45 files changed, 273 insertions, 10 deletions

diff --git a/Documentation/networking/3c509.txt b/Documentation/networking/device_drivers/3com/3c509.txt
index fbf722e15ac3..fbf722e15ac3 100644
--- a/Documentation/networking/3c509.txt
+++ b/Documentation/networking/device_drivers/3com/3c509.txt
diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/device_drivers/3com/vortex.txt
index ad3dead052a4..587f3fcfbcae 100644
--- a/Documentation/networking/vortex.txt
+++ b/Documentation/networking/device_drivers/3com/vortex.txt
@@ -1,4 +1,4 @@
-Documentation/networking/vortex.txt
+Documentation/networking/device_drivers/3com/vortex.txt
 Andrew Morton
 30 April 2000
 
diff --git a/Documentation/networking/ena.txt b/Documentation/networking/device_drivers/amazon/ena.txt
index 2b4b6f57e549..2b4b6f57e549 100644
--- a/Documentation/networking/ena.txt
+++ b/Documentation/networking/device_drivers/amazon/ena.txt
diff --git a/Documentation/networking/cxgb.txt b/Documentation/networking/device_drivers/chelsio/cxgb.txt
index 20a887615c4a..20a887615c4a 100644
--- a/Documentation/networking/cxgb.txt
+++ b/Documentation/networking/device_drivers/chelsio/cxgb.txt
diff --git a/Documentation/networking/cs89x0.txt b/Documentation/networking/device_drivers/cirrus/cs89x0.txt
index 0e190180eec8..0e190180eec8 100644
--- a/Documentation/networking/cs89x0.txt
+++ b/Documentation/networking/device_drivers/cirrus/cs89x0.txt
diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/device_drivers/davicom/dm9000.txt
index 5552e2e575c5..5552e2e575c5 100644
--- a/Documentation/networking/dm9000.txt
+++ b/Documentation/networking/device_drivers/davicom/dm9000.txt
diff --git a/Documentation/networking/de4x5.txt b/Documentation/networking/device_drivers/dec/de4x5.txt
index c8e4ca9b2c3e..c8e4ca9b2c3e 100644
--- a/Documentation/networking/de4x5.txt
+++ b/Documentation/networking/device_drivers/dec/de4x5.txt
diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/device_drivers/dec/dmfe.txt
index 25320bf19c86..25320bf19c86 100644
--- a/Documentation/networking/dmfe.txt
+++ b/Documentation/networking/device_drivers/dec/dmfe.txt
diff --git a/Documentation/networking/dl2k.txt b/Documentation/networking/device_drivers/dlink/dl2k.txt
index cba74f7a3abc..cba74f7a3abc 100644
--- a/Documentation/networking/dl2k.txt
+++ b/Documentation/networking/device_drivers/dlink/dl2k.txt
diff --git a/Documentation/networking/dpaa.txt b/Documentation/networking/device_drivers/freescale/dpaa.txt
index f88194f71c54..f88194f71c54 100644
--- a/Documentation/networking/dpaa.txt
+++ b/Documentation/networking/device_drivers/freescale/dpaa.txt
diff --git a/Documentation/networking/dpaa2/dpio-driver.rst b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst
index 13588104161b..a188466b6698 100644
--- a/Documentation/networking/dpaa2/dpio-driver.rst
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst
@@ -19,8 +19,8 @@ pool management for network interfaces.
 This document provides an overview the Linux DPIO driver, its
 subcomponents, and its APIs.
 
-See Documentation/networking/dpaa2/overview.rst for a general overview of DPAA2
-and the general DPAA2 driver architecture in Linux.
+See Documentation/networking/device_drivers/freescale/dpaa2/overview.rst for
+a general overview of DPAA2 and the general DPAA2 driver architecture in Linux.
 
 Driver Overview
 ---------------
diff --git a/Documentation/networking/dpaa2/ethernet-driver.rst b/Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst
index 90ec940749e8..cb4c9a0c5a17 100644
--- a/Documentation/networking/dpaa2/ethernet-driver.rst
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst
@@ -33,7 +33,7 @@ hardware resources, like queues, do not have a corresponding MC object and
 are treated as internal resources of other objects.
 
 For a more detailed description of the DPAA2 architecture and its object
-abstractions see *Documentation/networking/dpaa2/overview.rst*.
+abstractions see *Documentation/networking/device_drivers/freescale/dpaa2/overview.rst*.
 
 Each Linux net device is built on top of a Datapath Network Interface (DPNI)
 object and uses Buffer Pools (DPBPs), I/O Portals (DPIOs) and Concentrators
diff --git a/Documentation/networking/dpaa2/index.rst b/Documentation/networking/device_drivers/freescale/dpaa2/index.rst
index 67bd87fe6c53..67bd87fe6c53 100644
--- a/Documentation/networking/dpaa2/index.rst
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/index.rst
diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
index d638b5a8aadd..d638b5a8aadd 100644
--- a/Documentation/networking/dpaa2/overview.rst
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
diff --git a/Documentation/networking/gianfar.txt b/Documentation/networking/device_drivers/freescale/gianfar.txt
index ba1daea7f2e4..ba1daea7f2e4 100644
--- a/Documentation/networking/gianfar.txt
+++ b/Documentation/networking/device_drivers/freescale/gianfar.txt
diff --git a/Documentation/networking/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst
index 5e2839b4ec92..5e2839b4ec92 100644
--- a/Documentation/networking/e100.rst
+++ b/Documentation/networking/device_drivers/intel/e100.rst
diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst
index 6379d4d20771..6379d4d20771 100644
--- a/Documentation/networking/e1000.rst
+++ b/Documentation/networking/device_drivers/intel/e1000.rst
diff --git a/Documentation/networking/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst
index 33554e5416c5..33554e5416c5 100644
--- a/Documentation/networking/e1000e.rst
+++ b/Documentation/networking/device_drivers/intel/e1000e.rst
diff --git a/Documentation/networking/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst
index bf5e5942f28d..bf5e5942f28d 100644
--- a/Documentation/networking/fm10k.rst
+++ b/Documentation/networking/device_drivers/intel/fm10k.rst
diff --git a/Documentation/networking/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst
index 0cc16c525d10..0cc16c525d10 100644
--- a/Documentation/networking/i40e.rst
+++ b/Documentation/networking/device_drivers/intel/i40e.rst
diff --git a/Documentation/networking/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst
index f8b42b64eb28..f8b42b64eb28 100644
--- a/Documentation/networking/iavf.rst
+++ b/Documentation/networking/device_drivers/intel/iavf.rst
diff --git a/Documentation/networking/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst
index 4d118b827bbb..4d118b827bbb 100644
--- a/Documentation/networking/ice.rst
+++ b/Documentation/networking/device_drivers/intel/ice.rst
diff --git a/Documentation/networking/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst
index ba16b86d5593..e87a4a72ea2d 100644
--- a/Documentation/networking/igb.rst
+++ b/Documentation/networking/device_drivers/intel/igb.rst
@@ -177,6 +177,25 @@ rate limit using the IProute2 tool. Download the latest version of the
 IProute2 tool from Sourceforge if your version does not have all the features
 you require.
 
+Credit Based Shaper (Qav Mode)
+------------------------------
+When enabling the CBS qdisc in the hardware offload mode, traffic shaping using
+the CBS (described in the IEEE 802.1Q-2018 Section 8.6.8.2 and discussed in the
+Annex L) algorithm will run in the i210 controller, so it's more accurate and
+uses less CPU.
+
+When using offloaded CBS, and the traffic rate obeys the configured rate
+(doesn't go above it), CBS should have little to no effect in the latency.
+
+The offloaded version of the algorithm has some limits, caused by how the idle
+slope is expressed in the adapter's registers. It can only represent idle slopes
+in 16.38431 kbps units, which means that if a idle slope of 2576kbps is
+requested, the controller will be configured to use a idle slope of ~2589 kbps,
+because the driver rounds the value up. For more details, see the comments on
+:c:func:`igb_config_tx_modes()`.
+
+NOTE: This feature is exclusive to i210 models.
+
 
 Support
 =======
diff --git a/Documentation/networking/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst
index a8a9ffa4f8d3..a8a9ffa4f8d3 100644
--- a/Documentation/networking/igbvf.rst
+++ b/Documentation/networking/device_drivers/intel/igbvf.rst
diff --git a/Documentation/networking/README.ipw2100 b/Documentation/networking/device_drivers/intel/ipw2100.txt
index 6f85e1d06031..6f85e1d06031 100644
--- a/Documentation/networking/README.ipw2100
+++ b/Documentation/networking/device_drivers/intel/ipw2100.txt
diff --git a/Documentation/networking/README.ipw2200 b/Documentation/networking/device_drivers/intel/ipw2200.txt
index b7658bed4906..b7658bed4906 100644
--- a/Documentation/networking/README.ipw2200
+++ b/Documentation/networking/device_drivers/intel/ipw2200.txt
diff --git a/Documentation/networking/ixgb.rst b/Documentation/networking/device_drivers/intel/ixgb.rst
index 8bd80e27843d..8bd80e27843d 100644
--- a/Documentation/networking/ixgb.rst
+++ b/Documentation/networking/device_drivers/intel/ixgb.rst
diff --git a/Documentation/networking/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst
index 86d887a63606..86d887a63606 100644
--- a/Documentation/networking/ixgbe.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbe.rst
diff --git a/Documentation/networking/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst
index 56cde6366c2f..56cde6366c2f 100644
--- a/Documentation/networking/ixgbevf.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst
diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/device_drivers/microsoft/netvsc.txt
index 3bfa635bbbd5..3bfa635bbbd5 100644
--- a/Documentation/networking/netvsc.txt
+++ b/Documentation/networking/device_drivers/microsoft/netvsc.txt
diff --git a/Documentation/networking/s2io.txt b/Documentation/networking/device_drivers/neterion/s2io.txt
index 0362a42f7cf4..0362a42f7cf4 100644
--- a/Documentation/networking/s2io.txt
+++ b/Documentation/networking/device_drivers/neterion/s2io.txt
diff --git a/Documentation/networking/vxge.txt b/Documentation/networking/device_drivers/neterion/vxge.txt
index abfec245f97c..abfec245f97c 100644
--- a/Documentation/networking/vxge.txt
+++ b/Documentation/networking/device_drivers/neterion/vxge.txt
diff --git a/Documentation/networking/LICENSE.qla3xxx b/Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
index 2f2077e34d81..2f2077e34d81 100644
--- a/Documentation/networking/LICENSE.qla3xxx
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
diff --git a/Documentation/networking/LICENSE.qlcnic b/Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic
index 2ae3b64983ab..2ae3b64983ab 100644
--- a/Documentation/networking/LICENSE.qlcnic
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic
diff --git a/Documentation/networking/LICENSE.qlge b/Documentation/networking/device_drivers/qlogic/LICENSE.qlge
index ce64e4d15b21..ce64e4d15b21 100644
--- a/Documentation/networking/LICENSE.qlge
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qlge
diff --git a/Documentation/networking/rmnet.txt b/Documentation/networking/device_drivers/qualcomm/rmnet.txt
index 6b341eaf2062..6b341eaf2062 100644
--- a/Documentation/networking/rmnet.txt
+++ b/Documentation/networking/device_drivers/qualcomm/rmnet.txt
diff --git a/Documentation/networking/README.sb1000 b/Documentation/networking/device_drivers/sb1000.txt
index f92c2aac56a9..f92c2aac56a9 100644
--- a/Documentation/networking/README.sb1000
+++ b/Documentation/networking/device_drivers/sb1000.txt
diff --git a/Documentation/networking/smc9.txt b/Documentation/networking/device_drivers/smsc/smc9.txt
index d1e15074e43d..d1e15074e43d 100644
--- a/Documentation/networking/smc9.txt
+++ b/Documentation/networking/device_drivers/smsc/smc9.txt
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/device_drivers/stmicro/stmmac.txt
index 2bb07078f535..2bb07078f535 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/device_drivers/stmicro/stmmac.txt
diff --git a/Documentation/networking/ti-cpsw.txt b/Documentation/networking/device_drivers/ti/cpsw.txt
index d4d4c0751a09..d4d4c0751a09 100644
--- a/Documentation/networking/ti-cpsw.txt
+++ b/Documentation/networking/device_drivers/ti/cpsw.txt
diff --git a/Documentation/networking/tlan.txt b/Documentation/networking/device_drivers/ti/tlan.txt
index 34550dfcef74..34550dfcef74 100644
--- a/Documentation/networking/tlan.txt
+++ b/Documentation/networking/device_drivers/ti/tlan.txt
diff --git a/Documentation/networking/spider_net.txt b/Documentation/networking/device_drivers/toshiba/spider_net.txt
index b0b75f8463b3..b0b75f8463b3 100644
--- a/Documentation/networking/spider_net.txt
+++ b/Documentation/networking/device_drivers/toshiba/spider_net.txt
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index af2a69439b93..acdfb5d2bcaa 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -108,8 +108,8 @@ neigh/default/gc_thresh2 - INTEGER
 	Default: 512
 
 neigh/default/gc_thresh3 - INTEGER
-	Maximum number of neighbor entries allowed.  Increase this
-	when using large numbers of interfaces and when communicating
+	Maximum number of non-PERMANENT neighbor entries allowed.  Increase
+	this when using large numbers of interfaces and when communicating
 	with large numbers of directly-connected peers.
 	Default: 1024
 
diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
index 918a1374af30..f8eb77ddbd44 100644
--- a/Documentation/networking/snmp_counter.rst
+++ b/Documentation/networking/snmp_counter.rst
@@ -17,7 +17,9 @@ Defined in `RFC1213 ipInReceives`_
 
 The number of packets received by the IP layer. It gets increasing at the
 beginning of ip_rcv function, always be updated together with
-IpExtInOctets. It indicates the number of aggregated segments after
+IpExtInOctets. It will be increased even if the packet is dropped
+later (e.g. due to the IP header is invalid or the checksum is wrong
+and so on).  It indicates the number of aggregated segments after
 GRO/LRO.
 
 * IpInDelivers
@@ -57,6 +59,58 @@ status. They count the real frame number regardless the LRO/GRO. So
 for the same packet, you might find that IpInReceives count 1, but
 IpExtInNoECTPkts counts 2 or more.
 
+* IpInHdrErrors
+Defined in `RFC1213 ipInHdrErrors`_. It indicates the packet is
+dropped due to the IP header error. It might happen in both IP input
+and IP forward paths.
+
+.. _RFC1213 ipInHdrErrors: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpInAddrErrors
+Defined in `RFC1213 ipInAddrErrors`_. It will be increased in two
+scenarios: (1) The IP address is invalid. (2) The destination IP
+address is not a local address and IP forwarding is not enabled
+
+.. _RFC1213 ipInAddrErrors: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpExtInNoRoutes
+This counter means the packet is dropped when the IP stack receives a
+packet and can't find a route for it from the route table. It might
+happen when IP forwarding is enabled and the destination IP address is
+not a local address and there is no route for the destination IP
+address.
+
+* IpInUnknownProtos
+Defined in `RFC1213 ipInUnknownProtos`_. It will be increased if the
+layer 4 protocol is unsupported by kernel. If an application is using
+raw socket, kernel will always deliver the packet to the raw socket
+and this counter won't be increased.
+
+.. _RFC1213 ipInUnknownProtos: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpExtInTruncatedPkts
+For IPv4 packet, it means the actual data size is smaller than the
+"Total Length" field in the IPv4 header.
+
+* IpInDiscards
+Defined in `RFC1213 ipInDiscards`_. It indicates the packet is dropped
+in the IP receiving path and due to kernel internal reasons (e.g. no
+enough memory).
+
+.. _RFC1213 ipInDiscards: https://tools.ietf.org/html/rfc1213#page-28
+
+* IpOutDiscards
+Defined in `RFC1213 ipOutDiscards`_. It indicates the packet is
+dropped in the IP sending path and due to kernel internal reasons.
+
+.. _RFC1213 ipOutDiscards: https://tools.ietf.org/html/rfc1213#page-28
+
+* IpOutNoRoutes
+Defined in `RFC1213 ipOutNoRoutes`_. It indicates the packet is
+dropped in the IP sending path and no route is found for it.
+
+.. _RFC1213 ipOutNoRoutes: https://tools.ietf.org/html/rfc1213#page-29
+
 ICMP counters
 ============
 * IcmpInMsgs and IcmpOutMsgs
@@ -425,6 +479,100 @@ The sum of CWND detected by packet delay. Dividing this value by
 TcpExtTCPHystartDelayDetect is the average CWND which detected by the
 packet delay.
 
+TCP retransmission and congestion control
+======================================
+The TCP protocol has two retransmission mechanisms: SACK and fast
+recovery. They are exclusive with each other. When SACK is enabled,
+the kernel TCP stack would use SACK, or kernel would use fast
+recovery. The SACK is a TCP option, which is defined in `RFC2018`_,
+the fast recovery is defined in `RFC6582`_, which is also called
+'Reno'.
+
+The TCP congestion control is a big and complex topic. To understand
+the related snmp counter, we need to know the states of the congestion
+control state machine. There are 5 states: Open, Disorder, CWR,
+Recovery and Loss. For details about these states, please refer page 5
+and page 6 of this document:
+https://pdfs.semanticscholar.org/0e9c/968d09ab2e53e24c4dca5b2d67c7f7140f8e.pdf
+
+.. _RFC2018: https://tools.ietf.org/html/rfc2018
+.. _RFC6582: https://tools.ietf.org/html/rfc6582
+
+* TcpExtTCPRenoRecovery and TcpExtTCPSackRecovery
+When the congestion control comes into Recovery state, if sack is
+used, TcpExtTCPSackRecovery increases 1, if sack is not used,
+TcpExtTCPRenoRecovery increases 1. These two counters mean the TCP
+stack begins to retransmit the lost packets.
+
+* TcpExtTCPSACKReneging
+A packet was acknowledged by SACK, but the receiver has dropped this
+packet, so the sender needs to retransmit this packet. In this
+situation, the sender adds 1 to TcpExtTCPSACKReneging. A receiver
+could drop a packet which has been acknowledged by SACK, although it is
+unusual, it is allowed by the TCP protocol. The sender doesn't really
+know what happened on the receiver side. The sender just waits until
+the RTO expires for this packet, then the sender assumes this packet
+has been dropped by the receiver.
+
+* TcpExtTCPRenoReorder
+The reorder packet is detected by fast recovery. It would only be used
+if SACK is disabled. The fast recovery algorithm detects recorder by
+the duplicate ACK number. E.g., if retransmission is triggered, and
+the original retransmitted packet is not lost, it is just out of
+order, the receiver would acknowledge multiple times, one for the
+retransmitted packet, another for the arriving of the original out of
+order packet. Thus the sender would find more ACks than its
+expectation, and the sender knows out of order occurs.
+
+* TcpExtTCPTSReorder
+The reorder packet is detected when a hole is filled. E.g., assume the
+sender sends packet 1,2,3,4,5, and the receiving order is
+1,2,4,5,3. When the sender receives the ACK of packet 3 (which will
+fill the hole), two conditions will let TcpExtTCPTSReorder increase
+1: (1) if the packet 3 is not re-retransmitted yet. (2) if the packet
+3 is retransmitted but the timestamp of the packet 3's ACK is earlier
+than the retransmission timestamp.
+
+* TcpExtTCPSACKReorder
+The reorder packet detected by SACK. The SACK has two methods to
+detect reorder: (1) DSACK is received by the sender. It means the
+sender sends the same packet more than one times. And the only reason
+is the sender believes an out of order packet is lost so it sends the
+packet again. (2) Assume packet 1,2,3,4,5 are sent by the sender, and
+the sender has received SACKs for packet 2 and 5, now the sender
+receives SACK for packet 4 and the sender doesn't retransmit the
+packet yet, the sender would know packet 4 is out of order. The TCP
+stack of kernel will increase TcpExtTCPSACKReorder for both of the
+above scenarios.
+
+
+DSACK
+=====
+The DSACK is defined in `RFC2883`_. The receiver uses DSACK to report
+duplicate packets to the sender. There are two kinds of
+duplications: (1) a packet which has been acknowledged is
+duplicate. (2) an out of order packet is duplicate. The TCP stack
+counts these two kinds of duplications on both receiver side and
+sender side.
+
+.. _RFC2883 : https://tools.ietf.org/html/rfc2883
+
+* TcpExtTCPDSACKOldSent
+The TCP stack receives a duplicate packet which has been acked, so it
+sends a DSACK to the sender.
+
+* TcpExtTCPDSACKOfoSent
+The TCP stack receives an out of order duplicate packet, so it sends a
+DSACK to the sender.
+
+* TcpExtTCPDSACKRecv
+The TCP stack receives a DSACK, which indicate an acknowledged
+duplicate packet is received.
+
+* TcpExtTCPDSACKOfoRecv
+The TCP stack receives a DSACK, which indicate an out of order
+duplciate packet is received.
+
 examples
 =======
 
@@ -945,3 +1093,98 @@ Both TcpExtListenOverflows and TcpExtListenDrops were 4. If the time
 between the 4th nc and the nstat was longer, the value of
 TcpExtListenOverflows and TcpExtListenDrops would be larger, because
 the SYN of the 4th nc was dropped, the client was retrying.
+
+IpInAddrErrors, IpExtInNoRoutes and IpOutNoRoutes
+----------------------------------------------
+server A IP address: 192.168.122.250
+server B IP address: 192.168.122.251
+Prepare on server A, add a route to server B::
+
+  $ sudo ip route add 8.8.8.8/32 via 192.168.122.251
+
+Prepare on server B, disable send_redirects for all interfaces::
+
+  $ sudo sysctl -w net.ipv4.conf.all.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.ens3.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.lo.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.default.send_redirects=0
+
+We want to let sever A send a packet to 8.8.8.8, and route the packet
+to server B. When server B receives such packet, it might send a ICMP
+Redirect message to server A, set send_redirects to 0 will disable
+this behavior.
+
+First, generate InAddrErrors. On server B, we disable IP forwarding::
+
+  $ sudo sysctl -w net.ipv4.conf.all.forwarding=0
+
+On server A, we send packets to 8.8.8.8::
+
+  $ nc -v 8.8.8.8 53
+
+On server B, we check the output of nstat::
+
+  $ nstat
+  #kernel
+  IpInReceives                    3                  0.0
+  IpInAddrErrors                  3                  0.0
+  IpExtInOctets                   180                0.0
+  IpExtInNoECTPkts                3                  0.0
+
+As we have let server A route 8.8.8.8 to server B, and we disabled IP
+forwarding on server B, Server A sent packets to server B, then server B
+dropped packets and increased IpInAddrErrors. As the nc command would
+re-send the SYN packet if it didn't receive a SYN+ACK, we could find
+multiple IpInAddrErrors.
+
+Second, generate IpExtInNoRoutes. On server B, we enable IP
+forwarding::
+
+  $ sudo sysctl -w net.ipv4.conf.all.forwarding=1
+
+Check the route table of server B and remove the default route::
+
+  $ ip route show
+  default via 192.168.122.1 dev ens3 proto static
+  192.168.122.0/24 dev ens3 proto kernel scope link src 192.168.122.251
+  $ sudo ip route delete default via 192.168.122.1 dev ens3 proto static
+
+On server A, we contact 8.8.8.8 again::
+
+  $ nc -v 8.8.8.8 53
+  nc: connect to 8.8.8.8 port 53 (tcp) failed: Network is unreachable
+
+On server B, run nstat::
+
+  $ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpOutRequests                   1                  0.0
+  IcmpOutMsgs                     1                  0.0
+  IcmpOutDestUnreachs             1                  0.0
+  IcmpMsgOutType3                 1                  0.0
+  IpExtInNoRoutes                 1                  0.0
+  IpExtInOctets                   60                 0.0
+  IpExtOutOctets                  88                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+We enabled IP forwarding on server B, when server B received a packet
+which destination IP address is 8.8.8.8, server B will try to forward
+this packet. We have deleted the default route, there was no route for
+8.8.8.8, so server B increase IpExtInNoRoutes and sent the "ICMP
+Destination Unreachable" message to server A.
+
+Third, generate IpOutNoRoutes. Run ping command on server B::
+
+  $ ping -c 1 8.8.8.8
+  connect: Network is unreachable
+
+Run nstat on server B::
+
+  $ nstat
+  #kernel
+  IpOutNoRoutes                   1                  0.0
+
+We have deleted the default route on server B. Server B couldn't find
+a route for the 8.8.8.8 IP address, so server B increased
+IpOutNoRoutes.
diff --git a/Documentation/networking/xfrm_device.txt b/Documentation/networking/xfrm_device.txt
index 267f55b5f54a..a1c904dc70dc 100644
--- a/Documentation/networking/xfrm_device.txt
+++ b/Documentation/networking/xfrm_device.txt
@@ -111,9 +111,10 @@ the stack in xfrm_input().
 		xfrm_state_hold(xs);
 
 	store the state information into the skb
-		skb->sp = secpath_dup(skb->sp);
-		skb->sp->xvec[skb->sp->len++] = xs;
-		skb->sp->olen++;
+		sp = secpath_set(skb);
+		if (!sp) return;
+		sp->xvec[sp->len++] = xs;
+		sp->olen++;
 
 	indicate the success and/or error status of the offload
 		xo = xfrm_offload(skb);