9 files changed, 817 insertions, 72 deletions

diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index 77c3c202991b..8af6d9626878 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -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>
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 5ddbe350487a..ac98851f7a0c 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -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.
diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index 7a3bb1abb830..b132e4a3cf0f 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -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
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index c7712787933c..7185e4c41e59 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -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.
-
-        conf/all/rp_filter must also be set to TRUE to do 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.
+
+        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.  
+        Configure interface-specific Host/Router behaviour.
 
-        Note: It is recommended to have the same setting on all 
+        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.
@@ -1025,8 +1037,8 @@ 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
 
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
new file mode 100644
index 000000000000..0e58b4539176
--- /dev/null
+++ b/Documentation/networking/timestamping.txt
@@ -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.
diff --git a/Documentation/networking/timestamping/.gitignore b/Documentation/networking/timestamping/.gitignore
new file mode 100644
index 000000000000..71e81eb2e22f
--- /dev/null
+++ b/Documentation/networking/timestamping/.gitignore
@@ -0,0 +1 @@
+timestamping
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
new file mode 100644
index 000000000000..2a1489fdc036
--- /dev/null
+++ b/Documentation/networking/timestamping/Makefile
@@ -0,0 +1,6 @@
+CPPFLAGS = -I../../../include
+
+timestamping: timestamping.c
+
+clean:
+        rm -f timestamping
diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c
new file mode 100644
index 000000000000..43d143104210
--- /dev/null
+++ b/Documentation/networking/timestamping/timestamping.c
@@ -0,0 +1,533 @@
+/*
+ * This program demonstrates how the various time stamping features in
+ * the Linux kernel work. It emulates the behavior of a PTP
+ * implementation in stand-alone master mode by sending PTPv1 Sync
+ * multicasts once every second. It looks for similar packets, but
+ * beyond that doesn't actually implement PTP.
+ *
+ * Outgoing packets are time stamped with SO_TIMESTAMPING with or
+ * without hardware support.
+ *
+ * Incoming packets are time stamped with SO_TIMESTAMPING with or
+ * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and
+ * SO_TIMESTAMP[NS].
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Author: Patrick Ohly <patrick.ohly@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <string.h>
+
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <sys/select.h>
+#include <sys/ioctl.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "asm/types.h"
+#include "linux/net_tstamp.h"
+#include "linux/errqueue.h"
+
+#ifndef SO_TIMESTAMPING
+# define SO_TIMESTAMPING         37
+# define SCM_TIMESTAMPING        SO_TIMESTAMPING
+#endif
+
+#ifndef SO_TIMESTAMPNS
+# define SO_TIMESTAMPNS 35
+#endif
+
+#ifndef SIOCGSTAMPNS
+# define SIOCGSTAMPNS 0x8907
+#endif
+
+#ifndef SIOCSHWTSTAMP
+# define SIOCSHWTSTAMP 0x89b0
+#endif
+
+static void usage(const char *error)
+{
+        if (error)
+                printf("invalid option: %s\n", error);
+        printf("timestamping interface option*\n\n"
+               "Options:\n"
+               "  IP_MULTICAST_LOOP - looping outgoing multicasts\n"
+               "  SO_TIMESTAMP - normal software time stamping, ms resolution\n"
+               "  SO_TIMESTAMPNS - more accurate software time stamping\n"
+               "  SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n"
+               "  SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n"
+               "  SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n"
+               "  SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n"
+               "  SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
+               "  SOF_TIMESTAMPING_SYS_HARDWARE - request reporting of transformed HW time stamps\n"
+               "  SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
+               "  SIOCGSTAMP - check last socket time stamp\n"
+               "  SIOCGSTAMPNS - more accurate socket time stamp\n");
+        exit(1);
+}
+
+static void bail(const char *error)
+{
+        printf("%s: %s\n", error, strerror(errno));
+        exit(1);
+}
+
+static const unsigned char sync[] = {
+        0x00, 0x01, 0x00, 0x01,
+        0x5f, 0x44, 0x46, 0x4c,
+        0x54, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x00,
+        0x01, 0x01,
+
+        /* fake uuid */
+        0x00, 0x01,
+        0x02, 0x03, 0x04, 0x05,
+
+        0x00, 0x01, 0x00, 0x37,
+        0x00, 0x00, 0x00, 0x08,
+        0x00, 0x00, 0x00, 0x00,
+        0x49, 0x05, 0xcd, 0x01,
+        0x29, 0xb1, 0x8d, 0xb0,
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x01,
+
+        /* fake uuid */
+        0x00, 0x01,
+        0x02, 0x03, 0x04, 0x05,
+
+        0x00, 0x00, 0x00, 0x37,
+        0x00, 0x00, 0x00, 0x04,
+        0x44, 0x46, 0x4c, 0x54,
+        0x00, 0x00, 0xf0, 0x60,
+        0x00, 0x01, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x01,
+        0x00, 0x00, 0xf0, 0x60,
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x04,
+        0x44, 0x46, 0x4c, 0x54,
+        0x00, 0x01,
+
+        /* fake uuid */
+        0x00, 0x01,
+        0x02, 0x03, 0x04, 0x05,
+
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x00,
+        0x00, 0x00, 0x00, 0x00
+};
+
+static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len)
+{
+        struct timeval now;
+        int res;
+
+        res = sendto(sock, sync, sizeof(sync), 0,
+                addr, addr_len);
+        gettimeofday(&now, 0);
+        if (res < 0)
+                printf("%s: %s\n", "send", strerror(errno));
+        else
+                printf("%ld.%06ld: sent %d bytes\n",
+                       (long)now.tv_sec, (long)now.tv_usec,
+                       res);
+}
+
+static void printpacket(struct msghdr *msg, int res,
+                        char *data,
+                        int sock, int recvmsg_flags,
+                        int siocgstamp, int siocgstampns)
+{
+        struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name;
+        struct cmsghdr *cmsg;
+        struct timeval tv;
+        struct timespec ts;
+        struct timeval now;
+
+        gettimeofday(&now, 0);
+
+        printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n",
+               (long)now.tv_sec, (long)now.tv_usec,
+               (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
+               res,
+               inet_ntoa(from_addr->sin_addr),
+               msg->msg_controllen);
+        for (cmsg = CMSG_FIRSTHDR(msg);
+             cmsg;
+             cmsg = CMSG_NXTHDR(msg, cmsg)) {
+                printf("   cmsg len %d: ", cmsg->cmsg_len);
+                switch (cmsg->cmsg_level) {
+                case SOL_SOCKET:
+                        printf("SOL_SOCKET ");
+                        switch (cmsg->cmsg_type) {
+                        case SO_TIMESTAMP: {
+                                struct timeval *stamp =
+                                        (struct timeval *)CMSG_DATA(cmsg);
+                                printf("SO_TIMESTAMP %ld.%06ld",
+                                       (long)stamp->tv_sec,
+                                       (long)stamp->tv_usec);
+                                break;
+                        }
+                        case SO_TIMESTAMPNS: {
+                                struct timespec *stamp =
+                                        (struct timespec *)CMSG_DATA(cmsg);
+                                printf("SO_TIMESTAMPNS %ld.%09ld",
+                                       (long)stamp->tv_sec,
+                                       (long)stamp->tv_nsec);
+                                break;
+                        }
+                        case SO_TIMESTAMPING: {
+                                struct timespec *stamp =
+                                        (struct timespec *)CMSG_DATA(cmsg);
+                                printf("SO_TIMESTAMPING ");
+                                printf("SW %ld.%09ld ",
+                                       (long)stamp->tv_sec,
+                                       (long)stamp->tv_nsec);
+                                stamp++;
+                                printf("HW transformed %ld.%09ld ",
+                                       (long)stamp->tv_sec,
+                                       (long)stamp->tv_nsec);
+                                stamp++;
+                                printf("HW raw %ld.%09ld",
+                                       (long)stamp->tv_sec,
+                                       (long)stamp->tv_nsec);
+                                break;
+                        }
+                        default:
+                                printf("type %d", cmsg->cmsg_type);
+                                break;
+                        }
+                        break;
+                case IPPROTO_IP:
+                        printf("IPPROTO_IP ");
+                        switch (cmsg->cmsg_type) {
+                        case IP_RECVERR: {
+                                struct sock_extended_err *err =
+                                        (struct sock_extended_err *)CMSG_DATA(cmsg);
+                                printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s",
+                                        strerror(err->ee_errno),
+                                        err->ee_origin,
+#ifdef SO_EE_ORIGIN_TIMESTAMPING
+                                        err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ?
+                                        "bounced packet" : "unexpected origin"
+#else
+                                        "probably SO_EE_ORIGIN_TIMESTAMPING"
+#endif
+                                        );
+                                if (res < sizeof(sync))
+                                        printf(" => truncated data?!");
+                                else if (!memcmp(sync, data + res - sizeof(sync),
+                                                        sizeof(sync)))
+                                        printf(" => GOT OUR DATA BACK (HURRAY!)");
+                                break;
+                        }
+                        case IP_PKTINFO: {
+                                struct in_pktinfo *pktinfo =
+                                        (struct in_pktinfo *)CMSG_DATA(cmsg);
+                                printf("IP_PKTINFO interface index %u",
+                                        pktinfo->ipi_ifindex);
+                                break;
+                        }
+                        default:
+                                printf("type %d", cmsg->cmsg_type);
+                                break;
+                        }
+                        break;
+                default:
+                        printf("level %d type %d",
+                                cmsg->cmsg_level,
+                                cmsg->cmsg_type);
+                        break;
+                }
+                printf("\n");
+        }
+
+        if (siocgstamp) {
+                if (ioctl(sock, SIOCGSTAMP, &tv))
+                        printf("   %s: %s\n", "SIOCGSTAMP", strerror(errno));
+                else
+                        printf("SIOCGSTAMP %ld.%06ld\n",
+                               (long)tv.tv_sec,
+                               (long)tv.tv_usec);
+        }
+        if (siocgstampns) {
+                if (ioctl(sock, SIOCGSTAMPNS, &ts))
+                        printf("   %s: %s\n", "SIOCGSTAMPNS", strerror(errno));
+                else
+                        printf("SIOCGSTAMPNS %ld.%09ld\n",
+                               (long)ts.tv_sec,
+                               (long)ts.tv_nsec);
+        }
+}
+
+static void recvpacket(int sock, int recvmsg_flags,
+                       int siocgstamp, int siocgstampns)
+{
+        char data[256];
+        struct msghdr msg;
+        struct iovec entry;
+        struct sockaddr_in from_addr;
+        struct {
+                struct cmsghdr cm;
+                char control[512];
+        } control;
+        int res;
+
+        memset(&msg, 0, sizeof(msg));
+        msg.msg_iov = &entry;
+        msg.msg_iovlen = 1;
+        entry.iov_base = data;
+        entry.iov_len = sizeof(data);
+        msg.msg_name = (caddr_t)&from_addr;
+        msg.msg_namelen = sizeof(from_addr);
+        msg.msg_control = &control;
+        msg.msg_controllen = sizeof(control);
+
+        res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT);
+        if (res < 0) {
+                printf("%s %s: %s\n",
+                       "recvmsg",
+                       (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
+                       strerror(errno));
+        } else {
+                printpacket(&msg, res, data,
+                            sock, recvmsg_flags,
+                            siocgstamp, siocgstampns);
+        }
+}
+
+int main(int argc, char **argv)
+{
+        int so_timestamping_flags = 0;
+        int so_timestamp = 0;
+        int so_timestampns = 0;
+        int siocgstamp = 0;
+        int siocgstampns = 0;
+        int ip_multicast_loop = 0;
+        char *interface;
+        int i;
+        int enabled = 1;
+        int sock;
+        struct ifreq device;
+        struct ifreq hwtstamp;
+        struct hwtstamp_config hwconfig, hwconfig_requested;
+        struct sockaddr_in addr;
+        struct ip_mreq imr;
+        struct in_addr iaddr;
+        int val;
+        socklen_t len;
+        struct timeval next;
+
+        if (argc < 2)
+                usage(0);
+        interface = argv[1];
+
+        for (i = 2; i < argc; i++) {
+                if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
+                        so_timestamp = 1;
+                else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS"))
+                        so_timestampns = 1;
+                else if (!strcasecmp(argv[i], "SIOCGSTAMP"))
+                        siocgstamp = 1;
+                else if (!strcasecmp(argv[i], "SIOCGSTAMPNS"))
+                        siocgstampns = 1;
+                else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP"))
+                        ip_multicast_loop = 1;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SYS_HARDWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_SYS_HARDWARE;
+                else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE"))
+                        so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+                else
+                        usage(argv[i]);
+        }
+
+        sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP);
+        if (socket < 0)
+                bail("socket");
+
+        memset(&device, 0, sizeof(device));
+        strncpy(device.ifr_name, interface, sizeof(device.ifr_name));
+        if (ioctl(sock, SIOCGIFADDR, &device) < 0)
+                bail("getting interface IP address");
+
+        memset(&hwtstamp, 0, sizeof(hwtstamp));
+        strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name));
+        hwtstamp.ifr_data = (void *)&hwconfig;
+        memset(&hwconfig, 0, sizeof(&hwconfig));
+        hwconfig.tx_type =
+                (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
+                HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+        hwconfig.rx_filter =
+                (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+                HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
+        hwconfig_requested = hwconfig;
+        if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) {
+                if ((errno == EINVAL || errno == ENOTSUP) &&
+                    hwconfig_requested.tx_type == HWTSTAMP_TX_OFF &&
+                    hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE)
+                        printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n");
+                else
+                        bail("SIOCSHWTSTAMP");
+        }
+        printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n",
+               hwconfig_requested.tx_type, hwconfig.tx_type,
+               hwconfig_requested.rx_filter, hwconfig.rx_filter);
+
+        /* bind to PTP port */
+        addr.sin_family = AF_INET;
+        addr.sin_addr.s_addr = htonl(INADDR_ANY);
+        addr.sin_port = htons(319 /* PTP event port */);
+        if (bind(sock,
+                 (struct sockaddr *)&addr,
+                 sizeof(struct sockaddr_in)) < 0)
+                bail("bind");
+
+        /* set multicast group for outgoing packets */
+        inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */
+        addr.sin_addr = iaddr;
+        imr.imr_multiaddr.s_addr = iaddr.s_addr;
+        imr.imr_interface.s_addr =
+                ((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr;
+        if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF,
+                       &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0)
+                bail("set multicast");
+
+        /* join multicast group, loop our own packet */
+        if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP,
+                       &imr, sizeof(struct ip_mreq)) < 0)
+                bail("join multicast group");
+
+        if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP,
+                       &ip_multicast_loop, sizeof(enabled)) < 0) {
+                bail("loop multicast");
+        }
+
+        /* set socket options for time stamping */
+        if (so_timestamp &&
+                setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP,
+                           &enabled, sizeof(enabled)) < 0)
+                bail("setsockopt SO_TIMESTAMP");
+
+        if (so_timestampns &&
+                setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS,
+                           &enabled, sizeof(enabled)) < 0)
+                bail("setsockopt SO_TIMESTAMPNS");
+
+        if (so_timestamping_flags &&
+                setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING,
+                           &so_timestamping_flags,
+                           sizeof(so_timestamping_flags)) < 0)
+                bail("setsockopt SO_TIMESTAMPING");
+
+        /* request IP_PKTINFO for debugging purposes */
+        if (setsockopt(sock, SOL_IP, IP_PKTINFO,
+                       &enabled, sizeof(enabled)) < 0)
+                printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno));
+
+        /* verify socket options */
+        len = sizeof(val);
+        if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0)
+                printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno));
+        else
+                printf("SO_TIMESTAMP %d\n", val);
+
+        if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0)
+                printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS",
+                       strerror(errno));
+        else
+                printf("SO_TIMESTAMPNS %d\n", val);
+
+        if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) {
+                printf("%s: %s\n", "getsockopt SO_TIMESTAMPING",
+                       strerror(errno));
+        } else {
+                printf("SO_TIMESTAMPING %d\n", val);
+                if (val != so_timestamping_flags)
+                        printf("   not the expected value %d\n",
+                               so_timestamping_flags);
+        }
+
+        /* send packets forever every five seconds */
+        gettimeofday(&next, 0);
+        next.tv_sec = (next.tv_sec + 1) / 5 * 5;
+        next.tv_usec = 0;
+        while (1) {
+                struct timeval now;
+                struct timeval delta;
+                long delta_us;
+                int res;
+                fd_set readfs, errorfs;
+
+                gettimeofday(&now, 0);
+                delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 +
+                        (long)(next.tv_usec - now.tv_usec);
+                if (delta_us > 0) {
+                        /* continue waiting for timeout or data */
+                        delta.tv_sec = delta_us / 1000000;
+                        delta.tv_usec = delta_us % 1000000;
+
+                        FD_ZERO(&readfs);
+                        FD_ZERO(&errorfs);
+                        FD_SET(sock, &readfs);
+                        FD_SET(sock, &errorfs);
+                        printf("%ld.%06ld: select %ldus\n",
+                               (long)now.tv_sec, (long)now.tv_usec,
+                               delta_us);
+                        res = select(sock + 1, &readfs, 0, &errorfs, &delta);
+                        gettimeofday(&now, 0);
+                        printf("%ld.%06ld: select returned: %d, %s\n",
+                               (long)now.tv_sec, (long)now.tv_usec,
+                               res,
+                               res < 0 ? strerror(errno) : "success");
+                        if (res > 0) {
+                                if (FD_ISSET(sock, &readfs))
+                                        printf("ready for reading\n");
+                                if (FD_ISSET(sock, &errorfs))
+                                        printf("has error\n");
+                                recvpacket(sock, 0,
+                                           siocgstamp,
+                                           siocgstampns);
+                                recvpacket(sock, MSG_ERRQUEUE,
+                                           siocgstamp,
+                                           siocgstampns);
+                        }
+                } else {
+                        /* write one packet */
+                        sendpacket(sock,
+                                   (struct sockaddr *)&addr,
+                                   sizeof(addr));
+                        next.tv_sec += 5;
+                        continue;
+                }
+        }
+
+        return 0;
+}
diff --git a/Documentation/powerpc/dts-bindings/fsl/tsec.txt b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
index 7fa4b27574b5..edb7ae19e868 100644
--- a/Documentation/powerpc/dts-bindings/fsl/tsec.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
@@ -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 {