Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:

	net/netfilter/nf_conntrack_proto_tcp.c

1 files changed, 214 insertions, 42 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a40feaee62e..d84932650fd 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -148,9 +148,9 @@ tcp_available_congestion_control - STRING
 	but not loaded.
 
 tcp_base_mss - INTEGER
-	The initial value of search_low to be used by Packetization Layer
-	Path MTU Discovery (MTU probing).  If MTU probing is enabled,
-	this is the inital MSS used by the connection.
+	The initial value of search_low to be used by the packetization layer
+	Path MTU discovery (MTU probing).  If MTU probing is enabled,
+	this is the initial MSS used by the connection.
 
 tcp_congestion_control - STRING
 	Set the congestion control algorithm to be used for new
@@ -185,10 +185,9 @@ tcp_frto - INTEGER
 	timeouts.  It is particularly beneficial in wireless environments
 	where packet loss is typically due to random radio interference
 	rather than intermediate router congestion.  F-RTO is sender-side
-	only modification.  Therefore it does not require any support from
-	the peer, but in a typical case, however, where wireless link is
-	the local access link and most of the data flows downlink, the
-	faraway servers should have F-RTO enabled to take advantage of it.
+	only modification. Therefore it does not require any support from
+	the peer.
+
 	If set to 1, basic version is enabled.  2 enables SACK enhanced
 	F-RTO if flow uses SACK.  The basic version can be used also when
 	SACK is in use though scenario(s) with it exists where F-RTO
@@ -276,7 +275,7 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max
 	memory.
 
 tcp_moderate_rcvbuf - BOOLEAN
-	If set, TCP performs receive buffer autotuning, attempting to
+	If set, TCP performs receive buffer auto-tuning, attempting to
 	automatically size the buffer (no greater than tcp_rmem[2]) to
 	match the size required by the path for full throughput.  Enabled by
 	default.
@@ -336,7 +335,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	pressure.
 	Default: 8K
 
-	default: default size of receive buffer used by TCP sockets.
+	default: initial size of receive buffer used by TCP sockets.
 	This value overrides net.core.rmem_default used by other protocols.
 	Default: 87380 bytes. This value results in window of 65535 with
 	default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
@@ -344,8 +343,10 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 
 	max: maximal size of receive buffer allowed for automatically
 	selected receiver buffers for TCP socket. This value does not override
-	net.core.rmem_max, "static" selection via SO_RCVBUF does not use this.
-	Default: 87380*2 bytes.
+	net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
+	automatic tuning of that socket's receive buffer size, in which
+	case this value is ignored.
+	Default: between 87380B and 4MB, depending on RAM size.
 
 tcp_sack - BOOLEAN
 	Enable select acknowledgments (SACKS).
@@ -358,7 +359,7 @@ tcp_slow_start_after_idle - BOOLEAN
 	Default: 1
 
 tcp_stdurg - BOOLEAN
-	Use the Host requirements interpretation of the TCP urg pointer field.
+	Use the Host requirements interpretation of the TCP urgent pointer field.
 	Most hosts use the older BSD interpretation, so if you turn this on
 	Linux might not communicate correctly with them.
 	Default: FALSE
@@ -371,12 +372,12 @@ tcp_synack_retries - INTEGER
 tcp_syncookies - BOOLEAN
 	Only valid when the kernel was compiled with CONFIG_SYNCOOKIES
 	Send out syncookies when the syn backlog queue of a socket
-	overflows. This is to prevent against the common 'syn flood attack'
+	overflows. This is to prevent against the common 'SYN flood attack'
 	Default: FALSE
 
 	Note, that syncookies is fallback facility.
 	It MUST NOT be used to help highly loaded servers to stand
-	against legal connection rate. If you see synflood warnings
+	against legal connection rate. If you see SYN flood warnings
 	in your logs, but investigation	shows that they occur
 	because of overload with legal connections, you should tune
 	another parameters until this warning disappear.
@@ -386,7 +387,7 @@ tcp_syncookies - BOOLEAN
 	to use TCP extensions, can result in serious degradation
 	of some services (f.e. SMTP relaying), visible not by you,
 	but your clients and relays, contacting you. While you see
-	synflood warnings in logs not being really flooded, your server
+	SYN flood warnings in logs not being really flooded, your server
 	is seriously misconfigured.
 
 tcp_syn_retries - INTEGER
@@ -419,19 +420,21 @@ tcp_window_scaling - BOOLEAN
 	Enable window scaling as defined in RFC1323.
 
 tcp_wmem - vector of 3 INTEGERs: min, default, max
-	min: Amount of memory reserved for send buffers for TCP socket.
+	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.
 	Default: 4K
 
-	default: Amount of memory allowed for send buffers for TCP socket
-	by default. This value overrides net.core.wmem_default used
-	by other protocols, it is usually lower than net.core.wmem_default.
+	default: initial size of send buffer used by TCP sockets.  This
+	value overrides net.core.wmem_default used by other protocols.
+	It is usually lower than net.core.wmem_default.
 	Default: 16K
 
-	max: Maximal amount of memory allowed for automatically selected
-	send buffers for TCP socket. This value does not override
-	net.core.wmem_max, "static" selection via SO_SNDBUF does not use this.
-	Default: 128K
+	max: Maximal amount of memory allowed for automatically tuned
+	send buffers for TCP sockets. This value does not override
+	net.core.wmem_max.  Calling setsockopt() with SO_SNDBUF disables
+	automatic tuning of that socket's send buffer size, in which case
+	this value is ignored.
+	Default: between 64K and 4MB, depending on RAM size.
 
 tcp_workaround_signed_windows - BOOLEAN
 	If set, assume no receipt of a window scaling option means the
@@ -1073,24 +1076,193 @@ bridge-nf-filter-pppoe-tagged - BOOLEAN
 	Default: 1
 
 
-UNDOCUMENTED:
+proc/sys/net/sctp/* Variables:
+
+addip_enable - BOOLEAN
+	Enable or disable extension of  Dynamic Address Reconfiguration
+	(ADD-IP) functionality specified in RFC5061.  This extension provides
+	the ability to dynamically add and remove new addresses for the SCTP
+	associations.
+
+	1: Enable extension.
+
+	0: Disable extension.
+
+	Default: 0
+
+addip_noauth_enable - BOOLEAN
+	Dynamic Address Reconfiguration (ADD-IP) requires the use of
+	authentication to protect the operations of adding or removing new
+	addresses.  This requirement is mandated so that unauthorized hosts
+	would not be able to hijack associations.  However, older
+	implementations may not have implemented this requirement while
+	allowing the ADD-IP extension.  For reasons of interoperability,
+	we provide this variable to control the enforcement of the
+	authentication requirement.
+
+	1: Allow ADD-IP extension to be used without authentication.  This
+	   should only be set in a closed environment for interoperability
+	   with older implementations.
+
+	0: Enforce the authentication requirement
+
+	Default: 0
+
+auth_enable - BOOLEAN
+	Enable or disable Authenticated Chunks extension.  This extension
+	provides the ability to send and receive authenticated chunks and is
+	required for secure operation of Dynamic Address Reconfiguration
+	(ADD-IP) extension.
+
+	1: Enable this extension.
+	0: Disable this extension.
+
+	Default: 0
+
+prsctp_enable - BOOLEAN
+	Enable or disable the Partial Reliability extension (RFC3758) which
+	is used to notify peers that a given DATA should no longer be expected.
+
+	1: Enable extension
+	0: Disable
+
+	Default: 1
+
+max_burst - INTEGER
+	The limit of the number of new packets that can be initially sent.  It
+	controls how bursty the generated traffic can be.
+
+	Default: 4
+
+association_max_retrans - INTEGER
+	Set the maximum number for retransmissions that an association can
+	attempt deciding that the remote end is unreachable.  If this value
+	is exceeded, the association is terminated.
+
+	Default: 10
+
+max_init_retransmits - INTEGER
+	The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
+	that an association will attempt before declaring the destination
+	unreachable and terminating.
+
+	Default: 8
+
+path_max_retrans - INTEGER
+	The maximum number of retransmissions that will be attempted on a given
+	path.  Once this threshold is exceeded, the path is considered
+	unreachable, and new traffic will use a different path when the
+	association is multihomed.
+
+	Default: 5
+
+rto_initial - INTEGER
+	The initial round trip timeout value in milliseconds that will be used
+	in calculating round trip times.  This is the initial time interval
+	for retransmissions.
+
+	Default: 3000
 
-dev_weight FIXME
-discovery_slots FIXME
-discovery_timeout FIXME
-fast_poll_increase FIXME
-ip6_queue_maxlen FIXME
-lap_keepalive_time FIXME
-lo_cong FIXME
-max_baud_rate FIXME
-max_dgram_qlen FIXME
-max_noreply_time FIXME
-max_tx_data_size FIXME
-max_tx_window FIXME
-min_tx_turn_time FIXME
-mod_cong FIXME
-no_cong FIXME
-no_cong_thresh FIXME
-slot_timeout FIXME
-warn_noreply_time FIXME
+rto_max - INTEGER
+	The maximum value (in milliseconds) of the round trip timeout.  This
+	is the largest time interval that can elapse between retransmissions.
+
+	Default: 60000
+
+rto_min - INTEGER
+	The minimum value (in milliseconds) of the round trip timeout.  This
+	is the smallest time interval the can elapse between retransmissions.
+
+	Default: 1000
+
+hb_interval - INTEGER
+	The interval (in milliseconds) between HEARTBEAT chunks.  These chunks
+	are sent at the specified interval on idle paths to probe the state of
+	a given path between 2 associations.
+
+	Default: 30000
+
+sack_timeout - INTEGER
+	The amount of time (in milliseconds) that the implementation will wait
+	to send a SACK.
+
+	Default: 200
+
+valid_cookie_life - INTEGER
+	The default lifetime of the SCTP cookie (in milliseconds).  The cookie
+	is used during association establishment.
+
+	Default: 60000
+
+cookie_preserve_enable - BOOLEAN
+	Enable or disable the ability to extend the lifetime of the SCTP cookie
+	that is used during the establishment phase of SCTP association
+
+	1: Enable cookie lifetime extension.
+	0: Disable
+
+	Default: 1
+
+rcvbuf_policy - INTEGER
+	Determines if the receive buffer is attributed to the socket or to
+	association.   SCTP supports the capability to create multiple
+	associations on a single socket.  When using this capability, it is
+	possible that a single stalled association that's buffering a lot
+	of data may block other associations from delivering their data by
+	consuming all of the receive buffer space.  To work around this,
+	the rcvbuf_policy could be set to attribute the receiver buffer space
+	to each association instead of the socket.  This prevents the described
+	blocking.
+
+	1: rcvbuf space is per association
+	0: recbuf space is per socket
+
+	Default: 0
+
+sndbuf_policy - INTEGER
+	Similar to rcvbuf_policy above, this applies to send buffer space.
+
+	1: Send buffer is tracked per association
+	0: Send buffer is tracked per socket.
+
+	Default: 0
+
+sctp_mem - vector of 3 INTEGERs: min, pressure, max
+	Number of pages allowed for queueing by all SCTP sockets.
+
+	min: Below this number of pages SCTP is not bothered about its
+	memory appetite. When amount of memory allocated by SCTP exceeds
+	this number, SCTP starts to moderate memory usage.
+
+	pressure: This value was introduced to follow format of tcp_mem.
+
+	max: Number of pages allowed for queueing by all SCTP sockets.
+
+	Default is calculated at boot time from amount of available memory.
+
+sctp_rmem - vector of 3 INTEGERs: min, default, max
+	See tcp_rmem for a description.
+
+sctp_wmem  - vector of 3 INTEGERs: min, default, max
+	See tcp_wmem for a description.
+
+UNDOCUMENTED:
 
+/proc/sys/net/core/*
+	dev_weight FIXME
+
+/proc/sys/net/unix/*
+	max_dgram_qlen FIXME
+
+/proc/sys/net/irda/*
+	fast_poll_increase FIXME
+	warn_noreply_time FIXME
+	discovery_slots FIXME
+	slot_timeout FIXME
+	max_baud_rate FIXME
+	discovery_timeout FIXME
+	lap_keepalive_time FIXME
+	max_noreply_time FIXME
+	max_tx_data_size FIXME
+	max_tx_window FIXME
+	min_tx_turn_time FIXME