- 26 Aug, 2021 40 commits
-
-
Johannes Berg authored
In later firmware we haven't needed the TSC anyway since we have it already (and firmware image doesn't change), but the new version adds the ability to send down replay counters for more than one GTK. Implement that. Signed-off-by:
Johannes Berg <johannes.berg@intel.com> Signed-off-by:
Luca Coelho <luciano.coelho@intel.com> Link: https://lore.kernel.org/r/iwlwifi.20210805130823.28cd065e8c4a.Ic8406a78ee46b07e0ca1b8199522ef08ec6eef53@changeidSigned-off-by:
-
Johannes Berg authored
Now that only reprogramming is left in the initial key iteration, skip it entirely on unified firmware images instead of skipping only the command sending inside of it. Signed-off-by:
-
Johannes Berg authored
If we're sending the KEK/KCK data we also need the GTK and IGTK type, add a separate key iteration for that so we can make the configure_key iteration optional later. Signed-off-by:
-
Johannes Berg authored
Refactor the TSC/RSC configuration out from the normal wowlan key iteration so we can replace it later with a different one adapted to a different firmware API. Signed-off-by:
-
Johannes Berg authored
We only ever pass cmd_flags == CMD_ASYNC, so might as well not have the argument. Remove it. Signed-off-by:
-
Johannes Berg authored
We do a key iteration to program the keys, and while at it we also collect the data necessary for TKIP. This code has all kinds of dependencies on the firmware API though, so take out the TKIP phase 1 key generation and do that in a separate key iteration only if necessary. Signed-off-by:
-
Johannes Berg authored
There's no need to differentiate identical default and cipher type cases, nor do we really need to have a 'ret' variable. Signed-off-by:
-
Johannes Berg authored
The new version 3 of the station key API has gotten rid of the strange hole in the sequence counter values, support that. Signed-off-by:
-
Ilan Peer authored
Both 'iwl_scan_probe_params_v3' and 'iwl_scan_probe_params_v4' wrongly addressed the 'bssid_array' field which should supposed to be any array of BSSIDs each of size ETH_ALEN and not the opposite. Fix it. Signed-off-by:
Ilan Peer <ilan.peer@intel.com> Signed-off-by:
-
Johannes Berg authored
Bz device reset flow changed, now the hardware (instead of firmware) will reset the PCI bus etc., this can take up to 100ms. Signed-off-by:
-
Johannes Berg authored
The method to NMI the firmware also changed in Bz devices, implement the new logic. Signed-off-by:
-
Johannes Berg authored
Device startup changed in Bz, some register bits moved around. Change the code accordingly. The new Bz hardware changes also the way we wake it (grab NIC access) and the way we disable bus mastering, update the driver code accordingly. Signed-off-by:
-
Johannes Berg authored
On Bz devices, the MAC address CSRs changed from 0x380 to 0x30. Change the boolean configuration "mac_addr_from_csr" to hold the base address instead, and set it correctly for the different devices using this feature. Signed-off-by:
-
Johannes Berg authored
The real name isn't determined yet, but give them a new name that isn't clashing with older devices. Signed-off-by:
-
Johannes Berg authored
These devices have some places with different behaviour required, so split them off into their own family as they should be. Signed-off-by:
-
Mukesh Sisodiya authored
With recent changes in the firmware SRAM debug during D3 is enabled by default and need not be enabled by driver. cleaning the code to align the same. Signed-off-by:
Mukesh Sisodiya <mukesh.sisodiya@intel.com> Signed-off-by:
-
Johannes Berg authored
There's no need for all the complicated conditions here, any bufferable MMPDUs or MMPDUs for client interfaces are already coming through the TXQ interface, not iwl_mvm_mac_tx(). Simplify the logic. Signed-off-by:
-
Johannes Berg authored
Since switching to mac80211 TXQs, we no longer need to advertise more hardware queues than ACs, since we don't even set QUEUE_CONTROL anyway, so the vif->hw_queue[] mapping array won't be used. All we need (at least for now) is for hw->queues to indicate that we have enough queues to handle QoS. Signed-off-by:
-
Johannes Berg authored
When TVQM is enabled (iwl_mvm_has_new_tx_api() is true), then queue numbers are just sequentially assigned 0, 1, 2, ... Prior to TVQM, in DQA, there were some statically allocated queue numbers: * IWL_MVM_DQA_AUX_QUEUE == 1, * both IWL_MVM_DQA_INJECT_MONITOR_QUEUE and IWL_MVM_DQA_P2P_DEVICE_QUEUE == 2, and * IWL_MVM_DQA_AP_PROBE_RESP_QUEUE == 9. Now, these values are assigned to the members mvm->aux_queue, mvm->snif_queue, mvm->probe_queue and mvm->p2p_dev_queue by default. Normally, this doesn't really matter, and if TVQM is in fact available we override them to the real values after allocating a queue for use there. However, this allocation doesn't always happen. For example, for mvm->p2p_dev_queue (== 2) it only happens when the P2P Device interface is started, if any. If it's not started, the value in mvm->p2p_dev_queue remains 2. This wouldn't really matter all that much if it weren't for iwl_mvm_is_static_queue() which checks a queue number against one of those four static numbers. Now, if no P2P Device or monitor interface is added then queue 2 may be dynamically allocated, yet alias mvm->p2p_dev_queue or mvm->snif_queue, and thus iwl_mvm_is_static_queue() erroneously returns true for it. If it then gets full, all interface queues are stopped, instead of just backpressuring against the one TXQ that's really the only affected one. This clearly can lead to issues, as everything is stopped even if just a single TXQ filled its corresponding HW queue, if it happens to have an appropriate number (2 or 9, AUX is always reassigned.) Due to a mac80211 bug, this also led to a situation in which the queues remained stopped across a deauthentication and then attempts to connect to a new AP started failing, but that's fixed separately. Fix all of this by simply initializing the queue numbers to the invalid value until they're used, if TVQM is enabled, and also setting them back to that value when the queues are later freed again. Signed-off-by:
-
Zheng Yongjun authored
mutex lock can be initialized automatically with DEFINE_MUTEX() rather than explicitly calling mutex_init(). Signed-off-by:
Zheng Yongjun <zhengyongjun3@huawei.com> Signed-off-by:
-
Tom Rix authored
The macro use will already have a semicolon. Signed-off-by:
Tom Rix <trix@redhat.com> Signed-off-by:
-
Zhang Qilong authored
If beacon_inject_active is true, we will return without freeing beacon. Fid that by freeing it before returning. Signed-off-by:
Zhang Qilong <zhangqilong3@huawei.com> [reworded the commit message] Signed-off-by:
-
Wei Yongjun authored
GCC reports warning as follows: drivers/net/wireless/intel/iwlwifi/mvm/rfi.c:14:1: warning: 'static' is not at beginning of declaration [-Wold-style-declaration] 14 | const static struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = { | ^~~~~ Move static to the beginning of declaration. Fixes: 21254908 ("iwlwifi: mvm: add RFI-M support") Reported-by:Hulk Robot <hulkci@huawei.com> Signed-off-by:
Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by:
-
Luca Coelho authored
This check is useless, because we would return NULL in that case and none of the callers actually check that the return value was not NULL before accessing it. Signed-off-by:
-
Luca Coelho authored
If we use spaces in the queue names, we get files with spaces in their name in procfs, which is ugly. Remove the spaces. Reported-by:
Joe Perches <joe@perches.com> Signed-off-by:
-
Johannes Berg authored
The firmware SMPS request should only be honoured if the connection is currently with HE and on 160 MHz, so check that and then potentially reapply any request if the BW changes. Signed-off-by:
-
Johannes Berg authored
When installing a (new) key, set the replay counter so that after FW restart the firmware has the correct value of the replay counters. This doesn't have a large effect - for frames that reach the driver, it will do a replay check, and when installing a new key, the counter is normally zero to start with (not for GTK though, if joining the BSS for the first time). Since this only affects frames handled entirely by the FW, and that's restricted to a few unicast management frames, the only affect here is for those after a firmware restart. Signed-off-by:
-
Mordechay Goodstein authored
EAPOL failure results in deauthentication with various reasons, not related to AUTH failure specifically, so we just merge AUTH failure with failed to assoc to AP. Signed-off-by:
Mordechay Goodstein <mordechay.goodstein@intel.com> Signed-off-by:
-
Mordechay Goodstein authored
This helps understand why and what debug capabilities are running. Signed-off-by:
-
Ilan Peer authored
Add support for discovery of hidden networks on the 6GHz band, by including the scan request direct SSIDs in the FW scan request command: - In case a short SSID matches one of the direct SSIDs in the scan request command, add the matching SSID in the same offset in the 'direct_ssids' array. - Otherwise, add the SSID in one of the available slots. Additionally, as a preparation to handle hidden APs, refactor iwl_mvm_umac_scan_cfg_channels_v6_6g() the function. Signed-off-by:
-
Ilan Peer authored
The scan request processing populated the direct SSIDs in the FW scan request command also for 6GHz scan, which is not needed and might result in unexpected behavior. Fix the code to add the direct SSIDs only in case the scan is not a 6GHz scan. Signed-off-by:
-
Luca Coelho authored
This value is not a simple incrementing integer, it contains some flags as well, so reading it in hexadecimal is easier. Change the print to do it in hex instead of decimal. Signed-off-by:
-
Johannes Berg authored
If the firmware crashes while we're waiting for the reset handshake then it cannot possibly make progress anymore, and we will just time out the wait. That's pointless, so just stop waiting at that point. Additionally, if it never acknowledges the reset handshake, something went wrong. Dump an error in both of these cases, but we need to do it synchronously here since the device will be turned off. Signed-off-by:
-
Johannes Berg authored
In some cases it may be necessary to synchronously create a firmware error report, add the necessary infrastructure for this. Signed-off-by:
-
Johannes Berg authored
When switching op-modes, or more generally when reconfiguring, we might switch the RB size. In _iwl_pcie_rx_init() we have a comment saying we must free all RBs since we might switch the size, but this is actually too late: the switch has been done and we'll free the buffers with the wrong size. Fix this by always freeing the buffers, if any, at the start of configure, instead of only after the size may have changed. Signed-off-by:
-
Johannes Berg authored
On 64-bit machines, struct iwl_rx_mem_buffer has a lot of padding due to the use of pointers after the small items. Move the list entry before them, and while at it also add documentation for it. Signed-off-by:
-
Johannes Berg authored
If the firmware crashes while we're already shutting down the system, there isn't much we can do since the shutdown process is continuing and we wanted to do that. Don't do a FW restart, with the implied debug collection, in this case. Signed-off-by:
-
Johannes Berg authored
The device is capable of receiving MU-MIMO frames with 8 symbols, enable the bit here that says so. Signed-off-by:
-
Shaul Triebitz authored
If broadcast TWT is supported in the BSS, tell the firmware about it by setting the BROADCAST_TWT_SUPPORTED in the MAC context command. Signed-off-by:
Shaul Triebitz <shaul.triebitz@intel.com> Signed-off-by:
-
Mordechay Goodstein authored
Our HW supersets STBC for HE but never set it in assoc IE, fix it by setting it and enable using it. Signed-off-by:
-
