There is a performance issue when the number of VSIs are not multiple
of 8. This is caused due to the max children limitation per node(8) in
9 layer topology. The BW credits are shared evenly among the children
by default. Assume one node has 8 children and the other has 1.
The parent of these nodes share the BW credit equally among them.
Apparently this causes a problem for the first node which has 8 children.
The 9th VM get more BW credits than the first 8 VMs.
Example:
1) With 8 VM's:
for x in 0 1 2 3 4 5 6 7;
do taskset -c ${x} netperf -P0 -H 172.68.169.125 & sleep .1 ; done
tx_queue_0_packets: 23283027
tx_queue_1_packets: 23292289
tx_queue_2_packets: 23276136
tx_queue_3_packets: 23279828
tx_queue_4_packets: 23279828
tx_queue_5_packets: 23279333
tx_queue_6_packets: 23277745
tx_queue_7_packets: 23279950
tx_queue_8_packets: 0
2) With 9 VM's:
for x in 0 1 2 3 4 5 6 7 8;
do taskset -c ${x} netperf -P0 -H 172.68.169.125 & sleep .1 ; done
tx_queue_0_packets: 24163396
tx_queue_1_packets: 24164623
tx_queue_2_packets: 24163188
tx_queue_3_packets: 24163701
tx_queue_4_packets: 24163683
tx_queue_5_packets: 24164668
tx_queue_6_packets: 23327200
tx_queue_7_packets: 24163853
tx_queue_8_packets: 91101417
So on average queue 8 statistics show that 3.7 times more packets were
send there than to the other queues.
The FW starting with version 3.20, has increased the max number of
children per node by reducing the number of layers from 9 to 5. Reflect
this on driver side.
Signed-off-by: Raj Victor <victor.raj@intel.com>
Co-developed-by: Michal Wilczynski <michal.wilczynski@intel.com>
Signed-off-by: Michal Wilczynski <michal.wilczynski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Extend devlink_param *set function pointer to take extack as a param.
Sometimes it is needed to pass information to the end user from set
function. It is more proper to use for that netlink instead of passing
message to dmesg.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
During error recovery, such as AER fatal error slot reset, we call
bnxt_try_map_fw_health_reg() to try to get access to the health
register to determine the firmware state. Fix
bnxt_try_map_fw_health_reg() to recognize the P7 chip correctly
and set up the health register.
This fixes this type of AER slot reset failure:
bnxt_en 0000:04:00.0: AER: PCIe Bus Error: severity=Uncorrectable (Fatal), type=Inaccessible, (Unregistered Agent ID)
bnxt_en 0000:04:00.0 enp4s0f0np0: PCI I/O error detected
bnxt_en 0000:04:00.0 bnxt_re0: Handle device suspend call
bnxt_en 0000:04:00.1 enp4s0f1np1: PCI I/O error detected
bnxt_en 0000:04:00.1 bnxt_re1: Handle device suspend call
pcieport 0000:00:02.0: AER: Root Port link has been reset (0)
bnxt_en 0000:04:00.0 enp4s0f0np0: PCI Slot Reset
bnxt_en 0000:04:00.0: enabling device (0000 -> 0002)
bnxt_en 0000:04:00.0: Firmware not ready
bnxt_en 0000:04:00.1 enp4s0f1np1: PCI Slot Reset
bnxt_en 0000:04:00.1: enabling device (0000 -> 0002)
bnxt_en 0000:04:00.1: Firmware not ready
pcieport 0000:00:02.0: AER: device recovery failed
Fixes: a432a45bdb ("bnxt_en: Define basic P7 macros")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We do not support two simultaneous recoveries so check for reset
flag, BNXT_STATE_IN_FW_RESET, and do not proceed with AER further.
When the pci channel state is pci_channel_io_frozen, the PCIe link
can not be trusted so we disable the traffic immediately and stop
BAR access by calling bnxt_fw_fatal_close(). BAR access after
AER fatal error can cause an NMI.
Fixes: f75d9a0aa9 ("bnxt_en: Re-write PCI BARs after PCI fatal error.")
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce bnxt_fw_fatal_close() API which can be used
to stop data path and disable device when firmware
is in fatal state.
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support offloading of skbedit mark action.
For example, to mark with 0x0008, with dest ip 60.60.60.2 on eth2
interface:
# tc qdisc add dev eth2 ingress
# tc filter add dev eth2 ingress protocol ip flower \
dst_ip 60.60.60.2 action skbedit mark 0x0008 skip_sw
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver queries the Management Capabilities Mask (MCAM) register
during initialization to understand if it can read up to 128 bytes from
transceiver modules.
However, not all firmware versions support this register, leading to the
driver failing to load.
Fix by treating an error in the register query as an indication that the
feature is not supported.
Fixes: 1f4aea1f72 ("mlxsw: core_env: Read transceiver module EEPROM in 128 bytes chunks")
Reported-by: Tim 'mithro' Ansell <me@mith.ro>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/0afa8b2e8bac178f5f88211344429176dcc72281.1713446092.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The device's manual (PRM - Programmer's Reference Manual) classifies the
trap that is used to deliver EMAD responses as an "event trap". Among
other things, it means that the only actions that can be associated with
the trap are TRAP and FORWARD (NOP).
Currently, during driver de-initialization the driver unregisters the
trap by setting its action to DISCARD, which violates the above
guideline. Future firmware versions will prevent such misuses by
returning an error. This does not prevent the driver from working, but
an error will be printed to the kernel log during module removal /
devlink reload:
mlxsw_spectrum 0000:03:00.0: Reg cmd access status failed (status=7(bad parameter))
mlxsw_spectrum 0000:03:00.0: Reg cmd access failed (reg_id=7003(hpkt),type=write)
Suppress the error message by aligning the driver to the manual and use
a FORWARD (NOP) action when unregistering the trap.
Fixes: 4ec14b7634 ("mlxsw: Add interface to access registers and process events")
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/753a89e14008fde08cb4a2c1e5f537b81d8eb2d6.1713446092.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
driver needs queue msix vectors and one misc irq vector,
but only queue vectors need irq affinity.
when num_online_cpus is less than chip max msix vectors,
driver will acquire (num_online_cpus + 1) vecotrs, and
call pci_alloc_irq_vectors_affinity functions with affinity
params without setting pre_vectors or post_vectors, it will
cause return error code -ENOSPC.
Misc irq vector is vector 0, driver need to set affinity params
.pre_vectors = 1.
Fixes: 3f70318611 ("net: libwx: Add irq flow functions")
Signed-off-by: Duanqiang Wen <duanqiangwen@net-swift.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The qpl_cfg struct was used to make sure that no two different queues
are using QPL with the same qpl_id. We can remove that qpl_cfg struct
since now the qpl_ids map with the queues respectively as follows:
For tx queues: qpl_id = tx_qid
For rx queues: qpl_id = max_tx_queues + rx_qid
And when XDP is used, it will need the user to reduce the tx queues to
be at most half of the max_tx_queues. Then it will use the same number
of tx queues starting from the end of existing tx queues for XDP. So the
XDP queues will not exceed the max_tx_queues range and will not overlap
with the rx queues, where the qpl_ids will not have overlapping too.
Considering of that, we remove the qpl_cfg struct to get the qpl_id
directly based on the queue id. Unless we are erroneously allocating a
rx/tx queue that has already been allocated, we would never allocate
the qpl with the same qpl_id twice. In that case, it should fail much
earlier than the QPL assignment.
Suggested-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Ziwei Xiao <ziweixiao@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Shailend Chand <shailend@google.com>
Link: https://lore.kernel.org/r/20240417205757.778551-1-ziweixiao@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2024-04-17 (ice)
This series contains updates to ice driver only.
Marcin adds Tx malicious driver detection (MDD) events to be included as
part of mdd-auto-reset-vf.
Dariusz removes unnecessary implementation of ndo_get_phys_port_name.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
ice: Remove ndo_get_phys_port_name
ice: Add automatic VF reset on Tx MDD events
====================
Link: https://lore.kernel.org/r/20240417165634.2081793-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This driver currently doesn't support any control flags.
Use flow_rule_match_has_control_flags() to check for control flags,
such as can be set through `tc flower ... ip_flags frag`.
In case any control flags are masked, flow_rule_match_has_control_flags()
sets a NL extended error message, and we return -EOPNOTSUPP.
Only compile-tested.
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Link: https://lore.kernel.org/r/20240417144359.104225-1-ast@fiberby.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This driver currently doesn't support any control flags.
Use flow_rule_has_control_flags() to check for control flags,
such as can be set through `tc flower ... ip_flags frag`.
In case any control flags are masked, flow_rule_has_control_flags()
sets a NL extended error message, and we return -EOPNOTSUPP.
Only compile-tested.
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/20240417135131.99921-1-ast@fiberby.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The TX and RX DMA Channels used by the driver to exchange data with CPSW
are not guaranteed to be in a clean state during driver initialization.
The Bootloader could have used the same DMA Channels without cleaning them
up in the event of failure. Thus, reset and disable the DMA Channels to
ensure that they are in a clean state before using them.
Fixes: 93a7653031 ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Reported-by: Schuyler Patton <spatton@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20240417095425.2253876-1-s-vadapalli@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In ibmvnic_xmit() if ibmvnic_tx_scrq_flush() returns H_CLOSED then
it will inform upper level networking functions to disable tx
queues. H_CLOSED signals that the connection with the vnic server is
down and a transport event is expected to recover the device.
Previously, ibmvnic_tx_scrq_flush() was hard-coded to return success.
Therefore, the queues would remain active until ibmvnic_cleanup() is
called within do_reset().
The problem is that do_reset() depends on the RTNL lock. If several
ibmvnic devices are resetting then there can be a long wait time until
the last device can grab the lock. During this time the tx/rx queues
still appear active to upper level functions.
FYI, we do make a call to netif_carrier_off() outside the RTNL lock but
its calls to dev_deactivate() are also dependent on the RTNL lock.
As a result, large amounts of retransmissions were observed in a short
period of time, eventually leading to ETIMEOUT. This was specifically
seen with HNV devices, likely because of even more RTNL dependencies.
Therefore, ensure the return code of ibmvnic_tx_scrq_flush() is
propagated to the xmit function to allow for an earlier (and lock-less)
response to a transport event.
Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://lore.kernel.org/r/20240416164128.387920-1-nnac123@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The RX byte accounting for jumbo packets was changed to fix a potential
use-after-free bug. However, that fix used the wrong variable and so
only accounted for the number of bytes in the final descriptor, not the
number of bytes in the whole packet.
To fix this, we can simply update our stats with the correct number of
bytes before calling napi_gro_receive().
Also rename pkt_len to desc_len in ravb_rx_gbeth() to avoid any future
confusion. The variable name pkt_len is correct in ravb_rx_rcar() as
that function does not handle packets spanning multiple descriptors.
Fixes: 5a5a3e564d ("ravb: Fix potential use-after-free in ravb_rx_gbeth()")
Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Sending a 7kB ping packet to the RZ/G2L in v6.9-rc2 causes the following
backtrace:
WARNING: CPU: 0 PID: 0 at include/linux/skbuff.h:3127 skb_trim+0x30/0x38
Hardware name: Renesas SMARC EVK based on r9a07g044l2 (DT)
pc : skb_trim+0x30/0x38
lr : ravb_rx_csum_gbeth+0x40/0x90
Call trace:
skb_trim+0x30/0x38
ravb_rx_gbeth+0x56c/0x5cc
ravb_poll+0xa0/0x204
__napi_poll+0x38/0x17c
This is caused by ravb_rx_gbeth() calling ravb_rx_csum_gbeth() with the
wrong skb for a packet which spans multiple descriptors. To fix this,
use the correct skb.
Fixes: c2da940857 ("ravb: Add Rx checksum offload support for GbEth")
Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The RX loops in ravb_rx_gbeth() and ravb_rx_rcar() skip to the next loop
iteration if a zero-length descriptor is seen (indicating a DMA mapping
error). However, the current RX descriptor index `priv->cur_rx[q]` was
incremented at the end of the loop and so would not be incremented when
we skip to the next loop iteration. This would cause the loop to keep
seeing the same zero-length descriptor instead of moving on to the next
descriptor.
As the loop counter `i` still increments, the loop would eventually
terminate so there is no risk of being stuck here forever - but we
should still fix this to avoid wasting cycles.
To fix this, the RX descriptor index is incremented at the top of the
loop, in the for statement itself. The assignments of `entry` and `desc`
are brought into the loop to avoid the need for duplication.
Fixes: d8b48911fd ("ravb: fix ring memory allocation")
Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The units of "work done" in the RX path should be packets instead of
descriptors.
Descriptors which are used by the hardware to record error conditions or
are empty in the case of a DMA mapping error should not count towards
our RX work budget.
Also make the limit variable unsigned as it can never be negative.
Fixes: c156633f13 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The WLAN + WED reset sequence relies on being able to receive interrupts from
the card, in order to synchronize individual steps with the firmware.
When WED is stopped, leave interrupts running and rely on the driver turning
off unwanted ones.
WED DMA also needs to be disabled before resetting.
Fixes: f78cd9c783 ("net: ethernet: mtk_wed: update mtk_wed_stop")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20240416082330.82564-1-nbd@nbd.name
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In cases when VF sends malformed packets that are classified as malicious,
it can cause Tx queue to freeze as a result of Malicious Driver Detection
event. Such malformed packets can appear as a result of a faulty userspace
app running on VF. This frozen queue can be stuck for several minutes being
unusable.
User might prefer to immediately bring the VF back to operational state
after such event, which can be done by automatically resetting the VF which
caused MDD. This is already implemented for Rx events (mdd-auto-reset-vf
flag private flag needs to be set).
Extend the VF auto reset to also cover Tx MDD events. When any MDD event
occurs on VF (Tx or Rx) and the mdd-auto-reset-vf private flag is set,
perform a graceful VF reset to quickly bring it back to operational state.
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Co-developed-by: Liang-Min Wang <liang-min.wang@intel.com>
Signed-off-by: Liang-Min Wang <liang-min.wang@intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Add missing FLOW_DISSECTOR_KEY_ENC_* checks to TC flower filter parsing.
Without these checks, it would be possible to add filters with tunnel
options on non-tunnel devices. enc_* options are only valid for tunnel
devices.
Example:
devlink dev eswitch set $PF1_PCI mode switchdev
echo 1 > /sys/class/net/$PF1/device/sriov_numvfs
tc qdisc add dev $VF1_PR ingress
ethtool -K $PF1 hw-tc-offload on
tc filter add dev $VF1_PR ingress flower enc_ttl 12 skip_sw action drop
Fixes: 9e300987d4 ("ice: VXLAN and Geneve TC support")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The check for flags is done to not pass empty lookups to adding switch
rule functions. Since metadata is always added to lookups there is no
need to check against the flag.
It is also fixing the problem with such rule:
$ tc filter add dev gtp_dev ingress protocol ip prio 0 flower \
enc_dst_port 2123 action drop
Switch block in case of GTP can't parse the destination port, because it
should always be set to GTP specific value. The same with ethertype. The
result is that there is no other matching criteria than GTP tunnel. In
this case flags is 0, rule can't be added only because of defensive
check against flags.
Fixes: 9a225f81f5 ("ice: Support GTP-U and GTP-C offload in switchdev")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In case of traffic going from the VF (so ingress for port representor)
source VSI should be consider during packet classification. It is
needed for hardware to not match packets from different ports with
filters added on other port.
It is only for "from VF" traffic, because other traffic direction
doesn't have source VSI.
Set correct ::src_vsi in rule_info to pass it to the hardware filter.
For example this rule should drop only ipv4 packets from eth10, not from
the others VF PRs. It is needed to check source VSI in this case.
$tc filter add dev eth10 ingress protocol ip flower skip_sw action drop
Fixes: 0d08a441fb ("ice: ndo_setup_tc implementation for PF")
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Here is the list of the MAC capabilities specific to the particular DW MAC
IP-cores currently supported by the driver:
DW MAC100: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10 | MAC_100
DW GMAC: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10 | MAC_100 | MAC_1000
Allwinner sun8i MAC: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10 | MAC_100 | MAC_1000
DW QoS Eth: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD
if there is more than 1 active Tx/Rx queues:
MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10FD | MAC_100FD | MAC_1000FD | MAC_2500FD
DW XGMAC: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_1000FD | MAC_2500FD | MAC_5000FD | MAC_10000FD
DW XLGMAC: MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_1000FD | MAC_2500FD | MAC_5000FD | MAC_10000FD |
MAC_25000FD | MAC_40000FD | MAC_50000FD | MAC_100000FD
As you can see there are only two common capabilities:
MAC_ASYM_PAUSE | MAC_SYM_PAUSE.
Meanwhile what is currently implemented defines 10/100/1000 link speeds
for all IP-cores, which is definitely incorrect for DW MAC100, DW XGMAC
and DW XLGMAC devices.
Seeing the flow-control is implemented as a callback for each MAC IP-core
(see dwmac100_flow_ctrl(), dwmac1000_flow_ctrl(), sun8i_dwmac_flow_ctrl(),
etc) and since the MAC-specific setup() method is supposed to be called
for each available DW MAC-based device, the capabilities initialization
can be freely moved to these setup() functions, thus correctly setting up
the MAC-capabilities for each IP-core (including the Allwinner Sun8i). A
new stmmac_link::caps field was specifically introduced for that so to
have all link-specific info preserved in a single structure.
Note the suggested change fixes three earlier commits at a time. The
commit 5b0d7d7da6 ("net: stmmac: Add the missing speeds that XGMAC
supports") permitted the 10-100 link speeds and 1G half-duplex mode for DW
XGMAC IP-core even though it doesn't support them. The commit df7699c70c
("net: stmmac: Do not cut down 1G modes") incorrectly added the MAC1000
capability to the DW MAC100 IP-core. Similarly to the DW XGMAC the commit
8a880936e9 ("net: stmmac: Add XLGMII support") incorrectly permitted the
10-100 link speeds and 1G half-duplex mode for DW XLGMAC IP-core.
Fixes: 5b0d7d7da6 ("net: stmmac: Add the missing speeds that XGMAC supports")
Fixes: df7699c70c ("net: stmmac: Do not cut down 1G modes")
Fixes: 8a880936e9 ("net: stmmac: Add XLGMII support")
Suggested-by: Russell King (Oracle) <linux@armlinux.org.uk>
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Romain Gantois <romain.gantois@bootlin.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
It's possible to have the maximum link speed being artificially limited on
the platform-specific basis. It's done either by setting up the
plat_stmmacenet_data::max_speed field or by specifying the "max-speed"
DT-property. In such cases it's required that any specific
MAC-capabilities re-initializations would take the limit into account. In
particular the link speed capabilities may change during the number of
active Tx/Rx queues re-initialization. But the currently implemented
procedure doesn't take the speed limit into account.
Fix that by calling phylink_limit_mac_speed() in the
stmmac_reinit_queues() method if the speed limitation was required in the
same way as it's done in the stmmac_phy_setup() function.
Fixes: 95201f36f3 ("net: stmmac: update MAC capabilities when tx queues are updated")
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Romain Gantois <romain.gantois@bootlin.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
There are three DW MAC IP-cores which can have the multiple Tx/Rx queues
enabled:
DW GMAC v3.7+ with AV feature,
DW QoS Eth v4.x/v5.x,
DW XGMAC/XLGMAC
Based on the respective HW databooks, only the DW QoS Eth IP-core doesn't
support the half-duplex link mode in case if more than one queues enabled:
"In multiple queue/channel configurations, for half-duplex operation,
enable only the Q0/CH0 on Tx and Rx. For single queue/channel in
full-duplex operation, any queue/channel can be enabled."
The rest of the IP-cores don't have such constraint. Thus in order to have
the constraint applied for the DW QoS Eth MACs only, let's move the it'
implementation to the respective MAC-capabilities getter and make sure the
getter is called in the queues re-init procedure.
Fixes: b6cfffa7ad ("stmmac: fix DMA channel hang in half-duplex mode")
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Romain Gantois <romain.gantois@bootlin.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tony Nguyen says:
====================
This series contains updates to ice driver only.
Lukasz removes unnecessary argument from ice_fdir_comp_rules().
Jakub adds support for ethtool 'ether' flow-type rules.
Jake moves setting of VF MSI-X value to initialization function and adds
tracking of VF relative MSI-X index.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
ice: store VF relative MSI-X index in q_vector->vf_reg_idx
ice: set vf->num_msix in ice_initialize_vf_entry()
ice: Implement 'flow-type ether' rules
ice: Remove unnecessary argument from ice_fdir_comp_rules()
====================
Link: https://lore.kernel.org/r/20240412210534.916756-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This patch adds XDP (eXpress Data Path) support to TI AM65 CPSW
Ethernet driver. The following features are implemented:
- NETDEV_XDP_ACT_BASIC (XDP_PASS, XDP_TX, XDP_DROP, XDP_ABORTED)
- NETDEV_XDP_ACT_REDIRECT (XDP_REDIRECT)
- NETDEV_XDP_ACT_NDO_XMIT (ndo_xdp_xmit callback)
The page pool memory model is used to get better performance.
Below are benchmark results obtained for the receiver with iperf3 default
parameters:
- Without page pool: 495 Mbits/sec
- With page pool: 605 Mbits/sec (actually 610 Mbits/sec, with a 5 Mbits/sec
loss due to extra processing in the hot path to handle XDP).
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces a member and the related accessors which can be
used to store descriptor specific additional information. This member
can store, for instance, an ID to differentiate a skb TX buffer type
from a xdpf TX buffer type.
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds accessors for desc_size and cpumem members. They may be
used, for instance, to compute a descriptor index.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Upon reviewing the flower control flags handling in
this driver, I notice that the key wasn't being used,
only the mask.
Ie. `tc flower ... ip_flags nofrag` was hardware
offloaded as `... ip_flags frag`.
Only compile tested, no access to HW.
Fixes: c672e37279 ("octeontx2-pf: Add support to filter packet based on IP fragment")
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
gve has supported software timestamp generation since its inception,
but has not advertised that support via ethtool. This patch correctly
advertises that support.
Signed-off-by: John Fraker <jfraker@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add check for unsupported control flags.
Only compile-tested, no access to HW.
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use flow_rule_is_supp_control_flags()
Check the mask, not the key, for unsupported control flags.
Only compile-tested, no access to HW
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When disabling aRFS under the `priv->state_lock`, any scheduled
aRFS works are canceled using the `cancel_work_sync` function,
which waits for the work to end if it has already started.
However, while waiting for the work handler, the handler will
try to acquire the `state_lock` which is already acquired.
The worker acquires the lock to delete the rules if the state
is down, which is not the worker's responsibility since
disabling aRFS deletes the rules.
Add an aRFS state variable, which indicates whether the aRFS is
enabled and prevent adding rules when the aRFS is disabled.
Kernel log:
======================================================
WARNING: possible circular locking dependency detected
6.7.0-rc4_net_next_mlx5_5483eb2 #1 Tainted: G I
------------------------------------------------------
ethtool/386089 is trying to acquire lock:
ffff88810f21ce68 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}, at: __flush_work+0x74/0x4e0
but task is already holding lock:
ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core]
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&priv->state_lock){+.+.}-{3:3}:
__mutex_lock+0x80/0xc90
arfs_handle_work+0x4b/0x3b0 [mlx5_core]
process_one_work+0x1dc/0x4a0
worker_thread+0x1bf/0x3c0
kthread+0xd7/0x100
ret_from_fork+0x2d/0x50
ret_from_fork_asm+0x11/0x20
-> #0 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}:
__lock_acquire+0x17b4/0x2c80
lock_acquire+0xd0/0x2b0
__flush_work+0x7a/0x4e0
__cancel_work_timer+0x131/0x1c0
arfs_del_rules+0x143/0x1e0 [mlx5_core]
mlx5e_arfs_disable+0x1b/0x30 [mlx5_core]
mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core]
ethnl_set_channels+0x28f/0x3b0
ethnl_default_set_doit+0xec/0x240
genl_family_rcv_msg_doit+0xd0/0x120
genl_rcv_msg+0x188/0x2c0
netlink_rcv_skb+0x54/0x100
genl_rcv+0x24/0x40
netlink_unicast+0x1a1/0x270
netlink_sendmsg+0x214/0x460
__sock_sendmsg+0x38/0x60
__sys_sendto+0x113/0x170
__x64_sys_sendto+0x20/0x30
do_syscall_64+0x40/0xe0
entry_SYSCALL_64_after_hwframe+0x46/0x4e
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&priv->state_lock);
lock((work_completion)(&rule->arfs_work));
lock(&priv->state_lock);
lock((work_completion)(&rule->arfs_work));
*** DEADLOCK ***
3 locks held by ethtool/386089:
#0: ffffffff82ea7210 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40
#1: ffffffff82e94c88 (rtnl_mutex){+.+.}-{3:3}, at: ethnl_default_set_doit+0xd3/0x240
#2: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core]
stack backtrace:
CPU: 15 PID: 386089 Comm: ethtool Tainted: G I 6.7.0-rc4_net_next_mlx5_5483eb2 #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x60/0xa0
check_noncircular+0x144/0x160
__lock_acquire+0x17b4/0x2c80
lock_acquire+0xd0/0x2b0
? __flush_work+0x74/0x4e0
? save_trace+0x3e/0x360
? __flush_work+0x74/0x4e0
__flush_work+0x7a/0x4e0
? __flush_work+0x74/0x4e0
? __lock_acquire+0xa78/0x2c80
? lock_acquire+0xd0/0x2b0
? mark_held_locks+0x49/0x70
__cancel_work_timer+0x131/0x1c0
? mark_held_locks+0x49/0x70
arfs_del_rules+0x143/0x1e0 [mlx5_core]
mlx5e_arfs_disable+0x1b/0x30 [mlx5_core]
mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core]
ethnl_set_channels+0x28f/0x3b0
ethnl_default_set_doit+0xec/0x240
genl_family_rcv_msg_doit+0xd0/0x120
genl_rcv_msg+0x188/0x2c0
? ethnl_ops_begin+0xb0/0xb0
? genl_family_rcv_msg_dumpit+0xf0/0xf0
netlink_rcv_skb+0x54/0x100
genl_rcv+0x24/0x40
netlink_unicast+0x1a1/0x270
netlink_sendmsg+0x214/0x460
__sock_sendmsg+0x38/0x60
__sys_sendto+0x113/0x170
? do_user_addr_fault+0x53f/0x8f0
__x64_sys_sendto+0x20/0x30
do_syscall_64+0x40/0xe0
entry_SYSCALL_64_after_hwframe+0x46/0x4e
</TASK>
Fixes: 45bf454ae8 ("net/mlx5e: Enabling aRFS mechanism")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240411115444.374475-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Channels can potentially have independent mdev instances. Do not refer to
the global mdev instance in the mlx5e_priv instance for channel FW
operations related to coalescing. CQ numbers that would be valid on the
channel's mdev instance may not be correctly referenced if using the
mlx5e_priv instance.
Fixes: 67936e1385 ("net/mlx5e: Let channels be SD-aware")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240411115444.374475-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The cited patch introduces the concept of buckets in LAG in hash mode.
However, the patch doesn't clear the number of buckets in the LAG
deactivation. This results in using the wrong number of buckets in
case user create a hash mode LAG and afterwards create a non-hash
mode LAG.
Hence, restore buckets number to default after hash mode LAG
deactivation.
Fixes: 352899f384 ("net/mlx5: Lag, use buckets in hash mode")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240411115444.374475-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
I noticed that only 3 out of the 4 input bits were used,
mt.key->flags & FLOW_DIS_IS_FRAGMENT was never checked.
In order to avoid a complicated maze, I converted it to
use a 16 byte mapping table.
As shown in the table below the old heuristics doesn't
always do the right thing, ie. when FLOW_DIS_IS_FRAGMENT=1/1
then it used to only match follow-up fragment packets.
Here are all the combinations, and their resulting new/old
VCAP key/mask filter:
/- FLOW_DIS_IS_FRAGMENT (key/mask)
| /- FLOW_DIS_FIRST_FRAG (key/mask)
| | /-- new VCAP fragment (key/mask)
v v v v- old VCAP fragment (key/mask)
0/0 0/0 -/- -/- impossible (due to entry cond. on mask)
0/0 0/1 -/- 0/3 !! invalid (can't match non-fragment + follow-up frag)
0/0 1/0 -/- -/- impossible (key > mask)
0/0 1/1 1/3 1/3 first fragment
0/1 0/0 0/3 3/3 !! not fragmented
0/1 0/1 0/3 3/3 !! not fragmented (+ not first fragment)
0/1 1/0 -/- -/- impossible (key > mask)
0/1 1/1 -/- 1/3 !! invalid (non-fragment and first frag)
1/0 0/0 -/- -/- impossible (key > mask)
1/0 0/1 -/- -/- impossible (key > mask)
1/0 1/0 -/- -/- impossible (key > mask)
1/0 1/1 -/- -/- impossible (key > mask)
1/1 0/0 1/1 3/3 !! some fragment
1/1 0/1 3/3 3/3 follow-up fragment
1/1 1/0 -/- -/- impossible (key > mask)
1/1 1/1 1/3 1/3 first fragment
In the datasheet the VCAP fragment values are documented as:
0 = no fragment
1 = initial fragment
2 = suspicious fragment
3 = valid follow-up fragment
Result: 3 combinations match the old behavior,
3 combinations have been corrected,
2 combinations are now invalid, and fail,
8 combinations are impossible.
It should now be aligned with how FLOW_DIS_IS_FRAGMENT
and FLOW_DIS_FIRST_FRAG is set in __skb_flow_dissect() in
net/core/flow_dissector.c
Since the VCAP fragment values are not a bitfield, we have
to ignore the suspicious fragment value, eg. when matching
on any kind of fragment with FLOW_DIS_IS_FRAGMENT=1/1.
Only compile tested, and logic tested in userspace, as I
unfortunately don't have access to this switch chip (yet).
Fixes: d6c2964db3 ("net: microchip: sparx5: Adding more tc flower keys for the IS2 VCAP")
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Tested-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240411111321.114095-1-ast@fiberby.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
