Up until now we never needed to keep a networking locks around
representors accesses, we only accessed them when device was
reconfigured (under nfp pf->lock) or on fast path (under RCU).
Now we want to be able to iterate over all representors during
notifications, so make sure representor assignment is done
under RTNL lock.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Our representors are software devices built on top of the PF
vNIC, the queuing should only happen at the vNIC netdevice.
Allow representors to run qdisc-less.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Our representors are software devices built on top of the PF
vNIC, the only state they have are per-cpu stats, so make
the TX run locklessly.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for TSO over representors make sure the port id
prepend will always fit in the frame. The current max header
length is 255, which is ample, so assume worst case scenario
of 8 byte prepend and save ourselves the conditionals.
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>
The TSO-related offsets in the descriptor should not include
the length of the prepended metadata. Adjust them. Note that
this could not have caused issues in the past as we don't
support TSO with metadata prepend as of this patch.
Signed-off-by: Michael Rapson <michael.rapson@netronome.com>
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>
nd_q is only used at the very end of nfp_net_tx(), there is no need
to initialize it early.
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>
Move temporary variables in scope of the loop in nfp_net_tx_complete(),
and add a temp for txbuf software structure. This saves us 0.2% of CPU.
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>
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>
Most linux hosts never setup TCP MD5 keys. We can avoid a
cache line miss (accessing tp->md5ig_info) on RX and TX
using a jump label.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet says:
====================
tcp: take a bit more care of backlog stress
While working on the SACK compression issue Jean-Louis Dupond
reported, we found that his linux box was suffering very hard
from tail drops on the socket backlog queue.
First patch hints the compiler about sack flows being the norm.
Second patch changes non-sack code in preparation of the ack
compression.
Third patch fixes tcp_space() to take backlog into account.
Fourth patch is attempting coalescing when a new packet must
be added to the backlog queue. Cooking bigger skbs helps
to keep backlog list smaller and speeds its handling when
user thread finally releases the socket lock.
v3: Neal/Yuchung feedback addressed :
Do not aggregate if any skb has URG bit set.
Do not aggregate if the skbs have different ECE/CWR bits
v2: added feedback from Neal : tcp: take care of compressed acks in tcp_add_reno_sack()
added : tcp: hint compiler about sack flows
added : tcp: make tcp_space() aware of socket backlog
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In case GRO is not as efficient as it should be or disabled,
we might have a user thread trapped in __release_sock() while
softirq handler flood packets up to the point we have to drop.
This patch balances work done from user thread and softirq,
to give more chances to __release_sock() to complete its work
before new packets are added the the backlog.
This also helps if we receive many ACK packets, since GRO
does not aggregate them.
This patch brings ~60% throughput increase on a receiver
without GRO, but the spectacular gain is really on
1000x release_sock() latency reduction I have measured.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jean-Louis Dupond reported poor iscsi TCP receive performance
that we tracked to backlog drops.
Apparently we fail to send window updates reflecting the
fact that we are under stress.
Note that we might lack a proper window increase when
backlog is fully processed, since __release_sock() clears
sk->sk_backlog.len _after_ all skbs have been processed.
This should not matter in practice. If we had a significant
load through socket backlog, we are in a dangerous
situation.
Reported-by: Jean-Louis Dupond <jean-louis@dupond.be>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Tested-by: Jean-Louis Dupond<jean-louis@dupond.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
Neal pointed out that non sack flows might suffer from ACK compression
added in the following patch ("tcp: implement coalescing on backlog queue")
Instead of tweaking tcp_add_backlog() we can take into
account how many ACK were coalesced, this information
will be available in skb_shinfo(skb)->gso_segs
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tell the compiler that most TCP flows are using SACK these days.
There is no need to add the unlikely() clause in tcp_is_reno(),
the compiler is able to infer it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Trace events are already present for the receive entry points, to indicate
how the reception entered the stack.
This patch adds the corresponding exit trace events that will bound the
reception such that all events occurring between the entry and the exit
can be considered as part of the reception context. This greatly helps
for dependency and root cause analyses.
Without this, it is not possible with tracepoint instrumentation to
determine whether a sched_wakeup event following a netif_receive_skb
event is the result of the packet reception or a simple coincidence after
further processing by the thread. It is possible using other mechanisms
like kretprobes, but considering the "entry" points are already present,
it would be good to add the matching exit events.
In addition to linking packets with wakeups, the entry/exit event pair
can also be used to perform network stack latency analyses.
Signed-off-by: Geneviève Bastien <gbastien@versatic.net>
CC: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: David S. Miller <davem@davemloft.net>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> (tracing side)
Signed-off-by: David S. Miller <davem@davemloft.net>
There are no such structs flow_dissector_key_flow_vlan or
flow_dissector_key_flow_tags, the actual structs used are struct
flow_dissector_key_vlan and struct flow_dissector_key_tags. So correct the
comments against FLOW_DISSECTOR_KEY_VLAN, FLOW_DISSECTOR_KEY_FLOW_LABEL and
FLOW_DISSECTOR_KEY_CVLAN to refer to those.
Signed-off-by: Edward Cree <ecree@solarflare.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>
Allows adding unassociated stations from mac80211
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
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>
