Chained descriptors for fragments need to duplicate all the descriptor
fields of the skb head, so we copy the descriptor and then modify the
relevant fields. This is wasteful, because the top half of the descriptor
will get overwritten entirely while the bottom half is not modified at all.
Copy only the bottom half. This saves us 0.3% of CPU in a GSO test.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For flow offload adds, if the rhash insert code fails, the flow will still
have been offloaded but the reference to it in the driver freed.
Re-order the offload setup calls to ensure that a flow will only be written
to FW if a kernel reference is held and stored in the rhashtable. Remove
this hashtable entry if the offload fails.
Fixes: c01d0efa51 ("nfp: flower: use rhashtable for flow caching")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Calling nfp_compile_flow_metadata both assigns a stats context and
increments a ref counter on (or allocates) a mask id table entry. These
are released by the nfp_modify_flow_metadata call on flow deletion,
however, if a flow add fails after metadata is set then the flow entry
will be deleted but the metadata assignments leaked.
Add an error path to the flow add offload function to ensure allocated
metadata is released in the event of an offload fail.
Fixes: 81f3ddf254 ("nfp: add control message passing capabilities to flower offloads")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously when unbinding a slave the 802.3ad implementation only told
partner that the port is not suitable for aggregation by setting the port
aggregation state from aggregatable to individual. This is not enough. If the
physical layer still stays up and we only unbinded this port from the bond there
is nothing in the aggregation status alone to prevent the partner from sending
traffic towards us. To ensure that the partner doesn't consider this
port at all anymore we should also disable collecting and distributing to
signal that this actor is going away. Also clear AD_STATE_SYNCHRONIZATION to
ensure partner exits collecting + distributing state.
I have tested this behaviour againts Arista EOS switches with mlx5 cards
(physical link stays up even when interface is down) and simulated
the same situation virtually Linux <-> Linux with two network namespaces
running two veth device pairs. In both cases setting aggregation to
individual doesn't alone prevent traffic from being to sent towards this
port given that the link stays up in partners end. Partner still keeps
it's end in collecting + distributing state and continues until timeout is
reached. In most cases this means we are losing the traffic partner sends
towards our port while we wait for timeout. This is most visible with slow
periodic time (LACP rate slow).
Other open source implementations like Open VSwitch and libreswitch, and
vendor implementations like Arista EOS, seem to disable collecting +
distributing to when doing similar port disabling/detaching/removing change.
With this patch kernel implementation would behave the same way and ensure
partner doesn't consider our actor viable anymore.
Signed-off-by: Toni Peltonen <peltzi@peltzi.fi>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Acked-by: Jonathan Toppins <jtoppins@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The last set of csum offload fixes had a leak:
Checksum enabled status bits from rx descriptor were incorrectly
interpreted. Consequently all the other valid logic worked on zero bits.
That caused rx checksum offloads never to trigger.
Tested by dumping rx descriptors and validating resulting csum_level.
Reported-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Fixes: ad703c2b91 ("net: aquantia: invalid checksumm offload implementation")
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a spelling mistake in the oct_stats_strings array, fix it.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Setting up and tearing down debugfs is current unbalanced, as seen by
this error during resume from suspend:
[ 752.134067] dwc-eth-dwmac 2490000.ethernet eth0: ERROR failed to create debugfs directory
[ 752.134347] dwc-eth-dwmac 2490000.ethernet eth0: stmmac_hw_setup: failed debugFS registration
The imbalance happens because the driver creates the debugfs hierarchy
when the device is opened and tears it down when the device is closed.
There's little gain in that, and it could be argued that it is even
surprising because it's not usually done for other devices. Fix the
imbalance by moving the debugfs creation and teardown to the driver's
->probe() and ->remove() implementations instead.
Note that the ring descriptors cannot be read while the interface is
down, so make sure to return an empty file when the descriptors_status
debugfs file is read.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Acked-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Total number of VFs supported by PF is used to determine the last
byte of VF's mac address. Number of VFs supported is not always
16, use the variable nvfs to get the number of VFs supported
rather than hard coding it to 16.
Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If there are still pending packets in the tx queue when removing a station,
it could possibly lead to a call to further attempts to pull packets from
the mac80211 tx queue after it has already been removed from the scheduling
list.
Prevent this from happening by calling synchronize_rcu after deleting the
wcid pointer before further cleaning up the tx queues.
To be extra careful, ensure that mtxq->list is always initialized properly.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
There is some code in the mac80211 tx status processing code that could
potentially call back into the tx codepath.
To avoid deadlocks, make sure that no tx related spinlocks are taken
during the ieee80211_tx_status call.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
We always wait for CMD_CALIBRATION_OP mcu message, but wait argument is used
for do additional MT_MCU_COM_REG0 register operations, which are needed
for mt76x2e devices and we can use appropriate check instead of wait argument.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Remove mt76x2u_init_beacon_offsets routine since the driver supports
just STA mode
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Initialize bss_info_changed mac80211 callback to
mt76x02_bss_info_changed utility routine and remove duplicated code.
Use 8 as WCID index for sta interface
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Perform channel calibration after each channel switch and not only after
connection establishment since NetworkManager perform multiple frequency
scanning if RSSI in lower a given threshold
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Add MCU_CAL_TX_SHAPING calibration in mt76x2u_phy_channel_calibrate
routine since now mt76x2 and mt76x2u driver run the same firmware
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Enable VHT tx rates in ad-hoc mode for mt76x0e driver.
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Add mt76x02_config_mac_addr_list routine in order to set
the mac address list supported by the driver. Initialize
wiphy->addresses/n_addresses for mt76x0e driver
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Fix IBI_R11 configuration on non-radar channels for mt76x0e
driver. This patch improve system stability under heavy load.
Moreover use IBI_R11 name and remove magic numbers for
0x212c register
Fixes: 0c3b3abc9251 ("mt76x0: pci: add DFS support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Assure that after we initialize dev->cal.low_gain to -1 this
will cause update gain calibration. Otherwise this might or
might not happen depending on value of second bit of low_gain
and values read from registers in mt76x02_phy_adjust_vga_gain().
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
If we are associated and scanning is performed, sw_scan_complete callback
is done after we get back to operating channel, so we do not perform
queue cal work. Fix this queue cal work from sw_scan_complete().
On mt76x0 we have to restore gain in MT_BBP(AGC, 8) register after
scanning, as it was multiple times modified by channel switch code.
So queue cal work without any delay to set AGC gain value.
Similar like in mt76x2 init AGC gain only when set operating channel
and just check before queuing cal work in sw_scan_complete() if
initialization was already done.
Fixes: bbd10586f0 ("mt76x0: phy: do not run calibration during channel switch")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Remove wait argument from mt76x02_mcu_set_radio_state and newer wait
for response when sending CMD_POWER_SAVING_OP mcu command.
Note this change behaviour for PCIe devices, but the change is in
align with vendor driver.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Remove wait argument from mt76x02_mcu_function_select and wait for
response when function is not Q_SELECT, what is the same behaviour
like in vendor driver.
Note this change behaviour for PCIe devices for Q_SELECT function
form wait to no-wait, and for mt76x0u BW_SETTING from no-wait to wait.
But the change is in align with vendor driver.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
We almost always use patter like this:
skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
return mt76_mcu_send_msg(dev, skb, CMD_FUN_SET_OP, wait_resp);
This is not needed, we can allocate skb in mcu_send_msg routine.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
We use always 1 as band parameter for MCU_CAL_LC, this break 2GHz,
we should use 0 for this band instead.
Patch fixes problems happened sometimes when try to associate with 2GHz
AP and manifest by errors like below:
[14680.920823] wlan0: authenticate with 18:31:bf:c0:51:b0
[14681.109506] wlan0: send auth to 18:31:bf:c0:51:b0 (try 1/3)
[14681.310454] wlan0: send auth to 18:31:bf:c0:51:b0 (try 2/3)
[14681.518469] wlan0: send auth to 18:31:bf:c0:51:b0 (try 3/3)
[14681.726499] wlan0: authentication with 18:31:bf:c0:51:b0 timed out
Fixes: 9aec146d0f ("mt76x0: pci: introduce mt76x0_phy_calirate routine")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Use tssi calibrated value to configure tx power gain if tssi is enabled
in eeprom data
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Run mt76x0 tssi calibration process if enabled in eeprom data.
Perform calibration procedure every 4s
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Move mt76x02_eeprom_copy utility routine in mt76x02-lib module
in order to be reused by mt76x0 driver adding tssi calibration
support
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Use mt76x02_mac_wcid_setup and mt76x02_mac_shared_key_setup for
shared keys and wcid table initialization and remove duplicated
code
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Remove MT_TSO_CTRL and MT_HEADER_TRANS_CTRL_REG initialization since
it is already done in mt76_write_mac_initvals routine
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Use mt76x02_mac_wcid_setup utility routine for wcid init configuration
and remove duplicated code. This patch fixes a mt76x0 AP issue since
hw key table selection was set to pairwise by default
Fixes: dbad2adcb2c7 ("mt76x0: pci: enable AP support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Move WCID tx rate configuration at device bootstrap since
the related register are always set to 0
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Use mt76x02_mac_shared_key_setup utility routine for shared key
initialization and remove duplicated code
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Use mt76_poll_msec utility routine for CORE_R34 register polling
instead of mt76_poll in order to allow the hw to complete requested
calibration since on slow devices (e.g. mt7620 based boards) calibration
takes longer than 2ms
Fixes: 66a34c66e0 ("mt76x0: phy: add phy/vco temperature compensation")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
MT_BBP(AGC, 8) register has values depend on band in
mt76x0_bbp_switch_tab, so we should not overwrite other fields
than MT_BBP_AGC_GAIN when setting gain.
This can fix performance issues when connecting to 2.4GHz AP.
Fixes: 4636a2544c ("mt76x0: phy: align channel gain logic to mt76x2 one")
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
MT76x2/MT76x0 has somewhat unreliable tx status reporting, and for that
reason the driver currently does not report per-skb tx ack status at all.
This breaks things like client idle polling, which relies on the tx ack
status of a transmitted nullfunc frame.
This patch adds code to report skb-attached tx status if requested by
mac80211 or the rate control module. Since tx status is polled from a
simple FIFO register, the code needs to account for the possibility of
tx status events getting lost.
The code keeps a list of skbs for which tx status is required and passes
them to mac80211 once tx status has been filled in and the DMA queue is
done with it.
If a tx status event is not received after one second, the status rates
are cleared, and a succesful ACK is indicated to avoid spurious disassoc
during assoc or client polling.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
control->sta is set to NULL early when encryption is turned on for the
station and info->control.hw_key is not set.
This code is missing a check for the 802.11 header protected flag, otherwise
it resets the station for other frames, e.g. client probing frames.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Fixes a crash that could occur if a frame is sent to a station, but the
station's wcid was not used (e.g. for software encrypted mgmt tx)
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Introduce dfs support in mt76x0e driver and unlock radar channels
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Move mt76x2 DFS support in mt76x02-lib module in order to
be reused by mt76x0 driver and unlock DFS frequencies
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Unify drv_bss_info_changed mac80211 callback and remove duplicated
code in mt76x0 and mt76x2 drivers
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Move mt76x02_set_rts_threshold and mt76x02_mac_set_tx_protection
routines in mt76x02-lib module and remove duplicated code in mt76x0
and mt76x2 drivers. Remove pci_mac.c and mt76x0/mac.c since now are
empty files
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Move mt76x02_set_tx_ackto and mt76x02_set_coverage_class routines
in mt76x02-lib module in order to be reused by mt76x0 driver.
This is a preliminary patch to unify drv_bss_info_changed mac80211
callback between mt76x0 and mt76x2 drivers
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Add missing mac80211 callbacks to mt76x0e_ops data structure
and add mt76x02_beacon utility routines in mt76x0_bss_info_changed
in order to enable/disable beacon transmission
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
