apfs/linux-apfs
0
0
Fork 0
mirror of https://github.com/linux-apfs/linux-apfs.git synced 2026-05-01 15:00:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6

Browse Source 
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1750 commits)
  ixgbe: Allow Priority Flow Control settings to survive a device reset
  net: core: remove unneeded include in net/core/utils.c.
  e1000e: update version number
  e1000e: fix close interrupt race
  e1000e: fix loss of multicast packets
  e1000e: commonize tx cleanup routine to match e1000 & igb
  netfilter: fix nf_logger name in ebt_ulog.
  netfilter: fix warning in ebt_ulog init function.
  netfilter: fix warning about invalid const usage
  e1000: fix close race with interrupt
  e1000: cleanup clean_tx_irq routine so that it completely cleans ring
  e1000: fix tx hang detect logic and address dma mapping issues
  bridge: bad error handling when adding invalid ether address
  bonding: select current active slave when enslaving device for mode tlb and alb
  gianfar: reallocate skb when headroom is not enough for fcb
  Bump release date to 25Mar2009 and version to 0.22
  r6040: Fix second PHY address
  qeth: fix wait_event_timeout handling
  qeth: check for completion of a running recovery
  qeth: unregister MAC addresses during recovery.
  ...

Manually fixed up conflicts in:
	drivers/infiniband/hw/cxgb3/cxio_hal.h
	drivers/infiniband/hw/nes/nes_nic.c
This commit is contained in:
Linus Torvalds
2009-03-26 15:54:36 -07:00
parent 8690d8a9f6 08abe18af1
commit 13220a94d3
1185 changed files with 130343 additions and 90091 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Documentation/DocBook/mac80211.tmpl
+8 -4
View File
@@ -17,8 +17,7 @@
</authorgroup>
<copyright>
<year>2007</year>
<year>2008</year>
<year>2007-2009</year>
<holder>Johannes Berg</holder>
</copyright>
@@ -165,8 +164,8 @@ usage should require reading the full document.
!Pinclude/net/mac80211.h Frame format
</sect1>
<sect1>
<title>Alignment issues</title>
<para>TBD</para>
<title>Packet alignment</title>
!Pnet/mac80211/rx.c Packet alignment
</sect1>
<sect1>
<title>Calling into mac80211 from interrupts</title>
@@ -223,6 +222,11 @@ usage should require reading the full document.
!Finclude/net/mac80211.h ieee80211_key_flags
</chapter>
<chapter id="powersave">
<title>Powersave support</title>
!Pinclude/net/mac80211.h Powersave support
</chapter>
<chapter id="qos">
<title>Multiple queues and QoS support</title>
<para>TBD</para>
Documentation/feature-removal-schedule.txt
+3 -1
View File
@@ -229,7 +229,9 @@ Who: Jan Engelhardt <jengelh@computergmbh.de>
---------------------------
What: b43 support for firmware revision < 410
When: July 2008
When: The schedule was July 2008, but it was decided that we are going to keep the
code as long as there are no major maintanance headaches.
So it _could_ be removed _any_ time now, if it conflicts with something new.
Why: The support code for the old firmware hurts code readability/maintainability
and slightly hurts runtime performance. Bugfixes for the old firmware
are not provided by Broadcom anymore.
Documentation/networking/dccp.txt
+2 -1
View File
@@ -141,7 +141,8 @@ rx_ccid = 2
Default CCID for the receiver-sender half-connection; see tx_ccid.
seq_window = 100
The initial sequence window (sec. 7.5.2).
The initial sequence window (sec. 7.5.2) of the sender. This influences
the local ackno validity and the remote seqno validity windows (7.5.1).
tx_qlen = 5
The size of the transmit buffer in packets. A value of 0 corresponds
Documentation/networking/ip-sysctl.txt
+81 -67
View File
@@ -2,7 +2,7 @@
ip_forward - BOOLEAN
0 - disabled (default)
not 0 - enabled
not 0 - enabled
Forward Packets between interfaces.
@@ -36,49 +36,49 @@ rt_cache_rebuild_count - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
Maximum memory used to reassemble IP fragments. When
Maximum memory used to reassemble IP fragments. When
ipfrag_high_thresh bytes of memory is allocated for this purpose,
the fragment handler will toss packets until ipfrag_low_thresh
is reached.
ipfrag_low_thresh - INTEGER
See ipfrag_high_thresh
See ipfrag_high_thresh
ipfrag_time - INTEGER
Time in seconds to keep an IP fragment in memory.
Time in seconds to keep an IP fragment in memory.
ipfrag_secret_interval - INTEGER
Regeneration interval (in seconds) of the hash secret (or lifetime
Regeneration interval (in seconds) of the hash secret (or lifetime
for the hash secret) for IP fragments.
Default: 600
ipfrag_max_dist - INTEGER
ipfrag_max_dist is a non-negative integer value which defines the
maximum "disorder" which is allowed among fragments which share a
common IP source address. Note that reordering of packets is
not unusual, but if a large number of fragments arrive from a source
IP address while a particular fragment queue remains incomplete, it
probably indicates that one or more fragments belonging to that queue
have been lost. When ipfrag_max_dist is positive, an additional check
is done on fragments before they are added to a reassembly queue - if
ipfrag_max_dist (or more) fragments have arrived from a particular IP
address between additions to any IP fragment queue using that source
address, it's presumed that one or more fragments in the queue are
lost. The existing fragment queue will be dropped, and a new one
ipfrag_max_dist is a non-negative integer value which defines the
maximum "disorder" which is allowed among fragments which share a
common IP source address. Note that reordering of packets is
not unusual, but if a large number of fragments arrive from a source
IP address while a particular fragment queue remains incomplete, it
probably indicates that one or more fragments belonging to that queue
have been lost. When ipfrag_max_dist is positive, an additional check
is done on fragments before they are added to a reassembly queue - if
ipfrag_max_dist (or more) fragments have arrived from a particular IP
address between additions to any IP fragment queue using that source
address, it's presumed that one or more fragments in the queue are
lost. The existing fragment queue will be dropped, and a new one
started. An ipfrag_max_dist value of zero disables this check.
Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
result in unnecessarily dropping fragment queues when normal
reordering of packets occurs, which could lead to poor application
performance. Using a very large value, e.g. 50000, increases the
likelihood of incorrectly reassembling IP fragments that originate
reordering of packets occurs, which could lead to poor application
performance. Using a very large value, e.g. 50000, increases the
likelihood of incorrectly reassembling IP fragments that originate
from different IP datagrams, which could result in data corruption.
Default: 64
INET peer storage:
inet_peer_threshold - INTEGER
The approximate size of the storage. Starting from this threshold
The approximate size of the storage. Starting from this threshold
entries will be thrown aggressively. This threshold also determines
entries' time-to-live and time intervals between garbage collection
passes. More entries, less time-to-live, less GC interval.
@@ -105,7 +105,7 @@ inet_peer_gc_maxtime - INTEGER
in effect under low (or absent) memory pressure on the pool.
Measured in seconds.
TCP variables:
TCP variables:
somaxconn - INTEGER
Limit of socket listen() backlog, known in userspace as SOMAXCONN.
@@ -310,7 +310,7 @@ tcp_orphan_retries - INTEGER
tcp_reordering - INTEGER
Maximal reordering of packets in a TCP stream.
Default: 3
Default: 3
tcp_retrans_collapse - BOOLEAN
Bug-to-bug compatibility with some broken printers.
@@ -521,7 +521,7 @@ IP Variables:
ip_local_port_range - 2 INTEGERS
Defines the local port range that is used by TCP and UDP to
choose the local port. The first number is the first, the
choose the local port. The first number is the first, the
second the last local port number. Default value depends on
amount of memory available on the system:
> 128Mb 32768-61000
@@ -594,12 +594,12 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN
If zero, icmp error messages are sent with the primary address of
the exiting interface.
If non-zero, the message will be sent with the primary address of
the interface that received the packet that caused the icmp error.
This is the behaviour network many administrators will expect from
a router. And it can make debugging complicated network layouts
much easier.
much easier.
Note that if no primary address exists for the interface selected,
then the primary address of the first non-loopback interface that
@@ -611,7 +611,7 @@ igmp_max_memberships - INTEGER
Change the maximum number of multicast groups we can subscribe to.
Default: 20
conf/interface/* changes special settings per interface (where "interface" is
conf/interface/* changes special settings per interface (where "interface" is
the name of your network interface)
conf/all/* is special, changes the settings for all interfaces
@@ -625,11 +625,11 @@ log_martians - BOOLEAN
accept_redirects - BOOLEAN
Accept ICMP redirect messages.
accept_redirects for the interface will be enabled if:
- both conf/{all,interface}/accept_redirects are TRUE in the case forwarding
for the interface is enabled
- both conf/{all,interface}/accept_redirects are TRUE in the case
forwarding for the interface is enabled
or
- at least one of conf/{all,interface}/accept_redirects is TRUE in the case
forwarding for the interface is disabled
- at least one of conf/{all,interface}/accept_redirects is TRUE in the
case forwarding for the interface is disabled
accept_redirects for the interface will be disabled otherwise
default TRUE (host)
FALSE (router)
@@ -640,8 +640,8 @@ forwarding - BOOLEAN
mc_forwarding - BOOLEAN
Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
and a multicast routing daemon is required.
conf/all/mc_forwarding must also be set to TRUE to enable multicast routing
for the interface
conf/all/mc_forwarding must also be set to TRUE to enable multicast
routing for the interface
medium_id - INTEGER
Integer value used to differentiate the devices by the medium they
@@ -649,7 +649,7 @@ medium_id - INTEGER
the broadcast packets are received only on one of them.
The default value 0 means that the device is the only interface
to its medium, value of -1 means that medium is not known.
Currently, it is used to change the proxy_arp behavior:
the proxy_arp feature is enabled for packets forwarded between
two devices attached to different media.
@@ -699,16 +699,22 @@ accept_source_route - BOOLEAN
default TRUE (router)
FALSE (host)
rp_filter - BOOLEAN
1 - do source validation by reversed path, as specified in RFC1812
Recommended option for single homed hosts and stub network
routers. Could cause troubles for complicated (not loop free)
networks running a slow unreliable protocol (sort of RIP),
or using static routes.
rp_filter - INTEGER
0 - No source validation.
1 - Strict mode as defined in RFC3704 Strict Reverse Path
Each incoming packet is tested against the FIB and if the interface
is not the best reverse path the packet check will fail.
By default failed packets are discarded.
2 - Loose mode as defined in RFC3704 Loose Reverse Path
Each incoming packet's source address is also tested against the FIB
and if the source address is not reachable via any interface
the packet check will fail.
conf/all/rp_filter must also be set to TRUE to do source validation
Current recommended practice in RFC3704 is to enable strict mode
to prevent IP spoofing from DDos attacks. If using asymmetric routing
or other complicated routing, then loose mode is recommended.
conf/all/rp_filter must also be set to non-zero to do source validation
on the interface
Default value is 0. Note that some distributions enable it
@@ -782,6 +788,12 @@ arp_ignore - INTEGER
The max value from conf/{all,interface}/arp_ignore is used
when ARP request is received on the {interface}
arp_notify - BOOLEAN
Define mode for notification of address and device changes.
0 - (default): do nothing
1 - Generate gratuitous arp replies when device is brought up
or hardware address changes.
arp_accept - BOOLEAN
Define behavior when gratuitous arp replies are received:
0 - drop gratuitous arp frames
@@ -823,7 +835,7 @@ apply to IPv6 [XXX?].
bindv6only - BOOLEAN
Default value for IPV6_V6ONLY socket option,
which restricts use of the IPv6 socket to IPv6 communication
which restricts use of the IPv6 socket to IPv6 communication
only.
TRUE: disable IPv4-mapped address feature
FALSE: enable IPv4-mapped address feature
@@ -833,19 +845,19 @@ bindv6only - BOOLEAN
IPv6 Fragmentation:
ip6frag_high_thresh - INTEGER
Maximum memory used to reassemble IPv6 fragments. When
Maximum memory used to reassemble IPv6 fragments. When
ip6frag_high_thresh bytes of memory is allocated for this purpose,
the fragment handler will toss packets until ip6frag_low_thresh
is reached.
ip6frag_low_thresh - INTEGER
See ip6frag_high_thresh
See ip6frag_high_thresh
ip6frag_time - INTEGER
Time in seconds to keep an IPv6 fragment in memory.
ip6frag_secret_interval - INTEGER
Regeneration interval (in seconds) of the hash secret (or lifetime
Regeneration interval (in seconds) of the hash secret (or lifetime
for the hash secret) for IPv6 fragments.
Default: 600
@@ -854,17 +866,17 @@ conf/default/*:
conf/all/*:
Change all the interface-specific settings.
Change all the interface-specific settings.
[XXX: Other special features than forwarding?]
conf/all/forwarding - BOOLEAN
Enable global IPv6 forwarding between all interfaces.
Enable global IPv6 forwarding between all interfaces.
IPv4 and IPv6 work differently here; e.g. netfilter must be used
IPv4 and IPv6 work differently here; e.g. netfilter must be used
to control which interfaces may forward packets and which not.
This also sets all interfaces' Host/Router setting
This also sets all interfaces' Host/Router setting
'forwarding' to the specified value. See below for details.
This referred to as global forwarding.
@@ -875,12 +887,12 @@ proxy_ndp - BOOLEAN
conf/interface/*:
Change special settings per interface.
The functional behaviour for certain settings is different
The functional behaviour for certain settings is different
depending on whether local forwarding is enabled or not.
accept_ra - BOOLEAN
Accept Router Advertisements; autoconfigure using them.
Functional default: enabled if local forwarding is disabled.
disabled if local forwarding is enabled.
@@ -926,7 +938,7 @@ accept_source_route - INTEGER
Default: 0
autoconf - BOOLEAN
Autoconfigure addresses using Prefix Information in Router
Autoconfigure addresses using Prefix Information in Router
Advertisements.
Functional default: enabled if accept_ra_pinfo is enabled.
@@ -935,11 +947,11 @@ autoconf - BOOLEAN
dad_transmits - INTEGER
The amount of Duplicate Address Detection probes to send.
Default: 1
forwarding - BOOLEAN
Configure interface-specific Host/Router behaviour.
Note: It is recommended to have the same setting on all
forwarding - BOOLEAN
Configure interface-specific Host/Router behaviour.
Note: It is recommended to have the same setting on all
interfaces; mixed router/host scenarios are rather uncommon.
FALSE:
@@ -948,13 +960,13 @@ forwarding - BOOLEAN
1. IsRouter flag is not set in Neighbour Advertisements.
2. Router Solicitations are being sent when necessary.
3. If accept_ra is TRUE (default), accept Router
3. If accept_ra is TRUE (default), accept Router
Advertisements (and do autoconfiguration).
4. If accept_redirects is TRUE (default), accept Redirects.
TRUE:
If local forwarding is enabled, Router behaviour is assumed.
If local forwarding is enabled, Router behaviour is assumed.
This means exactly the reverse from the above:
1. IsRouter flag is set in Neighbour Advertisements.
@@ -989,7 +1001,7 @@ router_solicitation_interval - INTEGER
Default: 4
router_solicitations - INTEGER
Number of Router Solicitations to send until assuming no
Number of Router Solicitations to send until assuming no
routers are present.
Default: 3
@@ -1013,11 +1025,11 @@ temp_prefered_lft - INTEGER
max_desync_factor - INTEGER
Maximum value for DESYNC_FACTOR, which is a random value
that ensures that clients don't synchronize with each
that ensures that clients don't synchronize with each
other and generate new addresses at exactly the same time.
value is in seconds.
Default: 600
regen_max_retry - INTEGER
Number of attempts before give up attempting to generate
valid temporary addresses.
@@ -1025,13 +1037,15 @@ regen_max_retry - INTEGER
max_addresses - INTEGER
Number of maximum addresses per interface. 0 disables limitation.
It is recommended not set too large value (or 0) because it would
be too easy way to crash kernel to allow to create too much of
It is recommended not set too large value (or 0) because it would
be too easy way to crash kernel to allow to create too much of
autoconfigured addresses.
Default: 16
disable_ipv6 - BOOLEAN
Disable IPv6 operation.
Disable IPv6 operation. If accept_dad is set to 2, this value
will be dynamically set to TRUE if DAD fails for the link-local
address.
Default: FALSE (enable IPv6 operation)
accept_dad - INTEGER
Documentation/networking/ixgbe.txt
+199
View File
@@ -0,0 +1,199 @@
Linux Base Driver for 10 Gigabit PCI Express Intel(R) Network Connection
========================================================================
March 10, 2009
Contents
========
- In This Release
- Identifying Your Adapter
- Building and Installation
- Additional Configurations
- Support
In This Release
===============
This file describes the ixgbe Linux Base Driver for the 10 Gigabit PCI
Express Intel(R) Network Connection. This driver includes support for
Itanium(R)2-based systems.
For questions related to hardware requirements, refer to the documentation
supplied with your 10 Gigabit adapter. All hardware requirements listed apply
to use with Linux.
The following features are available in this kernel:
- Native VLANs
- Channel Bonding (teaming)
- SNMP
- Generic Receive Offload
- Data Center Bridging
Channel Bonding documentation can be found in the Linux kernel source:
/Documentation/networking/bonding.txt
Ethtool, lspci, and ifconfig can be used to display device and driver
specific information.
Identifying Your Adapter
========================
This driver supports devices based on the 82598 controller and the 82599
controller.
For specific information on identifying which adapter you have, please visit:
http://support.intel.com/support/network/sb/CS-008441.htm
Building and Installation
=========================
select m for "Intel(R) 10GbE PCI Express adapters support" located at:
Location:
-> Device Drivers
-> Network device support (NETDEVICES [=y])
-> Ethernet (10000 Mbit) (NETDEV_10000 [=y])
1. make modules & make modules_install
2. Load the module:
# modprobe ixgbe
The insmod command can be used if the full
path to the driver module is specified. For example:
insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgbe/ixgbe.ko
With 2.6 based kernels also make sure that older ixgbe drivers are
removed from the kernel, before loading the new module:
rmmod ixgbe; modprobe ixgbe
3. Assign an IP address to the interface by entering the following, where
x is the interface number:
ifconfig ethx <IP_address>
4. Verify that the interface works. Enter the following, where <IP_address>
is the IP address for another machine on the same subnet as the interface
that is being tested:
ping <IP_address>
Additional Configurations
=========================
Viewing Link Messages
---------------------
Link messages will not be displayed to the console if the distribution is
restricting system messages. In order to see network driver link messages on
your console, set dmesg to eight by entering the following:
dmesg -n 8
NOTE: This setting is not saved across reboots.
Jumbo Frames
------------
The driver supports Jumbo Frames for all adapters. Jumbo Frames support is
enabled by changing the MTU to a value larger than the default of 1500.
The maximum value for the MTU is 16110. Use the ifconfig command to
increase the MTU size. For example:
ifconfig ethx mtu 9000 up
The maximum MTU setting for Jumbo Frames is 16110. This value coincides
with the maximum Jumbo Frames size of 16128.
Generic Receive Offload, aka GRO
--------------------------------
The driver supports the in-kernel software implementation of GRO. GRO has
shown that by coalescing Rx traffic into larger chunks of data, CPU
utilization can be significantly reduced when under large Rx load. GRO is an
evolution of the previously-used LRO interface. GRO is able to coalesce
other protocols besides TCP. It's also safe to use with configurations that
are problematic for LRO, namely bridging and iSCSI.
GRO is enabled by default in the driver. Future versions of ethtool will
support disabling and re-enabling GRO on the fly.
Data Center Bridging, aka DCB
-----------------------------
DCB is a configuration Quality of Service implementation in hardware.
It uses the VLAN priority tag (802.1p) to filter traffic. That means
that there are 8 different priorities that traffic can be filtered into.
It also enables priority flow control which can limit or eliminate the
number of dropped packets during network stress. Bandwidth can be
allocated to each of these priorities, which is enforced at the hardware
level.
To enable DCB support in ixgbe, you must enable the DCB netlink layer to
allow the userspace tools (see below) to communicate with the driver.
This can be found in the kernel configuration here:
-> Networking support
-> Networking options
-> Data Center Bridging support
Once this is selected, DCB support must be selected for ixgbe. This can
be found here:
-> Device Drivers
-> Network device support (NETDEVICES [=y])
-> Ethernet (10000 Mbit) (NETDEV_10000 [=y])
-> Intel(R) 10GbE PCI Express adapters support
-> Data Center Bridging (DCB) Support
After these options are selected, you must rebuild your kernel and your
modules.
In order to use DCB, userspace tools must be downloaded and installed.
The dcbd tools can be found at:
http://e1000.sf.net
Ethtool
-------
The driver utilizes the ethtool interface for driver configuration and
diagnostics, as well as displaying statistical information. Ethtool
version 3.0 or later is required for this functionality.
The latest release of ethtool can be found from
http://sourceforge.net/projects/gkernel.
NAPI
----
NAPI (Rx polling mode) is supported in the ixgbe driver. NAPI is enabled
by default in the driver.
See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
Support
=======
For general information, go to the Intel support website at:
http://support.intel.com
or the Intel Wired Networking project hosted by Sourceforge at:
http://e1000.sourceforge.net
If an issue is identified with the released source code on the supported
kernel with a supported adapter, email the specific information related
to the issue to e1000-devel@lists.sf.net
Documentation/networking/rds.txt
+356
View File
@@ -0,0 +1,356 @@
Overview
========
This readme tries to provide some background on the hows and whys of RDS,
and will hopefully help you find your way around the code.
In addition, please see this email about RDS origins:
http://oss.oracle.com/pipermail/rds-devel/2007-November/000228.html
RDS Architecture
================
RDS provides reliable, ordered datagram delivery by using a single
reliable connection between any two nodes in the cluster. This allows
applications to use a single socket to talk to any other process in the
cluster - so in a cluster with N processes you need N sockets, in contrast
to N*N if you use a connection-oriented socket transport like TCP.
RDS is not Infiniband-specific; it was designed to support different
transports. The current implementation used to support RDS over TCP as well
as IB. Work is in progress to support RDS over iWARP, and using DCE to
guarantee no dropped packets on Ethernet, it may be possible to use RDS over
UDP in the future.
The high-level semantics of RDS from the application's point of view are
* Addressing
RDS uses IPv4 addresses and 16bit port numbers to identify
the end point of a connection. All socket operations that involve
passing addresses between kernel and user space generally
use a struct sockaddr_in.
The fact that IPv4 addresses are used does not mean the underlying
transport has to be IP-based. In fact, RDS over IB uses a
reliable IB connection; the IP address is used exclusively to
locate the remote node's GID (by ARPing for the given IP).
The port space is entirely independent of UDP, TCP or any other
protocol.
* Socket interface
RDS sockets work *mostly* as you would expect from a BSD
socket. The next section will cover the details. At any rate,
all I/O is performed through the standard BSD socket API.
Some additions like zerocopy support are implemented through
control messages, while other extensions use the getsockopt/
setsockopt calls.
Sockets must be bound before you can send or receive data.
This is needed because binding also selects a transport and
attaches it to the socket. Once bound, the transport assignment
does not change. RDS will tolerate IPs moving around (eg in
a active-active HA scenario), but only as long as the address
doesn't move to a different transport.
* sysctls
RDS supports a number of sysctls in /proc/sys/net/rds
Socket Interface
================
AF_RDS, PF_RDS, SOL_RDS
These constants haven't been assigned yet, because RDS isn't in
mainline yet. Currently, the kernel module assigns some constant
and publishes it to user space through two sysctl files
/proc/sys/net/rds/pf_rds
/proc/sys/net/rds/sol_rds
fd = socket(PF_RDS, SOCK_SEQPACKET, 0);
This creates a new, unbound RDS socket.
setsockopt(SOL_SOCKET): send and receive buffer size
RDS honors the send and receive buffer size socket options.
You are not allowed to queue more than SO_SNDSIZE bytes to
a socket. A message is queued when sendmsg is called, and
it leaves the queue when the remote system acknowledges
its arrival.
The SO_RCVSIZE option controls the maximum receive queue length.
This is a soft limit rather than a hard limit - RDS will
continue to accept and queue incoming messages, even if that
takes the queue length over the limit. However, it will also
mark the port as "congested" and send a congestion update to
the source node. The source node is supposed to throttle any
processes sending to this congested port.
bind(fd, &sockaddr_in, ...)
This binds the socket to a local IP address and port, and a
transport.
sendmsg(fd, ...)
Sends a message to the indicated recipient. The kernel will
transparently establish the underlying reliable connection
if it isn't up yet.
An attempt to send a message that exceeds SO_SNDSIZE will
return with -EMSGSIZE
An attempt to send a message that would take the total number
of queued bytes over the SO_SNDSIZE threshold will return
EAGAIN.
An attempt to send a message to a destination that is marked
as "congested" will return ENOBUFS.
recvmsg(fd, ...)
Receives a message that was queued to this socket. The sockets
recv queue accounting is adjusted, and if the queue length
drops below SO_SNDSIZE, the port is marked uncongested, and
a congestion update is sent to all peers.
Applications can ask the RDS kernel module to receive
notifications via control messages (for instance, there is a
notification when a congestion update arrived, or when a RDMA
operation completes). These notifications are received through
the msg.msg_control buffer of struct msghdr. The format of the
messages is described in manpages.
poll(fd)
RDS supports the poll interface to allow the application
to implement async I/O.
POLLIN handling is pretty straightforward. When there's an
incoming message queued to the socket, or a pending notification,
we signal POLLIN.
POLLOUT is a little harder. Since you can essentially send
to any destination, RDS will always signal POLLOUT as long as
there's room on the send queue (ie the number of bytes queued
is less than the sendbuf size).
However, the kernel will refuse to accept messages to
a destination marked congested - in this case you will loop
forever if you rely on poll to tell you what to do.
This isn't a trivial problem, but applications can deal with
this - by using congestion notifications, and by checking for
ENOBUFS errors returned by sendmsg.
setsockopt(SOL_RDS, RDS_CANCEL_SENT_TO, &sockaddr_in)
This allows the application to discard all messages queued to a
specific destination on this particular socket.
This allows the application to cancel outstanding messages if
it detects a timeout. For instance, if it tried to send a message,
and the remote host is unreachable, RDS will keep trying forever.
The application may decide it's not worth it, and cancel the
operation. In this case, it would use RDS_CANCEL_SENT_TO to
nuke any pending messages.
RDMA for RDS
============
see rds-rdma(7) manpage (available in rds-tools)
Congestion Notifications
========================
see rds(7) manpage
RDS Protocol
============
Message header
The message header is a 'struct rds_header' (see rds.h):
Fields:
h_sequence:
per-packet sequence number
h_ack:
piggybacked acknowledgment of last packet received
h_len:
length of data, not including header
h_sport:
source port
h_dport:
destination port
h_flags:
CONG_BITMAP - this is a congestion update bitmap
ACK_REQUIRED - receiver must ack this packet
RETRANSMITTED - packet has previously been sent
h_credit:
indicate to other end of connection that
it has more credits available (i.e. there is
more send room)
h_padding[4]:
unused, for future use
h_csum:
header checksum
h_exthdr:
optional data can be passed here. This is currently used for
passing RDMA-related information.
ACK and retransmit handling
One might think that with reliable IB connections you wouldn't need
to ack messages that have been received. The problem is that IB
hardware generates an ack message before it has DMAed the message
into memory. This creates a potential message loss if the HCA is
disabled for any reason between when it sends the ack and before
the message is DMAed and processed. This is only a potential issue
if another HCA is available for fail-over.
Sending an ack immediately would allow the sender to free the sent
message from their send queue quickly, but could cause excessive
traffic to be used for acks. RDS piggybacks acks on sent data
packets. Ack-only packets are reduced by only allowing one to be
in flight at a time, and by the sender only asking for acks when
its send buffers start to fill up. All retransmissions are also
acked.
Flow Control
RDS's IB transport uses a credit-based mechanism to verify that
there is space in the peer's receive buffers for more data. This
eliminates the need for hardware retries on the connection.
Congestion
Messages waiting in the receive queue on the receiving socket
are accounted against the sockets SO_RCVBUF option value. Only
the payload bytes in the message are accounted for. If the
number of bytes queued equals or exceeds rcvbuf then the socket
is congested. All sends attempted to this socket's address
should return block or return -EWOULDBLOCK.
Applications are expected to be reasonably tuned such that this
situation very rarely occurs. An application encountering this
"back-pressure" is considered a bug.
This is implemented by having each node maintain bitmaps which
indicate which ports on bound addresses are congested. As the
bitmap changes it is sent through all the connections which
terminate in the local address of the bitmap which changed.
The bitmaps are allocated as connections are brought up. This
avoids allocation in the interrupt handling path which queues
sages on sockets. The dense bitmaps let transports send the
entire bitmap on any bitmap change reasonably efficiently. This
is much easier to implement than some finer-grained
communication of per-port congestion. The sender does a very
inexpensive bit test to test if the port it's about to send to
is congested or not.
RDS Transport Layer
==================
As mentioned above, RDS is not IB-specific. Its code is divided
into a general RDS layer and a transport layer.
The general layer handles the socket API, congestion handling,
loopback, stats, usermem pinning, and the connection state machine.
The transport layer handles the details of the transport. The IB
transport, for example, handles all the queue pairs, work requests,
CM event handlers, and other Infiniband details.
RDS Kernel Structures
=====================
struct rds_message
aka possibly "rds_outgoing", the generic RDS layer copies data to
be sent and sets header fields as needed, based on the socket API.
This is then queued for the individual connection and sent by the
connection's transport.
struct rds_incoming
a generic struct referring to incoming data that can be handed from
the transport to the general code and queued by the general code
while the socket is awoken. It is then passed back to the transport
code to handle the actual copy-to-user.
struct rds_socket
per-socket information
struct rds_connection
per-connection information
struct rds_transport
pointers to transport-specific functions
struct rds_statistics
non-transport-specific statistics
struct rds_cong_map
wraps the raw congestion bitmap, contains rbnode, waitq, etc.
Connection management
=====================
Connections may be in UP, DOWN, CONNECTING, DISCONNECTING, and
ERROR states.
The first time an attempt is made by an RDS socket to send data to
a node, a connection is allocated and connected. That connection is
then maintained forever -- if there are transport errors, the
connection will be dropped and re-established.
Dropping a connection while packets are queued will cause queued or
partially-sent datagrams to be retransmitted when the connection is
re-established.
The send path
=============
rds_sendmsg()
struct rds_message built from incoming data
CMSGs parsed (e.g. RDMA ops)
transport connection alloced and connected if not already
rds_message placed on send queue
send worker awoken
rds_send_worker()
calls rds_send_xmit() until queue is empty
rds_send_xmit()
transmits congestion map if one is pending
may set ACK_REQUIRED
calls transport to send either non-RDMA or RDMA message
(RDMA ops never retransmitted)
rds_ib_xmit()
allocs work requests from send ring
adds any new send credits available to peer (h_credits)
maps the rds_message's sg list
piggybacks ack
populates work requests
post send to connection's queue pair
The recv path
=============
rds_ib_recv_cq_comp_handler()
looks at write completions
unmaps recv buffer from device
no errors, call rds_ib_process_recv()
refill recv ring
rds_ib_process_recv()
validate header checksum
copy header to rds_ib_incoming struct if start of a new datagram
add to ibinc's fraglist
if competed datagram:
update cong map if datagram was cong update
call rds_recv_incoming() otherwise
note if ack is required
rds_recv_incoming()
drop duplicate packets
respond to pings
find the sock associated with this datagram
add to sock queue
wake up sock
do some congestion calculations
rds_recvmsg
copy data into user iovec
handle CMSGs
return to application
Documentation/networking/timestamping.txt
+180
View File
@@ -0,0 +1,180 @@
The existing interfaces for getting network packages time stamped are:
* SO_TIMESTAMP
Generate time stamp for each incoming packet using the (not necessarily
monotonous!) system time. Result is returned via recv_msg() in a
control message as timeval (usec resolution).
* SO_TIMESTAMPNS
Same time stamping mechanism as SO_TIMESTAMP, but returns result as
timespec (nsec resolution).
* IP_MULTICAST_LOOP + SO_TIMESTAMP[NS]
Only for multicasts: approximate send time stamp by receiving the looped
packet and using its receive time stamp.
The following interface complements the existing ones: receive time
stamps can be generated and returned for arbitrary packets and much
closer to the point where the packet is really sent. Time stamps can
be generated in software (as before) or in hardware (if the hardware
has such a feature).
SO_TIMESTAMPING:
Instructs the socket layer which kind of information is wanted. The
parameter is an integer with some of the following bits set. Setting
other bits is an error and doesn't change the current state.
SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamp in hardware
SOF_TIMESTAMPING_TX_SOFTWARE: if SOF_TIMESTAMPING_TX_HARDWARE is off or
fails, then do it in software
SOF_TIMESTAMPING_RX_HARDWARE: return the original, unmodified time stamp
as generated by the hardware
SOF_TIMESTAMPING_RX_SOFTWARE: if SOF_TIMESTAMPING_RX_HARDWARE is off or
fails, then do it in software
SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp
SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to
the system time base
SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in
software
SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
following control message:
struct scm_timestamping {
struct timespec systime;
struct timespec hwtimetrans;
struct timespec hwtimeraw;
};
recvmsg() can be used to get this control message for regular incoming
packets. For send time stamps the outgoing packet is looped back to
the socket's error queue with the send time stamp(s) attached. It can
be received with recvmsg(flags=MSG_ERRQUEUE). The call returns the
original outgoing packet data including all headers preprended down to
and including the link layer, the scm_timestamping control message and
a sock_extended_err control message with ee_errno==ENOMSG and
ee_origin==SO_EE_ORIGIN_TIMESTAMPING. A socket with such a pending
bounced packet is ready for reading as far as select() is concerned.
If the outgoing packet has to be fragmented, then only the first
fragment is time stamped and returned to the sending socket.
All three values correspond to the same event in time, but were
generated in different ways. Each of these values may be empty (= all
zero), in which case no such value was available. If the application
is not interested in some of these values, they can be left blank to
avoid the potential overhead of calculating them.
systime is the value of the system time at that moment. This
corresponds to the value also returned via SO_TIMESTAMP[NS]. If the
time stamp was generated by hardware, then this field is
empty. Otherwise it is filled in if SOF_TIMESTAMPING_SOFTWARE is
set.
hwtimeraw is the original hardware time stamp. Filled in if
SOF_TIMESTAMPING_RAW_HARDWARE is set. No assumptions about its
relation to system time should be made.
hwtimetrans is the hardware time stamp transformed so that it
corresponds as good as possible to system time. This correlation is
not perfect; as a consequence, sorting packets received via different
NICs by their hwtimetrans may differ from the order in which they were
received. hwtimetrans may be non-monotonic even for the same NIC.
Filled in if SOF_TIMESTAMPING_SYS_HARDWARE is set. Requires support
by the network device and will be empty without that support.
SIOCSHWTSTAMP:
Hardware time stamping must also be initialized for each device driver
that is expected to do hardware time stamping. The parameter is:
struct hwtstamp_config {
int flags; /* no flags defined right now, must be zero */
int tx_type; /* HWTSTAMP_TX_* */
int rx_filter; /* HWTSTAMP_FILTER_* */
};
Desired behavior is passed into the kernel and to a specific device by
calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose
ifr_data points to a struct hwtstamp_config. The tx_type and
rx_filter are hints to the driver what it is expected to do. If
the requested fine-grained filtering for incoming packets is not
supported, the driver may time stamp more than just the requested types
of packets.
A driver which supports hardware time stamping shall update the struct
with the actual, possibly more permissive configuration. If the
requested packets cannot be time stamped, then nothing should be
changed and ERANGE shall be returned (in contrast to EINVAL, which
indicates that SIOCSHWTSTAMP is not supported at all).
Only a processes with admin rights may change the configuration. User
space is responsible to ensure that multiple processes don't interfere
with each other and that the settings are reset.
/* possible values for hwtstamp_config->tx_type */
enum {
/*
* no outgoing packet will need hardware time stamping;
* should a packet arrive which asks for it, no hardware
* time stamping will be done
*/
HWTSTAMP_TX_OFF,
/*
* enables hardware time stamping for outgoing packets;
* the sender of the packet decides which are to be
* time stamped by setting SOF_TIMESTAMPING_TX_SOFTWARE
* before sending the packet
*/
HWTSTAMP_TX_ON,
};
/* possible values for hwtstamp_config->rx_filter */
enum {
/* time stamp no incoming packet at all */
HWTSTAMP_FILTER_NONE,
/* time stamp any incoming packet */
HWTSTAMP_FILTER_ALL,
/* return value: time stamp all packets requested plus some others */
HWTSTAMP_FILTER_SOME,
/* PTP v1, UDP, any kind of event packet */
HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
...
};
DEVICE IMPLEMENTATION
A driver which supports hardware time stamping must support the
SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored
in the skb with skb_hwtstamp_set().
Time stamps for outgoing packets are to be generated as follows:
- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware()
returns non-zero. If yes, then the driver is expected
to do hardware time stamping.
- If this is possible for the skb and requested, then declare
that the driver is doing the time stamping by calling
skb_hwtstamp_tx_in_progress(). A driver not supporting
hardware time stamping doesn't do that. A driver must never
touch sk_buff::tstamp! It is used to store how time stamping
for an outgoing packets is to be done.
- As soon as the driver has sent the packet and/or obtained a
hardware time stamp for it, it passes the time stamp back by
calling skb_hwtstamp_tx() with the original skb, the raw
hardware time stamp and a handle to the device (necessary
to convert the hardware time stamp to system time). If obtaining
the hardware time stamp somehow fails, then the driver should
not fall back to software time stamping. The rationale is that
this would occur at a later time in the processing pipeline
than other software time stamping and therefore could lead
to unexpected deltas between time stamps.
- If the driver did not call skb_hwtstamp_tx_in_progress(), then
dev_hard_start_xmit() checks whether software time stamping
is wanted as fallback and potentially generates the time stamp.
Documentation/networking/timestamping/.gitignore
+1
View File
@@ -0,0 +1 @@
timestamping
Documentation/networking/timestamping/Makefile
+6
View File
@@ -0,0 +1,6 @@
CPPFLAGS = -I../../../include
timestamping: timestamping.c
clean:
rm -f timestamping
Documentation/networking/timestamping/timestamping.c
+533
View File
File diff suppressed because it is too large Load Diff
Documentation/powerpc/dts-bindings/fsl/tsec.txt
+6
View File
@@ -56,6 +56,12 @@ Properties:
hardware.
- fsl,magic-packet : If present, indicates that the hardware supports
waking up via magic packet.
- bd-stash : If present, indicates that the hardware supports stashing
buffer descriptors in the L2.
- rx-stash-len : Denotes the number of bytes of a received buffer to stash
in the L2.
- rx-stash-idx : Denotes the index of the first byte from the received
buffer to stash in the L2.
Example:
ethernet@24000 {
MAINTAINERS
+8
View File
@@ -1011,6 +1011,8 @@ L: netdev@vger.kernel.org
S: Supported
BROADCOM TG3 GIGABIT ETHERNET DRIVER
P: Matt Carlson
M: mcarlson@broadcom.com
P: Michael Chan
M: mchan@broadcom.com
L: netdev@vger.kernel.org
@@ -3646,6 +3648,12 @@ M: florian.fainelli@telecomint.eu
L: netdev@vger.kernel.org
S: Maintained
RDS - RELIABLE DATAGRAM SOCKETS
P: Andy Grover
M: andy.grover@oracle.com
L: rds-devel@oss.oracle.com
S: Supported
READ-COPY UPDATE (RCU)
P: Dipankar Sarma
M: dipankar@in.ibm.com
arch/alpha/include/asm/socket.h
+3
View File
@@ -62,6 +62,9 @@
#define SO_MARK 36
#define SO_TIMESTAMPING 37
#define SCM_TIMESTAMPING SO_TIMESTAMPING
/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
* have to define SOCK_NONBLOCK to a different value here.
*/
arch/arm/include/asm/socket.h
+3
View File
@@ -54,4 +54,7 @@
#define SO_MARK 36
#define SO_TIMESTAMPING 37
#define SCM_TIMESTAMPING SO_TIMESTAMPING
#endif /* _ASM_SOCKET_H */
arch/arm/mach-kirkwood/common.c
+4 -1
View File
@@ -231,14 +231,17 @@ static struct platform_device kirkwood_switch_device = {
void __init kirkwood_ge00_switch_init(struct dsa_platform_data *d, int irq)
{
int i;
if (irq != NO_IRQ) {
kirkwood_switch_resources[0].start = irq;
kirkwood_switch_resources[0].end = irq;
kirkwood_switch_device.num_resources = 1;
}
d->mii_bus = &kirkwood_ge00_shared.dev;
d->netdev = &kirkwood_ge00.dev;
for (i = 0; i < d->nr_chips; i++)
d->chip[i].mii_bus = &kirkwood_ge00_shared.dev;
kirkwood_switch_device.dev.platform_data = d;
platform_device_register(&kirkwood_switch_device);
arch/arm/mach-kirkwood/rd88f6281-setup.c
+9 -4
View File
@@ -75,7 +75,7 @@ static struct mv643xx_eth_platform_data rd88f6281_ge00_data = {
.duplex = DUPLEX_FULL,
};
static struct dsa_platform_data rd88f6281_switch_data = {
static struct dsa_chip_data rd88f6281_switch_chip_data = {
.port_names[0] = "lan1",
.port_names[1] = "lan2",
.port_names[2] = "lan3",
@@ -83,6 +83,11 @@ static struct dsa_platform_data rd88f6281_switch_data = {
.port_names[5] = "cpu",
};
static struct dsa_platform_data rd88f6281_switch_plat_data = {
.nr_chips = 1,
.chip = &rd88f6281_switch_chip_data,
};
static struct mv643xx_eth_platform_data rd88f6281_ge01_data = {
.phy_addr = MV643XX_ETH_PHY_ADDR(11),
};
@@ -105,12 +110,12 @@ static void __init rd88f6281_init(void)
kirkwood_ge00_init(&rd88f6281_ge00_data);
kirkwood_pcie_id(&dev, &rev);
if (rev == MV88F6281_REV_A0) {
rd88f6281_switch_data.sw_addr = 10;
rd88f6281_switch_chip_data.sw_addr = 10;
kirkwood_ge01_init(&rd88f6281_ge01_data);
} else {
rd88f6281_switch_data.port_names[4] = "wan";
rd88f6281_switch_chip_data.port_names[4] = "wan";
}
kirkwood_ge00_switch_init(&rd88f6281_switch_data, NO_IRQ);
kirkwood_ge00_switch_init(&rd88f6281_switch_plat_data, NO_IRQ);
kirkwood_rtc_init();
kirkwood_sata_init(&rd88f6281_sata_data);
arch/arm/mach-orion5x/common.c
+4 -1
View File
@@ -220,14 +220,17 @@ static struct platform_device orion5x_switch_device = {
void __init orion5x_eth_switch_init(struct dsa_platform_data *d, int irq)
{
int i;
if (irq != NO_IRQ) {
orion5x_switch_resources[0].start = irq;
orion5x_switch_resources[0].end = irq;
orion5x_switch_device.num_resources = 1;
}
d->mii_bus = &orion5x_eth_shared.dev;
d->netdev = &orion5x_eth.dev;
for (i = 0; i < d->nr_chips; i++)
d->chip[i].mii_bus = &orion5x_eth_shared.dev;
orion5x_switch_device.dev.platform_data = d;
platform_device_register(&orion5x_switch_device);
arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
+7 -2
View File
@@ -94,7 +94,7 @@ static struct mv643xx_eth_platform_data rd88f5181l_fxo_eth_data = {
.duplex = DUPLEX_FULL,
};
static struct dsa_platform_data rd88f5181l_fxo_switch_data = {
static struct dsa_chip_data rd88f5181l_fxo_switch_chip_data = {
.port_names[0] = "lan2",
.port_names[1] = "lan1",
.port_names[2] = "wan",
@@ -103,6 +103,11 @@ static struct dsa_platform_data rd88f5181l_fxo_switch_data = {
.port_names[7] = "lan3",
};
static struct dsa_platform_data rd88f5181l_fxo_switch_plat_data = {
.nr_chips = 1,
.chip = &rd88f5181l_fxo_switch_chip_data,
};
static void __init rd88f5181l_fxo_init(void)
{
/*
@@ -117,7 +122,7 @@ static void __init rd88f5181l_fxo_init(void)
*/
orion5x_ehci0_init();
orion5x_eth_init(&rd88f5181l_fxo_eth_data);
orion5x_eth_switch_init(&rd88f5181l_fxo_switch_data, NO_IRQ);
orion5x_eth_switch_init(&rd88f5181l_fxo_switch_plat_data, NO_IRQ);
orion5x_uart0_init();
orion5x_setup_dev_boot_win(RD88F5181L_FXO_NOR_BOOT_BASE,
arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
+8 -2
View File
@@ -95,7 +95,7 @@ static struct mv643xx_eth_platform_data rd88f5181l_ge_eth_data = {
.duplex = DUPLEX_FULL,
};
static struct dsa_platform_data rd88f5181l_ge_switch_data = {
static struct dsa_chip_data rd88f5181l_ge_switch_chip_data = {
.port_names[0] = "lan2",
.port_names[1] = "lan1",
.port_names[2] = "wan",
@@ -104,6 +104,11 @@ static struct dsa_platform_data rd88f5181l_ge_switch_data = {
.port_names[7] = "lan3",
};
static struct dsa_platform_data rd88f5181l_ge_switch_plat_data = {
.nr_chips = 1,
.chip = &rd88f5181l_ge_switch_chip_data,
};
static struct i2c_board_info __initdata rd88f5181l_ge_i2c_rtc = {
I2C_BOARD_INFO("ds1338", 0x68),
};
@@ -122,7 +127,8 @@ static void __init rd88f5181l_ge_init(void)
*/
orion5x_ehci0_init();
orion5x_eth_init(&rd88f5181l_ge_eth_data);
orion5x_eth_switch_init(&rd88f5181l_ge_switch_data, gpio_to_irq(8));
orion5x_eth_switch_init(&rd88f5181l_ge_switch_plat_data,
gpio_to_irq(8));
orion5x_i2c_init();
orion5x_uart0_init();
arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
+8 -2
View File
@@ -35,7 +35,7 @@ static struct mv643xx_eth_platform_data rd88f6183ap_ge_eth_data = {
.duplex = DUPLEX_FULL,
};
static struct dsa_platform_data rd88f6183ap_ge_switch_data = {
static struct dsa_chip_data rd88f6183ap_ge_switch_chip_data = {
.port_names[0] = "lan1",
.port_names[1] = "lan2",
.port_names[2] = "lan3",
@@ -44,6 +44,11 @@ static struct dsa_platform_data rd88f6183ap_ge_switch_data = {
.port_names[5] = "cpu",
};
static struct dsa_platform_data rd88f6183ap_ge_switch_plat_data = {
.nr_chips = 1,
.chip = &rd88f6183ap_ge_switch_chip_data,
};
static struct mtd_partition rd88f6183ap_ge_partitions[] = {
{
.name = "kernel",
@@ -89,7 +94,8 @@ static void __init rd88f6183ap_ge_init(void)
*/
orion5x_ehci0_init();
orion5x_eth_init(&rd88f6183ap_ge_eth_data);
orion5x_eth_switch_init(&rd88f6183ap_ge_switch_data, gpio_to_irq(3));
orion5x_eth_switch_init(&rd88f6183ap_ge_switch_plat_data,
gpio_to_irq(3));
spi_register_board_info(rd88f6183ap_ge_spi_slave_info,
ARRAY_SIZE(rd88f6183ap_ge_spi_slave_info));
orion5x_spi_init();

Some files were not shown because too many files have changed in this diff Show More