1================================
2Documentation for /proc/sys/net/
3================================
4
5Copyright
6
7Copyright (c) 1999
8
9	- Terrehon Bowden <terrehon@pacbell.net>
10	- Bodo Bauer <bb@ricochet.net>
11
12Copyright (c) 2000
13
14	- Jorge Nerin <comandante@zaralinux.com>
15
16Copyright (c) 2009
17
18	- Shen Feng <shen@cn.fujitsu.com>
19
20For general info and legal blurb, please look in index.rst.
21
22------------------------------------------------------------------------------
23
24This file contains the documentation for the sysctl files in
25/proc/sys/net
26
27The interface  to  the  networking  parts  of  the  kernel  is  located  in
28/proc/sys/net. The following table shows all possible subdirectories.  You may
29see only some of them, depending on your kernel's configuration.
30
31
32Table : Subdirectories in /proc/sys/net
33
34 ========= =================== = ========== ===================
35 Directory Content               Directory  Content
36 ========= =================== = ========== ===================
37 802       E802 protocol         mptcp      Multipath TCP
38 appletalk Appletalk protocol    netfilter  Network Filter
39 ax25      AX25                  netrom     NET/ROM
40 bridge    Bridging              rose       X.25 PLP layer
41 core      General parameter     tipc       TIPC
42 ethernet  Ethernet protocol     unix       Unix domain sockets
43 ipv4      IP version 4          x25        X.25 protocol
44 ipv6      IP version 6
45 ========= =================== = ========== ===================
46
471. /proc/sys/net/core - Network core options
48============================================
49
50bpf_jit_enable
51--------------
52
53This enables the BPF Just in Time (JIT) compiler. BPF is a flexible
54and efficient infrastructure allowing to execute bytecode at various
55hook points. It is used in a number of Linux kernel subsystems such
56as networking (e.g. XDP, tc), tracing (e.g. kprobes, uprobes, tracepoints)
57and security (e.g. seccomp). LLVM has a BPF back end that can compile
58restricted C into a sequence of BPF instructions. After program load
59through bpf(2) and passing a verifier in the kernel, a JIT will then
60translate these BPF proglets into native CPU instructions. There are
61two flavors of JITs, the newer eBPF JIT currently supported on:
62
63  - x86_64
64  - x86_32
65  - arm64
66  - arm32
67  - ppc64
68  - ppc32
69  - sparc64
70  - mips64
71  - s390x
72  - riscv64
73  - riscv32
74
75And the older cBPF JIT supported on the following archs:
76
77  - mips
78  - sparc
79
80eBPF JITs are a superset of cBPF JITs, meaning the kernel will
81migrate cBPF instructions into eBPF instructions and then JIT
82compile them transparently. Older cBPF JITs can only translate
83tcpdump filters, seccomp rules, etc, but not mentioned eBPF
84programs loaded through bpf(2).
85
86Values:
87
88	- 0 - disable the JIT (default value)
89	- 1 - enable the JIT
90	- 2 - enable the JIT and ask the compiler to emit traces on kernel log.
91
92bpf_jit_harden
93--------------
94
95This enables hardening for the BPF JIT compiler. Supported are eBPF
96JIT backends. Enabling hardening trades off performance, but can
97mitigate JIT spraying.
98
99Values:
100
101	- 0 - disable JIT hardening (default value)
102	- 1 - enable JIT hardening for unprivileged users only
103	- 2 - enable JIT hardening for all users
104
105where "privileged user" in this context means a process having
106CAP_BPF or CAP_SYS_ADMIN in the root user name space.
107
108bpf_jit_kallsyms
109----------------
110
111When BPF JIT compiler is enabled, then compiled images are unknown
112addresses to the kernel, meaning they neither show up in traces nor
113in /proc/kallsyms. This enables export of these addresses, which can
114be used for debugging/tracing. If bpf_jit_harden is enabled, this
115feature is disabled.
116
117Values :
118
119	- 0 - disable JIT kallsyms export (default value)
120	- 1 - enable JIT kallsyms export for privileged users only
121
122bpf_jit_limit
123-------------
124
125This enforces a global limit for memory allocations to the BPF JIT
126compiler in order to reject unprivileged JIT requests once it has
127been surpassed. bpf_jit_limit contains the value of the global limit
128in bytes.
129
130dev_weight
131----------
132
133The maximum number of packets that kernel can handle on a NAPI interrupt,
134it's a Per-CPU variable. For drivers that support LRO or GRO_HW, a hardware
135aggregated packet is counted as one packet in this context.
136
137Default: 64
138
139dev_weight_rx_bias
140------------------
141
142RPS (e.g. RFS, aRFS) processing is competing with the registered NAPI poll function
143of the driver for the per softirq cycle netdev_budget. This parameter influences
144the proportion of the configured netdev_budget that is spent on RPS based packet
145processing during RX softirq cycles. It is further meant for making current
146dev_weight adaptable for asymmetric CPU needs on RX/TX side of the network stack.
147(see dev_weight_tx_bias) It is effective on a per CPU basis. Determination is based
148on dev_weight and is calculated multiplicative (dev_weight * dev_weight_rx_bias).
149
150Default: 1
151
152dev_weight_tx_bias
153------------------
154
155Scales the maximum number of packets that can be processed during a TX softirq cycle.
156Effective on a per CPU basis. Allows scaling of current dev_weight for asymmetric
157net stack processing needs. Be careful to avoid making TX softirq processing a CPU hog.
158
159Calculation is based on dev_weight (dev_weight * dev_weight_tx_bias).
160
161Default: 1
162
163default_qdisc
164-------------
165
166The default queuing discipline to use for network devices. This allows
167overriding the default of pfifo_fast with an alternative. Since the default
168queuing discipline is created without additional parameters so is best suited
169to queuing disciplines that work well without configuration like stochastic
170fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use
171queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin
172which require setting up classes and bandwidths. Note that physical multiqueue
173interfaces still use mq as root qdisc, which in turn uses this default for its
174leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead
175default to noqueue.
176
177Default: pfifo_fast
178
179busy_read
180---------
181
182Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)
183Approximate time in us to busy loop waiting for packets on the device queue.
184This sets the default value of the SO_BUSY_POLL socket option.
185Can be set or overridden per socket by setting socket option SO_BUSY_POLL,
186which is the preferred method of enabling. If you need to enable the feature
187globally via sysctl, a value of 50 is recommended.
188
189Will increase power usage.
190
191Default: 0 (off)
192
193busy_poll
194----------------
195Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL)
196Approximate time in us to busy loop waiting for events.
197Recommended value depends on the number of sockets you poll on.
198For several sockets 50, for several hundreds 100.
199For more than that you probably want to use epoll.
200Note that only sockets with SO_BUSY_POLL set will be busy polled,
201so you want to either selectively set SO_BUSY_POLL on those sockets or set
202sysctl.net.busy_read globally.
203
204Will increase power usage.
205
206Default: 0 (off)
207
208mem_pcpu_rsv
209------------
210
211Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU.
212
213rmem_default
214------------
215
216The default setting of the socket receive buffer in bytes.
217
218rmem_max
219--------
220
221The maximum receive socket buffer size in bytes.
222
223rps_default_mask
224----------------
225
226The default RPS CPU mask used on newly created network devices. An empty
227mask means RPS disabled by default.
228
229tstamp_allow_data
230-----------------
231Allow processes to receive tx timestamps looped together with the original
232packet contents. If disabled, transmit timestamp requests from unprivileged
233processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set.
234
235Default: 1 (on)
236
237
238wmem_default
239------------
240
241The default setting (in bytes) of the socket send buffer.
242
243wmem_max
244--------
245
246The maximum send socket buffer size in bytes.
247
248message_burst and message_cost
249------------------------------
250
251These parameters  are used to limit the warning messages written to the kernel
252log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
253denial-of-service attack  impossible. A higher message_cost factor, results in
254fewer messages that will be written. Message_burst controls when messages will
255be dropped.  The  default  settings  limit  warning messages to one every five
256seconds.
257
258warnings
259--------
260
261This sysctl is now unused.
262
263This was used to control console messages from the networking stack that
264occur because of problems on the network like duplicate address or bad
265checksums.
266
267These messages are now emitted at KERN_DEBUG and can generally be enabled
268and controlled by the dynamic_debug facility.
269
270netdev_budget
271-------------
272
273Maximum number of packets taken from all interfaces in one polling cycle (NAPI
274poll). In one polling cycle interfaces which are registered to polling are
275probed in a round-robin manner. Also, a polling cycle may not exceed
276netdev_budget_usecs microseconds, even if netdev_budget has not been
277exhausted.
278
279netdev_budget_usecs
280---------------------
281
282Maximum number of microseconds in one NAPI polling cycle. Polling
283will exit when either netdev_budget_usecs have elapsed during the
284poll cycle or the number of packets processed reaches netdev_budget.
285
286netdev_max_backlog
287------------------
288
289Maximum number of packets, queued on the INPUT side, when the interface
290receives packets faster than kernel can process them.
291
292netdev_rss_key
293--------------
294
295RSS (Receive Side Scaling) enabled drivers use a 40 bytes host key that is
296randomly generated.
297Some user space might need to gather its content even if drivers do not
298provide ethtool -x support yet.
299
300::
301
302  myhost:~# cat /proc/sys/net/core/netdev_rss_key
303  84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8: ... (52 bytes total)
304
305File contains nul bytes if no driver ever called netdev_rss_key_fill() function.
306
307Note:
308  /proc/sys/net/core/netdev_rss_key contains 52 bytes of key,
309  but most drivers only use 40 bytes of it.
310
311::
312
313  myhost:~# ethtool -x eth0
314  RX flow hash indirection table for eth0 with 8 RX ring(s):
315      0:    0     1     2     3     4     5     6     7
316  RSS hash key:
317  84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
318
319netdev_tstamp_prequeue
320----------------------
321
322If set to 0, RX packet timestamps can be sampled after RPS processing, when
323the target CPU processes packets. It might give some delay on timestamps, but
324permit to distribute the load on several cpus.
325
326If set to 1 (default), timestamps are sampled as soon as possible, before
327queueing.
328
329netdev_unregister_timeout_secs
330------------------------------
331
332Unregister network device timeout in seconds.
333This option controls the timeout (in seconds) used to issue a warning while
334waiting for a network device refcount to drop to 0 during device
335unregistration. A lower value may be useful during bisection to detect
336a leaked reference faster. A larger value may be useful to prevent false
337warnings on slow/loaded systems.
338Default value is 10, minimum 1, maximum 3600.
339
340skb_defer_max
341-------------
342
343Max size (in skbs) of the per-cpu list of skbs being freed
344by the cpu which allocated them. Used by TCP stack so far.
345
346Default: 64
347
348optmem_max
349----------
350
351Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
352of struct cmsghdr structures with appended data.
353
354fb_tunnels_only_for_init_net
355----------------------------
356
357Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
358sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities
359(a) value = 0; respective fallback tunnels are created when module is
360loaded in every net namespaces (backward compatible behavior).
361(b) value = 1; [kcmd value: initns] respective fallback tunnels are
362created only in init net namespace and every other net namespace will
363not have them.
364(c) value = 2; [kcmd value: none] fallback tunnels are not created
365when a module is loaded in any of the net namespace. Setting value to
366"2" is pointless after boot if these modules are built-in, so there is
367a kernel command-line option that can change this default. Please refer to
368Documentation/admin-guide/kernel-parameters.txt for additional details.
369
370Not creating fallback tunnels gives control to userspace to create
371whatever is needed only and avoid creating devices which are redundant.
372
373Default : 0  (for compatibility reasons)
374
375devconf_inherit_init_net
376------------------------
377
378Controls if a new network namespace should inherit all current
379settings under /proc/sys/net/{ipv4,ipv6}/conf/{all,default}/. By
380default, we keep the current behavior: for IPv4 we inherit all current
381settings from init_net and for IPv6 we reset all settings to default.
382
383If set to 1, both IPv4 and IPv6 settings are forced to inherit from
384current ones in init_net. If set to 2, both IPv4 and IPv6 settings are
385forced to reset to their default values. If set to 3, both IPv4 and IPv6
386settings are forced to inherit from current ones in the netns where this
387new netns has been created.
388
389Default : 0  (for compatibility reasons)
390
391txrehash
392--------
393
394Controls default hash rethink behaviour on socket when SO_TXREHASH option is set
395to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt).
396
397If set to 1 (default), hash rethink is performed on listening socket.
398If set to 0, hash rethink is not performed.
399
400gro_normal_batch
401----------------
402
403Maximum number of the segments to batch up on output of GRO. When a packet
404exits GRO, either as a coalesced superframe or as an original packet which
405GRO has decided not to coalesce, it is placed on a per-NAPI list. This
406list is then passed to the stack when the number of segments reaches the
407gro_normal_batch limit.
408
409high_order_alloc_disable
410------------------------
411
412By default the allocator for page frags tries to use high order pages (order-3
413on x86). While the default behavior gives good results in most cases, some users
414might have hit a contention in page allocations/freeing. This was especially
415true on older kernels (< 5.14) when high-order pages were not stored on per-cpu
416lists. This allows to opt-in for order-0 allocation instead but is now mostly of
417historical importance.
418
419Default: 0
420
4212. /proc/sys/net/unix - Parameters for Unix domain sockets
422----------------------------------------------------------
423
424There is only one file in this directory.
425unix_dgram_qlen limits the max number of datagrams queued in Unix domain
426socket's buffer. It will not take effect unless PF_UNIX flag is specified.
427
428
4293. /proc/sys/net/ipv4 - IPV4 settings
430-------------------------------------
431Please see: Documentation/networking/ip-sysctl.rst and
432Documentation/admin-guide/sysctl/net.rst for descriptions of these entries.
433
434
4354. Appletalk
436------------
437
438The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
439when Appletalk is loaded. The configurable parameters are:
440
441aarp-expiry-time
442----------------
443
444The amount  of  time  we keep an ARP entry before expiring it. Used to age out
445old hosts.
446
447aarp-resolve-time
448-----------------
449
450The amount of time we will spend trying to resolve an Appletalk address.
451
452aarp-retransmit-limit
453---------------------
454
455The number of times we will retransmit a query before giving up.
456
457aarp-tick-time
458--------------
459
460Controls the rate at which expires are checked.
461
462The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
463on a machine.
464
465The fields  indicate  the DDP type, the local address (in network:node format)
466the remote  address,  the  size of the transmit pending queue, the size of the
467received queue  (bytes waiting for applications to read) the state and the uid
468owning the socket.
469
470/proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
471shows the  name  of the interface, its Appletalk address, the network range on
472that address  (or  network number for phase 1 networks), and the status of the
473interface.
474
475/proc/net/atalk_route lists  each  known  network  route.  It lists the target
476(network) that the route leads to, the router (may be directly connected), the
477route flags, and the device the route is using.
478
4795. TIPC
480-------
481
482tipc_rmem
483---------
484
485The TIPC protocol now has a tunable for the receive memory, similar to the
486tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max)
487
488::
489
490    # cat /proc/sys/net/tipc/tipc_rmem
491    4252725 34021800        68043600
492    #
493
494The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values
495are scaled (shifted) versions of that same value.  Note that the min value
496is not at this point in time used in any meaningful way, but the triplet is
497preserved in order to be consistent with things like tcp_rmem.
498
499named_timeout
500-------------
501
502TIPC name table updates are distributed asynchronously in a cluster, without
503any form of transaction handling. This means that different race scenarios are
504possible. One such is that a name withdrawal sent out by one node and received
505by another node may arrive after a second, overlapping name publication already
506has been accepted from a third node, although the conflicting updates
507originally may have been issued in the correct sequential order.
508If named_timeout is nonzero, failed topology updates will be placed on a defer
509queue until another event arrives that clears the error, or until the timeout
510expires. Value is in milliseconds.
511