In previous patch mlxsw_afa_resource_del() was added to avoid a duplicate
resource detruction scenario.
For mirror actions, such duplicate destruction leads to a crash as in:
# tc qdisc add dev swp49 ingress
# tc filter add dev swp49 parent ffff: \
protocol ip chain 100 pref 10 \
flower skip_sw dst_ip 192.168.101.1 action drop
# tc filter add dev swp49 parent ffff: \
protocol ip pref 10 \
flower skip_sw dst_ip 192.168.101.1 action goto chain 100 \
action mirred egress mirror dev swp4
Therefore add a call to mlxsw_afa_resource_del() in
mlxsw_afa_mirror_destroy() in order to clear that resource
from rule's resources.
Fixes: d0d13c1858 ("mlxsw: spectrum_acl: Add support for mirror action")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each tc flower rule uses a hidden count action. As counter resource may
not be available due to limited HW resources, update _counter_create()
and _counter_destroy() pair to follow previously introduced symmetric
error condition handling, add a call to mlxsw_afa_resource_del() as part
of the counter resource destruction.
Fixes: c18c1e186b ("mlxsw: core: Make counter index allocated inside the action append")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some ACL actions require the allocation of a separate resource
prior to applying the action itself. When facing an error condition
during the setup phase of the action, resource should be destroyed.
For such actions the destruction was done twice which is dangerous
and lead to a potential crash.
The destruction took place first upon error on action setup phase
and then as the rule was destroyed.
The following sequence generated a crash:
# tc qdisc add dev swp49 ingress
# tc filter add dev swp49 parent ffff: \
protocol ip chain 100 pref 10 \
flower skip_sw dst_ip 192.168.101.1 action drop
# tc filter add dev swp49 parent ffff: \
protocol ip pref 10 \
flower skip_sw dst_ip 192.168.101.1 action goto chain 100 \
action mirred egress mirror dev swp4
Therefore add mlxsw_afa_resource_del() as a complement of
mlxsw_afa_resource_add() to add symmetry to resource_list membership
handling. Call this from mlxsw_afa_fwd_entry_ref_destroy() to make the
_fwd_entry_ref_create() and _fwd_entry_ref_destroy() pair of calls a
NOP.
Fixes: 140ce42121 ("mlxsw: core: Convert fwd_entry_ref list to be generic per-block resource list")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Spectrum switch ACL action set is built in groups of three actions
which may point to additional actions. A group holds a single record
which can be set as goto record for pointing at a following group
or can be set to mark the termination of the lookup. This is perfectly
adequate for handling a series of actions to be executed on a packet.
While the SW model allows configuration of conflicting actions
where it is clear that some actions will never execute, the mlxsw
driver must block such configurations as it creates a conflict
over the single terminate/goto record value.
For a conflicting actions configuration such as:
# tc filter add dev swp49 parent ffff: \
protocol ip pref 10 \
flower skip_sw dst_ip 192.168.101.1 \
action goto chain 100 \
action mirred egress mirror dev swp4
Where it is clear that the last action will never execute, the
mlxsw driver was issuing a warning instead of returning an error.
Therefore replace that warning with an error for this specific
case.
Fixes: 4cda7d8d70 ("mlxsw: core: Introduce flexible actions support")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that the unregister_netdev flow for IPoIB no longer relies on external
code we can now introduce the use of priv_destructor and
needs_free_netdev.
The rdma_netdev flow is switched to use the netdev common priv_destructor
instead of the special free_rdma_netdev and the IPOIB ULP adjusted:
- priv_destructor needs to switch to point to the ULP's destructor
which will then call the rdma_ndev's in the right order
- We need to be careful around the error unwind of register_netdev
as it sometimes calls priv_destructor on failure
- ULPs need to use ndo_init/uninit to ensure proper ordering
of failures around register_netdev
Switching to priv_destructor is a necessary pre-requisite to using
the rtnl new_link mechanism.
The VNIC user for rdma_netdev should also be revised, but that is left for
another patch.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Denis Drozdov <denisd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
The BTF conflicts were simple overlapping changes.
The virtio_net conflict was an overlap of a fix of statistics counter,
happening alongisde a move over to a bonafide statistics structure
rather than counting value on the stack.
Signed-off-by: David S. Miller <davem@davemloft.net>
This sysctl setting controls whether packet priority should be updated
after forwarding. Configure RGCR.usp accordingly so that the device is
in sync with the kernel handling.
Note that RGCR doesn't allow changing arbitrary parameters
mid-operation, however "usp" is exempt and can be reconfigured.
Also react to NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE notifications
that signify change in this configuration.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The boilerplate to schedule NETEVENT_IPV4_MPATH_HASH_UPDATE and
NETEVENT_IPV6_MPATH_HASH_UPDATE handling is almost equivalent to that of
NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE that's coming in the next
patch. The only difference is which actual worker function should be
called. Extract this boilerplate into a named function in order to allow
reuse.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a potential execution path in which variable *err* is returned
without being properly initialized previously.
Fix this by initializing variable *err* to 0.
Addresses-Coverity-ID: 1472116 ("Uninitialized scalar variable")
Fixes: 0ec13877ce ("net/mlx5e: Gather all XDP pre-requisite checks in a single function")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After introduction of the cited commit, mlx5e_build_nic_params
receives the netdevice mtu in order to set the sw_mtu of mlx5e_params.
For enhanced IPoIB, the netdevice mtu is not set in this stage,
therefore, the initial sw_mtu equals zero. As a result, the hw_mtu
of the receive queue will be calculated incorrectly causing traffic
issues.
To fix this issue, query for port mtu before building the nic params.
Fixes: 472a1e44b3 ("net/mlx5e: Save MTU in channels params")
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
MTU helper function is used by both conventional mlx5e
instances (PF/VF) and the eswitch representors. The representor
shouldn't change the nic vport context MTU, the VF is responsible for
that. Therefore set_mtu_cb has a null value when changing the
representor MTU.
Fixes: 250a42b6a7 ("net/mlx5e: Support configurable MTU for vport representors")
Signed-off-by: Adi Nissim <adin@mellanox.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The hairpin offload code has dependency on the trust mode being PCP.
Hence we should set PCP as the default for handling cases where we are
disallowed to read the trust mode from the FW, or failed to initialize it.
Fixes: 106be53b6b ('net/mlx5e: Set per priority hairpin pairs')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Execute mlx5_eswitch_init() only if we have MLX5_ESWITCH_MANAGER
capabilities.
Do the same for mlx5_eswitch_cleanup().
Fixes: a9f7705ffd ("net/mlx5: Unify vport manager capability check")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Commit 58b99ee3e3 ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
forgot to return/free the xdp_frame in case the DMA mapping failed, correct this.
Also DMA unmap the frame in case mlx5e_xmit_xdp_frame() fails.
Fixes: 58b99ee3e3 ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This series from Gal and Saeed provides updates to mlx5 vxlan implementation.
Gal, started with three cleanups to reflect the actual hardware vxlan state
- reflect 4789 UDP port default addition to software database
- check maximum number of vxlan UDP ports
- cleanup an unused member in vxlan work
Then Gal provides performance optimization by replacing the
vxlan radix tree with a hash table.
Measuring mlx5e_vxlan_lookup_port execution time:
Radix Tree Hash Table
--------------- ------------ ------------
Single Stream 161 ns 79 ns (51% improvement)
Multi Stream 259 ns 136 ns (47% improvement)
Measuring UDP stream packet rate, single fully utilized TX core:
Radix Tree: 498,300 PPS
Hash Table: 555,468 PPS (11% improvement)
Next, from Saeed, vxlan refactoring to allow sharing the vxlan table
between different mlx5 netdevice instances like PF and VF representors,
this is done by making mlx5 vxlan interface more generic and decoupling
it from PF netdevice structures and logic, then moving it into mlx5 core
as a low level interface so it can be used by VF representors, which is
illustrated in the last patch of the serious.
-Saeed.
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJbW7KLAAoJEEg/ir3gV/o+YZ8H/2D4Ogav0zxQaNnw4ASYPpVA
luW1tvGUyk3C+fgbZO7tp/DETGJKbSodSMV9ZasEFFuHPft37mQaEIZf2rq58DvT
Q6vaaewyRCB6SzIGYjCZWtLI0aE5QtwMWDRbRBlRyQ0zUV6wr26W3WWWM2SpCJGK
zSuAF3Np0dEPTzBB566CY0nhYpsBiBXm2QJcgySL2WIx1nwQ6X8MJxjErhgQV+2L
1wVT6YTm1K2cdx9LsORt3FB/mFTQcOJCpl88AyhBB+pc7+i6pBtBp95tcqD8wmtF
dnMBmR+JzT108VxvcBnpwCxuVI7lLCcAs9hYITTGzUbo6rqT8xXV2HQ1KwU17Ow=
=tJj8
-----END PGP SIGNATURE-----
Merge tag 'mlx5e-updates-2018-07-27' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5e-updates-2018-07-27 (Vxlan updates)
This series from Gal and Saeed provides updates to mlx5 vxlan implementation.
Gal, started with three cleanups to reflect the actual hardware vxlan state
- reflect 4789 UDP port default addition to software database
- check maximum number of vxlan UDP ports
- cleanup an unused member in vxlan work
Then Gal provides performance optimization by replacing the
vxlan radix tree with a hash table.
Measuring mlx5e_vxlan_lookup_port execution time:
Radix Tree Hash Table
--------------- ------------ ------------
Single Stream 161 ns 79 ns (51% improvement)
Multi Stream 259 ns 136 ns (47% improvement)
Measuring UDP stream packet rate, single fully utilized TX core:
Radix Tree: 498,300 PPS
Hash Table: 555,468 PPS (11% improvement)
Next, from Saeed, vxlan refactoring to allow sharing the vxlan table
between different mlx5 netdevice instances like PF and VF representors,
this is done by making mlx5 vxlan interface more generic and decoupling
it from PF netdevice structures and logic, then moving it into mlx5 core
as a low level interface so it can be used by VF representors, which is
illustrated in the last patch of the serious.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Move vxlan logic and objects to mlx5 core dirver.
Since it going to be used from different mlx5 interfaces.
e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Vxlan API can and will be called from different mlx5 modules, we should
not count on mlx5e private state lock only, hence we introduce a vxlan
private mutex to sync between add/del vxlan port operations.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
For a better API mlx5_vxlan_{add/del}_port can fail, make them return
error values.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Rename vxlan functions from mlx5e_vxlan_* to mlx5_vxlan_*.
Rename mlx5e_vxlan_db to mlx5_vxlan and move it from en.h to vxlan.c
since it is not related to mlx5e anymore.
Allocate mlx5_vxlan structure dynamically in order to make it easier to
move later to core driver and to make it private in vxlan.c.
This is in preparation to move vxlan API to mlx5 core.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
The name mlx5e_vxlan will be used in downstream patch to describe
mlx5 vxlan structure that will replace mlx5e_vxlan_db.
Hence we rename struct mlx5e_vxlan to mlx5_vxlan_port which describes a
mlx5 vxlan port.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Create a direct vxlan API to add and delete vxlan ports from HW.
+void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);
And move vxlan_add/del_work to en_main.c since they are netdev only
logic.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Add direct vxlan delete function to be called from vxlan_delete_work.
Needed in downstream patch.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Cleanup the sa_family member of the vxlan work, it is unused/needed
anywhere in the code.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The VXLAN database is accessed in the data path for each VXLAN TX skb in
order to check whether the UDP port is being offloaded or not.
The number of elements in the database is relatively small, we can
simplify the radix-tree to a hash table and speedup the lookup process.
Measuring mlx5e_vxlan_lookup_port execution time:
Radix Tree Hash Table
--------------- ------------ ------------
Single Stream 161 ns 79 ns (51% improvement)
Multi Stream 259 ns 136 ns (47% improvement)
Measuring UDP stream packet rate, single fully utilized TX core:
Radix Tree: 498,300 PPS
Hash Table: 555,468 PPS (11% improvement)
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The NIC has a limited number of offloaded VXLAN UDP ports (usually 4).
Instead of letting the firmware fail when trying to add more ports than
it can handle, let the driver check it on its own.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The hardware offloads 4789 UDP port (default VXLAN port) automatically.
Add it to the software database as well in order to reflect the hardware
state appropriately.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The APP TLVs are used for communicating priority-to-protocol ID maps for
a given netdevice. Support the following APP TLVs:
- DSCP (selector 5) to configure priority-to-DSCP code point maps. Use
these maps to configure packet priority on ingress, and DSCP code
point rewrite on egress.
- Default priority (selector 1, PID 0) to configure priority for the
DSCP code points that don't have one assigned by the DSCP selector. In
future this could also be used for assigning default port priority
when a packet arrives without DSCP tagging.
Besides setting up the maps themselves, also configure port trust level
and rewrite bits.
Port trust level determines whether, for a packet arriving through a
certain port, the priority should be determined based on PCP or DSCP
header fields. So far, mlxsw kept the device default of trust-PCP. Now,
as soon as the first DSCP APP TLV is configured, switch to trust-DSCP.
Only when all DSCP APP TLVs are removed, switch back to trust-PCP again.
Note that the default priority APP TLV doesn't impact the trust level
configuration.
Rewrite bits determine whether DSCP and PCP fields of egressing packets
should be updated according to switch priority. When port trust is
switched to DSCP, enable rewrite of DSCP field.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This register controls mapping from Priority to DSCP for purposes of
rewrite. Note that rewrite happens as the packet is transmitted provided
that the DSCP rewrite bit is enabled for the packet.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This register configures the rewrite enable (whether PCP or DSCP value
in packet should be updated according to packet priority) per receive
port.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The QPTS register controls the port policy to calculate the switch
priority and packet color based on incoming packet fields.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The QPDPM register controls the mapping from DSCP field to Switch
Priority for IP packets.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use designated function mlx5e_dma_get() to get
the mlx5e_sq_dma object to be pushed into fifo.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Pointers in DB are static, move them to read-only area so they
do not share a cacheline with fields modified in datapath.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
A loaded XDP program might write to the xdp_frame data area,
prefetchw() it to avoid a potential cache miss.
Performance tests:
ConnectX-5, XDP_TX packet rate, single ring.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Before: 13,172,976 pps
After: 13,456,248 pps
2% gain.
Fixes: 22f4539881 ("net/mlx5e: Support XDP over Striding RQ")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add implementation for the ndo_xdp_xmit callback.
Dedicate a new set of XDP-SQ instances to satisfy the XDP_REDIRECT
requests. These instances are totally separated from the existing
XDP-SQ objects that satisfy local XDP_TX actions.
Performance tests:
xdp_redirect_map from ConnectX-5 to ConnectX-5.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Packet-rate of 64B packets.
Single queue: 7 Mpps.
Multi queue: 55 Mpps.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
In the downstream patch that adds support to XDP_REDIRECT-out,
the XDP xmit frame function doesn't share the same run context as
the NAPI that polls the XDP-SQ completion queue.
Hence, need to re-order the XDP-SQ fields to avoid cacheline
false-sharing.
Take redirect_flush and doorbell out of DB, into separated
cachelines.
Add a cacheline breaker within the stats struct.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Separate the XDP counters into two sets:
(1) One set reside in the RQ stats, and they monitor XDP stats
in the RQ side.
(2) Another set is per XDP-SQ, and they monitor XDP stats that
are related to XDP transmit flow.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Convert the XDP xmit functions to use the generic xdp_frame API
in XDP_TX flow.
Same functions will be used later in this series to transmit
the XDP redirect-out packets as well.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add per-ring and total stats for received packets that
goes into XDP redirection.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Take XDP code out of the general EN header and RX file into
new XDP files.
Currently, XDP-SQ resides only within an RQ and used from a
single flow (XDP_TX) triggered upon RX completions.
In a downstream patch, additional type of XDP-SQ instances will be
presented and used for the XDP_REDIRECT flow, totally unrelated to
the RX context.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add checks in control path upon an MTU change or an XDP program set,
to prevent reaching cases where large MTU and XDP are set simultaneously.
This is to make sure we allow XDP only with the linear RX memory scheme,
i.e. a received packet is not scattered to different pages.
Change mlx5e_rx_get_linear_frag_sz() accordingly, so that we make sure
the XDP configuration can really be set, instead of assuming that it is.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Dedicate a function to all checks done when setting an XDP program.
Take indications from priv instead of netdev features.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
No need to expose the MPWQE free function to control path.
The dealloc function already exposed, use it.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Now that all the pieces are in place we can start using the A-TCAM
instead of only using the C-TCAM. This allows for much higher scale and
better performance (to be improved further by follow-up patch sets).
Perform the integration with the A-TCAM and the eRP core by reverting
the changes introduced by "mlxsw: spectrum_acl: Enable C-TCAM only mode
in eRP core" and add calls from the C-TCAM code into the eRP core.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement rule insertion and deletion into the A-TCAM before we flip the
driver to start using the A-TCAM.
Rule insertion into the A-TCAM is very similar to C-TCAM, but there are
subtle differences between regions of different sizes (i.e., different
number of key blocks).
Specifically, as explained in "mlxsw: spectrum_acl: Allow encoding a
partial key", in 12 key blocks regions a rule is split into two and the
two halves of the rule are linked using a "large entry key ID".
Such differences are abstracted away by using different region
operations per region type.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When A-TCAM will be used together with C-TCAM, the C-TCAM code will need
to call into the eRP core in order to get an eRP for an inserted entry.
The eRP core takes an A-TCAM region as one of its arguments, so pass the
C-TCAM region to the insertion function which will later allow us to
derive the A-TCAM region, given it contains the C-TCAM one.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before we start using the A-TCAM we need to make sure the region is
properly initialized.
This includes the setting of its type (which affects the size of its eRP
table, for example) and its registration with the eRP core.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each TCAM region currently uses its own resources and there is no
sharing between the different regions.
This is going to change with A-TCAM as each region will need to allocate
an eRP table from the global eRP tables array.
Make the global TCAM resources available to each region by passing the
TCAM private data to the region initialization routine.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2 the C-TCAM is only used for rules that can't fit in the
A-TCAM due to a limited number of masks per A-TCAM region.
In addition, rules inserted into the C-TCAM may affect rules residing in
the A-TCAM, by clearing their C-TCAM prune bit.
The two regions are thus closely related and can be thought of as if the
C-TCAM region is encapsulated in the A-TCAM one.
Change the data structures to reflect that before introducing A-TCAM
support and make C-TCAM region initialization part of the A-TCAM region
initialization sequence.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Initialize the A-TCAM as part of the driver's initialization routine.
Specifically, initialize the eRP tables so that A-TCAM regions will be
able to perform allocations of eRP tables upon rule insertion in
subsequent patches.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When working with 12 key blocks in the A-TCAM, rules are split into two
records, which constitute two lookups. The two records are linked using
a "large entry key ID". The ID is assigned to key blocks 6 to 11 and
resolved during the first lookup. The second lookup is performed using
the ID and the remaining key blocks.
Allow encoding a partial key so that it can be later used to check if an
ID can be reused.
This is done by adding two arguments to the existing encode function
that specify the range of the block indexes we would like to encode. The
key and mask arguments become optional, as we will not need to encode
both of them all the time.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In a similar fashion to Spectrum-1's region struct, Spectrum-2's struct
needs to store a pointer to the common region struct.
The pointer will be used in follow-up patches that implement rules
insertion and deletion.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The number of eRPs that can be used by a single A-TCAM region is limited
to 16. When more eRPs are needed, an ordinary circuit TCAM (C-TCAM) can
be used to hold the extra eRPs.
Unlike the A-TCAM, only a single (last) lookup is performed in the
C-TCAM and not a lookup per-eRP. However, modeling the C-TCAM as extra
eRPs will allow us to easily introduce support for pruning in a
follow-up patch set and is also logically correct.
The following diagram depicts the relation between both TCAMs:
C-TCAM
+-------------------+ +--------------------+ +-----------+
| | | | | |
| eRP #1 (A-TCAM) +----> ... +----+ eRP #16 (A-TCAM) +----+ eRP #17 |
| | | | | ... |
+-------------------+ +--------------------+ | eRP #N |
| |
+-----------+
Lookup order is from left to right.
Extend the eRP core APIs with a C-TCAM parameter which indicates whether
the requested eRP is to be used with the C-TCAM or not.
Since the C-TCAM is only meant to absorb rules that can't fit in the
A-TCAM due to exceeded number of eRPs or key collision, an error is
returned when a C-TCAM eRP needs to be created when the eRP state
machine is in its initial state (i.e., 'no masks'). This should only
happen in the face of very unlikely errors when trying to push rules
into the A-TCAM.
In order not to perform unnecessary lookups, the eRP core will only
enable a C-TCAM lookup for a given region if it knows there are C-TCAM
eRPs present.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, no calls are performed into the eRP core, but in order to
make review easier we would like to gradually add these calls.
Have the eRP core initialize a region's master mask to all ones and
allow it to use an empty eRP table. This directs the lookup to the
C-TCAM and allows the C-TCAM only mode to continue working.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When rules are inserted into the A-TCAM they are associated with a mask,
which is part of the lookup key: { masked key, mask ID, region ID }.
These masks are called rule patterns (RP) and the aggregation of several
masks into one (to be introduced in follow-up patch sets) is called an
extended RP (eRP).
When a packet undergoes a lookup in an ACL region it is masked by the
current set of eRPs used by the region, looking for an exact match.
Eventually, the rule with the highest priority is picked.
These eRPs are stored in several global banks to allow for lookup to
occur using several eRPs simultaneously.
At first, an ACL region will only require a single mask - upon the
insertion of the first rule. In this case, the region can use the
"master RP" which is composed by OR-ing all the masks used by the
region. This mask is a property of the region and thus there is no need
to use the above mentioned banks.
At some point, a second mask will be needed. In this case, the region
will need to allocate an eRP table from the above mentioned banks and
insert its masks there.
>From now on, upon lookup, the eRP table used by the region will be
fetched from the eRP banks - using {eRP bank, Index within the bank} -
and the eRPs present in the table will be used to mask the packet. Note
that masks with consecutive indexes are inserted into consecutive banks.
When rules are deleted and a region only needs a single mask once again
it can free its eRP table and use the master RP.
The above logic is implemented in the eRP core and represented using the
following state machine:
+------------+ create mask - as master RP +---------------+
| +--------------------------------> |
| no masks | | single mask |
| <--------------------------------+ |
+------------+ delete mask +-----+--^------+
| |
| |
create mask - | | delete mask -
create mask transition to use eRP | | transition to
+--------+ table | | use master RP
| | | |
| | | |
+----v--------+----+ create mask +----v--+-----+
| <-------------------------------+ |
| multiple masks | | two masks |
| +-------------------------------> |
+------------------+ delete mask - if two +-------------+
remaining
The code that actually configures rules in the A-TCAM will interface
with the eRP core by getting or putting an eRP based on the required
mask used by the rule.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the following resources to be used by A-TCAM code:
* Maximum number of eRP banks
* Maximum size of eRP bank
* Number of eRP entries required for a 2/4/8/12 key blocks mask
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a resource to make sure we do not exceed the maximum number of
supported large key IDs in a region.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The register is used to add and delete eRPs from the eRP table.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The register is used to configure rules in the A-TCAM.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before introducing A-TCAM support we need to make sure all the necessary
fields are configurable and not hard coded to values that worked for the
C-TCAM only use case.
This includes - for example - the ability to configure the eRP table
used by the TCAM region.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow obtaining MTTs starting at any index,
thus give a better cache utilization.
For this, allow setting log_mtts_per_seg to 0, and use
this in default.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Anaty Rahamim Bar Kat <anaty@mellanox.com>
Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable offloading of TC matching on tos/ttl for ipv4/6 tunnels.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the values provided by user-space for the encapsulation headers.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currnetly, the ttl for the encapsulation headers is taken from the
route lookup result. As a pre-step to allow for an offload case when
the user specifies the ttl, take it from the route lookup only if
not zero. While here, also move to use u8 instead int for the ttl.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Function mlx4_RST2INIT_QP_wrapper saved the qp number passed in the qp
context, rather than the one passed in the input modifier.
However, the qp number in the qp context is not defined as a
required parameter by the FW. Therefore, drivers may choose to not
specify the qp number in the qp context for the reset-to-init transition.
Thus, we must save the qp number passed in the command input modifier --
which is always present. (This saved qp number is used as the input
modifier for command 2RST_QP when a slave's qp's are destroyed).
Fixes: c82e9aa0a8 ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux.git
This is required to resolve dependencies of the next series of RDMA
patches.
* branch 'mellanox/mlx5-next':
net/mlx5: Add support for flow table destination number
net/mlx5: Add forward compatible support for the FTE match data
net/mlx5: Fix tristate and description for MLX5 module
net/mlx5: Better return types for CQE API
net/mlx5: Use ERR_CAST() instead of coding it
net/mlx5: Add missing SET_DRIVER_VERSION command translation
net/mlx5: Add XRQ commands definitions
net/mlx5: Add core support for double vlan push/pop steering action
net/mlx5: Expose MPEGC (Management PCIe General Configuration) structures
net/mlx5: FW tracer, add hardware structures
net/mlx5: fix uaccess beyond "count" in debugfs read/write handlers
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Return extack messages in order to explain failures
of unsupported actions, keys and invalid user input.
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Return extack messages for failures in action set creation.
Messages provide reasons for not being able to implement
the action in HW.
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Return extack messages for failures in action set creation.
Errors may occur when action is not currently supported or due
to lack of resources.
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Propagate extack pointer in order to add extack messages for ACL.
In the follow-up patches, appropriate messages will be added
in various points.
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support to set a destination from a flow table number.
This functionality will be used in downstream patches from this
series by the DEVX stuff.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Use the PRM size including the reserved when working with the FTE
match data.
This comes to support forward compatibility for cases that current
reserved data will be exposed by the firmware by an application that
uses the DEVX API without changing the kernel.
Also drop some driver checks around the match criteria leaving the work
for firmware to enable forward compatibility for future bits there.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Since cld_flower provides information about the filter template for
specific chain, use this information in order to prepare a region.
Use the template to find out what elements are going to be used
and pass that down to mlxsw_sp_acl_tcam_group_add(). Later on, when the
first filter is inserted, the mlxsw_sp_acl_tcam_group_use_patterns()
function would use this element usage information instead of looking
up a pattern.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes the splitting of UDP_GSO_L4 packets in the driver,
and exposes UDP_GSO_L4 as a PARTIAL_GSO feature. Thus, the network stack
is not responsible for splitting the packet into two.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
As we can configure two push/pop actions in one flow table entry,
add support to offload those double vlan actions in a rule to HW.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Extract actions offloading code to a new function, and also extend data
structures for double vlan actions.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
We can match on both outer and inner vlan tags, add support for
offloading that.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
It is possible for neigh entry not to exist if it was cleaned already.
When we bring down an interface the neigh gets deleted but it could be
that our listener for neigh event to clear the encap valid bit didn't
start yet and the neigh update last used work is started first.
In this scenario the encap entry has valid bit set but the neigh entry
doesn't exist.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add the tracer file to the makefile and add the init
function to the load one flow.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
For each message the driver should do the following:
1- Find the message string in the strings database
2- Count the param number of each message
3- Wait for the param events and accumulate them
4- Calculate the event timestamp using the local event timestamp
and the first timestamp event following it.
5- Print message to trace log
Enable the tracing by:
echo 1 > /sys/kernel/debug/tracing/events/mlx5/mlx5_fw/enable
Read traces by:
cat /sys/kernel/debug/tracing/trace
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The tracer has one event, event 0x26, with two subtypes:
- Subtype 0: Ownership change
- Subtype 1: Traces available
An ownership change occurs in the following cases:
1- Owner releases his ownership, in this case, an event will be
sent to inform others to reattempt acquire ownership.
2- Ownership was taken by a higher priority tool, in this case
the owner should understand that it lost ownership, and go through
tear down flow.
The second subtype indicates that there are traces in the trace buffer,
in this case, the driver polls the tracer buffer for new traces, parse
them and prepares the messages for printing.
The HW starts tracing from the first address in the tracer buffer.
Driver receives an event notifying that new trace block exists.
HW posts a timestamp event at the last 8B of every 256B block.
Comparing the timestamp to the last handled timestamp would indicate
that this is a new trace block. Once the new timestamp is detected,
the entire block is considered valid.
Block validation and parsing, should be done after copying the current
block to a different location, in order to avoid block overwritten
during processing.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
For each PF do the following:
1- Allocate memory for the tracer strings database and read the
strings from the FW to the SW. These strings will be used later for
parsing traces.
2- Allocate and dma map tracer buffers.
Traces that will be written into the buffer will be parsed as a group
of one or more traces, referred to as trace message. The trace message
represents a C-like printf string.
First trace of a message holds the pointer to the correct string in
strings database. The following traces holds the variables of the
message.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Implement FW tracer logic and registers access, initialization and
cleanup flows.
Initializing the tracer will be part of load one flow, as multiple
PFs will try to acquire ownership but only one will succeed and will
be the tracer owner.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
mlx5 core infrastructure updates and fixes.
From Eran:
- Add MPEGC (Management PCIe General Configuration) registers and btis
- Fix tristate and description for MLX5 module
rom Feras:
- Add hardware structures for the firmware tracer
From Jainbo:
- Core support for double vlan push/pop steering action
From Max:
- Add XRQ commands definitions
From Noa:
- Add missing SET_DRIVER_VERSION command translation
From Roi:
- Use ERR_CAST() instead of coding it
From Tariq:
- Better return types for CQE API
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
We get egress rules through the egdev mechanism when the ingress device
is not supporting offload, with the expected use-case of tunnel decap
ingress rule set on shared tunnel device.
Make sure to offload egress/egdev rules only if decap action (tunnel key
unset) exists there and err otherwise.
Fixes: 717503b9cf ("net: sched: convert cls_flower->egress_dev users to tc_setup_cb_egdev infra")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Fix bad alignment of SQ buffer in fragmented QP allocation.
It should start directly after RQ buffer ends.
Take special care of the end case where the RQ buffer does not occupy
a whole page. RQ size is a power of two, so would be the case only for
small RQ sizes (RQ size < PAGE_SIZE).
Fix wrong assignments for sqb->size (mistakenly assigned RQ size),
and for npages value of RQ and SQ.
Fixes: 3a2f703312 ("net/mlx5: Use order-0 allocations for all WQ types")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The flow counters binding support commit introduced a code change where
none NULL 'rule_dest' is always passed to mlx5_add_flow_rules, this breaks
'DON'T_TRAP' rules insertion.
The fix uses the equivalent 'dest_num' value instead of dest pointer
at the failed check.
fixes: 3b3233fbf0 ('IB/mlx5: Add flow counters binding support')
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Driver is yet to support aRFS for encapsulated packets, return early
error in such case.
Fixes: 18c908e477 ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Quota should follow the amount of rules which do expire, and not the
number of rules that were examined, fixed that.
Fixes: 18c908e477 ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When driver converts HW timestamp to wall clock time it subtracts
the last saved cycle counter from the HW timestamp and converts the
difference to nanoseconds.
The conversion is done by multiplying the cycles difference with the
clock multiplier value as a first step and therefore the cycles
difference should be small enough so that the multiplication product
doesn't exceed 64bit.
The overflow handling routine is in charge of updating the last saved
cycle counter in driver and it is called periodically using kernel
delayed workqueue.
The delay period for this work is calculated using the max HW cycle
counter value (a 41 bit mask) as a base which doesn't take the 64bit
limit into account so the delay period may be incorrect and too
long to prevent a large difference between the HW counter and the last
saved counter in SW.
This change adjusts the work period for the HW clock overflow work by
taking the minimum between the previous value and the quotient of max
u64 value and the clock multiplier value.
Fixes: ef9814deaf ("net/mlx5e: Add HW timestamping (TS) support")
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Removed an error message received when configuring ETS total
bandwidth to be zero.
Our hardware doesn't support such configuration, so we shall
reject it in the driver. Nevertheless, we removed the error message
in order to eliminate error messages caused by old userspace tools
who try to pass such configuration.
Fixes: ff0891915c ("net/mlx5e: Fix ETS BW check")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Current description did not include new devices. Fix that by proving the
correct generic description.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
This makes it more readable that rule is being used to return an err.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When translating command opcodes to a string, SET_DRIVER_VERSION
command was missing.
Fixes: 42ca502e17 ('net/mlx5_core: Use a macro in mlx5_command_str()')
Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Update mlx5 command list and error return function to handle XRQ
commands.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
As newer firmware supports double push/pop in a single FTE, we add
core bits and extend vlan action logic for it.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
These dummy helpers are all intended to be inline functions,
but one of them by accident came without the 'inline' keyword,
causing a harmless warning:
In file included from drivers/net/ethernet/mellanox/mlx5/core/main.c:63:
drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h:79:1: error: 'mlx5_accel_tls_add_flow' defined but not used [-Werror=unused-function]
mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
Fixes: ab412e1dd7 ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend existing driver for Spectrum ASIC to support Spectrum-2 ASIC.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Utilize only C-TCAM for now. Do very minimal A-TCAM initialization in
order to make C-TCAM work.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2, ACL regions that use 8 or 12 key blocks require several
consecutive hardware regions.
In order to allow defragmentation, the device stores a mapping from a
logical region ID to an hardware region ID, which is similar to the page
table that is used to translate virtual addresses to physical addresses.
Add the region association callback to the region create sequence and
implement it as a NOP in Spectrum which does not require it.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Encode each flexible key block in the general block scheme according its
block index.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum the key (and mask) block layout is very straight forward and
every block is 16 bytes aligned.
However, in Spectrum-2 the blocks are not even byte aligned, which makes
it difficult to encode them using current method.
Instead, first encode each block and then encode the block in the
general blocks layout.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PGCR register configures general Policy-Engine settings.
Specifically, we are going to use it in order to set the default action
base pointer, which determines where the default action (when there is
no hit) is located for each region.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PERERP register configures the region eRPs. It can be used, for
example, to enable lookup in the C-TCAM in addition to the A-TCAM.
To be able to perform a lookup in the C-TCAM we need to "use" the eRP
table. This is done by marking the pointer as valid, but zeroing the eRP
table vector.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PERCR register configures the region parameters such as whether to
consult the bloom filter before performing a lookup using a specific
eRP.
For C-TCAM only usage we don't need to accurately set the master mask.
Instead, we can set all of its bits to make sure all the extracted keys
are actually used.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PERAR register is used to associate a hw region for region_id's.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2, activity cannot be find out by TCAM rule (PTCEv2 register),
but rather by associated action set. For that purpose, extend action ops
to allow query activity from PEFA register. Block activity is decided
according to activity of the first set.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2, the PEFA register is extend to report if the action set
was hit during processing of packets. Introduce this extension and
adjust the code around this accordingly.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce key blocks for Spectrum-2 that contains the same elements used
already for Spectrum1. Along with that, introduce encoder stub.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2, no action set is stored directly in TCAM, all are located
in KVD linear. So ask core to treat the first set as dummy empty one,
to be just used for PTCEV2 purposes.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add dummy ops for now. The ops are going to be implemented later on.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum-2, KVD linear indexes are hashed into KVD hash. Therefore it
is possible for multiple resource types to use same indexes. There are
multiple index spaces. Also, the index space is bigger than the actual
KVD hash area, which allows to have holes in the index space without any
penalization. The HW has to be told in case the index for particular
resource type is no longer used so it can be freed from KVD hash. IEDR
register is used for that.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The IEDR register is used for deleting entries from the entry tables.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a new rx packet arrives, the rx path will decide whether to reuse
the remainder of the page or not according to one of the below conditions:
1. frag_info->frag_stride == PAGE_SIZE / 2
2. frags->page_offset + frag_info->frag_size > PAGE_SIZE;
The first condition is no met for when XDP is set.
For XDP, page_offset is always set to priv->rx_headroom which is
XDP_PACKET_HEADROOM and frag_info->frag_size is around mtu size + some
padding, still the 2nd release condition will hold since
XDP_PACKET_HEADROOM + 1536 < PAGE_SIZE, as a result the page will not
be released and will be _wrongly_ reused for next free rx descriptor.
In XDP there is an assumption to have a page per packet and reuse can
break such assumption and might cause packet data corruptions.
Fix this by adding an extra condition (!priv->rx_headroom) to the 2nd
case to avoid page reuse when XDP is set, since rx_headroom is set to 0
for non XDP setup and set to XDP_PACKET_HEADROOM for XDP setup.
No additional cache line is required for the new condition.
Fixes: 34db548bfb ("mlx4: add page recycling in receive path")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Suggested-by: Martin KaFai Lau <kafai@fb.com>
CC: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Expose counters ASIC has in the group of RFC 2819 counters that count
number of packets within specific size range.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the byte count indication in CQE for processed IPsec
packets that contain a metadata header.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds common functions to handle mellanox metadata headers.
These functions are used by IPsec and TLS to process FPGA metadata.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables TLS Rx based on available HW capabilities.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds software statistics for TLS to count important
events.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement the TLS rx offload data path according to the
requirements of the TLS generic NIC offload infrastructure.
Special metadata ethertype is used to pass information to
the hardware.
When hardware loses synchronization a special resync request
metadata message is used to request resync.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the mlx5 implementation of the TLS Rx routines to add/del TLS
contexts, also add the tls_dev_resync_rx routine
to work with the TLS inline Rx crypto offload infrastructure.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Innova TLS, TLS contexts are added or deleted
via a command message over the SBU connection.
The HW then sends a response message over the same connection.
Complete the implementation for Innova TLS (FPGA-based) hardware by
adding support for rx inline crypto offload.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For symmetry, we rename mlx5e_tls_offload_context to
mlx5e_tls_offload_context_tx before we add mlx5e_tls_offload_context_rx.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For symmetry, we rename tls_offload_context to
tls_offload_context_tx before we add tls_offload_context_rx.
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2018-07-15
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Various different arm32 JIT improvements in order to optimize code emission
and make the JIT code itself more robust, from Russell.
2) Support simultaneous driver and offloaded XDP in order to allow for advanced
use-cases where some work is offloaded to the NIC and some to the host. Also
add ability for bpftool to load programs and maps beyond just the cgroup case,
from Jakub.
3) Add BPF JIT support in nfp for multiplication as well as division. For the
latter in particular, it uses the reciprocal algorithm to emulate it, from Jiong.
4) Add BTF pretty print functionality to bpftool in plain and JSON output
format, from Okash.
5) Add build and installation to the BPF helper man page into bpftool, from Quentin.
6) Add a TCP BPF callback for listening sockets which is triggered right after
the socket transitions to TCP_LISTEN state, from Andrey.
7) Add a new cgroup tree command to bpftool which iterates over the whole cgroup
tree and prints all attached programs, from Roman.
8) Improve xdp_redirect_cpu sample to support parsing of double VLAN tagged
packets, from Jesper.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Hosts using a VRRP router send their packets with a destination MAC of
the VRRP router which is of the following form [1]:
IPv4 - 00-00-5E-00-01-{VRID}
IPv6 - 00-00-5E-00-02-{VRID}
Where VRID is the ID of the virtual router. Such packets are directed to
the router block in the ASIC by an FDB entry that was added in the
previous patch.
However, in certain cases it is possible to skip this FDB lookup and
send such packets directly to the router. This is accomplished by adding
these special MAC addresses to the RIF cache. If the cache is hit, the
packet will skip the L2 lookup and ingress the router with the RIF
specified in the cache entry.
1. https://tools.ietf.org/html/rfc5798#section-7.3
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Virtual Router Redundancy Protocol packets are used to communicate the
state of the Master router associated with the virtual router ID (VRID).
These are link-local multicast packets sent with IP protocol 112 that
are trapped in the router block in the ASIC.
Add a trap for these packets and mark the trapped packets to prevent
them from potentially being re-flooded by the bridge driver.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
An IP packet received on a netdev with a macvlan upper whose MAC matches
the packet's destination MAC will be re-injected to the Rx path as if it
was received by the macvlan, and perform an L3 lookup.
Reflect this functionality to the ASIC by programming FDB entries that
will direct MACs of macvlan uppers to the router.
In a similar fashion to router interfaces (RIFs) that are programmed
upon the addition of the first IP address on an interface and destroyed
upon the removal of the last IP address, the FDB entries for the macvlan
are added and destroyed based on the addition of the first and removal
of the last IP address on the macvlan.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to allow more unicast MAC addresses (e.g., VRRP virtual MAC) to
be directed to the router we need to enable macvlan uppers on top of
mlxsw netdevs.
Allow macvlan upper devices on top of mlxsw netdevs and sanitize
configurations that can't work. For example, a macvlan can't be enslaved
to a bridge as without ACLs the device doesn't take the destination MAC
into account when classifying a packet to a bridge instance (i.e., a
FID).
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
prog_attached of struct netdev_bpf should have been superseded
by simply setting prog_id long time ago, but we kept it around
to allow offloading drivers to communicate attachment mode (drv
vs hw). Subsequently drivers were also allowed to report back
attachment flags (prog_flags), and since nowadays only programs
attached will XDP_FLAGS_HW_MODE can get offloaded, we can tell
the attachment mode from the flags driver reports. Remove
prog_attached member.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This parameter enables capturing region snapshot of the crspace
during critical errors. The default value of this parameter is
disabled, it can be enabled using devlink param commands.
It is possible to configure during runtime and also driver init.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Crdump allows the driver to create a snapshot of the FW PCI
crspace and health buffer during a critical FW issue.
In case of a FW command timeout, FW getting stuck or a non zero
value on the catastrophic buffer, a snapshot will be taken.
The snapshot is exposed using devlink, cr-space, fw-health
address regions are registered on init and snapshots are attached
once a new snapshot is collected by the driver.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Health buffer address is a 32 bit PCI address offset provided by
the FW. This offset is used for reading FW health debug data
located on the shared CR space. Cr space is accessible in both
driver and FW and allows for different queries and configurations.
Health buffer size is always 64B of readable data followed by a
lock which is used to block volatile CR space access.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When offloading mirror-to-gretap, mlxsw needs to preroute the path that
the encapsulated packet will take. That path may include a LAG device
above a front panel port. So far, mlxsw resolved the path to the first
up front panel slave of the LAG interface, but that only reflects
administrative state of the port. It neglects to consider whether the
port actually has a carrier, and what the LACP state is.
So instead of checking upness of the device, check carrier state and
txability.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
L2 Fwd Offload & 10GbE Intel Driver Updates 2018-07-09
This patch series is meant to allow support for the L2 forward offload, aka
MACVLAN offload without the need for using ndo_select_queue.
The existing solution currently requires that we use ndo_select_queue in
the transmit path if we want to associate specific Tx queues with a given
MACVLAN interface. In order to get away from this we need to repurpose the
tc_to_txq array and XPS pointer for the MACVLAN interface and use those as
a means of accessing the queues on the lower device. As a result we cannot
offload a device that is configured as multiqueue, however it doesn't
really make sense to configure a macvlan interfaced as being multiqueue
anyway since it doesn't really have a qdisc of its own in the first place.
The big changes in this set are:
Allow lower device to update tc_to_txq and XPS map of offloaded MACVLAN
Disable XPS for single queue devices
Replace accel_priv with sb_dev in ndo_select_queue
Add sb_dev parameter to fallback function for ndo_select_queue
Consolidated ndo_select_queue functions that appeared to be duplicates
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In general, accessing userspace memory beyond the length of the supplied
buffer in VFS read/write handlers can lead to both kernel memory corruption
(via kernel_read()/kernel_write(), which can e.g. be triggered via
sys_splice()) and privilege escalation inside userspace.
In this case, the affected files are in debugfs (and should therefore only
be accessible to root) and check that *pos is zero (which prevents the
sys_splice() trick). Therefore, this is not a security fix, but rather a
small cleanup.
For the read handlers, fix it by using simple_read_from_buffer() instead of
custom logic.
For the write handler, add a check.
changed in v2:
- also fix dbg_write()
Fixes: e126ba97db ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
These resources are needed for Spectrum-2 KVD linear management
implementation.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prepare for Spectrum-2 FW version checking and
make mlxsw_sp_fw_rev_validate() per-ASIC as well as required FW revision
and FW filename.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For Spectrum-2, we need to insert priority to C-TCAM because HW
needs that info in order to correctly process scenarios where rules
are in both C-TCAM and A-TCAM.
So extend the mlxsw_sp_acl_ctcam_entry_add() args to accept indication
if priority needs to be filled up and implement the priority
computation and fill-up.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is going to be needed for Spectrum-2 C-TCAM implementation.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since Spectrum-2 encodes blocks into different HW layout, push this
code into Spectrum-specific op.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the flex keys for Spectrum-2 differ not only in blocks definitions
but also in encoding layout, prepare for the implementation and pass
Spectrum/Spectrum-2 specific ops down to mlxsw_afk_create.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>