- 05 Jul, 2016 40 commits
-
-
David S. Miller authored
Jiri Pirko says: ==================== mlxsw: Implement IPV4 unicast routing This patchset enables IPv4 unicast routing in the Mellanox Spectrum ASIC switch driver. This builds upon the work that was done by a couple of previous patchsets. Patches 1,2,6 add a couple of dependencies outside the driver. Namely, the ability to propagate ndo_neigh_construct()/destroy() through stacked devices and a notification whenever DELAY_PROBE_TIME changes. When propagated down, the ndos allow drivers to add and remove neighbour entries from their private neighbour table. The DELAY_PROBE_TIME notification gives drivers the ability to correctly configure their polling interval for neighbour activity, so that active neighbour won't be marked as STALE. Patches 3-5,7-8 add the neighbour offloading infrastructure, where patch 7 uses the DELAY_PROBE_TIME notification in order to correctly configure the device's polling interval. Patch 8 finally programs neighbours to the device's table based on NEIGH_UPDATE notifications, so that directly connected routes can be used. Patches 9-16 build upon the previous patches and extend the router with remote routes (nexthop) support. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Yotam Gigi authored
Now, the driver sends arp probes for all unresolved neighbours that are currently a nexthop for some route on the system. The job is set periodically every 5 seconds. Signed-off-by:
Yotam Gigi <yotamg@mellanox.com> Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
-
Yotam Gigi authored
For nexthop neighbours we need to make kernel to think there is a traffic flowing to them preventing it from going to stale state. Otherwise kernel would stale it and eventually the neigh would be removed from HW and nexthop as well. That would reduce ECMP group in HW. Signed-off-by:
-
Jiri Pirko authored
Implement next-hop routing offload including ECMP. To make it possible, introduce next-hop group entity. This entity keeps track of resolved neighbours and updates HW adjacency table accordingly. Note that HW next-hops are stored in this adjacency table, in form of MAC. Signed-off-by:
-
Jiri Pirko authored
The RALEU register is used to mass update remote action adjacency index and ecmp size. Signed-off-by:
-
Yotam Gigi authored
The RATR register is used to configure the Router Adjacency (next-hop) Table. Signed-off-by:
-
Jiri Pirko authored
This is a very simple manager for KVD linear area. Currently, the allocator will either allocate a single entry from pre-defined sub-area, or in case more than one entry is needed, it will allocate 32-entry chunk in other pre-defined sub-area. Signed-off-by:
-
Jiri Pirko authored
Override the defaults and define the area sizes ourselves. Signed-off-by:
-
Jiri Pirko authored
Up until now we only used hash-based tables in the device, but we are going to use the linear table for remote routes adjacency lists. Add the configuration fields that control the size of the linear table. Signed-off-by:
-
Yotam Gigi authored
Listen to any NEIGH_UPDATE events sent and program the device accordingly. If NUD state is VALID and neighbour isn't yet offloaded, then program it into the device's table. Otherwise, just edit its parameters. If NUD state machine transitioned neighbour out of VALID state and it's present in the device's table, then remove it. Note that the device is programmed in delayed work, as the netevent notification chain is atomic and prevents us from going to sleep. Signed-off-by:
-
Yotam Gigi authored
As previously explained, the driver should periodically poll the device for neighbours activity according to the configured DELAY_PROBE_TIME. This will prevent active neighbours from staying in STALE state for long periods of time. During init configure the polling interval according to the DELAY_PROBE_TIME used in the default table. In addition, register a netevent notification block, so that the interval is updated whenever DELAY_PROBE_TIME changes. Using the computed interval schedule a delayed work, which will update the kernel via neigh_event_send() on any active neighbour since the last delayed work. Signed-off-by:
-
Ido Schimmel authored
When the data plane is offloaded the traffic doesn't go through the networking stack. Therefore, after first resolving a neighbour the NUD state machine will transition it from REACHABLE to STALE until it's finally deleted by the garbage collector. To prevent such situations the offloading driver should notify the NUD state machine on any neighbours that were recently used. The driver's polling interval should be set so that the NUD state machine can function as if the traffic wasn't offloaded. Currently, there are no in-tree drivers that can report confirmation for a neighbour, but only 'used' indication. Therefore, the polling interval should be set according to DELAY_FIRST_PROBE_TIME, as a neighbour will transition from REACHABLE state to DELAY (instead of STALE) if "a packet was sent within the last DELAY_FIRST_PROBE_TIME seconds" (RFC 4861). Send a netevent whenever the DELAY_FIRST_PROBE_TIME changes - either via netlink or sysctl - so that offloading drivers can correctly set their polling interval. Signed-off-by:
-
Yotam Gigi authored
The RAUHTD register allows dumping entries from the Router Unicast Host Table. Signed-off-by:
-
Yotam Gigi authored
The RAUHT register is used to configure and query the Unicast Host Table in devices that implement the Algorithmic LPM. In other words, it is used to configure neighbour entries in the device. Signed-off-by:
-
Jiri Pirko authored
We need to hold some private data for every neigh entry. It would be possible to do it using neigh_priv_len/ndo_neigh_construct/ ndo_neigh_destroy however only for the port device itself. That would not work for stacked devices like bridge/team/bond. So introduce a private neigh table. Hook onto ndos neigh_construct/destroy and add/remove table entry according to that. Signed-off-by:
-
Jiri Pirko authored
L2 upper device needs to propagate neigh_construct/destroy calls down to lower devices. Do this by defining default ndo functions and use them in team, bond, bridge and vlan. Signed-off-by:
-
Jiri Pirko authored
As the following patch will allow upper devices to follow the call down lower devices, we need to add dev here and not rely on n->dev. Signed-off-by:
-
David S. Miller authored
Florian Fainelli says: ==================== net: r6040: Misc updates Here are some various updates for the r6040 driver, mostly to make it more modern and catch up with the latest API improvements. ==================== Signed-off-by: -
Florian Fainelli authored
Bump version to 0.28 and date to 4th of July 2016. Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Florian Fainelli authored
Update my email address in the driver and MAINTAINERS file. Signed-off-by:
-
Florian Fainelli authored
We maintain how much work we did in NAPI context, so provide that with napi_complete_done(). Signed-off-by:
-
Florian Fainelli authored
We are already in hard IRQ context, so we can use __napi_schedule_irqoff() to save a few operations. Signed-off-by:
-
Florian Fainelli authored
Kick the transmission only if this is the last SKB to transmit or the queue is not already stopped. Signed-off-by:
-
Florian Fainelli authored
Instead of taking one interrupt per packet transmitted, re-use the same NAPI context to free transmitted buffers. Since we are no longer in hard IRQ context replace dev_kfree_skb_irq() by dev_kfree_skb(). Signed-off-by:
-
Florian Fainelli authored
Pad the SKB to the minimum length of ETH_ZLEN by using skb_put_padto() and take this operation out of the critical section since there is no need to check any HW resources before doing that. Signed-off-by:
-
Florian Fainelli authored
r6040_xmit() is increasing transmit statistics during transmission while this may still fail, do this in r6040_tx() where we complete transmitted buffers instead. Signed-off-by:
-
Florian Fainelli authored
Instead of open coding our own version utilize the library provided function. Signed-off-by:
-
Wei Yongjun authored
Remove including <linux/version.h> that don't need it. Signed-off-by:
Wei Yongjun <weiyj.lk@gmail.com> Signed-off-by:
-
David S. Miller authored
Saeed Mahameed says: ==================== Mellanox 100G mlx5 ethtool ntuple steering This series adds Ethernet ethtool ntuple steering 'ethtool -N|U' and exposes two more counter sets to Ethtool statistics, RDMA vport and global flow control statistics. We start from three refactoring patches of the flow steering infrastructure - mlx5_add_flow_rule will now receive mlx5 flow spec to simplify and reduce number of parameters - All low level steering objects are now wrapped in mlx5_flow_steering structure for better encapsulation - Flow steering object will now be removed properly and generically rather than traversing on a well-known steering tree objects Patch#4 adds the infrastructure and the data structures needed for the ethtool ntuple steering, all implemented in a new file 'en_fs_ethtool.c'. Add the support for set_rxnfc ethtool callback to add/remove/replace a flow spec of ethter type L2. Patch#5 adds the support for L3/L4 flow specs and a higher priority in favor for L3/L4 rules when interleaving with L2 rules. Patch#6 adds the support for get_rxnfc ethtool callback. Patch#7,8 adds RDMA vport and global flow control statistics. Applied on top: 8186f6e3 ('net-next: mediatek: fix compile error inside mtk_poll_controller()') ==================== Signed-off-by: -
Gal Pressman authored
Just like per prio counters, the global flow counters are queried from per priority counters register. Global flow control counters are stored in priority 0 PFC counters. Signed-off-by:
Gal Pressman <galp@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
-
Gal Pressman authored
Add the needed descriptors to expose RoCE RDMA counters. Signed-off-by:
-
Maor Gottlieb authored
Enhance the existing get_rxnfc callback: 1. Get flow rule of specific ID. 2. Get all flow rules. 3. Get number of rules. Signed-off-by:
Maor Gottlieb <maorg@mellanox.com> Signed-off-by:
-
Maor Gottlieb authored
Add support to add flow steering rules with ethtool of L3/L4 flow types (ip4/tcp4/udp4). Those rules will be in higher priority than l2 flow rules, in order to prefer more specific rules. Mask is not supported for l3/l4 flow types. Signed-off-by:
-
Maor Gottlieb authored
Implement etrhtool set_rxnfc callback to support ethtool flow spec direct steering. This patch adds only the support of ether flow type spec. L3/L4 flow specs support will be added in downstream patches. Signed-off-by:
-
Maor Gottlieb authored
Instead of explicitly cleaning up the well known parts of the steering tree, we use the generic tree structure to traverse for cleanup. No functional changes. Signed-off-by:
-
Maor Gottlieb authored
Instead of having all steering private name spaces and steering module fields flat in mlx5_core_priv, we wrap them in mlx5_flow_steering for better modularity and API exposure. Signed-off-by:
-
Maor Gottlieb authored
Reduce the set of arguments passed to mlx5_add_flow_rule by introducing flow_spec structure. Signed-off-by:
-
John Crispin authored
Commit 80673029 ("net-next: mediatek: add support for IRQ grouping") adds handling for irq 1 and 2 to the uninit function but did not remove irq 0 which is not used since irq grouping was introduced. Fix this by removing the superfluous call to free_irq(). Reported-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
John Crispin <john@phrozen.org> Acked-by:
-
Fabio Estevam authored
Since commit f786f356 ("net: ethernet: lpc_eth: use phydev from struct net_device") the 'pldat' variable became unused, so just remove it. Reported-by:
Olof's autobuilder <build@lixom.net> Signed-off-by:
Fabio Estevam <festevam@gmail.com> Signed-off-by:
-
git://git.open-mesh.org/linux-mergeDavid S. Miller authored
Simon Wunderlich says: ==================== This feature patchset includes the following changes: - Cleanup work by Markus Pargmann and Sven Eckelmann (six patches) - Initial Netlink support by Matthias Schiffer (two patches) - Throughput Meter implementation by Antonio Quartulli, a kernel-space traffic generator to estimate link speeds. This feature is useful on low-end WiFi APs where running iperf or netperf from userspace gives wrong results due to heavy userspace/kernelspace overhead. (two patches) - API clean-up work by Antonio Quartulli (one patch) ==================== Signed-off-by:
-
