This is a preliminary patch to support 6GHz band on mt7921 devices.
Tested-by: Deren Wu <[email protected]>
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
This adds the new mib counters from last patch into ethtool
stats.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Add register definitions and read & accumulate them in
the mib polling logic. Note that some registers should not
be read since firmware is already reading them. If driver
reads those, they will be cleared-on-read, and so the firmware
stats will be incorrect.
For these 'do-not-read' stats, add them to the registers definition
so that other developers can be aware of these constraints, but do
not actually read them in the driver.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
These counters are clear-on-read, so we need to accumulate
them in the update_stats poll logic, and read the accumulated
values instead of directly doing register reads when reporting
to debugfs and ethtool stats.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
The tx status callback is not called for every frame, so
those specific counters under-count, but at least they give
some idea of what is going on.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Add tx-mode (ofdma, ht, vht, HE) histogram,
tx-ru-idx histogram, and tx-bandwidth histogram.
Also add tx attempts and tx success counters.
All of this is per-station.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
This exposes some tx-path stats to the ethtool API, so that
ethtool -S wlanX provides some more useful info.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
We should pass the error code to the caller immediately
to avoid the possible infinite retry to release the semaphore.
Fixes: 1c099ab44727 ("mt76: mt7921: add MCU support")
Co-developed-by: YN Chen <[email protected]>
Signed-off-by: YN Chen <[email protected]>
Signed-off-by: Sean Wang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Robustify hardware initialization in the current driver probing flow
to get rid of the device is possibly lost after the machine boot due
to possible firmware abnormal state by trying to recover the failure
with more chances.
Tested-by: Leon Yen <[email protected]>
Tested-by: YN Chen <[email protected]>
Signed-off-by: Sean Wang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Fix possible infinite loop in mt7915_load_patch if
mt7915_mcu_patch_sem_ctrl always returns an error.
Fixes: e57b7901469fc ("mt76: add mac80211 driver for MT7915 PCIe-based chipsets")
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Check all possible errors returned in mt7915_mcu_init routine.
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Remove unused tx rate reporting through mcu tx done event since
now tx status is fully supported
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Report tx rate from tx status packets instead of receiving periodic mcu
event. This improves flexibility, accuracy and AQL performance, and
simplifies code flow for better readability.
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Introduce infrastructure support for tx status reporting
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Similar to mt7915, introduce mt7921_txwi_free to report tx rate to
mac80211. This is a preliminary patch to add proper tx status report.
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Without this change, garbage is seen in the hwmon name and sensors output
for mt7615 is garbled.
Fixes: 109e505ad944 ("mt76: mt7615: add thermal sensor device support")
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Without this change, garbage is seen in the hwmon name and sensors output
for mt7915 is garbled. It appears that the hwmon logic does not make a
copy of the incoming string, but instead just copies a char* and expects
it to never go away.
Fixes: d6938251bb5b ("mt76: mt7915: add thermal sensor device support")
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
The user is allowed to change beacon tx rate (HT/VHT/HE) from hostapd.
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Initialize brightness_set and blink_set callbacks to enable LED support.
The base 0x7c000000 is MCU space so driver can't touch it, and should
map the LED base to 0x18000000 host's view.
Signed-off-by: MeiChia Chiu <[email protected]>
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Money Wang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
napi_schedule() can call __raise_softirq_irqoff(), which can perform softirq
handling, so it must not be called in a pure process context with BH enabled.
Signed-off-by: Felix Fietkau <[email protected]>
Give a proper boottime_ns value for netlink RX to avoid scan
issues with Android.
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
We shouldn't put back the device into fw own state after wifi reset at
driver unbind stage to fix the following error because that is not the
consistent state the current driver bind stage expects.
localhost ~ # echo 0000:01:00.0 > /sys/bus/pci/drivers/mt7921e/unbind
localhost ~ # echo 0000:01:00.0 > /sys/bus/pci/drivers/mt7921e/bind
...
[ 481.172969] mt7921e 0000:01:00.0: ASIC revision: feed0000
[ 482.133547] mt7921e: probe of 0000:01:00.0 failed with error -110
-bash: echo: write error: No such device
Fixes: c1af184ba830 ("mt76: mt7921: fix dma hang in rmmod")
Co-developed-by: YN Chen <[email protected]>
Signed-off-by: YN Chen <[email protected]>
Signed-off-by: Sean Wang <[email protected]>
Tested-by: Chen-Yu Tsai <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
./drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c:172:8-9:WARNING:
return of 0/1 in function 'mt7663_usb_sdio_tx_status_data' with return
type bool
Return statements in functions returning bool should use true/false
instead of 1/0.
Generated by: scripts/coccinelle/misc/boolreturn.cocci
Reported-by: Zeal Robot <[email protected]>
Signed-off-by: jing yangyang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
mt7921 mac work can be idle for a long time due to runtime-pm so
update mib counters dumping phy stats
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
As for 7915 moving mt7921_queue_rx_skb makes it possible to make
some functions in mac.c static
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
basic_rate could be 0 ie. hidden AP. Always pick the lowest rate
for such cases.
Fixes: 75fb2e62d444 (mt76: add mt76_default_basic_rate more devices can rely on)
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
In preparation to enable -Wimplicit-fallthrough for Clang, fix the
following warning by explicitly adding a break statement:
drivers/net/wireless/mediatek/mt76/mt7921/main.c:392:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough]
Link: https://github.com/KSPP/linux/issues/115
Signed-off-by: Gustavo A. R. Silva <[email protected]>
Introduce mcu APIs to configure bss coloring and to report bss coloring
collisions. Add support to report coloring countdown in beacon sent by
the device.
Co-developed-by: Ryder Lee <[email protected]>
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
At 160, this chip can only do 2x2 NSS. Fix the features
accordingly, verified it shows up properly in iw phy foo info
now.
Signed-off-by: Ben Greear <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
WMM index range needs to be split between both PHYs if a second PHY exists.
The condition for that was accidentally written as checking if the vif PHY
is the secondary one
Signed-off-by: Felix Fietkau <[email protected]>
Drop MT_DRV_AMSDU_OFFLOAD after introducing IEEE80211_OFFLOAD_ENCAP_ENABLED
flag in mac80211. Driver now checks vif->offload_flags to know encap offload
status of each interface.
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
1. EIFS has been divided into OFDM/CCK fields after 11ax generation.
2. For 5G/6G SIFS setting, hardware counts extra 6us for OFDM.
Signed-off-by: Ryder Lee <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
According to the firmware usage, OFDM rates should fill out bit 6 - 13
while CCK rates should fill out bit 0 - 3 in legacy field of RA info to
make the rate adaption runs propertly. Otherwise, a unicast frame might be
picking up the unsupported rate to send out.
Fixes: 1c099ab44727 ("mt76: mt7921: add MCU support")
Reported-by: Joshua Emele <[email protected]>
Co-developed-by: YN Chen <[email protected]>
Signed-off-by: YN Chen <[email protected]>
Signed-off-by: Sean Wang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
When reboot system, no power cycles, firmware is already downloaded,
return -EIO will break driver as error:
mt7921e: probe of 0000:03:00.0 failed with error -5
Skip firmware download and continue to probe.
Signed-off-by: Aaron Ma <[email protected]>
Fixes: 1c099ab44727c ("mt76: mt7921: add MCU support")
Signed-off-by: David S. Miller <[email protected]>
Report HE MU/BF radiotap.
That fixed HE MU packets dropped by mac80211 because they are missing the
ieee80211_radiotap_he_mu header.
Fixes: 163f4d22c118d ("mt76: mt7921: add MAC support")
Co-developed-by: Ryder Lee <[email protected]>
Signed-off-by: Ryder Lee <[email protected]>
Co-developed-by: Eric-SY Chang <[email protected]>
Signed-off-by: Eric-SY Chang <[email protected]>
Tested-by: Eric-SY Chang <[email protected]>
Signed-off-by: Sean Wang <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Move mt7615_mcu_set_p2p_oppps routine in mt76_connac_lib module in order
to be reused in mt7921 driver
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Introduce mt76_register_debugfs_fops routine in order to
define per-driver regs file operations and make sure the
device is up before reading or writing its registers
Fixes: 1d8efc741df8 'mt76: mt7921: introduce Runtime PM support'
Fixes: de5ff3c9d1a2 'mt76: mt7615: introduce pm_power_save delayed work'
Signed-off-by: Lorenzo Bianconi <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
