- 01 Aug, 2015 6 commits
-
-
David S. Miller authored
Tom Herbert says: ==================== ipv6: Turn on auto IPv6 flow labels by default BSD (MacOS) has already turned on flow labels by default and this does not seem to be causing any problems in the Internet. Let's go ahead and turn them on by default. We'll continue to monitor for any devices start choking on them. Flow labels are important since they are the desired solution for network devices to perform ECMP and RSS (RFC6437 and RFC6438). Traditionally, devices perform a 5-tuple hash on packets that includes port numbers. For the most part, these devices can only compute 5-tuple hashes for TCP and UDP. This severely limits our ability to get good network load balancing for other protocols (IPIP, GRE,ESP, etc.), and hence we are limited in using other protocols. Unfortunately, this method is accepted as the de facto standard to the extent that there are several proposals to encapsulate protocols in UDP _just_ for the purposes for getting ECMP to work. With hosts generating flow labels and devices taking them as input into ECMP (several already do), we can start to fix this fundamental problem. This patch set: - Changes IPV6_FLOWINFO sockopt to be opt-out of flow labels for connections rather than opt-in - Disable flow label state ranges sysctl by default - Enable auto flow labels sysctl by default v2: - Added functions to create an skb->hash based on flowi4 and flowi6. These are called in output path when creating a packet - Call skb_get_hash_flowi6 in ip6_make_flowlabel - Implement the auto_flowlabels sysctl as a mode for auto flowlabels. There are four modes which correspond to flow labels being enabled and whether socket option can be used to opt in or opt out of using them ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tom Herbert authored
Initialize auto_flowlabels to one. This enables automatic flow labels, individual socket may disable them using the IPV6_AUTOFLOWLABEL socket option. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tom Herbert authored
Per RFC6437 stateful flow labels (e.g. labels set by flow label manager) cannot "disturb" nodes taking part in stateless flow labels. While the ranges only reduce the flow label entropy by one bit, it is conceivable that this might bias the algorithm on some routers causing a load imbalance. For best results on the Internet we really need the full 20 bits. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tom Herbert authored
Change the meaning of net.ipv6.auto_flowlabels to provide a mode for automatic flow labels generation. There are four modes: 0: flow labels are disabled 1: flow labels are enabled, sockets can opt-out 2: flow labels are allowed, sockets can opt-in 3: flow labels are enabled and enforced, no opt-out for sockets np->autoflowlabel is initialized according to the sysctl value. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tom Herbert authored
We can't call skb_get_hash here since the packet is not complete to do flow_dissector. Create hash based on flowi6 instead. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tom Herbert authored
Add skb_get_hash_flowi6 and skb_get_hash_flowi4 which derive an sk_buff hash from flowi6 and flowi4 structures respectively. These functions can be called when creating a packet in the output path where the new sk_buff does not yet contain a fully formed packet that is parsable by flow dissector. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 31 Jul, 2015 33 commits
-
-
David S. Miller authored
Florian Fainelli says: ==================== net: GENET, SYSTEMPORT and DSA netconsole This patch series adds support for netconsole in the GENET, SYSTEMPORT and DSA drivers. A small refactoring to the DSA transmit path is required to avoid duplicating the dsa_netpoll_send_skb() into each and every tagging protocol supported. Testing on e.g: mv643xx_eth and/or e1000e would be much appreciated! Changes in v2: - properly disable/enable interrupts in GENET and SYSTEMPORT - pass the reallocated SKB back to dsa_slave_xmit() in case a tag protocol had to alter the original SKB ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Florian Fainelli authored
Add support for using DSA slave network devices with netconsole, which requires us to allocate and free custom netpoll instances and invoke the parent network device poll controller callback. In order for netconsole to work, we need to construct the DSA tag, but not queue the skb for transmission on the master network device xmit function. Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Florian Fainelli authored
All tagging protocols do the same thing: increment device statistics, make room for the tag to be inserted, create the tag, invoke the parent network device transmit function. In order to prepare for adding netpoll support, which requires the tag creation, but not using the parent network device transmit function, do some little refactoring which eliminates duplication between the 4 tagging protocols supported. We need to return a sk_buff pointer back to the caller because the tag specific transmit function may have to reallocate the original skb (e.g: tag_trailer.c) and this is the one we should be transmitting, not the original sk_buff we were passed. Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Florian Fainelli authored
Implement a poll controller for netconsole which invokes the RX interrupt handler to poll for incoming packets, and cleans up all TX queues by invoking the TX interrupt handler. Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Florian Fainelli authored
Implement a poll controller for netconsole which invokes both of our interrupt handlers for the different RX/TX queues. Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Nikolay Aleksandrov authored
tlb_dynamic_lb could be set only via sysfs, this patch allows it to be set via netlink. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Merge tag 'wireless-drivers-next-for-davem-2015-07-31' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next Kalle Valo says: ==================== Major changes: mwifiex: * add TX DATA Pause support * add multichannel and TDLS channel switch support ath10k: * enable VHT for IBSS * initial work to support qca99x0 and the corresponding 10.4 firmware branch ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Daniel Pieczko authored
Signed-off-by: Shradha Shah <sshah@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Daniel Pieczko authored
The policy in the net driver is to attempt MCDI commands and then handle any EPERM error codes appropriately when returned by unprivileged functions. The ethtool selftest contains some tests which are useful on an unprivileged function, such as the event queue interrupt tests, but other tests cannot be performed as the function does not have the required permissions. If a test returns -EPERM, act as though the test was not run and continue. Signed-off-by: Shradha Shah <sshah@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Shaohui Xie authored
This patch added driver to support Aquantia PHYs AQ1202, AQ2104, AQR105, AQR405, which accessed through clause 45. Signed-off-by: Shaohui Xie <Shaohui.Xie@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Use vsprintf extension %pI4 instead. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
hayeswang authored
The UEFI driver would enable zero length, and the Linux driver doesn't need it. Zero length let the hw complete the transfer with length 0, when there is no received packet. It would add the load of USB host controller and reduce the performance. Signed-off-by: Hayes Wang <hayeswang@realtek.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Alexei Starovoitov authored
Two vxlan driver flags FLOWBASED and COLLECT_METADATA need to be set to make use of its new flow mode. The former already exposed. Expose the latter. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Roopa Prabhu says: ==================== af_mpls: fix undefined reference to ip6_route_output with CONFIG_IPV6=n This patch series uses ipv6_stub_impl.ipv6_dst_lookup instead of ip6_route_output. Follows the vxlan drivers usage of ipv6_stub_impl.ipv6_dst_lookup. There is no sk in the af_mpls context from where ipv6_stub_impl.ipv6_dst_lookup is used. sk appears to be needed to get the namespace 'net' and is optional otherwise. This patch series changes ipv6_stub_impl.ipv6_dst_lookup to take net argument. sk remains optional. v1 - v2: use IS_BUILTIN v2 - v3: Use new Kconfig option that depends on (IPV6 || IPV6=n) as suggested by Dave. Also uses IS_ERR as suggested by Thomas. v3 - v4: Include missed case of (MPLS_ROUTING=y && IPV6=m) reported by Dave. v4 - v5: Use ipv6_stub_impl.ipv6_dst_lookup as suggested by Hannes v5 - v6: protect against null ipv6_stub by statically declaring a ipv6_dst_lookup NOP func ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Roopa Prabhu authored
Undefined reference to ip6_route_output and ip_route_output was reported with CONFIG_INET=n and CONFIG_IPV6=n. This patch uses ipv6_stub_impl.ipv6_dst_lookup instead of ip6_route_output. And wraps affected code under IS_ENABLED(CONFIG_INET) and IS_ENABLED(CONFIG_IPV6). Reported-by: kbuild test robot <fengguang.wu@intel.com> Reported-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Roopa Prabhu authored
This patch adds net argument to ipv6_stub_impl.ipv6_dst_lookup for use cases where sk is not available (like mpls). sk appears to be needed to get the namespace 'net' and is optional otherwise. This patch series changes ipv6_stub_impl.ipv6_dst_lookup to take net argument. sk remains optional. All callers of ipv6_stub_impl.ipv6_dst_lookup have been modified to pass net. I have modified them to use already available 'net' in the scope of the call. I can change them to sock_net(sk) to avoid any unintended change in behaviour if sock namespace is different. They dont seem to be from code inspection. Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Alexei Starovoitov authored
Introduce helpers to let eBPF programs attached to TC manipulate tunnel metadata: bpf_skb_[gs]et_tunnel_key(skb, key, size, flags) skb: pointer to skb key: pointer to 'struct bpf_tunnel_key' size: size of 'struct bpf_tunnel_key' flags: room for future extensions First eBPF program that uses these helpers will allocate per_cpu metadata_dst structures that will be used on TX. On RX metadata_dst is allocated by tunnel driver. Typical usage for TX: struct bpf_tunnel_key tkey; ... populate tkey ... bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), 0); bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); RX: struct bpf_tunnel_key tkey = {}; bpf_skb_get_tunnel_key(skb, &tkey, sizeof(tkey), 0); ... lookup or redirect based on tkey ... 'struct bpf_tunnel_key' will be extended in the future by adding elements to the end and the 'size' argument will indicate which fields are populated, thereby keeping backwards compatibility. The 'flags' argument may be used as well when the 'size' is not enough or to indicate completely different layout of bpf_tunnel_key. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Woojung.Huh@microchip.com authored
Repost patch of driver for LAN7800 family of USB 2.0 & USB 3.0 to Gigabit Ethernet. - remove module param which can be configurable by standard mechanism. - remove other module parms except msg_level per review comment. - update to handle byte swap for statistics structure correctly. Signed-off-by: Woojung Huh <woojung.huh@microchip.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
This patch adds support to read the dmesg BPF JIT dump also from a file instead of the klog buffer. I found this quite useful when going through some 'before/after patch' logs. It also fixes a regex leak found by valgrind when no image dump was found. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Kalle Valo authored
This reverts commit 6301566e. Oleksij Rempel noticed that the randomness doesn't look to be good enough and Stephan Mueller commented: "I would say that the discussed RNG does not seem fit for hooking it up with the hwrandom framework." http://lkml.kernel.org/g/3945775.m5HblJPgiO@tauon.atsec.com So let's the revert the patch until we are sure that we can trust this random generator. Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
-
David S. Miller authored
Jon Maloy says: ==================== tipc: separate link aggregation from link layer We continue the work on separating the roles of the link aggregation and link layers, as well as making code cleanups in general. This second commit batch focuses on moving the orchestration of link failover and synchronization to the node level, as well as preparing the node lock structure for further future impovements. We also make some changes to message delivery between link and socket layer, in order to make this mechanism safer and less obscure. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
We simplify the link creation function tipc_link_create() and the way the link struct it is connected to the node struct. In particular, we remove the duplicate initialization of some fields which are anyway set in tipc_link_reset(). Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
Currently, when we extract small messages from a message bundle, or when many messages have accumulated in the link arrival queue, those messages are added one by one to the lock protected link input queue. This may increase contention with the reader of that queue, in the function tipc_sk_rcv(). This commit introduces a temporary, unprotected input queue in tipc_link_rcv() for such cases. Only when the arrival queue has been emptied, and the function is ready to return, does it splice the whole temporary queue into the real input queue. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
After the most recent changes, all access calls to a link which may entail addition of messages to the link's input queue are postpended by an explicit call to tipc_sk_rcv(), using a reference to the correct queue. This means that the potentially hazardous implicit delivery, using tipc_node_unlock() in combination with a binary flag and a cached queue pointer, now has become redundant. This commit removes this implicit delivery mechanism both for regular data messages and for binding table update messages. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
In order to facilitate future improvements to the locking structure, we want to make resetting and establishing of links non-atomic. I.e., the functions tipc_node_link_up() and tipc_node_link_down() should be called from outside the node lock context, and grab/release the node lock themselves. This requires that we can freeze the link state from the moment it is set to RESETTING or PEER_RESET in one lock context until it is set to RESET or ESTABLISHING in a later context. The recently introduced link FSM makes this possible, so we are now ready to introduce the above change. This commit implements this. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
The node lock is currently grabbed and and released in the function tipc_disc_rcv() in the file discover.c. As a preparation for the next commits, we need to move this node lock handling, along with the code area it is covering, to node.c. This commit introduces this change. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
Until now, we have been handling link failover and synchronization by using an additional link state variable, "exec_mode". This variable is not independent of the link FSM state, something causing a risk of inconsistencies, apart from the fact that it clutters the code. The conditions are now in place to define a new link FSM that covers all existing use cases, including failover and synchronization, and eliminate the "exec_mode" field altogether. The FSM must also support non-atomic resetting of links, which will be introduced later. The new link FSM is shown below, with 7 states and 8 events. Only events leading to state change are shown as edges. +------------------------------------+ |RESET_EVT | | | | +--------------+ | +-----------------| SYNCHING |-----------------+ | |FAILURE_EVT +--------------+ PEER_RESET_EVT| | | A | | | | | | | | | | | | | | |SYNCH_ |SYNCH_ | | | |BEGIN_EVT |END_EVT | | | | | | | V | V V | +-------------+ +--------------+ +------------+ | | RESETTING |<---------| ESTABLISHED |--------->| PEER_RESET | | +-------------+ FAILURE_ +--------------+ PEER_ +------------+ | | EVT | A RESET_EVT | | | | | | | | | | | | | +--------------+ | | | RESET_EVT| |RESET_EVT |ESTABLISH_EVT | | | | | | | | | | | | V V | | | +-------------+ +--------------+ RESET_EVT| +--->| RESET |--------->| ESTABLISHING |<----------------+ +-------------+ PEER_ +--------------+ | A RESET_EVT | | | | | | | |FAILOVER_ |FAILOVER_ |FAILOVER_ |BEGIN_EVT |END_EVT |BEGIN_EVT | | | V | | +-------------+ | | FAILINGOVER |<----------------+ +-------------+ These changes are fully backwards compatible. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
The implementation of the link FSM currently takes decisions about and sends out link protocol messages. This is unnecessary, since such actions are not the result of any link state change, and are even decided based on non-FSM state information ("silent_intv_cnt"). We now move the sending of unicast link protocol messages to the function tipc_link_timeout(), and the initial broadcast synchronization message to tipc_node_link_up(). The latter is done because a link instance should not need to know whether it is the first or second link to a destination. Such information is now restricted to and handled by the link aggregation layer in node.c Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
Link failover and synchronization have until now been handled by the links themselves, forcing them to have knowledge about and to access parallel links in order to make the two algorithms work correctly. In this commit, we move the control part of this functionality to the link aggregation level in node.c, which is the right location for this. As a result, the two algorithms become easier to follow, and the link implementation becomes simpler. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
In the next commit, we will move link synch/failover orchestration to the link aggregation level. In order to do this, we first need to extend the node FSM with two more states, NODE_SYNCHING and NODE_FAILINGOVER, plus four new events to enter and leave those states. This commit introduces this change, without yet making use of it. The node FSM now looks as follows: +-----------------------------------------+ | PEER_DOWN_EVT| | | +------------------------+----------------+ | |SELF_DOWN_EVT | | | | | | | | +-----------+ +-----------+ | | |NODE_ | |NODE_ | | | +----------|FAILINGOVER|<---------|SYNCHING |------------+ | | |SELF_ +-----------+ FAILOVER_+-----------+ PEER_ | | | |DOWN_EVT | A BEGIN_EVT A | DOWN_EVT| | | | | | | | | | | | | | | | | | | | |FAILOVER_|FAILOVER_ |SYNCH_ |SYNCH_ | | | | |END_EVT |BEGIN_EVT |BEGIN_EVT|END_EVT | | | | | | | | | | | | | | | | | | | | | +--------------+ | | | | | +------->| SELF_UP_ |<-------+ | | | | +----------------| PEER_UP |------------------+ | | | | |SELF_DOWN_EVT +--------------+ PEER_DOWN_EVT| | | | | | A A | | | | | | | | | | | | | | PEER_UP_EVT| |SELF_UP_EVT | | | | | | | | | | | V V V | | V V V +------------+ +-----------+ +-----------+ +------------+ |SELF_DOWN_ | |SELF_UP_ | |PEER_UP_ | |PEER_DOWN | |PEER_LEAVING|<------|PEER_COMING| |SELF_COMING|------>|SELF_LEAVING| +------------+ SELF_ +-----------+ +-----------+ PEER_ +------------+ | DOWN_EVT A A DOWN_EVT | | | | | | | | | | SELF_UP_EVT| |PEER_UP_EVT | | | | | | | | | |PEER_DOWN_EVT +--------------+ SELF_DOWN_EVT| +------------------->| SELF_DOWN_ |<--------------------+ | PEER_DOWN | +--------------+ Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
In many cases the call order when a link is reset goes as follows: tipc_node_xx()->tipc_link_reset()->tipc_node_link_down() This is not the right order if we want the node to be in control, so in this commit we change the order to: tipc_node_xx()->tipc_node_link_down()->tipc_link_reset() The fact that tipc_link_reset() now is called from only one location with a well-defined state will also facilitate later simplifications of tipc_link_reset() and the link FSM. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
In line with our effort to let the node level have full control over its links, we want to move all link reset calls from link.c to node.c. Some of the calls can be moved by simply moving the calling function, when this is the right thing to do. For the remaining calls we use the now established technique of returning a TIPC_LINK_DOWN_EVT flag from tipc_link_rcv(), whereafter we perform the reset call when the call returns. This change serves as a preparation for the coming commits. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Jon Paul Maloy authored
The function tipc_link_activate() is redundant, since it mostly performs settings that have already been done in a preceding tipc_link_reset(). There are three exceptions to this: - The actual state change to TIPC_LINK_WORKING. This should anyway be done in the FSM, and not in a separate function. - Registration of the link with the bearer. This should be done by the node, since we don't want the link to have any knowledge about its specific bearer. - Call to tipc_node_link_up() for user access registration. With the new role distribution between link aggregation and link level this becomes the wrong call order; tipc_node_link_up() should instead be called directly as a result of a TIPC_LINK_UP event, hence by the node itself. This commit implements those changes. Tested-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 30 Jul, 2015 1 commit
-
-
David S. Miller authored
Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next Johan Hedberg says: ==================== pull request: bluetooth-next 2015-07-30 Here's a set of Bluetooth & 802.15.4 patches intended for the 4.3 kernel. - Cleanups & fixes to mac802154 - Refactoring of Intel Bluetooth HCI driver - Various coding style fixes to Bluetooth HCI drivers - Support for Intel Lightning Peak Bluetooth devices - Generic class code in interface descriptor in btusb to match more HW - Refactoring of Bluetooth HS code together with a new config option - Support for BCM4330B1 Broadcom UART controller Let me know if there are any issues pulling. Thanks. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-