __always_inline void __sock_put(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 722) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 723) refcount_dec(&sk->sk_refcnt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 724) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 725)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 726) static inline bool sk_del_node_init(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 727) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 728) bool rc = __sk_del_node_init(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 729)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 730) if (rc) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 731) /* paranoid for a while -acme */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 732) WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 733) __sock_put(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 734) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 735) return rc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 736) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 737) #define sk_del_node_init_rcu(sk) sk_del_node_init(sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 738)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 739) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 740) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 741) if (sk_hashed(sk)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 742) hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 743) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 744) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 745) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 746) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 747)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 748) static inline bool sk_nulls_del_node_init_rcu(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 749) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 750) bool rc = __sk_nulls_del_node_init_rcu(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 751)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 752) if (rc) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 753) /* paranoid for a while -acme */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 754) WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 755) __sock_put(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 756) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 757) return rc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 758) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 759)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 760) static inline void __sk_add_node(struct sock *sk, struct hlist_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 761) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 762) hlist_add_head(&sk->sk_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 763) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 764)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 765) static inline void sk_add_node(struct sock *sk, struct hlist_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 766) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 767) sock_hold(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 768) __sk_add_node(sk, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 769) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 770)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 771) static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 772) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 773) sock_hold(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 774) if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 775) sk->sk_family == AF_INET6)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 776) hlist_add_tail_rcu(&sk->sk_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 777) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 778) hlist_add_head_rcu(&sk->sk_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 779) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 780)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 781) static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 782) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 783) sock_hold(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 784) hlist_add_tail_rcu(&sk->sk_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 785) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 786)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 787) static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 788) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 789) hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 790) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 791)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 792) static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 793) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 794) hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 795) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 796)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 797) static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 798) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 799) sock_hold(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 800) __sk_nulls_add_node_rcu(sk, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 801) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 802)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 803) static inline void __sk_del_bind_node(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 804) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 805) __hlist_del(&sk->sk_bind_node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 806) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 807)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 808) static inline void sk_add_bind_node(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 809) struct hlist_head *list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 810) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 811) hlist_add_head(&sk->sk_bind_node, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 812) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 813)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 814) #define sk_for_each(__sk, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 815) hlist_for_each_entry(__sk, list, sk_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 816) #define sk_for_each_rcu(__sk, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 817) hlist_for_each_entry_rcu(__sk, list, sk_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 818) #define sk_nulls_for_each(__sk, node, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 819) hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 820) #define sk_nulls_for_each_rcu(__sk, node, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 821) hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 822) #define sk_for_each_from(__sk) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 823) hlist_for_each_entry_from(__sk, sk_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 824) #define sk_nulls_for_each_from(__sk, node) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 825) if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 826) hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 827) #define sk_for_each_safe(__sk, tmp, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 828) hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 829) #define sk_for_each_bound(__sk, list) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 830) hlist_for_each_entry(__sk, list, sk_bind_node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 831)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 832) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 833) * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 834) * @tpos: the type * to use as a loop cursor.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 835) * @pos: the &struct hlist_node to use as a loop cursor.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 836) * @head: the head for your list.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 837) * @offset: offset of hlist_node within the struct.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 838) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 839) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 840) #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 841) for (pos = rcu_dereference(hlist_first_rcu(head)); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 842) pos != NULL && \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 843) ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 844) pos = rcu_dereference(hlist_next_rcu(pos)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 845)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 846) static inline struct user_namespace *sk_user_ns(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 847) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 848) /* Careful only use this in a context where these parameters
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 849) * can not change and must all be valid, such as recvmsg from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 850) * userspace.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 851) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 852) return sk->sk_socket->file->f_cred->user_ns;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 853) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 854)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 855) /* Sock flags */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 856) enum sock_flags {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 857) SOCK_DEAD,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 858) SOCK_DONE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 859) SOCK_URGINLINE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 860) SOCK_KEEPOPEN,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 861) SOCK_LINGER,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 862) SOCK_DESTROY,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 863) SOCK_BROADCAST,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 864) SOCK_TIMESTAMP,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 865) SOCK_ZAPPED,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 866) SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 867) SOCK_DBG, /* %SO_DEBUG setting */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 868) SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 869) SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 870) SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 871) SOCK_MEMALLOC, /* VM depends on this socket for swapping */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 872) SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 873) SOCK_FASYNC, /* fasync() active */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 874) SOCK_RXQ_OVFL,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 875) SOCK_ZEROCOPY, /* buffers from userspace */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 876) SOCK_WIFI_STATUS, /* push wifi status to userspace */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 877) SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 878) * Will use last 4 bytes of packet sent from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 879) * user-space instead.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 880) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 881) SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 882) SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 883) SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 884) SOCK_TXTIME,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 885) SOCK_XDP, /* XDP is attached */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 886) SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 887) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 888)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 889) #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 890)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 891) static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 892) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 893) nsk->sk_flags = osk->sk_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 894) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 895)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 896) static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 897) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 898) __set_bit(flag, &sk->sk_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 899) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 900)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 901) static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 902) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 903) __clear_bit(flag, &sk->sk_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 904) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 905)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 906) static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 907) int valbool)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 908) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 909) if (valbool)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 910) sock_set_flag(sk, bit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 911) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 912) sock_reset_flag(sk, bit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 913) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 914)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 915) static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 916) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 917) return test_bit(flag, &sk->sk_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 918) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 919)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 920) #ifdef CONFIG_NET
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 921) DECLARE_STATIC_KEY_FALSE(memalloc_socks_key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 922) static inline int sk_memalloc_socks(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 923) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 924) return static_branch_unlikely(&memalloc_socks_key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 925) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 926)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 927) void __receive_sock(struct file *file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 928) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 929)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 930) static inline int sk_memalloc_socks(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 931) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 932) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 933) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 934)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 935) static inline void __receive_sock(struct file *file)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 936) { }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 937) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 938)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 939) static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 940) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 941) return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 942) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 943)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 944) static inline void sk_acceptq_removed(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 945) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 946) WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 947) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 948)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 949) static inline void sk_acceptq_added(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 950) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 951) WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 952) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 953)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 954) static inline bool sk_acceptq_is_full(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 955) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 956) return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 957) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 958)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 959) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 960) * Compute minimal free write space needed to queue new packets.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 961) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 962) static inline int sk_stream_min_wspace(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 963) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 964) return READ_ONCE(sk->sk_wmem_queued) >> 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 965) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 966)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 967) static inline int sk_stream_wspace(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 968) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 969) return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 970) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 971)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 972) static inline void sk_wmem_queued_add(struct sock *sk, int val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 973) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 974) WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 975) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 976)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 977) void sk_stream_write_space(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 978)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 979) /* OOB backlog add */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 980) static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 981) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 982) /* dont let skb dst not refcounted, we are going to leave rcu lock */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 983) skb_dst_force(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 984)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 985) if (!sk->sk_backlog.tail)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 986) WRITE_ONCE(sk->sk_backlog.head, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 987) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 988) sk->sk_backlog.tail->next = skb;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 989)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 990) WRITE_ONCE(sk->sk_backlog.tail, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 991) skb->next = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 992) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 993)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 994) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 995) * Take into account size of receive queue and backlog queue
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 996) * Do not take into account this skb truesize,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 997) * to allow even a single big packet to come.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 998) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 999) static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1000) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1001) unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1002)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1003) return qsize > limit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1004) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1005)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1006) /* The per-socket spinlock must be held here. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1007) static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1008) unsigned int limit)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1009) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1010) if (sk_rcvqueues_full(sk, limit))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1011) return -ENOBUFS;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1012)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1013) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1014) * If the skb was allocated from pfmemalloc reserves, only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1015) * allow SOCK_MEMALLOC sockets to use it as this socket is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1016) * helping free memory
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1017) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1018) if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1019) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1020)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1021) __sk_add_backlog(sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1022) sk->sk_backlog.len += skb->truesize;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1023) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1024) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1025)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1026) int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1027)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1028) static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1029) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1030) if (sk_memalloc_socks() && skb_pfmemalloc(skb))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1031) return __sk_backlog_rcv(sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1032)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1033) return sk->sk_backlog_rcv(sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1034) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1035)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1036) static inline void sk_incoming_cpu_update(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1037) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1038) int cpu = raw_smp_processor_id();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1039)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1040) if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1041) WRITE_ONCE(sk->sk_incoming_cpu, cpu);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1042) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1043)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1044) static inline void sock_rps_record_flow_hash(__u32 hash)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1045) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1046) #ifdef CONFIG_RPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1047) struct rps_sock_flow_table *sock_flow_table;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1048)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1049) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1050) sock_flow_table = rcu_dereference(rps_sock_flow_table);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1051) rps_record_sock_flow(sock_flow_table, hash);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1052) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1053) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1054) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1055)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1056) static inline void sock_rps_record_flow(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1057) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1058) #ifdef CONFIG_RPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1059) if (static_branch_unlikely(&rfs_needed)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1060) /* Reading sk->sk_rxhash might incur an expensive cache line
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1061) * miss.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1062) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1063) * TCP_ESTABLISHED does cover almost all states where RFS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1064) * might be useful, and is cheaper [1] than testing :
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1065) * IPv4: inet_sk(sk)->inet_daddr
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1066) * IPv6: ipv6_addr_any(&sk->sk_v6_daddr)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1067) * OR an additional socket flag
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1068) * [1] : sk_state and sk_prot are in the same cache line.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1069) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1070) if (sk->sk_state == TCP_ESTABLISHED)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1071) sock_rps_record_flow_hash(sk->sk_rxhash);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1072) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1073) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1074) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1075)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1076) static inline void sock_rps_save_rxhash(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1077) const struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1078) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1079) #ifdef CONFIG_RPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1080) if (unlikely(sk->sk_rxhash != skb->hash))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1081) sk->sk_rxhash = skb->hash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1082) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1083) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1084)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1085) static inline void sock_rps_reset_rxhash(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1086) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1087) #ifdef CONFIG_RPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1088) sk->sk_rxhash = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1089) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1090) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1091)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1092) #define sk_wait_event(__sk, __timeo, __condition, __wait) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1093) ({ int __rc; \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1094) release_sock(__sk); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1095) __rc = __condition; \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1096) if (!__rc) { \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1097) *(__timeo) = wait_woken(__wait, \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1098) TASK_INTERRUPTIBLE, \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1099) *(__timeo)); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1100) } \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1101) sched_annotate_sleep(); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1102) lock_sock(__sk); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1103) __rc = __condition; \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1104) __rc; \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1105) })
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1106)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1107) int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1108) int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1109) void sk_stream_wait_close(struct sock *sk, long timeo_p);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1110) int sk_stream_error(struct sock *sk, int flags, int err);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1111) void sk_stream_kill_queues(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1112) void sk_set_memalloc(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1113) void sk_clear_memalloc(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1114)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1115) void __sk_flush_backlog(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1116)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1117) static inline bool sk_flush_backlog(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1118) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1119) if (unlikely(READ_ONCE(sk->sk_backlog.tail))) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1120) __sk_flush_backlog(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1121) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1122) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1123) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1124) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1125)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1126) int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1127)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1128) struct request_sock_ops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1129) struct timewait_sock_ops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1130) struct inet_hashinfo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1131) struct raw_hashinfo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1132) struct smc_hashinfo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1133) struct module;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1134)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1135) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1136) * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1137) * un-modified. Special care is taken when initializing object to zero.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1138) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1139) static inline void sk_prot_clear_nulls(struct sock *sk, int size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1140) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1141) if (offsetof(struct sock, sk_node.next) != 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1142) memset(sk, 0, offsetof(struct sock, sk_node.next));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1143) memset(&sk->sk_node.pprev, 0,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1144) size - offsetof(struct sock, sk_node.pprev));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1145) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1146)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1147) /* Networking protocol blocks we attach to sockets.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1148) * socket layer -> transport layer interface
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1149) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1150) struct proto {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1151) void (*close)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1152) long timeout);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1153) int (*pre_connect)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1154) struct sockaddr *uaddr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1155) int addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1156) int (*connect)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1157) struct sockaddr *uaddr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1158) int addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1159) int (*disconnect)(struct sock *sk, int flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1160)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1161) struct sock * (*accept)(struct sock *sk, int flags, int *err,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1162) bool kern);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1163)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1164) int (*ioctl)(struct sock *sk, int cmd,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1165) unsigned long arg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1166) int (*init)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1167) void (*destroy)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1168) void (*shutdown)(struct sock *sk, int how);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1169) int (*setsockopt)(struct sock *sk, int level,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1170) int optname, sockptr_t optval,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1171) unsigned int optlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1172) int (*getsockopt)(struct sock *sk, int level,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1173) int optname, char __user *optval,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1174) int __user *option);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1175) void (*keepalive)(struct sock *sk, int valbool);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1176) #ifdef CONFIG_COMPAT
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1177) int (*compat_ioctl)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1178) unsigned int cmd, unsigned long arg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1179) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1180) int (*sendmsg)(struct sock *sk, struct msghdr *msg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1181) size_t len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1182) int (*recvmsg)(struct sock *sk, struct msghdr *msg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1183) size_t len, int noblock, int flags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1184) int *addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1185) int (*sendpage)(struct sock *sk, struct page *page,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1186) int offset, size_t size, int flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1187) int (*bind)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1188) struct sockaddr *addr, int addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1189) int (*bind_add)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1190) struct sockaddr *addr, int addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1191)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1192) int (*backlog_rcv) (struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1193) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1194)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1195) void (*release_cb)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1196)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1197) /* Keeping track of sk's, looking them up, and port selection methods. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1198) int (*hash)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1199) void (*unhash)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1200) void (*rehash)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1201) int (*get_port)(struct sock *sk, unsigned short snum);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1202)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1203) /* Keeping track of sockets in use */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1204) #ifdef CONFIG_PROC_FS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1205) unsigned int inuse_idx;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1206) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1207)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1208) bool (*stream_memory_free)(const struct sock *sk, int wake);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1209) bool (*stream_memory_read)(const struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1210) /* Memory pressure */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1211) void (*enter_memory_pressure)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1212) void (*leave_memory_pressure)(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1213) atomic_long_t *memory_allocated; /* Current allocated memory. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1214) struct percpu_counter *sockets_allocated; /* Current number of sockets. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1215) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1216) * Pressure flag: try to collapse.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1217) * Technical note: it is used by multiple contexts non atomically.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1218) * All the __sk_mem_schedule() is of this nature: accounting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1219) * is strict, actions are advisory and have some latency.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1220) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1221) unsigned long *memory_pressure;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1222) long *sysctl_mem;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1223)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1224) int *sysctl_wmem;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1225) int *sysctl_rmem;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1226) u32 sysctl_wmem_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1227) u32 sysctl_rmem_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1228)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1229) int max_header;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1230) bool no_autobind;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1231)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1232) struct kmem_cache *slab;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1233) unsigned int obj_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1234) slab_flags_t slab_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1235) unsigned int useroffset; /* Usercopy region offset */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1236) unsigned int usersize; /* Usercopy region size */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1237)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1238) struct percpu_counter *orphan_count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1239)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1240) struct request_sock_ops *rsk_prot;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1241) struct timewait_sock_ops *twsk_prot;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1242)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1243) union {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1244) struct inet_hashinfo *hashinfo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1245) struct udp_table *udp_table;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1246) struct raw_hashinfo *raw_hash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1247) struct smc_hashinfo *smc_hash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1248) } h;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1249)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1250) struct module *owner;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1251)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1252) char name[32];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1253)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1254) struct list_head node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1255) #ifdef SOCK_REFCNT_DEBUG
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1256) atomic_t socks;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1257) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1258) int (*diag_destroy)(struct sock *sk, int err);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1259) } __randomize_layout;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1260)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1261) int proto_register(struct proto *prot, int alloc_slab);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1262) void proto_unregister(struct proto *prot);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1263) int sock_load_diag_module(int family, int protocol);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1264)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1265) #ifdef SOCK_REFCNT_DEBUG
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1266) static inline void sk_refcnt_debug_inc(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1267) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1268) atomic_inc(&sk->sk_prot->socks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1269) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1270)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1271) static inline void sk_refcnt_debug_dec(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1272) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1273) atomic_dec(&sk->sk_prot->socks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1274) printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1275) sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1276) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1277)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1278) static inline void sk_refcnt_debug_release(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1279) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1280) if (refcount_read(&sk->sk_refcnt) != 1)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1281) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1282) sk->sk_prot->name, sk, refcount_read(&sk->sk_refcnt));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1283) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1284) #else /* SOCK_REFCNT_DEBUG */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1285) #define sk_refcnt_debug_inc(sk) do { } while (0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1286) #define sk_refcnt_debug_dec(sk) do { } while (0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1287) #define sk_refcnt_debug_release(sk) do { } while (0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1288) #endif /* SOCK_REFCNT_DEBUG */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1289)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1290) static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1291) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1292) if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1293) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1294)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1295) return sk->sk_prot->stream_memory_free ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1296) sk->sk_prot->stream_memory_free(sk, wake) : true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1297) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1298)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1299) static inline bool sk_stream_memory_free(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1300) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1301) return __sk_stream_memory_free(sk, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1302) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1303)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1304) static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1305) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1306) return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1307) __sk_stream_memory_free(sk, wake);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1308) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1309)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1310) static inline bool sk_stream_is_writeable(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1311) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1312) return __sk_stream_is_writeable(sk, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1313) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1314)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1315) static inline int sk_under_cgroup_hierarchy(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1316) struct cgroup *ancestor)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1317) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1318) #ifdef CONFIG_SOCK_CGROUP_DATA
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1319) return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1320) ancestor);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1321) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1322) return -ENOTSUPP;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1323) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1324) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1325)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1326) static inline bool sk_has_memory_pressure(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1327) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1328) return sk->sk_prot->memory_pressure != NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1329) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1330)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1331) static inline bool sk_under_memory_pressure(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1332) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1333) if (!sk->sk_prot->memory_pressure)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1334) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1335)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1336) if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1337) mem_cgroup_under_socket_pressure(sk->sk_memcg))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1338) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1339)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1340) return !!*sk->sk_prot->memory_pressure;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1341) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1342)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1343) static inline long
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1344) sk_memory_allocated(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1345) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1346) return atomic_long_read(sk->sk_prot->memory_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1347) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1348)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1349) static inline long
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1350) sk_memory_allocated_add(struct sock *sk, int amt)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1351) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1352) return atomic_long_add_return(amt, sk->sk_prot->memory_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1353) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1354)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1355) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1356) sk_memory_allocated_sub(struct sock *sk, int amt)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1357) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1358) atomic_long_sub(amt, sk->sk_prot->memory_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1359) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1360)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1361) static inline void sk_sockets_allocated_dec(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1362) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1363) percpu_counter_dec(sk->sk_prot->sockets_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1364) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1365)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1366) static inline void sk_sockets_allocated_inc(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1367) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1368) percpu_counter_inc(sk->sk_prot->sockets_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1369) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1370)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1371) static inline u64
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1372) sk_sockets_allocated_read_positive(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1373) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1374) return percpu_counter_read_positive(sk->sk_prot->sockets_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1375) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1376)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1377) static inline int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1378) proto_sockets_allocated_sum_positive(struct proto *prot)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1379) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1380) return percpu_counter_sum_positive(prot->sockets_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1381) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1382)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1383) static inline long
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1384) proto_memory_allocated(struct proto *prot)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1385) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1386) return atomic_long_read(prot->memory_allocated);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1387) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1388)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1389) static inline bool
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1390) proto_memory_pressure(struct proto *prot)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1391) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1392) if (!prot->memory_pressure)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1393) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1394) return !!*prot->memory_pressure;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1395) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1396)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1397)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1398) #ifdef CONFIG_PROC_FS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1399) /* Called with local bh disabled */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1400) void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1401) int sock_prot_inuse_get(struct net *net, struct proto *proto);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1402) int sock_inuse_get(struct net *net);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1403) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1404) static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1405) int inc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1406) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1407) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1408) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1409)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1410)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1411) /* With per-bucket locks this operation is not-atomic, so that
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1412) * this version is not worse.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1413) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1414) static inline int __sk_prot_rehash(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1415) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1416) sk->sk_prot->unhash(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1417) return sk->sk_prot->hash(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1418) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1419)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1420) /* About 10 seconds */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1421) #define SOCK_DESTROY_TIME (10*HZ)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1422)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1423) /* Sockets 0-1023 can't be bound to unless you are superuser */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1424) #define PROT_SOCK 1024
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1425)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1426) #define SHUTDOWN_MASK 3
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1427) #define RCV_SHUTDOWN 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1428) #define SEND_SHUTDOWN 2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1429)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1430) #define SOCK_SNDBUF_LOCK 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1431) #define SOCK_RCVBUF_LOCK 2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1432) #define SOCK_BINDADDR_LOCK 4
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1433) #define SOCK_BINDPORT_LOCK 8
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1434)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1435) struct socket_alloc {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1436) struct socket socket;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1437) struct inode vfs_inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1438) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1439)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1440) static inline struct socket *SOCKET_I(struct inode *inode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1441) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1442) return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1443) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1444)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1445) static inline struct inode *SOCK_INODE(struct socket *socket)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1446) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1447) return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1448) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1449)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1450) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1451) * Functions for memory accounting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1452) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1453) int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1454) int __sk_mem_schedule(struct sock *sk, int size, int kind);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1455) void __sk_mem_reduce_allocated(struct sock *sk, int amount);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1456) void __sk_mem_reclaim(struct sock *sk, int amount);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1457)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1458) /* We used to have PAGE_SIZE here, but systems with 64KB pages
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1459) * do not necessarily have 16x time more memory than 4KB ones.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1460) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1461) #define SK_MEM_QUANTUM 4096
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1462) #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1463) #define SK_MEM_SEND 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1464) #define SK_MEM_RECV 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1465)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1466) /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1467) static inline long sk_prot_mem_limits(const struct sock *sk, int index)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1468) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1469) long val = sk->sk_prot->sysctl_mem[index];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1470)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1471) #if PAGE_SIZE > SK_MEM_QUANTUM
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1472) val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1473) #elif PAGE_SIZE < SK_MEM_QUANTUM
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1474) val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1475) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1476) return val;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1477) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1478)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1479) static inline int sk_mem_pages(int amt)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1480) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1481) return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1482) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1483)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1484) static inline bool sk_has_account(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1485) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1486) /* return true if protocol supports memory accounting */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1487) return !!sk->sk_prot->memory_allocated;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1488) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1489)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1490) static inline bool sk_wmem_schedule(struct sock *sk, int size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1491) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1492) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1493) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1494) return size <= sk->sk_forward_alloc ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1495) __sk_mem_schedule(sk, size, SK_MEM_SEND);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1496) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1497)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1498) static inline bool
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1499) sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1500) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1501) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1502) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1503) return size <= sk->sk_forward_alloc ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1504) __sk_mem_schedule(sk, size, SK_MEM_RECV) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1505) skb_pfmemalloc(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1506) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1507)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1508) static inline void sk_mem_reclaim(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1509) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1510) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1511) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1512) if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1513) __sk_mem_reclaim(sk, sk->sk_forward_alloc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1514) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1515)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1516) static inline void sk_mem_reclaim_partial(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1517) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1518) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1519) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1520) if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1521) __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1522) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1523)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1524) static inline void sk_mem_charge(struct sock *sk, int size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1525) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1526) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1527) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1528) sk->sk_forward_alloc -= size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1529) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1530)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1531) static inline void sk_mem_uncharge(struct sock *sk, int size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1532) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1533) if (!sk_has_account(sk))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1534) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1535) sk->sk_forward_alloc += size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1536)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1537) /* Avoid a possible overflow.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1538) * TCP send queues can make this happen, if sk_mem_reclaim()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1539) * is not called and more than 2 GBytes are released at once.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1540) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1541) * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1542) * no need to hold that much forward allocation anyway.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1543) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1544) if (unlikely(sk->sk_forward_alloc >= 1 << 21))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1545) __sk_mem_reclaim(sk, 1 << 20);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1546) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1547)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1548) DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1549) static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1550) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1551) sk_wmem_queued_add(sk, -skb->truesize);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1552) sk_mem_uncharge(sk, skb->truesize);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1553) if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1554) !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1555) skb_ext_reset(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1556) skb_zcopy_clear(skb, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1557) sk->sk_tx_skb_cache = skb;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1558) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1559) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1560) __kfree_skb(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1561) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1562)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1563) static inline void sock_release_ownership(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1564) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1565) if (sk->sk_lock.owned) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1566) sk->sk_lock.owned = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1567)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1568) /* The sk_lock has mutex_unlock() semantics: */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1569) mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1570) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1571) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1572)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1573) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1574) * Macro so as to not evaluate some arguments when
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1575) * lockdep is not enabled.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1576) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1577) * Mark both the sk_lock and the sk_lock.slock as a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1578) * per-address-family lock class.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1579) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1580) #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1581) do { \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1582) sk->sk_lock.owned = 0; \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1583) init_waitqueue_head(&sk->sk_lock.wq); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1584) spin_lock_init(&(sk)->sk_lock.slock); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1585) debug_check_no_locks_freed((void *)&(sk)->sk_lock, \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1586) sizeof((sk)->sk_lock)); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1587) lockdep_set_class_and_name(&(sk)->sk_lock.slock, \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1588) (skey), (sname)); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1589) lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1590) } while (0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1591)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1592) #ifdef CONFIG_LOCKDEP
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1593) static inline bool lockdep_sock_is_held(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1594) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1595) return lockdep_is_held(&sk->sk_lock) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1596) lockdep_is_held(&sk->sk_lock.slock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1597) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1598) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1599)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1600) void lock_sock_nested(struct sock *sk, int subclass);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1601)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1602) static inline void lock_sock(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1603) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1604) lock_sock_nested(sk, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1605) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1606)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1607) void __release_sock(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1608) void release_sock(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1609)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1610) /* BH context may only use the following locking interface. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1611) #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1612) #define bh_lock_sock_nested(__sk) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1613) spin_lock_nested(&((__sk)->sk_lock.slock), \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1614) SINGLE_DEPTH_NESTING)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1615) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1616)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1617) bool lock_sock_fast(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1618) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1619) * unlock_sock_fast - complement of lock_sock_fast
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1620) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1621) * @slow: slow mode
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1622) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1623) * fast unlock socket for user context.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1624) * If slow mode is on, we call regular release_sock()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1625) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1626) static inline void unlock_sock_fast(struct sock *sk, bool slow)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1627) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1628) if (slow)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1629) release_sock(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1630) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1631) spin_unlock_bh(&sk->sk_lock.slock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1632) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1633)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1634) /* Used by processes to "lock" a socket state, so that
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1635) * interrupts and bottom half handlers won't change it
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1636) * from under us. It essentially blocks any incoming
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1637) * packets, so that we won't get any new data or any
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1638) * packets that change the state of the socket.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1639) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1640) * While locked, BH processing will add new packets to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1641) * the backlog queue. This queue is processed by the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1642) * owner of the socket lock right before it is released.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1643) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1644) * Since ~2.3.5 it is also exclusive sleep lock serializing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1645) * accesses from user process context.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1646) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1647)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1648) static inline void sock_owned_by_me(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1649) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1650) #ifdef CONFIG_LOCKDEP
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1651) WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1652) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1653) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1654)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1655) static inline bool sock_owned_by_user(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1656) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1657) sock_owned_by_me(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1658) return sk->sk_lock.owned;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1659) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1660)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1661) static inline bool sock_owned_by_user_nocheck(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1662) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1663) return sk->sk_lock.owned;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1664) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1665)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1666) /* no reclassification while locks are held */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1667) static inline bool sock_allow_reclassification(const struct sock *csk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1668) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1669) struct sock *sk = (struct sock *)csk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1670)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1671) return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1672) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1673)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1674) struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1675) struct proto *prot, int kern);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1676) void sk_free(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1677) void sk_destruct(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1678) struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1679) void sk_free_unlock_clone(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1680)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1681) struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1682) gfp_t priority);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1683) void __sock_wfree(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1684) void sock_wfree(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1685) struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1686) gfp_t priority);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1687) void skb_orphan_partial(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1688) void sock_rfree(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1689) void sock_efree(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1690) #ifdef CONFIG_INET
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1691) void sock_edemux(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1692) void sock_pfree(struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1693) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1694) #define sock_edemux sock_efree
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1695) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1696)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1697) int sock_setsockopt(struct socket *sock, int level, int op,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1698) sockptr_t optval, unsigned int optlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1699)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1700) int sock_getsockopt(struct socket *sock, int level, int op,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1701) char __user *optval, int __user *optlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1702) int sock_gettstamp(struct socket *sock, void __user *userstamp,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1703) bool timeval, bool time32);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1704) struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1705) int noblock, int *errcode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1706) struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1707) unsigned long data_len, int noblock,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1708) int *errcode, int max_page_order);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1709) void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1710) void sock_kfree_s(struct sock *sk, void *mem, int size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1711) void sock_kzfree_s(struct sock *sk, void *mem, int size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1712) void sk_send_sigurg(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1713)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1714) struct sockcm_cookie {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1715) u64 transmit_time;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1716) u32 mark;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1717) u16 tsflags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1718) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1719)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1720) static inline void sockcm_init(struct sockcm_cookie *sockc,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1721) const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1722) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1723) *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1724) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1725)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1726) int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1727) struct sockcm_cookie *sockc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1728) int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1729) struct sockcm_cookie *sockc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1730)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1731) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1732) * Functions to fill in entries in struct proto_ops when a protocol
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1733) * does not implement a particular function.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1734) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1735) int sock_no_bind(struct socket *, struct sockaddr *, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1736) int sock_no_connect(struct socket *, struct sockaddr *, int, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1737) int sock_no_socketpair(struct socket *, struct socket *);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1738) int sock_no_accept(struct socket *, struct socket *, int, bool);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1739) int sock_no_getname(struct socket *, struct sockaddr *, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1740) int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1741) int sock_no_listen(struct socket *, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1742) int sock_no_shutdown(struct socket *, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1743) int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1744) int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1745) int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1746) int sock_no_mmap(struct file *file, struct socket *sock,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1747) struct vm_area_struct *vma);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1748) ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1749) size_t size, int flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1750) ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1751) int offset, size_t size, int flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1752)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1753) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1754) * Functions to fill in entries in struct proto_ops when a protocol
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1755) * uses the inet style.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1756) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1757) int sock_common_getsockopt(struct socket *sock, int level, int optname,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1758) char __user *optval, int __user *optlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1759) int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1760) int flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1761) int sock_common_setsockopt(struct socket *sock, int level, int optname,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1762) sockptr_t optval, unsigned int optlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1763)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1764) void sk_common_release(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1765)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1766) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1767) * Default socket callbacks and setup code
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1768) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1769)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1770) /* Initialise core socket variables */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1771) void sock_init_data(struct socket *sock, struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1772)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1773) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1774) * Socket reference counting postulates.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1775) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1776) * * Each user of socket SHOULD hold a reference count.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1777) * * Each access point to socket (an hash table bucket, reference from a list,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1778) * running timer, skb in flight MUST hold a reference count.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1779) * * When reference count hits 0, it means it will never increase back.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1780) * * When reference count hits 0, it means that no references from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1781) * outside exist to this socket and current process on current CPU
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1782) * is last user and may/should destroy this socket.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1783) * * sk_free is called from any context: process, BH, IRQ. When
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1784) * it is called, socket has no references from outside -> sk_free
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1785) * may release descendant resources allocated by the socket, but
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1786) * to the time when it is called, socket is NOT referenced by any
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1787) * hash tables, lists etc.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1788) * * Packets, delivered from outside (from network or from another process)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1789) * and enqueued on receive/error queues SHOULD NOT grab reference count,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1790) * when they sit in queue. Otherwise, packets will leak to hole, when
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1791) * socket is looked up by one cpu and unhasing is made by another CPU.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1792) * It is true for udp/raw, netlink (leak to receive and error queues), tcp
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1793) * (leak to backlog). Packet socket does all the processing inside
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1794) * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1795) * use separate SMP lock, so that they are prone too.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1796) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1797)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1798) /* Ungrab socket and destroy it, if it was the last reference. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1799) static inline void sock_put(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1800) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1801) if (refcount_dec_and_test(&sk->sk_refcnt))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1802) sk_free(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1803) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1804) /* Generic version of sock_put(), dealing with all sockets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1805) * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1806) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1807) void sock_gen_put(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1808)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1809) int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1810) unsigned int trim_cap, bool refcounted);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1811) static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1812) const int nested)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1813) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1814) return __sk_receive_skb(sk, skb, nested, 1, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1815) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1816)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1817) static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1818) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1819) /* sk_tx_queue_mapping accept only upto a 16-bit value */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1820) if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1821) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1822) sk->sk_tx_queue_mapping = tx_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1823) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1824)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1825) #define NO_QUEUE_MAPPING USHRT_MAX
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1826)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1827) static inline void sk_tx_queue_clear(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1828) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1829) sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1830) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1831)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1832) static inline int sk_tx_queue_get(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1833) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1834) if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1835) return sk->sk_tx_queue_mapping;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1836)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1837) return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1838) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1839)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1840) static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1841) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1842) #ifdef CONFIG_XPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1843) if (skb_rx_queue_recorded(skb)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1844) u16 rx_queue = skb_get_rx_queue(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1845)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1846) if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1847) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1848)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1849) sk->sk_rx_queue_mapping = rx_queue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1850) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1851) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1852) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1853)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1854) static inline void sk_rx_queue_clear(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1855) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1856) #ifdef CONFIG_XPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1857) sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1858) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1859) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1860)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1861) #ifdef CONFIG_XPS
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1862) static inline int sk_rx_queue_get(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1863) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1864) if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1865) return sk->sk_rx_queue_mapping;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1866)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1867) return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1868) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1869) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1870)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1871) static inline void sk_set_socket(struct sock *sk, struct socket *sock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1872) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1873) sk->sk_socket = sock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1874) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1875)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1876) static inline wait_queue_head_t *sk_sleep(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1877) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1878) BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1879) return &rcu_dereference_raw(sk->sk_wq)->wait;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1880) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1881) /* Detach socket from process context.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1882) * Announce socket dead, detach it from wait queue and inode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1883) * Note that parent inode held reference count on this struct sock,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1884) * we do not release it in this function, because protocol
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1885) * probably wants some additional cleanups or even continuing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1886) * to work with this socket (TCP).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1887) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1888) static inline void sock_orphan(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1889) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1890) write_lock_bh(&sk->sk_callback_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1891) sock_set_flag(sk, SOCK_DEAD);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1892) sk_set_socket(sk, NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1893) sk->sk_wq = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1894) write_unlock_bh(&sk->sk_callback_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1895) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1896)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1897) static inline void sock_graft(struct sock *sk, struct socket *parent)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1898) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1899) WARN_ON(parent->sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1900) write_lock_bh(&sk->sk_callback_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1901) rcu_assign_pointer(sk->sk_wq, &parent->wq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1902) parent->sk = sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1903) sk_set_socket(sk, parent);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1904) sk->sk_uid = SOCK_INODE(parent)->i_uid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1905) security_sock_graft(sk, parent);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1906) write_unlock_bh(&sk->sk_callback_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1907) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1908)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1909) kuid_t sock_i_uid(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1910) unsigned long sock_i_ino(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1911)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1912) static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1913) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1914) return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1915) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1916)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1917) static inline u32 net_tx_rndhash(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1918) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1919) u32 v = prandom_u32();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1920)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1921) return v ?: 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1922) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1923)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1924) static inline void sk_set_txhash(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1925) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1926) /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1927) WRITE_ONCE(sk->sk_txhash, net_tx_rndhash());
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1928) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1929)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1930) static inline bool sk_rethink_txhash(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1931) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1932) if (sk->sk_txhash) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1933) sk_set_txhash(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1934) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1935) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1936) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1937) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1938)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1939) static inline struct dst_entry *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1940) __sk_dst_get(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1941) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1942) return rcu_dereference_check(sk->sk_dst_cache,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1943) lockdep_sock_is_held(sk));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1944) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1945)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1946) static inline struct dst_entry *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1947) sk_dst_get(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1948) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1949) struct dst_entry *dst;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1950)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1951) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1952) dst = rcu_dereference(sk->sk_dst_cache);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1953) if (dst && !atomic_inc_not_zero(&dst->__refcnt))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1954) dst = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1955) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1956) return dst;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1957) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1958)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1959) static inline void __dst_negative_advice(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1960) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1961) struct dst_entry *ndst, *dst = __sk_dst_get(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1962)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1963) if (dst && dst->ops->negative_advice) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1964) ndst = dst->ops->negative_advice(dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1965)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1966) if (ndst != dst) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1967) rcu_assign_pointer(sk->sk_dst_cache, ndst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1968) sk_tx_queue_clear(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1969) sk->sk_dst_pending_confirm = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1970) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1971) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1972) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1973)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1974) static inline void dst_negative_advice(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1975) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1976) sk_rethink_txhash(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1977) __dst_negative_advice(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1978) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1979)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1980) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1981) __sk_dst_set(struct sock *sk, struct dst_entry *dst)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1982) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1983) struct dst_entry *old_dst;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1984)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1985) sk_tx_queue_clear(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1986) sk->sk_dst_pending_confirm = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1987) old_dst = rcu_dereference_protected(sk->sk_dst_cache,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1988) lockdep_sock_is_held(sk));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1989) rcu_assign_pointer(sk->sk_dst_cache, dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1990) dst_release(old_dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1991) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1992)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1993) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1994) sk_dst_set(struct sock *sk, struct dst_entry *dst)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1995) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1996) struct dst_entry *old_dst;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1997)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1998) sk_tx_queue_clear(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1999) sk->sk_dst_pending_confirm = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2000) old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2001) dst_release(old_dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2002) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2003)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2004) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2005) __sk_dst_reset(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2006) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2007) __sk_dst_set(sk, NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2008) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2009)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2010) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2011) sk_dst_reset(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2012) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2013) sk_dst_set(sk, NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2014) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2015)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2016) struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2017)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2018) struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2019)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2020) static inline void sk_dst_confirm(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2021) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2022) if (!READ_ONCE(sk->sk_dst_pending_confirm))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2023) WRITE_ONCE(sk->sk_dst_pending_confirm, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2024) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2025)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2026) static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2027) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2028) if (skb_get_dst_pending_confirm(skb)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2029) struct sock *sk = skb->sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2030) unsigned long now = jiffies;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2031)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2032) /* avoid dirtying neighbour */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2033) if (READ_ONCE(n->confirmed) != now)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2034) WRITE_ONCE(n->confirmed, now);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2035) if (sk && READ_ONCE(sk->sk_dst_pending_confirm))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2036) WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2037) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2038) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2039)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2040) bool sk_mc_loop(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2041)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2042) static inline bool sk_can_gso(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2043) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2044) return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2045) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2046)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2047) void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2048)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2049) static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2050) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2051) sk->sk_route_nocaps |= flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2052) sk->sk_route_caps &= ~flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2053) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2054)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2055) static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2056) struct iov_iter *from, char *to,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2057) int copy, int offset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2058) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2059) if (skb->ip_summed == CHECKSUM_NONE) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2060) __wsum csum = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2061) if (!csum_and_copy_from_iter_full(to, copy, &csum, from))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2062) return -EFAULT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2063) skb->csum = csum_block_add(skb->csum, csum, offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2064) } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2065) if (!copy_from_iter_full_nocache(to, copy, from))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2066) return -EFAULT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2067) } else if (!copy_from_iter_full(to, copy, from))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2068) return -EFAULT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2069)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2070) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2071) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2072)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2073) static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2074) struct iov_iter *from, int copy)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2075) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2076) int err, offset = skb->len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2077)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2078) err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2079) copy, offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2080) if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2081) __skb_trim(skb, offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2082)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2083) return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2084) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2085)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2086) static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2087) struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2088) struct page *page,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2089) int off, int copy)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2090) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2091) int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2092)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2093) err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2094) copy, skb->len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2095) if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2096) return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2097)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2098) skb->len += copy;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2099) skb->data_len += copy;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2100) skb->truesize += copy;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2101) sk_wmem_queued_add(sk, copy);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2102) sk_mem_charge(sk, copy);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2103) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2104) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2105)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2106) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2107) * sk_wmem_alloc_get - returns write allocations
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2108) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2109) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2110) * Return: sk_wmem_alloc minus initial offset of one
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2111) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2112) static inline int sk_wmem_alloc_get(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2113) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2114) return refcount_read(&sk->sk_wmem_alloc) - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2115) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2116)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2117) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2118) * sk_rmem_alloc_get - returns read allocations
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2119) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2120) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2121) * Return: sk_rmem_alloc
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2122) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2123) static inline int sk_rmem_alloc_get(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2124) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2125) return atomic_read(&sk->sk_rmem_alloc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2126) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2127)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2128) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2129) * sk_has_allocations - check if allocations are outstanding
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2130) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2131) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2132) * Return: true if socket has write or read allocations
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2133) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2134) static inline bool sk_has_allocations(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2135) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2136) return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2137) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2138)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2139) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2140) * skwq_has_sleeper - check if there are any waiting processes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2141) * @wq: struct socket_wq
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2142) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2143) * Return: true if socket_wq has waiting processes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2144) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2145) * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2146) * barrier call. They were added due to the race found within the tcp code.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2147) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2148) * Consider following tcp code paths::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2149) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2150) * CPU1 CPU2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2151) * sys_select receive packet
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2152) * ... ...
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2153) * __add_wait_queue update tp->rcv_nxt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2154) * ... ...
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2155) * tp->rcv_nxt check sock_def_readable
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2156) * ... {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2157) * schedule rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2158) * wq = rcu_dereference(sk->sk_wq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2159) * if (wq && waitqueue_active(&wq->wait))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2160) * wake_up_interruptible(&wq->wait)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2161) * ...
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2162) * }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2163) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2164) * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2165) * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2166) * could then endup calling schedule and sleep forever if there are no more
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2167) * data on the socket.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2168) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2169) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2170) static inline bool skwq_has_sleeper(struct socket_wq *wq)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2171) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2172) return wq && wq_has_sleeper(&wq->wait);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2173) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2174)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2175) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2176) * sock_poll_wait - place memory barrier behind the poll_wait call.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2177) * @filp: file
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2178) * @sock: socket to wait on
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2179) * @p: poll_table
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2180) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2181) * See the comments in the wq_has_sleeper function.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2182) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2183) static inline void sock_poll_wait(struct file *filp, struct socket *sock,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2184) poll_table *p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2185) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2186) if (!poll_does_not_wait(p)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2187) poll_wait(filp, &sock->wq.wait, p);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2188) /* We need to be sure we are in sync with the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2189) * socket flags modification.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2190) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2191) * This memory barrier is paired in the wq_has_sleeper.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2192) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2193) smp_mb();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2194) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2195) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2196)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2197) static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2198) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2199) /* This pairs with WRITE_ONCE() in sk_set_txhash() */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2200) u32 txhash = READ_ONCE(sk->sk_txhash);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2201)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2202) if (txhash) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2203) skb->l4_hash = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2204) skb->hash = txhash;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2205) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2206) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2207)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2208) void skb_set_owner_w(struct sk_buff *skb, struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2209)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2210) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2211) * Queue a received datagram if it will fit. Stream and sequenced
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2212) * protocols can't normally use this as they need to fit buffers in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2213) * and play with them.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2214) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2215) * Inlined as it's very short and called for pretty much every
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2216) * packet ever received.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2217) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2218) static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2219) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2220) skb_orphan(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2221) skb->sk = sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2222) skb->destructor = sock_rfree;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2223) atomic_add(skb->truesize, &sk->sk_rmem_alloc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2224) sk_mem_charge(sk, skb->truesize);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2225) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2226)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2227) static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2228) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2229) if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2230) skb_orphan(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2231) skb->destructor = sock_efree;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2232) skb->sk = sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2233) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2234) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2235) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2236) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2237)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2238) void sk_reset_timer(struct sock *sk, struct timer_list *timer,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2239) unsigned long expires);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2240)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2241) void sk_stop_timer(struct sock *sk, struct timer_list *timer);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2242)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2243) void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2244)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2245) int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2246) struct sk_buff *skb, unsigned int flags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2247) void (*destructor)(struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2248) struct sk_buff *skb));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2249) int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2250) int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2251)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2252) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2253) struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2254)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2255) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2256) * Recover an error report and clear atomically
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2257) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2258)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2259) static inline int sock_error(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2260) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2261) int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2262)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2263) /* Avoid an atomic operation for the common case.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2264) * This is racy since another cpu/thread can change sk_err under us.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2265) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2266) if (likely(data_race(!sk->sk_err)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2267) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2268)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2269) err = xchg(&sk->sk_err, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2270) return -err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2271) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2272)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2273) static inline unsigned long sock_wspace(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2274) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2275) int amt = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2276)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2277) if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2278) amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2279) if (amt < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2280) amt = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2281) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2282) return amt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2283) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2284)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2285) /* Note:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2286) * We use sk->sk_wq_raw, from contexts knowing this
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2287) * pointer is not NULL and cannot disappear/change.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2288) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2289) static inline void sk_set_bit(int nr, struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2290) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2291) if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2292) !sock_flag(sk, SOCK_FASYNC))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2293) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2294)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2295) set_bit(nr, &sk->sk_wq_raw->flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2296) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2297)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2298) static inline void sk_clear_bit(int nr, struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2299) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2300) if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2301) !sock_flag(sk, SOCK_FASYNC))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2302) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2303)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2304) clear_bit(nr, &sk->sk_wq_raw->flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2305) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2306)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2307) static inline void sk_wake_async(const struct sock *sk, int how, int band)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2308) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2309) if (sock_flag(sk, SOCK_FASYNC)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2310) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2311) sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2312) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2313) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2314) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2315)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2316) /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2317) * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2318) * Note: for send buffers, TCP works better if we can build two skbs at
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2319) * minimum.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2320) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2321) #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2322)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2323) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2324) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2325)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2326) static inline void sk_stream_moderate_sndbuf(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2327) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2328) u32 val;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2329)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2330) if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2331) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2332)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2333) val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2334)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2335) WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2336) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2337)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2338) struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2339) bool force_schedule);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2340)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2341) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2342) * sk_page_frag - return an appropriate page_frag
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2343) * @sk: socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2344) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2345) * Use the per task page_frag instead of the per socket one for
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2346) * optimization when we know that we're in process context and own
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2347) * everything that's associated with %current.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2348) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2349) * Both direct reclaim and page faults can nest inside other
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2350) * socket operations and end up recursing into sk_page_frag()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2351) * while it's already in use: explicitly avoid task page_frag
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2352) * usage if the caller is potentially doing any of them.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2353) * This assumes that page fault handlers use the GFP_NOFS flags.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2354) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2355) * Return: a per task page_frag if context allows that,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2356) * otherwise a per socket one.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2357) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2358) static inline struct page_frag *sk_page_frag(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2359) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2360) if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2361) (__GFP_DIRECT_RECLAIM | __GFP_FS))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2362) return ¤t->task_frag;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2363)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2364) return &sk->sk_frag;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2365) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2366)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2367) bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2368)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2369) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2370) * Default write policy as shown to user space via poll/select/SIGIO
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2371) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2372) static inline bool sock_writeable(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2373) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2374) return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2375) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2376)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2377) static inline gfp_t gfp_any(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2378) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2379) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2380) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2381)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2382) static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2383) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2384) return noblock ? 0 : sk->sk_rcvtimeo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2385) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2386)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2387) static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2388) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2389) return noblock ? 0 : sk->sk_sndtimeo;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2390) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2391)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2392) static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2393) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2394) int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2395)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2396) return v ?: 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2397) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2398)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2399) /* Alas, with timeout socket operations are not restartable.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2400) * Compare this to poll().
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2401) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2402) static inline int sock_intr_errno(long timeo)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2403) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2404) return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2405) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2406)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2407) struct sock_skb_cb {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2408) u32 dropcount;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2409) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2410)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2411) /* Store sock_skb_cb at the end of skb->cb[] so protocol families
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2412) * using skb->cb[] would keep using it directly and utilize its
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2413) * alignement guarantee.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2414) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2415) #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2416) sizeof(struct sock_skb_cb)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2417)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2418) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2419) SOCK_SKB_CB_OFFSET))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2420)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2421) #define sock_skb_cb_check_size(size) \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2422) BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2423)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2424) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2425) sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2426) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2427) SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2428) atomic_read(&sk->sk_drops) : 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2429) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2430)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2431) static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2432) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2433) int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2434)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2435) atomic_add(segs, &sk->sk_drops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2436) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2437)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2438) static inline ktime_t sock_read_timestamp(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2439) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2440) #if BITS_PER_LONG==32
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2441) unsigned int seq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2442) ktime_t kt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2443)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2444) do {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2445) seq = read_seqbegin(&sk->sk_stamp_seq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2446) kt = sk->sk_stamp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2447) } while (read_seqretry(&sk->sk_stamp_seq, seq));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2448)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2449) return kt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2450) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2451) return READ_ONCE(sk->sk_stamp);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2452) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2453) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2454)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2455) static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2456) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2457) #if BITS_PER_LONG==32
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2458) write_seqlock(&sk->sk_stamp_seq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2459) sk->sk_stamp = kt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2460) write_sequnlock(&sk->sk_stamp_seq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2461) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2462) WRITE_ONCE(sk->sk_stamp, kt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2463) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2464) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2465)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2466) void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2467) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2468) void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2469) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2470)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2471) static inline void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2472) sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2473) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2474) ktime_t kt = skb->tstamp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2475) struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2476)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2477) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2478) * generate control messages if
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2479) * - receive time stamping in software requested
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2480) * - software time stamp available and wanted
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2481) * - hardware time stamps available and wanted
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2482) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2483) if (sock_flag(sk, SOCK_RCVTSTAMP) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2484) (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2485) (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2486) (hwtstamps->hwtstamp &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2487) (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2488) __sock_recv_timestamp(msg, sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2489) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2490) sock_write_timestamp(sk, kt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2491)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2492) if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2493) __sock_recv_wifi_status(msg, sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2494) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2495)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2496) void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2497) struct sk_buff *skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2498)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2499) #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2500) static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2501) struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2502) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2503) #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2504) (1UL << SOCK_RCVTSTAMP))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2505) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2506) SOF_TIMESTAMPING_RAW_HARDWARE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2507)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2508) if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2509) __sock_recv_ts_and_drops(msg, sk, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2510) else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2511) sock_write_timestamp(sk, skb->tstamp);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2512) else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2513) sock_write_timestamp(sk, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2514) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2515)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2516) void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2517)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2518) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2519) * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2520) * @sk: socket sending this packet
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2521) * @tsflags: timestamping flags to use
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2522) * @tx_flags: completed with instructions for time stamping
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2523) * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2524) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2525) * Note: callers should take care of initial ``*tx_flags`` value (usually 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2526) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2527) static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2528) __u8 *tx_flags, __u32 *tskey)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2529) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2530) if (unlikely(tsflags)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2531) __sock_tx_timestamp(tsflags, tx_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2532) if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2533) tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2534) *tskey = sk->sk_tskey++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2535) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2536) if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2537) *tx_flags |= SKBTX_WIFI_STATUS;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2538) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2539)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2540) static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2541) __u8 *tx_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2542) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2543) _sock_tx_timestamp(sk, tsflags, tx_flags, NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2544) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2545)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2546) static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2547) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2548) _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2549) &skb_shinfo(skb)->tskey);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2550) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2551)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2552) DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2553) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2554) * sk_eat_skb - Release a skb if it is no longer needed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2555) * @sk: socket to eat this skb from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2556) * @skb: socket buffer to eat
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2557) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2558) * This routine must be called with interrupts disabled or with the socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2559) * locked so that the sk_buff queue operation is ok.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2560) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2561) static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2562) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2563) __skb_unlink(skb, &sk->sk_receive_queue);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2564) if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2565) !sk->sk_rx_skb_cache) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2566) sk->sk_rx_skb_cache = skb;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2567) skb_orphan(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2568) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2569) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2570) __kfree_skb(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2571) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2572)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2573) static inline
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2574) struct net *sock_net(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2575) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2576) return read_pnet(&sk->sk_net);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2577) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2578)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2579) static inline
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2580) void sock_net_set(struct sock *sk, struct net *net)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2581) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2582) write_pnet(&sk->sk_net, net);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2583) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2584)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2585) static inline bool
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2586) skb_sk_is_prefetched(struct sk_buff *skb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2587) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2588) #ifdef CONFIG_INET
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2589) return skb->destructor == sock_pfree;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2590) #else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2591) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2592) #endif /* CONFIG_INET */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2593) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2594)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2595) /* This helper checks if a socket is a full socket,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2596) * ie _not_ a timewait or request socket.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2597) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2598) static inline bool sk_fullsock(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2599) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2600) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2601) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2602)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2603) static inline bool
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2604) sk_is_refcounted(struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2605) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2606) /* Only full sockets have sk->sk_flags. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2607) return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2608) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2609)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2610) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2611) * skb_steal_sock - steal a socket from an sk_buff
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2612) * @skb: sk_buff to steal the socket from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2613) * @refcounted: is set to true if the socket is reference-counted
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2614) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2615) static inline struct sock *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2616) skb_steal_sock(struct sk_buff *skb, bool *refcounted)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2617) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2618) if (skb->sk) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2619) struct sock *sk = skb->sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2620)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2621) *refcounted = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2622) if (skb_sk_is_prefetched(skb))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2623) *refcounted = sk_is_refcounted(sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2624) skb->destructor = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2625) skb->sk = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2626) return sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2627) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2628) *refcounted = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2629) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2630) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2631)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2632) /* Checks if this SKB belongs to an HW offloaded socket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2633) * and whether any SW fallbacks are required based on dev.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2634) * Check decrypted mark in case skb_orphan() cleared socket.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2635) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2636) static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2637) struct net_device *dev)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2638) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2639) #ifdef CONFIG_SOCK_VALIDATE_XMIT
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2640) struct sock *sk = skb->sk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2641)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2642) if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2643) skb = sk->sk_validate_xmit_skb(sk, dev, skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2644) #ifdef CONFIG_TLS_DEVICE
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2645) } else if (unlikely(skb->decrypted)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2646) pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2647) kfree_skb(skb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2648) skb = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2649) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2650) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2651) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2652)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2653) return skb;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2654) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2655)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2656) /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2657) * SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2658) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2659) static inline bool sk_listener(const struct sock *sk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2660) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2661) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2662) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2663)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2664) void sock_enable_timestamp(struct sock *sk, enum sock_flags flag);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2665) int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2666) int type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2667)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2668) bool sk_ns_capable(const struct sock *sk,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2669) struct user_namespace *user_ns, int cap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2670) bool sk_capable(const struct sock *sk, int cap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2671) bool sk_net_capable(const struct sock *sk, int cap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2672)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2673) void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2674)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2675) /* Take into consideration the size of the struct sk_buff overhead in the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2676) * determination of these values, since that is non-constant across
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2677) * platforms. This makes socket queueing behavior and performance
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2678) * not depend upon such differences.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2679) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2680) #define _SK_MEM_PACKETS 256
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2681) #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2682) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2683) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2684)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2685) extern __u32 sysctl_wmem_max;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2686) extern __u32 sysctl_rmem_max;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2687)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2688) extern int sysctl_tstamp_allow_data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2689) extern int sysctl_optmem_max;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2690)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2691) extern __u32 sysctl_wmem_default;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2692) extern __u32 sysctl_rmem_default;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2693)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2694) #define SKB_FRAG_PAGE_ORDER get_order(32768)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2695) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2696)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2697) static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2698) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2699) /* Does this proto have per netns sysctl_wmem ? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2700) if (proto->sysctl_wmem_offset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2701) return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2702)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2703) return *proto->sysctl_wmem;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2704) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2705)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2706) static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2707) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2708) /* Does this proto have per netns sysctl_rmem ? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2709) if (proto->sysctl_rmem_offset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2710) return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2711)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2712) return *proto->sysctl_rmem;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2713) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2714)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2715) /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2716) * Some wifi drivers need to tweak it to get more chunks.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2717) * They can use this helper from their ndo_start_xmit()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2718) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2719) static inline void sk_pacing_shift_update(struct sock *sk, int val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2720) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2721) if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2722) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2723) WRITE_ONCE(sk->sk_pacing_shift, val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2724) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2725)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2726) /* if a socket is bound to a device, check that the given device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2727) * index is either the same or that the socket is bound to an L3
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2728) * master device and the given device index is also enslaved to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2729) * that L3 master
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2730) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2731) static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2732) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2733) int mdif;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2734)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2735) if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2736) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2737)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2738) mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2739) if (mdif && mdif == sk->sk_bound_dev_if)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2740) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2741)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2742) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2743) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2744)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2745) void sock_def_readable(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2746)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2747) int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2748) void sock_enable_timestamps(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2749) void sock_no_linger(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2750) void sock_set_keepalive(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2751) void sock_set_priority(struct sock *sk, u32 priority);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2752) void sock_set_rcvbuf(struct sock *sk, int val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2753) void sock_set_mark(struct sock *sk, u32 val);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2754) void sock_set_reuseaddr(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2755) void sock_set_reuseport(struct sock *sk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2756) void sock_set_sndtimeo(struct sock *sk, s64 secs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2757)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2758) int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2759)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2760) #endif /* _SOCK_H */
Orange Pi5 kernel
Deprecated Linux kernel 5.10.110 for OrangePi 5/5B/5+ boards
3 Commits
0 Branches
0 Tags