Add support for the BPF_PROG_TYPE_XDP hook in mlx4 driver.

In tc/socket bpf programs, helpers linearize skb fragments as needed
when the program touches the packet data. However, in the pursuit of
speed, XDP programs will not be allowed to use these slower functions,
especially if it involves allocating an skb.

Therefore, disallow MTU settings that would produce a multi-fragment
packet that XDP programs would fail to access. Future enhancements could
be done to increase the allowable MTU.

The xdp program is present as a per-ring data structure, but as of yet
it is not possible to set at that granularity through any ndo.
Signed-off-by: NBrenden Blanco <bblanco@plumgrid.com>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

'vr' should be a valid pointer here, so returning 'PTR_ERR(vr)' is wrong.
Return an explicit error code (-ENOENT) instead.

Fixes: 61c503f9 ("mlxsw: spectrum_router: Implement fib4 add/del switchdev obj ops")
Signed-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The VF representors support only TC filter/action offloads
(not mqprio) and this is enabled for them by default.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Enhance the TC offload code such that when the eswitch exists and it's
mode being SRIOV offloads, we do TC actions parsing and setup targeted
for eswitch. Next, we add the offloaded flow to the HW e-switch (fdb).
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the setup code that parses the TC actions needed to support offloading drop
and mirred/redirect for SRIOV e-switch. We can redirect between two devices if
they belong to the same HW switch, compare the switchdev HW ID attribute to
enforce that.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Towards reusing the TC offloads code for an SRIOV use-case, change some of the
helper functions to have _nic in their names so it's clear what's NIC unique
and what's general. Also group together the NIC related helpers so we can easily
branch per the use-case in downstream patch.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This allows for upper levels in the driver, e.g the TC offload code to add
e-switch offloaded steering rules. The caller provides the rule spec for
matching, action, source and destination vports.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the offloads mode, some slow path rules are added by the driver (e.g
send-to-vport), while offloaded rules are to be added from upper layers.

The slow path rules have lower priority and we don't want matching on
offloaded rules to suffer from extra steering hops related to the slow
path rules.

We use two priorities, one for offloaded rules (fast path), and one for
the control rules (slow path). To allow for that, we enable two priorities
for the FDB namespace in the FS core code.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currenly, the code that programs the flow actions into the firmware
doesn't check if was actually asked to offload the statistics, fix that.

Fixes: aad7e08d ('net/mlx5e: Hardware offloaded flower filter statistics support')
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit utilize the ability of ConnectX-4 to bulk read flow counters.
Few bulk counter queries could be done instead of issuing thousands of
firmware commands per second to get statistics of all flows set to HW,
such as those programmed when we offload tc filters.

Counters are stored sorted by hardware id, and queried in blocks (id +
number of counters).

Due to hardware requirement, start of block and number of counters in a
block must be four aligned.
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NAmir Vadai <amir@vadai.me>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to use bulk counters, we need to have counters sorted by id.
Signed-off-by: NAmir Vadai <amir@vadai.me>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Trace EMAD messages going down to HW and up from HW. Devlink needs to be
registered before EMAD init so the trace function can be called
with valid devlink handle.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
v1->v2:
- Use trace_devlink_hwmsg directly
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

GCC complains on unused-but-set-variable, clean this up.

Fixes: 23898c76 ('net/mlx5: E-Switch, Modify node guid on vf set MAC')
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Acked-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The RALEU register is used to mass update remote action adjacency index
and ecmp size.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The RATR register is used to configure the Router Adjacency (next-hop)
Table.
Signed-off-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Override the defaults and define the area sizes ourselves.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The RAUHTD register allows dumping entries from the Router Unicast Host
Table.
Signed-off-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the needed descriptors to expose RoCE RDMA counters.
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reduce the set of arguments passed to mlx5_add_flow_rule
by introducing flow_spec structure.
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As with the previously introduced L3 interfaces, listen to 'inetaddr'
notifications sent for bridges devices configured on top of the port
netdevs and create / destroy router interfaces (RIFs) accordingly.
This also includes VLAN devices configured on top of the VLAN-aware
bridge.

The RIFs will be destroyed either when the last IP address is removed or
when the underlying FID is is destroyed.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Before introducing support for L3 interfaces on top of the VLAN-aware
bridge we need to add some missing infrastructure.

Such an interface can either be the bridge device itself or a VLAN
device on top of it. In the first case the router interface (RIF) is
associated with FID 1, which is created whenever the first port netdev
joins the bridge. We currently assume the default PVID is 1 and that
it's already created, as it seems reasonable. This can be extended in
the future.

However, in the second case it's entirely possible we've yet to create a
matching FID. This can happen if the VLAN device was configured before
making any bridge port member in the VLAN.

Prevent such ordering problems by using the VLAN device's CHANGEUPPER
event to configure the FID. Make the VLAN device hold a reference to the
FID and prevent it from being destroyed even if none of the port netdevs
is using it.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Previous commit deprecated the vFIDs used to get traffic to the CPU
('port_vfids'). Thus, we now use the vFIDs as god intended and the
artificial split is no longer needed.

Rename functions and variables to reflect that.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Up until now we only supported bridged interfaces. Packets ingressing
through the switch ports were either classified to FIDs (in the case of
the VLAN-aware bridge) or vFIDs (in the case of VLAN-unaware bridges).
The packets were then forwarded according to the FDB. Routing was done
entirely in slowpath, by splitting the vFID range in two and using the
lower 0.5K vFIDs as dummy bridges that simply flooded all incoming
traffic to the CPU.

Instead, allow packets to be routed in the device by creating router
interfaces (RIFs) that will direct them to the router block.
Specifically, the RIFs introduced here are Sub-port RIFs used for VLAN
devices and port netdevs. Packets ingressing from the {Port / LAG ID, VID}
with which the RIF was programmed with will be assigned to a special
kind of FIDs called rFIDs and from there directed to the router.

Create a RIF whenever the first IPv4 address was programmed on a VLAN /
LAG / port netdev. Destroy it upon removal of the last IPv4 address.
Receive these notifications by registering for the 'inetaddr'
notification chain. A non-zero (10) priority is used for the
notification block, so that RIFs will be created before routes are
offloaded via FIB code.

Note that another trigger for RIF destruction are CHANGEUPPER
notifications causing the underlying FID's reference count to go down to
zero. This can happen, for example, when a VLAN netdev with an IP address
is put under bridge. While this configuration doesn't make sense it does
cause the device and the kernel to get out of sync when the netdev is
unbridged. We intend to address this in the future, hopefully in current
cycle.

Finally, Remove the lower 0.5K vFIDs, as they are deprecated by the RIFs,
which will trap packets according to their DIP.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We are just about to introduce router interfaces (RIFs), but before that
we need to be able update the device with the correct RIF attributes
whenever they change for the netdev the RIF is backing. Two such
attributes are MTU and MAC.

The MAC is used both to set the source MAC of packets egressing from the
RIF and also to program an FDB rule that will direct packets to the
router block.

Use the existing netdevice notification block and respond to CHANGEADDR
and CHANGEMTU accordingly. Store both attributes in the RIF struct
in case we need to revert to old attributes following a failed update.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add functions that iterate over lower devices and find port device.
As a dependency add netdev_for_each_all_lower_dev and
netdev_for_each_all_lower_dev_rcu macro with
netdev_all_lower_get_next and netdev_all_lower_get_next_rcu shelpers.

Also, add functions to return mlxsw struct according to lower device
found and mlxsw_port struct with a reference to lower device.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>