The CPU policer used to police packets being trapped via a local route
(IP2ME) was incorrectly configured to police based on bytes per second
instead of packets per second.
Change the policer to police based on packets per second and avoid
packet loss under certain circumstances.
Fixes: 9148e7cf73 ("mlxsw: spectrum: Add policers for trap groups")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
doorbell only depends on xmit_more and netif_tx_queue_stopped()
Using __netdev_tx_sent_queue() avoids messing with BQL stop flag,
and is more generic.
This patch increases performance on GSO workload by keeping
doorbells to the minimum required.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
An MC-aware mode was introduced in commit 7b81953066 ("mlxsw:
spectrum: Configure MC-aware mode on mlxsw ports"). In MC-aware mode,
BUM traffic gets a special treatment by being assigned to a separate set
of traffic classes 8..15. Pairs of TCs 0 and 8, 1 and 9, etc., are then
configured to strictly prioritize the lower-numbered ones. The intention
is to prevent BUM traffic from flooding the switch and push out all UC
traffic, which would otherwise happen, and instead give UC traffic
precedence.
However strictly prioritizing UC traffic has the effect that UC overload
pushes out all BUM traffic, such as legitimate ARP queries. These
packets are kept in queues for a while, but under sustained UC overload,
their lifetime eventually expires and these packets are dropped. That is
detrimental to network performance as well.
Therefore configure the MC TCs (8..15) with minimum shaper of 200Mbps (a
minimum permitted value) to allow a trickle of necessary control traffic
to get through.
Fixes: 7b81953066 ("mlxsw: spectrum: Configure MC-aware mode on mlxsw ports")
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>
Add QEEC.mise (minimum shaper enable) and QEEC.min_shaper_rate to enable
configuration of minimum shaper.
Increase the QEEC length to 0x20 as well: that's the length that the
register has had for a long time now, but with the configurations that
mlxsw typically exercises, the firmware tolerated 0x1C-sized packets.
With mise=true however, FW rejects packets unless they have the full
required length.
Fixes: b9b7cee405 ("mlxsw: reg: Add QoS ETS Element Configuration register")
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>
As shown by Dmitris, we need to use csum_block_add() instead of csum_add()
when adding the FCS contribution to skb csum.
Before 4.18 (more exactly commit 88078d98d1 "net: pskb_trim_rcsum()
and CHECKSUM_COMPLETE are friends"), the whole skb csum was thrown away,
so RXFCS changes were ignored.
Then before commit d55bef5059 ("net: fix pskb_trim_rcsum_slow() with
odd trim offset") both mlx5 and pskb_trim_rcsum_slow() bugs were canceling
each other.
Now we fixed pskb_trim_rcsum_slow() we need to fix mlx5.
Note that this patch also rewrites mlx5e_get_fcs() to :
- Use skb_header_pointer() instead of reinventing it.
- Use __get_unaligned_cpu32() to avoid possible non aligned accesses
as Dmitris pointed out.
Fixes: 902a545904 ("net/mlx5e: When RXFCS is set, add FCS data into checksum calculation")
Reported-by: Paweł Staszewski <pstaszewski@itcare.pl>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eran Ben Elisha <eranbe@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Dimitris Michailidis <dmichail@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Paweł Staszewski <pstaszewski@itcare.pl>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Tested-By: Maria Pasechnik <mariap@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Abdul Haleem reported a build error on ppc :
drivers/net/ethernet/mellanox/mlx4/en_rx.c:582:18: warning: `struct
iphdr` declared inside parameter list [enabled by default]
struct iphdr *iph)
^
drivers/net/ethernet/mellanox/mlx4/en_rx.c:582:18: warning: its scope is
only this definition or declaration, which is probably not what you want
[enabled by default]
drivers/net/ethernet/mellanox/mlx4/en_rx.c: In function
get_fixed_ipv4_csum:
drivers/net/ethernet/mellanox/mlx4/en_rx.c:586:20: error: dereferencing
pointer to incomplete type
__u8 ipproto = iph->protocol;
^
Fixes: 55469bc6b5 ("drivers: net: remove <net/busy_poll.h> inclusion when not needed")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After a failed reload, the driver is still registered to devlink, its
devlink instance is still allocated and the 'reload_fail' flag is set.
Then, in the next reload try, the driver's allocated devlink instance will
be freed without unregistering from devlink and its components (e.g,
resources). This scenario can cause a use-after-free if the user tries to
execute command via devlink user-space tool.
Fix by not freeing the devlink instance during reload (failed or not).
Fixes: 24cc68ad6c ("mlxsw: core: Add support for reload")
Signed-off-by: Shalom Toledo <shalomt@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>
Demands to remove FDB entries should be honored even if the FDB entry in
question was originally learned, and not added by the user. Therefore
ignore the added_by_user datum for SWITCHDEV_FDB_DEL_TO_DEVICE.
Fixes: 816a3bed95 ("switchdev: Add fdb.added_by_user to switchdev notifications")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers using generic NAPI interface no longer need to include
<net/busy_poll.h>, since busy polling was moved to core networking
stack long ago.
See commit 79e7fff47b ("net: remove support for per driver
ndo_busy_poll()") for reference.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
FDB_MAX_CHAIN is three. We wanted to allocate enough memory to hold four
structs but there are missing parentheses so we only allocate enough
memory for three structs and the first byte of the fourth one.
Fixes: 328edb499f ("net/mlx5: Split FDB fast path prio to multiple namespaces")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net/sched/cls_api.c has overlapping changes to a call to
nlmsg_parse(), one (from 'net') added rtm_tca_policy instead of NULL
to the 5th argument, and another (from 'net-next') added cb->extack
instead of NULL to the 6th argument.
net/ipv4/ipmr_base.c is a case of a bug fix in 'net' being done to
code which moved (to mr_table_dump)) in 'net-next'. Thanks to David
Ahern for the heads up.
Signed-off-by: David S. Miller <davem@davemloft.net>
These are counters for errors received on rx side, such as
FEC errors.
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Driver callback function for 'ethtool --show-fec',
'ethtool --set-fec' commands.
The query function returns active and configured FEC policy
for current link speed.
The set function sets FEC policy for all supported link
speeds.
1) If current link speed doesn't support requested FEC policy,
the function fails.
2) If a different link speed doesn't support requested FEC
policy, FEC capbilities for this speed are turned off.
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Added functions to query and set link FEC policy.
To get/set FEC capabilities in PPLM reg we need to query
current link speed.
'mlx5_get_fec_speed_field' queries current link speed and returns
correct field offset.
FEC Query's return value is divided into 'active FEC policy', which is
the FEC policy used by the link, and 'configured FEC policy', which
is the FEC policy requested by the user.
The two values may differ if:
1) FEC policy was configured to 'auto',
in which case the active FEC policy would be the default FEC policy
for current link speed.
2) FEC policy was changed, but no link reset is performed. In which case,
the active FEC policy would become the configured one after a link
reset.
FEC set function sets FEC policy for all link speeds and perform link
reset.
1) If current link speed doesn't support requested FEC policy,
the function fails.
2) If a different link speed doesn't support requested FEC policy,
FEC capbilities for this speed are turned off and a warning message
is printed.
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Fs_counters list can temporary become unsorted when new counters are
created/deleted concurrently. Idr is used to quickly lookup position to
insert new counter in logarithmic time. However, if new flows are
concurrently inserted during time window when flows with adjacent ids are
already removed from idr but are still present in counters list,
mlx5_fc_stats_work() observes counters list in inconsistent state, which
results following warning:
[ 1839.561955] mlx5_core 0000:81:00.0: mlx5_cmd_fc_bulk_get:587:(pid 729): Flow counter id (0x102d5) out of range (0x1c0a8..0x1c10b). Counter ignored.
Move idr_remove() call to be executed synchronously with counter deletion
from list. Extract this code to mlx5_fc_stats_remove() helper function that
is called by workqueue job handler mlx5_fc_stats_work().
Fixes: 12d6066c3b ("net/mlx5: Add flow counters idr")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
In fs_counters elements from both addlist and dellist are removed by
mlx5_fc_stats_work() without any locking. This introduces race condition
when batch of new rules is created and then immediately deleted (for
example, when error occurred during flow creation). In such case some of
the rules might be in dellist, but not in addlist when mlx5_fc_stats_work()
is executed concurrently with tc, which will result rule deletion and
use-after-free on next iteration because deleted rules are still in
addlist.
Always take dellist first to guarantee that rules can only be deleted after
they were removed from addlist.
Fixes: 6e5e228391 ("net/mlx5: Add new list to store deleted flow counters")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reported-by: Chris Mi <chrism@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Take struct mlx5_frag_buf out of mlx5_frag_buf_ctrl, as it is not
needed to manage and control the datapath of the fragmented buffers API.
struct mlx5_frag_buf contains control info to manage the allocation
and de-allocation of the fragmented buffer.
Its fields are not relevant for datapath, so here I take them out of the
struct mlx5_frag_buf_ctrl, except for the fragments array itself.
In addition, modified mlx5_fill_fbc to initialise the frags pointers
as well. This implies that the buffer must be allocated before the
function is called.
A set of type-specific *_get_byte_size() functions are replaced by
a generic one.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
========================================================================
From Or Gerlitz <ogerlitz@mellanox.com>:
This series from Paul adds support to mlx5 e-switch tc offloading of multiple priorities and chains.
This is made of four building blocks (along with few minor driver refactors):
[1] Split FDB fast path prio to multiple namespaces
Currently the FDB name-space contains two priorities, fast path (p0) and slow path (p1).
The slow path contains the per representor SQ send-to-vport TX rule and the match-all
RX miss rule. As a pre-step to support multi-chains and priorities, we split the FDB fast path
to multiple namespaces (sub namespaces), each with multiple priorities.
[2] E-Switch chains and priorities
A chain is a group of priorities. We use the fdb parallel sub-namespaces to implement chains,
and a flow table for each priority in them.
Because these namespaces are parallel and in series to the slow path
fdb, the chains aren't connected to each other (but to the slow path),
and one must use a explicit goto action to reach a different chain.
Flow tables for the priorities are created on demand and destroyed
once not used.
[3] Add a no-append flow insertion mode, use it for TC offloads
Enhance the driver fs core, such that if a no-append flag is set by the caller,
we add a new FTE, instead of appending the actions of the inserted rule when
the same match already exists.
For encap rules, we defer the HW offloading till we have a valid neighbor. This can
result in the packet hitting a lower priority rule in the HW DP. Use the no-append API
to push these packets to the slow path FDB table, so they go to the TC kernel DP as done
before priorities where supported.
[4] Offloading tc priorities and chains for eswitch flows
Using [1], [2] and [3] above we add the support for offloading both chains
and priorities. To get to a new chain, use the tc goto action. We support
a fixed prio range 1-16, and chains 0-3.
=============================================================================
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJbx6k1AAoJEEg/ir3gV/o+l40H/14rNaV27vefjuALgOvNX4DY
iSI5UFv9ILnAemcD2xkVfJeGolwdzoRhCXJ5oyCylCPnP4tb9zgDgwu9V/WmIRG+
DOaPLu+0V6jqfEGO5sXJPMhJNUR8WWAjfu66htJ0Nc1HV2OM5eYrcvjaYCfW4Egr
QFWGyq4sPyYcpbb7wURbhmkfs8Vwxcj9c2cZIfXo3VJsKxULqU9Mj5hZnirI1OAy
UhjLssb/8wfHmwNcqETI9ae7O+vPDMLkxdQvpviEBI+HJ7vZ6op2X4lVEsn/Bx2E
/KrHGQObkwim8thTOYkQeJtqptWbiRvkpNnwryUV1fwjWPl6X1r3bXH7RdeRwCg=
=aFCc
-----END PGP SIGNATURE-----
Merge tag 'mlx5-updates-2018-10-17' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
mlx5-updates-2018-10-17
========================================================================
From Or Gerlitz <ogerlitz@mellanox.com>:
This series from Paul adds support to mlx5 e-switch tc offloading of multiple priorities and chains.
This is made of four building blocks (along with few minor driver refactors):
[1] Split FDB fast path prio to multiple namespaces
Currently the FDB name-space contains two priorities, fast path (p0) and slow path (p1).
The slow path contains the per representor SQ send-to-vport TX rule and the match-all
RX miss rule. As a pre-step to support multi-chains and priorities, we split the FDB fast path
to multiple namespaces (sub namespaces), each with multiple priorities.
[2] E-Switch chains and priorities
A chain is a group of priorities. We use the fdb parallel sub-namespaces to implement chains,
and a flow table for each priority in them.
Because these namespaces are parallel and in series to the slow path
fdb, the chains aren't connected to each other (but to the slow path),
and one must use a explicit goto action to reach a different chain.
Flow tables for the priorities are created on demand and destroyed
once not used.
[3] Add a no-append flow insertion mode, use it for TC offloads
Enhance the driver fs core, such that if a no-append flag is set by the caller,
we add a new FTE, instead of appending the actions of the inserted rule when
the same match already exists.
For encap rules, we defer the HW offloading till we have a valid neighbor. This can
result in the packet hitting a lower priority rule in the HW DP. Use the no-append API
to push these packets to the slow path FDB table, so they go to the TC kernel DP as done
before priorities where supported.
[4] Offloading tc priorities and chains for eswitch flows
Using [1], [2] and [3] above we add the support for offloading both chains
and priorities. To get to a new chain, use the tc goto action. We support
a fixed prio range 1-16, and chains 0-3.
=============================================================================
Signed-off-by: David S. Miller <davem@davemloft.net>
When the switch driver (e.g., mlxsw_spectrum) determines it needs to
flash a new firmware version it resets the ASIC after the flashing
process. The bus driver (e.g., mlxsw_pci) then registers itself again
with mlxsw_core which means (among other things) that the device
registers itself again with the hwmon subsystem again.
Since the device was registered with the hwmon subsystem using
devm_hwmon_device_register_with_groups(), then the old hwmon device
(registered before the flashing) was never unregistered and was
referencing stale data, resulting in a use-after free.
Fix by removing reliance on device managed APIs in mlxsw_hwmon_init().
Fixes: c86d62cc41 ("mlxsw: spectrum: Reset FW after flash")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the device, VxLAN encapsulation takes place in the FDB table where
certain {MAC, FID} entries are programmed with an underlay unicast IP.
MAC addresses that are not programmed in the FDB are flooded to the
relevant local ports and also to a list of underlay unicast IPs that are
programmed using the all zeros MAC address in the VxLAN driver.
One difference between the hardware and software data paths is the fact
that in the software data path there are two FDB lookups prior to the
encapsulation of the packet. First in the bridge's FDB table using {MAC,
VID} and another in the VxLAN's FDB table using {MAC, VNI}.
Therefore, when a new VxLAN FDB entry is notified, it is only programmed
to the device if there is a corresponding entry in the bridge's FDB
table. Similarly, when a new bridge FDB entry pointing to the VxLAN
device is notified, it is only programmed to the device if there is a
corresponding entry in the VxLAN's FDB table.
Note that the above scheme will result in a discrepancy between both
data paths if only one FDB table is populated in the software data path.
For example, if only the bridge's FDB is populated with an entry
pointing to a VxLAN device, then a packet hitting the entry will only be
flooded by the kernel to remote VTEPs whereas the device will also flood
the packets to other local ports member in the VLAN.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enslavement of VxLAN devices to offloaded bridges was never forbidden by
mlxsw, but this patch makes sure the required configuration is performed
in order to allow VxLAN encapsulation and decapsulation to take place in
the device.
The patch handles both the case where a VxLAN device is enslaved to an
already offloaded bridge and the case where the first mlxsw port is
enslaved to a bridge that already has VxLAN device configured.
Invalid configurations are sanitized and an error string is returned via
extack.
Since encapsulation and decapsulation do not occur when the VxLAN device
is down, the driver makes sure to enable / disable these functionalities
based on NETDEV_PRE_UP and NETDEV_DOWN events.
Note that NETDEV_PRE_UP is used in favor of NETDEV_UP, as the former
allows to veto the operation, if necessary.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, an FDB entry only ceases being offloaded when it is deleted.
This changes with VxLAN encapsulation.
Devices capable of performing VxLAN encapsulation usually have only one
FDB table, unlike the software data path which has two - one in the
bridge driver and another in the VxLAN driver.
Therefore, bridge FDB entries pointing to a VxLAN device are only
offloaded if there is a corresponding entry in the VxLAN FDB.
Allow clearing the offload indication in case the corresponding entry
was deleted from the VxLAN FDB.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a local route that matches the source IP of an offloaded NVE tunnel
is notified, the driver needs to program it to perform NVE decapsulation
instead of merely trapping packets to the CPU.
This patch complements "mlxsw: spectrum_router: Enable local routes
promotion to perform NVE decap" where existing local routes were
promoted to perform NVE decapsulation.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
802.1D FIDs are used to represent VLAN-unaware bridges and currently
this is the only type of FID that supports NVE configuration.
Since the NVE tunnel device does not take a reference on the FID, it is
possible for the FID to be destroyed when it still has NVE
configuration.
Therefore, when destroying the FID make sure to disable its NVE
configuration.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The common NVE core expects each encapsulation type to implement a
certain set of operations that are specific to this type and the
currently used ASIC. These operations include things such as the ability
to determine whether a certain NVE configuration can be offloaded and
ASIC-specific initialization for this type.
Implement these operations for VxLAN on the Spectrum ASIC. Spectrum-2
support will be added by a future patchset.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Spectrum ASIC supports different types of NVE encapsulations (e.g.,
VxLAN, NVGRE) with more types to be supported by future ASICs.
Despite being different, all these encapsulations share some common
functionality such as the enablement of NVE encapsulation on a given
filtering identifier (FID) and the addition of remote VTEPs to the
linked-list of VTEPs that traffic should be flooded to.
Implement this common core and allow different ASICs to register
different operations for different encapsulation types.
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 the device, different VRFs (routing tables) are represented using
different virtual routers (VRs) and thus the kernel's table IDs are
mapped to VR IDs.
Allow internal users of the IP router to query the VR ID based on a
kernel table ID.
This is needed - for example - when configuring the underlay VR where
VxLAN encapsulated packets will undergo an L3 lookup. In this case, the
kernel's table ID is derived from the VxLAN device's configuration.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an NVE tunnel with an IP underlay (e.g., VxLAN) is configured the
local route to the tunnel's source IP needs to be promoted to perform
NVE decapsulation.
Expose an API in the unicast IP router to promote / demote local routes.
The case where a local route is configured after the creation of the NVE
tunnel will be handled in a subsequent patch in the set.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current APIs only allow looking for a FID and creating it in case it
does not exist.
With VxLAN, in case the bridge to which the VxLAN device was enslaved
does not already have a corresponding FID, then it means that something
went wrong that we need to be aware of.
Add an API to look up a FID, but without creating it in order to catch
above-mentioned situation.
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 the device, the VNI and the list of remote VTEPs a packet should be
flooded to is a property of the filtering identifier (FID).
During encapsulation, the VNI is taken from the FID the packet was
classified to. During decapsulation, the overlay packet is injected into
a bridge and classified to a FID based on the VNI it came with.
Allow NVE configuration for a FID. Currently, this is only supported
with 802.1D FIDs which are used for VLAN-unaware bridges. However, NVE
configuration is going to be supported with 802.1Q FIDs which is why the
related fields are placed in the common FID struct.
Since the device requires a 1:1 mapping between FID and VNI, the driver
maintains a hashtable keyed by VNI and checks if the VNI is already
associated with an existing 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>
Currently we fail when user specify a non-zero chain, this patch adds the
support for it and tc priorities. To get to a new chain, use the tc
goto action.
Currently we support a fixed prio range 1-16, and chain range 0-3.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When adding a vxlan tc rule, and a neighbour isn't available, we
don't insert any rule to hardware. Once we enable offloading flows
with multiple priorities, a packet that should have matched this rule
will continue in hardware pipeline and might match a wrong one.
This is unlike in tc software path where it will be matched and
forwarded to the vxlan device (which will cause a ARP lookup
eventually) and stop processing further tc filters.
To address that, when when a neighbour isn't available (EAGAIN from
attach_encap), or gets deleted, change the original action to be a
forward to slow path instead. Neighbour update will restore the original
action once the neighbour becomes available. This will be done atomically
so at any given time we will have a the correct match.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
A pre-step for the tc offloads code to use this when a neigh is
not available for encap rules.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The code for adding/deleting fdb flow is repeated when
user-space does flow add/del and when we add/del from
the neigh update path - unify them to avoid the duplication.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When replacing a tc flower rule, flower first requests to add the
new rule (new action), then deletes the old one.
But currently when asked to add a new tc flower flow, we append the
actions (and counters to it).
This can result in a fte with two flow counters or conflicting
actions (drop and encap action) which firmware complains/errs
about and isn't achieving what the user aimed for.
Instead, insert the flow using the new no-append flag which will add a
new HW rule, the old flow and rule will be deleted later by flower
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanmox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
If no-append flag is set, we will add a new FTE, instead of appending
the actions of the inserted rule when the same match already exists.
While here, move the has_flow_tag boolean indicator to be a flag too.
This patch doesn't change any functionality.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanmox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
A chain is a group of priorities, so use the fdb parallel
sub namespaces to implement chains, and a flow table for each
priority in them.
Because these namespaces are parallel and in series to the slow path
fdb, the chains aren't connected to one another (but to the slow path),
and one must use a explicit goto action to reach a different chain.
Flow tables for the priorities will be created on demand and destroyed
once not used.
The Firmware has four pools of tables for sizes S/XS/M/L (4k, 64k, 1m, 4m).
We maintain ghost copies of the pools occupancy.
When a new table is to be created, we scan the pools from large to small
and find the 1st table size which can be now created. When a table is
destroyed, we update the relevant pool.
Multi chain/prio isn't enabled yet by this patch, for now all flows
will use the default chain 0, and prio 1.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Be symmetric with the e-switch API to add rules which has a
specific function to add fwd rules which are used as part of
vport mirroring.
This patch doesn't change any functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Towards supporting multi-chains and priorities, split the FDB fast path
to multiple namespaces (sub namespaces), each with multiple priorities.
This patch adds a new flow steering type, FS_TYPE_PRIO_CHAINS, which is
like current FS_TYPE_PRIO, but may contain only namespaces, and those
will be in parallel to one another in terms of managing of the flow
tables connections inside them. Meaning, while searching for the next
or previous flow table to connect for a new table inside such namespace
we skip the parallel namespaces in the same level under the
FS_TYPE_PRIO_CHAINS prio we originated from.
We use this new type for splitting the fast path prio into multiple
parallel namespaces, each containing normal prios.
The prios inside them (and their tables) will be connected to one
another, but not from one parallel namespace to another, instead the
last prio in each namespace will be connected to the next prio in
the containing FDB namespace, which is the slow path prio.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Move to have clear separation on the code path to add nic vs e-switch
flows. While here we break the code that deals with adding offloaded
TC tool to few smaller stages, each on helper function.
Besides getting us simpler and readable code, these are pre-steps
for being able to have two HW flows serving one SW TC flow for some
e-switch use cases.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Refactor the flow add utility functions to return err code instead of rule
pointers. This will allow for simpler logic when one tc rule is
duplicated to two HW rules in downstream patches.
Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently, when a flow rule is created using the FS core layer, the caller
has to pass the entire flow counter object and not just the counter HW
handle (ID). This requires both the FS core and the caller to have
knowledge about the inner implementation of the FS layer flow counters
cache and limits the possible users.
Move to use the counter ID across the place when dealing with flows.
Doing this decoupling, now can we privatize the inner implementation
of the flow counters.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
There's no real reason for the e-switch logic to manage the creation of
counters for offloaded flows. The API already has the directive for the
caller to denote they want to attach a counter to the created flow.
As such, we go and move the management of flow counters to the mlx5e
tc offload logic. This also lets us remove an inelegant interface where
the FS layer had to provide a way to retrieve a counter from a flow rule.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
mlx5 updates for both net-next and rdma-next
* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: (21 commits)
net/mlx5: Expose DC scatter to CQE capability bit
net/mlx5: Update mlx5_ifc with DEVX UID bits
net/mlx5: Set uid as part of DCT commands
net/mlx5: Set uid as part of SRQ commands
net/mlx5: Set uid as part of SQ commands
net/mlx5: Set uid as part of RQ commands
net/mlx5: Set uid as part of QP commands
net/mlx5: Set uid as part of CQ commands
net/mlx5: Rename incorrect naming in IFC file
net/mlx5: Export packet reformat alloc/dealloc functions
net/mlx5: Pass a namespace for packet reformat ID allocation
net/mlx5: Expose new packet reformat capabilities
{net, RDMA}/mlx5: Rename encap to reformat packet
net/mlx5: Move header encap type to IFC header file
net/mlx5: Break encap/decap into two separated flow table creation flags
net/mlx5: Add support for more namespaces when allocating modify header
net/mlx5: Export modify header alloc/dealloc functions
net/mlx5: Add proper NIC TX steering flow tables support
net/mlx5: Cleanup flow namespace getter switch logic
net/mlx5: Add memic command opcode to command checker
...
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJbvqcMAAoJEEg/ir3gV/o+eFsH/2TbJH+i1BuGMVwCB8o+U1Rz
C01pJmR7Lb7WwQZ8ZKTOqQkS7BkGX1hNGyIlc4i6ZnP+4gsVJAbP6LKPjTvyD7e6
TNb8bvxTUCOovknrevKkGba8tzoTTsC4wwwbHLGHd1hkKSY1P5hXg8R7vpear+n6
/PFJwzpIXDAa8AHqeORCNYj7MneUm3kaahcmSOxOhvDbRx3UG9cgy7tEhPjZbRn5
jPFsxFCSPcGedtI+g8bzodmpneTcu1KF6QCunrl2bGt5EzgDrbaw1UUoctxD2CJR
Ch45W807EvBJoFiJXXCNf9N+p5020F/Q+mTmK7khPirUjdtoLdcT9Goswpjfbtk=
=vJIA
-----END PGP SIGNATURE-----
Merge tag 'mlx5-fixes-2018-10-10' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
Mellanox, mlx5 fixes 2018-10-10
This pull request includes some fixes to mlx5 driver,
Please pull and let me know if there's any problem.
For -stable v4.11:
('net/mlx5: Take only bit 24-26 of wqe.pftype_wq for page fault type')
For -stable v4.17:
('net/mlx5: Fix memory leak when setting fpga ipsec caps')
For -stable v4.18:
('net/mlx5: WQ, fixes for fragmented WQ buffers API')
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
IPoIB netlink support and mlx5e pre-allocated netdevice initialization
IP link was broken due to the changes in IPoIB for the rdma_netdev
support after commit cd565b4b51
("IB/IPoIB: Support acceleration options callbacks").
This patchset fixes IPoIB pkey creation and removal using rtnetlink by
adding support in both IPoIB ULP layer and mlx5 layer:
From Jason and Denis:
1) Introduces changes in the RDMA netdev code in order to
allow allocation of the netdev to be done by the rtnl netdev code.
2) Reworks IPoIB initialization to use the two step rdma_netdev
creation.
From Feras and Saeed, mlx5e netdev layer refactoring to allow accepting
pre-allocated netdevs:
3) Adds support to initialize/cleanup netdevs that are not created
by mlx5 driver.
4) Change mlx5e netdevice layer to accept the pre-allocated netdevice
queue number.
5) Initialize mlx5e generic structures in one place to be used for all
netdevs types NIC/representors/IPoIB (both mlx5 allocated and
pre-allocted).
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJbvqHhAAoJEEg/ir3gV/o+TRQH+wYWgvi5AbqYlGpT8xSho8Dg
5tuFE9AbYDGLLWptZgtYXsBsTaltGVqKnwWy//dAuuSI7LvqtjeKqq0G1JKau70L
/49+vv8NTQ6vov2yY95yzzEo5B1/zVcYEl9dmJl4y6Xlwc+YIteewReVqRj+tucR
xO7ghLWc1o4Pl7gWBAcOULyOsZc+CtG8ElwEaBROXTtYRpsR7FKn7vN+WdWZ2VOG
MjtCUaG0vZlK1vaF76J3P9bL2V3y6o6i6S8RZwg1kPxO4jnrzyGrkxWMOX6f32KB
JAUcLVlJW5wckcRAKfTwLxsFMrc9vLBPHyj4XneXVWGKh8/dGUGY5gdGIJV5Jlc=
=m0tM
-----END PGP SIGNATURE-----
Merge tag 'mlx5e-updates-2018-10-10' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5e-updates-2018-10-10
IPoIB netlink support and mlx5e pre-allocated netdevice initialization
IP link was broken due to the changes in IPoIB for the rdma_netdev
support after commit cd565b4b51
("IB/IPoIB: Support acceleration options callbacks").
This patchset fixes IPoIB pkey creation and removal using rtnetlink by
adding support in both IPoIB ULP layer and mlx5 layer:
From Jason and Denis:
1) Introduces changes in the RDMA netdev code in order to
allow allocation of the netdev to be done by the rtnl netdev code.
2) Reworks IPoIB initialization to use the two step rdma_netdev
creation.
From Feras and Saeed, mlx5e netdev layer refactoring to allow accepting
pre-allocated netdevs:
3) Adds support to initialize/cleanup netdevs that are not created
by mlx5 driver.
4) Change mlx5e netdevice layer to accept the pre-allocated netdevice
queue number.
5) Initialize mlx5e generic structures in one place to be used for all
netdevs types NIC/representors/IPoIB (both mlx5 allocated and
pre-allocted).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts were easy to resolve using immediate context mostly,
except the cls_u32.c one where I simply too the entire HEAD
chunk.
Signed-off-by: David S. Miller <davem@davemloft.net>
During boot, mlx4_core sets the driverinit configuration parameters and
updates the devlink module on the initial values calling
devlink_param_driverinit_value_set().
If devlink_param_driverinit_value_set() returns an error mlx4_core
reports kernel module warning.
This caused false alarm during boot in case kernel was compiled with
CONFIG_NET_DEVLINK off.
Fix by removing warning reported in case
devlink_param_driverinit_value_set() fails.
This actually makes the function mlx4_devlink_set_init_value()
redundant to using directly devlink_param_driverinit_value_set() and so
removed.
It fixes the following kernel trace:
mlx4_core 0000:00:06.0: devlink set parameter 0 value failed (err = -95)
mlx4_core 0000:00:06.0: devlink set parameter 1 value failed (err = -95)
mlx4_core 0000:00:06.0: devlink set parameter 4 value failed (err = -95)
mlx4_core 0000:00:06.0: devlink set parameter 5 value failed (err = -95)
mlx4_core 0000:00:06.0: devlink set parameter 3 value failed (err = -95)
Fixes: bd1b51dc66 ("mlx4: Add mlx4 initial parameters table and register it")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The DECAP_ECN0 trap will be used to trap packets where the overlay
packet is marked with Non-ECT, but the underlay packet is marked with
either ECT(0), ECT(1) or CE. When trapped, such packets will be counted
as errors by the VxLAN driver and thus provide better visibility.
The NVE_ENCAP_ARP trap will be used to trap ARP packets undergoing NVE
encapsulation. This is needed in order to support E-VPN ARP suppression,
where the Linux bridge does not flood ARP packets through tunnel ports
in case it can answer the ARP request itself.
Note that all the packets trapped via these traps are marked with
'offload_fwd_mark', so as to not be re-flooded by the Linux bridge
through the ASIC ports.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the following resources to be used by the NVE code:
* Number of IPv4 underlay destination IPs in a single TNUMT record
* Number of IPv6 underlay destination IPs in a single TNUMT record
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
