| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
During WILC chip wake-up sequence, the clockless status register sometimes
reports failure even when the actual status is successful. So, for the
clockless register, remove the incorrect error status reporting during the
read and write command API's.
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-8-ajay.kathat@microchip.com
|
|
For SPI bus, the register read fails after read/write to the clockless
register during chip wakeup sequence. Add workaround to send CMD_RESET
command during chip wake-up sequence to overcome the issue.
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-7-ajay.kathat@microchip.com
|
|
Add reset/terminate/repeat command for SPI module. In case of SPI commands
failure, the host should issue a RESET command to WILC chip to recover
from any temporary bus error.
For now, the new command support is added and later the SPI read/write
API's would be modified to make use of these commands for retry mechanism
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-6-ajay.kathat@microchip.com
|
|
Use the correct sequence to configure clockless registers for chip wake-up.
The following sequence is expected from WILC chip for wakeup:
- set wakeup bit in wakeup_reg register
- after setting the wakeup bit, read back the clock status bit for wakeup
complete.
For SDIO/SPI modules, the wakeup sequence is the same except uses different
register values so refactored the code to use common function for both
SDIO/SPI bus.
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-5-ajay.kathat@microchip.com
|
|
Add new WID(WID_WOWLAN_TRIGGER) to send wake_enable information to firmware.
In 'set_wakeup' cfg80211_ops callback, the enable information was not
passed to firmware which is required to handle WOWLan trigger notification
from firmware.
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-4-ajay.kathat@microchip.com
|
|
When the BSS reference holds a valid reference, it is not freed. The 'if'
condition is wrong. Instead of the 'if (bss)' check, the 'if (!bss)' check
is used.
The issue is solved by removing the unnecessary 'if' check because
cfg80211_put_bss() already performs the NULL validation.
Fixes: 6cd4fa5ab691 ("staging: wilc1000: make use of cfg80211_inform_bss_frame()")
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-3-ajay.kathat@microchip.com
|
|
Move initialization & deinitialization of 'deinit_lock' mutex lock inside
wlan_init_locks() & wlan_deinit_locks() API's respectively alongside other
locks. After the movement, the client count variable(client_count) which is
used for lock init/deinit is removed.
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916164902.74629-2-ajay.kathat@microchip.com
|
|
The module parameters are missing dev_oper_mode 12, BT classic alone,
add it. Moreover, the parameters encode newlines, which ends up being
printed malformed e.g. by modinfo, so fix that too.
However, the module parameter string is duplicated in both USB and SDIO
modules and the dev_oper_mode mode enumeration in those module parameters
is a duplicate of macros used by the driver. Furthermore, the enumeration
is confusing.
So, deduplicate the module parameter string and use __stringify() to
encode the correct mode enumeration values into the module parameter
string. Finally, replace 'Wi-Fi' with 'Wi-Fi alone' and 'BT' with
'BT classic alone' to clarify what those modes really mean.
Fixes: 898b255339310 ("rsi: add module parameter operating mode")
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Amitkumar Karwar <amit.karwar@redpinesignals.com>
Cc: Angus Ainslie <angus@akkea.ca>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: Karun Eagalapati <karun256@gmail.com>
Cc: Martin Fuzzey <martin.fuzzey@flowbird.group>
Cc: Martin Kepplinger <martink@posteo.de>
Cc: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Cc: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Cc: Siva Rebbagondla <siva8118@gmail.com>
Cc: netdev@vger.kernel.org
Cc: <stable@vger.kernel.org> # 4.17+
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210916144245.10181-1-marex@denx.de
|
|
The BSS priority here for a new P2P_CLIENT device was accidentally set
to an enum that's certainly not meant for this. Since
MWIFIEX_BSS_ROLE_STA is 0 anyway, we can just set the bss_priority to 0
instead here.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-10-verdre@v0yd.nl
|
|
When creating a new virtual interface in mwifiex_add_virtual_intf(), we
update our internal driver states like bss_type, bss_priority, bss_role
and bss_mode to reflect the mode the firmware will be set to.
When switching virtual interface mode using
mwifiex_init_new_priv_params() though, we currently only update bss_mode
and bss_role. In order for the interface mode switch to actually work,
we also need to update bss_type to its proper value, so do that.
This fixes a crash of the firmware (because the driver tries to execute
commands that are invalid in AP mode) when switching from station mode
to AP mode.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-9-verdre@v0yd.nl
|
|
Looks like this case was simply overseen, so handle it, too.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-8-verdre@v0yd.nl
|
|
It's possible to change virtual interface type between P2P_CLIENT and
P2P_GO, the card supports that just fine, and it happens for example
when using miracast with the miraclecast software.
So allow type changes between P2P_CLIENT and P2P_GO and simply call into
mwifiex_change_vif_to_p2p(), which handles this just fine. We have to
call mwifiex_cfg80211_deinit_p2p() before though to make sure the old
p2p mode is properly uninitialized.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-7-verdre@v0yd.nl
|
|
In mwifiex_init_new_priv_params() we update our private driver state to
reflect the currently selected virtual interface type. Most notably we
set the bss_mode to the mode we're going to put the firmware in.
Now after we updated the driver state we actually start talking to the
firmware and instruct it to set up the new mode. Those commands can and
will sometimes fail, in which case we return with an error from
mwifiex_change_vif_to_*. We currently update our virtual interface type
counters after this return, which means the code is never reached when a
firmware error happens and we never update the counters. Since we have
updated our bss_mode earlier though, the counters now no longer reflect
the actual state of the driver.
This will break things on the next virtual interface change, because the
virtual interface type we're switching away from didn't get its counter
incremented, and we end up decrementing a 0-counter.
To fix this, simply update the virtual interface type counters right
after updating our driver structures, so that they are always in sync.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-6-verdre@v0yd.nl
|
|
Use a small helper function to increment and decrement the counter of
the interface types we currently manage. This makes the code that
actually changes and sets up the interface type a bit less messy and
also helps avoiding mistakes in case someone increments/decrements a
counter wrongly.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-5-verdre@v0yd.nl
|
|
We currently handle changing from the P2P to the STATION virtual
interface type slightly different than changing from P2P to ADHOC: When
changing to STATION, we don't send the SET_BSS_MODE command. We do send
that command on all other type-changes though, and it probably makes
sense to send the command since after all we just changed our BSS_MODE.
Looking at prior changes to this part of the code, it seems that this is
simply a leftover from old refactorings.
Since sending the SET_BSS_MODE command is the only difference between
mwifiex_change_vif_to_sta_adhoc() and the current code, we can now use
mwifiex_change_vif_to_sta_adhoc() for both switching to ADHOC and
STATION interface type.
This does not fix any particular bug and just "looked right", so there's
a small chance it might be a regression.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-4-verdre@v0yd.nl
|
|
Instead of bailing out in the function which is supposed to do the type
change, detect invalid changes beforehand using a generic function and
return an error if the change is not allowed.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-3-verdre@v0yd.nl
|
|
Handle the obvious invalid virtual interface type changes with a general
check instead of looking at the individual change.
For type changes from P2P_CLIENT to P2P_GO and the other way round, this
changes the behavior slightly: We now still do nothing, but return
-EOPNOTSUPP instead of 0. Now that behavior was incorrect before and
still is, because type changes between these two types are actually
possible and supported, which we'll fix in a following commit.
Signed-off-by: Jonas Dreßler <verdre@v0yd.nl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210914195909.36035-2-verdre@v0yd.nl
|
|
Current adaptivity mechanism is achieved in driver, by periodically
referencing the IGI value and then updating related registers.
But we find that this way may halt TX activity too long if huge
and temporary energy is detected frequently. So we move the mechanism
to firmware for immediately reacting this case to recover TX rapidly.
Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210830072014.12250-5-pkshih@realtek.com
|
|
Add Energy Detected CCA (EDCCA) mechanism to detect energy on the channel.
And EDCCA support adaptivity mode now. From MIC Ordinance Regulating Radio
Equipment article 49.20, ETSI EN-300-328 and EN-301-893, the device should
be able to dynamically pause TX activity when energy detected on the air.
According to ETSI/JP DFS region, driver will set corresponding threshold
and stop TX activity if the detected energy exceeds the threshold. For now,
we support it on 8822b and 8822c first.
By default, EDCCA mechanism is turned on. For ETSI/JP DFS region, it will
turn to adaptivity mode. However, with adaptivity, if environment is too
noisy, TX may often be halted. So, a debugfs for EDCCA is added. It can
show what EDCCA mode is used currently. And EDCCA mechanism can be turned
on/off through the debugfs while debugging.
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210830072014.12250-4-pkshih@realtek.com
|
|
Realtek chips can program a specific country domain on efuse to
indicate what is the expected rtw_regulatory. For chips with a
programmed country domain, we set REGULATORY_STRICT_REG to tell
stack to consider follow-up regulatory_hint() as the superset of
our regulatory rule. Besides, on driver side, only the request via
NL80211_REGDOM_SET_BY_DRIVER, which matches programmed country
domain, will be handled to keep rtw_regulatory unchanged.
For worldwide roaming chips, i.e. ones without a specific programmed
country domain, system of distro can set expected regulatory via
NL80211_REGDOM_SET_BY_USER. With setting from it, rtw_regulatory
will handle the requests only via NL80211_REGDOM_SET_BY_USER to
follow setting from system of distro. REGULATORY_COUNTRY_IE_IGNORE
will then be set to tell stack to ignore country IE for us. The
restrictions mentioned above will remain until 00, i.e. worldwide,
is set via NL80211_REGDOM_SET_BY_USER.
On the other hand, for worldwide roamin chips, if there is no
specific regulatory set via NL80211_REGDOM_SET_BY_USER, requests
from all regulatory notifications will be handled by rtw_regulatory.
And REGULATORY_COUNTRY_IE_IGNORE won't be set.
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210830072014.12250-3-pkshih@realtek.com
|
|
Mapping table from country code to rtw_regulatory, which manages tx power
limit according to countries, is updated. And mapping architecture is also
upgraded. For more precise control on tx power limit, it allows different
rtw_regulatory for different bands logically. Besides, a helper function
to query rtw_regulatory for current band under current country is provided.
For older chips, some newly added rtw_regulatory may not be configured.
To avoid that those chips have no limit on some countries mapping to a
newer rtw_regulatory after table update, a backward selection mechanism
of rtw_regulatory is introduced. It can help chips use a rtw_regulatory
which has been configured as an alternative of a newer one which is not
configured.
In addition, rtw88 actually doesn't manage channel plans by itself.
Instead, it follows them from stack. So, correct some naming about
chplan with regd, and remove the unnecessary channel control for now.
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210830072014.12250-2-pkshih@realtek.com
|
|
Idle Mode Power Save (IMPS) is a power saving mechanism which when called
by wcn36xx will cause the radio hardware to enter power collapse.
This particular call maps nicely to a simple conjunction/disjunction around
IEEE80211_CONF_CHANGE_IDLE and IEEE80211_CONF_IDLE.
Here we enter idle when we are not associated with an AP. The kernel will
incrementally toggle idle on/off in the process of trying to establish a
connection, thus saving power until we are connected to the AP again, at
which point we give way to BMPS if power_save is on.
We've validated that with IMPS an apq8039 device which has the wcn36xx
module loaded but, has not authenticated with an AP will get to VMIN on
suspend and will not without IMPS.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Tested-by: Benjamin Li <benl@squareup.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210909153320.2624649-1-bryan.odonoghue@linaro.org
|
|
Qcom documents suggest passing of negative values to the dump command,
however currently we convert from string to u32 not s32, so we cannot pass
a two's complement value to the firmware in this way.
There is in fact only one parameter which takes a two's complement value
<tigger threshold> in the antenna diversity switch command.
Downstream:
iwpriv wlan0 dump 71 3 <schedule period> <trigger threshold> <hysteresis value>
Upstream:
echo "71 3 <schedule period> <trigger threshold> <hysteresis value>" > /sys/kernel/debug/ieee80211/phy0/wcn36xx/dump
Fixes: 8e84c2582169 ("wcn36xx: mac80211 driver for Qualcomm WCN3660/WCN3680 hardware")
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210909144428.2564650-3-bryan.odonoghue@linaro.org
|
|
We have been tracking a strange bug with Antenna Diversity Switching (ADS)
on wcn3680b for a while.
ADS is configured like this:
A. Via a firmware configuration table baked into the NV area.
1. Defines if ADS is enabled.
2. Defines which GPIOs are connected to which antenna enable pin.
3. Defines which antenna/GPIO is primary and which is secondary.
B. WCN36XX_CFG_VAL(ANTENNA_DIVERSITY, N)
N is a bitmask of available antenna.
Setting N to 3 indicates a bitmask of enabled antenna (1 | 2).
Obviously then we can set N to 1 or N to 2 to fix to a particular
antenna and disable antenna diversity.
C. WCN36XX_CFG_VAL(ASD_PROBE_INTERVAL, XX)
XX is the number of beacons between each antenna RSSI check.
Setting this value to 50 means, every 50 received beacons, run the
ADS algorithm.
D. WCN36XX_CFG_VAL(ASD_TRIGGER_THRESHOLD, YY)
YY is a two's complement integer which specifies the RSSI decibel
threshold below which ADS will run.
We default to -60db here, meaning a measured RSSI <= -60db will
trigger an ADS probe.
E. WCN36XX_CFG_VAL(ASD_RTT_RSSI_HYST_THRESHOLD, Z)
Z is a hysteresis value, indicating a delta which the RSSI must
exceed for the antenna switch to be valid.
For example if HYST_THRESHOLD == 3 AntennaId1-RSSI == -60db and
AntennaId-2-RSSI == -58db then firmware will not switch antenna.
The threshold needs to be -57db or better to satisfy the criteria.
F. A firmware feature bit also exists ANTENNA_DIVERSITY_SELECTION.
This feature bit is used by the firmware to report if
ANTENNA_DIVERSITY_SELECTION is supported. The host is not required to
toggle this bit to enable or disable ADS.
ADS works like this:
A. Every XX beacons the firmware switches to or remains on the primary
antenna.
B. The firmware then sends a Request-To-Send (RTS) packet to the AP.
C. The firmware waits for a Clear-To-Send (CTS) response from the AP.
D. The firmware then notes the received RSSI on the CTS packet.
E. The firmware then repeats steps A-D on the secondary antenna.
F. Subsequently if the RSSI on the measured antenna is better than
ASD_TRIGGER_THRESHOLD + the active antenna's RSSI then the
measured antenna becomes the active antenna.
G. If RSSI rises past ASD_TRIGGER_THRESHOLD then ADS doesn't run at
all even if there is a substantially better RSSI on the alternative
antenna.
What we have been observing is that the RTS packet is being sent but the
MAC address is a byte-swapped version of the target MAC. The ADS/RTS MAC is
corrupted only when the link is encrypted, if the AP is open the RTS MAC is
correct. Similarly if we configure the firmware to an RTS/CTS sequence for
regular data - the transmitted RTS MAC is correctly formatted.
Internally the wcn36xx firmware uses the indexes in the SMD commands to
populate and extract data from specific entries in an STA lookup table. The
AP's MAC appears a number of times in different indexes within this lookup
table, so the MAC address extracted for the data-transmit RTS and the MAC
address extracted for the ADS/RTS packet are not the same STA table index.
Our analysis indicates the relevant firmware STA table index is
"bssSelfStaIdx".
There is an STA populate function responsible for formatting the MAC
address of the bssSelfStaIdx including byte-swapping the MAC address.
Its clear then that the required STA populate command did not run for
bssSelfStaIdx.
So taking a look at the sequence of SMD commands sent to the firmware we
see the following downstream when moving from an unencrypted to encrypted
BSS setup.
- WLAN_HAL_CONFIG_BSS_REQ
- WLAN_HAL_CONFIG_STA_REQ
- WLAN_HAL_SET_STAKEY_REQ
Upstream in wcn36xx we have
- WLAN_HAL_CONFIG_BSS_REQ
- WLAN_HAL_SET_STAKEY_REQ
The solution then is to add the missing WLAN_HAL_CONFIG_STA_REQ between
WLAN_HAL_CONFIG_BSS_REQ and WLAN_HAL_SET_STAKEY_REQ.
No surprise WLAN_HAL_CONFIG_STA_REQ is the routine responsible for
populating the STA lookup table in the firmware and once done the MAC sent
by the ADS routine is in the correct byte-order.
This bug is apparent with ADS but it is also the case that any other
firmware routine that depends on the "bssSelfStaIdx" would retrieve
malformed data on an encrypted link.
Fixes: 3e977c5c523d ("wcn36xx: Define wcn3680 specific firmware parameters")
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Tested-by: Benjamin Li <benl@squareup.com>
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210909144428.2564650-2-bryan.odonoghue@linaro.org
|
|
Firmware sends delete_sta_context_ind when it detects the AP has gone
away in STA mode. Right now the handler for that indication only handles
AP mode; fix it to also handle STA mode.
Cc: stable@vger.kernel.org
Signed-off-by: Benjamin Li <benl@squareup.com>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210901180606.11686-1-benl@squareup.com
|
|
The Linux device model permits both the ->shutdown and ->remove driver
methods to get called during a shutdown procedure. Example: a DSA switch
which sits on an SPI bus, and the SPI bus driver calls this on its
->shutdown method:
spi_unregister_controller
-> device_for_each_child(&ctlr->dev, NULL, __unregister);
-> spi_unregister_device(to_spi_device(dev));
-> device_del(&spi->dev);
So this is a simple pattern which can theoretically appear on any bus,
although the only other buses on which I've been able to find it are
I2C:
i2c_del_adapter
-> device_for_each_child(&adap->dev, NULL, __unregister_client);
-> i2c_unregister_device(client);
-> device_unregister(&client->dev);
The implication of this pattern is that devices on these buses can be
unregistered after having been shut down. The drivers for these devices
might choose to return early either from ->remove or ->shutdown if the
other callback has already run once, and they might choose that the
->shutdown method should only perform a subset of the teardown done by
->remove (to avoid unnecessary delays when rebooting).
So in other words, the device driver may choose on ->remove to not
do anything (therefore to not unregister an MDIO bus it has registered
on ->probe), because this ->remove is actually triggered by the
device_shutdown path, and its ->shutdown method has already run and done
the minimally required cleanup.
This used to be fine until the blamed commit, but now, the following
BUG_ON triggers:
void mdiobus_free(struct mii_bus *bus)
{
/* For compatibility with error handling in drivers. */
if (bus->state == MDIOBUS_ALLOCATED) {
kfree(bus);
return;
}
BUG_ON(bus->state != MDIOBUS_UNREGISTERED);
bus->state = MDIOBUS_RELEASED;
put_device(&bus->dev);
}
In other words, there is an attempt to free an MDIO bus which was not
unregistered. The attempt to free it comes from the devres release
callbacks of the SPI device, which are executed after the device is
unregistered.
I'm not saying that the fact that MDIO buses allocated using devres
would automatically get unregistered wasn't strange. I'm just saying
that the commit didn't care about auditing existing call paths in the
kernel, and now, the following code sequences are potentially buggy:
(a) devm_mdiobus_alloc followed by plain mdiobus_register, for a device
located on a bus that unregisters its children on shutdown. After
the blamed patch, either both the alloc and the register should use
devres, or none should.
(b) devm_mdiobus_alloc followed by plain mdiobus_register, and then no
mdiobus_unregister at all in the remove path. After the blamed
patch, nobody unregisters the MDIO bus anymore, so this is even more
buggy than the previous case which needs a specific bus
configuration to be seen, this one is an unconditional bug.
In this case, the Realtek drivers fall under category (b). To solve it,
we can register the MDIO bus under devres too, which restores the
previous behavior.
Fixes: ac3a68d56651 ("net: phy: don't abuse devres in devm_mdiobus_register()")
Reported-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Reported-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When interfacing with a Broadcom PHY, request the auto-power down, DLL
disable and IDDQ-SR modes to be enabled.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When interfacing with a Broadcom PHY, request the auto-power down, DLL
disable and IDDQ-SR modes to be enabled.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Since we enable APD and DLL/RXC/TXC disable we need to use
bcm54xx_suspend() in order not to do a read/modify/write of the BMCR
register which is incompatible with the desired settings.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
These two Ethernet PHYs support IDDQ-SR therefore wire-up the suspend
and resume callbacks to point to bcm54xx_suspend() and bcm54xx_resume().
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for putting the PHY into IDDQ Soft Recovery mode by setting
the TOP_MISC register bits accordingly. This requires us to implement a
custom bcm54xx_suspend() routine which diverges from genphy_suspend() in
order to configure the PHY to enter IDDQ with software recovery as well
as avoid doing a read/modify/write on the BMCR register.
Doing a read/modify/write on the BMCR register means that the
auto-negotation bit may remain which interferes with the ability to put
the PHY into IDDQ-SR mode. We do software reset upon suspend in order to
put the PHY back into its state prior to suspend as recommended by the
datasheet.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
An unsupported AKM would end up printing "invalid cipher group". Instead
print "invalid akm suite" with the offending AKM.
Signed-off-by: James Prestwood <prestwoj@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210901190641.255624-1-prestwoj@gmail.com
|
|
P2P client mode was only working the first time.
On subsequent connection attempts the group was successfully created but
no data was sent (no transmitted data packets were seen with a sniffer).
The reason for this was that the hardware was being configured in fixed
rate mode with rate RSI_RATE_1 (1Mbps) which is not valid in the 5GHz band.
In P2P mode wpa_supplicant uses NL80211_CMD_SET_TX_BITRATE_MASK to disallow
the 11b rates in the 2.4GHz band which updated common->fixedrate_mask.
rsi_set_min_rate() then used the fixedrate_mask to calculate the minimum
allowed rate, or 0xffff = auto if none was found.
However that calculation did not account for the different rate sets
allowed in the different bands leading to the error.
Fixing set_min_rate() would result in 6Mb/s being used all the time
which is not what we want either.
The reason the problem did not occur on the first connection is that
rsi_mac80211_set_rate_mask() only updated the fixedrate_mask for
the *current* band. When it was called that was still 2.4GHz as the
switch is done later. So the when set_min_rate() was subsequently
called after the switch to 5GHz it still had a mask of zero, leading
to defaulting to auto mode.
Fix this by differentiating the case of a single rate being
requested, in which case the hardware will be used in fixed rate
mode with just that rate, and multiple rates being requested,
in which case we remain in auto mode but the firmware rate selection
algorithm is configured with a restricted set of rates.
Fixes: dad0d04fa7ba ("rsi: Add RS9113 wireless driver")
Signed-off-by: Martin Fuzzey <martin.fuzzey@flowbird.group>
CC: stable@vger.kernel.org
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1630337206-12410-4-git-send-email-martin.fuzzey@flowbird.group
|
|
My previous patch checked if encryption should be enabled by directly
checking info->control.hw_key (like the downstream driver).
However that missed that the control and driver_info members of
struct ieee80211_tx_info are union fields.
Due to this when rsi_core_xmit() updates fields in "tx_params"
(driver_info) it can overwrite the control.hw_key, causing the result
of the later test to be incorrect.
With the current structure layout the first byte of control.hw_key is
overlayed with the vap_id so, since we only test if control.hw_key is
NULL / non NULL, a non zero vap_id will incorrectly enable encryption.
In basic STA and AP modes the vap_id is always zero so it works but in
P2P client mode a second VIF is created causing vap_id to be non zero
and hence encryption to be enabled before keys have been set.
Fix this by extracting the key presence flag to a new field in the driver
private tx_params structure and populating it first.
Fixes: 314538041b56 ("rsi: fix AP mode with WPA failure due to encrypted EAPOL")
Signed-off-by: Martin Fuzzey <martin.fuzzey@flowbird.group>
CC: stable@vger.kernel.org
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1630337206-12410-3-git-send-email-martin.fuzzey@flowbird.group
|
|
When BT coexistence is enabled (eg oper mode 13, which is the default)
the initialisation on startup sometimes silently fails.
In a normal initialisation we see
usb 1-1.3: Product: Wireless USB Network Module
usb 1-1.3: Manufacturer: Redpine Signals, Inc.
usb 1-1.3: SerialNumber: 000000000001
rsi_91x: rsi_probe: Initialized os intf ops
rsi_91x: rsi_load_9116_firmware: Loading chunk 0
rsi_91x: rsi_load_9116_firmware: Loading chunk 1
rsi_91x: rsi_load_9116_firmware: Loading chunk 2
rsi_91x: Max Stations Allowed = 1
But sometimes the last log is missing and the wlan net device is
not created.
Running a userspace loop that resets the hardware via a GPIO shows the
problem occurring ~5/100 resets.
The problem does not occur in oper mode 1 (wifi only).
Adding logs shows that the initialisation state machine requests a MAC
reset via rsi_send_reset_mac() but the firmware does not reply, leading
to the initialisation sequence being incomplete.
Fix this by delaying attaching the BT adapter until the wifi
initialisation has completed.
With this applied I have done > 300 reset loops with no errors.
Fixes: 716b840c7641 ("rsi: handle BT traffic in driver")
Signed-off-by: Martin Fuzzey <martin.fuzzey@flowbird.group>
CC: stable@vger.kernel.org
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1630337206-12410-2-git-send-email-martin.fuzzey@flowbird.group
|
|
hclge_get_reset_status() should return the tqp reset status.
However, if the CMDQ fails, the caller will take it as tqp reset
success status by mistake. Therefore, uses a parameters to get
the tqp reset status instead.
Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The input parameters may not be reliable, so check the vlan id before
using it, otherwise may set wrong vlan id into hardware.
Fixes: dc8131d846d4 ("net: hns3: Fix for packet loss due wrong filter config in VLAN tbls")
Signed-off-by: liaoguojia <liaoguojia@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The input parameters may not be reliable. Before using the
queue id, we should check this parameter. Otherwise, memory
overwriting may occur.
Fixes: d34100184685 ("net: hns3: refactor the mailbox message between PF and VF")
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
vport_id include PF and VFs, vport_id = 0 means PF, other values mean VFs.
So the actual vf id is equal to vport_id minus 1.
Some VF print logs are actually vport, and logs of vf id actually use
vport id, so this patch fixes them.
Fixes: ac887be5b0fe ("net: hns3: change print level of RAS error log from warning to error")
Fixes: adcf738b804b ("net: hns3: cleanup some print format warning")
Signed-off-by: Jiaran Zhang <zhangjiaran@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The vf id from ethtool is added 1 before configured to driver.
So it's necessary to minus 1 when printing it, in order to
keep consistent with user's configuration.
Fixes: dd74f815dd41 ("net: hns3: Add support for rule add/delete for flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When user change rss 'hfunc' without set rss 'hkey' by ethtool
-X command, the driver will ignore the 'hfunc' for the hkey is
NULL. It's unreasonable. So fix it.
Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Fixes: 374ad291762a ("net: hns3: Add RSS general configuration support for VF")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The smallest TX ring size we support must fit a TX SKB with MAX_SKB_FRAGS
+ 1. Because the first TX BD for a packet is always a long TX BD, we
need an extra TX BD to fit this packet. Define BNXT_MIN_TX_DESC_CNT with
this value to make this more clear. The current code uses a minimum
that is off by 1. Fix it using this constant.
The tx_wake_thresh to determine when to wake up the TX queue is half the
ring size but we must have at least BNXT_MIN_TX_DESC_CNT for the next
packet which may have maximum fragments. So the comparison of the
available TX BDs with tx_wake_thresh should be >= instead of > in the
current code. Otherwise, at the smallest ring size, we will never wake
up the TX queue and will cause TX timeout.
Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadocm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for jumbo frames. Full support for jumbo frames requires
changes in the DSA switch driver (lantiq_gswip.c).
Tested on BT Hone Hub 5A.
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
IOSM Makefile & WWAN Kconfig changes to support fw flashing & cd
collection module compliation.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Implements transport layer protocol for fw flashing/coredump
collection.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Implements protocol for coredump collection.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Implements protocol for fw flashing and PSI injection for
coredump collection.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Register with devlink framework and implment callbacks required
for fw flashing and coredump collection.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Fix spacing and improve name for 83xx phy following other phy in the
same driver.
Signed-off-by: Ansuel Smith <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add resume/suspend function to qca83xx internal phy.
We can't use the at803x generic function as the documentation lacks of
any support for WoL regs.
Signed-off-by: Ansuel Smith <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
Ajay Singh
Marek Vasut
Jonas Dreßler
Chin-Yen Lee
Zong-Zhe Yang
Bryan O'Donoghue
Benjamin Li
Vladimir Oltean
Florian Fainelli
James Prestwood
Martin Fuzzey
Yufeng Mo
liaoguojia
Jiaran Zhang
Jian Shen
Michael Chan
Aleksander Jan Bajkowski
M Chetan Kumar
Ansuel Smith