| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
E-switch offloads mode initialize/cleanup multiple steering related
entities (flow table/group). Refactor these operations to internal
helper functions for better block design.
This patch doesn't change any functionality.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Commands referring to vports use the following scheme:
1. When referring to my own vport, put 0 in vport and 0 in other_vport.
2. When referring to another vport, put the vport number of the
referred vport and put 1 in other_vport. It was assumed that driver
is accessing other vport when vport number is greater than 0.
With the above scheme, the case that ECPF eswitch manager is trying
to access host PF vport will fall over with scheme 1 as the vport
number is 0. This is apparently wrong as driver is trying to refer
other vport.
As such usage can only happen in the eswitch context, change relevant
functions to provide other vport input properly.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
In SmartNIC mode, the eswitch manager is not necessarily the PF
(vport 0). Use a helper function to get the correct eswitch manager
vport number and cache on the eswitch instance for fast reference.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
When bonding is added, driver assumes that it's RoCE LAG if no VF is
enabled. This is not enough for ECPF as the VF is enabled in host PF
side. LAG should only choose RoCE mode when both slave devices meet
conditions below:
1. E-Switch offloads mode is NONE.
2. No VF is enabled.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Merge mlx5-next shared branched into net-next,
From Bodong Wang:
1) Introduction of ECPF (Embedded CPU Physical Function), and low level
bits for mlx5 SmartNic capabilities support.
2) Vport enumeration refactoring that affect mlx5_ib and mlx5_core
From Aya Levin,
3) Add support for 50Gbps per lane link modes in the Port Type and Speed
register (PTYS)
4) Refactor low level query functions for PTYS register
5) Add support for 50Gbps per lane link modes to mlx5_ib
Note: due to a change in API in mlx5/core and a later patch from net-next,
a fixup was squashed with this merge commit that replaces FDB_UPLINK_VPORT
with MLX5_VPORT_UPLINK which exists only in upstream net-next.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The netfilter conflicts were rather simple overlapping
changes.
However, the cls_tcindex.c stuff was a bit more complex.
On the 'net' side, Cong is fixing several races and memory
leaks. Whilst on the 'net-next' side we have Vlad adding
the rtnl-ness support.
What I've decided to do, in order to resolve this, is revert the
conversion over to using a workqueue that Cong did, bringing us back
to pure RCU. I did it this way because I believe that either Cong's
races don't apply with have Vlad did things, or Cong will have to
implement the race fix slightly differently.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch exposes new link modes (including 50Gbps per lane), and ext_*
fields which describes the new link modes in Port Type and Speed
register (PTYS).
Access functions, translation functions (speed <-> HW bits) and
link max speed function were modified.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
This patch fascicles queries to speed related fields in Port Type and
Speed register (PTYS) into a single API. I addition, this patch
refactors functions which serves only Ethernet driver: remove the
protocol type as an input parameter, move code from 'core' directory
into 'en' directory and add 'eth' prefix to the function's name. The
patch also encapsulates functions that are not used outside the Ethernet
driver removes redundant include files.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
When dealing with the offloads mode initialization, driver refers to
the number of VFs and add magic number one (1) to take account of the
uplink. This is not clear and will make the code less readable after
adding other vports (e.g. host PF). As these are special vports
compared to VF vports, add a helper macro to denote such special
vports and eliminate the use of magic number.
Moreover, when creating offloads flow table and groups, the driver
reserves two more slots for UC and MC miss rules. Replace this magic
number with a helper macro as well.
This patch doesn't change any functionality.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
These are two macros in the driver general header which deal with the
number of total vports and if a vport is vport manager. Such macros
are vport entities, better to place them at the vport header file.
This patch doesn't change any functionality.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Driver used to name uplink vport as FDB_UPLINK_VPORT, it's hard to
comply with the same naming convention along with the introduction of
other vports. Use MLX5_VPORT as the prefix for such vports and
relocate the uplink vport definition to public header file for the
benefits of both net and IB drivers.
This patch doesn't change any functionality.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
In Embedded CPU (EC) configurations, the EC driver needs to know when
the number of virtual functions change on the corresponding PF at the
host side. This is required so the EC driver can create or destroy
representor net devices that represent the VFs ports.
Whenever a change in the number of VFs occurs, firmware will generate an
event towards the EC which will trigger a work to complete the rest of
the handling. The specifics of the handling will be introduced in a
downstream patch.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The QUERY_HOST_PARAMS command is used by an Embedded CPU Physical
Function (ECPF) driver to identify and retrieve information about the
PF on the host side. E.g, number of virtual functions and PCI BDF.
The number of VFs can be changed on the fly, a function is added to
query current number of VFs and will be used in downstream patches.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
With the introduction of ECPF, we require that the ECPF driver will
aways call enable/disable HCA for that PF in the same way a PF does
this for its VFs. The PF is still responsible for calling enable and
disable HCA for its VFs.
To distinguish between the ECPF executing enable/disable HCA for
itself or for the PF, it sets the embedded CPU function bit in the
input params struct of these commands. When the bit is cleared and
function ID is zero, it refers to the peer PF.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Mellanox's SmartNIC combines embedded CPU(e.g, ARM) processing power
with advanced network offloads to accelerate a multitude of security,
networking and storage applications.
With the introduction of the SmartNIC, there is a new PCI function
called Embedded CPU Physical Function(ECPF). And it's possible for a
PF to get its ICM pages from the ECPF PCI function. Driver shall
identify if it is running on such a function by reading a bit in
the initialization segment.
When firmware asks for pages, it would issue a page request event
specifying how many pages it requests and for which function. That
driver responds with a manage_pages command providing the requested
pages along with an indication for which function it is providing these
pages.
The encoding before this patch was as follows:
function_id == 0: pages are requested for the function receiving
the EQE.
function_id != 0: pages are requested for VF identified by the
function_id value
A new one bit field in the EQE identifies that pages are requested for
the ECPF.
The notion of page_supplier can be introduced here and to support that,
manage pages and query pages were modified so firmware can distinguish
the following cases:
1. Function provides pages for itself
2. PF provides pages for its VF
3. ECPF provides pages to itself
4. ECPF provides pages for another function
This distinction is possible through the introduction of the bit
"embedded_cpu_function" in query_pages, manage_pages and page request
EQE.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Use u16 for vport number, which matches how hardware refers to this
argument throughout commands.
This patch doesn't change any functionality.
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Currently mlx5 driver creates xdp redirect hw queues unconditionally on
netdevice open, This is great until someone starts redirecting XDP traffic
via ndo_xdp_xmit on mlx5 device and changes the device configuration at
the same time, this might cause crashes, since the other device's napi
is not aware of the mlx5 state change (resources un-availability).
To fix this we must synchronize with other devices napi's on the system.
Added a new flag under mlx5e_priv to determine XDP TX resources are
available, set/clear it up when necessary and use synchronize_rcu()
when the flag is turned off, so other napi's are in-sync with it, before
we actually cleanup the hw resources.
The flag is tested prior to committing to transmit on mlx5e_xdp_xmit, and
it is sufficient to determine if it safe to transmit or not. The other
two internal flags (MLX5E_STATE_OPENED and MLX5E_SQ_STATE_ENABLED) become
unnecessary. Thus, they are removed from data path.
Fixes: 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Reported-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Eliminate the following compilation warning:
drivers/net/ethernet/mellanox/mlx5/core/events.c: warning: 'error_str'
may be used uninitialized in this function [-Wuninitialized]: => 238:3
Fixes: c2fb3db22d35 ("net/mlx5: Rework handling of port module events")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Mikhael Goikhman <migo@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
When EEH is injected and PCI bus stalls, mlx5's pci error detect
function is called to deactivate the command interface and tear down
the device. The issue is that there can be a thread that already
passed MLX5_DEVICE_STATE_INTERNAL_ERROR check, it will send the command
and stuck in the wait_func.
Solution:
Add function mlx5_cmd_flush to disable command interface and clear all
the pending commands. When device state is set to
MLX5_DEVICE_STATE_INTERNAL_ERROR, call mlx5_cmd_flush to ensure all
pending threads waiting for firmware commands completion are terminated.
Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
New channels are applied to the priv channels only after they
are successfully opened. Then, the indirection table should be built
according to the new number of channels.
Currently, such build is preformed independently of whether the
channels opening is successful, and is not reverted on failure.
The bug is caused due to removal of rss params from channels struct
and moving it to priv struct. That change cause to independency between
channels and rss params.
This causes a crash on a later point, when accessing rqn of a non
existing channel.
This patch fixes it by moving the indirection table build right before
switching the priv channels to new channels struct, after the new set of
channels was successfully opened.
Fixes: bbeb53b8b2c9 ("net/mlx5e: Move RSS params to a dedicated struct")
Signed-off-by: Maria Pasechnik <mariap@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Update newly introduced function to be aligned to netdev coding style.
Fixes: 46861e3e88be ("net/mlx5: Set ODP SRQ support in firmware")
Reported-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
mlx5_eq_cq_get() is called in IRQ handler, the spinlock inside
gets a lot of contentions when we test some heavy workload
with 60 RX queues and 80 CPU's, and it is clearly shown in the
flame graph.
In fact, radix_tree_lookup() is perfectly fine with RCU read lock,
we don't have to take a spinlock on this hot path. This is pretty
much similar to commit 291c566a2891
("net/mlx4_core: Fix racy CQ (Completion Queue) free"). Slow paths
are still serialized with the spinlock, and with synchronize_irq()
it should be safe to just move the fast path to RCU read lock.
This patch itself reduces the latency by about 50% for our memcached
workload on a 4.14 kernel we test. In upstream, as pointed out by Saeed,
this spinlock gets some rework in commit 02d92f790364
("net/mlx5: CQ Database per EQ"), so the difference could be smaller.
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
An ipvlan bug fix in 'net' conflicted with the abstraction away
of the IPV6 specific support in 'net-next'.
Similarly, a bug fix for mlx5 in 'net' conflicted with the flow
action conversion in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
With this patch, ndo_tx_timeout callback will be redirected to the tx
reporter in order to detect a tx timeout error and report it to the
devlink health. (The watchdog detects tx timeouts, but the driver verify
the issue still exists before launching any recover method).
In addition, recover from tx timeout in case of lost interrupt was added
to the tx reporter recover method. The tx timeout recover from lost
interrupt is not a new feature in the driver, this patch re-organize the
functionality and move it to the tx reporter recovery flow.
tx timeout example:
(with auto_recover set to false, if set to true, the manual recover and
diagnose sections are irrelevant)
$cat /sys/kernel/debug/tracing/trace
...
devlink_health_report: bus_name=pci dev_name=0000:00:09.0
driver_name=mlx5_core reporter_name=tx: TX timeout on queue: 0, SQ: 0x8a,
CQ: 0x35, SQ Cons: 0x2 SQ Prod: 0x2, usecs since last trans: 14912000
$devlink health show
pci/0000:00:09.0:
name tx
state healthy #err 1 #recover 0 last_dump_ts N/A
parameters:
grace_period 500 auto_recover false
$devlink health diagnose pci/0000:00:09.0 reporter tx -j -p
{
"SQs": [ {
"sqn": 138,
"HW state": 1,
"stopped": true
},{
"sqn": 142,
"HW state": 1,
"stopped": false
} ]
}
$devlink health diagnose pci/0000:00:09.0 reporter tx
SQs:
sqn: 138 HW state: 1 stopped: true
sqn: 142 HW state: 1 stopped: false
$devlink health recover pci/0000:00:09 reporter tx
$devlink health show
pci/0000:00:09.0:
name tx
state healthy #err 1 #recover 1 last_dump_ts N/A
parameters:
grace_period 500 auto_recover false
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add mlx5e tx reporter to devlink health reporters. This reporter will be
responsible for diagnosing, reporting and recovering of tx errors.
This patch declares the TX reporter operations and creates it using the
devlink health API. Currently, this reporter supports reporting and
recovering from send error CQE only. In addition, it adds diagnose
information for the open SQs.
For a local SQ recover (due to driver error report), in case of SQ recover
failure, the recover operation will be considered as a failure.
For a full tx recover, an attempt to close and open the channels will be
done. If this one passed successfully, it will be considered as a
successful recover.
The SQ recover from error CQE flow is not a new feature in the driver,
this patch re-organize the functions and adapt them for the devlink
health API. For this purpose, move code from en_main.c to a new file
named reporter_tx.c.
Diagnose output:
$devlink health diagnose pci/0000:00:09.0 reporter tx -j -p
{
"SQs": [ {
"sqn": 138,
"HW state": 1,
"stopped": false
},{
"sqn": 142,
"HW state": 1,
"stopped": false
} ]
}
$devlink health diagnose pci/0000:00:09.0 reporter tx
SQs:
sqn: 138 HW state: 1 stopped: false
sqn: 142 HW state: 1 stopped: false
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In some case, we may use multiple pedit actions to modify packets.
The command shown as below: the last pedit action is effective.
$ tc filter add dev netdev_rep parent ffff: protocol ip prio 1 \
flower skip_sw ip_proto icmp dst_ip 3.3.3.3 \
action pedit ex munge ip dst set 192.168.1.100 pipe \
action pedit ex munge eth src set 00:00:00:00:00:01 pipe \
action pedit ex munge eth dst set 00:00:00:00:00:02 pipe \
action csum ip pipe \
action tunnel_key set src_ip 1.1.1.100 dst_ip 1.1.1.200 dst_port 4789 id 100 \
action mirred egress redirect dev vxlan0
To fix it, we add max_mod_hdr_actions to mlx5e_tc_flow_parse_attr struction,
max_mod_hdr_actions will store the max pedit action number we support and
num_mod_hdr_actions indicates how many pedit action we used, and store all
pedit action to mod_hdr_actions.
Fixes: d79b6df6b10a ("net/mlx5e: Add parsing of TC pedit actions to HW format")
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When we offload tc filters to hardware, hardware flows can
be updated when mac of encap destination ip is changed.
But we ignore one case, that the mac of local encap ip can
be changed too, so we should also update them.
To fix it, add route_dev in mlx5e_encap_entry struct to save
the local encap netdevice, and when mac changed, kernel will
flush all the neighbour on the netdevice and send NETEVENT_NEIGH_UPDATE
event. The mlx5 driver will delete the flows and add them when neighbour
available again.
Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow")
Cc: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
mlx5e only supports SWITCHDEV_ATTR_ID_PORT_PARENT_ID, which makes it a
great candidate to be converted to use the ndo_get_port_parent_id() NDO
instead of implementing switchdev_port_attr_get().
Since mlx5e makes use of switchdev_port_parent_id() convert it to use
netdev_port_same_parent_id().
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch updates drivers to use the new flow action infrastructure.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch provides the flow_stats structure that acts as container for
tc_cls_flower_offload, then we can use to restore the statistics on the
existing TC actions. Hence, tcf_exts_stats_update() is not used from
drivers anymore.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds pedit_headers_action structure to store the result of
parsing tc pedit actions. Then, it calls alloc_tc_pedit_action() to
populate the mlx5e hardware intermediate representation once all actions
have been parsed.
This patch comes in preparation for the new flow_action infrastructure,
where each packet mangling comes in an separated action, ie. not packed
as in tc pedit.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch wraps the dissector key and mask - that flower uses to
represent the matching side - around the flow_match structure.
To avoid a follow up patch that would edit the same LoCs in the drivers,
this patch also wraps this new flow match structure around the flow rule
object. This new structure will also contain the flow actions in follow
up patches.
This introduces two new interfaces:
bool flow_rule_match_key(rule, dissector_id)
that returns true if a given matching key is set on, and:
flow_rule_match_XYZ(rule, &match);
To fetch the matching side XYZ into the match container structure, to
retrieve the key and the mask with one single call.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In packets that need to be decaped the internal headers
have to be checked, not the external ones.
Fixes: bdd66ac0aeed ("net/mlx5e: Disallow TC offloading of unsupported match/action combinations")
Signed-off-by: Guy Shattah <sguy@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The match level computed by the driver gets to be wrong for decap
rules with wildcarded inner packet match such as:
tc filter add dev vxlan_sys_4789 protocol all parent ffff: prio 2 flower
enc_dst_ip 192.168.0.9 enc_key_id 100 enc_dst_port 4789
action tunnel_key unset
action mirred egress redirect dev eth1
The FW errs for a missing matching meta-data indicator for the outer
headers (where we do have a match), and a wrong matching meta-data
indicator for the inner headers (where we don't have a match).
Fix that by taking into account the matching on the tunnel info and
relating the match level of the encapsulated packet to the firmware
inner headers indicator in case of decap.
As for vxlan we mandate a match on the tunnel udp dst port, and in general
we practically madndate a match on the source or dest ip for any IP tunnel,
the fix was done in a minimal manner around the tunnel match parsing code.
Fixes: d708f902989b ('net/mlx5e: Get the required HW match level while parsing TC flow matches')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Slava Ovsiienko <viacheslavo@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
At Innova IPsec TX offload data path a special software parser metadata
is used to pass some packet attributes to the hardware, this metadata
is passed using the Ethernet control segment of a WQE (a HW descriptor)
header.
The cited commit might nullify this header, hence the metadata is lost,
this caused a significant performance drop during hw offloading
operation.
Fix by restoring the metadata at the Ethernet control segment in case
it was nullified.
Fixes: 37fdffb217a4 ("net/mlx5: WQ, fixes for fragmented WQ buffers API")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Add the tab before '}' and keep the code style consistent.
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
To avoid compatibility issue with older kernels the firmware doesn't
allow SRQ to work with ODP unless kernel asks for it.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
|
|
Representors software stats are basic, this patch is reusing the
mlx5e_fold_sw_stats in representors, which sums up the basic stats64 for a
mlx5e netdevice.
Fixes: 8bfaf07f7806 ("net/mlx5e: Present SW stats when state is not opened")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
This behavior is already adopted for all other cases in the cited patch.
The representor's functions were missed, here we modify the them to
behave similarly.
Fixes: 8bfaf07f7806 ("net/mlx5e: Present SW stats when state is not opened")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
mlx5e_grp_sw_update_stats can be called from two threads,
1) ndo_get_stats64
2) get_ethtool_stats
For this reason and to minimize concurrency issue impact on 64bit machines
mlx5e_grp_sw_update_stats folds the software stats into a temporary
variable then copies it to the global driver stats, both ethtool and ndo
statistics callbacks will use the global software stats variable to report
whatever stats they need.
Actually ndo_get_stats64 doesn't need to fold the whole software stats
(mlx5e_grp_sw_update_stats), all it needs is five counters to fill the
rtnl_link_stats64 relevant stats parameter.
Hence this patch introduces a simpler helper function to fold software
stats for ndo_get_stats64 which will work directly on rtnl_link_stats64
stats parameter and not on the global or even temporary mlx5e_sw_stats
variable.
Since now mlx5e_grp_sw_update_stats is not called by ndo_get_stats64 we
can make it static and remove the temp var.
Unlike mlx5e_grp_sw_update_stats the new fold stats function doesn't
need to zero out the output statistics parameter since it is already
done by the stack @dev_get_stats().
This patch is fixing stack usage of mlx5e_grp_sw_update_stats on
x86 gcc-4.9 and higher, the concurrency issue between mlx5's
ndo_get_stats64 and get_ethtool_stats is resolved as well.
Fixes: 8bfaf07f7806 ("net/mlx5e: Present SW stats when state is not opened")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
We were not tracking flow tables so far, add it up.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
This confusing construction confuses the compiler which can't see
that flow is initialized if !err:
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c: In function `mlx5e_configure_flower`
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:2727:28: warning:
`flow` may be used uninitialized in this function
[-Wmaybe-uninitialized]
There is no reason for two function outputs, just return the
pointer directly and use ERR_PTR to encode a failure.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Currently we have one cpu in XPS cpumask per tx queue, this is good
enough for default configuration where there is a tx queue per cpu.
However, once configuration changes to use less tx queues, part of the
cpus are not XPS-mapped and so the select queue decision falls back to
hash calculation and balancing is not guaranteed.
Expand XPS cpumask to enable using all cpus even when number of tx
queues is smaller than number of cpus.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Only the Receive CQ makes use of these fields. Take them
out into a separate struct and save space in the generic
CQ structure.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
In the non-linear SKB memory scheme of Striding RQ, a packet header
could cross page boundary. This requires special care in fast path
that costs LoC, additional runtime instructions and branches.
It could happen when the header (up to 256B) does not fit in
a single stride. Avoid this by working with a stride size that fits
the maximum possible header. Stride is increased form 64B to 256B.
Performance:
Tested packet rate for UDP streams, single ring, on ConnectX-5.
Configuration:
Set Striding RQ and LRO ON (to enabled the non-linear SKB scheme).
GRO OFF, early drop by TC rule.
64B: 4x worse memory utilization, no page-crossers headers
- No degradation (5,887,305 pps).
- The reduction in memory utilization is compensated by the saving of
branches tests.
192B: 1.33x worse memory utilization, avoid page-crossers headers
- Before: 5,727,252. After: 5,777,037. ~1% gain.
256B: Same memory util, no page-crossers
- Before: 5,691,885. After: 5,748,007. ~1% gain.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
It turns out that libvirt uses 0-vid as a default if no vlan was
set for the guest (which is the case for switchdev mode) and errs
if we disallow that:
error: Failed to start domain vm75
error: Cannot set interface MAC/vlanid to 6a:66:2d:48:92:c2/0 \
for ifname enp59s0f0 vf 0: Operation not supported
So allow this in order not to break existing systems.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Maor Dickman <maord@mellanox.com>
Reviewed-by: Gavi Teitz <gavi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
With VF LAG commit 491c37e49b48 "net/mlx5e: In case of LAG, one switch
parent id is used for all representors", both uplinks and all the VFs
(on both of them) get the same switchdev id.
This cause the provisioning system method to identify the rep of a given
VF from the parent PF PCI device using switchev id and physical port
name to break, since VFm of PF0 will have the (id, name) as VFm of PF1.
To fix that, we align to use the framework agreed upstream and set by
nfp commit 168c478e107e "nfp: wire get_phys_port_name on representors":
$ cat /sys/class/net/eth4_*/phys_port_name
p0
pf0vf0
pf0vf1
Now, the names will be different, e.g. pf0vf0 vs. pf1vf0.
Fixes: 491c37e49b48 ("net/mlx5e: In case of LAG, one switch parent id is used for all representors")
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Waleed Musa <waleedm@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Prior to this patch the driver prohibited spoof checking on invalid MAC.
Now the user can set this configuration if it wishes to.
This is required since libvirt might invalidate the VF Mac by setting it
to zero, while spoofcheck is ON.
Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The lock in qp_table might be taken from process context or from
interrupt context. This may lead to a deadlock unless it is taken with
IRQs disabled.
Discovered by lockdep
================================
WARNING: inconsistent lock state
4.20.0-rc6
--------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W}
python/12572 [HC1[1]:SC0[0]:HE0:SE1] takes:
00000000052a4df4 (&(&table->lock)->rlock#2){?.+.}, /0x50 [mlx5_core]
{HARDIRQ-ON-W} state was registered at:
_raw_spin_lock+0x33/0x70
mlx5_get_rsc+0x1a/0x50 [mlx5_core]
mlx5_ib_eqe_pf_action+0x493/0x1be0 [mlx5_ib]
process_one_work+0x90c/0x1820
worker_thread+0x87/0xbb0
kthread+0x320/0x3e0
ret_from_fork+0x24/0x30
irq event stamp: 103928
hardirqs last enabled at (103927): [] nk+0x1a/0x1c
hardirqs last disabled at (103928): [] unk+0x1a/0x1c
softirqs last enabled at (103924): [] tcp_sendmsg+0x31/0x40
softirqs last disabled at (103922): [] 80
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&table->lock)->rlock#2);
lock(&(&table->lock)->rlock#2);
*** DEADLOCK ***
Fixes: 032080ab43ac ("IB/mlx5: Lock QP during page fault handling")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
Bodong Wang
Saeed Mahameed
David S. Miller
Aya Levin
Tariq Toukan
Huy Nguyen
Maria Pasechnik
Leon Romanovsky
Cong Wang
Eran Ben Elisha
Tonghao Zhang
Florian Fainelli
Pablo Neira Ayuso
Guy Shattah
Or Gerlitz
Raed Salem
Moni Shoua
Jason Gunthorpe
Moshe Shemesh