Skip to content

Commit f9da455

Browse files
committed
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov. 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J Benniston. 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn Mork. 4) BPF now has a "random" opcode, from Chema Gonzalez. 5) Add more BPF documentation and improve test framework, from Daniel Borkmann. 6) Support TCP fastopen over ipv6, from Daniel Lee. 7) Add software TSO helper functions and use them to support software TSO in mvneta and mv643xx_eth drivers. From Ezequiel Garcia. 8) Support software TSO in fec driver too, from Nimrod Andy. 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli. 10) Handle broadcasts more gracefully over macvlan when there are large numbers of interfaces configured, from Herbert Xu. 11) Allow more control over fwmark used for non-socket based responses, from Lorenzo Colitti. 12) Do TCP congestion window limiting based upon measurements, from Neal Cardwell. 13) Support busy polling in SCTP, from Neal Horman. 14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru. 15) Bridge promisc mode handling improvements from Vlad Yasevich. 16) Don't use inetpeer entries to implement ID generation any more, it performs poorly, from Eric Dumazet. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits) rtnetlink: fix userspace API breakage for iproute2 < v3.9.0 tcp: fixing TLP's FIN recovery net: fec: Add software TSO support net: fec: Add Scatter/gather support net: fec: Increase buffer descriptor entry number net: fec: Factorize feature setting net: fec: Enable IP header hardware checksum net: fec: Factorize the .xmit transmit function bridge: fix compile error when compiling without IPv6 support bridge: fix smatch warning / potential null pointer dereference via-rhine: fix full-duplex with autoneg disable bnx2x: Enlarge the dorq threshold for VFs bnx2x: Check for UNDI in uncommon branch bnx2x: Fix 1G-baseT link bnx2x: Fix link for KR with swapped polarity lane sctp: Fix sk_ack_backlog wrap-around problem net/core: Add VF link state control policy net/fsl: xgmac_mdio is dependent on OF_MDIO net/fsl: Make xgmac_mdio read error message useful net_sched: drr: warn when qdisc is not work conserving ...
2 parents 0e04c64 + e5eca6d commit f9da455

File tree

1,265 files changed

+61466
-22881
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

1,265 files changed

+61466
-22881
lines changed

Documentation/ABI/testing/sysfs-class-net

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -169,6 +169,14 @@ Description:
169169
"unknown", "notpresent", "down", "lowerlayerdown", "testing",
170170
"dormant", "up".
171171

172+
What: /sys/class/net/<iface>/phys_port_id
173+
Date: July 2013
174+
KernelVersion: 3.12
175+
Contact: netdev@vger.kernel.org
176+
Description:
177+
Indicates the interface unique physical port identifier within
178+
the NIC, as a string.
179+
172180
What: /sys/class/net/<iface>/speed
173181
Date: October 2009
174182
KernelVersion: 2.6.33
Lines changed: 149 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,149 @@
1+
What: /sys/class/net/<iface>/cdc_ncm/min_tx_pkt
2+
Date: May 2014
3+
KernelVersion: 3.16
4+
Contact: Bjørn Mork <bjorn@mork.no>
5+
Description:
6+
The driver will pad NCM Transfer Blocks (NTBs) longer
7+
than this to tx_max, allowing the device to receive
8+
tx_max sized frames with no terminating short
9+
packet. NTBs shorter than this limit are transmitted
10+
as-is, without any padding, and are terminated with a
11+
short USB packet.
12+
13+
Padding to tx_max allows the driver to transmit NTBs
14+
back-to-back without any interleaving short USB
15+
packets. This reduces the number of short packet
16+
interrupts in the device, and represents a tradeoff
17+
between USB bus bandwidth and device DMA optimization.
18+
19+
Set to 0 to pad all frames. Set greater than tx_max to
20+
disable all padding.
21+
22+
What: /sys/class/net/<iface>/cdc_ncm/rx_max
23+
Date: May 2014
24+
KernelVersion: 3.16
25+
Contact: Bjørn Mork <bjorn@mork.no>
26+
Description:
27+
The maximum NTB size for RX. Cannot exceed the
28+
maximum value supported by the device. Must allow at
29+
least one max sized datagram plus headers.
30+
31+
The actual limits are device dependent. See
32+
dwNtbInMaxSize.
33+
34+
Note: Some devices will silently ignore changes to
35+
this value, resulting in oversized NTBs and
36+
corresponding framing errors.
37+
38+
What: /sys/class/net/<iface>/cdc_ncm/tx_max
39+
Date: May 2014
40+
KernelVersion: 3.16
41+
Contact: Bjørn Mork <bjorn@mork.no>
42+
Description:
43+
The maximum NTB size for TX. Cannot exceed the
44+
maximum value supported by the device. Must allow at
45+
least one max sized datagram plus headers.
46+
47+
The actual limits are device dependent. See
48+
dwNtbOutMaxSize.
49+
50+
What: /sys/class/net/<iface>/cdc_ncm/tx_timer_usecs
51+
Date: May 2014
52+
KernelVersion: 3.16
53+
Contact: Bjørn Mork <bjorn@mork.no>
54+
Description:
55+
Datagram aggregation timeout in µs. The driver will
56+
wait up to 3 times this timeout for more datagrams to
57+
aggregate before transmitting an NTB frame.
58+
59+
Valid range: 5 to 4000000
60+
61+
Set to 0 to disable aggregation.
62+
63+
The following read-only attributes all represent fields of the
64+
structure defined in section 6.2.1 "GetNtbParameters" of "Universal
65+
Serial Bus Communications Class Subclass Specifications for Network
66+
Control Model Devices" (CDC NCM), Revision 1.0 (Errata 1), November
67+
24, 2010 from USB Implementers Forum, Inc. The descriptions are
68+
quoted from table 6-3 of CDC NCM: "NTB Parameter Structure".
69+
70+
What: /sys/class/net/<iface>/cdc_ncm/bmNtbFormatsSupported
71+
Date: May 2014
72+
KernelVersion: 3.16
73+
Contact: Bjørn Mork <bjorn@mork.no>
74+
Description:
75+
Bit 0: 16-bit NTB supported (set to 1)
76+
Bit 1: 32-bit NTB supported
77+
Bits 2 – 15: reserved (reset to zero; must be ignored by host)
78+
79+
What: /sys/class/net/<iface>/cdc_ncm/dwNtbInMaxSize
80+
Date: May 2014
81+
KernelVersion: 3.16
82+
Contact: Bjørn Mork <bjorn@mork.no>
83+
Description:
84+
IN NTB Maximum Size in bytes
85+
86+
What: /sys/class/net/<iface>/cdc_ncm/wNdpInDivisor
87+
Date: May 2014
88+
KernelVersion: 3.16
89+
Contact: Bjørn Mork <bjorn@mork.no>
90+
Description:
91+
Divisor used for IN NTB Datagram payload alignment
92+
93+
What: /sys/class/net/<iface>/cdc_ncm/wNdpInPayloadRemainder
94+
Date: May 2014
95+
KernelVersion: 3.16
96+
Contact: Bjørn Mork <bjorn@mork.no>
97+
Description:
98+
Remainder used to align input datagram payload within
99+
the NTB: (Payload Offset) mod (wNdpInDivisor) =
100+
wNdpInPayloadRemainder
101+
102+
What: /sys/class/net/<iface>/cdc_ncm/wNdpInAlignment
103+
Date: May 2014
104+
KernelVersion: 3.16
105+
Contact: Bjørn Mork <bjorn@mork.no>
106+
Description:
107+
NDP alignment modulus for NTBs on the IN pipe. Shall
108+
be a power of 2, and shall be at least 4.
109+
110+
What: /sys/class/net/<iface>/cdc_ncm/dwNtbOutMaxSize
111+
Date: May 2014
112+
KernelVersion: 3.16
113+
Contact: Bjørn Mork <bjorn@mork.no>
114+
Description:
115+
OUT NTB Maximum Size
116+
117+
What: /sys/class/net/<iface>/cdc_ncm/wNdpOutDivisor
118+
Date: May 2014
119+
KernelVersion: 3.16
120+
Contact: Bjørn Mork <bjorn@mork.no>
121+
Description:
122+
OUT NTB Datagram alignment modulus
123+
124+
What: /sys/class/net/<iface>/cdc_ncm/wNdpOutPayloadRemainder
125+
Date: May 2014
126+
KernelVersion: 3.16
127+
Contact: Bjørn Mork <bjorn@mork.no>
128+
Description:
129+
Remainder used to align output datagram payload
130+
offsets within the NTB: Padding, shall be transmitted
131+
as zero by function, and ignored by host. (Payload
132+
Offset) mod (wNdpOutDivisor) = wNdpOutPayloadRemainder
133+
134+
What: /sys/class/net/<iface>/cdc_ncm/wNdpOutAlignment
135+
Date: May 2014
136+
KernelVersion: 3.16
137+
Contact: Bjørn Mork <bjorn@mork.no>
138+
Description:
139+
NDP alignment modulus for use in NTBs on the OUT
140+
pipe. Shall be a power of 2, and shall be at least 4.
141+
142+
What: /sys/class/net/<iface>/cdc_ncm/wNtbOutMaxDatagrams
143+
Date: May 2014
144+
KernelVersion: 3.16
145+
Contact: Bjørn Mork <bjorn@mork.no>
146+
Description:
147+
Maximum number of datagrams that the host may pack
148+
into a single OUT NTB. Zero means that the device
149+
imposes no limit.
Lines changed: 79 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,79 @@
1+
What: /sys/class/<iface>/queues/rx-<queue>/rps_cpus
2+
Date: March 2010
3+
KernelVersion: 2.6.35
4+
Contact: netdev@vger.kernel.org
5+
Description:
6+
Mask of the CPU(s) currently enabled to participate into the
7+
Receive Packet Steering packet processing flow for this
8+
network device queue. Possible values depend on the number
9+
of available CPU(s) in the system.
10+
11+
What: /sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
12+
Date: April 2010
13+
KernelVersion: 2.6.35
14+
Contact: netdev@vger.kernel.org
15+
Description:
16+
Number of Receive Packet Steering flows being currently
17+
processed by this particular network device receive queue.
18+
19+
What: /sys/class/<iface>/queues/tx-<queue>/tx_timeout
20+
Date: November 2011
21+
KernelVersion: 3.3
22+
Contact: netdev@vger.kernel.org
23+
Description:
24+
Indicates the number of transmit timeout events seen by this
25+
network interface transmit queue.
26+
27+
What: /sys/class/<iface>/queues/tx-<queue>/xps_cpus
28+
Date: November 2010
29+
KernelVersion: 2.6.38
30+
Contact: netdev@vger.kernel.org
31+
Description:
32+
Mask of the CPU(s) currently enabled to participate into the
33+
Transmit Packet Steering packet processing flow for this
34+
network device transmit queue. Possible vaules depend on the
35+
number of available CPU(s) in the system.
36+
37+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
38+
Date: November 2011
39+
KernelVersion: 3.3
40+
Contact: netdev@vger.kernel.org
41+
Description:
42+
Indicates the hold time in milliseconds to measure the slack
43+
of this particular network device transmit queue.
44+
Default value is 1000.
45+
46+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
47+
Date: November 2011
48+
KernelVersion: 3.3
49+
Contact: netdev@vger.kernel.org
50+
Description:
51+
Indicates the number of bytes (objects) in flight on this
52+
network device transmit queue.
53+
54+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
55+
Date: November 2011
56+
KernelVersion: 3.3
57+
Contact: netdev@vger.kernel.org
58+
Description:
59+
Indicates the current limit of bytes allowed to be queued
60+
on this network device transmit queue. This value is clamped
61+
to be within the bounds defined by limit_max and limit_min.
62+
63+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
64+
Date: November 2011
65+
KernelVersion: 3.3
66+
Contact: netdev@vger.kernel.org
67+
Description:
68+
Indicates the absolute maximum limit of bytes allowed to be
69+
queued on this network device transmit queue. See
70+
include/linux/dynamic_queue_limits.h for the default value.
71+
72+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
73+
Date: November 2011
74+
KernelVersion: 3.3
75+
Contact: netdev@vger.kernel.org
76+
Description:
77+
Indicates the absolute minimum limit of bytes allowed to be
78+
queued on this network device transmit queue. Default value is
79+
0.

0 commit comments

Comments
 (0)