arch/m68k/kernel/syscalltable.S


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402

/*
 *  Copyright (C) 2002, Greg Ungerer (gerg@snapgear.com)
 *
 *  Based on older entry.S files, the following copyrights apply:
 *
 *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
 *                      Kenneth Albanowski <kjahds@kjahds.com>,
 *  Copyright (C) 2000  Lineo Inc. (www.lineo.com) 
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Linux/m68k support by Hamish Macdonald
 */

#include <linux/linkage.h>

#ifndef CONFIG_MMU
#define sys_mmap2		sys_mmap_pgoff
#endif

.section .rodata
ALIGN
ENTRY(sys_call_table)
	.long sys_restart_syscall	/* 0 - old "setup()" system call, used for restarting */
	.long sys_exit
	.long __sys_fork
	.long sys_read
	.long sys_write
	.long sys_open			/* 5 */
	.long sys_close
	.long sys_waitpid
	.long sys_creat
	.long sys_link
	.long sys_unlink		/* 10 */
	.long sys_execve
	.long sys_chdir
	.long sys_time
	.long sys_mknod
	.long sys_chmod			/* 15 */
	.long sys_chown16
	.long sys_ni_syscall		/* old break syscall holder */
	.long sys_stat
	.long sys_lseek
	.long sys_getpid		/* 20 */
	.long sys_mount
	.long sys_oldumount
	.long sys_setuid16
	.long sys_getuid16
	.long sys_stime			/* 25 */
	.long sys_ptrace
	.long sys_alarm
	.long sys_fstat
	.long sys_pause
	.long sys_utime			/* 30 */
	.long sys_ni_syscall		/* old stty syscall holder */
	.long sys_ni_syscall		/* old gtty syscall holder */
	.long sys_access
	.long sys_nice
	.long sys_ni_syscall		/* 35 - old ftime syscall holder */
	.long sys_sync
	.long sys_kill
	.long sys_rename
	.long sys_mkdir
	.long sys_rmdir			/* 40 */
	.long sys_dup
	.long sys_pipe
	.long sys_times
	.long sys_ni_syscall		/* old prof syscall holder */
	.long sys_brk			/* 45 */
	.long sys_setgid16
	.long sys_getgid16
	.long sys_signal
	.long sys_geteuid16
	.long sys_getegid16		/* 50 */
	.long sys_acct
	.long sys_umount		/* recycled never used phys() */
	.long sys_ni_syscall		/* old lock syscall holder */
	.long sys_ioctl
	.long sys_fcntl			/* 55 */
	.long sys_ni_syscall		/* old mpx syscall holder */
	.long sys_setpgid
	.long sys_ni_syscall		/* old ulimit syscall holder */
	.long sys_ni_syscall
	.long sys_umask			/* 60 */
	.long sys_chroot
	.long sys_ustat
	.long sys_dup2
	.long sys_getppid
	.long sys_getpgrp		/* 65 */
	.long sys_setsid
	.long sys_sigaction
	.long sys_sgetmask
	.long sys_ssetmask
	.long sys_setreuid16		/* 70 */
	.long sys_setregid16
	.long sys_sigsuspend
	.long sys_sigpending
	.long sys_sethostname
	.long sys_setrlimit		/* 75 */
	.long sys_old_getrlimit
	.long sys_getrusage
	.long sys_gettimeofday
	.long sys_settimeofday
	.long sys_getgroups16		/* 80 */
	.long sys_setgroups16
	.long sys_old_select
	.long sys_symlink
	.long sys_lstat
	.long sys_readlink		/* 85 */
	.long sys_uselib
	.long sys_swapon
	.long sys_reboot
	.long sys_old_readdir
	.long sys_old_mmap		/* 90 */
	.long sys_munmap
	.long sys_truncate
	.long sys_ftruncate
	.long sys_fchmod
	.long sys_fchown16		/* 95 */
	.long sys_getpriority
	.long sys_setpriority
	.long sys_ni_syscall		/* old profil syscall holder */
	.long sys_statfs
	.long sys_fstatfs		/* 100 */
	.long sys_ni_syscall		/* ioperm for i386 */
	.long sys_socketcall
	.long sys_syslog
	.long sys_setitimer
	.long sys_getitimer		/* 105 */
	.long sys_newstat
	.long sys_newlstat
	.long sys_newfstat
	.long sys_ni_syscall
	.long sys_ni_syscall		/* 110 - iopl for i386 */
	.long sys_vhangup
	.long sys_ni_syscall		/* obsolete idle() syscall */
	.long sys_ni_syscall		/* vm86old for i386 */
	.long sys_wait4
	.long sys_swapoff		/* 115 */
	.long sys_sysinfo
	.long sys_ipc
	.long sys_fsync
	.long sys_sigreturn
	.long __sys_clone		/* 120 */
	.long sys_setdomainname
	.long sys_newuname
	.long sys_cacheflush		/* modify_ldt for i386 */
	.long sys_adjtimex
	.long sys_mprotect		/* 125 */
	.long sys_sigprocmask
	.long sys_ni_syscall		/* old "create_module" */
	.long sys_init_module
	.long sys_delete_module
	.long sys_ni_syscall		/* 130 - old "get_kernel_syms" */
	.long sys_quotactl
	.long sys_getpgid
	.long sys_fchdir
	.long sys_bdflush
	.long sys_sysfs			/* 135 */
	.long sys_personality
	.long sys_ni_syscall		/* for afs_syscall */
	.long sys_setfsuid16
	.long sys_setfsgid16
	.long sys_llseek		/* 140 */
	.long sys_getdents
	.long sys_select
	.long sys_flock
	.long sys_msync
	.long sys_readv			/* 145 */
	.long sys_writev
	.long sys_getsid
	.long sys_fdatasync
	.long sys_sysctl
	.long sys_mlock			/* 150 */
	.long sys_munlock
	.long sys_mlockall
	.long sys_munlockall
	.long sys_sched_setparam
	.long sys_sched_getparam	/* 155 */
	.long sys_sched_setscheduler
	.long sys_sched_getscheduler
	.long sys_sched_yield
	.long sys_sched_get_priority_max
	.long sys_sched_get_priority_min  /* 160 */
	.long sys_sched_rr_get_interval
	.long sys_nanosleep
	.long sys_mremap
	.long sys_setresuid16
	.long sys_getresuid16		/* 165 */
	.long sys_getpagesize
	.long sys_ni_syscall		/* old "query_module" */
	.long sys_poll
	.long sys_ni_syscall		/* old nfsservctl */
	.long sys_setresgid16		/* 170 */
	.long sys_getresgid16
	.long sys_prctl
	.long sys_rt_sigreturn
	.long sys_rt_sigaction
	.long sys_rt_sigprocmask	/* 175 */
	.long sys_rt_sigpending
	.long sys_rt_sigtimedwait
	.long sys_rt_sigqueueinfo
	.long sys_rt_sigsuspend
	.long sys_pread64		/* 180 */
	.long sys_pwrite64
	.long sys_lchown16
	.long sys_getcwd
	.long sys_capget
	.long sys_capset		/* 185 */
	.long sys_sigaltstack
	.long sys_sendfile
	.long sys_ni_syscall		/* streams1 */
	.long sys_ni_syscall		/* streams2 */
	.long __sys_vfork		/* 190 */
	.long sys_getrlimit
	.long sys_mmap2
	.long sys_truncate64
	.long sys_ftruncate64
	.long sys_stat64		/* 195 */
	.long sys_lstat64
	.long sys_fstat64
	.long sys_chown
	.long sys_getuid
	.long sys_getgid		/* 200 */
	.long sys_geteuid
	.long sys_getegid
	.long sys_setreuid
	.long sys_setregid
	.long sys_getgroups		/* 205 */
	.long sys_setgroups
	.long sys_fchown
	.long sys_setresuid
	.long sys_getresuid
	.long sys_setresgid		/* 210 */
	.long sys_getresgid
	.long sys_lchown
	.long sys_setuid
	.long sys_setgid
	.long sys_setfsuid		/* 215 */
	.long sys_setfsgid
	.long sys_pivot_root
	.long sys_ni_syscall
	.long sys_ni_syscall
	.long sys_getdents64		/* 220 */
	.long sys_gettid
	.long sys_tkill
	.long sys_setxattr
	.long sys_lsetxattr
	.long sys_fsetxattr		/* 225 */
	.long sys_getxattr
	.long sys_lgetxattr
	.long sys_fgetxattr
	.long sys_listxattr
	.long sys_llistxattr		/* 230 */
	.long sys_flistxattr
	.long sys_removexattr
	.long sys_lremovexattr
	.long sys_fremovexattr
	.long sys_futex			/* 235 */
	.long sys_sendfile64
	.long sys_mincore
	.long sys_madvise
	.long sys_fcntl64
	.long sys_readahead		/* 240 */
	.long sys_io_setup
	.long sys_io_destroy
	.long sys_io_getevents
	.long sys_io_submit
	.long sys_io_cancel		/* 245 */
	.long sys_fadvise64
	.long sys_exit_group
	.long sys_lookup_dcookie
	.long sys_epoll_create
	.long sys_epoll_ctl		/* 250 */
	.long sys_epoll_wait
	.long sys_remap_file_pages
	.long sys_set_tid_address
	.long sys_timer_create
	.long sys_timer_settime		/* 255 */
	.long sys_timer_gettime
	.long sys_timer_getoverrun
	.long sys_timer_delete
	.long sys_clock_settime
	.long sys_clock_gettime		/* 260 */
	.long sys_clock_getres
	.long sys_clock_nanosleep
	.long sys_statfs64
	.long sys_fstatfs64
	.long sys_tgkill		/* 265 */
	.long sys_utimes
	.long sys_fadvise64_64
	.long sys_mbind
	.long sys_get_mempolicy
	.long sys_set_mempolicy		/* 270 */
	.long sys_mq_open
	.long sys_mq_unlink
	.long sys_mq_timedsend
	.long sys_mq_timedreceive
	.long sys_mq_notify		/* 275 */
	.long sys_mq_getsetattr
	.long sys_waitid
	.long sys_ni_syscall		/* for sys_vserver */
	.long sys_add_key
	.long sys_request_key		/* 280 */
	.long sys_keyctl
	.long sys_ioprio_set
	.long sys_ioprio_get
	.long sys_inotify_init
	.long sys_inotify_add_watch	/* 285 */
	.long sys_inotify_rm_watch
	.long sys_migrate_pages
	.long sys_openat
	.long sys_mkdirat
	.long sys_mknodat		/* 290 */
	.long sys_fchownat
	.long sys_futimesat
	.long sys_fstatat64
	.long sys_unlinkat
	.long sys_renameat		/* 295 */
	.long sys_linkat
	.long sys_symlinkat
	.long sys_readlinkat
	.long sys_fchmodat
	.long sys_faccessat		/* 300 */
	.long sys_pselect6
	.long sys_ppoll
	.long sys_unshare
	.long sys_set_robust_list
	.long sys_get_robust_list	/* 305 */
	.long sys_splice
	.long sys_sync_file_range
	.long sys_tee
	.long sys_vmsplice
	.long sys_move_pages		/* 310 */
	.long sys_sched_setaffinity
	.long sys_sched_getaffinity
	.long sys_kexec_load
	.long sys_getcpu
	.long sys_epoll_pwait		/* 315 */
	.long sys_utimensat
	.long sys_signalfd
	.long sys_timerfd_create
	.long sys_eventfd
	.long sys_fallocate		/* 320 */
	.long sys_timerfd_settime
	.long sys_timerfd_gettime
	.long sys_signalfd4
	.long sys_eventfd2
	.long sys_epoll_create1		/* 325 */
	.long sys_dup3
	.long sys_pipe2
	.long sys_inotify_init1
	.long sys_preadv
	.long sys_pwritev		/* 330 */
	.long sys_rt_tgsigqueueinfo
	.long sys_perf_event_open
	.long sys_get_thread_area
	.long sys_set_thread_area
	.long sys_atomic_cmpxchg_32	/* 335 */
	.long sys_atomic_barrier
	.long sys_fanotify_init
	.long sys_fanotify_mark
	.long sys_prlimit64
	.long sys_name_to_handle_at	/* 340 */
	.long sys_open_by_handle_at
	.long sys_clock_adjtime
	.long sys_syncfs
	.long sys_setns
	.long sys_process_vm_readv	/* 345 */
	.long sys_process_vm_writev
	.long sys_kcmp
	.long sys_finit_module
	.long sys_sched_setattr
	.long sys_sched_getattr		/* 350 */
	.long sys_renameat2
	.long sys_getrandom
	.long sys_memfd_create
	.long sys_bpf
	.long sys_execveat		/* 355 */
	.long sys_socket
	.long sys_socketpair
	.long sys_bind
	.long sys_connect
	.long sys_listen		/* 360 */
	.long sys_accept4
	.long sys_getsockopt
	.long sys_setsockopt
	.long sys_getsockname
	.long sys_getpeername		/* 365 */
	.long sys_sendto
	.long sys_sendmsg
	.long sys_recvfrom
	.long sys_recvmsg
	.long sys_shutdown		/* 370 */
	.long sys_recvmmsg
	.long sys_sendmmsg
	.long sys_userfaultfd
	.long sys_membarrier
	.long sys_mlock2		/* 375 */
	.long sys_copy_file_range
	.long sys_preadv2
	.long sys_pwritev2
	.long sys_statx
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for the AF_INET socket handler.
 *
 * Version:	@(#)sock.h	1.0.4	05/13/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche <flla@stud.uni-sb.de>
 *
 * Fixes:
 *		Alan Cox	:	Volatiles in skbuff pointers. See
 *					skbuff comments. May be overdone,
 *					better to prove they can be removed
 *					than the reverse.
 *		Alan Cox	:	Added a zapped field for tcp to note
 *					a socket is reset and must stay shut up
 *		Alan Cox	:	New fields for options
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Eliminate low level recv/recvfrom
 *		David S. Miller	:	New socket lookup architecture.
 *              Steve Whitehouse:       Default routines for sock_ops
 *              Arnaldo C. Melo :	removed net_pinfo, tp_pinfo and made
 *              			protinfo be just a void pointer, as the
 *              			protocol specific parts were moved to
 *              			respective headers and ipv4/v6, etc now
 *              			use private slabcaches for its socks
 *              Pedro Hortas	:	New flags field for socket options
 *
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */
#ifndef _SOCK_H
#define _SOCK_H

#include <linux/hardirq.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/list_nulls.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>	/* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/memcontrol.h>
#include <linux/res_counter.h>

#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>

#include <linux/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>

struct cgroup;
struct cgroup_subsys;
#ifdef CONFIG_NET
int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss);
#else
static inline
int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
{
	return 0;
}
static inline
void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
{
}
#endif
/*
 * This structure really needs to be cleaned up.
 * Most of it is for TCP, and not used by any of
 * the other protocols.
 */

/* Define this to get the SOCK_DBG debugging facility. */
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
					printk(KERN_DEBUG msg); } while (0)
#else
/* Validate arguments and do nothing */
static inline __printf(2, 3)
void SOCK_DEBUG(struct sock *sk, const char *msg, ...)
{
}
#endif

/* This is the per-socket lock.  The spinlock provides a synchronization
 * between user contexts and software interrupt processing, whereas the
 * mini-semaphore synchronizes multiple users amongst themselves.
 */
typedef struct {
	spinlock_t		slock;
	int			owned;
	wait_queue_head_t	wq;
	/*
	 * We express the mutex-alike socket_lock semantics
	 * to the lock validator by explicitly managing
	 * the slock as a lock variant (in addition to
	 * the slock itself):
	 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} socket_lock_t;

struct sock;
struct proto;
struct net;

/**
 *	struct sock_common - minimal network layer representation of sockets
 *	@skc_daddr: Foreign IPv4 addr
 *	@skc_rcv_saddr: Bound local IPv4 addr
 *	@skc_hash: hash value used with various protocol lookup tables
 *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
 *	@skc_family: network address family
 *	@skc_state: Connection state
 *	@skc_reuse: %SO_REUSEADDR setting
 *	@skc_bound_dev_if: bound device index if != 0
 *	@skc_bind_node: bind hash linkage for various protocol lookup tables
 *	@skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
 *	@skc_prot: protocol handlers inside a network family
 *	@skc_net: reference to the network namespace of this socket
 *	@skc_node: main hash linkage for various protocol lookup tables
 *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
 *	@skc_tx_queue_mapping: tx queue number for this connection
 *	@skc_refcnt: reference count
 *
 *	This is the minimal network layer representation of sockets, the header
 *	for struct sock and struct inet_timewait_sock.
 */
struct sock_common {
	/* skc_daddr and skc_rcv_saddr must be grouped :
	 * cf INET_MATCH() and INET_TW_MATCH()
	 */
	__be32			skc_daddr;
	__be32			skc_rcv_saddr;

	union  {
		unsigned int	skc_hash;
		__u16		skc_u16hashes[2];
	};
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	union {
		struct hlist_node	skc_bind_node;
		struct hlist_nulls_node skc_portaddr_node;
	};
	struct proto		*skc_prot;
#ifdef CONFIG_NET_NS
	struct net	 	*skc_net;
#endif
	/*
	 * fields between dontcopy_begin/dontcopy_end
	 * are not copied in sock_copy()
	 */
	/* private: */
	int			skc_dontcopy_begin[0];
	/* public: */
	union {
		struct hlist_node	skc_node;
		struct hlist_nulls_node skc_nulls_node;
	};
	int			skc_tx_queue_mapping;
	atomic_t		skc_refcnt;
	/* private: */
	int                     skc_dontcopy_end[0];
	/* public: */
};

struct cg_proto;
/**
  *	struct sock - network layer representation of sockets
  *	@__sk_common: shared layout with inet_timewait_sock
  *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
  *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
  *	@sk_lock:	synchronizer
  *	@sk_rcvbuf: size of receive buffer in bytes
  *	@sk_wq: sock wait queue and async head
  *	@sk_dst_cache: destination cache
  *	@sk_dst_lock: destination cache lock
  *	@sk_policy: flow policy
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_write_queue: Packet sending queue
  *	@sk_async_wait_queue: DMA copied packets
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_allocation: allocation mode
  *	@sk_sndbuf: size of send buffer in bytes
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
  *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
  *	@sk_gso_max_size: Maximum GSO segment size to build
  *	@sk_lingertime: %SO_LINGER l_linger setting
  *	@sk_backlog: always used with the per-socket spinlock held
  *	@sk_callback_lock: used with the callbacks in the end of this struct
  *	@sk_error_queue: rarely used
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
  *	@sk_err: last error
  *	@sk_err_soft: errors that don't cause failure but are the cause of a
  *		      persistent failure not just 'timed out'
  *	@sk_drops: raw/udp drops counter
  *	@sk_ack_backlog: current listen backlog
  *	@sk_max_ack_backlog: listen backlog set in listen()
  *	@sk_priority: %SO_PRIORITY setting
  *	@sk_type: socket type (%SOCK_STREAM, etc)
  *	@sk_protocol: which protocol this socket belongs in this network family
  *	@sk_peer_pid: &struct pid for this socket's peer
  *	@sk_peer_cred: %SO_PEERCRED setting
  *	@sk_rcvlowat: %SO_RCVLOWAT setting
  *	@sk_rcvtimeo: %SO_RCVTIMEO setting
  *	@sk_sndtimeo: %SO_SNDTIMEO setting
  *	@sk_rxhash: flow hash received from netif layer
  *	@sk_filter: socket filtering instructions
  *	@sk_protinfo: private area, net family specific, when not using slab
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_socket: Identd and reporting IO signals
  *	@sk_user_data: RPC layer private data
  *	@sk_sndmsg_page: cached page for sendmsg
  *	@sk_sndmsg_off: cached offset for sendmsg
  *	@sk_send_head: front of stuff to transmit
  *	@sk_security: used by security modules
  *	@sk_mark: generic packet mark
  *	@sk_classid: this socket's cgroup classid
  *	@sk_cgrp: this socket's cgroup-specific proto data
  *	@sk_write_pending: a write to stream socket waits to start
  *	@sk_state_change: callback to indicate change in the state of the sock
  *	@sk_data_ready: callback to indicate there is data to be processed
  *	@sk_write_space: callback to indicate there is bf sending space available
  *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
  *	@sk_backlog_rcv: callback to process the backlog
  *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
 */
struct sock {
	/*
	 * Now struct inet_timewait_sock also uses sock_common, so please just
	 * don't add nothing before this first member (__sk_common) --acme
	 */
	struct sock_common	__sk_common;
#define sk_node			__sk_common.skc_node
#define sk_nulls_node		__sk_common.skc_nulls_node
#define sk_refcnt		__sk_common.skc_refcnt
#define sk_tx_queue_mapping	__sk_common.skc_tx_queue_mapping

#define sk_dontcopy_begin	__sk_common.skc_dontcopy_begin
#define sk_dontcopy_end		__sk_common.skc_dontcopy_end
#define sk_hash			__sk_common.skc_hash
#define sk_family		__sk_common.skc_family
#define sk_state		__sk_common.skc_state
#define sk_reuse		__sk_common.skc_reuse
#define sk_bound_dev_if		__sk_common.skc_bound_dev_if
#define sk_bind_node		__sk_common.skc_bind_node
#define sk_prot			__sk_common.skc_prot
#define sk_net			__sk_common.skc_net
	socket_lock_t		sk_lock;
	struct sk_buff_head	sk_receive_queue;
	/*
	 * The backlog queue is special, it is always used with
	 * the per-socket spinlock held and requires low latency
	 * access. Therefore we special case it's implementation.
	 * Note : rmem_alloc is in this structure to fill a hole
	 * on 64bit arches, not because its logically part of
	 * backlog.
	 */
	struct {
		atomic_t	rmem_alloc;
		int		len;
		struct sk_buff	*head;
		struct sk_buff	*tail;
	} sk_backlog;
#define sk_rmem_alloc sk_backlog.rmem_alloc
	int			sk_forward_alloc;
#ifdef CONFIG_RPS
	__u32			sk_rxhash;
#endif
	atomic_t		sk_drops;
	int			sk_rcvbuf;

	struct sk_filter __rcu	*sk_filter;
	struct socket_wq __rcu	*sk_wq;

#ifdef CONFIG_NET_DMA
	struct sk_buff_head	sk_async_wait_queue;
#endif

#ifdef CONFIG_XFRM
	struct xfrm_policy	*sk_policy[2];
#endif
	unsigned long 		sk_flags;
	struct dst_entry	*sk_dst_cache;
	spinlock_t		sk_dst_lock;
	atomic_t		sk_wmem_alloc;
	atomic_t		sk_omem_alloc;
	int			sk_sndbuf;
	struct sk_buff_head	sk_write_queue;
	kmemcheck_bitfield_begin(flags);
	unsigned int		sk_shutdown  : 2,
				sk_no_check  : 2,
				sk_userlocks : 4,
				sk_protocol  : 8,
				sk_type      : 16;
	kmemcheck_bitfield_end(flags);
	int			sk_wmem_queued;
	gfp_t			sk_allocation;
	netdev_features_t	sk_route_caps;
	netdev_features_t	sk_route_nocaps;
	int			sk_gso_type;
	unsigned int		sk_gso_max_size;
	int			sk_rcvlowat;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
	struct proto		*sk_prot_creator;
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
	__u32			sk_priority;
#ifdef CONFIG_CGROUPS
	__u32			sk_cgrp_prioidx;
#endif
	struct pid		*sk_peer_pid;
	const struct cred	*sk_peer_cred;
	long			sk_rcvtimeo;
	long			sk_sndtimeo;
	void			*sk_protinfo;
	struct timer_list	sk_timer;
	ktime_t			sk_stamp;
	struct socket		*sk_socket;
	void			*sk_user_data;
	struct page		*sk_sndmsg_page;
	struct sk_buff		*sk_send_head;
	__u32			sk_sndmsg_off;
	int			sk_write_pending;
#ifdef CONFIG_SECURITY
	void			*sk_security;
#endif
	__u32			sk_mark;
	u32			sk_classid;
	struct cg_proto		*sk_cgrp;
	void			(*sk_state_change)(struct sock *sk);
	void			(*sk_data_ready)(struct sock *sk, int bytes);
	void			(*sk_write_space)(struct sock *sk);
	void			(*sk_error_report)(struct sock *sk);
  	int			(*sk_backlog_rcv)(struct sock *sk,
						  struct sk_buff *skb);  
	void                    (*sk_destruct)(struct sock *sk);
};

/*
 * Hashed lists helper routines
 */
static inline struct sock *sk_entry(const struct hlist_node *node)
{
	return hlist_entry(node, struct sock, sk_node);
}

static inline struct sock *__sk_head(const struct hlist_head *head)
{
	return hlist_entry(head->first, struct sock, sk_node);
}

static inline struct sock *sk_head(const struct hlist_head *head)
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
}

static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
}

static inline struct sock *sk_next(const struct sock *sk)
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

static inline struct sock *sk_nulls_next(const struct sock *sk)
{
	return (!is_a_nulls(sk->sk_nulls_node.next)) ?
		hlist_nulls_entry(sk->sk_nulls_node.next,
				  struct sock, sk_nulls_node) :
		NULL;
}

static inline int sk_unhashed(const struct sock *sk)
{
	return hlist_unhashed(&sk->sk_node);
}

static inline int sk_hashed(const struct sock *sk)
{
	return !sk_unhashed(sk);
}

static __inline__ void sk_node_init(struct hlist_node *node)
{
	node->pprev = NULL;
}

static __inline__ void sk_nulls_node_init(struct hlist_nulls_node *node)
{
	node->pprev = NULL;
}

static __inline__ void __sk_del_node(struct sock *sk)
{
	__hlist_del(&sk->sk_node);
}

/* NB: equivalent to hlist_del_init_rcu */
static __inline__ int __sk_del_node_init(struct sock *sk)
{
	if (sk_hashed(sk)) {
		__sk_del_node(sk);
		sk_node_init(&sk->sk_node);
		return 1;
	}
	return 0;
}

/* Grab socket reference count. This operation is valid only
   when sk is ALREADY grabbed f.e. it is found in hash table
   or a list and the lookup is made under lock preventing hash table
   modifications.
 */

static inline void sock_hold(struct sock *sk)
{
	atomic_inc(&sk->sk_refcnt);
}

/* Ungrab socket in the context, which assumes that socket refcnt
   cannot hit zero, f.e. it is true in context of any socketcall.
 */
static inline void __sock_put(struct sock *sk)
{
	atomic_dec(&sk->sk_refcnt);
}

static __inline__ int sk_del_node_init(struct sock *sk)
{
	int rc = __sk_del_node_init(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}
#define sk_del_node_init_rcu(sk)	sk_del_node_init(sk)

static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk)
{
	if (sk_hashed(sk)) {
		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
		return 1;
	}
	return 0;
}

static __inline__ int sk_nulls_del_node_init_rcu(struct sock *sk)
{
	int rc = __sk_nulls_del_node_init_rcu(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}

static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
	hlist_add_head(&sk->sk_node, list);
}

static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	__sk_add_node(sk, list);
}

static __inline__ void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	hlist_add_head_rcu(&sk->sk_node, list);
}

static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
}

static __inline__ void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
	sock_hold(sk);
	__sk_nulls_add_node_rcu(sk, list);
}

static __inline__ void __sk_del_bind_node(struct sock *sk)
{
	__hlist_del(&sk->sk_bind_node);
}

static __inline__ void sk_add_bind_node(struct sock *sk,
					struct hlist_head *list)
{
	hlist_add_head(&sk->sk_bind_node, list);
}

#define sk_for_each(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_node)
#define sk_for_each_rcu(__sk, node, list) \
	hlist_for_each_entry_rcu(__sk, node, list, sk_node)
#define sk_nulls_for_each(__sk, node, list) \
	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
#define sk_nulls_for_each_rcu(__sk, node, list) \
	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
#define sk_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_from(__sk, node, sk_node)
#define sk_nulls_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
		hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
#define sk_for_each_safe(__sk, node, tmp, list) \
	hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
#define sk_for_each_bound(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_bind_node)

/* Sock flags */
enum sock_flags {
	SOCK_DEAD,
	SOCK_DONE,
	SOCK_URGINLINE,
	SOCK_KEEPOPEN,
	SOCK_LINGER,
	SOCK_DESTROY,
	SOCK_BROADCAST,
	SOCK_TIMESTAMP,
	SOCK_ZAPPED,
	SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
	SOCK_DBG, /* %SO_DEBUG setting */
	SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
	SOCK_TIMESTAMPING_SOFTWARE,     /* %SOF_TIMESTAMPING_SOFTWARE */
	SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
	SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
	SOCK_FASYNC, /* fasync() active */
	SOCK_RXQ_OVFL,
	SOCK_ZEROCOPY, /* buffers from userspace */
	SOCK_WIFI_STATUS, /* push wifi status to userspace */
};

static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
{
	nsk->sk_flags = osk->sk_flags;
}

static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
	__set_bit(flag, &sk->sk_flags);
}

static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
	__clear_bit(flag, &sk->sk_flags);
}

static inline int sock_flag(struct sock *sk, enum sock_flags flag)
{
	return test_bit(flag, &sk->sk_flags);
}

static inline void sk_acceptq_removed(struct sock *sk)
{
	sk->sk_ack_backlog--;
}

static inline void sk_acceptq_added(struct sock *sk)
{
	sk->sk_ack_backlog++;
}

static inline int sk_acceptq_is_full(struct sock *sk)
{
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
	return sk->sk_wmem_queued >> 1;
}

static inline int sk_stream_wspace(struct sock *sk)
{
	return sk->sk_sndbuf - sk->sk_wmem_queued;
}

extern void sk_stream_write_space(struct sock *sk);

static inline int sk_stream_memory_free(struct sock *sk)
{
	return sk->sk_wmem_queued < sk->sk_sndbuf;
}

/* OOB backlog add */
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	/* dont let skb dst not refcounted, we are going to leave rcu lock */
	skb_dst_force(skb);

	if (!sk->sk_backlog.tail)
		sk->sk_backlog.head = skb;
	else
		sk->sk_backlog.tail->next = skb;

	sk->sk_backlog.tail = skb;
	skb->next = NULL;
}

/*
 * Take into account size of receive queue and backlog queue
 * Do not take into account this skb truesize,
 * to allow even a single big packet to come.
 */
static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb)
{
	unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);

	return qsize > sk->sk_rcvbuf;
}

/* The per-socket spinlock must be held here. */
static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	if (sk_rcvqueues_full(sk, skb))
		return -ENOBUFS;

	__sk_add_backlog(sk, skb);
	sk->sk_backlog.len += skb->truesize;
	return 0;
}

static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	return sk->sk_backlog_rcv(sk, skb);
}

static inline void sock_rps_record_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_record_sock_flow(sock_flow_table, sk->sk_rxhash);
	rcu_read_unlock();
#endif
}

static inline void sock_rps_reset_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash);
	rcu_read_unlock();
#endif
}

static inline void sock_rps_save_rxhash(struct sock *sk,
					const struct sk_buff *skb)
{
#ifdef CONFIG_RPS
	if (unlikely(sk->sk_rxhash != skb->rxhash)) {
		sock_rps_reset_flow(sk);
		sk->sk_rxhash = skb->rxhash;
	}
#endif
}

static inline void sock_rps_reset_rxhash(struct sock *sk)
{
#ifdef CONFIG_RPS
	sock_rps_reset_flow(sk);
	sk->sk_rxhash = 0;
#endif
}

#define sk_wait_event(__sk, __timeo, __condition)			\
	({	int __rc;						\
		release_sock(__sk);					\
		__rc = __condition;					\
		if (!__rc) {						\
			*(__timeo) = schedule_timeout(*(__timeo));	\
		}							\
		lock_sock(__sk);					\
		__rc = __condition;					\
		__rc;							\
	})

extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
extern int sk_stream_error(struct sock *sk, int flags, int err);
extern void sk_stream_kill_queues(struct sock *sk);

extern int sk_wait_data(struct sock *sk, long *timeo);

struct request_sock_ops;
struct timewait_sock_ops;
struct inet_hashinfo;
struct raw_hashinfo;
struct module;

/* Networking protocol blocks we attach to sockets.
 * socket layer -> transport layer interface
 * transport -> network interface is defined by struct inet_proto
 */
struct proto {
	void			(*close)(struct sock *sk, 
					long timeout);
	int			(*connect)(struct sock *sk,
				        struct sockaddr *uaddr, 
					int addr_len);
	int			(*disconnect)(struct sock *sk, int flags);

	struct sock *		(*accept) (struct sock *sk, int flags, int *err);

	int			(*ioctl)(struct sock *sk, int cmd,
					 unsigned long arg);
	int			(*init)(struct sock *sk);
	void			(*destroy)(struct sock *sk);
	void			(*shutdown)(struct sock *sk, int how);
	int			(*setsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*getsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval, 
					int __user *option);  	 
#ifdef CONFIG_COMPAT
	int			(*compat_setsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*compat_getsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int __user *option);
	int			(*compat_ioctl)(struct sock *sk,
					unsigned int cmd, unsigned long arg);
#endif
	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg, size_t len);
	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg,
					size_t len, int noblock, int flags, 
					int *addr_len);
	int			(*sendpage)(struct sock *sk, struct page *page,
					int offset, size_t size, int flags);
	int			(*bind)(struct sock *sk, 
					struct sockaddr *uaddr, int addr_len);

	int			(*backlog_rcv) (struct sock *sk, 
						struct sk_buff *skb);

	/* Keeping track of sk's, looking them up, and port selection methods. */
	void			(*hash)(struct sock *sk);
	void			(*unhash)(struct sock *sk);
	void			(*rehash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);
	void			(*clear_sk)(struct sock *sk, int size);

	/* Keeping track of sockets in use */
#ifdef CONFIG_PROC_FS
	unsigned int		inuse_idx;
#endif

	/* Memory pressure */
	void			(*enter_memory_pressure)(struct sock *sk);
	atomic_long_t		*memory_allocated;	/* Current allocated memory. */
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
	 * All the __sk_mem_schedule() is of this nature: accounting
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	long			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;
	bool			no_autobind;

	struct kmem_cache	*slab;
	unsigned int		obj_size;
	int			slab_flags;

	struct percpu_counter	*orphan_count;

	struct request_sock_ops	*rsk_prot;
	struct timewait_sock_ops *twsk_prot;

	union {
		struct inet_hashinfo	*hashinfo;
		struct udp_table	*udp_table;
		struct raw_hashinfo	*raw_hash;
	} h;

	struct module		*owner;

	char			name[32];

	struct list_head	node;
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
	/*
	 * cgroup specific init/deinit functions. Called once for all
	 * protocols that implement it, from cgroups populate function.
	 * This function has to setup any files the protocol want to
	 * appear in the kmem cgroup filesystem.
	 */
	int			(*init_cgroup)(struct cgroup *cgrp,
					       struct cgroup_subsys *ss);
	void			(*destroy_cgroup)(struct cgroup *cgrp,
						  struct cgroup_subsys *ss);
	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
};

struct cg_proto {
	void			(*enter_memory_pressure)(struct sock *sk);
	struct res_counter	*memory_allocated;	/* Current allocated memory. */
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
	int			*memory_pressure;
	long			*sysctl_mem;
	/*
	 * memcg field is used to find which memcg we belong directly
	 * Each memcg struct can hold more than one cg_proto, so container_of
	 * won't really cut.
	 *
	 * The elegant solution would be having an inverse function to
	 * proto_cgroup in struct proto, but that means polluting the structure
	 * for everybody, instead of just for memcg users.
	 */
	struct mem_cgroup	*memcg;
};

extern int proto_register(struct proto *prot, int alloc_slab);
extern void proto_unregister(struct proto *prot);

#ifdef SOCK_REFCNT_DEBUG
static inline void sk_refcnt_debug_inc(struct sock *sk)
{
	atomic_inc(&sk->sk_prot->socks);
}

static inline void sk_refcnt_debug_dec(struct sock *sk)
{
	atomic_dec(&sk->sk_prot->socks);
	printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}

inline void sk_refcnt_debug_release(const struct sock *sk)
{
	if (atomic_read(&sk->sk_refcnt) != 1)
		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
		       sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
#define sk_refcnt_debug_dec(sk) do { } while (0)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
extern struct jump_label_key memcg_socket_limit_enabled;
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
					       struct cg_proto *cg_proto)
{
	return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
}
#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
#else
#define mem_cgroup_sockets_enabled 0
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
					       struct cg_proto *cg_proto)
{
	return NULL;
}
#endif


static inline bool sk_has_memory_pressure(const struct sock *sk)
{
	return sk->sk_prot->memory_pressure != NULL;
}

static inline bool sk_under_memory_pressure(const struct sock *sk)
{
	if (!sk->sk_prot->memory_pressure)
		return false;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		return !!*sk->sk_cgrp->memory_pressure;

	return !!*sk->sk_prot->memory_pressure;
}

static inline void sk_leave_memory_pressure(struct sock *sk)
{
	int *memory_pressure = sk->sk_prot->memory_pressure;

	if (!memory_pressure)
		return;

	if (*memory_pressure)
		*memory_pressure = 0;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;
		struct proto *prot = sk->sk_prot;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			if (*cg_proto->memory_pressure)
				*cg_proto->memory_pressure = 0;
	}

}

static inline void sk_enter_memory_pressure(struct sock *sk)
{
	if (!sk->sk_prot->enter_memory_pressure)
		return;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;
		struct proto *prot = sk->sk_prot;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			cg_proto->enter_memory_pressure(sk);
	}

	sk->sk_prot->enter_memory_pressure(sk);
}

static inline long sk_prot_mem_limits(const struct sock *sk, int index)
{
	long *prot = sk->sk_prot->sysctl_mem;
	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		prot = sk->sk_cgrp->sysctl_mem;
	return prot[index];
}

static inline void memcg_memory_allocated_add(struct cg_proto *prot,
					      unsigned long amt,
					      int *parent_status)
{
	struct res_counter *fail;
	int ret;

	ret = res_counter_charge(prot->memory_allocated,
				 amt << PAGE_SHIFT, &fail);

	if (ret < 0)
		*parent_status = OVER_LIMIT;
}

static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
					      unsigned long amt)
{
	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
}

static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
{
	u64 ret;
	ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
	return ret >> PAGE_SHIFT;
}

static inline long
sk_memory_allocated(const struct sock *sk)
{
	struct proto *prot = sk->sk_prot;
	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		return memcg_memory_allocated_read(sk->sk_cgrp);

	return atomic_long_read(prot->memory_allocated);
}

static inline long
sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
		/* update the root cgroup regardless */
		atomic_long_add_return(amt, prot->memory_allocated);
		return memcg_memory_allocated_read(sk->sk_cgrp);
	}

	return atomic_long_add_return(amt, prot->memory_allocated);
}

static inline void
sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp &&
	    parent_status != OVER_LIMIT) /* Otherwise was uncharged already */
		memcg_memory_allocated_sub(sk->sk_cgrp, amt);

	atomic_long_sub(amt, prot->memory_allocated);
}

static inline void sk_sockets_allocated_dec(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			percpu_counter_dec(cg_proto->sockets_allocated);
	}

	percpu_counter_dec(prot->sockets_allocated);
}

static inline void sk_sockets_allocated_inc(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			percpu_counter_inc(cg_proto->sockets_allocated);
	}

	percpu_counter_inc(prot->sockets_allocated);
}

static inline int
sk_sockets_allocated_read_positive(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated);

	return percpu_counter_sum_positive(prot->sockets_allocated);
}

static inline int
proto_sockets_allocated_sum_positive(struct proto *prot)
{
	return percpu_counter_sum_positive(prot->sockets_allocated);
}

static inline long
proto_memory_allocated(struct proto *prot)
{
	return atomic_long_read(prot->memory_allocated);
}

static inline bool
proto_memory_pressure(struct proto *prot)
{
	if (!prot->memory_pressure)
		return false;
	return !!*prot->memory_pressure;
}


#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
extern int sock_prot_inuse_get(struct net *net, struct proto *proto);
#else
static void inline sock_prot_inuse_add(struct net *net, struct proto *prot,
		int inc)
{
}
#endif


/* With per-bucket locks this operation is not-atomic, so that
 * this version is not worse.
 */
static inline void __sk_prot_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	sk->sk_prot->hash(sk);
}

void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);

/* About 10 seconds */
#define SOCK_DESTROY_TIME (10*HZ)

/* Sockets 0-1023 can't be bound to unless you are superuser */
#define PROT_SOCK	1024

#define SHUTDOWN_MASK	3
#define RCV_SHUTDOWN	1
#define SEND_SHUTDOWN	2

#define SOCK_SNDBUF_LOCK	1
#define SOCK_RCVBUF_LOCK	2
#define SOCK_BINDADDR_LOCK	4
#define SOCK_BINDPORT_LOCK	8

/* sock_iocb: used to kick off async processing of socket ios */
struct sock_iocb {
	struct list_head	list;

	int			flags;
	int			size;
	struct socket		*sock;
	struct sock		*sk;
	struct scm_cookie	*scm;
	struct msghdr		*msg, async_msg;
	struct kiocb		*kiocb;
};

static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
{
	return (struct sock_iocb *)iocb->private;
}

static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
{
	return si->kiocb;
}

struct socket_alloc {
	struct socket socket;
	struct inode vfs_inode;
};

static inline struct socket *SOCKET_I(struct inode *inode)
{
	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
}

static inline struct inode *SOCK_INODE(struct socket *socket)
{
	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
}

/*
 * Functions for memory accounting
 */
extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
extern void __sk_mem_reclaim(struct sock *sk);

#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND	0
#define SK_MEM_RECV	1

static inline int sk_mem_pages(int amt)
{
	return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
}

static inline int sk_has_account(struct sock *sk)
{
	/* return true if protocol supports memory accounting */
	return !!sk->sk_prot->memory_allocated;
}

static inline int sk_wmem_schedule(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return 1;
	return size <= sk->sk_forward_alloc ||
		__sk_mem_schedule(sk, size, SK_MEM_SEND);
}

static inline int sk_rmem_schedule(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return 1;
	return size <= sk->sk_forward_alloc ||
		__sk_mem_schedule(sk, size, SK_MEM_RECV);
}

static inline void sk_mem_reclaim(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

static inline void sk_mem_reclaim_partial(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

static inline void sk_mem_charge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc -= size;
}

static inline void sk_mem_uncharge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc += size;
}

static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued -= skb->truesize;
	sk_mem_uncharge(sk, skb->truesize);
	__kfree_skb(skb);
}

/* Used by processes to "lock" a socket state, so that
 * interrupts and bottom half handlers won't change it
 * from under us. It essentially blocks any incoming
 * packets, so that we won't get any new data or any
 * packets that change the state of the socket.
 *
 * While locked, BH processing will add new packets to
 * the backlog queue.  This queue is processed by the
 * owner of the socket lock right before it is released.
 *
 * Since ~2.3.5 it is also exclusive sleep lock serializing
 * accesses from user process context.
 */
#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)

/*
 * Macro so as to not evaluate some arguments when
 * lockdep is not enabled.
 *
 * Mark both the sk_lock and the sk_lock.slock as a
 * per-address-family lock class.
 */
#define sock_lock_init_class_and_name(sk, sname, skey, name, key) 	\
do {									\
	sk->sk_lock.owned = 0;						\
	init_waitqueue_head(&sk->sk_lock.wq);				\
	spin_lock_init(&(sk)->sk_lock.slock);				\
	debug_check_no_locks_freed((void *)&(sk)->sk_lock,		\
			sizeof((sk)->sk_lock));				\
	lockdep_set_class_and_name(&(sk)->sk_lock.slock,		\
		       	(skey), (sname));				\
	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
} while (0)

extern void lock_sock_nested(struct sock *sk, int subclass);

static inline void lock_sock(struct sock *sk)
{
	lock_sock_nested(sk, 0);
}

extern void release_sock(struct sock *sk);

/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
#define bh_lock_sock_nested(__sk) \
				spin_lock_nested(&((__sk)->sk_lock.slock), \
				SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

extern bool lock_sock_fast(struct sock *sk);
/**
 * unlock_sock_fast - complement of lock_sock_fast
 * @sk: socket
 * @slow: slow mode
 *
 * fast unlock socket for user context.
 * If slow mode is on, we call regular release_sock()
 */
static inline void unlock_sock_fast(struct sock *sk, bool slow)
{
	if (slow)
		release_sock(sk);
	else
		spin_unlock_bh(&sk->sk_lock.slock);
}


extern struct sock		*sk_alloc(struct net *net, int family,
					  gfp_t priority,
					  struct proto *prot);
extern void			sk_free(struct sock *sk);
extern void			sk_release_kernel(struct sock *sk);
extern struct sock		*sk_clone_lock(const struct sock *sk,
					       const gfp_t priority);

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
					      gfp_t priority);
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
					      gfp_t priority);
extern void			sock_wfree(struct sk_buff *skb);
extern void			sock_rfree(struct sk_buff *skb);

extern int			sock_setsockopt(struct socket *sock, int level,
						int op, char __user *optval,
						unsigned int optlen);

extern int			sock_getsockopt(struct socket *sock, int level,
						int op, char __user *optval, 
						int __user *optlen);
extern struct sk_buff 		*sock_alloc_send_skb(struct sock *sk,
						     unsigned long size,
						     int noblock,
						     int *errcode);
extern struct sk_buff 		*sock_alloc_send_pskb(struct sock *sk,
						      unsigned long header_len,
						      unsigned long data_len,
						      int noblock,
						      int *errcode);
extern void *sock_kmalloc(struct sock *sk, int size,
			  gfp_t priority);
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);

#ifdef CONFIG_CGROUPS
extern void sock_update_classid(struct sock *sk);
#else
static inline void sock_update_classid(struct sock *sk)
{
}
#endif

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * does not implement a particular function.
 */
extern int                      sock_no_bind(struct socket *, 
					     struct sockaddr *, int);
extern int                      sock_no_connect(struct socket *,
						struct sockaddr *, int, int);
extern int                      sock_no_socketpair(struct socket *,
						   struct socket *);
extern int                      sock_no_accept(struct socket *,
					       struct socket *, int);
extern int                      sock_no_getname(struct socket *,
						struct sockaddr *, int *, int);
extern unsigned int             sock_no_poll(struct file *, struct socket *,
					     struct poll_table_struct *);
extern int                      sock_no_ioctl(struct socket *, unsigned int,
					      unsigned long);
extern int			sock_no_listen(struct socket *, int);
extern int                      sock_no_shutdown(struct socket *, int);
extern int			sock_no_getsockopt(struct socket *, int , int,
						   char __user *, int __user *);
extern int			sock_no_setsockopt(struct socket *, int, int,
						   char __user *, unsigned int);
extern int                      sock_no_sendmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t);
extern int                      sock_no_recvmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t, int);
extern int			sock_no_mmap(struct file *file,
					     struct socket *sock,
					     struct vm_area_struct *vma);
extern ssize_t			sock_no_sendpage(struct socket *sock,
						struct page *page,
						int offset, size_t size, 
						int flags);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * uses the inet style.
 */
extern int sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen);
extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size, int flags);
extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, unsigned int optlen);
extern int compat_sock_common_getsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int __user *optlen);
extern int compat_sock_common_setsockopt(struct socket *sock, int level,
		int optname, char __user *optval, unsigned int optlen);

extern void sk_common_release(struct sock *sk);

/*
 *	Default socket callbacks and setup code
 */
 
/* Initialise core socket variables */
extern void sock_init_data(struct socket *sock, struct sock *sk);

extern void sk_filter_release_rcu(struct rcu_head *rcu);

/**
 *	sk_filter_release - release a socket filter
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */

static inline void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
		call_rcu(&fp->rcu, sk_filter_release_rcu);
}

static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);
	sk_filter_release(fp);
}

static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
	atomic_inc(&fp->refcnt);
	atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
}

/*
 * Socket reference counting postulates.
 *
 * * Each user of socket SHOULD hold a reference count.
 * * Each access point to socket (an hash table bucket, reference from a list,
 *   running timer, skb in flight MUST hold a reference count.
 * * When reference count hits 0, it means it will never increase back.
 * * When reference count hits 0, it means that no references from
 *   outside exist to this socket and current process on current CPU
 *   is last user and may/should destroy this socket.
 * * sk_free is called from any context: process, BH, IRQ. When
 *   it is called, socket has no references from outside -> sk_free
 *   may release descendant resources allocated by the socket, but
 *   to the time when it is called, socket is NOT referenced by any
 *   hash tables, lists etc.
 * * Packets, delivered from outside (from network or from another process)
 *   and enqueued on receive/error queues SHOULD NOT grab reference count,
 *   when they sit in queue. Otherwise, packets will leak to hole, when
 *   socket is looked up by one cpu and unhasing is made by another CPU.
 *   It is true for udp/raw, netlink (leak to receive and error queues), tcp
 *   (leak to backlog). Packet socket does all the processing inside
 *   BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
 *   use separate SMP lock, so that they are prone too.
 */

/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
	if (atomic_dec_and_test(&sk->sk_refcnt))
		sk_free(sk);
}

extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
			  const int nested);

static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
{
	sk->sk_tx_queue_mapping = tx_queue;
}

static inline void sk_tx_queue_clear(struct sock *sk)
{
	sk->sk_tx_queue_mapping = -1;
}

static inline int sk_tx_queue_get(const struct sock *sk)
{
	return sk ? sk->sk_tx_queue_mapping : -1;
}

static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
	sk_tx_queue_clear(sk);
	sk->sk_socket = sock;
}

static inline wait_queue_head_t *sk_sleep(struct sock *sk)
{
	BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
	return &rcu_dereference_raw(sk->sk_wq)->wait;
}
/* Detach socket from process context.
 * Announce socket dead, detach it from wait queue and inode.
 * Note that parent inode held reference count on this struct sock,
 * we do not release it in this function, because protocol
 * probably wants some additional cleanups or even continuing
 * to work with this socket (TCP).
 */
static inline void sock_orphan(struct sock *sk)
{
	write_lock_bh(&sk->sk_callback_lock);
	sock_set_flag(sk, SOCK_DEAD);
	sk_set_socket(sk, NULL);
	sk->sk_wq  = NULL;
	write_unlock_bh(&sk->sk_callback_lock);
}

static inline void sock_graft(struct sock *sk, struct socket *parent)
{
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_wq = parent->wq;
	parent->sk = sk;
	sk_set_socket(sk, parent);
	security_sock_graft(sk, parent);
	write_unlock_bh(&sk->sk_callback_lock);
}

extern int sock_i_uid(struct sock *sk);
extern unsigned long sock_i_ino(struct sock *sk);

static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
	return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) ||
						       lockdep_is_held(&sk->sk_lock.slock));
}

static inline struct dst_entry *
sk_dst_get(struct sock *sk)
{
	struct dst_entry *dst;

	rcu_read_lock();
	dst = rcu_dereference(sk->sk_dst_cache);
	if (dst)
		dst_hold(dst);
	rcu_read_unlock();
	return dst;
}

extern void sk_reset_txq(struct sock *sk);

static inline void dst_negative_advice(struct sock *sk)
{
	struct dst_entry *ndst, *dst = __sk_dst_get(sk);

	if (dst && dst->ops->negative_advice) {
		ndst = dst->ops->negative_advice(dst);

		if (ndst != dst) {
			rcu_assign_pointer(sk->sk_dst_cache, ndst);
			sk_reset_txq(sk);
		}
	}
}

static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	struct dst_entry *old_dst;

	sk_tx_queue_clear(sk);
	/*
	 * This can be called while sk is owned by the caller only,
	 * with no state that can be checked in a rcu_dereference_check() cond
	 */
	old_dst = rcu_dereference_raw(sk->sk_dst_cache);
	rcu_assign_pointer(sk->sk_dst_cache, dst);
	dst_release(old_dst);
}

static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	spin_lock(&sk->sk_dst_lock);
	__sk_dst_set(sk, dst);
	spin_unlock(&sk->sk_dst_lock);
}

static inline void
__sk_dst_reset(struct sock *sk)
{
	__sk_dst_set(sk, NULL);
}

static inline void
sk_dst_reset(struct sock *sk)
{
	spin_lock(&sk->sk_dst_lock);
	__sk_dst_reset(sk);
	spin_unlock(&sk->sk_dst_lock);
}

extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);

extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);

static inline int sk_can_gso(const struct sock *sk)
{
	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}

extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);

static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
{
	sk->sk_route_nocaps |= flags;
	sk->sk_route_caps &= ~flags;
}

static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
					   char __user *from, char *to,
					   int copy, int offset)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
		__wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
		if (err)
			return err;
		skb->csum = csum_block_add(skb->csum, csum, offset);
	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
		if (!access_ok(VERIFY_READ, from, copy) ||
		    __copy_from_user_nocache(to, from, copy))
			return -EFAULT;
	} else if (copy_from_user(to, from, copy))
		return -EFAULT;

	return 0;
}

static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
				       char __user *from, int copy)
{
	int err, offset = skb->len;

	err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
				       copy, offset);
	if (err)
		__skb_trim(skb, offset);

	return err;
}

static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
					   struct sk_buff *skb,
					   struct page *page,
					   int off, int copy)
{
	int err;

	err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
				       copy, skb->len);
	if (err)
		return err;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk->sk_wmem_queued   += copy;
	sk_mem_charge(sk, copy);
	return 0;
}

static inline int skb_copy_to_page(struct sock *sk, char __user *from,
				   struct sk_buff *skb, struct page *page,
				   int off, int copy)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
		__wsum csum = csum_and_copy_from_user(from,
						     page_address(page) + off,
							    copy, 0, &err);
		if (err)
			return err;
		skb->csum = csum_block_add(skb->csum, csum, skb->len);
	} else if (copy_from_user(page_address(page) + off, from, copy))
		return -EFAULT;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk->sk_wmem_queued   += copy;
	sk_mem_charge(sk, copy);
	return 0;
}

/**
 * sk_wmem_alloc_get - returns write allocations
 * @sk: socket
 *
 * Returns sk_wmem_alloc minus initial offset of one
 */
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_wmem_alloc) - 1;
}

/**
 * sk_rmem_alloc_get - returns read allocations
 * @sk: socket
 *
 * Returns sk_rmem_alloc
 */
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_rmem_alloc);
}

/**
 * sk_has_allocations - check if allocations are outstanding
 * @sk: socket
 *
 * Returns true if socket has write or read allocations
 */
static inline int sk_has_allocations(const struct sock *sk)
{
	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}

/**
 * wq_has_sleeper - check if there are any waiting processes
 * @wq: struct socket_wq
 *
 * Returns true if socket_wq has waiting processes
 *
 * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
 * barrier call. They were added due to the race found within the tcp code.
 *
 * Consider following tcp code paths:
 *
 * CPU1                  CPU2
 *
 * sys_select            receive packet
 *   ...                 ...
 *   __add_wait_queue    update tp->rcv_nxt
 *   ...                 ...
 *   tp->rcv_nxt check   sock_def_readable
 *   ...                 {
 *   schedule               rcu_read_lock();
 *                          wq = rcu_dereference(sk->sk_wq);
 *                          if (wq && waitqueue_active(&wq->wait))
 *                              wake_up_interruptible(&wq->wait)
 *                          ...
 *                       }
 *
 * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
 * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
 * could then endup calling schedule and sleep forever if there are no more
 * data on the socket.
 *
 */
static inline bool wq_has_sleeper(struct socket_wq *wq)
{

	/*
	 * We need to be sure we are in sync with the
	 * add_wait_queue modifications to the wait queue.
	 *
	 * This memory barrier is paired in the sock_poll_wait.
	 */
	smp_mb();
	return wq && waitqueue_active(&wq->wait);
}

/**
 * sock_poll_wait - place memory barrier behind the poll_wait call.
 * @filp:           file
 * @wait_address:   socket wait queue
 * @p:              poll_table
 *
 * See the comments in the wq_has_sleeper function.
 */
static inline void sock_poll_wait(struct file *filp,
		wait_queue_head_t *wait_address, poll_table *p)
{
	if (p && wait_address) {
		poll_wait(filp, wait_address, p);
		/*
		 * We need to be sure we are in sync with the
		 * socket flags modification.
		 *
		 * This memory barrier is paired in the wq_has_sleeper.
		*/
		smp_mb();
	}
}

/*
 * 	Queue a received datagram if it will fit. Stream and sequenced
 *	protocols can't normally use this as they need to fit buffers in
 *	and play with them.
 *
 * 	Inlined as it's very short and called for pretty much every
 *	packet ever received.
 */

static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = sock_wfree;
	/*
	 * We used to take a refcount on sk, but following operation
	 * is enough to guarantee sk_free() wont free this sock until
	 * all in-flight packets are completed
	 */
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}

static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = sock_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	sk_mem_charge(sk, skb->truesize);
}

extern void sk_reset_timer(struct sock *sk, struct timer_list* timer,
			   unsigned long expires);

extern void sk_stop_timer(struct sock *sk, struct timer_list* timer);

extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

extern int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);

/*
 *	Recover an error report and clear atomically
 */
 
static inline int sock_error(struct sock *sk)
{
	int err;
	if (likely(!sk->sk_err))
		return 0;
	err = xchg(&sk->sk_err, 0);
	return -err;
}

static inline unsigned long sock_wspace(struct sock *sk)
{
	int amt = 0;

	if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
		amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
		if (amt < 0) 
			amt = 0;
	}
	return amt;
}

static inline void sk_wake_async(struct sock *sk, int how, int band)
{
	if (sock_flag(sk, SOCK_FASYNC))
		sock_wake_async(sk->sk_socket, how, band);
}

#define SOCK_MIN_SNDBUF 2048
/*
 * Since sk_rmem_alloc sums skb->truesize, even a small frame might need
 * sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak
 */
#define SOCK_MIN_RCVBUF (2048 + sizeof(struct sk_buff))

static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
		sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
	}
}

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);

static inline struct page *sk_stream_alloc_page(struct sock *sk)
{
	struct page *page = NULL;

	page = alloc_pages(sk->sk_allocation, 0);
	if (!page) {
		sk_enter_memory_pressure(sk);
		sk_stream_moderate_sndbuf(sk);
	}
	return page;
}

/*
 *	Default write policy as shown to user space via poll/select/SIGIO
 */
static inline int sock_writeable(const struct sock *sk) 
{
	return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
}

static inline gfp_t gfp_any(void)
{
	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}

static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_rcvtimeo;
}

static inline long sock_sndtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_sndtimeo;
}

static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
	return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
}

/* Alas, with timeout socket operations are not restartable.
 * Compare this to poll().
 */
static inline int sock_intr_errno(long timeo)
{
	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}

extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb);
extern void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb);

static __inline__ void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
	ktime_t kt = skb->tstamp;
	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);

	/*
	 * generate control messages if
	 * - receive time stamping in software requested (SOCK_RCVTSTAMP
	 *   or SOCK_TIMESTAMPING_RX_SOFTWARE)
	 * - software time stamp available and wanted
	 *   (SOCK_TIMESTAMPING_SOFTWARE)
	 * - hardware time stamps available and wanted
	 *   (SOCK_TIMESTAMPING_SYS_HARDWARE or
	 *   SOCK_TIMESTAMPING_RAW_HARDWARE)
	 */
	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
	    sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) ||
	    (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) ||
	    (hwtstamps->hwtstamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) ||
	    (hwtstamps->syststamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)))
		__sock_recv_timestamp(msg, sk, skb);
	else
		sk->sk_stamp = kt;

	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
		__sock_recv_wifi_status(msg, sk, skb);
}

extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
				     struct sk_buff *skb);

static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
					  struct sk_buff *skb)
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
			   (1UL << SOCK_RCVTSTAMP)			| \
			   (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)	| \
			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) 	| \
			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))

	if (sk->sk_flags & FLAGS_TS_OR_DROPS)
		__sock_recv_ts_and_drops(msg, sk, skb);
	else
		sk->sk_stamp = skb->tstamp;
}

/**
 * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
 * @sk:		socket sending this packet
 * @tx_flags:	filled with instructions for time stamping
 *
 * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if
 * parameters are invalid.
 */
extern int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);

/**
 * sk_eat_skb - Release a skb if it is no longer needed
 * @sk: socket to eat this skb from
 * @skb: socket buffer to eat
 * @copied_early: flag indicating whether DMA operations copied this data early
 *
 * This routine must be called with interrupts disabled or with the socket
 * locked so that the sk_buff queue operation is ok.
*/
#ifdef CONFIG_NET_DMA
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	if (!copied_early)
		__kfree_skb(skb);
	else
		__skb_queue_tail(&sk->sk_async_wait_queue, skb);
}
#else
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	__kfree_skb(skb);
}
#endif

static inline
struct net *sock_net(const struct sock *sk)
{
	return read_pnet(&sk->sk_net);
}

static inline
void sock_net_set(struct sock *sk, struct net *net)
{
	write_pnet(&sk->sk_net, net);
}

/*
 * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
 * They should not hold a reference to a namespace in order to allow
 * to stop it.
 * Sockets after sk_change_net should be released using sk_release_kernel
 */
static inline void sk_change_net(struct sock *sk, struct net *net)
{
	put_net(sock_net(sk));
	sock_net_set(sk, hold_net(net));
}

static inline struct sock *skb_steal_sock(struct sk_buff *skb)
{
	if (unlikely(skb->sk)) {
		struct sock *sk = skb->sk;

		skb->destructor = NULL;
		skb->sk = NULL;
		return sk;
	}
	return NULL;
}

extern void sock_enable_timestamp(struct sock *sk, int flag);
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
extern int sock_get_timestampns(struct sock *, struct timespec __user *);

/* 
 *	Enable debug/info messages 
 */
extern int net_msg_warn;
#define NETDEBUG(fmt, args...) \
	do { if (net_msg_warn) printk(fmt,##args); } while (0)

#define LIMIT_NETDEBUG(fmt, args...) \
	do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)

extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;

extern void sk_init(void);

extern int sysctl_optmem_max;

extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;

#endif	/* _SOCK_H */