summaryrefslogtreecommitdiff
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt10
-rw-r--r--Documentation/devicetree/bindings/net/brcm,systemport.txt5
-rw-r--r--Documentation/devicetree/bindings/net/cpsw.txt3
-rw-r--r--Documentation/devicetree/bindings/net/dsa/dsa.txt20
-rw-r--r--Documentation/devicetree/bindings/net/dsa/marvell.txt93
-rw-r--r--Documentation/devicetree/bindings/net/meson-dwmac.txt16
-rw-r--r--Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt3
-rw-r--r--Documentation/devicetree/bindings/net/stmmac.txt3
-rw-r--r--Documentation/devicetree/bindings/net/wireless/ieee80211.txt24
-rw-r--r--Documentation/driver-api/80211/cfg80211.rst3
-rw-r--r--Documentation/networking/dsa/dsa.txt24
-rw-r--r--Documentation/networking/ip-sysctl.txt40
-rw-r--r--Documentation/networking/packet_mmap.txt9
-rw-r--r--Documentation/networking/regulatory.txt8
-rw-r--r--Documentation/siphash.txt175
-rw-r--r--Documentation/sysctl/net.txt21
16 files changed, 355 insertions, 102 deletions
diff --git a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
index fb40891ee606..9a734d808aa7 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
@@ -2,7 +2,7 @@
Required properties:
-- compatible: should be "brcm,bcm7445-switch-v4.0"
+- compatible: should be "brcm,bcm7445-switch-v4.0" or "brcm,bcm7278-switch-v4.0"
- reg: addresses and length of the register sets for the device, must be 6
pairs of register addresses and lengths
- interrupts: interrupts for the devices, must be two interrupts
@@ -41,6 +41,13 @@ Optional properties:
Admission Control Block supports reporting the number of packets in-flight in a
switch queue
+Port subnodes:
+
+Optional properties:
+
+- brcm,use-bcm-hdr: boolean property, if present, indicates that the switch
+ port has Broadcom tags enabled (per-packet metadata)
+
Example:
switch_top@f0b00000 {
@@ -114,6 +121,7 @@ switch_top@f0b00000 {
port@0 {
label = "gphy";
reg = <0>;
+ brcm,use-bcm-hdr;
};
...
};
diff --git a/Documentation/devicetree/bindings/net/brcm,systemport.txt b/Documentation/devicetree/bindings/net/brcm,systemport.txt
index 877da34145b0..83f29e0e11ba 100644
--- a/Documentation/devicetree/bindings/net/brcm,systemport.txt
+++ b/Documentation/devicetree/bindings/net/brcm,systemport.txt
@@ -1,7 +1,10 @@
* Broadcom BCM7xxx Ethernet Systemport Controller (SYSTEMPORT)
Required properties:
-- compatible: should be one of "brcm,systemport-v1.00" or "brcm,systemport"
+- compatible: should be one of:
+ "brcm,systemport-v1.00"
+ "brcm,systemportlite-v1.00" or
+ "brcm,systemport"
- reg: address and length of the register set for the device.
- interrupts: interrupts for the device, first cell must be for the rx
interrupts, and the second cell should be for the transmit queues. An
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index ebda7c93453a..7cc15c96ea95 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -23,7 +23,6 @@ Required properties:
Optional properties:
- ti,hwmods : Must be "cpgmac0"
-- no_bd_ram : Must be 0 or 1
- dual_emac : Specifies Switch to act as Dual EMAC
- syscon : Phandle to the system control device node, which is
the control module device of the am33x
@@ -70,7 +69,6 @@ Examples:
cpdma_channels = <8>;
ale_entries = <1024>;
bd_ram_size = <0x2000>;
- no_bd_ram = <0>;
rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
@@ -99,7 +97,6 @@ Examples:
cpdma_channels = <8>;
ale_entries = <1024>;
bd_ram_size = <0x2000>;
- no_bd_ram = <0>;
rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index a4a570fb2494..cfe8f64eca4f 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -34,13 +34,9 @@ Required properties:
Each port children node must have the following mandatory properties:
- reg : Describes the port address in the switch
-- label : Describes the label associated with this port, which
- will become the netdev name. Special labels are
- "cpu" to indicate a CPU port and "dsa" to
- indicate an uplink/downlink port between switches in
- the cluster.
-A port labelled "dsa" has the following mandatory property:
+An uplink/downlink port between switches in the cluster has the following
+mandatory property:
- link : Should be a list of phandles to other switch's DSA
port. This port is used as the outgoing port
@@ -48,12 +44,17 @@ A port labelled "dsa" has the following mandatory property:
information must be given, not just the one hop
routes to neighbouring switches.
-A port labelled "cpu" has the following mandatory property:
+A CPU port has the following mandatory property:
- ethernet : Should be a phandle to a valid Ethernet device node.
This host device is what the switch port is
connected to.
+A user port has the following optional property:
+
+- label : Describes the label associated with this port, which
+ will become the netdev name.
+
Port child nodes may also contain the following optional standardised
properties, described in binding documents:
@@ -107,7 +108,6 @@ linked into one DSA cluster.
switch0port5: port@5 {
reg = <5>;
- label = "dsa";
phy-mode = "rgmii-txid";
link = <&switch1port6
&switch2port9>;
@@ -119,7 +119,6 @@ linked into one DSA cluster.
port@6 {
reg = <6>;
- label = "cpu";
ethernet = <&fec1>;
fixed-link {
speed = <100>;
@@ -165,7 +164,6 @@ linked into one DSA cluster.
switch1port5: port@5 {
reg = <5>;
- label = "dsa";
link = <&switch2port9>;
phy-mode = "rgmii-txid";
fixed-link {
@@ -176,7 +174,6 @@ linked into one DSA cluster.
switch1port6: port@6 {
reg = <6>;
- label = "dsa";
phy-mode = "rgmii-txid";
link = <&switch0port5>;
fixed-link {
@@ -255,7 +252,6 @@ linked into one DSA cluster.
switch2port9: port@9 {
reg = <9>;
- label = "dsa";
phy-mode = "rgmii-txid";
link = <&switch1port5
&switch0port5>;
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
index b3dd6b40e0de..7ef9dbb08957 100644
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt
@@ -14,9 +14,9 @@ The properties described here are those specific to Marvell devices.
Additional required and optional properties can be found in dsa.txt.
Required properties:
-- compatible : Should be one of "marvell,mv88e6085" or
- "marvell,mv88e6190"
-- reg : Address on the MII bus for the switch.
+- compatible : Should be one of "marvell,mv88e6085" or
+ "marvell,mv88e6190"
+- reg : Address on the MII bus for the switch.
Optional properties:
@@ -26,30 +26,67 @@ Optional properties:
- interrupt-controller : Indicates the switch is itself an interrupt
controller. This is used for the PHY interrupts.
#interrupt-cells = <2> : Controller uses two cells, number and flag
-- mdio : container of PHY and devices on the switches MDIO
- bus
+- mdio : Container of PHY and devices on the switches MDIO
+ bus.
+- mdio? : Container of PHYs and devices on the external MDIO
+ bus. The node must contains a compatible string of
+ "marvell,mv88e6xxx-mdio-external"
+
Example:
- mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- interrupt-parent = <&gpio0>;
- interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
- interrupt-controller;
- #interrupt-cells = <2>;
-
- switch0: switch@0 {
- compatible = "marvell,mv88e6085";
- reg = <0>;
- reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
- };
- mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- switch1phy0: switch1phy0@0 {
- reg = <0>;
- interrupt-parent = <&switch0>;
- interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
- };
- };
- };
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = <&gpio0>;
+ interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+
+ switch0: switch@0 {
+ compatible = "marvell,mv88e6085";
+ reg = <0>;
+ reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
+ };
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy0: switch1phy0@0 {
+ reg = <0>;
+ interrupt-parent = <&switch0>;
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ };
+ };
+ };
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = <&gpio0>;
+ interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+
+ switch0: switch@0 {
+ compatible = "marvell,mv88e6390";
+ reg = <0>;
+ reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
+ };
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy0: switch1phy0@0 {
+ reg = <0>;
+ interrupt-parent = <&switch0>;
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ };
+ };
+
+ mdio1 {
+ compatible = "marvell,mv88e6xxx-mdio-external";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy9: switch1phy0@9 {
+ reg = <9>;
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/net/meson-dwmac.txt b/Documentation/devicetree/bindings/net/meson-dwmac.txt
index 89e62ddc69ca..0703ad3f3c1e 100644
--- a/Documentation/devicetree/bindings/net/meson-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/meson-dwmac.txt
@@ -25,6 +25,22 @@ Required properties on Meson8b and newer:
- "clkin0" - first parent clock of the internal mux
- "clkin1" - second parent clock of the internal mux
+Optional properties on Meson8b and newer:
+- amlogic,tx-delay-ns: The internal RGMII TX clock delay (provided
+ by this driver) in nanoseconds. Allowed values
+ are: 0ns, 2ns, 4ns, 6ns.
+ When phy-mode is set to "rgmii" then the TX
+ delay should be explicitly configured. When
+ not configured a fallback of 2ns is used.
+ When the phy-mode is set to either "rgmii-id"
+ or "rgmii-txid" the TX clock delay is already
+ provided by the PHY. In that case this
+ property should be set to 0ns (which disables
+ the TX clock delay in the MAC to prevent the
+ clock from going off because both PHY and MAC
+ are adding a delay).
+ Any configuration is ignored when the phy-mode
+ is set to "rmii".
Example for Meson6:
diff --git a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
index d93f71ce8346..21d27aa4c68c 100644
--- a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
+++ b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
@@ -1,5 +1,8 @@
* Synopsys DWC Ethernet QoS IP version 4.10 driver (GMAC)
+This binding is deprecated, but it continues to be supported, but new
+features should be preferably added to the stmmac binding document.
+
This binding supports the Synopsys Designware Ethernet QoS (Quality Of Service)
IP block. The IP supports multiple options for bus type, clocking and reset
structure, and feature list. Consequently, a number of properties and list
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 128da752fec9..d3bfc2b30fb5 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -49,6 +49,8 @@ Optional properties:
- snps,force_sf_dma_mode Force DMA to use the Store and Forward
mode for both tx and rx. This flag is
ignored if force_thresh_dma_mode is set.
+- snps,en-tx-lpi-clockgating Enable gating of the MAC TX clock during
+ TX low-power mode
- snps,multicast-filter-bins: Number of multicast filter hash bins
supported by this device instance
- snps,perfect-filter-entries: Number of perfect filter entries supported
@@ -65,7 +67,6 @@ Optional properties:
- snps,wr_osr_lmt: max write outstanding req. limit
- snps,rd_osr_lmt: max read outstanding req. limit
- snps,kbbe: do not cross 1KiB boundary.
- - snps,axi_all: align address
- snps,blen: this is a vector of supported burst length.
- snps,fb: fixed-burst
- snps,mb: mixed-burst
diff --git a/Documentation/devicetree/bindings/net/wireless/ieee80211.txt b/Documentation/devicetree/bindings/net/wireless/ieee80211.txt
new file mode 100644
index 000000000000..f6442b1397f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/wireless/ieee80211.txt
@@ -0,0 +1,24 @@
+Common IEEE 802.11 properties
+
+This provides documentation of common properties that are valid for all wireless
+devices.
+
+Optional properties:
+ - ieee80211-freq-limit : list of supported frequency ranges in KHz. This can be
+ used for devices that in a given config support less channels than
+ normally. It may happen chipset supports a wide wireless band but it is
+ limited to some part of it due to used antennas or power amplifier.
+ An example case for this can be tri-band wireless router with two
+ identical chipsets used for two different 5 GHz subbands. Using them
+ incorrectly could not work or decrease performance noticeably.
+
+Example:
+
+pcie@0,0 {
+ reg = <0x0000 0 0 0 0>;
+ wifi@0,0 {
+ reg = <0x0000 0 0 0 0>;
+ ieee80211-freq-limit = <2402000 2482000>,
+ <5170000 5250000>;
+ };
+};
diff --git a/Documentation/driver-api/80211/cfg80211.rst b/Documentation/driver-api/80211/cfg80211.rst
index b1e149ea6fee..eca534ab6172 100644
--- a/Documentation/driver-api/80211/cfg80211.rst
+++ b/Documentation/driver-api/80211/cfg80211.rst
@@ -45,6 +45,9 @@ Device registration
:functions: wiphy_new
.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_read_of_freq_limits
+
+.. kernel-doc:: include/net/cfg80211.h
:functions: wiphy_register
.. kernel-doc:: include/net/cfg80211.h
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index 63912ef34606..b8b40753133e 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -295,7 +295,6 @@ DSA currently leverages the following subsystems:
- MDIO/PHY library: drivers/net/phy/phy.c, mdio_bus.c
- Switchdev: net/switchdev/*
- Device Tree for various of_* functions
-- HWMON: drivers/hwmon/*
MDIO/PHY library
----------------
@@ -349,12 +348,6 @@ Documentation/devicetree/bindings/net/dsa/dsa.txt. PHY/MDIO library helper
functions such as of_get_phy_mode(), of_phy_connect() are also used to query
per-port PHY specific details: interface connection, MDIO bus location etc..
-HWMON
------
-
-Some switch drivers feature internal temperature sensors which are exposed as
-regular HWMON devices in /sys/class/hwmon/.
-
Driver development
==================
@@ -495,23 +488,6 @@ Power management
BR_STATE_DISABLED and propagating changes to the hardware if this port is
disabled while being a bridge member
-Hardware monitoring
--------------------
-
-These callbacks are only available if CONFIG_NET_DSA_HWMON is enabled:
-
-- get_temp: this function queries the given switch for its temperature
-
-- get_temp_limit: this function returns the switch current maximum temperature
- limit
-
-- set_temp_limit: this function configures the maximum temperature limit allowed
-
-- get_temp_alarm: this function returns the critical temperature threshold
- returning an alarm notification
-
-See Documentation/hwmon/sysfs-interface for details.
-
Bridge layer
------------
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 7dd65c9cf707..17f2e7791042 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -246,21 +246,12 @@ tcp_dsack - BOOLEAN
Allows TCP to send "duplicate" SACKs.
tcp_early_retrans - INTEGER
- Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
- for triggering fast retransmit when the amount of outstanding data is
- small and when no previously unsent data can be transmitted (such
- that limited transmit could be used). Also controls the use of
- Tail loss probe (TLP) that converts RTOs occurring due to tail
- losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
+ Tail loss probe (TLP) converts RTOs occurring due to tail
+ losses into fast recovery (draft-ietf-tcpm-rack). Note that
+ TLP requires RACK to function properly (see tcp_recovery below)
Possible values:
- 0 disables ER
- 1 enables ER
- 2 enables ER but delays fast recovery and fast retransmit
- by a fourth of RTT. This mitigates connection falsely
- recovers when network has a small degree of reordering
- (less than 3 packets).
- 3 enables delayed ER and TLP.
- 4 enables TLP only.
+ 0 disables TLP
+ 3 or 4 enables TLP
Default: 3
tcp_ecn - INTEGER
@@ -712,18 +703,6 @@ tcp_thin_linear_timeouts - BOOLEAN
Documentation/networking/tcp-thin.txt
Default: 0
-tcp_thin_dupack - BOOLEAN
- Enable dynamic triggering of retransmissions after one dupACK
- for thin streams. If set, a check is performed upon reception
- of a dupACK to determine if the stream is thin (less than 4
- packets in flight). As long as the stream is found to be thin,
- data is retransmitted on the first received dupACK. This
- improves retransmission latency for non-aggressive thin
- streams, often found to be time-dependent.
- For more information on thin streams, see
- Documentation/networking/tcp-thin.txt
- Default: 0
-
tcp_limit_output_bytes - INTEGER
Controls TCP Small Queue limit per tcp socket.
TCP bulk sender tends to increase packets in flight until it
@@ -843,6 +822,15 @@ ip_local_reserved_ports - list of comma separated ranges
Default: Empty
+ip_unprivileged_port_start - INTEGER
+ This is a per-namespace sysctl. It defines the first
+ unprivileged port in the network namespace. Privileged ports
+ require root or CAP_NET_BIND_SERVICE in order to bind to them.
+ To disable all privileged ports, set this to 0. It may not
+ overlap with the ip_local_reserved_ports range.
+
+ Default: 1024
+
ip_nonlocal_bind - BOOLEAN
If set, allows processes to bind() to non-local IP addresses,
which can be quite useful - but may break some applications.
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index daa015af16a0..f3b9e507ab05 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -565,7 +565,7 @@ TPACKET_V1 --> TPACKET_V2:
(void *)hdr + TPACKET_ALIGN(sizeof(struct tpacket_hdr))
TPACKET_V2 --> TPACKET_V3:
- - Flexible buffer implementation:
+ - Flexible buffer implementation for RX_RING:
1. Blocks can be configured with non-static frame-size
2. Read/poll is at a block-level (as opposed to packet-level)
3. Added poll timeout to avoid indefinite user-space wait
@@ -574,7 +574,12 @@ TPACKET_V2 --> TPACKET_V3:
4.1 block::timeout
4.2 tpkt_hdr::sk_rxhash
- RX Hash data available in user space
- - Currently only RX_RING available
+ - TX_RING semantics are conceptually similar to TPACKET_V2;
+ use tpacket3_hdr instead of tpacket2_hdr, and TPACKET3_HDRLEN
+ instead of TPACKET2_HDRLEN. In the current implementation,
+ the tp_next_offset field in the tpacket3_hdr MUST be set to
+ zero, indicating that the ring does not hold variable sized frames.
+ Packets with non-zero values of tp_next_offset will be dropped.
-------------------------------------------------------------------------------
+ AF_PACKET fanout mode
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index 356f791af574..7818b5fe448b 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -156,12 +156,12 @@ struct ieee80211_regdomain mydriver_jp_regdom = {
//.alpha2 = "99", /* If I have no alpha2 to map it to */
.reg_rules = {
/* IEEE 802.11b/g, channels 1..14 */
- REG_RULE(2412-20, 2484+20, 40, 6, 20, 0),
+ REG_RULE(2412-10, 2484+10, 40, 6, 20, 0),
/* IEEE 802.11a, channels 34..48 */
- REG_RULE(5170-20, 5240+20, 40, 6, 20,
+ REG_RULE(5170-10, 5240+10, 40, 6, 20,
NL80211_RRF_NO_IR),
/* IEEE 802.11a, channels 52..64 */
- REG_RULE(5260-20, 5320+20, 40, 6, 20,
+ REG_RULE(5260-10, 5320+10, 40, 6, 20,
NL80211_RRF_NO_IR|
NL80211_RRF_DFS),
}
@@ -205,7 +205,7 @@ the data in regdb.c as an alternative to using CRDA.
The file net/wireless/db.txt should be kept up-to-date with the db.txt
file available in the git repository here:
- git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/sforshee/wireless-regdb.git
Again, most users in most situations should be using the CRDA package
provided with their distribution, and in most other situations users
diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
new file mode 100644
index 000000000000..908d348ff777
--- /dev/null
+++ b/Documentation/siphash.txt
@@ -0,0 +1,175 @@
+ SipHash - a short input PRF
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@zx2c4.com>
+
+SipHash is a cryptographically secure PRF -- a keyed hash function -- that
+performs very well for short inputs, hence the name. It was designed by
+cryptographers Daniel J. Bernstein and Jean-Philippe Aumasson. It is intended
+as a replacement for some uses of: `jhash`, `md5_transform`, `sha_transform`,
+and so forth.
+
+SipHash takes a secret key filled with randomly generated numbers and either
+an input buffer or several input integers. It spits out an integer that is
+indistinguishable from random. You may then use that integer as part of secure
+sequence numbers, secure cookies, or mask it off for use in a hash table.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+siphash_key_t key;
+get_random_bytes(&key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u64 siphash(const void *data, size_t len, const siphash_key_t *key);
+
+And:
+
+u64 siphash_1u64(u64, const siphash_key_t *key);
+u64 siphash_2u64(u64, u64, const siphash_key_t *key);
+u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
+u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
+u64 siphash_1u32(u32, const siphash_key_t *key);
+u64 siphash_2u32(u32, u32, const siphash_key_t *key);
+u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
+u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
+
+If you pass the generic siphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+ DECLARE_HASHTABLE(hashtable, 8);
+ siphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+ get_random_bytes(&table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+ return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Security
+
+SipHash has a very high security margin, with its 128-bit key. So long as the
+key is kept secret, it is impossible for an attacker to guess the outputs of
+the function, even if being able to observe many outputs, since 2^128 outputs
+is significant.
+
+Linux implements the "2-4" variant of SipHash.
+
+5. Struct-passing Pitfalls
+
+Often times the XuY functions will not be large enough, and instead you'll
+want to pass a pre-filled struct to siphash. When doing this, it's important
+to always ensure the struct has no padding holes. The easiest way to do this
+is to simply arrange the members of the struct in descending order of size,
+and to use offsetendof() instead of sizeof() for getting the size. For
+performance reasons, if possible, it's probably a good thing to align the
+struct to the right boundary. Here's an example:
+
+const struct {
+ struct in6_addr saddr;
+ u32 counter;
+ u16 dport;
+} __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .counter = counter,
+ .dport = dport
+};
+u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
+
+6. Resources
+
+Read the SipHash paper if you're interested in learning more:
+https://131002.net/siphash/siphash.pdf
+
+
+~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
+
+HalfSipHash - SipHash's insecure younger cousin
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@zx2c4.com>
+
+On the off-chance that SipHash is not fast enough for your needs, you might be
+able to justify using HalfSipHash, a terrifying but potentially useful
+possibility. HalfSipHash cuts SipHash's rounds down from "2-4" to "1-3" and,
+even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output)
+instead of SipHash's 128-bit key. However, this may appeal to some
+high-performance `jhash` users.
+
+Danger!
+
+Do not ever use HalfSipHash except for as a hashtable key function, and only
+then when you can be absolutely certain that the outputs will never be
+transmitted out of the kernel. This is only remotely useful over `jhash` as a
+means of mitigating hashtable flooding denial of service attacks.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+hsiphash_key_t key;
+get_random_bytes(&key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
+
+And:
+
+u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
+u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
+u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
+u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key);
+
+If you pass the generic hsiphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+ DECLARE_HASHTABLE(hashtable, 8);
+ hsiphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+ get_random_bytes(&table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+ return &table->hashtable[hsiphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Performance
+
+HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements,
+this will not be a problem, as the hashtable lookup isn't the bottleneck. And
+in general, this is probably a good sacrifice to make for the security and DoS
+resistance of HalfSipHash.
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index f0480f7ea740..b80fbd4e5575 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -61,6 +61,27 @@ The maximum number of packets that kernel can handle on a NAPI interrupt,
it's a Per-CPU variable.
Default: 64
+dev_weight_rx_bias
+--------------
+
+RPS (e.g. RFS, aRFS) processing is competing with the registered NAPI poll function
+of the driver for the per softirq cycle netdev_budget. This parameter influences
+the proportion of the configured netdev_budget that is spent on RPS based packet
+processing during RX softirq cycles. It is further meant for making current
+dev_weight adaptable for asymmetric CPU needs on RX/TX side of the network stack.
+(see dev_weight_tx_bias) It is effective on a per CPU basis. Determination is based
+on dev_weight and is calculated multiplicative (dev_weight * dev_weight_rx_bias).
+Default: 1
+
+dev_weight_tx_bias
+--------------
+
+Scales the maximum number of packets that can be processed during a TX softirq cycle.
+Effective on a per CPU basis. Allows scaling of current dev_weight for asymmetric
+net stack processing needs. Be careful to avoid making TX softirq processing a CPU hog.
+Calculation is based on dev_weight (dev_weight * dev_weight_tx_bias).
+Default: 1
+
default_qdisc
--------------
generated by cgit (git 2.34.1) at 2024-06-29 02:55:59 +0000