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
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: 6cd4fa5ab6 ("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
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
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
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: 8e84c25821 ("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: 3e977c5c52 ("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
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: dad0d04fa7 ("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: 314538041b ("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: 716b840c76 ("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
pdev_id in structure 'wmi_pdev_bss_chan_info_event' is wrongly placed
at the beginning. This causes invalid values in survey dump. Hence, align
the structure with the firmware.
Note: The firmware releases follow this order since the feature was
implemented. Also, it is not changing across the branches including
QCA6390.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.1.0.1-01228-QCAHKSWPL_SILICONZ-1
Signed-off-by: Ritesh Singh <ritesi@codeaurora.org>
Signed-off-by: Seevalamuthu Mariappan <seevalam@codeaurora.org>
Signed-off-by: Jouni Malinen <jouni@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210720214922.118078-3-jouni@codeaurora.org
In 4addr, AP wired backbone to STA wired backbone ping fails due to ARP
request not getting answered. Here 4addr ARP multicast packet is sent in
3addr, so that 4addr STA not honouring the 3addr ARP multicast packet.
Fix this issue by sending out multicast packet in 4addr format, firmware
expects peer meta flag instead of vdev meta flag in Tx descriptor.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.4.0.1-01641-QCAHKSWPL_SILICONZ-1
Signed-off-by: Karthikeyan Periyasamy <periyasa@codeaurora.org>
Signed-off-by: Jouni Malinen <jouni@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210720213147.90042-2-jouni@codeaurora.org
Ath11k FW requires peer parameter WMI_PEER_USE_4ADDR to be set for
4-addr peers allowing 4-address frame transmission to those peers.
Add ath11k driver callback for sta_set_4addr() to queue new workq
set_4addr_wk only once based on new boolean, use_4addr_set.
sta_set_4addr() will be called during 4-addr STA association cases
applicable for both AP and STA modes.
In ath11k_sta_set_4addr_wk(),
AP mode:
WMI_PEER_USE_4ADDR will be set for the corresponding
associated 4-addr STA(s)
STA mode:
WMI_PEER_USE_4ADDR will be set for the AP to which the
4-addr STA got associated.
Tested-on: IPQ8074 WLAN.HK.2.1.0.1-01238-QCAHKSWPL_SILICONZ-1
Signed-off-by: Sathishkumar Muruganandam <murugana@codeaurora.org>
Signed-off-by: Jouni Malinen <jouni@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210720213147.90042-1-jouni@codeaurora.org
extends the owl loader to fetch important pci initialization
values - which are stored together with the calibration data -
through the nvmem subsystem.
This allows for much faster WIFI/ath9k initializations on devices
that do not require to perform any post-processing (like XOR'ing/
reversal or unpacking)... than the current way through the
firmware_request which involves the filesystem/userspace.
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/bc79ba1c6f6435000577bf1e5f4d7ebe18a8df97.1630157099.git.chunkeey@gmail.com
On most embedded ath9k devices (like range extenders,
routers, accesspoints, ...) the calibration data is
stored in a MTD partitions named "ART", or "caldata"/
"calibration".
Since commit 4b361cfa86 ("mtd: core: add OTP nvmem provider support"):
All MTD partitions are all automatically available through
the nvmem subsystem.
This feature - together with an nvmem cell definition either
in the platform data or via device-tree allows drivers to get
the data necessary for initializing the WIFI, without having
to wait around for the filesystem and userspace to do
the extractions.
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/f9b732b50a3453fadf3923cc75d365bae3505fe7.1630157099.git.chunkeey@gmail.com
Pull networking fixes and stragglers from Jakub Kicinski:
"Networking stragglers and fixes, including changes from netfilter,
wireless and can.
Current release - regressions:
- qrtr: revert check in qrtr_endpoint_post(), fixes audio and wifi
- ip_gre: validate csum_start only on pull
- bnxt_en: fix 64-bit doorbell operation on 32-bit kernels
- ionic: fix double use of queue-lock, fix a sleeping in atomic
- can: c_can: fix null-ptr-deref on ioctl()
- cs89x0: disable compile testing on powerpc
Current release - new code bugs:
- bridge: mcast: fix vlan port router deadlock, consistently disable
BH
Previous releases - regressions:
- dsa: tag_rtl4_a: fix egress tags, only port 0 was working
- mptcp: fix possible divide by zero
- netfilter: nft_ct: protect nft_ct_pcpu_template_refcnt with mutex
- netfilter: socket: icmp6: fix use-after-scope
- stmmac: fix MAC not working when system resume back with WoL active
Previous releases - always broken:
- ip/ip6_gre: use the same logic as SIT interfaces when computing
v6LL address
- seg6: set fc_nlinfo in nh_create_ipv4, nh_create_ipv6
- mptcp: only send extra TCP acks in eligible socket states
- dsa: lantiq_gswip: fix maximum frame length
- stmmac: fix overall budget calculation for rxtx_napi
- bnxt_en: fix firmware version reporting via devlink
- renesas: sh_eth: add missing barrier to fix freeing wrong tx
descriptor
Stragglers:
- netfilter: conntrack: switch to siphash
- netfilter: refuse insertion if chain has grown too large
- ncsi: add get MAC address command to get Intel i210 MAC address"
* tag 'net-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (76 commits)
ieee802154: Remove redundant initialization of variable ret
net: stmmac: fix MAC not working when system resume back with WoL active
net: phylink: add suspend/resume support
net: renesas: sh_eth: Fix freeing wrong tx descriptor
bonding: 3ad: pass parameter bond_params by reference
cxgb3: fix oops on module removal
can: c_can: fix null-ptr-deref on ioctl()
can: rcar_canfd: add __maybe_unused annotation to silence warning
net: wwan: iosm: Unify IO accessors used in the driver
net: wwan: iosm: Replace io.*64_lo_hi() with regular accessors
net: qcom/emac: Replace strlcpy with strscpy
ip6_gre: Revert "ip6_gre: add validation for csum_start"
net: hns3: make hclgevf_cmd_caps_bit_map0 and hclge_cmd_caps_bit_map0 static
selftests/bpf: Test XDP bonding nest and unwind
bonding: Fix negative jump label count on nested bonding
MAINTAINERS: add VM SOCKETS (AF_VSOCK) entry
stmmac: dwmac-loongson:Fix missing return value
iwlwifi: fix printk format warnings in uefi.c
net: create netdev->dev_addr assignment helpers
bnxt_en: Fix possible unintended driver initiated error recovery
...
The variable 'package_size' is an unsigned long, and should be printed
out using '%lu', not '%zd' (that would be for a size_t).
Yes, on many architectures (including x86-64), 'size_t' is in fact the
same type as 'long', but that's a fairly random architecture definition,
and on some platforms 'size_t' is in fact 'int' rather than 'long'.
That is the case on traditional 32-bit x86. Yes, both types are the
exact same 32-bit size, and it would all print out perfectly correctly,
but '%zd' ends up still being wrong.
And we can't make 'package_size' be a 'size_t', because we get the
actual value using efivar_entry_get() that takes a pointer to an
'unsigned long'. So '%lu' it is.
This fixes two of the i386 allmodconfig build warnings (that is now an
error due to -Werror).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The kernel test robot reports printk format warnings in uefi.c, so
correct them.
../drivers/net/wireless/intel/iwlwifi/fw/uefi.c: In function 'iwl_uefi_get_pnvm':
../drivers/net/wireless/intel/iwlwifi/fw/uefi.c:52:30: warning: format '%zd' expects argument of type 'signed size_t', but argument 7 has type 'long unsigned int' [-Wformat=]
52 | "PNVM UEFI variable not found %d (len %zd)\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
53 | err, package_size);
| ~~~~~~~~~~~~
| |
| long unsigned int
../drivers/net/wireless/intel/iwlwifi/fw/uefi.c:59:29: warning: format '%zd' expects argument of type 'signed size_t', but argument 6 has type 'long unsigned int' [-Wformat=]
59 | IWL_DEBUG_FW(trans, "Read PNVM from UEFI with size %zd\n", package_size);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~
| |
| long unsigned int
Fixes: 84c3c9952a ("iwlwifi: move UEFI code to a separate file")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: Luca Coelho <luciano.coelho@intel.com>
Cc: linux-wireless@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210821020901.25901-1-rdunlap@infradead.org
Pull Kbuild updates from Masahiro Yamada:
- Add -s option (strict mode) to merge_config.sh to make it fail when
any symbol is redefined.
- Show a warning if a different compiler is used for building external
modules.
- Infer --target from ARCH for CC=clang to let you cross-compile the
kernel without CROSS_COMPILE.
- Make the integrated assembler default (LLVM_IAS=1) for CC=clang.
- Add <linux/stdarg.h> to the kernel source instead of borrowing
<stdarg.h> from the compiler.
- Add Nick Desaulniers as a Kbuild reviewer.
- Drop stale cc-option tests.
- Fix the combination of CONFIG_TRIM_UNUSED_KSYMS and CONFIG_LTO_CLANG
to handle symbols in inline assembly.
- Show a warning if 'FORCE' is missing for if_changed rules.
- Various cleanups
* tag 'kbuild-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild: (39 commits)
kbuild: redo fake deps at include/ksym/*.h
kbuild: clean up objtool_args slightly
modpost: get the *.mod file path more simply
checkkconfigsymbols.py: Fix the '--ignore' option
kbuild: merge vmlinux_link() between ARCH=um and other architectures
kbuild: do not remove 'linux' link in scripts/link-vmlinux.sh
kbuild: merge vmlinux_link() between the ordinary link and Clang LTO
kbuild: remove stale *.symversions
kbuild: remove unused quiet_cmd_update_lto_symversions
gen_compile_commands: extract compiler command from a series of commands
x86: remove cc-option-yn test for -mtune=
arc: replace cc-option-yn uses with cc-option
s390: replace cc-option-yn uses with cc-option
ia64: move core-y in arch/ia64/Makefile to arch/ia64/Kbuild
sparc: move the install rule to arch/sparc/Makefile
security: remove unneeded subdir-$(CONFIG_...)
kbuild: sh: remove unused install script
kbuild: Fix 'no symbols' warning when CONFIG_TRIM_UNUSD_KSYMS=y
kbuild: Switch to 'f' variants of integrated assembler flag
kbuild: Shuffle blank line to improve comment meaning
...
Start supporting API version 66 for AX devices.
Th iwlwifi FW API is frozen every 6 weeks, so we need to bump the
newest version number that the driver supports accordingly. In this
specific case, support for new HW will only be possible with the new
FW version. This change still keeps backwards compatibility with
older FW API versions for existing devices.
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210901101412.300012-1-luca@coelho.fi
Due to a rebase damage, we lost the rtnl_lock() when the patch was
sent out. This causes an RTNL imbalance and failed assertions, due to
missing RTNL protection, for instance:
RTNL: assertion failed at net/wireless/reg.c (4025)
WARNING: CPU: 60 PID: 1720 at net/wireless/reg.c:4025 regulatory_set_wiphy_regd_sync+0x7f/0x90 [cfg80211]
Call Trace:
iwl_mvm_init_mcc+0x170/0x190 [iwlmvm]
iwl_op_mode_mvm_start+0x824/0xa60 [iwlmvm]
iwl_opmode_register+0xd0/0x130 [iwlwifi]
init_module+0x23/0x1000 [iwlmvm]
Fix this by adding the missing rtnl_lock() back to the code.
Fixes: eb09ae93da ("iwlwifi: mvm: load regdomain at INIT stage")
Link: https://lore.kernel.org/lkml/CAHk-=wjB_zBwZ+WR9LOpvgjvaQn=cqryoKigod8QnZs=iYGEhA@mail.gmail.com/
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
