1/proc/sys/net/ipv4/* Variables:
   2
   3ip_forward - BOOLEAN
   4	0 - disabled (default)
   5	not 0 - enabled
   6
   7	Forward Packets between interfaces.
   8
   9	This variable is special, its change resets all configuration
  10	parameters to their default state (RFC1122 for hosts, RFC1812
  11	for routers)
  12
  13ip_default_ttl - INTEGER
  14	Default value of TTL field (Time To Live) for outgoing (but not
  15	forwarded) IP packets. Should be between 1 and 255 inclusive.
  16	Default: 64 (as recommended by RFC1700)
  17
  18ip_no_pmtu_disc - INTEGER
  19	Disable Path MTU Discovery. If enabled in mode 1 and a
  20	fragmentation-required ICMP is received, the PMTU to this
  21	destination will be set to min_pmtu (see below). You will need
  22	to raise min_pmtu to the smallest interface MTU on your system
  23	manually if you want to avoid locally generated fragments.
  24
  25	In mode 2 incoming Path MTU Discovery messages will be
  26	discarded. Outgoing frames are handled the same as in mode 1,
  27	implicitly setting IP_PMTUDISC_DONT on every created socket.
  28
  29	Mode 3 is a hardend pmtu discover mode. The kernel will only
  30	accept fragmentation-needed errors if the underlying protocol
  31	can verify them besides a plain socket lookup. Current
  32	protocols for which pmtu events will be honored are TCP, SCTP
  33	and DCCP as they verify e.g. the sequence number or the
  34	association. This mode should not be enabled globally but is
  35	only intended to secure e.g. name servers in namespaces where
  36	TCP path mtu must still work but path MTU information of other
  37	protocols should be discarded. If enabled globally this mode
  38	could break other protocols.
  39
  40	Possible values: 0-3
  41	Default: FALSE
  42
  43min_pmtu - INTEGER
  44	default 552 - minimum discovered Path MTU
  45
  46ip_forward_use_pmtu - BOOLEAN
  47	By default we don't trust protocol path MTUs while forwarding
  48	because they could be easily forged and can lead to unwanted
  49	fragmentation by the router.
  50	You only need to enable this if you have user-space software
  51	which tries to discover path mtus by itself and depends on the
  52	kernel honoring this information. This is normally not the
  53	case.
  54	Default: 0 (disabled)
  55	Possible values:
  56	0 - disabled
  57	1 - enabled
  58
  59fwmark_reflect - BOOLEAN
  60	Controls the fwmark of kernel-generated IPv4 reply packets that are not
  61	associated with a socket for example, TCP RSTs or ICMP echo replies).
  62	If unset, these packets have a fwmark of zero. If set, they have the
  63	fwmark of the packet they are replying to.
  64	Default: 0
  65
  66route/max_size - INTEGER
  67	Maximum number of routes allowed in the kernel.  Increase
  68	this when using large numbers of interfaces and/or routes.
  69	From linux kernel 3.6 onwards, this is deprecated for ipv4
  70	as route cache is no longer used.
  71
  72neigh/default/gc_thresh1 - INTEGER
  73	Minimum number of entries to keep.  Garbage collector will not
  74	purge entries if there are fewer than this number.
  75	Default: 128
  76
  77neigh/default/gc_thresh2 - INTEGER
  78	Threshold when garbage collector becomes more aggressive about
  79	purging entries. Entries older than 5 seconds will be cleared
  80	when over this number.
  81	Default: 512
  82
  83neigh/default/gc_thresh3 - INTEGER
  84	Maximum number of neighbor entries allowed.  Increase this
  85	when using large numbers of interfaces and when communicating
  86	with large numbers of directly-connected peers.
  87	Default: 1024
  88
  89neigh/default/unres_qlen_bytes - INTEGER
  90	The maximum number of bytes which may be used by packets
  91	queued for each	unresolved address by other network layers.
  92	(added in linux 3.3)
  93	Setting negative value is meaningless and will return error.
  94	Default: 65536 Bytes(64KB)
  95
  96neigh/default/unres_qlen - INTEGER
  97	The maximum number of packets which may be queued for each
  98	unresolved address by other network layers.
  99	(deprecated in linux 3.3) : use unres_qlen_bytes instead.
 100	Prior to linux 3.3, the default value is 3 which may cause
 101	unexpected packet loss. The current default value is calculated
 102	according to default value of unres_qlen_bytes and true size of
 103	packet.
 104	Default: 31
 105
 106mtu_expires - INTEGER
 107	Time, in seconds, that cached PMTU information is kept.
 108
 109min_adv_mss - INTEGER
 110	The advertised MSS depends on the first hop route MTU, but will
 111	never be lower than this setting.
 112
 113IP Fragmentation:
 114
 115ipfrag_high_thresh - INTEGER
 116	Maximum memory used to reassemble IP fragments. When
 117	ipfrag_high_thresh bytes of memory is allocated for this purpose,
 118	the fragment handler will toss packets until ipfrag_low_thresh
 119	is reached. This also serves as a maximum limit to namespaces
 120	different from the initial one.
 121
 122ipfrag_low_thresh - INTEGER
 123	Maximum memory used to reassemble IP fragments before the kernel
 124	begins to remove incomplete fragment queues to free up resources.
 125	The kernel still accepts new fragments for defragmentation.
 126
 127ipfrag_time - INTEGER
 128	Time in seconds to keep an IP fragment in memory.
 129
 130ipfrag_max_dist - INTEGER
 131	ipfrag_max_dist is a non-negative integer value which defines the
 132	maximum "disorder" which is allowed among fragments which share a
 133	common IP source address. Note that reordering of packets is
 134	not unusual, but if a large number of fragments arrive from a source
 135	IP address while a particular fragment queue remains incomplete, it
 136	probably indicates that one or more fragments belonging to that queue
 137	have been lost. When ipfrag_max_dist is positive, an additional check
 138	is done on fragments before they are added to a reassembly queue - if
 139	ipfrag_max_dist (or more) fragments have arrived from a particular IP
 140	address between additions to any IP fragment queue using that source
 141	address, it's presumed that one or more fragments in the queue are
 142	lost. The existing fragment queue will be dropped, and a new one
 143	started. An ipfrag_max_dist value of zero disables this check.
 144
 145	Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
 146	result in unnecessarily dropping fragment queues when normal
 147	reordering of packets occurs, which could lead to poor application
 148	performance. Using a very large value, e.g. 50000, increases the
 149	likelihood of incorrectly reassembling IP fragments that originate
 150	from different IP datagrams, which could result in data corruption.
 151	Default: 64
 152
 153INET peer storage:
 154
 155inet_peer_threshold - INTEGER
 156	The approximate size of the storage.  Starting from this threshold
 157	entries will be thrown aggressively.  This threshold also determines
 158	entries' time-to-live and time intervals between garbage collection
 159	passes.  More entries, less time-to-live, less GC interval.
 160
 161inet_peer_minttl - INTEGER
 162	Minimum time-to-live of entries.  Should be enough to cover fragment
 163	time-to-live on the reassembling side.  This minimum time-to-live  is
 164	guaranteed if the pool size is less than inet_peer_threshold.
 165	Measured in seconds.
 166
 167inet_peer_maxttl - INTEGER
 168	Maximum time-to-live of entries.  Unused entries will expire after
 169	this period of time if there is no memory pressure on the pool (i.e.
 170	when the number of entries in the pool is very small).
 171	Measured in seconds.
 172
 173TCP variables:
 174
 175somaxconn - INTEGER
 176	Limit of socket listen() backlog, known in userspace as SOMAXCONN.
 177	Defaults to 128.  See also tcp_max_syn_backlog for additional tuning
 178	for TCP sockets.
 179
 180tcp_abort_on_overflow - BOOLEAN
 181	If listening service is too slow to accept new connections,
 182	reset them. Default state is FALSE. It means that if overflow
 183	occurred due to a burst, connection will recover. Enable this
 184	option _only_ if you are really sure that listening daemon
 185	cannot be tuned to accept connections faster. Enabling this
 186	option can harm clients of your server.
 187
 188tcp_adv_win_scale - INTEGER
 189	Count buffering overhead as bytes/2^tcp_adv_win_scale
 190	(if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
 191	if it is <= 0.
 192	Possible values are [-31, 31], inclusive.
 193	Default: 1
 194
 195tcp_allowed_congestion_control - STRING
 196	Show/set the congestion control choices available to non-privileged
 197	processes. The list is a subset of those listed in
 198	tcp_available_congestion_control.
 199	Default is "reno" and the default setting (tcp_congestion_control).
 200
 201tcp_app_win - INTEGER
 202	Reserve max(window/2^tcp_app_win, mss) of window for application
 203	buffer. Value 0 is special, it means that nothing is reserved.
 204	Default: 31
 205
 206tcp_autocorking - BOOLEAN
 207	Enable TCP auto corking :
 208	When applications do consecutive small write()/sendmsg() system calls,
 209	we try to coalesce these small writes as much as possible, to lower
 210	total amount of sent packets. This is done if at least one prior
 211	packet for the flow is waiting in Qdisc queues or device transmit
 212	queue. Applications can still use TCP_CORK for optimal behavior
 213	when they know how/when to uncork their sockets.
 214	Default : 1
 215
 216tcp_available_congestion_control - STRING
 217	Shows the available congestion control choices that are registered.
 218	More congestion control algorithms may be available as modules,
 219	but not loaded.
 220
 221tcp_base_mss - INTEGER
 222	The initial value of search_low to be used by the packetization layer
 223	Path MTU discovery (MTU probing).  If MTU probing is enabled,
 224	this is the initial MSS used by the connection.
 225
 226tcp_congestion_control - STRING
 227	Set the congestion control algorithm to be used for new
 228	connections. The algorithm "reno" is always available, but
 229	additional choices may be available based on kernel configuration.
 230	Default is set as part of kernel configuration.
 231	For passive connections, the listener congestion control choice
 232	is inherited.
 233	[see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
 234
 235tcp_dsack - BOOLEAN
 236	Allows TCP to send "duplicate" SACKs.
 237
 238tcp_early_retrans - INTEGER
 239	Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
 240	for triggering fast retransmit when the amount of outstanding data is
 241	small and when no previously unsent data can be transmitted (such
 242	that limited transmit could be used). Also controls the use of
 243	Tail loss probe (TLP) that converts RTOs occurring due to tail
 244	losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
 245	Possible values:
 246		0 disables ER
 247		1 enables ER
 248		2 enables ER but delays fast recovery and fast retransmit
 249		  by a fourth of RTT. This mitigates connection falsely
 250		  recovers when network has a small degree of reordering
 251		  (less than 3 packets).
 252		3 enables delayed ER and TLP.
 253		4 enables TLP only.
 254	Default: 3
 255
 256tcp_ecn - INTEGER
 257	Control use of Explicit Congestion Notification (ECN) by TCP.
 258	ECN is used only when both ends of the TCP connection indicate
 259	support for it.  This feature is useful in avoiding losses due
 260	to congestion by allowing supporting routers to signal
 261	congestion before having to drop packets.
 262	Possible values are:
 263		0 Disable ECN.  Neither initiate nor accept ECN.
 264		1 Enable ECN when requested by incoming connections and
 265		  also request ECN on outgoing connection attempts.
 266		2 Enable ECN when requested by incoming connections
 267		  but do not request ECN on outgoing connections.
 268	Default: 2
 269
 270tcp_ecn_fallback - BOOLEAN
 271	If the kernel detects that ECN connection misbehaves, enable fall
 272	back to non-ECN. Currently, this knob implements the fallback
 273	from RFC3168, section 6.1.1.1., but we reserve that in future,
 274	additional detection mechanisms could be implemented under this
 275	knob. The value	is not used, if tcp_ecn or per route (or congestion
 276	control) ECN settings are disabled.
 277	Default: 1 (fallback enabled)
 278
 279tcp_fack - BOOLEAN
 280	Enable FACK congestion avoidance and fast retransmission.
 281	The value is not used, if tcp_sack is not enabled.
 282
 283tcp_fin_timeout - INTEGER
 284	The length of time an orphaned (no longer referenced by any
 285	application) connection will remain in the FIN_WAIT_2 state
 286	before it is aborted at the local end.  While a perfectly
 287	valid "receive only" state for an un-orphaned connection, an
 288	orphaned connection in FIN_WAIT_2 state could otherwise wait
 289	forever for the remote to close its end of the connection.
 290	Cf. tcp_max_orphans
 291	Default: 60 seconds
 292
 293tcp_frto - INTEGER
 294	Enables Forward RTO-Recovery (F-RTO) defined in RFC5682.
 295	F-RTO is an enhanced recovery algorithm for TCP retransmission
 296	timeouts.  It is particularly beneficial in networks where the
 297	RTT fluctuates (e.g., wireless). F-RTO is sender-side only
 298	modification. It does not require any support from the peer.
 299
 300	By default it's enabled with a non-zero value. 0 disables F-RTO.
 301
 302tcp_invalid_ratelimit - INTEGER
 303	Limit the maximal rate for sending duplicate acknowledgments
 304	in response to incoming TCP packets that are for an existing
 305	connection but that are invalid due to any of these reasons:
 306
 307	  (a) out-of-window sequence number,
 308	  (b) out-of-window acknowledgment number, or
 309	  (c) PAWS (Protection Against Wrapped Sequence numbers) check failure
 310
 311	This can help mitigate simple "ack loop" DoS attacks, wherein
 312	a buggy or malicious middlebox or man-in-the-middle can
 313	rewrite TCP header fields in manner that causes each endpoint
 314	to think that the other is sending invalid TCP segments, thus
 315	causing each side to send an unterminating stream of duplicate
 316	acknowledgments for invalid segments.
 317
 318	Using 0 disables rate-limiting of dupacks in response to
 319	invalid segments; otherwise this value specifies the minimal
 320	space between sending such dupacks, in milliseconds.
 321
 322	Default: 500 (milliseconds).
 323
 324tcp_keepalive_time - INTEGER
 325	How often TCP sends out keepalive messages when keepalive is enabled.
 326	Default: 2hours.
 327
 328tcp_keepalive_probes - INTEGER
 329	How many keepalive probes TCP sends out, until it decides that the
 330	connection is broken. Default value: 9.
 331
 332tcp_keepalive_intvl - INTEGER
 333	How frequently the probes are send out. Multiplied by
 334	tcp_keepalive_probes it is time to kill not responding connection,
 335	after probes started. Default value: 75sec i.e. connection
 336	will be aborted after ~11 minutes of retries.
 337
 338tcp_l3mdev_accept - BOOLEAN
 339	Enables child sockets to inherit the L3 master device index.
 340	Enabling this option allows a "global" listen socket to work
 341	across L3 master domains (e.g., VRFs) with connected sockets
 342	derived from the listen socket to be bound to the L3 domain in
 343	which the packets originated. Only valid when the kernel was
 344	compiled with CONFIG_NET_L3_MASTER_DEV.
 345
 346tcp_low_latency - BOOLEAN
 347	If set, the TCP stack makes decisions that prefer lower
 348	latency as opposed to higher throughput.  By default, this
 349	option is not set meaning that higher throughput is preferred.
 350	An example of an application where this default should be
 351	changed would be a Beowulf compute cluster.
 352	Default: 0
 353
 354tcp_max_orphans - INTEGER
 355	Maximal number of TCP sockets not attached to any user file handle,
 356	held by system.	If this number is exceeded orphaned connections are
 357	reset immediately and warning is printed. This limit exists
 358	only to prevent simple DoS attacks, you _must_ not rely on this
 359	or lower the limit artificially, but rather increase it
 360	(probably, after increasing installed memory),
 361	if network conditions require more than default value,
 362	and tune network services to linger and kill such states
 363	more aggressively. Let me to remind again: each orphan eats
 364	up to ~64K of unswappable memory.
 365
 366tcp_max_syn_backlog - INTEGER
 367	Maximal number of remembered connection requests, which have not
 368	received an acknowledgment from connecting client.
 369	The minimal value is 128 for low memory machines, and it will
 370	increase in proportion to the memory of machine.
 371	If server suffers from overload, try increasing this number.
 372
 373tcp_max_tw_buckets - INTEGER
 374	Maximal number of timewait sockets held by system simultaneously.
 375	If this number is exceeded time-wait socket is immediately destroyed
 376	and warning is printed. This limit exists only to prevent
 377	simple DoS attacks, you _must_ not lower the limit artificially,
 378	but rather increase it (probably, after increasing installed memory),
 379	if network conditions require more than default value.
 380
 381tcp_mem - vector of 3 INTEGERs: min, pressure, max
 382	min: below this number of pages TCP is not bothered about its
 383	memory appetite.
 384
 385	pressure: when amount of memory allocated by TCP exceeds this number
 386	of pages, TCP moderates its memory consumption and enters memory
 387	pressure mode, which is exited when memory consumption falls
 388	under "min".
 389
 390	max: number of pages allowed for queueing by all TCP sockets.
 391
 392	Defaults are calculated at boot time from amount of available
 393	memory.
 394
 395tcp_min_rtt_wlen - INTEGER
 396	The window length of the windowed min filter to track the minimum RTT.
 397	A shorter window lets a flow more quickly pick up new (higher)
 398	minimum RTT when it is moved to a longer path (e.g., due to traffic
 399	engineering). A longer window makes the filter more resistant to RTT
 400	inflations such as transient congestion. The unit is seconds.
 401	Default: 300
 402
 403tcp_moderate_rcvbuf - BOOLEAN
 404	If set, TCP performs receive buffer auto-tuning, attempting to
 405	automatically size the buffer (no greater than tcp_rmem[2]) to
 406	match the size required by the path for full throughput.  Enabled by
 407	default.
 408
 409tcp_mtu_probing - INTEGER
 410	Controls TCP Packetization-Layer Path MTU Discovery.  Takes three
 411	values:
 412	  0 - Disabled
 413	  1 - Disabled by default, enabled when an ICMP black hole detected
 414	  2 - Always enabled, use initial MSS of tcp_base_mss.
 415
 416tcp_probe_interval - INTEGER
 417	Controls how often to start TCP Packetization-Layer Path MTU
 418	Discovery reprobe. The default is reprobing every 10 minutes as
 419	per RFC4821.
 420
 421tcp_probe_threshold - INTEGER
 422	Controls when TCP Packetization-Layer Path MTU Discovery probing
 423	will stop in respect to the width of search range in bytes. Default
 424	is 8 bytes.
 425
 426tcp_no_metrics_save - BOOLEAN
 427	By default, TCP saves various connection metrics in the route cache
 428	when the connection closes, so that connections established in the
 429	near future can use these to set initial conditions.  Usually, this
 430	increases overall performance, but may sometimes cause performance
 431	degradation.  If set, TCP will not cache metrics on closing
 432	connections.
 433
 434tcp_orphan_retries - INTEGER
 435	This value influences the timeout of a locally closed TCP connection,
 436	when RTO retransmissions remain unacknowledged.
 437	See tcp_retries2 for more details.
 438
 439	The default value is 8.
 440	If your machine is a loaded WEB server,
 441	you should think about lowering this value, such sockets
 442	may consume significant resources. Cf. tcp_max_orphans.
 443
 444tcp_recovery - INTEGER
 445	This value is a bitmap to enable various experimental loss recovery
 446	features.
 447
 448	RACK: 0x1 enables the RACK loss detection for fast detection of lost
 449	      retransmissions and tail drops.
 450
 451	Default: 0x1
 452
 453tcp_reordering - INTEGER
 454	Initial reordering level of packets in a TCP stream.
 455	TCP stack can then dynamically adjust flow reordering level
 456	between this initial value and tcp_max_reordering
 457	Default: 3
 458
 459tcp_max_reordering - INTEGER
 460	Maximal reordering level of packets in a TCP stream.
 461	300 is a fairly conservative value, but you might increase it
 462	if paths are using per packet load balancing (like bonding rr mode)
 463	Default: 300
 464
 465tcp_retrans_collapse - BOOLEAN
 466	Bug-to-bug compatibility with some broken printers.
 467	On retransmit try to send bigger packets to work around bugs in
 468	certain TCP stacks.
 469
 470tcp_retries1 - INTEGER
 471	This value influences the time, after which TCP decides, that
 472	something is wrong due to unacknowledged RTO retransmissions,
 473	and reports this suspicion to the network layer.
 474	See tcp_retries2 for more details.
 475
 476	RFC 1122 recommends at least 3 retransmissions, which is the
 477	default.
 478
 479tcp_retries2 - INTEGER
 480	This value influences the timeout of an alive TCP connection,
 481	when RTO retransmissions remain unacknowledged.
 482	Given a value of N, a hypothetical TCP connection following
 483	exponential backoff with an initial RTO of TCP_RTO_MIN would
 484	retransmit N times before killing the connection at the (N+1)th RTO.
 485
 486	The default value of 15 yields a hypothetical timeout of 924.6
 487	seconds and is a lower bound for the effective timeout.
 488	TCP will effectively time out at the first RTO which exceeds the
 489	hypothetical timeout.
 490
 491	RFC 1122 recommends at least 100 seconds for the timeout,
 492	which corresponds to a value of at least 8.
 493
 494tcp_rfc1337 - BOOLEAN
 495	If set, the TCP stack behaves conforming to RFC1337. If unset,
 496	we are not conforming to RFC, but prevent TCP TIME_WAIT
 497	assassination.
 498	Default: 0
 499
 500tcp_rmem - vector of 3 INTEGERs: min, default, max
 501	min: Minimal size of receive buffer used by TCP sockets.
 502	It is guaranteed to each TCP socket, even under moderate memory
 503	pressure.
 504	Default: 1 page
 505
 506	default: initial size of receive buffer used by TCP sockets.
 507	This value overrides net.core.rmem_default used by other protocols.
 508	Default: 87380 bytes. This value results in window of 65535 with
 509	default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
 510	less for default tcp_app_win. See below about these variables.
 511
 512	max: maximal size of receive buffer allowed for automatically
 513	selected receiver buffers for TCP socket. This value does not override
 514	net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
 515	automatic tuning of that socket's receive buffer size, in which
 516	case this value is ignored.
 517	Default: between 87380B and 6MB, depending on RAM size.
 518
 519tcp_sack - BOOLEAN
 520	Enable select acknowledgments (SACKS).
 521
 522tcp_slow_start_after_idle - BOOLEAN
 523	If set, provide RFC2861 behavior and time out the congestion
 524	window after an idle period.  An idle period is defined at
 525	the current RTO.  If unset, the congestion window will not
 526	be timed out after an idle period.
 527	Default: 1
 528
 529tcp_stdurg - BOOLEAN
 530	Use the Host requirements interpretation of the TCP urgent pointer field.
 531	Most hosts use the older BSD interpretation, so if you turn this on
 532	Linux might not communicate correctly with them.
 533	Default: FALSE
 534
 535tcp_synack_retries - INTEGER
 536	Number of times SYNACKs for a passive TCP connection attempt will
 537	be retransmitted. Should not be higher than 255. Default value
 538	is 5, which corresponds to 31seconds till the last retransmission
 539	with the current initial RTO of 1second. With this the final timeout
 540	for a passive TCP connection will happen after 63seconds.
 541
 542tcp_syncookies - BOOLEAN
 543	Only valid when the kernel was compiled with CONFIG_SYN_COOKIES
 544	Send out syncookies when the syn backlog queue of a socket
 545	overflows. This is to prevent against the common 'SYN flood attack'
 546	Default: 1
 547
 548	Note, that syncookies is fallback facility.
 549	It MUST NOT be used to help highly loaded servers to stand
 550	against legal connection rate. If you see SYN flood warnings
 551	in your logs, but investigation	shows that they occur
 552	because of overload with legal connections, you should tune
 553	another parameters until this warning disappear.
 554	See: tcp_max_syn_backlog, tcp_synack_retries, tcp_abort_on_overflow.
 555
 556	syncookies seriously violate TCP protocol, do not allow
 557	to use TCP extensions, can result in serious degradation
 558	of some services (f.e. SMTP relaying), visible not by you,
 559	but your clients and relays, contacting you. While you see
 560	SYN flood warnings in logs not being really flooded, your server
 561	is seriously misconfigured.
 562
 563	If you want to test which effects syncookies have to your
 564	network connections you can set this knob to 2 to enable
 565	unconditionally generation of syncookies.
 566
 567tcp_fastopen - INTEGER
 568	Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
 569	in the opening SYN packet. To use this feature, the client application
 570	must use sendmsg() or sendto() with MSG_FASTOPEN flag rather than
 571	connect() to perform a TCP handshake automatically.
 572
 573	The values (bitmap) are
 574	1: Enables sending data in the opening SYN on the client w/ MSG_FASTOPEN.
 575	2: Enables TCP Fast Open on the server side, i.e., allowing data in
 576	   a SYN packet to be accepted and passed to the application before
 577	   3-way hand shake finishes.
 578	4: Send data in the opening SYN regardless of cookie availability and
 579	   without a cookie option.
 580	0x100: Accept SYN data w/o validating the cookie.
 581	0x200: Accept data-in-SYN w/o any cookie option present.
 582	0x400/0x800: Enable Fast Open on all listeners regardless of the
 583	   TCP_FASTOPEN socket option. The two different flags designate two
 584	   different ways of setting max_qlen without the TCP_FASTOPEN socket
 585	   option.
 586
 587	Default: 1
 588
 589	Note that the client & server side Fast Open flags (1 and 2
 590	respectively) must be also enabled before the rest of flags can take
 591	effect.
 592
 593	See include/net/tcp.h and the code for more details.
 594
 595tcp_syn_retries - INTEGER
 596	Number of times initial SYNs for an active TCP connection attempt
 597	will be retransmitted. Should not be higher than 127. Default value
 598	is 6, which corresponds to 63seconds till the last retransmission
 599	with the current initial RTO of 1second. With this the final timeout
 600	for an active TCP connection attempt will happen after 127seconds.
 601
 602tcp_timestamps - BOOLEAN
 603	Enable timestamps as defined in RFC1323.
 604
 605tcp_min_tso_segs - INTEGER
 606	Minimal number of segments per TSO frame.
 607	Since linux-3.12, TCP does an automatic sizing of TSO frames,
 608	depending on flow rate, instead of filling 64Kbytes packets.
 609	For specific usages, it's possible to force TCP to build big
 610	TSO frames. Note that TCP stack might split too big TSO packets
 611	if available window is too small.
 612	Default: 2
 613
 614tcp_pacing_ss_ratio - INTEGER
 615	sk->sk_pacing_rate is set by TCP stack using a ratio applied
 616	to current rate. (current_rate = cwnd * mss / srtt)
 617	If TCP is in slow start, tcp_pacing_ss_ratio is applied
 618	to let TCP probe for bigger speeds, assuming cwnd can be
 619	doubled every other RTT.
 620	Default: 200
 621
 622tcp_pacing_ca_ratio - INTEGER
 623	sk->sk_pacing_rate is set by TCP stack using a ratio applied
 624	to current rate. (current_rate = cwnd * mss / srtt)
 625	If TCP is in congestion avoidance phase, tcp_pacing_ca_ratio
 626	is applied to conservatively probe for bigger throughput.
 627	Default: 120
 628
 629tcp_tso_win_divisor - INTEGER
 630	This allows control over what percentage of the congestion window
 631	can be consumed by a single TSO frame.
 632	The setting of this parameter is a choice between burstiness and
 633	building larger TSO frames.
 634	Default: 3
 635
 636tcp_tw_recycle - BOOLEAN
 637	Enable fast recycling TIME-WAIT sockets. Default value is 0.
 638	It should not be changed without advice/request of technical
 639	experts.
 640
 641tcp_tw_reuse - BOOLEAN
 642	Allow to reuse TIME-WAIT sockets for new connections when it is
 643	safe from protocol viewpoint. Default value is 0.
 644	It should not be changed without advice/request of technical
 645	experts.
 646
 647tcp_window_scaling - BOOLEAN
 648	Enable window scaling as defined in RFC1323.
 649
 650tcp_wmem - vector of 3 INTEGERs: min, default, max
 651	min: Amount of memory reserved for send buffers for TCP sockets.
 652	Each TCP socket has rights to use it due to fact of its birth.
 653	Default: 1 page
 654
 655	default: initial size of send buffer used by TCP sockets.  This
 656	value overrides net.core.wmem_default used by other protocols.
 657	It is usually lower than net.core.wmem_default.
 658	Default: 16K
 659
 660	max: Maximal amount of memory allowed for automatically tuned
 661	send buffers for TCP sockets. This value does not override
 662	net.core.wmem_max.  Calling setsockopt() with SO_SNDBUF disables
 663	automatic tuning of that socket's send buffer size, in which case
 664	this value is ignored.
 665	Default: between 64K and 4MB, depending on RAM size.
 666
 667tcp_notsent_lowat - UNSIGNED INTEGER
 668	A TCP socket can control the amount of unsent bytes in its write queue,
 669	thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
 670	reports POLLOUT events if the amount of unsent bytes is below a per
 671	socket value, and if the write queue is not full. sendmsg() will
 672	also not add new buffers if the limit is hit.
 673
 674	This global variable controls the amount of unsent data for
 675	sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
 676	to the global variable has immediate effect.
 677
 678	Default: UINT_MAX (0xFFFFFFFF)
 679
 680tcp_workaround_signed_windows - BOOLEAN
 681	If set, assume no receipt of a window scaling option means the
 682	remote TCP is broken and treats the window as a signed quantity.
 683	If unset, assume the remote TCP is not broken even if we do
 684	not receive a window scaling option from them.
 685	Default: 0
 686
 687tcp_thin_linear_timeouts - BOOLEAN
 688	Enable dynamic triggering of linear timeouts for thin streams.
 689	If set, a check is performed upon retransmission by timeout to
 690	determine if the stream is thin (less than 4 packets in flight).
 691	As long as the stream is found to be thin, up to 6 linear
 692	timeouts may be performed before exponential backoff mode is
 693	initiated. This improves retransmission latency for
 694	non-aggressive thin streams, often found to be time-dependent.
 695	For more information on thin streams, see
 696	Documentation/networking/tcp-thin.txt
 697	Default: 0
 698
 699tcp_thin_dupack - BOOLEAN
 700	Enable dynamic triggering of retransmissions after one dupACK
 701	for thin streams. If set, a check is performed upon reception
 702	of a dupACK to determine if the stream is thin (less than 4
 703	packets in flight). As long as the stream is found to be thin,
 704	data is retransmitted on the first received dupACK. This
 705	improves retransmission latency for non-aggressive thin
 706	streams, often found to be time-dependent.
 707	For more information on thin streams, see
 708	Documentation/networking/tcp-thin.txt
 709	Default: 0
 710
 711tcp_limit_output_bytes - INTEGER
 712	Controls TCP Small Queue limit per tcp socket.
 713	TCP bulk sender tends to increase packets in flight until it
 714	gets losses notifications. With SNDBUF autotuning, this can
 715	result in a large amount of packets queued in qdisc/device
 716	on the local machine, hurting latency of other flows, for
 717	typical pfifo_fast qdiscs.
 718	tcp_limit_output_bytes limits the number of bytes on qdisc
 719	or device to reduce artificial RTT/cwnd and reduce bufferbloat.
 720	Default: 262144
 721
 722tcp_challenge_ack_limit - INTEGER
 723	Limits number of Challenge ACK sent per second, as recommended
 724	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
 725	Default: 100
 726
 727UDP variables:
 728
 729udp_mem - vector of 3 INTEGERs: min, pressure, max
 730	Number of pages allowed for queueing by all UDP sockets.
 731
 732	min: Below this number of pages UDP is not bothered about its
 733	memory appetite. When amount of memory allocated by UDP exceeds
 734	this number, UDP starts to moderate memory usage.
 735
 736	pressure: This value was introduced to follow format of tcp_mem.
 737
 738	max: Number of pages allowed for queueing by all UDP sockets.
 739
 740	Default is calculated at boot time from amount of available memory.
 741
 742udp_rmem_min - INTEGER
 743	Minimal size of receive buffer used by UDP sockets in moderation.
 744	Each UDP socket is able to use the size for receiving data, even if
 745	total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
 746	Default: 1 page
 747
 748udp_wmem_min - INTEGER
 749	Minimal size of send buffer used by UDP sockets in moderation.
 750	Each UDP socket is able to use the size for sending data, even if
 751	total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
 752	Default: 1 page
 753
 754CIPSOv4 Variables:
 755
 756cipso_cache_enable - BOOLEAN
 757	If set, enable additions to and lookups from the CIPSO label mapping
 758	cache.  If unset, additions are ignored and lookups always result in a
 759	miss.  However, regardless of the setting the cache is still
 760	invalidated when required when means you can safely toggle this on and
 761	off and the cache will always be "safe".
 762	Default: 1
 763
 764cipso_cache_bucket_size - INTEGER
 765	The CIPSO label cache consists of a fixed size hash table with each
 766	hash bucket containing a number of cache entries.  This variable limits
 767	the number of entries in each hash bucket; the larger the value the
 768	more CIPSO label mappings that can be cached.  When the number of
 769	entries in a given hash bucket reaches this limit adding new entries
 770	causes the oldest entry in the bucket to be removed to make room.
 771	Default: 10
 772
 773cipso_rbm_optfmt - BOOLEAN
 774	Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of
 775	the CIPSO draft specification (see Documentation/netlabel for details).
 776	This means that when set the CIPSO tag will be padded with empty
 777	categories in order to make the packet data 32-bit aligned.
 778	Default: 0
 779
 780cipso_rbm_structvalid - BOOLEAN
 781	If set, do a very strict check of the CIPSO option when
 782	ip_options_compile() is called.  If unset, relax the checks done during
 783	ip_options_compile().  Either way is "safe" as errors are caught else
 784	where in the CIPSO processing code but setting this to 0 (False) should
 785	result in less work (i.e. it should be faster) but could cause problems
 786	with other implementations that require strict checking.
 787	Default: 0
 788
 789IP Variables:
 790
 791ip_local_port_range - 2 INTEGERS
 792	Defines the local port range that is used by TCP and UDP to
 793	choose the local port. The first number is the first, the
 794	second the last local port number.
 795	If possible, it is better these numbers have different parity.
 796	(one even and one odd values)
 797	The default values are 32768 and 60999 respectively.
 798
 799ip_local_reserved_ports - list of comma separated ranges
 800	Specify the ports which are reserved for known third-party
 801	applications. These ports will not be used by automatic port
 802	assignments (e.g. when calling connect() or bind() with port
 803	number 0). Explicit port allocation behavior is unchanged.
 804
 805	The format used for both input and output is a comma separated
 806	list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
 807	10). Writing to the file will clear all previously reserved
 808	ports and update the current list with the one given in the
 809	input.
 810
 811	Note that ip_local_port_range and ip_local_reserved_ports
 812	settings are independent and both are considered by the kernel
 813	when determining which ports are available for automatic port
 814	assignments.
 815
 816	You can reserve ports which are not in the current
 817	ip_local_port_range, e.g.:
 818
 819	$ cat /proc/sys/net/ipv4/ip_local_port_range
 820	32000	60999
 821	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
 822	8080,9148
 823
 824	although this is redundant. However such a setting is useful
 825	if later the port range is changed to a value that will
 826	include the reserved ports.
 827
 828	Default: Empty
 829
 830ip_nonlocal_bind - BOOLEAN
 831	If set, allows processes to bind() to non-local IP addresses,
 832	which can be quite useful - but may break some applications.
 833	Default: 0
 834
 835ip_dynaddr - BOOLEAN
 836	If set non-zero, enables support for dynamic addresses.
 837	If set to a non-zero value larger than 1, a kernel log
 838	message will be printed when dynamic address rewriting
 839	occurs.
 840	Default: 0
 841
 842ip_early_demux - BOOLEAN
 843	Optimize input packet processing down to one demux for
 844	certain kinds of local sockets.  Currently we only do this
 845	for established TCP sockets.
 846
 847	It may add an additional cost for pure routing workloads that
 848	reduces overall throughput, in such case you should disable it.
 849	Default: 1
 850
 851icmp_echo_ignore_all - BOOLEAN
 852	If set non-zero, then the kernel will ignore all ICMP ECHO
 853	requests sent to it.
 854	Default: 0
 855
 856icmp_echo_ignore_broadcasts - BOOLEAN
 857	If set non-zero, then the kernel will ignore all ICMP ECHO and
 858	TIMESTAMP requests sent to it via broadcast/multicast.
 859	Default: 1
 860
 861icmp_ratelimit - INTEGER
 862	Limit the maximal rates for sending ICMP packets whose type matches
 863	icmp_ratemask (see below) to specific targets.
 864	0 to disable any limiting,
 865	otherwise the minimal space between responses in milliseconds.
 866	Note that another sysctl, icmp_msgs_per_sec limits the number
 867	of ICMP packets	sent on all targets.
 868	Default: 1000
 869
 870icmp_msgs_per_sec - INTEGER
 871	Limit maximal number of ICMP packets sent per second from this host.
 872	Only messages whose type matches icmp_ratemask (see below) are
 873	controlled by this limit.
 874	Default: 1000
 875
 876icmp_msgs_burst - INTEGER
 877	icmp_msgs_per_sec controls number of ICMP packets sent per second,
 878	while icmp_msgs_burst controls the burst size of these packets.
 879	Default: 50
 880
 881icmp_ratemask - INTEGER
 882	Mask made of ICMP types for which rates are being limited.
 883	Significant bits: IHGFEDCBA9876543210
 884	Default mask:     0000001100000011000 (6168)
 885
 886	Bit definitions (see include/linux/icmp.h):
 887		0 Echo Reply
 888		3 Destination Unreachable *
 889		4 Source Quench *
 890		5 Redirect
 891		8 Echo Request
 892		B Time Exceeded *
 893		C Parameter Problem *
 894		D Timestamp Request
 895		E Timestamp Reply
 896		F Info Request
 897		G Info Reply
 898		H Address Mask Request
 899		I Address Mask Reply
 900
 901	* These are rate limited by default (see default mask above)
 902
 903icmp_ignore_bogus_error_responses - BOOLEAN
 904	Some routers violate RFC1122 by sending bogus responses to broadcast
 905	frames.  Such violations are normally logged via a kernel warning.
 906	If this is set to TRUE, the kernel will not give such warnings, which
 907	will avoid log file clutter.
 908	Default: 1
 909
 910icmp_errors_use_inbound_ifaddr - BOOLEAN
 911
 912	If zero, icmp error messages are sent with the primary address of
 913	the exiting interface.
 914
 915	If non-zero, the message will be sent with the primary address of
 916	the interface that received the packet that caused the icmp error.
 917	This is the behaviour network many administrators will expect from
 918	a router. And it can make debugging complicated network layouts
 919	much easier.
 920
 921	Note that if no primary address exists for the interface selected,
 922	then the primary address of the first non-loopback interface that
 923	has one will be used regardless of this setting.
 924
 925	Default: 0
 926
 927igmp_max_memberships - INTEGER
 928	Change the maximum number of multicast groups we can subscribe to.
 929	Default: 20
 930
 931	Theoretical maximum value is bounded by having to send a membership
 932	report in a single datagram (i.e. the report can't span multiple
 933	datagrams, or risk confusing the switch and leaving groups you don't
 934	intend to).
 935
 936	The number of supported groups 'M' is bounded by the number of group
 937	report entries you can fit into a single datagram of 65535 bytes.
 938
 939	M = 65536-sizeof (ip header)/(sizeof(Group record))
 940
 941	Group records are variable length, with a minimum of 12 bytes.
 942	So net.ipv4.igmp_max_memberships should not be set higher than:
 943
 944	(65536-24) / 12 = 5459
 945
 946	The value 5459 assumes no IP header options, so in practice
 947	this number may be lower.
 948
 949igmp_max_msf - INTEGER
 950	Maximum number of addresses allowed in the source filter list for a
 951	multicast group.
 952	Default: 10
 953
 954igmp_qrv - INTEGER
 955	Controls the IGMP query robustness variable (see RFC2236 8.1).
 956	Default: 2 (as specified by RFC2236 8.1)
 957	Minimum: 1 (as specified by RFC6636 4.5)
 958
 959conf/interface/*  changes special settings per interface (where
 960"interface" is the name of your network interface)
 961
 962conf/all/*	  is special, changes the settings for all interfaces
 963
 964log_martians - BOOLEAN
 965	Log packets with impossible addresses to kernel log.
 966	log_martians for the interface will be enabled if at least one of
 967	conf/{all,interface}/log_martians is set to TRUE,
 968	it will be disabled otherwise
 969
 970accept_redirects - BOOLEAN
 971	Accept ICMP redirect messages.
 972	accept_redirects for the interface will be enabled if:
 973	- both conf/{all,interface}/accept_redirects are TRUE in the case
 974	  forwarding for the interface is enabled
 975	or
 976	- at least one of conf/{all,interface}/accept_redirects is TRUE in the
 977	  case forwarding for the interface is disabled
 978	accept_redirects for the interface will be disabled otherwise
 979	default TRUE (host)
 980		FALSE (router)
 981
 982forwarding - BOOLEAN
 983	Enable IP forwarding on this interface.
 984
 985mc_forwarding - BOOLEAN
 986	Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
 987	and a multicast routing daemon is required.
 988	conf/all/mc_forwarding must also be set to TRUE to enable multicast
 989	routing	for the interface
 990
 991medium_id - INTEGER
 992	Integer value used to differentiate the devices by the medium they
 993	are attached to. Two devices can have different id values when
 994	the broadcast packets are received only on one of them.
 995	The default value 0 means that the device is the only interface
 996	to its medium, value of -1 means that medium is not known.
 997
 998	Currently, it is used to change the proxy_arp behavior:
 999	the proxy_arp feature is enabled for packets forwarded between
1000	two devices attached to different media.
1001
1002proxy_arp - BOOLEAN
1003	Do proxy arp.
1004	proxy_arp for the interface will be enabled if at least one of
1005	conf/{all,interface}/proxy_arp is set to TRUE,
1006	it will be disabled otherwise
1007
1008proxy_arp_pvlan - BOOLEAN
1009	Private VLAN proxy arp.
1010	Basically allow proxy arp replies back to the same interface
1011	(from which the ARP request/solicitation was received).
1012
1013	This is done to support (ethernet) switch features, like RFC
1014	3069, where the individual ports are NOT allowed to
1015	communicate with each other, but they are allowed to talk to
1016	the upstream router.  As described in RFC 3069, it is possible
1017	to allow these hosts to communicate through the upstream
1018	router by proxy_arp'ing. Don't need to be used together with
1019	proxy_arp.
1020
1021	This technology is known by different names:
1022	  In RFC 3069 it is called VLAN Aggregation.
1023	  Cisco and Allied Telesyn call it Private VLAN.
1024	  Hewlett-Packard call it Source-Port filtering or port-isolation.
1025	  Ericsson call it MAC-Forced Forwarding (RFC Draft).
1026
1027shared_media - BOOLEAN
1028	Send(router) or accept(host) RFC1620 shared media redirects.
1029	Overrides ip_secure_redirects.
1030	shared_media for the interface will be enabled if at least one of
1031	conf/{all,interface}/shared_media is set to TRUE,
1032	it will be disabled otherwise
1033	default TRUE
1034
1035secure_redirects - BOOLEAN
1036	Accept ICMP redirect messages only for gateways,
1037	listed in default gateway list.
1038	secure_redirects for the interface will be enabled if at least one of
1039	conf/{all,interface}/secure_redirects is set to TRUE,
1040	it will be disabled otherwise
1041	default TRUE
1042
1043send_redirects - BOOLEAN
1044	Send redirects, if router.
1045	send_redirects for the interface will be enabled if at least one of
1046	conf/{all,interface}/send_redirects is set to TRUE,
1047	it will be disabled otherwise
1048	Default: TRUE
1049
1050bootp_relay - BOOLEAN
1051	Accept packets with source address 0.b.c.d destined
1052	not to this host as local ones. It is supposed, that
1053	BOOTP relay daemon will catch and forward such packets.
1054	conf/all/bootp_relay must also be set to TRUE to enable BOOTP relay
1055	for the interface
1056	default FALSE
1057	Not Implemented Yet.
1058
1059accept_source_route - BOOLEAN
1060	Accept packets with SRR option.
1061	conf/all/accept_source_route must also be set to TRUE to accept packets
1062	with SRR option on the interface
1063	default TRUE (router)
1064		FALSE (host)
1065
1066accept_local - BOOLEAN
1067	Accept packets with local source addresses. In combination with
1068	suitable routing, this can be used to direct packets between two
1069	local interfaces over the wire and have them accepted properly.
1070	default FALSE
1071
1072route_localnet - BOOLEAN
1073	Do not consider loopback addresses as martian source or destination
1074	while routing. This enables the use of 127/8 for local routing purposes.
1075	default FALSE
1076
1077rp_filter - INTEGER
1078	0 - No source validation.
1079	1 - Strict mode as defined in RFC3704 Strict Reverse Path
1080	    Each incoming packet is tested against the FIB and if the interface
1081	    is not the best reverse path the packet check will fail.
1082	    By default failed packets are discarded.
1083	2 - Loose mode as defined in RFC3704 Loose Reverse Path
1084	    Each incoming packet's source address is also tested against the FIB
1085	    and if the source address is not reachable via any interface
1086	    the packet check will fail.
1087
1088	Current recommended practice in RFC3704 is to enable strict mode
1089	to prevent IP spoofing from DDos attacks. If using asymmetric routing
1090	or other complicated routing, then loose mode is recommended.
1091
1092	The max value from conf/{all,interface}/rp_filter is used
1093	when doing source validation on the {interface}.
1094
1095	Default value is 0. Note that some distributions enable it
1096	in startup scripts.
1097
1098arp_filter - BOOLEAN
1099	1 - Allows you to have multiple network interfaces on the same
1100	subnet, and have the ARPs for each interface be answered
1101	based on whether or not the kernel would route a packet from
1102	the ARP'd IP out that interface (therefore you must use source
1103	based routing for this to work). In other words it allows control
1104	of which cards (usually 1) will respond to an arp request.
1105
1106	0 - (default) The kernel can respond to arp requests with addresses
1107	from other interfaces. This may seem wrong but it usually makes
1108	sense, because it increases the chance of successful communication.
1109	IP addresses are owned by the complete host on Linux, not by
1110	particular interfaces. Only for more complex setups like load-
1111	balancing, does this behaviour cause problems.
1112
1113	arp_filter for the interface will be enabled if at least one of
1114	conf/{all,interface}/arp_filter is set to TRUE,
1115	it will be disabled otherwise
1116
1117arp_announce - INTEGER
1118	Define different restriction levels for announcing the local
1119	source IP address from IP packets in ARP requests sent on
1120	interface:
1121	0 - (default) Use any local address, configured on any interface
1122	1 - Try to avoid local addresses that are not in the target's
1123	subnet for this interface. This mode is useful when target
1124	hosts reachable via this interface require the source IP
1125	address in ARP requests to be part of their logical network
1126	configured on the receiving interface. When we generate the
1127	request we will check all our subnets that include the
1128	target IP and will preserve the source address if it is from
1129	such subnet. If there is no such subnet we select source
1130	address according to the rules for level 2.
1131	2 - Always use the best local address for this target.
1132	In this mode we ignore the source address in the IP packet
1133	and try to select local address that we prefer for talks with
1134	the target host. Such local address is selected by looking
1135	for primary IP addresses on all our subnets on the outgoing
1136	interface that include the target IP address. If no suitable
1137	local address is found we select the first local address
1138	we have on the outgoing interface or on all other interfaces,
1139	with the hope we will receive reply for our request and
1140	even sometimes no matter the source IP address we announce.
1141
1142	The max value from conf/{all,interface}/arp_announce is used.
1143
1144	Increasing the restriction level gives more chance for
1145	receiving answer from the resolved target while decreasing
1146	the level announces more valid sender's information.
1147
1148arp_ignore - INTEGER
1149	Define different modes for sending replies in response to
1150	received ARP requests that resolve local target IP addresses:
1151	0 - (default): reply for any local target IP address, configured
1152	on any interface
1153	1 - reply only if the target IP address is local address
1154	configured on the incoming interface
1155	2 - reply only if the target IP address is local address
1156	configured on the incoming interface and both with the
1157	sender's IP address are part from same subnet on this interface
1158	3 - do not reply for local addresses configured with scope host,
1159	only resolutions for global and link addresses are replied
1160	4-7 - reserved
1161	8 - do not reply for all local addresses
1162
1163	The max value from conf/{all,interface}/arp_ignore is used
1164	when ARP request is received on the {interface}
1165
1166arp_notify - BOOLEAN
1167	Define mode for notification of address and device changes.
1168	0 - (default): do nothing
1169	1 - Generate gratuitous arp requests when device is brought up
1170	    or hardware address changes.
1171
1172arp_accept - BOOLEAN
1173	Define behavior for gratuitous ARP frames who's IP is not
1174	already present in the ARP table:
1175	0 - don't create new entries in the ARP table
1176	1 - create new entries in the ARP table
1177
1178	Both replies and requests type gratuitous arp will trigger the
1179	ARP table to be updated, if this setting is on.
1180
1181	If the ARP table already contains the IP address of the
1182	gratuitous arp frame, the arp table will be updated regardless
1183	if this setting is on or off.
1184
1185mcast_solicit - INTEGER
1186	The maximum number of multicast probes in INCOMPLETE state,
1187	when the associated hardware address is unknown.  Defaults
1188	to 3.
1189
1190ucast_solicit - INTEGER
1191	The maximum number of unicast probes in PROBE state, when
1192	the hardware address is being reconfirmed.  Defaults to 3.
1193
1194app_solicit - INTEGER
1195	The maximum number of probes to send to the user space ARP daemon
1196	via netlink before dropping back to multicast probes (see
1197	mcast_resolicit).  Defaults to 0.
1198
1199mcast_resolicit - INTEGER
1200	The maximum number of multicast probes after unicast and
1201	app probes in PROBE state.  Defaults to 0.
1202
1203disable_policy - BOOLEAN
1204	Disable IPSEC policy (SPD) for this interface
1205
1206disable_xfrm - BOOLEAN
1207	Disable IPSEC encryption on this interface, whatever the policy
1208
1209igmpv2_unsolicited_report_interval - INTEGER
1210	The interval in milliseconds in which the next unsolicited
1211	IGMPv1 or IGMPv2 report retransmit will take place.
1212	Default: 10000 (10 seconds)
1213
1214igmpv3_unsolicited_report_interval - INTEGER
1215	The interval in milliseconds in which the next unsolicited
1216	IGMPv3 report retransmit will take place.
1217	Default: 1000 (1 seconds)
1218
1219promote_secondaries - BOOLEAN
1220	When a primary IP address is removed from this interface
1221	promote a corresponding secondary IP address instead of
1222	removing all the corresponding secondary IP addresses.
1223
1224drop_unicast_in_l2_multicast - BOOLEAN
1225	Drop any unicast IP packets that are received in link-layer
1226	multicast (or broadcast) frames.
1227	This behavior (for multicast) is actually a SHOULD in RFC
1228	1122, but is disabled by default for compatibility reasons.
1229	Default: off (0)
1230
1231drop_gratuitous_arp - BOOLEAN
1232	Drop all gratuitous ARP frames, for example if there's a known
1233	good ARP proxy on the network and such frames need not be used
1234	(or in the case of 802.11, must not be used to prevent attacks.)
1235	Default: off (0)
1236
1237
1238tag - INTEGER
1239	Allows you to write a number, which can be used as required.
1240	Default value is 0.
1241
1242xfrm4_gc_thresh - INTEGER
1243	The threshold at which we will start garbage collecting for IPv4
1244	destination cache entries.  At twice this value the system will
1245	refuse new allocations. The value must be set below the flowcache
1246	limit (4096 * number of online cpus) to take effect.
1247
1248igmp_link_local_mcast_reports - BOOLEAN
1249	Enable IGMP reports for link local multicast groups in the
1250	224.0.0.X range.
1251	Default TRUE
1252
1253Alexey Kuznetsov.
1254kuznet@ms2.inr.ac.ru
1255
1256Updated by:
1257Andi Kleen
1258ak@muc.de
1259Nicolas Delon
1260delon.nicolas@wanadoo.fr
1261
1262
1263
1264
1265/proc/sys/net/ipv6/* Variables:
1266
1267IPv6 has no global variables such as tcp_*.  tcp_* settings under ipv4/ also
1268apply to IPv6 [XXX?].
1269
1270bindv6only - BOOLEAN
1271	Default value for IPV6_V6ONLY socket option,
1272	which restricts use of the IPv6 socket to IPv6 communication
1273	only.
1274		TRUE: disable IPv4-mapped address feature
1275		FALSE: enable IPv4-mapped address feature
1276
1277	Default: FALSE (as specified in RFC3493)
1278
1279flowlabel_consistency - BOOLEAN
1280	Protect the consistency (and unicity) of flow label.
1281	You have to disable it to use IPV6_FL_F_REFLECT flag on the
1282	flow label manager.
1283	TRUE: enabled
1284	FALSE: disabled
1285	Default: TRUE
1286
1287auto_flowlabels - INTEGER
1288	Automatically generate flow labels based on a flow hash of the
1289	packet. This allows intermediate devices, such as routers, to
1290	identify packet flows for mechanisms like Equal Cost Multipath
1291	Routing (see RFC 6438).
1292	0: automatic flow labels are completely disabled
1293	1: automatic flow labels are enabled by default, they can be
1294	   disabled on a per socket basis using the IPV6_AUTOFLOWLABEL
1295	   socket option
1296	2: automatic flow labels are allowed, they may be enabled on a
1297	   per socket basis using the IPV6_AUTOFLOWLABEL socket option
1298	3: automatic flow labels are enabled and enforced, they cannot
1299	   be disabled by the socket option
1300	Default: 1
1301
1302flowlabel_state_ranges - BOOLEAN
1303	Split the flow label number space into two ranges. 0-0x7FFFF is
1304	reserved for the IPv6 flow manager facility, 0x80000-0xFFFFF
1305	is reserved for stateless flow labels as described in RFC6437.
1306	TRUE: enabled
1307	FALSE: disabled
1308	Default: true
1309
1310anycast_src_echo_reply - BOOLEAN
1311	Controls the use of anycast addresses as source addresses for ICMPv6
1312	echo reply
1313	TRUE:  enabled
1314	FALSE: disabled
1315	Default: FALSE
1316
1317idgen_delay - INTEGER
1318	Controls the delay in seconds after which time to retry
1319	privacy stable address generation if a DAD conflict is
1320	detected.
1321	Default: 1 (as specified in RFC7217)
1322
1323idgen_retries - INTEGER
1324	Controls the number of retries to generate a stable privacy
1325	address if a DAD conflict is detected.
1326	Default: 3 (as specified in RFC7217)
1327
1328mld_qrv - INTEGER
1329	Controls the MLD query robustness variable (see RFC3810 9.1).
1330	Default: 2 (as specified by RFC3810 9.1)
1331	Minimum: 1 (as specified by RFC6636 4.5)
1332
1333IPv6 Fragmentation:
1334
1335ip6frag_high_thresh - INTEGER
1336	Maximum memory used to reassemble IPv6 fragments. When
1337	ip6frag_high_thresh bytes of memory is allocated for this purpose,
1338	the fragment handler will toss packets until ip6frag_low_thresh
1339	is reached.
1340
1341ip6frag_low_thresh - INTEGER
1342	See ip6frag_high_thresh
1343
1344ip6frag_time - INTEGER
1345	Time in seconds to keep an IPv6 fragment in memory.
1346
1347conf/default/*:
1348	Change the interface-specific default settings.
1349
1350
1351conf/all/*:
1352	Change all the interface-specific settings.
1353
1354	[XXX:  Other special features than forwarding?]
1355
1356conf/all/forwarding - BOOLEAN
1357	Enable global IPv6 forwarding between all interfaces.
1358
1359	IPv4 and IPv6 work differently here; e.g. netfilter must be used
1360	to control which interfaces may forward packets and which not.
1361
1362	This also sets all interfaces' Host/Router setting
1363	'forwarding' to the specified value.  See below for details.
1364
1365	This referred to as global forwarding.
1366
1367proxy_ndp - BOOLEAN
1368	Do proxy ndp.
1369
1370fwmark_reflect - BOOLEAN
1371	Controls the fwmark of kernel-generated IPv6 reply packets that are not
1372	associated with a socket for example, TCP RSTs or ICMPv6 echo replies).
1373	If unset, these packets have a fwmark of zero. If set, they have the
1374	fwmark of the packet they are replying to.
1375	Default: 0
1376
1377conf/interface/*:
1378	Change special settings per interface.
1379
1380	The functional behaviour for certain settings is different
1381	depending on whether local forwarding is enabled or not.
1382
1383accept_ra - INTEGER
1384	Accept Router Advertisements; autoconfigure using them.
1385
1386	It also determines whether or not to transmit Router
1387	Solicitations. If and only if the functional setting is to
1388	accept Router Advertisements, Router Solicitations will be
1389	transmitted.
1390
1391	Possible values are:
1392		0 Do not accept Router Advertisements.
1393		1 Accept Router Advertisements if forwarding is disabled.
1394		2 Overrule forwarding behaviour. Accept Router Advertisements
1395		  even if forwarding is enabled.
1396
1397	Functional default: enabled if local forwarding is disabled.
1398			    disabled if local forwarding is enabled.
1399
1400accept_ra_defrtr - BOOLEAN
1401	Learn default router in Router Advertisement.
1402
1403	Functional default: enabled if accept_ra is enabled.
1404			    disabled if accept_ra is disabled.
1405
1406accept_ra_from_local - BOOLEAN
1407	Accept RA with source-address that is found on local machine
1408        if the RA is otherwise proper and able to be accepted.
1409        Default is to NOT accept these as it may be an un-intended
1410        network loop.
1411
1412	Functional default:
1413           enabled if accept_ra_from_local is enabled
1414               on a specific interface.
1415	   disabled if accept_ra_from_local is disabled
1416               on a specific interface.
1417
1418accept_ra_min_hop_limit - INTEGER
1419	Minimum hop limit Information in Router Advertisement.
1420
1421	Hop limit Information in Router Advertisement less than this
1422	variable shall be ignored.
1423
1424	Default: 1
1425
1426accept_ra_pinfo - BOOLEAN
1427	Learn Prefix Information in Router Advertisement.
1428
1429	Functional default: enabled if accept_ra is enabled.
1430			    disabled if accept_ra is disabled.
1431
1432accept_ra_rt_info_max_plen - INTEGER
1433	Maximum prefix length of Route Information in RA.
1434
1435	Route Information w/ prefix larger than or equal to this
1436	variable shall be ignored.
1437
1438	Functional default: 0 if accept_ra_rtr_pref is enabled.
1439			    -1 if accept_ra_rtr_pref is disabled.
1440
1441accept_ra_rtr_pref - BOOLEAN
1442	Accept Router Preference in RA.
1443
1444	Functional default: enabled if accept_ra is enabled.
1445			    disabled if accept_ra is disabled.
1446
1447accept_ra_mtu - BOOLEAN
1448	Apply the MTU value specified in RA option 5 (RFC4861). If
1449	disabled, the MTU specified in the RA will be ignored.
1450
1451	Functional default: enabled if accept_ra is enabled.
1452			    disabled if accept_ra is disabled.
1453
1454accept_redirects - BOOLEAN
1455	Accept Redirects.
1456
1457	Functional default: enabled if local forwarding is disabled.
1458			    disabled if local forwarding is enabled.
1459
1460accept_source_route - INTEGER
1461	Accept source routing (routing extension header).
1462
1463	>= 0: Accept only routing header type 2.
1464	< 0: Do not accept routing header.
1465
1466	Default: 0
1467
1468autoconf - BOOLEAN
1469	Autoconfigure addresses using Prefix Information in Router
1470	Advertisements.
1471
1472	Functional default: enabled if accept_ra_pinfo is enabled.
1473			    disabled if accept_ra_pinfo is disabled.
1474
1475dad_transmits - INTEGER
1476	The amount of Duplicate Address Detection probes to send.
1477	Default: 1
1478
1479forwarding - INTEGER
1480	Configure interface-specific Host/Router behaviour.
1481
1482	Note: It is recommended to have the same setting on all
1483	interfaces; mixed router/host scenarios are rather uncommon.
1484
1485	Possible values are:
1486		0 Forwarding disabled
1487		1 Forwarding enabled
1488
1489	FALSE (0):
1490
1491	By default, Host behaviour is assumed.  This means:
1492
1493	1. IsRouter flag is not set in Neighbour Advertisements.
1494	2. If accept_ra is TRUE (default), transmit Router
1495	   Solicitations.
1496	3. If accept_ra is TRUE (default), accept Router
1497	   Advertisements (and do autoconfiguration).
1498	4. If accept_redirects is TRUE (default), accept Redirects.
1499
1500	TRUE (1):
1501
1502	If local forwarding is enabled, Router behaviour is assumed.
1503	This means exactly the reverse from the above:
1504
1505	1. IsRouter flag is set in Neighbour Advertisements.
1506	2. Router Solicitations are not sent unless accept_ra is 2.
1507	3. Router Advertisements are ignored unless accept_ra is 2.
1508	4. Redirects are ignored.
1509
1510	Default: 0 (disabled) if global forwarding is disabled (default),
1511		 otherwise 1 (enabled).
1512
1513hop_limit - INTEGER
1514	Default Hop Limit to set.
1515	Default: 64
1516
1517mtu - INTEGER
1518	Default Maximum Transfer Unit
1519	Default: 1280 (IPv6 required minimum)
1520
1521ip_nonlocal_bind - BOOLEAN
1522	If set, allows processes to bind() to non-local IPv6 addresses,
1523	which can be quite useful - but may break some applications.
1524	Default: 0
1525
1526router_probe_interval - INTEGER
1527	Minimum interval (in seconds) between Router Probing described
1528	in RFC4191.
1529
1530	Default: 60
1531
1532router_solicitation_delay - INTEGER
1533	Number of seconds to wait after interface is brought up
1534	before sending Router Solicitations.
1535	Default: 1
1536
1537router_solicitation_interval - INTEGER
1538	Number of seconds to wait between Router Solicitations.
1539	Default: 4
1540
1541router_solicitations - INTEGER
1542	Number of Router Solicitations to send until assuming no
1543	routers are present.
1544	Default: 3
1545
1546use_oif_addrs_only - BOOLEAN
1547	When enabled, the candidate source addresses for destinations
1548	routed via this interface are restricted to the set of addresses
1549	configured on this interface (vis. RFC 6724, section 4).
1550
1551	Default: false
1552
1553use_tempaddr - INTEGER
1554	Preference for Privacy Extensions (RFC3041).
1555	  <= 0 : disable Privacy Extensions
1556	  == 1 : enable Privacy Extensions, but prefer public
1557	         addresses over temporary addresses.
1558	  >  1 : enable Privacy Extensions and prefer temporary
1559	         addresses over public addresses.
1560	Default:  0 (for most devices)
1561		 -1 (for point-to-point devices and loopback devices)
1562
1563temp_valid_lft - INTEGER
1564	valid lifetime (in seconds) for temporary addresses.
1565	Default: 604800 (7 days)
1566
1567temp_prefered_lft - INTEGER
1568	Preferred lifetime (in seconds) for temporary addresses.
1569	Default: 86400 (1 day)
1570
1571keep_addr_on_down - INTEGER
1572	Keep all IPv6 addresses on an interface down event. If set static
1573	global addresses with no expiration time are not flushed.
1574	  >0 : enabled
1575	   0 : system default
1576	  <0 : disabled
1577
1578	Default: 0 (addresses are removed)
1579
1580max_desync_factor - INTEGER
1581	Maximum value for DESYNC_FACTOR, which is a random value
1582	that ensures that clients don't synchronize with each
1583	other and generate new addresses at exactly the same time.
1584	value is in seconds.
1585	Default: 600
1586
1587regen_max_retry - INTEGER
1588	Number of attempts before give up attempting to generate
1589	valid temporary addresses.
1590	Default: 5
1591
1592max_addresses - INTEGER
1593	Maximum number of autoconfigured addresses per interface.  Setting
1594	to zero disables the limitation.  It is not recommended to set this
1595	value too large (or to zero) because it would be an easy way to
1596	crash the kernel by allowing too many addresses to be created.
1597	Default: 16
1598
1599disable_ipv6 - BOOLEAN
1600	Disable IPv6 operation.  If accept_dad is set to 2, this value
1601	will be dynamically set to TRUE if DAD fails for the link-local
1602	address.
1603	Default: FALSE (enable IPv6 operation)
1604
1605	When this value is changed from 1 to 0 (IPv6 is being enabled),
1606	it will dynamically create a link-local address on the given
1607	interface and start Duplicate Address Detection, if necessary.
1608
1609	When this value is changed from 0 to 1 (IPv6 is being disabled),
1610	it will dynamically delete all address on the given interface.
1611
1612accept_dad - INTEGER
1613	Whether to accept DAD (Duplicate Address Detection).
1614	0: Disable DAD
1615	1: Enable DAD (default)
1616	2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
1617	   link-local address has been found.
1618
1619force_tllao - BOOLEAN
1620	Enable sending the target link-layer address option even when
1621	responding to a unicast neighbor solicitation.
1622	Default: FALSE
1623
1624	Quoting from RFC 2461, section 4.4, Target link-layer address:
1625
1626	"The option MUST be included for multicast solicitations in order to
1627	avoid infinite Neighbor Solicitation "recursion" when the peer node
1628	does not have a cache entry to return a Neighbor Advertisements
1629	message.  When responding to unicast solicitations, the option can be
1630	omitted since the sender of the solicitation has the correct link-
1631	layer address; otherwise it would not have be able to send the unicast
1632	solicitation in the first place. However, including the link-layer
1633	address in this case adds little overhead and eliminates a potential
1634	race condition where the sender deletes the cached link-layer address
1635	prior to receiving a response to a previous solicitation."
1636
1637ndisc_notify - BOOLEAN
1638	Define mode for notification of address and device changes.
1639	0 - (default): do nothing
1640	1 - Generate unsolicited neighbour advertisements when device is brought
1641	    up or hardware address changes.
1642
1643mldv1_unsolicited_report_interval - INTEGER
1644	The interval in milliseconds in which the next unsolicited
1645	MLDv1 report retransmit will take place.
1646	Default: 10000 (10 seconds)
1647
1648mldv2_unsolicited_report_interval - INTEGER
1649	The interval in milliseconds in which the next unsolicited
1650	MLDv2 report retransmit will take place.
1651	Default: 1000 (1 second)
1652
1653force_mld_version - INTEGER
1654	0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed
1655	1 - Enforce to use MLD version 1
1656	2 - Enforce to use MLD version 2
1657
1658suppress_frag_ndisc - INTEGER
1659	Control RFC 6980 (Security Implications of IPv6 Fragmentation
1660	with IPv6 Neighbor Discovery) behavior:
1661	1 - (default) discard fragmented neighbor discovery packets
1662	0 - allow fragmented neighbor discovery packets
1663
1664optimistic_dad - BOOLEAN
1665	Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
1666		0: disabled (default)
1667		1: enabled
1668
1669use_optimistic - BOOLEAN
1670	If enabled, do not classify optimistic addresses as deprecated during
1671	source address selection.  Preferred addresses will still be chosen
1672	before optimistic addresses, subject to other ranking in the source
1673	address selection algorithm.
1674		0: disabled (default)
1675		1: enabled
1676
1677stable_secret - IPv6 address
1678	This IPv6 address will be used as a secret to generate IPv6
1679	addresses for link-local addresses and autoconfigured
1680	ones. All addresses generated after setting this secret will
1681	be stable privacy ones by default. This can be changed via the
1682	addrgenmode ip-link. conf/default/stable_secret is used as the
1683	secret for the namespace, the interface specific ones can
1684	overwrite that. Writes to conf/all/stable_secret are refused.
1685
1686	It is recommended to generate this secret during installation
1687	of a system and keep it stable after that.
1688
1689	By default the stable secret is unset.
1690
1691drop_unicast_in_l2_multicast - BOOLEAN
1692	Drop any unicast IPv6 packets that are received in link-layer
1693	multicast (or broadcast) frames.
1694
1695	By default this is turned off.
1696
1697drop_unsolicited_na - BOOLEAN
1698	Drop all unsolicited neighbor advertisements, for example if there's
1699	a known good NA proxy on the network and such frames need not be used
1700	(or in the case of 802.11, must not be used to prevent attacks.)
1701
1702	By default this is turned off.
1703
1704icmp/*:
1705ratelimit - INTEGER
1706	Limit the maximal rates for sending ICMPv6 packets.
1707	0 to disable any limiting,
1708	otherwise the minimal space between responses in milliseconds.
1709	Default: 1000
1710
1711xfrm6_gc_thresh - INTEGER
1712	The threshold at which we will start garbage collecting for IPv6
1713	destination cache entries.  At twice this value the system will
1714	refuse new allocations. The value must be set below the flowcache
1715	limit (4096 * number of online cpus) to take effect.
1716
1717
1718IPv6 Update by:
1719Pekka Savola <pekkas@netcore.fi>
1720YOSHIFUJI Hideaki / USAGI Project <yoshfuji@linux-ipv6.org>
1721
1722
1723/proc/sys/net/bridge/* Variables:
1724
1725bridge-nf-call-arptables - BOOLEAN
1726	1 : pass bridged ARP traffic to arptables' FORWARD chain.
1727	0 : disable this.
1728	Default: 1
1729
1730bridge-nf-call-iptables - BOOLEAN
1731	1 : pass bridged IPv4 traffic to iptables' chains.
1732	0 : disable this.
1733	Default: 1
1734
1735bridge-nf-call-ip6tables - BOOLEAN
1736	1 : pass bridged IPv6 traffic to ip6tables' chains.
1737	0 : disable this.
1738	Default: 1
1739
1740bridge-nf-filter-vlan-tagged - BOOLEAN
1741	1 : pass bridged vlan-tagged ARP/IP/IPv6 traffic to {arp,ip,ip6}tables.
1742	0 : disable this.
1743	Default: 0
1744
1745bridge-nf-filter-pppoe-tagged - BOOLEAN
1746	1 : pass bridged pppoe-tagged IP/IPv6 traffic to {ip,ip6}tables.
1747	0 : disable this.
1748	Default: 0
1749
1750bridge-nf-pass-vlan-input-dev - BOOLEAN
1751	1: if bridge-nf-filter-vlan-tagged is enabled, try to find a vlan
1752	interface on the bridge and set the netfilter input device to the vlan.
1753	This allows use of e.g. "iptables -i br0.1" and makes the REDIRECT
1754	target work with vlan-on-top-of-bridge interfaces.  When no matching
1755	vlan interface is found, or this switch is off, the input device is
1756	set to the bridge interface.
1757	0: disable bridge netfilter vlan interface lookup.
1758	Default: 0
1759
1760proc/sys/net/sctp/* Variables:
1761
1762addip_enable - BOOLEAN
1763	Enable or disable extension of  Dynamic Address Reconfiguration
1764	(ADD-IP) functionality specified in RFC5061.  This extension provides
1765	the ability to dynamically add and remove new addresses for the SCTP
1766	associations.
1767
1768	1: Enable extension.
1769
1770	0: Disable extension.
1771
1772	Default: 0
1773
1774pf_enable - INTEGER
1775	Enable or disable pf (pf is short for potentially failed) state. A value
1776	of pf_retrans > path_max_retrans also disables pf state. That is, one of
1777	both pf_enable and pf_retrans > path_max_retrans can disable pf state.
1778	Since pf_retrans and path_max_retrans can be changed by userspace
1779	application, sometimes user expects to disable pf state by the value of
1780	pf_retrans > path_max_retrans, but occasionally the value of pf_retrans
1781	or path_max_retrans is changed by the user application, this pf state is
1782	enabled. As such, it is necessary to add this to dynamically enable
1783	and disable pf state. See:
1784	https://datatracker.ietf.org/doc/draft-ietf-tsvwg-sctp-failover for
1785	details.
1786
1787	1: Enable pf.
1788
1789	0: Disable pf.
1790
1791	Default: 1
1792
1793addip_noauth_enable - BOOLEAN
1794	Dynamic Address Reconfiguration (ADD-IP) requires the use of
1795	authentication to protect the operations of adding or removing new
1796	addresses.  This requirement is mandated so that unauthorized hosts
1797	would not be able to hijack associations.  However, older
1798	implementations may not have implemented this requirement while
1799	allowing the ADD-IP extension.  For reasons of interoperability,
1800	we provide this variable to control the enforcement of the
1801	authentication requirement.
1802
1803	1: Allow ADD-IP extension to be used without authentication.  This
1804	   should only be set in a closed environment for interoperability
1805	   with older implementations.
1806
1807	0: Enforce the authentication requirement
1808
1809	Default: 0
1810
1811auth_enable - BOOLEAN
1812	Enable or disable Authenticated Chunks extension.  This extension
1813	provides the ability to send and receive authenticated chunks and is
1814	required for secure operation of Dynamic Address Reconfiguration
1815	(ADD-IP) extension.
1816
1817	1: Enable this extension.
1818	0: Disable this extension.
1819
1820	Default: 0
1821
1822prsctp_enable - BOOLEAN
1823	Enable or disable the Partial Reliability extension (RFC3758) which
1824	is used to notify peers that a given DATA should no longer be expected.
1825
1826	1: Enable extension
1827	0: Disable
1828
1829	Default: 1
1830
1831max_burst - INTEGER
1832	The limit of the number of new packets that can be initially sent.  It
1833	controls how bursty the generated traffic can be.
1834
1835	Default: 4
1836
1837association_max_retrans - INTEGER
1838	Set the maximum number for retransmissions that an association can
1839	attempt deciding that the remote end is unreachable.  If this value
1840	is exceeded, the association is terminated.
1841
1842	Default: 10
1843
1844max_init_retransmits - INTEGER
1845	The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
1846	that an association will attempt before declaring the destination
1847	unreachable and terminating.
1848
1849	Default: 8
1850
1851path_max_retrans - INTEGER
1852	The maximum number of retransmissions that will be attempted on a given
1853	path.  Once this threshold is exceeded, the path is considered
1854	unreachable, and new traffic will use a different path when the
1855	association is multihomed.
1856
1857	Default: 5
1858
1859pf_retrans - INTEGER
1860	The number of retransmissions that will be attempted on a given path
1861	before traffic is redirected to an alternate transport (should one
1862	exist).  Note this is distinct from path_max_retrans, as a path that
1863	passes the pf_retrans threshold can still be used.  Its only
1864	deprioritized when a transmission path is selected by the stack.  This
1865	setting is primarily used to enable fast failover mechanisms without
1866	having to reduce path_max_retrans to a very low value.  See:
1867	http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
1868	for details.  Note also that a value of pf_retrans > path_max_retrans
1869	disables this feature. Since both pf_retrans and path_max_retrans can
1870	be changed by userspace application, a variable pf_enable is used to
1871	disable pf state.
1872
1873	Default: 0
1874
1875rto_initial - INTEGER
1876	The initial round trip timeout value in milliseconds that will be used
1877	in calculating round trip times.  This is the initial time interval
1878	for retransmissions.
1879
1880	Default: 3000
1881
1882rto_max - INTEGER
1883	The maximum value (in milliseconds) of the round trip timeout.  This
1884	is the largest time interval that can elapse between retransmissions.
1885
1886	Default: 60000
1887
1888rto_min - INTEGER
1889	The minimum value (in milliseconds) of the round trip timeout.  This
1890	is the smallest time interval the can elapse between retransmissions.
1891
1892	Default: 1000
1893
1894hb_interval - INTEGER
1895	The interval (in milliseconds) between HEARTBEAT chunks.  These chunks
1896	are sent at the specified interval on idle paths to probe the state of
1897	a given path between 2 associations.
1898
1899	Default: 30000
1900
1901sack_timeout - INTEGER
1902	The amount of time (in milliseconds) that the implementation will wait
1903	to send a SACK.
1904
1905	Default: 200
1906
1907valid_cookie_life - INTEGER
1908	The default lifetime of the SCTP cookie (in milliseconds).  The cookie
1909	is used during association establishment.
1910
1911	Default: 60000
1912
1913cookie_preserve_enable - BOOLEAN
1914	Enable or disable the ability to extend the lifetime of the SCTP cookie
1915	that is used during the establishment phase of SCTP association
1916
1917	1: Enable cookie lifetime extension.
1918	0: Disable
1919
1920	Default: 1
1921
1922cookie_hmac_alg - STRING
1923	Select the hmac algorithm used when generating the cookie value sent by
1924	a listening sctp socket to a connecting client in the INIT-ACK chunk.
1925	Valid values are:
1926	* md5
1927	* sha1
1928	* none
1929	Ability to assign md5 or sha1 as the selected alg is predicated on the
1930	configuration of those algorithms at build time (CONFIG_CRYPTO_MD5 and
1931	CONFIG_CRYPTO_SHA1).
1932
1933	Default: Dependent on configuration.  MD5 if available, else SHA1 if
1934	available, else none.
1935
1936rcvbuf_policy - INTEGER
1937	Determines if the receive buffer is attributed to the socket or to
1938	association.   SCTP supports the capability to create multiple
1939	associations on a single socket.  When using this capability, it is
1940	possible that a single stalled association that's buffering a lot
1941	of data may block other associations from delivering their data by
1942	consuming all of the receive buffer space.  To work around this,
1943	the rcvbuf_policy could be set to attribute the receiver buffer space
1944	to each association instead of the socket.  This prevents the described
1945	blocking.
1946
1947	1: rcvbuf space is per association
1948	0: rcvbuf space is per socket
1949
1950	Default: 0
1951
1952sndbuf_policy - INTEGER
1953	Similar to rcvbuf_policy above, this applies to send buffer space.
1954
1955	1: Send buffer is tracked per association
1956	0: Send buffer is tracked per socket.
1957
1958	Default: 0
1959
1960sctp_mem - vector of 3 INTEGERs: min, pressure, max
1961	Number of pages allowed for queueing by all SCTP sockets.
1962
1963	min: Below this number of pages SCTP is not bothered about its
1964	memory appetite. When amount of memory allocated by SCTP exceeds
1965	this number, SCTP starts to moderate memory usage.
1966
1967	pressure: This value was introduced to follow format of tcp_mem.
1968
1969	max: Number of pages allowed for queueing by all SCTP sockets.
1970
1971	Default is calculated at boot time from amount of available memory.
1972
1973sctp_rmem - vector of 3 INTEGERs: min, default, max
1974	Only the first value ("min") is used, "default" and "max" are
1975	ignored.
1976
1977	min: Minimal size of receive buffer used by SCTP socket.
1978	It is guaranteed to each SCTP socket (but not association) even
1979	under moderate memory pressure.
1980
1981	Default: 1 page
1982
1983sctp_wmem  - vector of 3 INTEGERs: min, default, max
1984	Currently this tunable has no effect.
1985
1986addr_scope_policy - INTEGER
1987	Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
1988
1989	0   - Disable IPv4 address scoping
1990	1   - Enable IPv4 address scoping
1991	2   - Follow draft but allow IPv4 private addresses
1992	3   - Follow draft but allow IPv4 link local addresses
1993
1994	Default: 1
1995
1996
1997/proc/sys/net/core/*
1998	Please see: Documentation/sysctl/net.txt for descriptions of these entries.
1999
2000
2001/proc/sys/net/unix/*
2002max_dgram_qlen - INTEGER
2003	The maximum length of dgram socket receive queue
2004
2005	Default: 10
2006
2007
2008UNDOCUMENTED:
2009
2010/proc/sys/net/irda/*
2011	fast_poll_increase FIXME
2012	warn_noreply_time FIXME
2013	discovery_slots FIXME
2014	slot_timeout FIXME
2015	max_baud_rate FIXME
2016	discovery_timeout FIXME
2017	lap_keepalive_time FIXME
2018	max_noreply_time FIXME
2019	max_tx_data_size FIXME
2020	max_tx_window FIXME
2021	min_tx_turn_time FIXME